This work continues the review and illustrative application to energy systems of the “Fourth-Order Best-Estimate Results with Reduced Uncertainties Predictive Modeling” (4th-BERRU-PM) methodology. The 4th-BERRU-PM methodology uses the Maximum Entropy (MaxEnt) principle to incorporate fourth-order experimental and computational information, in-cluding fourth (and higher) order sensitivities of computed model responses with respect to model parameters. The 4th-BERRU-PM methodology yields the fourth-order MaxEnt posterior distribution of experimentally measured and computed model responses and parameters, in the combined phase-space of model responses and parameters. The 4th-BERRU-PM methodology encompasses fourth-order sensitivity analysis (SA) and uncertainty quantification (UQ), which were reviewed in the accompanying work (Part 1), as well as fourth-order data assimilation (DA) and model calibration (MC) capabilities, which will be reviewed and illustrated in this work (Part 2). The applicability of the 4th-BERRU-PM methodology to energy systems is illustrated by using the Polyethylene-Reflected Plutonium (acronym: PERP) OECD/NEA reactor physics benchmark, which is modeled using the linear neutron transport Boltzmann equation, involving 21976 im-precisely known parameters. This benchmark is representative of “large-scale computations” such as those involved in the modeling of energy systems. The result (“response”) of interest for the PERP benchmark is the leakage of neutrons through the outer surface of this spherical benchmark, which can be computed numerically and measured experimentally. The impact of the high-order sensitivities of the response with respect to the PERP model parameters is quantified for “high-precision” parameters (2% standard deviations) and “medium-precision” parameters (5% standard deviations). Analyzing the best-estimate results with reduced uncertainties for the 1st- through 4th-order moments (mean values, covariance, skewness, and kurtosis) produced by the 4th-BERRU-PM methodology for the PERP benchmark indicates that, even for systems mod-eled by linear equations (e.g., the PERP benchmark), retaining only first-order sensitivities is insufficient for reliable predictive modeling (including SA, UQ, DA, MC). At least second-order sensitivities should be retained in order to obtain reliable predictions.

Switched model predictive control (S-MPC) and recurrent neural network with long short-term memory (RNN-LSTM) are powerful control methods that have been extensively studied for energy management in microgrids (MGs). These methods are complementary in terms of constraint satisfaction, computational demand, adaptability, and comprehensibility, but typically one method is chosen over the other. The S-MPC method selects optimal models and control strategies dynamically based on the system’s operating mode and performance objectives. On the other hand, integration of auto-regressive (AR) with these powerful control methods improves prediction accuracy and system conditions’ adaptability. This paper compares the two approaches to control and proposes a novel algorithm called Switched Auto-regressive Neural Control (S-ANC) that combines their respective strengths. Using a control formulation equivalent to S-MPC and the same controller model for learning, the results indicate that pure RNN-LSTM cannot provide constraint satisfaction. The novel S-ANC algorithm can satisfy constraints and deliver comparable performance to MPC while enabling continuous learning. Results indicate that S-MPC optimization increases power flows within the MG, resulting in efficient utilization of energy resources. By merging the AR and LSTM, the model’s computational time decreased by nearly 47.2%. Also, this study evaluated our predictive model’s accuracy: (i) R-squared error is 0.951, indicating strong predictive ability, and (ii) mean absolute error (MAE) and mean square error (MSE) values of 0.571 indicate accurate predictions with minimal deviations from actual values.

Deep learning neural networks require an immense amount of computation, especially in the training phase of the network when networks with multiple layers of intermediate neurons need to be built. In this paper, we will focus on the PSO algorithm with the aim of significantly accelerating the DLNN training phase by taking advantage of the GPGPU architecture and the Apache Spark analytics engine for large-scale data processing tasks. PSO is a bio-inspired stochastic optimization method whose goal is to iteratively improve the solution to a (usually complex) problem by attempting to approximate a given objective. However, parallelizing an efficient PSO is not a straightforward process due to the complexity of the computations performed on the swarm of particles and the iterative execution of the algorithm until a solution close to the objective with minimal error is achieved. In the present work, two parallelizations of the PSO algorithm have been implemented , both designed for a distributed execution environment. The synchronous parallel PSO implementation ensures consistency at the cost of potential idle time due to global synchronization, while the asynchronous parallel PSO approach improves execution time by reducing the need for global synchronization, making it more suitable for large datasets and distributed environments such as Apache Spark. Both variants of PSO have been implemented to distribute the computational load supported by this algorithm –due to the costly fitness evaluation and updating of particle positions– across the different Spark cluster executor nodes to effectively achieve coarse-grained parallelism, resulting in a significant performance increase over current sequential variants of PSO.

The main functions of the automated systems rely on the advanced sensors for detection and perception of the environment around the vehicle. Radars and cameras are commonly utilized to detect the potential obstacles and vehicles ahead on the road. Nevertheless, cameras can generate spurious detections in the extreme weather conditions such as fog, rain, dust, snow, dark, and heavy sunlight in the sky. Due to limitations in vertical field view of the radars, single radars are not reliable to detect the height of the targets precisely. In this paper, a triple radar arrangement (long-range, medium-range, and short-range radars) based on sensor fusion technique is proposed to detect objects with different size in level 2 Advanced Driver-Assistance (ADAS) system. The typical objects including truck, pedestrians, and animals are detected in different scenarios. The developed model considered ISO 26262 and ISO/PAS 21448 to reasonably address insufficient robustness and inability of the sensors. The models of sensor and level 2 ADAS systems are developed using MATLAB toolbox and Simulink. Sensor detection performance is determined by running simulations with triple radar setup. Obtained results demonstrate that the proposed approach generates accurate detections of targets in all tested scenarios.

This study focuses on predicting PM2.5 levels at the University of Petroșani by employing advanced machine learning techniques to analyze a dataset that encapsulates a wide array of air pollutants and meteorological factors. Utilizing data from IoT sensors and established environmental monitoring stations, the research leverages Random Forest, Gradient Boosting Machines, and Support Vector Regression models to forecast air quality, emphasizing the complex interplay between various pollutants. The models demonstrate varying degrees of accuracy, with the Random Forest model achieving the highest predictive power, indicated by an R2 score of 0.82764. Our findings highlight the significant impact of specific pollutants such as NO, NO2, and CO on PM2.5 levels, suggesting targeted mitigation strategies could enhance local air quality. Additionally, the study explores the role of temporal dynamics in pollution trends, employing time-series analysis to further refine the predictive accuracy. This research contributes to the field of environmental science by providing a nuanced understanding of air quality fluctuations in a university setting and offering a replicable model for similar environments seeking to reduce airborne pollutants and protect public health.

Patients who survived critical COVID-19 frequently reported post-acute sequelae of COVID-19 (PASC) such as psychosomatic and neurocognitive health problems. The goal of this study was to identify clinical risk factors and other predictors for such long-term consequences in severely ill COVID-19 patients. Adult COVID-19 intensive care unit (ICU) survivors from August 2020 to May 2021 were enrolled. A broad range of clinical, laboratory and chest computed tomography (CT) data was collected during ICU stay. The association between ICU predictors and psychosomatic, respiratory and neurocognitive assessments 12 months after ICU discharge was analyzed using univariate regression analysis. In 17 patients (mean age 58.9 ± 11.4 years), laboratory markers (CRP, lymphocytes, hemoglobin), ICU severity (SOFA, SAPS II, need for mechanical ventilation), complications (ARDS), and lung CT data (ground-glass opacity) were promising predictors of depressive and anxiety symptoms, fatigue, and sleep problems. Recovery of psychosomatic health such as fatigue, depression and anxiety correlated with lower levels of inflammation and high hemoglobin levels. ARDS, mechanical ventilation and worse SOFA and SAPS II scores were further risk factors for depressive and anxiety symptoms. Our study identified novel associations such as pulmonary ground-glass opacity being positively associated with depression, anxiety, fatigue, and insomnia levels.

This paper addresses challenges and solutions in urban development and infrastructure resilience, particularly in the context of Japan's rapidly urbanizing landscape. It explores the integration of smart city concepts to combat land subsidence and liquefaction, phenomena highlighted by the 2011 Great East Japan Earthquake. Using advanced technologies such as smart sensing and predictive analytics through kriging and ensemble learning, the study aims to improve the accuracy of geotechnical investigations and urban planning. By analyzing data from 433 geotechnical surveys in Setagaya, Tokyo, it develops predictive models to accurately determine the depth of bearing layers critical to urban infrastructure. The results demonstrate the superiority of ensemble learning in predicting the depth of bearing layers, with significant implications for smart city development and the sustainability of urban environments. This interdisciplinary approach not only seeks to mitigate risks associated with geological disturbances, but also promotes sustainable urban growth that prioritizes safety and prosperity. Through advanced technology and comprehensive research, the study underscores the potential of smart cities to address urban complexities and ensure a resilient, sustainable future.

The aims of this paper can be traced back to goals number seven, twelve and thirteen introduced by Agenda 2030, namely "affordable and clean energy", “responsible consumption and production” and "climate action”, respectively. This is due to the fact that the present work supports decarbonization processes acting in a direct way on the electricity consumption achieved by plants pertaining to the waste industry; in fact, this study aims at the realization of a machine learning model for predicting the energy consumption achieved by a mechanical biological treatment (MBT) waste plant located in central Italy, given the distribution of the entering waste. This model is implemented in MATLAB. The model can be used to tune the distribution of the entering waste in order to adapt the plant energy consumption to the capability of the energy sources and can serve as a play-ground model for other energy transformation plants. The results of the study, which feed the literature on the application of artificial intelligence to real industrial plants, could be used to determine energy efficiency actions that could be incorporated into Property’s strategic planning.

The prevalence of chronic diseases is dramatically increasing demand for emergency healthcare. Existing systems rely on patients self-identifying symptoms, causing dangerous delays. This study develops an AI and IoT-powered “digital twin” solution to enable continuous real-time monitoring and timely prediction of diverse medical emergencies. A digital twin is a virtual representation of an individual, modeled using multidimensional physiological data from wearable sensors. Machine learning techniques analyze patterns in this data to identify anomalies and predict emergencies like heart attacks or falls. A key contribution is an optimized ensemble algorithm combining gradient boosted trees, neural networks, and other techniques to accurately detect emergency events. Evaluation on a dataset of 9158 samples shows the digital twin identifies key emergencies with over 90% recall, enabling prevention and rapid response. It allows risk stratification and personalized interventions based on early warnings, circumventing over 2 million avoidable emergency room visits annually. This study demonstrates the feasibility of an integrated, predictive, patient-centric emergency response system enabled by digital twin technology.

In recent years, metabolomics has been used as a powerful tool to better understand the physiology of neurodegenerative diseases and identify potential biomarkers for progression. We used targeted and untargeted aqueous, and lipidomic profiles of the metabolome from human cerebrospinal fluid to build multivariate predictive models distinguishing patients with Alzheimer’s disease (AD), Parkinson’s disease (PD), and healthy age-matched controls. We emphasize several statistical challenges associated with metabolomic studies where the number of measured metabolites far exceeds sample size. We found strong separation in the metabolome between PD and controls, as well as between PD and AD, with weaker separation between AD and controls. Consistent with existing literature, we found alanine, kynurenine, tryptophan, and serine to be associated with PD classification against controls, while alanine, creatine, and long chain ceramides were associated with AD classification against controls. We conducted a univariate pathway analysis of untargeted and targeted metabolite profiles and find that vitamin E and urea cycle metabolism pathways are associated with PD, while the aspartate/asparagine and c21-steroid hormone biosynthesis pathways are associated with AD. We also found that the amount of metabolite missingness varied by phenotype, highlighting the importance of examining missing data in future metabolomic studies.

Abstract:Global ship demolition is mostly concentrated in south Asian countries, namely Bangladesh, India, Pakistan and China, since 1990’s, having competitive advantage for their high natural tide, and low environmental and social costs. Due to high social and environmental externalities, stakeholders increase monitoring of the externalities and continue to prescribe improvement towards sustainability, which put pressures on profitability and competitiveness. As a consequence, also seen in the past, a leakage effect may emerge, leading to shift of this activity to a region, with relatively less monitored and less stricter on social and environmental impacts. Unfortunately, the leakage effect is never predicted in shipbreaking in order to understand the level of push compatible in the given socio-economic contexts. In this study, we have attempted to predict the future ship demolition landscape, applying machine learning technique to 34,531 in-service vessels worldwide, larger than 500 gross tonnage (GT), which is run against a learning model based on 3500 demolished vessels from 2014. This study shows that redistribution may occur among the top recycling nations: India may emerge out to be a dominant player in shipbreaking, surpassing Bangladesh by a margin of two-fold, while Pakistan and China are in decreasing trend. In addition, the leakage effect is observed, in that Vietnam is predicted to be the fourth largest ship demolition country, while China and Pakistan recede from the third and fourth place to 6th and 8th. Turkey is predicted to advance from fifth position to third position by vessel count but stays same in term of total GT dismantled. Although it is not clear if any leakage is to be observed in the near future, this study may be a model for future predictive analytics and help stakeholders take evidence-based business decisions.

In this paper, a capacitor microphone system is presented to improve the conversion of mechanical energy to electrical energy using a nonlinear auto regressive moving average-L2 (NARMA-L2) and model predictive control (MPC) controllers for the analysis of the open loop and closed loop system. The open loop system response shows that the output voltage signal need to be improved. The comparison of the closed loop system with the proposed controllers have been analyzed and a promising result have been obtained using Matlab/Simulink.

Modularity is arguably one of the most influential theses guiding research on brain and cognitive function since phrenology. This paper considers the following question: is modularity entailed by recent Bayesian models of brain and cognitive function, especially the predictive processing framework? It starts by considering three of the most well-articulated arguments for the view that modularity and predictive processing work well together. It argues that all three kinds of arguments for modularity come up short, albeit for different reasons. The analysis in this paper, although formulated in the context of predictive processing, speaks to broader issues with how to understand the relationship between functional segregation and integration and the reciprocal architecture of the predictive brain. These conclusions have implications for how to study brain and cognitive function. Specifically, when cognitive neuroscience works within an acyclic Markov decision scheme, adopted by most Bayesian models of brain and cognitive function, it may very well be methodologically misguided. This speaks to an increasing tendency within the cognitive neurosciences to emphasise recurrent and reciprocal neuronal processing captured within newly emerging dynamical causal modelling frameworks. The conclusions also suggest that functional integration is an organising principle of brain and cognitive function.

Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to compute the set of optimal compromises (the Pareto set) between the conflicting objectives. The advances in algorithms and the increasing interest in Pareto optimal solutions have led to a wide range of new applications related to optimal and feedback control which results in new challenges such as expensive models or real-time applicability. Since the Pareto set generally consists of an infinite number of solutions, the computational effort can quickly become challenging which is particularly problematic when the objectives are costly to evaluate or when a solution has to be presented very quickly. This article gives an overview over recent developments in accelerating multiobjective optimal control for complex problems where either PDE constraints are present or where a feedback behavior has to be achieved. In the first case, surrogate models yield significant speed-ups. Besides classical meta-modeling techniques for multiobjective optimization, a promising alternative for control problems is to introduce a surrogate model for the system dynamics. In the case of real-time requirements, various promising model predictive control approaches have been proposed, using either fast online solvers or offline-online decomposition. We also briefly comment on dimension reduction in many-objective optimization problems as another technique for reducing the numerical effort.

Background: Studies have tried to identify predictors of functional markers of keratoconus progression, whereas structural outcomes of collagen cross-linking have not been properly investigated. Objective: find and set up a combination of diagnostic modalities and measurements to reliably reflect CXL efficiency. Material and methods: We retrospectively reviewed the medical histories of 107 KC patients (131 eyes) who underwent CXL in a medical center from January 2018 to December 2022. The dataset included preoperative examinations and follow-up results, which provided a total of 796 observations. The cases of other corneal diseases, repeated CXL, pregnancy, and observations without follow-up examinations were excluded. Results: The study findings revealed a significant drop in the central and corneal thickness during 14.01±9.98 months of observations. Linear and polynomial equations suggested different trends in pachymetry change after CXL. The linear model showed corneal thinning, and according to the polynomials, pachymetry findings return to baseline values two years after CXL. Conclusion: The most reliable prognosis of postoperative corneal thickness is achieved with the models trained on keratometry readings and topography indices. BAD indices are also reliable predictors of the corneal thickness after CXL. A combination of the aforementioned structural parameters and their derivatives can reliably predict CXL efficiency.

Powder bed fusion (PBF) process is a metal additive manufacturing process which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for optimizing a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for optimizing the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters -- i.e., laser specifications -- and mechanical properties and how to achieve parts with high density (> 98%) as well as better ultimate mechanical properties. In this paper, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage of 10.236% that are used to optimize process parameters in accordance with user or manufacturer requirements. These models use support vector regression, random forest regression, and neural network techniques. It is shown that the intelligent selection of process parameters using these models can achieve an optimized density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.

A robust explicit model predictive control (EMPC)-based frequency adaptive grid voltage sensorless control is developed for a grid-connected inverter (GCI) via a linear matrix inequality (LMI) approach under the model parameter uncertainties and non-ideal grid environment. The control scheme is achieved by an enhanced prediction model rather than the conventional prediction model provided by fixed parameters to maintain the quality of grid currents injected into the grid when the model parameters are varied. Furthermore, an LMI-based observer is integrated with the disturbance observer to improve the reference tracking performance and reject disturbances. The proposed observer is employed for the grid frequency adaptive control without need of grid voltage sensors. The proposed current controller and observer employ the LMI scheme to maintain a stable and robust operation of the GCI. The discrete-time frequency response and pole-zero map analyses are used to investigate system stability and robustness against parameter uncertainties. Comprehensive simulation, experimental results and analyses clearly demonstrate the robustness of the proposed control scheme under various adverse test conditions with unexpected grid and system uncertainties.

This paper aims to provide the smart grid research community with an open and accessible general mathematical framework to develop and implement optimal flexibility mechanisms in large-scale network applications. The motivation of this paper is twofold. On the one hand, flexibility mechanisms are currently a hot topic of research, which is aimed to mitigate variation and uncertainty of electricity demand and supply in decentralised grids with a high aggregated share of renewables. On the other hand, a large part of such related research is performed by heuristic methods, which are generally inefficient (such methods do not guarantee optimality) and difficult to extrapolate for different use cases. Alternatively, this paper presents an MPC-based (Model Predictive Control) framework explicitly including a generic flexibility mechanism which is easy to particularise to specific strategies such as Demand Response, Flexible Production and Energy Efficiency Services. The proposed framework is benchmarked with other non-optimal control configurations to better show the advantages it provides. The work of this paper is completed by the implementation of a generic use case which aims to further clarify the use of the framework and thus, to ease its adoption by other researchers in their specific flexibility mechanisms applications.

The life cycle of a microgrid covers all the stages from idea to implementation, exploitation until its end of life, but with a lifespan of around 25 years. Covering them usually requires several software tools, which can make integration of results from different stages very difficult and may imply costs hard to estimate from the beginning of a project. This paper proposes a single platform of four modules developed in Matlab to assist all the processes a microgrid passes during its lifetime. The authors detail the architecture, functions and the development of the platform, either by using existing tools available in Matlab, or by developing new ones and designing new user interfaces linked with scripts based on its complex mathematical libraries. A proof-of-concept for this platform was presented by applying the life-cycle assessment process on a real-case study, a microgrid consisting in a photovoltaic plant, an office building as consumer and energy storage units.

Melanoma is the most aggressive and deadly form of skin cancer, and its incidence has been steadily increasing over the past few decades, particularly in the Caucasian population [1]. Current treatment strategies, the combination of BRAF and MEK inhibitors (BRAF/MEKi) in BRAFV600 mutant melanoma, and immune checkpoint inhibitors (ICI), have changed the clinical evolution of this disease [2]. However, a significant percentage of patients do not benefit from these therapies. Therefore, to improve patient selection, it is imperative to look for novel biomarkers. Immune subsets, particularly the quantification of lymphoid populations, could contribute to the identification of ICI responders. The aim of this review is to thoroughly examine significant published data on this topic in melanoma patients and to evaluate the potential role of lymphoid subsets as prognostic and predictive response biomarkers.

This paper explores the feasibility of applying Bayesian statistical methods to study the distortion patterns induced by carburizing heat treatment. By establishing posterior and predictive distribution models for torsion bar dimensions, we aim to accurately understand and predict the expansion behavior, thus enhancing control over carburizing-induced dimensional changes. Bayesian methods allow for the integration of prior knowledge and real-time data, providing a more comprehensive understanding of the distortion phenomena. This approach not only improves the precision of dimensional predictions but also contributes to optimizing the overall manufacturing process, ensuring that the torsion bars meet the rigorous standards required for high-performance applications in demanding industrial environments.

Attention-Deficit/Hyperactivity Disorder (ADHD) is traditionally conceptualized within a framework emphasizing deficits in attention regulation and executive function. However, emerging evidence from the fields of predictive coding and active inference offers a novel lens through which to understand ADHD not merely as a disorder of attention but as a distinctive mode of neurodevelopmental variation. This article synthesizes current research and theoretical models to propose a redefined understanding of ADHD. By integrating insights from Ryan Smith, Paul B. Badcock, and Karl J. Friston (2020), we explore the premise that individuals with ADHD exhibit unique differences in how their brains generate and update predictions about the environment, leading to the characteristic behavioral patterns observed in ADHD. We argue that ADHD involves a divergence in the brain's predictive models and its ability to minimize prediction error, impacting sensory processing, attention allocation, and motor control. This perspective illuminates the adaptive aspects of ADHD, suggesting that what are often labeled as deficits could also reflect an adaptive fit to certain environmental contexts, underscoring the role of neurodiversity in human evolution. Furthermore, we discuss the implications of this reconceptualization for clinical practice, including diagnosis, treatment, and support for individuals with ADHD, emphasizing approaches that align with their unique neurocognitive profiles. This article calls for a shift in the narrative surrounding ADHD, advocating for a model that appreciates the complexity and adaptiveness of neurodevelopmental diversity.

COVID-19 has substantially influenced healthcare systems, requiring early prognosis for innovative therapies and optimal results, especially in individuals with comorbidities. Healthcare practitioners have used AI systems for investigating, anticipating, and predicting diseases, through means including medication development, clinical trial analysis, and pandemic forecasting. This study proposes the use of AI to predict disease severity in terms of hospital mortality among COVID-19 patients. Methodology: A cross-sectional study was conducted the approval from the Research Ethics Committee of King Abdulaziz University (KAU), Saudi Arabia. The study used sequential sampling approaches to include 50 Real-Time Polymerase Chain Reaction (RT-PCR) positive COVID-19 patients from KAU's coronavirus isolation wards. A pre-designed form was used to collect each patient's demographic information, including age and gender, signs and symptoms, illness severity (mild, moderate, severe), and laboratory findings. Furthermore, the length of the hospital stay and the result, whether the patient recovered or died, were reported. Results: The study involved 50 patients with varying degrees of disease severity, most of whom suffered from fever, fatigue, cough, sore throat, and diarrhoea. Laboratory analysis of COVID-19 patients showed increased white blood cell and platelet counts, with C-reactive protein levels above normal. Elevated LDH levels indicated possible tissue damage, while ferritin levels were elevated. Other enzymes were in the normal range, but bilirubin levels were slightly elevated. Overall, the patient's lab results indicated inflammation and possible blood clot formation. The study evaluated the predictive accuracy for outcomes and mortality of COVID-19 patients based on factors such as CRP, LDH, Ferritin, ALP, Bilirubin, D-dimers, and hospital stay (p-value ≤0.05). The predictive accuracy mortality of patients with COVID-19 using AI showed Hospital stay, D-Dimers ALP, Bilirubin, LDH, CRP, and Ferritin significantly affected hospital mortality. (p ≤ 0.0001). Conclusion: Artificial Intelligence is crucial for identifying early coronavirus infections and monitoring patient conditions. It improves treatment consistency and decision-making via the development of algorithms. AI can track the crisis at various scales, facilitate research, and aid in developing treatment regimens, prevention strategies, and drugs and vaccines. It also aids in monitoring health and facilitating research on the virus.

This study explored factors influencing the adoption of blockchain technology in US educational settings using the UTAUT2 model. Results from 160 IT officers via an online survey and PLS-SEM analysis showed that performance expectancy and social influence significantly predict behavioral intentions towards blockchain adoption, impacting actual utilization. While some factors like effort expectancy, facilitating conditions, hedonic motivation, price value, and habit did not show significant relationships, this research underscores UTAUT2's relevance in blockchain acceptance in education. Future studies should address limitations and explore diverse stakeholder perspectives for strategic implementation approaches.

Background/Purpose: Multimorbidity of malaria, anaemia, and malnutrition (MAMM) is a condition in which an individual cohabits with two or more of these health outcomes and is becoming an emergent public health concern in sub-Saharan African countries. The independent associations of a child’s demographic variables and socioeconomic disparities with a child’s health outcomes have been established in literature. However, the effects of the intersection of these factors on MAMM, while accounting for other covariates have not been studied. Therefore, this study aimed to determine how children’s sex, age and socioeconomic status interact to explain the variations in MAMM among children aged 6-59 months in Nigeria. Methods: Data from the 2018 Nigeria Demographic and Health Survey and the 2018 National Human Development Report (NHDR) were used. The study includes weighted samples of 10,184 children aged 6-59 months in Nigeria. A three-level multilevel mixed effect ordinal logistic regression model such that individual characteristics at level 1 are nested in communities at level 2 and nested in states at level 3 was used. Subsequently, predictive probability charts and average adjusted probability tables were used to interpret the intersectional effects. Five models were created in this scenario. Model 1 is the interaction between the child's sex and wealth status; model 2, child's sex and age; model 3 is between child's age and wealth status; model 4 has the three 2-way interactions of child's sex, age, and household wealth status, and model 5 includes model 4 and the 3-way interactions between a child's sex, age, and wealth quintiles. Results: The prevalence of children with ‘none of the three diseases’ outcomes was 17.3% (1767/10,184), while, 34.4% (3499/10,184) had ‘only one of the diseases’, and 48.3% (4,918/10,184) cohabit with ‘two or more’ of MAMM. However, in the multivariate analyses, model 3 was the best fit compared with other models, so, that the two-way interaction effects of a child's age and wealth status are significant predictors in the model. Children aged 36-47 months living in the poorest households have the probability of 0.11, 0.18, and 0.32 of contracting MAMM above the probability of children of the same age and live in the middle, more prosperous and richest households, respectively, while all other covariates are held constant. Thus, the variation in MAMM over a child's age differs depending on the household wealth quintile. In other words, as the children grow older, variations in MAMM become more evident between the rich and the poor household. Conclusion: Therefore, it is recommended that policies that are geared toward economic redistribution will help bridged the disparities observed in multiple diseases among children aged 6-59 months in Nigeria

This research article aims to examine the factors that influence behavioral intentions using the traffic accident claim system in Indonesia. This research uses the Theory of Planned Behavior, the Model of Technology Acceptance, and the Integrated Theory of Technology Acceptance and Use, as well as using the Structural Equation Modeling-Partial Least Squares. The questionnaire was distributed to 580 respondents from three institutions – police, hospitals, and state-owned insurance companies – using quota sampling techniques. The results showed that TPB, TAM, and UTAUT had a significant influence in encouraging behavioral intentions using the traffic accident claim system. Further, the study found that 21st-century digital skills have a moderate role in the impact of acceptance models, planned behavior, and technology use on behavioral intent. Although the study was conducted in Indonesia and is limited to three institutions, it provides strategic guidance for policymakers to improve the use of traffic accident claim systems and reduce Road Traffic Accidents. Further research is recommended to explore from different angles and focus on service providers/operators of traffic accident claim systems to refine the findings of this study. This study contributes to the literature by investigating the factors that influence behavioral intentions using traffic accident claim systems and has a high degree of accuracy of answers from the point of view of traffic safety officers.

Background: Perioperative treatment is a gold standard in locally advanced gastric cancer or GEJ cancer in western population. Unfortunately, the response rate after neoadjuvant chemotherapy (NAC) remains limited. Moreover, there are currently no biomarkers enabling an individual prediction of therapeutic efficacy. The aim of this study was identification of serum biomarkers of early response to NAC. Methods: We conducted this prospective study in the MSCNRIO, in Warsaw, Poland. A total of 71 patients and 15 healthy volunteers signed informed consent. Complete blood count, blood chemical tests, carcinoembryonic antigen (CEA) carcinoma antigen 125 (CA125), carcinoma an-tigen 19.9 (CA19.9), d-dimer, fibrinogen (F) were measured at baseline and before every cycle. Circulating tumour cells (CTCs) and interleukin-1β (IL-1β), interleukin-6 (IL-6), interleukin-8 (IL-8), interleukin-10 (IL-10) were measured in a pilot group of 40 patients at baseline and before cycle two (C2) and cycle three (C3). Results: Of all the measured parameters, only IL-6 serum level was statistically significant. The IL-6 level before C2 of chemotherapy was significantly decreased in complete pathological re-sponse (pCR) vs non-pCR group (3.71 pg/mL vs 7.63 pg/mL, p=0,004). In all patients with IL-6 levels below 5.0 pg/mL in C2, tumour regression TRG1a/1b according to Becker classification and ypN0 were detected in postoperative histopathological specimens. The IL-6 level before C1 of chemotherapy was significantly elevated in ypN+ vs ypN0 (7.69 pg/mL vs 2.89 pg/mL, p=0.022). Conclusions: The trial showed that elevated level of IL-6 prior to treatment and C2 might be a predictor of pathologic response to NAC.

Background: Machine learning can analyze vast amounts of data and make predictions for events in the future. Our group created machine learning models for vital sign predictions. To transport the information of these predictions without numbers and numerical values and make them easily usable for human caregivers, we aimed to integrate them into the Philips Visual-Patient-avatar, an avatar-based visualization of patient monitoring. Methods: We conducted a computer-based simulation study with 70 participants in three European university hospitals. We validated the vital sign prediction visualizations by testing their identification by anesthesiologists and intensivists. Each prediction visualization consisted of a condition (e.g., blood pressure low) and an urgency (a visual indication of the timespan in which the condition is expected to occur). To obtain qualitative user feedback, we also conducted standardised interviews and derived statements that participants later rated in an online survey. Results: The mixed logistic regression model showed 77.9% (95%CI 73.2-82.0%) correct identification of prediction visualizations (i.e. condition and urgency both correctly identified) and 93.8% (95%CI 93.7-93.8%) for conditions only (i.e. without considering urgencies). Forty-nine of 70 participants completed the online survey. The online survey participants agreed that the prediction visualizations were fun to use (32/49, 65.3%), and that they could imagine working with them in the future (30/49, 61.2%). They also agreed that identifying the urgencies was difficult (32/49, 65.3%). Conclusions: This study found that care providers correctly identified >90% of the conditions (i.e. without considering urgencies). The accuracy of identification decreased when considering urgencies in addition to conditions. Therefore, in future development of the technology, we will focus on either only displaying conditions (without urgencies) or improve the visualizations of urgency to enhance usability for human users.

Objective: To explore the application effect of predictive psychological nursing in the nursing of outpatients with indwelling needle intravenous infusion .Methods: Select 80 patients who received intravenous indwelling needle infusion therapy in the outpatient department of our hospital from January 2022 to December 2022 as the research objects , and divided them into observation group and experimental group according to the different nursing plans received by the patients . 40 cases in each group. The observation group received routine nursing intervention, and the experimental group received predictive psychological nursing intervention. The puncture situation, psychological state level, self-care ability, adverse reactions and nursing satisfaction were compared between the two groups of patients .Results: The puncture success rate of the observation group was 72.5% (29/40), and that of the experimental group was 95.0% (38/40). The puncture success rate of the experimental group was significantly higher than that of the observation group (P<0.05) ; The SAS scores and SDS scores of the treatment group after nursing were significantly lower than those of the observation group (all, P<0.05) ; the self-care skills, self-concept, self-responsibility, health knowledge and ESCA total scores of the experimental group after nursing were significantly higher than those of the observation group. group (all, P<0.05); the incidence of adverse reactions in the observation group was 25.0% (10/40), the incidence of adverse reactions in the experimental group was 7.5% (3/40), and the incidence of adverse reactions in the experimental group was significantly lower than that in the observation group group (P<0.05); the nursing satisfaction of the observation group was 80.0% (32/40), and the nursing satisfaction of the experimental group was 100.0% (40/40), and the nursing satisfaction of the experimental group was significantly higher than that of the observation group (P<0.05 ).Conclusion: The application effect of the predictive psychological nursing intervention model in the outpatient department for intravenous indwelling needle infusion therapy is significant. The implementation of this model can effectively improve the success rate of puncture, improve the patient's psychological state, improve the self-care ability of patients, and reduce the adverse effects of patients. Risk of reaction, so as to further obtain the satisfaction and recognition of patients and their families.

Abstract: Embodied pedagogy maintains that teaching and learning abstract concepts can benefit significantly from integrating bodily movements in the process. Here we explored the involvement of eye movements in the process of collective embodied learning of a concept in physics - angular velocity. Embodied learning was accomplished by the subjects forming a line that rotated around a central object, in this case, a bottle. We tracked the gaze resulting from eye and head movements in 12 subjects, who both actively participated in the collective embodied exercise and passively watched it. The tracking data of 7 of these 12 subjects passed our tracking reliability criteria in all trials and are reported here. During active learning, the learners tended to look ahead of the rotating line (by 35.18±14.82 degrees). In contrast, while passively watching others performing the task, the learners tended to look directly at the line. Interestingly, while the learners were performing the collective exercise they were unaware of looking ahead of the rotating line. We discuss possible differences between active and passive embodied learning that might be indicated by the observed differences in gaze control.

Precision Agriculture is the ability to handle variations in productivity within a field and maximize financial return, optimize resource utilization and minimize impact of the environment. It is also the process of automated data collection, cloud storage and utilization to build robust decision support system. In case of Ethiopia, due to poor communication infrastructure coverage and absence of the state-of-the-art technology in the agriculture sector, implementing precision farming system is a challenging tasks in the domain area. In this work, we proposed a fusion of multiple sensors using IOT and IIOT infrastructure to collect critical data from farming fields to develop precision farming facility for decision makers. The main purpose was to monitor weather variability, automate irrigation process, extract critical soil properties. In addition, we have used time series data collected from sensor devices to build forecasting model. Fusion of multiple IoT device provide a mechanism in the agriculture area to deal with real-time monitoring of crops. It is cost-effective technology and required low-energy with edge computing sensor device. We employed the Message Queuing Telemetry Transport (MQTT) protocol to connect the Industrial/Internet of Things (I/IoT) to the cloud server. The communication between system user and sensor device has been done via cloud using Node-RED platform, web android APIs. The cloud-based Eco-system allows us to aggregate, visualize, and analyze live streams output from each sensor in real-time manner. Finally, we have built time series forecasting model using records collected by each sensor device. Using the multi-variate time series data-set, we have obtained about 99 forecasting accuracy on some important variables. Finally, we have developed mobile and web-based application for the end-user to monitor the proposed system remotely.

There is immense variability in the postharvest quality of Hass avocados. However, there is a lack of knowledge to guaranteeing the robustness of fruit with consistent quality. The aims of this work were to develop a multivariate methodology for evaluating the postharvest quality of avocado and to determine predictive quality markers to manage fruit quality. Fruit samples produced under different nutrient management, elevation, date-to-harvest, and growing-cycle conditions were analyzed. The results highlighted soil and weather differences among orchards. Nutrient management practices based on index balancing in some samples increased both productivity and the fruit size. High variability was observed in the dry matter related to the age of the fruit at harvest. Ripening heterogeneity was very large in low-elevation orchards where the fruit was picked relatively early. High flesh mineral contents delayed fruit ripening. At low growing temperatures, more oleic and linoleic acids were present in fruits. The sensory texture and taste descriptors were affected by the fruit age and related to the flesh composition. Logistic, PLS-DA, and biplot models effectively represented the variabilities in the ripening pattern, composition, and sensory profile of avocado fruits and allowed the samples to be grouped according to the internal fruit quality.

Immune checkpoint inhibitors (ICI) are currently use in a wide range of tumors, but only 20-40% of patients achieve clinical benefit. Aim of our study was to find predictive biomarkers of ICI treatment. We analyzed by immunohistochemistry various cell subsets, including CD3+ cells, CD8+ cells, CD68+ cells, CD20+ cells, FoxP3+ cells, and molecules as LAG-3, IDO1, TGfβ. Comprehensive genomic profiles were analyzed. Correlation of various biomarkers with efficacy of ICI treatment in patients with advanced solid tumors was evaluated. We evaluated 56 patients treated with ICI monotherapy. Longer median progression-free survival (PFS) was found in tumors negative for nuclear FoxP3 (P = 0.002, HR 0.14) and in TMB-high tumors (P = 0.024, HR 0.38). Longer overall survival (OS) was found in patient with intraepithelial CD8 negativity (P = 0.045, HR 0.47). In malignant melanoma CD68 negativity, FoxP3 negativity and PDL TPS ≥ 1 was associated with longer PFS. In NSCLC FoxP3 was associated with longer PFS and OS. We found that absence of expression of several biomarkers such as CD68 and FoxP3 is associated with better survival. TMB-high and PD-L1 expression not universally but in certain disease could predict response.

Background Content marketing is increasingly important for online branding. Brand popularity can be more easily determined online than sales-based measures but is not yet well-explained from a content marketing perspective. Promising predictors are open data syndication policies, connectivity to e-commerce platforms, product reviews, data health, and the depth and width of a brands product portfolio. A predictive content marketing model can help brand owners to understand their e-commerce potential. Methods We used brand popularity (Brand Popularity Rank) and catalog data in combination with product reviews from an independent content aggregator. For all datasets, we selected the overlapping dataset for brand popularity and brand reviews based on a period of 90 days from June 10, 2022, till September 24, 2022 (n = 333 brands). Backward stepwise multiple linear regression was used to develop a predictive content marketing model of the Brand Popularity Rank. Results Through stepwise backward multiple linear regression five highly significant (p < 0.01) predictive factors for brand rank are selected in our content marketing model: the brand’s data syndication policy, the number of connected e-commerce platforms, a brand’s number of products, its number of products per category, and the number of product categories in which it is active. Our model explains 78% of the variance of Brand Popularity Rank and has a good and highly significant fit: F (5, 327) = 233.5, p < 0.00001. Conclusions We conclude that a content marketing model can adequately predict a Brand Popularity Rank based on online popularity. In this model an open content syndication policy, more connected e-commerce platforms, and catalog size, i.e., presence in more categories and more products per category are each related to a better (lower) Brand Popularity Rank score.

Based on the resource-based theory, the current study examines the relationship between competitive strategies and strategic alliance performance. Furthermore, big data predictive analytics is treated as a boundary condition between competitive strategies and strategic alliance performance. Big data of predictive analytics in operations and industrial management has been a focal point in the current era. There has been little attention has about big data predictive analytics influences on competitive strategies and strategic alliance performance, especially in developing countries like Pakistan. A survey instrument was used to record the responses from 331 employees of the telecom sectors companies working in Pakistan. Study findings show that big competitive strategies have a positive and significant relationship with strategic alliances performance. It was also found that big data predictive analytics plays the role of moderator between competitive strategies and strategic alliance performance. The study add a new perspective and contribution to the literature on big data predictive analytics, strategic alliance performance, and competitive strategies in Pakistan's telecom sector companies. Further, the study results explain that big data analytics is just like the companies' lifeblood in the current era. The efficient and effective use of big data analytics, companies can boost their standards in a competitive environment.

This paper attempts to compare two different approaches to solve the problem of accident rates prediction based on human factors for industrial workers. One of the methods has already been done using Fuzzy c-Means Clustering and proved to be working with decent results. The second method which will be covered in this paper is using Artificial Neural Networks. The primary goal of this work is to insure that ANN will work efficiently in such prediction problem. The second goal is to reveal the fact that which one of the two selected methodologies is better at defining the estimation of accident rates among people who work in different industrial fields. The purpose has been achieved when the outcome of the ANN was obtained and compared accordingly with the output of the research previously carried out with Fuzzy c-means clustering method. Comparing the outcomes of these two different methods gave an immense insight on which features are more important than others when it comes to laborers properties with completely different background such as varying levels of health, knowledge, experience, training and physical properties. At the end of the research, it becomes clear that accident rates estimation for laborers with properly trained Artificial Neural Network gives better results when it is compared with Fuzzy c-Means Clustering method. Standard deviation method was used to calculate the validity of ANN technique. The result was compared with Fuzzy c-mean clustering technique. Impressive improvement of 8.8% in the accident rate prediction was achieved using Tailored-Made-ANN.

Breast Cancer diagnosis is one of the most studied problems in the medical domain. In the medical domain, cancer diagnosis has been studied extensively which instantiates the need of early prediction of cancer disease. For obtaining advance prediction, health records are exploited and given as input to an automated system. This paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining possibility of being affected by breast cancer. Proposed model is compared against other baseline classifiers such as stacked Simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that stacked GRU-LSTM-BRNN yield better classification performance for predictions related to breast cancer disease.

As the educational landscape evolves, understanding and fostering student adaptability has become increasingly critical. This study presents a comparative analysis of (XAI) techniques to interpret machine learning models aimed at classifying student adaptability levels. Leveraging a robust dataset, we employed several machine learning algorithms with a particular focus on Random Forest, which demonstrated a 91% accuracy. Our study utilizes (SHAP), (LIME), Anchors, (ALE), and counterfactual explanations to reveal the specific contributions of various features impacting adaptability predictions. Consistently, 'Class Duration' and 'Financial Condition' emerge as key factors, while the study also underscores the subtle effects of 'Institution Type' and 'Load-shedding'. This multi-faceted interpretability approach bridges the gap between machine learning performance and educational relevance, presenting a model that not only predicts but also explains the dynamic factors influencing student adaptability. The synthesized insights advocate for educational policies accommodating socioeconomic factors, instructional time, and infrastructure stability to enhance student adaptability. The implications extend to informed and personalized educational interventions, fostering an adaptable learning environment. This methodical research contributes to responsible AI application in education, promoting predictive and interpretable models for equitable and effective educational strategies.

Neoadjuvant therapy (NAT) for early-stage pancreatic ductal adenocarcinoma (PDA) has recently gained prominence. We investigated the clinical significance of mucin 5 AC (MUC5AC), which exists in two major glycoforms, a less-glycosylated immature isoform (IM) and a heavi-ly-glycosylated mature isoform (MM), as a biomarker in resected PDA. Immunohistochemistry was performed on 100 resected PDAs to evaluate the expression of IM and MM isoforms of MUC5AC using respective monoclonal antibodies CLH2 (NBP2-44455) and 45M1 (ab3649). MUC5AC localization (cytoplasmic, apical, and extra-cellular, EC) was determined, and H-scores were calculated. Univariate and multivariate (MVA) Cox regression models were used to estimate progression-free survival (PFS) and overall survival (OS). Of 100 resected PDA patients, 43 received NAT, and 57 were treatment-naïve with upfront surgery (UpS). In the study population (N=100), IM expression (objective response vs. no response vs. UpS = H-scores 104 vs. 152 vs. 163, p=0.01) and MM-MUC5AC detection rates (56% vs. 63% vs. 82%, p=0.02) were significantly different. In the NAT-group, MM-MUC5AC-negative patients had significantly better PFS on MVA (Hazard Ratio, 0.2, 95 % CI: 0.059-0.766, p = 0.01). Similar results were noted in a FOLFIRINOX sub-group (N=36). We established an association of MUC5AC expression with treatment response and outcomes.

As modern systems are becoming more complex their control strategy cannot longer relay only on measurement information that usually comes from probes but also from mathematical models. Those systems models can lead to unbearable computation times due to their own complexity, turning the control process non-viable, which leads to the implementation of surrogate models that enable to achieve estimates within acceptable time to take decisions. A control trained with Deep Reinforcement Learning algorithm, using a Physics-Informed Neural Network to obtain the temperature map on the following time step, replaces the need of running Direct Numerical Simulations. On this work we considered an 1D heat conduction problem, which temperature distribution feeds a control system to activate a heat source aiming to obtain a constant, previously defined, temperature value. With this approach, control training becomes much faster without the need of performing numerical simulations or laboratory measurements, as well the control is taken based on Neural Network enabling its implementation on simple processors to edge computing.

The use of didactic and interactive materials is essential in generating interest among students and teachers in utilizing mathematical models and digital technologies for the educational process. These materials create a dynamic and engaging learning environment that promotes a deeper understanding of complex concepts and fosters a passion for learning. Additionally, integrating interactive materials into pilot courses can assist teachers in better assessing student learning and adjusting the teaching strategies accordingly and the teachers can receive valuable insights into students' strengths and weaknesses, allowing them to provide targeted support and intervention when needed. In this context, the purpose of this paper is to introduce an approach for solving mathematics problems embedded in technical scenarios within the defense and security fields with the aid of digital technology. In this way, students can visualize abstract concepts, experiment with different scenarios, and receive instant feedback on their understanding. This paper helps to reinforce key concepts and enhance problem-solving skills, sparking curiosity, creativity, and encouraging active participation and collaboration. Throughout the development of this proposal, good practices are adopted, and advice for improvement is collected while having a wide range of users, giving feedback, discussions, and testing (pilot) short-term learning/teaching/training activities.

This work presents a Fault-Tolerant Model Predictive Control (FTMPC) algorithm applied to a simulation model for sewer networks. The control system will aim to prevent contaminated water from escaping the network, especially during periods of heavy rainfall, that can cause combined sewer overflows (CSO), while maintaining the flow of water towards the wastewater treatment plant (WWTP) as close as possible to its nominal value. The main purpose of the work is to preserve the operation of the predictive controller as much as possible, in accordance with its operational objectives, when there may be anomalies affecting the elements of the control system, mainly sensors and actuators. Comparing the results obtained considering various types of faults, with situations of normal controlled operation and with the behavior of the sewer network when no control is applied, will allow some conclusions to be drawn at the end.

Throughout the Covid19 period, families were forced to stay indoors, adapting to online school-ing, remote work, and virtual social engagements, inevitably altering the dynamics within households. There is a notable increase in mental health challenges in terms of anxiety and de-pression in children and adolescents. This study intends to explore the psychosocial effects of the Covid-19 pandemic in Italian families adopting self- and proxy-report questionnaires on anxiety, anger, and health-related quality of life. The results showed that approximately 20% obtained a clinical anxiety score and only 10% obtained a clinical anger score. There was found a difference in the perception of the quality of life reported by the child and that perceived by the parent. The stepwise regression model showed that total anxiety scores were predicted by sex, quality of life scores from the parents' self-report version and total anger score. Another stepwise regression model identified physiological and social anxiety as the best predictors that impact the quality of life. Parental well-being actively influences the well-being of children, so it is fundamental to implement preventive programmes and promote child well-being providing parents the most adequate support possible.

Lysophosphatidic acid (LPA) is a promising biomarker candidate to screen for ovarian cancer (OC) and potentially stratify and treat patients according to disease stage. LPA is known to target actin-binding protein gelsolin that is a key regulator of actin filament assembly. Previous studies have shown that the phosphate headgroup of LPA alone is inadequate to bind to the short chain of amino acids in gelsolin known as the PIP2-binding domain. Thus, the molecular-level detail of the mechanism of LPA binding is poorly understood. Here, we model LPA binding to the PIP2-binding domain of gelsolin in the gelsolin-actin complex through extensive ten microsecond atomistic molecular dynamics (MD) simulations. We predict that LPA binding causes a local conformational rearrangement due to LPA interactions with both gelsolin and actin residues. These conformational changes are a result of the amphipathic nature of LPA, where the anionic phosphate, polar glycerol and ester groups, and lipophilic aliphatic tail mediate LPA binding via charged electrostatic, hydrogen bonding, and van der Waals interactions. The negatively-charged LPA headgroup binds to the PIP2-binding domain of gelsolin-actin while its hydrophobic tail is inserted into actin, creating a strong LPA-insertion pocket that weakens the gelsolin–actin interface. The computed structure, dynamics, and energetics of the ternary gelsolin–LPA–actin complex confirms that a quantitative OC assay is possible based on LPA-triggered actin release from the gelsolin-actin complex.

Locally advanced rectal cancer (LARC) has traditionally been treated with trimodality therapy consisting of neoadjuvant radiation +/- chemotherapy, surgery and adjuvant chemotherapy. There is currently a clinical need for biomarkers to predict treatment response and outcomes, especially during neoadjuvant therapy. Liquid biopsy in the form of circulating tumour cells (CTCs) and circulating nucleic acids in particular microRNAs (miRNA) are novel, highly stable and clinically relevant regulators of disease. We studied a prospective cohort of 52 patients with LARC, and obtained samples at baseline, during treatment, and post-treatment. We enumerated CTCs during chemoradiation at these three time-points, using the IsofluxTM CTC Isolation and detection platform. We then subjected the isolated CTCs to miRNA expression analyses, using a panel of 106 miRNA candidates. We identified CTCs in 73% of patients at baseline, and numbers fell during treatment and miRNA expression profiles also changed during treatment. Between baseline and during treatment (week 3) time-points three microRNAs (hsa-miR-95, hsa-miR-10a and hsa-miR-16-1*) were highly differentially expressed. Importantly, hsa-miR-19b-3p and hsa-miR-483-5p were found to correlate with good response to treatment. The latter (hsa-miR-483-5p) was also found to be differentially expressed between good responders and poor responders. They represent potential predictive biomarkers and a potential miRNA-based treatment strategy. In this study, we demonstrate that CTCs are present and can be isolated in the non-metastatic early stage cancer setting, and their associated miRNA profiles can potentially be utilized to predict treatment response.

Effective marketing decision-making benefits from a rigorous, data-driven process that systematically evaluates alternatives based on insights and analysis. This study develops and evaluates a 5-stage decision-making process model integrating marketing engineering principles aimed to optimize marketing decisions. An experiment randomized 150 participants into groups following either the proposed model or an unaided approach. Results indicate the model-following group achieved significantly higher ROI from marketing decisions (19.3% vs 16.4%) and employed key elements like customer segmentation, experimentation, and optimization to a greater extent. However, limitations including the experiment's scenario, self-report measures, and cross-sectional design constrain implications. Future research employing probability sampling, multiple decision contexts, longitudinal designs, manipulation checks, and objective metrics can further validate the proposed model. Overall, the study advances the understanding of how structured decision processes based on marketing engineering principles may optimize marketing decisions and outcomes.

This study employs a high-fidelity numerical framework to determine the plastic material flow patterns and temperature distributions that lead to void formation during friction stir welding (FSW), and to relate the void morphologies to the underlying alloy material properties and process conditions. Three aluminum alloys, viz., 6061-T6, 7075-T6, and 5053-H18 were investigated under varying traverse speeds. The choice of aluminum alloys enables investigation of a wide range of thermal and mechanical properties. The numerical simulations were validated using experimental observations of void morphologies in these three alloys. Temperatures, plastic strain rates, and material flow patterns are considered. The key results from this study are: (1) The predicted stir zone and void morphology are in good agreement with the experimental observations, (2) The temperature and plastic strain-rate maps in the steady-state process conditions show a strong dependency on the alloy type and traverse speeds, (3) The material velocity contours provide a good insight into the material flow in the stir zone for the FSW process conditions that result in voids as well as those that do not result in voids. The numerical model and the ensuing parametric studies presented in this work provide a framework for understanding material flow under different process conditions in aluminum alloys, and potentially in other alloys. Furthermore, the utility of the numerical model for making quantitative predictions and investigating different process parameters to reduce void formation is demonstrated.

For a decade, the studies of dynamic control for unmanned aerial vehicles took a large interest, where drones as a useful technology in different areas were always suffering from several issues like instability-high energy consumption of batteries - inaccuracy of tracking targets. Different approaches are proposed for dealing with the non-linearity issues which present the most important features of this system. This paper describes our focus on the most common control strategies, known as model predictive control MPC, by developing a model based on the sensors embedded in our Tello quadrotor used for indoor purposes. The original controller of Tello quadrotor is supposed to be a slave, where the designed model predictive controller is created in MATLAB and imported to another embedded system, considered as a master; the objective of this model is to track the reference trajectory, almost keeping the stability of the system and ensure the low energy consumption. In the first part, a profound description of the modelling process of a dynamic model for drones is presented, explaining the design of MPC controller with both linear and non-linear strategies built in MATLAB. In the final part, simulation and results are discussed regarding its behaviour and performance, highlighting the MPC model's important role on drones' energy consumption profile.

High-performance motor drives that operate in harsh conditions require an accurate and robust angular position measurement to correctly estimate the speed and reduce the torque ripple produced by angular estimation error. For that reason, a resolver is used in motor drives as a position sensor due to its robustness. A resolver-to-digital converter (RDC) is an observer used to get the angular position from the resolver signals. Most RDCs are based on angle tracking observers (ATOs). On the other hand, generalized predictive control (GPC) has become a powerful tool in developing controllers and observers for industrial applications. However, no GPC-based RDC with zero steady-state error during constant speed operation was proposed. This paper proposes an RDC based on a second-order difference GPC (SOD-GPC). In SOD-GPC, the second-order difference operator is applied to design a GPC model with two embedded integrators. Thus, the SOD-GPC is used to design a type-II ATO whose steady-state angle estimation error tends to zero during constant speed operation. Simulation and experimental results prove that the proposed RDC system has better performance than other literature approaches.

Circulating tumor cells (CTCs) enumeration is a promising technique to predict cancer prognosis and treatment response. CTCs were evaluated in healthy subjects, cirrhotic controls and hepatocarcinoma (HCC) patients. CTCs were isolated using microfluidic system based on the expression of EpCAM, EGFR and three epithelial to mesenchymal transition (EMT) markers. Patients were stratified according to disease progression and exitus. Although counts of individual CTCs, clustered CTCs and α-fetoprotein (AFP) at basal level in patients with HCC were significantly increased compared with the values obtained in cirrhotic patients and control subjects, only individual CTCs (p=0.027), but not clustered CTCs (p=0.063) and AFP (p=0.072), were independent predictors of HCC development. The univariate regression model showed that basal levels of CTCs46 were related to high risk of HCC (Odds Ratio 3.467, p=0.011). The stratification of our cohort according to disease progression and death showed that basal individual CTCs 76 (Hazard Ratio 5.131, p=0.004) were related to disease progression, as well as the difference of clustered CTCs between 1-month and baseline levels 1.5 were related to death (Hazard Ratio 10.204, p=0.036). In conclusion, the preoperative and 1-month measurements of CTCs in blood constitute useful markers to predict the outcome of patients under TACE treatment.

Rapid increase in digital data coupled with advances in deep learning algorithms is opening unprecedented opportunities for incorporating multiple data sources for modeling spatial dynamics of human infectious diseases. We used Convolutional Neural Networks (CNN) in conjunction with satellite imagery-based urban housing and socio-economic data to predict disease density in a developing country setting. We explored both single (uni) and multiple input (multimodality) network architectures for this purpose. We achieved maximum test set accuracy of 81.6 per cent using a single input CNN model built with one convolutional layer and trained using housing image data. However, this fairly good performance was biased in favor of specific disease density classes due to an unbalanced data set despite our use of methods to address the problem. These results suggest CNN are promising for modeling spatial dynamics of human infectious diseases, especially in a developing country setting. Urban housing signals extracted from satellite imagery seem suitable for this purpose, under the same context.

The complex progression, specialized care, and comorbidities of chronic diseases place a financial and health burden on society. In some instances, the high hospital readmission rate is also a result of chronic diseases. The readmission rates can be decreased if the quality of life for patients is increased and healthcare costs are reduced through effective management and preventive measures. As a result, healthcare professionals, service providers, and policy-makers are looking for innovative approaches to reduce healthcare costs while enhancing the quality of care. There is an emerging trend in deploying technological advancements like artificial intelligence (AI), the Internet of Things (IoT), sensors, wearables, social media, mobile apps, and genomics to decrease hospital readmissions. In some instances, predictive analytics, early warning systems, personal-ized care management, remote monitoring and Telehealth, decision support systems, patient education and engagement, and other areas of artificial intelligence and machine learning have outperformed traditional approaches in lowering hospital readmissions. Although AI effectively reduces readmission, there are potential risks if it is not combined with efficient interventions. Therefore, real-time monitoring and intervention are required for AI systems to increase patient safety and decrease hospital readmissions. To achieve autonomy, prevent harm, achieve fairness, and achieve explicability, the ethical principles relating to AI systems should be taken into ac-count. This study examines the significant impact on health and the economy of hospital read-missions for chronic diseases and the role of AI in reducing readmissions.

A reduced order model is developed to monitor aeroengines condition (defining their degradation from a baseline state) in real-time, by using data collected in specific sensors. This reduced model is constructed by applying higher order singular value decomposition plus interpolation to appropriate data, organized in tensor form. Such data are obtained using a detailed engine model that takes the engine physics into account. Thus, the method synergically combines the advantages of data-driven (fast online operation) and model-based (the engine physics is accounted for) condition monitoring methods. Using this reduced order model as surrogate of the engine model, two gradient-like condition monitoring tools are constructed. The first tool is extremely fast and able to precisely compute `on the fly’ the turbine inlet temperature, which is a paramount parameter for the engine performance, operation, and maintenance, and can only be roughly estimated by the engine instrumentation in civil aviation. The second tool is not so fast (but still reasonably inexpensive) and precisely computes both, the engine degradation and the turbine inlet temperature at which sensors data have been acquired. These tools are robust in connection with random noise added to the sensors data and can be straight forwardly applied to other mechanical systems.

This study investigates the application of regression neural networks, in particular the fitrnet model, in predicting the hardness of steels. The experiments involve extensive tuning of hyperparameters using Bayesian optimization and employ 5-fold and 10-fold cross-validation schemes. The trained models are rigorously evaluated, and their performances are compared using various metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The results provide valuable insights into the effectiveness of the models and their ability to generalize to unseen data. In particular, Model 4208 (8-85-141-1) emerges as the top performer with an impressive RMSE of 1.0790 and an R² of 0.9900. The research paper contains an illustrative example that demonstrates the practical application of the developed model in determining the hardenability band for a specific steel grade and shows the effectiveness of the model in predicting and optimizing heat treatment results.

Background: Cervical cancer prevention in regions with limited access to screening and HPV vaccination necessitates innovative approaches. This study explored the potential of a test-and-treat strategy using mRNA HPV tests to impact cervical cancer prevention in a high-prevalence HIV population. Methods: A cervical screening study was conducted at three South African hospitals involving 710 under-screened, non-pregnant women (25 to 65 years) without known cervical diseases. Cytology, HPV testing, colposcopy, and biopsies were performed concurrently. Histopathologists determined final histological diagnoses based on biopsy and LLETZ histology. mRNA-HPV-genotyping for 3 (16, 18, 45) to 8 (16, 18, 31, 33, 35, 45, 52, 58) high-risk types was performed on leftover liquid-based cytology material. The preventive potential of the test-and-treat approach was estimated based on published data, reporting the causative HPV types in cervical cancer tissue from South African women. Treatment was provided as needed. Results: HPV positivity rate more than doubled from 3-type (15.2%; 95% CI: 12.6-17.8) to 8-type mRNA (31.5%; 95% CI: 28.8-34.9) combinations, significantly higher among HIV-positive women. CIN3+ prevalence among HIV-positive women (26.4%) was double that of HIV-negative women (12.9%) (p&lt;0.01). The 6-type combination showed the best balance of sensitivity, specificity and treatment group size, and effectiveness to prevent cervical cancer. A 4-type combination (16, 18, 35, 45) could potentially prevent 77.6% (95% CI: 71.2-84.0) of cervical cancer burden by treating 20% and detecting 41.1% of CIN3 cases in the study group. Similarly, a 6-type combination (16, 18, 31, 33, 35, 45), treating 25% and including 62% of CIN3 cases, might prevent 85% of cervical cancer cases (95% CI: 79.6-90.6) among HIV-positive and negative women. Conclusion: Employing mRNA HPV tests within a test-and-treat approach holds huge promise for targeted cervical cancer prevention in under-screened populations. Testing for mRNA of the 6 highest-risk HPV types in this population and treating them all is projected to effectively prevent progression from CIN3 to invasive cervical cancer while reducing overtreatment in resource-constrained settings.

This study explores the application of data mining techniques in marketing strategies, highlighting their impact on customer segmentation, predictive analytics, and personalization. Data mining has emerged as a transformative tool for businesses seeking to enhance their marketing effectiveness by providing deep insights into customer behavior and preferences. Techniques such as clustering, predictive modeling, and personalization are examined for their roles in improving marketing outcomes. Clustering methods, including K-means and hierarchical clustering, enable businesses to categorize customers into meaningful segments, allowing for more targeted marketing efforts. Predictive analytics, utilizing models like decision trees and neural networks, offers the capability to forecast future customer behaviors and trends, thereby optimizing resource allocation and strategy planning. Personalization techniques, such as collaborative filtering and dynamic recommendations, enhance customer engagement by delivering tailored content and offers. Despite these advantages, the study also addresses the challenges associated with data mining, including data privacy concerns, data quality issues, and the shortage of skilled personnel. These challenges underscore the need for effective data management practices and ethical considerations in the application of data mining. Furthermore, the integration of emerging technologies like artificial intelligence and real-time analytics is discussed as a means to overcome existing obstacles and drive future advancements in marketing strategies. The findings underscore the significant role of data mining in revolutionizing marketing practices and highlight the ongoing need for adaptation and innovation in response to evolving market dynamics.

Introduction: The escalating morbidity, mortality, and healthcare costs associated with invasive candidiasis pose significant challenges in pediatric intensive care units (PICUs). Conventional diagnostic methods fall short in effectiveness, while various risk factors exacerbate the prevalence of these infections. This study introduces a novel model that amalgamates the Candida Score with key predictors to enhance the specificity and applicability of mortality risk assessments for pediatric patients with fungemia. Methods: This retrospective cohort study aimed to develop an integrated model for estimating mortality risk in children with fungemia in PICUs. We constructed and evaluated multiple predictive models using the Candida Score and other relevant clinical and laboratory variables. The discriminative abilities of the models were assessed using the area under the receiver operating characteristic curve (AUC). Results: The study cohort comprised 85 pediatric patients admitted between 2016 and 2020, with a median age of 6 months and a male predominance of 62.4%. The mortality rate was 45.9%. Candida albicans was the most prevalent causative agent, accounting for 37.55% of fungemia cases. Multivariable Logistic regression revealed the duration of mechanical ventilation, and the Candida Score were significant predictors of mortality. Each additional day of ventilation increased mortality odds by 11.5% (OR = 1.115, 95% CI: 1.025-1.212, p = 0.011), while a higher Candida Score more than doubled the odds (OR = 2.205, 95% CI: 1.359-3.578, p = 0.001).The Random Forest predictive model demonstrated superior discriminative performance, with an AUC of 0.838 (95% CI: 0.738-0.917), outperforming Gradient Boosting and Logistic Regression models, which had AUCs of 0.7759 (95% CI: 0.667-0.877) and 0.7085 (95% CI: 0.589-0.813), respectively. Although the internal validation yielded satisfactory results, external validation is warranted. Conclusion: This study presents an innovative approach for accurately assessing the risk of mortality due to fungemia in PICU patients by integrating the Candida Score with critical predictors. The Random Forest model emerged as the most effective predictive tool due to its exceptional discriminative ability.

The abstract of the study on the challenges and opportunities of supply chain digitalization encapsulates the primary findings and their implications from the perspectives of industry leaders. This qualitative research investigated how senior executives across diverse sectors perceive and manage the transition to digital supply chains. Interviews with twenty industry leaders revealed key challenges such as data integration, cybersecurity, organizational resistance, and financial constraints. Data integration issues were particularly pronounced, as participants struggled with unifying disparate data sources from legacy and modern systems, creating barriers to achieving cohesive digital frameworks. Cybersecurity emerged as a critical concern due to the increased vulnerability of digital supply chains to cyber threats, necessitating robust and proactive security measures. Organizational resistance, driven by employee apprehensions about job displacement and technological unfamiliarity, highlighted the need for effective change management practices, including clear communication and training. Financial constraints, especially for small and medium-sized enterprises (SMEs), underscored the difficulty of justifying the substantial investments required for advanced digital technologies. Despite these challenges, the study identified significant opportunities associated with digitalization, including enhanced operational efficiency, improved visibility, predictive analytics, and better customer satisfaction. Digital tools were found to streamline processes, reduce manual intervention, and provide real-time insights into supply chain performance, thus facilitating more informed decision-making and swift responses to disruptions. The accelerated adoption of digital technologies during the COVID-19 pandemic demonstrated their essential role in enhancing supply chain resilience and agility. Additionally, the integration of sustainability goals through digitalization supported resource optimization and waste reduction, aligning with broader corporate social responsibility objectives. The findings suggest that while the path to digital transformation is complex, the benefits of improved efficiency, decision-making, customer satisfaction, and sustainability present compelling incentives for organizations to invest in and embrace digital supply chain solutions.

.Cloud manufacturing is an evolving networked framework that enables multiple manufacturers to collaborate in providing a range of services, including design, development, production, and post-sales support. The framework operates on an integrated platform encompassing a range of Industry 4.0 technologies, such as Industrial Internet of Things (IIoT) devices, cloud computing, Internet communication, big data analytics, artificial intelligence, and blockchains. The connectivity of industrial equipment and robots to Internet opens the cloud manufacturing to the massive attack surface of cybersecurity and cyber crime threats caused by external and internal attackers. The impacts can be severe because physical infrastructure of industries is at stake. One potential method to deter such attacks involves utilizing blockchain and artificial intelligence to track the provenance of IIoT devices. This research explores a practical approach to achieve this goal by gathering provenance data associated with operational constraints defined in smart contracts and identifying deviations from these constraints through predictive auditing using artificial intelligence. A software architecture comprising IIoT communications to machine learning for comparing the latest data with the predictive auditing outcomes and logging appropriate risks was designed, developed, and tested. The state changes in the smart ledger of smart contracts were linked with the risks such that the blockchain peers can timely detect high deviations and take actions. The research defined the constraints related to physical boundaries and weight lifting limits allocated to three forklifts and showcased the mechanisms of detecting risks of breaking these constraints with the help of artificial intelligence. It also demonstrated state change rejections by blockchains at medium and high-risk levels. This research followed software development in Java 8 using JDK 8, CORDA blockchain framework, and Weka package for random forest machine learning. As a result of this, the model, along with its design and implementation, has the potential to enhance efficiency and productivity, foster greater trust and transparency in the manufacturing process, booster risk management, strengthen cybersecurity, and advance sustainability efforts.

The behavioral variant of frontotemporal dementia (bvFTD) has a devastating effect on multiple domains of daily living. The purpose of this PRISMA-compliant systematic review is to summarize the most important factors associated with functional impairment in this clinical group by critically analyzing the existing literature spanning the period from 2000 to 2023. To be included in the review, the study had to investigate any kind of correlates of functional status in bvFTD patients, using a previously validated instrument of functional assessment. Out of 40 articles assessed for eligibility, 18 met the inclusion criteria. The anatomical pattern of cerebral atrophy at baseline appeared to be the strongest predictor of the rate of functional decline over time, with the frontal-dominant anatomical subtype being associated with a faster rate of functional impairment. Additionally, executive dysfunction as well as apathy appeared to contribute significantly to functional disability in bvFTD patients. A comparative examination of bvFTD in relation to other clinical subtypes of FTD and other types of dementia in general suggests that it’s the predominant atrophy of the frontal lobes along with the subsequent unique combination of cognitive and neuropsychiatric manifestations that account for the pronounced functional limitations observed in these individuals, even from the early stages of the disease.

The global prevalence of insulin resistance (IR) is increasing continuously, influencing metabolic parameters and fertility as well. The metabolic changes due to IR can alter the molecular composition of plasma and other body fluids. Follicular fluid (FF) is derived mainly from plasma, and it is a critical microenvironment for the developing oocytes. It contains various metabolites and amino acids, and the quality of the oocytes is linked at least partially to amino acid metabolism. Our goal was to determine quantitatively the amino acid (AA) profile of FF in IVF patients and to compare IR and non-insulin resistance (NIR) groups to investigate the AA changes in their FF. By UHPLC-based method we quantified the main 20 amino acids from human FF samples in the IR and NIR groups. Several amino acids (aspartate, glycine, glutamate, and cysteine) differed significantly (p&lt;0.05 or less) between the two groups. The most significant alterations between the IR and NIR groups were related to the glutathione metabolic pathway involving glycine, serine, and threonine. Since insulin resistance alters the amino acid composition of the FF, the oocytes may undergo metabolism-induced changes resulting in poor oocyte quality and less fertility in the insulin resistance groups.

Lodging is a common problem in maize production that seriously impacts yield, quality, and the capacity for mechanical harvesting. Evaluation of site-specific lodging risks requires establishment of a method for multi-year monitoring. In this study, spectral images collected by the Sentinel-2 satellite were processed to obtain three types of data: gray-level co-occurrence matrix texture (GLCM), vegetation indices (VIs), and spectral reflectance (SR). Lodging classification models were then established with Random Forest (RF) using each of the three data types separately (the GLCM, VI, and SR models) and in combination (SR+VI model, SR+GLCM model, VI+GLCM mod-el, and SR+VI+GLCM model). By gradually removing features with low importance scores from the SR+VI+GLCM model and analyzing the changes in the overall accuracy (OA), the optimal set of predictive variables was identified and used to construct the optimal model. A model built us-ing data from a single timepoint in 2021 was tested on data collected at a similar timepoint in 2019 and vice versa to assess interannual model generalizability. The results of this study demon-strate that for monitoring maize lodging, models constructed with a single feature type, the GLCM model had significantly lower accuracy compared to the VI and SR models. During certain growth stages, the model constructed with combined features had significantly higher accuracy in monitoring maize lodging compared to models constructed with a single feature. During the pro-cess of selecting the optimal predictive variables, it was found that the accuracy of the model did not increase as the number of predictive variables increased. The results show that the positive and negative validation models had an accuracy of 96.55% and 95.18%, with kappa values of 0.93 and 0.83, respectively. This indicates that the model has strong generality for the same repro-ductive stage between years. This study provides a detailed method for large-scale maize lodging monitoring, allowing for identification of optimal planting practices to reduce the probability of lodging and ultimately improving regional maize yield and quality.

The use of artificial intelligence (AI) applications in education has the potential to revolutionize the learning experience for international students, who face unique challenges when studying in a foreign country. This paper explores various examples of AI applications in education and their potential impact on international students. AI applications such as personalized learning experiences, adaptive testing, predictive analytics, and chatbots for learning and research are examined for their potential to improve learning efficiency and provide customized education support. It also explores the significant risks and limitations associated with AI technologies, such as privacy, cultural differences, language proficiency, and ethical implications. To maximize the potential benefits of AI applications in higher education, it is crucial to implement appropriate safeguards and regulations. This paper provides a starting point for research on the potential impact of artificial intelligence on international students’ educational experiences and how AI may be integrated into educational administration and learning processes.

Tissue programmed death ligand-1 (PD-L1) protein expression is predictive of immune checkpoint inhibitor (ICI) benefit. However, tissue PD-L1 can be fraught with tissue acquisition and heterogeneity limitations. Plasma testing can overcome these limitations. However, the overall survival (OS) predictive benefit of plasma PD-L1 assays have not been well characterized. Patients with stage IV non-small cell lung cancer (NSCLC) and plasma cfRNA PD-L1 by PCR expression were identified and assessed for OS. 16 patients treated with front-line ICI-based regimens were assessed and represented a real-world patient population with over half with a performance status of 2 or greater. 10 contemporaneous patients at the same institution treated with chemotherapy alone were also identified and assessed. With a median follow-up of 33 months, median OS was 13 months with a 30% 3-year OS for the ICI treated patients compared to a median OS of 3 months and a 10% 3-year OS for those treated with chemotherapy alone. Comparative log-rank test p-value = 0.014 and a hazard ratio 0.376 (95%-CI 0.134-1.057). Plasma cfRNA PD-L1 was associated with a statistically significant survival benefit from ICI-based treatment compared to chemotherapy in the first line treatment of a real-world patient population of advanced NSCLC.

Individual differences in the responsiveness of the brain to transcranial electrical stimulation (tES) is increasingly demonstrated in large variability in the tES effects. Anatomically detailed computational brain models have been developed to address this variability; however, static brain models are not ‘realistic’ in accounting for the dynamic state of the brain. Therefore, human-in-the-loop optimization is proposed in this perspective article based on an extensive systems analysis of the tES neurovascular effects. First, modal analysis was conducted using a physiologically detailed neurovascular model that found stable modes in the 0 Hz to 0.05 Hz range for the pathway for vessel response through the smooth muscle cells, measured with functional near-infrared spectroscopy (fNIRS). tES effects in the 0 Hz to 0.05 Hz range can also be measured with functional magnetic resonance imaging (fMRI)-tDCS data with a maximum TR=10sec. Therefore, we investigated an open-source fMRI-tDCS dataset that used a TR=3.36sec. We found that both the anodal tDCS condition and sham tDCS condition had similar Finite Impulse Response at the region of interest underlying the anode and a remote location, which indicated a global hemodynamic effect of sham tDCS beyond the intended transient sensations. Here, transient sensations can have arousal effects on the hemodynamics so we conducted a healthy case series for black box modeling of fNIRS-pupillometry of short-duration tDCS effects. The block exogeneity test rejected the claim that tDCS is not a 1-step Granger-cause of the fNIRS total hemoglobin changes (HbT) and pupil dilation changes (p<0.05). Also, grey-box modeling using fNIRS of the tDCS effects in chronic stroke showed HbT response to be significantly different (paired-sample t-test, p<0.05) between the ipsilesional and the contralesional hemisphere for primary motor cortex tDCS and cerebellar tDCS which was subserved by the smooth muscle cells. Here, our perspective is that various physiological pathways subserving tES effects can lead to state-trait variability that can be challenging for clinical translation. Therefore, we conducted a case study on human-in-the-loop optimization using our reduced dimension model and a stochastic, derivative-free Covariance Matrix Adaptation Evolution Strategy. Future studies need to investigate human-in-the-loop optimization of tES for reducing inter-subject and intra-subject variability in tES effects.

BACKGROUND Epidemiological sciences have been evolving at an exponential rate paralleled only by the comparable growth within the discipline of data science. Digital epidemiological studies are playing a vital role in medical science analytics for the past few decades. To date, there are no published attempts at deploying the use of real-time analytics in connection with the disciplines of Dentistry or Medicine. AIMS AND OBJECTIVES We deployed a real-time statistical analysis in connection with topics in Dental Anatomy and Dental Pathology represented by the maxillary sinus, posterior maxillary teeth, related oral pathology. The purpose is to infer the digital epidemiology based on a continuous stream of raw data retrieved from Google Trends database. MATERIALS AND METHODS Statistical analysis was carried out via Microsoft Excel 2016 and SPSS version 24. Google Trends database was used to retrieve data for digital epidemiology. Real-time analytics and the statistical inference were based on encoding a programming script using Python high-level programming language. A systematic review of the literature was carried out via PubMed-NCBI, the Cochrane Library, and Elsevier databases. RESULTS The comprehensive review of databases of the literature, based on specific keywords search, yielded 491813 published studies. These were distributed as 488884 (PubMed-NCBI), 1611 (the Cochrane Library), and 1318 (Elsevier). However, there was no single study attempting real-time analytics. Nevertheless, we succeeded in achieving an automated real-time stream of data accompanied by a statistical inference based on data extrapolated from Google Trends. CONCLUSION Real-time analytics are of considerable impact when implemented in biological and life sciences as they will tremendously reduce the required resources for research. Predictive analytics, based on artificial neural networks and machine learning algorithms, can be the next step to be deployed in continuation of the real-time systems to prognosticate changes in the temporal trends and the digital epidemiology of phenomena of interest.

This qualitative research explores the impact of Artificial Intelligence (AI) on Customer Relationship Management (CRM), providing a comprehensive analysis of how AI technologies are transforming CRM practices. AI integration in CRM has revolutionized customer interactions, enabling enhanced personalization, efficiency, and customer engagement. By leveraging machine learning, natural language processing, and predictive analytics, organizations can create highly tailored customer experiences, automate routine tasks, and anticipate future customer needs with precision. The study identifies the significant benefits of AI, including improved customer insights, faster response times, and proactive engagement strategies. However, it also highlights the challenges associated with AI adoption in CRM, such as data privacy and security concerns, algorithmic bias, high implementation costs, and resistance to change. The findings emphasize the need for robust data protection measures, strategies to mitigate biases, significant investments in technology and training, and effective change management to overcome these challenges. The thematic analysis reveals key areas where AI is making an impact, including customer service, customer segmentation, and personalized marketing strategies. Additionally, the study discusses the organizational implications of AI adoption, such as enhanced decision-making, increased productivity, and the necessity for staff reskilling. Future directions for AI in CRM suggest further advancements in AI algorithms, greater integration with other business systems, enhanced customer experiences, and a focus on ethical AI practices. This research underscores the transformative potential of AI in CRM and provides insights for organizations aiming to leverage AI for improved customer relationship management.

As the use of AI in medical imaging has increased, so has the need to explain a model’s results. Segmentation models are one technique used to produce explainable results. Due to larger size and sophistication, segmentation models which operate on 2D data can often produce better results than models operating on 3D data. In the real world, imaging is combined with clinical factors for diagnosis. To replicate this, multimodal models are used which combine image and text modalities. I propose a multimodal arrangement that converts 3D scans to 2D and uses a 2D segmentation model (DeepLabV3) to analyze the images. This is combined with clinical biomarkers to achieve a complete confidence score. Using the Medical Segmentation Decathlon Lung (MSDL) dataset and the LUng CAncer Screening dataset (LUCAS), I achieved a testing Dice coefficient of 0.91 on segmentation with a receiver operating characteristic (ROC), average precision (AP), and F-Score of 0.89, 0.91, and 0.85 respectively on the final multimodal results. This approach raises the F-score from the previously achieved value of 0.508 to 0.85, creating a new baseline of what is achievable with multimodal lung cancer diagnostics and possible methods to achieve these accuracies.

The study delves into the critical examination of the Size of Loss distribution patterns in the context of auto insurance during pre- and post-pandemics, emphasizing their profound influence on insurance pricing and regulatory frameworks. Through a comprehensive analysis of the historical Size of Loss data, insurers and regulators gain essential insights into the probabilities and magnitudes of insurance claims, informing the determination of precise insurance premiums and the management of case reserving. This approach aids in fostering fair competition, ensuring equitable premium rates, and preventing discriminatory pricing practices, thereby promoting a balanced insurance landscape. The research further investigates the transformative impact of the COVID-19 pandemic on these Size of Loss patterns, given the substantial shifts in driving behaviors and risk landscapes. Also, the research contributes to the literature by addressing the need for more studies focusing on the implications of the COVID-19 pandemic on pre- and post-pandemic auto insurance loss patterns, thus offering a holistic perspective encompassing both insurance pricing and regulatory dimensions.

Infertility affects millions worldwide, posing a significant global health challenge. The proteomic analysis of follicular fluid provides a comprehensive view of the complex molecular landscape within ovarian follicles, offering valuable information on the factors influencing oocyte development and on the overall reproductive health. The follicular fluid is derived from the plasma and contains various proteins that can have different roles in oocyte health and infertility and this fluid is a critical microenvironment for the developing oocytes as well. Using HPLC/MS method we investigated the protein composition of the follicular fluid and after classification we did relative quantification of the identified proteins in the pregnant (P) and non-pregnant (NP) groups. Based on the protein-protein interaction analysis ALB and ApoA1 was found to be hub proteins and the quantitative comparison of the P and NP groups resulted significantly lower concentration of ApoA1 and HDL-cholesterol in the P group. As both molecules are involved in the cholesterol transport, we also investigated their role in the development of oocytes and in the prediction of fertility.

This article presents a forecast model that uses a hybrid architecture of recurrent neural networks (RNN) with surface neural networks (ANN), based on historical records of exported active energy (EAE) and weather data. Two types of models were developed: the first type includes six models that use EAE records and weather variables as inputs, while the second type includes eight models that use only weather variables. Different metrics were applied to assess the performance of these models, and the best model of each type was selected. Finally, a comparison of the performance between the selected models of both types is presented, and they are validated with real data provided by a solar plant, achieving acceptable levels of accuracy. The selected model of the first type has an RMSE of 0.19, MSE of 0.03, MAE of 0.09, a correlation coefficient of 0.96, and a determination coefficient of 0.93. The other selected model of the second type showed lower precision in the metrics (RMSE = 0.24, MSE = 0.06, MAE = 0.10, Corr. Coef. = 0.95, and Det. Coef. = 0.90). Both models demonstrated good performance and acceptable accuracy in forecasting the weekly photovoltaic energy production of the solar plant.

The study is based on the notion that big data predictive analytics is important for developing strategic alliances performance of companies. this study investigates the relationship between big data predictive analytics, big data culture, and competitive strategies 'techniques were adopted, such as descriptive statistics, correlation,regression, etc. using SPSS and SmartPLS statistical software. Hypotheses were tested with bootstrapped analysis using SEM (through SmartPLS). The study developed a structural equation model by using the SEM analysis. The results of the SEM analysis suggested the hypothesized model of the study was valid. The results supported all the hypotheses of the study.Through empirical analysis, demonstrated the conclusion is that the big data predictive analytics has a positive and significant relationship with strategic alliance performance

This work presents a nonlinear model predictive control scheme that challenges overcoming the obstacles holding back over decades to develop affordable autonomous control and monitoring systems applied in the large-scale industry. Among the numerous proposals in the literature, most do not consider the significant fluctuation of kinetic parameters in the reduced mathematical model ADM2, widely used for control and monitoring purposes. The prevalent cause, on a basis, is the lack of information caused by some dynamics and parameters that cannot be measured in real-time by reliable sensors. In addition, to make matters worse, those systems inherently act with nonlinear nature and have a high sensitiveness to uncontrollable inputs and perturbations. Therefore, to prevent these drawbacks, this work proposes a new methodology that reconstructs the lack of information from the non-measurable dynamics, concentration of bacterias, and the kinetic parameters related to reaction rates. Simulations results demonstrate the effectiveness of the methodology compared with traditional industrial control schemes.

One of the most important challenges in the Machine and Deep Learning areas today is to build good models using small datasets, because sometimes it is not possible to have large ones. Several techniques have been proposed in the literature to address this challenge. This paper aims at studying the different available Deep Learning techniques and performing a thorough experimentation to analyze which technique or combination thereof improves the performance and effectiveness of the models. A complete comparison with classical Machine Learning techniques was carried out, to contrast the results obtained using both techniques when working with small datasets. Thirteen algorithms were implemented and trained using three different small datasets (MNIST, Fashion MNIST, and CIFAR-10). Each experiment was evaluated using a well-established set of metrics (Accuracy, Precision, Recall, F1, and the Matthews correlation coefficient). The experimentation allowed concluding that it is possible to find a technique or combination of them to mitigate a lack of data, but this depends on the nature of the dataset, the amount of data, and the metrics used to evaluate them.

Persistent Pain after Spinal Surgery can be successfully addressed by Spinal Cord Stimulation (SCS). International guidelines strongly recommend that a lead trial be performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears that patient outcomes, WITH OR WITHOUT lead trial, are similar. In contrast, during trialing, infection rate drops drastically within time and can compromise the therapy. Using composite pain assessment experience and previous research, we hypothesized that ma-chine learning models could be robust screening tools and reliable predictors of long-term SCS efficacy. We developed several algorithms including logistic regression, Regularized Logistic Regression (RLR), naive Bayes classifier, artificial neural networks, random forest and gradient boosted trees to test this hypothesis and to perform internal and external validations, the objec-tive being to confront model predictions with lead trial results using a 1-year composite out-come from 103 patients. While almost all models have demonstrated superiority on lead trial-ing, the RLR model appears to represent the best compromise between complexity and inter-pretability in prediction of SCS efficacy. These results underscore the need to use AI based-predictive medicine, as a synergistic mathematical approach, aimed at helping implanters to optimize their clinical choices on daily practice.

The strategy of any organization is based on the growth of its customer base, and one of its principles is that selling a product to an existing customer is much more profitable than acquiring a new customer. However, this approach has several opportunities for improvement, since it usually has a totally reactive approach, which does not give opportunity to the areas specialized in customer experience and recovery, to give an effective response for that moment, since the customer is gone at the time of the intervention. This happens because usually a diagnostic analysis of customers who have stopped buying products or services in a defined period, commonly three (3) periods or months, is performed. This thesis work challenges the way to face this problem, and proposes the development of a complete solution, which does not focus exclusively on the prediction of churn, as is usually done in the state of the art research, but to intervene in different interactions that can be carried out with customers. The above focused not only to prevent customer churn, but to generate an added value of continuous improvement in sales processes, increase customer penetration, leading to an improvement in customer experience and consequently, an increase in customer loyalty.

In this paper, the power quality of interconnected microgrids is managed using a Model Predictive Control (MPC) methodology which manipulates the power converters of the microgrids in order to achieve the requirements. The control algorithm is developed for the microgrids working modes: grid-connected, islanded and interconnected. The results and simulations are also applied to the transition between the different working modes. In order to show the potential of the control algorithm, a comparison study is carried out with classical Proportional-Integral Pulse Width Modulation (PI-PWM) based controllers. The proposed control algorithm not only improves the transient response in comparison with classical methods but also shows an optimal behavior in all the working modes, minimizing the harmonics content in current and voltage even with the presence of non-balanced and non-harmonic-free three-phase voltage and current systems

Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.

Introduction: Identifying the complexity of palliative care needs is a key aspect of referral to specialised multidisciplinary early palliative care (EPC) teams. The PALCOM scale is an instrument consisting of five multidimensional assessment domains, developed in 2018 and validated in 2023, to identify the level of complexity in patients with advanced cancer. Objectives: The main objective of this study was to determine the degree of instability (likelihood of level change or death), health resource consumption and survival of patients according to the level of palliative complexity assigned at the baseline visit during a 6-month follow-up. Method: An observational, prospective, multicentre study was conducted using pooled data from the development and validation cohort of the PALCOM scale. The main outcome variables were: a) instability ratio (IR), defined as the probability of level change or death; b) emergency department visits; c) days of hospitalisation; d) hospital death; e) survival. All variables were analysed monthly according to the level of complexity assigned at the baseline visit. Results: A total of 607 patients with advanced cancer were enrolled. According to the PALCOM scale, 20% of patients were classified as low complexity, 50% as medium and 30% as high complexity. The overall IR was 45% in the low complexity group, 68% in the medium complexity group and 78% in the high complexity group (p

This research explores the transformative impact of artificial intelligence (AI) on personalizing marketing campaigns, highlighting how AI technologies are reshaping modern marketing practices. AI tools such as machine learning, natural language processing (NLP), predictive analytics, deep learning, and computer vision are integral to enhancing customer engagement and optimizing marketing strategies. Machine learning algorithms enable precise customer segmentation and personalized recommendations, leading to more targeted and effective marketing messages. NLP facilitates the analysis of customer sentiment and enhances communication through advanced language processing and AI-powered chatbots. Predictive analytics and deep learning provide businesses with the capability to forecast customer behaviors and recognize complex data patterns, further refining marketing efforts. Computer vision technology contributes to personalization through innovations like visual search and augmented reality, creating immersive customer experiences. Despite the numerous benefits, the adoption of AI in marketing presents several challenges. Data privacy and security concerns, integration complexities, and the potential for algorithmic bias are critical issues that need to be addressed. Ethical considerations, including transparency and fairness in data usage, are also paramount to maintaining customer trust and ensuring responsible AI application. The future of AI in marketing promises continued advancements, with trends such as hyper-personalization and enhanced integration with technologies like the Internet of Things and voice search expected to drive further innovation. Overall, AI significantly enhances marketing effectiveness by offering tailored solutions and strategic insights while necessitating a thoughtful approach to ethical and practical challenges.

This qualitative research investigates how supply chain innovations drive marketing differentiation in consumer goods companies. In a competitive global marketplace, firms are increasingly leveraging advanced supply chain management (SCM) practices to enhance operational efficiency and create distinctive market positions. The study explores five key supply chain innovations—digitalization, sustainability practices, predictive analytics, agile supply chain models, and collaborative partnerships—and their impact on marketing differentiation strategies. Data were collected through semi-structured interviews with 20 executives and managers from leading consumer goods companies, analyzing themes related to innovation adoption, challenges, and outcomes. Findings indicate that digital technologies such as IoT, AI, and blockchain are pivotal in improving supply chain visibility, optimizing inventory management, and enabling real-time decision-making, thereby supporting personalized customer experiences and agile responses to market dynamics. Sustainability practices, including sustainable sourcing and green logistics, emerge as critical drivers of brand reputation and consumer trust, aligning with growing consumer preferences for eco-friendly products. Predictive analytics facilitate better demand forecasting and pricing strategies, while agile supply chain models enhance flexibility and responsiveness in delivering products faster to market. Despite benefits, challenges include integrating innovations with legacy systems, managing resistance to change, and addressing data security concerns. Strategies for overcoming these barriers include leadership commitment, cross-functional collaboration, talent development, and strategic partnerships. By embracing these strategies and innovations, consumer goods companies can strengthen their competitive positioning, enhance customer satisfaction, and achieve sustainable growth in a rapidly evolving marketplace.

Non-neural Machine Learning (ML) and Deep Learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three data sets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM and Transformers) are compared using multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure.

Carbon Capture and Storage (CCS) stands as a pivotal technological stride toward a sustainable future, with the practice of injecting supercritical CO2 into subsurface formations having already been an established practice for enhanced oil recovery operations. The overarching objective of CCS is to protract the operational viability and sustainability of platforms and oilfields, thereby facilitating a seamless transition towards sustainable practices. This study introduces a comprehensive framework for optimizing well placements in CCS operations, employing a derivative-free method known as Bayesian optimization. The development plan is tailored for scenarios featuring aquifers devoid of flow boundaries, incorporating production wells tasked with controlling pressure buildup and injection wells dedicated to CO2 sequestration. Notably, the wells operate under group control, signifying predefined injection and production targets and constraints that must be adhered to throughout the project’s lifespan. As a result, the objective function remains invariant under specific permutations of the well locations. Our investigation delves into the efficacy of Bayesian optimization under the introduced permutation invariance. The results reveal that it demonstrates critical efficiency in handling the optimization task extremely fast. In essence, this study advocates for the efficacy of Bayesian optimization in the context of optimizing well placements for CCS operations, emphasizing its potential as a preferred methodology for enhancing sustainability in the energy sector.

A Digital Twin (DT) refers to a virtual representation or digital replica of a physical object, system, process, or entity. This concept involves creating a detailed, real-time digital counterpart that mimics the behavior, characteristics, and attributes of its physical counterpart. DTs have the potential to improve efficiency, reduce costs, and enhance decision-making by providing a detailed, real-time understanding of the physical systems they represent. While this technology is finding application in numerous fields, such as energy, healthcare, transportation, it appears to be a key component of the digital transformation of industries. In this paper, we present the research results achieved by IoTwins, a European research project aimed at investigating opportunities and issues of adopting DTs in the fields of industrial manufacturing and facility management. Particularly, we discuss a DT model and a reference architecture for use by the research community to implement a platform for the development and deployment of industrial DTs in the cloud continuum. Guided by the devised architectures’ principles, we implemented an open platform and a development methodology to help companies build DT-based industrial applications and deploy them in the so-called Edge/Cloud continuum. To prove the research value and the usability of the implemented platform, we discuss a simple yet practical development use case.

The Ames/quantitative structure-activity relationship (QSAR) International Challenge Projects held during 2014–2017 and 2020–2022, evaluated the performance of various predictive models. Despite the significant insights gained, the rules allowing participants to select prediction targets introduced ambiguity in model performance evaluation. This reanalysis identified the highest-performing prediction model, assuming a 100% coverage rate (COV) for all prediction target compounds and an estimated performance variation due to changes in COV. All models from both projects were evaluated using balance accuracy (BA), Matthews correlation coefficient (MCC), F1 Score (F1), and the first principal component (PC1). After normalizing the COV, a correlation analysis with these indicators was conducted, and the evaluation index for all prediction models in terms of the COV was estimated. In total, 109 models, the highest estimated BA (76.9) at 100% COV was MMI-VOTE1, reported by Meiji Pharmaceutical University (MPU). The best models for MCC, F1, and PC1 were all MMI-STK1, also reported by MPU. All models reported by MPU ranked in the top four. MMI-STK1 was estimated to have F1 scores of 59.2, 61.5, and 63.1 at COV levels of 90%, 60%, and 30%, respectively. These findings highlight the current state and potential of the Ames prediction technology.

The paper deals with the Model Predictive Control (MPC) algorithm as applied to the sensorless control of a Permanent Magnet Synchronous Motor (PMSM). The proposed estimation strategy, based on the unscented Kalman filter (UKF), uses only the measurement of the motor current for the online estimation of speed, rotor position and load torque. Information about the system state feeds the MPC. Results verify the effectiveness and applicability of the proposed sensorless control technique. An implementation in low speed direct drive astronomy telescope mount systems is investigated.

In this paper, the problem of autonomous optimal absolute orbit keeping for a satellite mission in Low Earth Orbit using electric propulsion is considered. The main peculiarity of the approach is to support small satellite missions in which the platform is equipped with a single thruster nozzle which provides acceleration on a single direction at a time. This constraint implies that an attitude maneuver is necessary before or during each thrusting arc to direct the nozzle into the desired direction. In this context, an attitude guidance algorithm specific for the orbit maneuver has been developed. A Model Predictive Control scheme is proposed, where the attitude kinematics are coupled with the orbital dynamics in order to obtain the optimal guidance profiles in terms of satellite state, reference attitude, and thrust magnitude. The proposed control scheme is developed exploiting Formation Flying techniques where the reference orbit is that of a virtual spacecraft that the main satellite is required to rendezvous with. In addition to the controller design, the closed loop configuration is presented supported by numerical simulations. The efficacy of the proposed autonomous orbit keeping approach is shown in several application scenarios.

In this study, a novel two-layer control scheme aimed at enhancing the dynamic performance of a nonlinear vehicle through the utilization of an optimal control approach grounded in predictive control principles is presented. The first layer of our control system focuses on the computation of an optimized rotational torque that ensures lateral dynamic stability. This torque is subsequently translated into differential forces acting on the wheels, employing the inverse tire model to derive the desired longitudinal slips. These slip values are then transmitted to the second layer of our control system. In the second layer, the electric motors associated with the vehicle's wheels dynamically adjust the input torque to accurately track the desired slip, thereby ensuring the overall stability of the electric vehicle. In view of the paramount importance of energy consumption in electric vehicles, we adopt optimal control strategies to substantially minimize battery utilization. To this end, careful selection of appropriate weighting coefficients in the control laws enables us to maintain the electric motors within their permissible operational range while simultaneously minimizing battery energy consumption for desired slip tracking. Extensive simulation results validate the effectiveness of our proposed control system in proficiently managing nonlinear effects and safeguarding the vehicle's stability.

This paper presents designing an attitude motion control strategy for a half-car model using an anti-jerk predictive controller. Anti-jerk predictive controller based on active aerodynamics surfaces is employed to deal with the anticipated future road maneuvers and improve vehicle ride performance by canceling out external jerks acting on the vehicle body. The body jerks are produced during vehicle traversing on a double lane-change maneuver, acceleration, or braking. The control strategy helps the vehicle to achieve a realistic operation of the active aerodynamic surface to improve the vehicle’s ride performance, i.e., ride comfort and road holding during cornering, acceleration, or braking. The anti-jerk predictive controller is developed based on the predictive control strategy, which predicts future road inputs and uses them to compensate for the vehicle’s attitude motion. The simulation results show that the proposed control strategy effectively reduces the effects of vehicle body jerks transmitted to the passengers, improving ride comfort without degrading vehicle handling. The anti-jerk predictive controller successfully tracks the desired attitude position by canceling the external body jerks.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This thesis work challenges the way to face this problem, and pro- 12 poses the development of a complete solution, which does not focus exclusively on the prediction 13 of churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

The strategy of any organization is based on the growth of its customer base, and one of 6 its principles is that selling a product to an existing customer is much more profitable than acquiring 7 a new customer. However, this approach has several opportunities for improvement, since it usu- 8 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 9 customer experience and recovery, to give an effective response for that moment, since the customer 10 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 11 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 12 riods or months, is performed. This paper challenges the way to face this problem, and proposes 13 the development of a complete solution, which does not focus exclusively on the prediction of 14 churn, as is usually done in the state of the art research, but to intervene in different interactions 15 that can be carried out with customers. The above focused not only to prevent customer churn, but 16 to generate an added value of continuous improvement in sales processes, increase customer pene- 17 tration, leading to an improvement in customer experience and consequently, an increase in cus- 18 tomer loyalty.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This paper challenges the way to face this problem, and proposes 12 the development of a complete solution, which does not focus exclusively on the prediction of 13 churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

Monitoring volatile organic compounds (VOCs) places a crucial role in environmental pollutants control and indoor air quality. In this study, a metal-oxide (MOx) sensor detector (used in a commercially available monitor) was employed to delineate the composition of air containing three common VOCs (ethanol, acetone and hexane) under various concentrations. Experiments with a single component and double components were conducted to investigate how the solvents interact with the metal oxide sensor. The experimental results revealed that the affinity between VOC and sensor was in the following order: acetone > ethanol > n-hexane. A mathematical model was developed, based on the experimental findings and data analysis, to convert the output resistance value of the sensor into concentration values, which in turn can be used to calculate a VOC-based air quality index. Empirical equations were established based on inferences of vapor composition versus resistance trends, and on an approach of using original and diluted air samples to generate two sets of resistance data per sample. The calibration of numerous model parameters allowed matching simulated curves to measured data. As such, the predictive mathematical model enabled quantifying not only the total concentration of sensed VOCs, but also estimating the VOC composition. This first attempt to obtain semi-quantitative data from a single MOx sensor, despite remaining selectivity challenges, is aimed at expanding the capability of mobile air pollutants monitoring devices.

The aim of this study was to develop and validate a predictive early tooth loss multivariable model for periodontitis patients before periodontal treatment. A total of 544 patients seeking periodontal care at a university dental hospital were enrolled in the study. Teeth extracted after periodontal diagnosis and due to periodontal reasons were recorded. Clinical and sociodemographic variables were analyzed, considering the risk of short-term tooth loss. This study followed the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines for development and validation, with two cohorts considered as follows: 455 patients in the development phase and 99 in the validation phase. As a result, it was possible to compute a predictive model based on tooth type and clinical attachment loss. The model explained 25.3% of the total variability and correctly ranked 98.9% of the cases. The final reduced model area under the curve (AUC) was 0.809 (95% Confidence Interval (95% CI): 0.629 - 0.989) for the validation sample and 0.920 (95% CI: 0.891 - 0.950) for the development cohort. The established model presented adequate prediction potential of early tooth loss due to periodontitis. This model may have clinical and epidemiologic relevance towards the prediction of tooth loss burden.

Although decision making strategy based on clinico-histopathological criteria is well established, renal cell carcinoma (RCC) represents a spectrum of biological ecosystems characterized by distinct genetic and molecular alterations, diverse clinical courses and potential specific therapeutic vulnerabilities. Given the plethora of drugs available, the subtype-tailored treatment to RCC subtype holds the potential to improve patient outcome, shrinking treatment-related morbidity and cost. The emerging knowledge of the molecular taxonomy of RCC is evolving, whilst the antiangiogenic and immunotherapy landscape maintained and reinforced their potential. Although several prognostic factors of survival in patients with RCC have been described, no reliable predictive biomarkers of treatment individual sensitivity or resistance have been identified. In this review, we summarize the available evidence able to prompt more precise and individualized patient selection in well-designed clinical trials, covering the unmet need of medical choices in the era of next-generation anti-angiogenesis and immunotherapy.

A new model predictive control (MPC) algorithm is used to select optimal air conditioning setpoints for a commercial office building, considering variable electricity prices, weather, occupancy and lighting. This algorithm, Cost-Comfort Particle Swarm Optimization (CCPSO), is the first to combine a realistic, smooth representation of occupants’ willingness to pay for thermal comfort with a bottom-up, non-linear model of the building and air conditioning system under control. We find that using a quadratic preference function for temperature can yield solutions that are both more comfortable and lower-cost than previous work that used a ``brick wall'' preference function with no preference for further cooling within an allowed temperature band and infinite aversion to going outside the allowed band. Using historical pricing data for a summer month in Chicago, CCPSO provided a 3\% reduction in costs vs. a ``brick-wall'' MPC approach with similar comfort and 13\% reduction in costs vs. a standard night setback strategy. CCPSO also reduced peak-hours demand by 3\% vs. the ``brick-wall'' strategy and 15\% vs. standard night-setback. At the same time, the CCPSO strategy increased off-peak energy consumption by 15\% vs. the ``brick-wall'' strategy. This may be valuable for power systems integrating large amounts of renewable power, which can otherwise become uneconomic due to saturation of demand during off-peak hours.

Predictive maintenance technologies have emerged as a transformative force in retail supply chain management, offering the potential to significantly enhance operational efficiency, reduce costs, and improve customer satisfaction. This study explores the implementation and impact of predictive maintenance within the retail sector, focusing on its benefits, challenges, technological tools, and future directions. The findings indicate that predictive maintenance enables a proactive approach to equipment management, leading to substantial reductions in downtime and maintenance costs, extended equipment lifespan, and enhanced sustainability through reduced energy consumption and waste. However, the adoption of these technologies is not without challenges. High initial costs, the need for specialized skills in data analytics and IoT, issues with data quality and reliability, organizational resistance, and cybersecurity concerns present significant barriers to successful implementation. Technological tools such as IoT sensors, data analytics platforms, machine learning algorithms, and digital twins are crucial for the effective functioning of predictive maintenance systems, providing real-time data monitoring and analysis that improve decision-making and maintenance planning. The study also highlights promising future trends, including advancements in AI, machine learning, IoT, and blockchain technologies, which are expected to further enhance predictive maintenance capabilities. To fully realize the potential of predictive maintenance, companies must address the identified challenges, invest in workforce development, and implement robust data security measures. Future research should focus on exploring these advancements, understanding the broader environmental impacts, and conducting cross-industry analyses to identify best practices. Overall, while predictive maintenance offers substantial benefits, its successful integration requires a nuanced approach that balances technological innovation with strategic and operational considerations.

The rapid progress in renewable energy sources and the increasing complexity of energy distribution networks have highlighted the need for efficient and intelligent energy management systems. This paper presents a comparative analysis of two optimisation algorithms, P and M70, used for the optimal control of the operation of microgrids in islanded mode. The main objective is to minimise production costs while ensuring a reliable energy supply. Algorithm P prioritises the use of photovoltaic (PV) and battery storage and operates the diesel generator at minimum capacity to reduce fuel consumption and maximise the use of renewable energy sources. Algorithm M70, on the other hand, uses a heuristic approach to adaptively manage energy resources in real time. In this study, the performance of both algorithms is evaluated through simulation in different operating scenarios. The results show that both algorithms significantly improve the efficiency of the microgrid, with the M70 algorithm showing better adaptability and cost efficiency in dynamic environments. This research contributes to ongoing efforts to develop robust and scalable energy management systems for future smart grids.

Due to the manufacturing process of Additive Manufacturing (AM) Parts the mechanical properties cannot be predicted. The scope of the present work is to propose a predictive tool for the mechanical properties of AM parts through the use of Adaptive Neuro-Fuzzy Inference System (ANFIS). The Adaptive Neuro-Fuzzy Inference System (ANFIS) combines neural networks with fuzzy logic to generate a mapping between the inputs and the output. Real data experiments from different AM technologies and materials compose the initial dataset so a detailed investigation is conducted to gain knowledge of how different parameters affect the UTS, the elongation and the Young modulus of each experiment. Experimental data were also use to train, check and verify the methodology. The method is tested for FFF technology, PLA material and 3 point bending stress, with interesting results.

Accurate streamflow forecasting is crucial for effectively managing water resources, particularly in countries like Colombia, where hydroelectric power generation significantly contributes to the national energy grid. Although highly interpretable, traditional deterministic, physically-driven models often suffer from complexity and require extensive parameterization. Data-driven models like Linear Autoregressive (LAR) and Long Short-Term Memory (LSTM) networks offer simplicity and performance but cannot quantify uncertainty. This work introduces Sparse Variational Gaussian Processes (SVGPs) for forecasting streamflow contributions. The proposed SVGP model reduces computational complexity compared to traditional Gaussian Processes, making it highly scalable for large datasets. The methodology employs optimal hyperparameters and shared inducing points to capture short-term and long-term relationships among reservoirs. Training, validation, and analysis of the proposed approach consider the streamflow dataset from 23 geographically dispersed reservoirs recorded during twelve years in Colombia. Performance assessment reveals that the proposal outperforms baseline Linear Autoregressive (LAR) and Long Short-Term Memory (LSTM) models in three key aspects: adaptability to changing dynamics, provision of informative confidence intervals through Bayesian inference, and enhanced forecasting accuracy. Therefore, the SVGP-based forecasting methodology offers a scalable and interpretable solution for multi-output streamflow forecasting, thereby contributing to more effective water resource management and hydroelectric planning.