The integration of supply chain data analytics with marketing strategies has become increasingly critical for organizations seeking to enhance customer insights and competitive advantage in today's dynamic business environment. This qualitative research explores the intersection of these two disciplines, focusing on implementation strategies, benefits, challenges, and future directions. Through semi-structured interviews with industry experts and stakeholders, key themes emerged, highlighting the importance of cross-functional collaboration, technological integration, and robust data governance in achieving effective integration. The study identifies significant benefits, including enhanced customer insights, improved operational efficiencies, and competitive advantage through personalized marketing strategies and optimized supply chain management. However, challenges such as data silos, technological complexities, and regulatory compliance issues pose barriers that require strategic solutions and organizational commitment. Future directions point towards the continued evolution of predictive analytics, AI-driven solutions, and sustainability integration, shaping the future landscape of supply chain management and marketing. Proactive engagement with regulatory frameworks and ethical considerations will be crucial in navigating these challenges and building trust with consumers. Ultimately, this research contributes to a deeper understanding of how organizations can leverage data analytics to drive strategic decision-making, enhance customer relationships, and achieve sustainable growth in an increasingly data-driven economy.

Machine learning has become more prevalent as a tool used for biogeochemical analysis in agricultural management. However, a common drawback of machine learning models is the lack of interpretability, as they are black boxes that provide little insight into agricultural management. To overcome this limitation, we compared three tree-based models (decision tree, random forest, and gradient boosting) to explain soil organic matter content through Shapley additive explanations (SHAP). Here, we used nationwide data on field crops, soil, terrain, and climate across South Korea (n = 9,584). Using the SHAP method, we identified common primary controls of the models, for example, regions with precipitation levels above 1400 mm and exchangeable potassium levels exceeding 1 cmol+ kg-1, which favor enhanced organic matter in the soil. Different models identified different impacts of nutrients on the organic matter level in the soil. The SHAP method is practical for assessing whether different machine learning models yield consistent findings in addressing these inquiries. Increasing the explainability of these models means determining essential variables related to soil organic matter management and understanding their associations for specific instances.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multiclass classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, it’s detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.

In this paper, we discuss the most significant application opportunities and outline the challenges in performing a real-time and energy-efficient management of the distributed resources available at mobile devices and Internet-to-Data Center. We also present an energy-efficient adaptive scheduler for Vehicular Fog Computing (VFC) that operates at the edge of a vehicular network, connected to the served Vehicular Clients (VCs) through an Infrastructure-to-Vehicular (I2V) over multiple Foglets (Fls). The scheduler optimizes the energy by leveraging the heterogeneity of Fls, where the Fl provider shapes the system workload by maximizing the task admission rate over data transfer and computation. The presented scheduling algorithm demonstrates that the resulting adaptive scheduler allows scalable and distributed implementation.

Abstract: Intensity of natural and man-made disasters is increasing day by day. Disaster is one of the major threats that affects the sustainable development of tourist attractions. Big data and Internet of Things(IoT) will greatly improve the disaster management. Based on the Big Data and IoT, a tourism attraction disaster management system is designed, divided into several stages namely pre-disaster early warning prevention, disaster mitigation, recovery and reconstruction after disaster and updating disaster planning. Then, the system flow is analysed, as well as the system structure is constructed. Additional, system function and its operation flow are introduced, including disaster warning, disaster relief, disaster assessment, real-time monitoring and supporting disaster planning functions. Finally, an application case is introduced. Research intends to improve tourism area disasters management.

As time continues to advance, the need for robust security threat mitigation has become increasingly vital in software. However, ensuring early effective security threat mitigation requires optimal test data and consistent test case design. It is a constant struggle to maximize test coverage through test data optimization. We conducted explanatory research to maximize test coverage of security requirements as modeled in Structured Misuse Case Description (SMCD) i.e., structured specification of misuse case, so as to improve consistency in optimal test data generation. We specified constraints upon Mal activity in Object Constraint Language (OCL) in order to minimize human dependency and improve consistency in optimal test data generation. It was evident through results that MC/DC generated optimal test data of security threats through SMCD in comparison to the Decision Coverage method thus resulting in designing a significantly lower number of test cases and yet maximizing test coverage of security threats. MC/DC generated test data with n+1, while Decision Coverage generated test data with〖 2〗^n, we, therefore, conclude that MC/DC maximizes test coverage through optimal test data from SMCD in comparison to Decision Coverage.

Previous studies demonstrate the critical importance of non-coding RNAs interfacing with chromatin-modifying machinery resulting in promoter-enhancer-based gene regulation and raise the possibility that many other enhancer-like RNAs may operate via similar mechanisms. Critically, more than 80% of the disease-linked variations identified in genome-wide studies are located in the non-coding regions of genomes, especially non-coding RNA, suggesting non-coding RNAs are relevant to disease. Thus, a critical path forward for understanding non-coding RNAs' role, especially long non-coding RNAs, is to understand the genomic regions' transcriptional regulation, especially non-coding regions. Here, we developed a user-friendly R package called SomaGene for studying and identifying enhancer-like non-coding RNAs with enriched somatic mutations in the cancer genome. SomaGene accepts different genomic variants (whole genome/exome somatic point mutations, structural variations, copy number variations) to identify those RNAs that significantly mutated in diseases (e.g., cancer). It then uses multiple publicly available genomics and epigenetics datasets including ENCODE epigenomics annotations, FANTOM5 tissue-specific expression profiles, disease-associated genome-wide association SNPs, and tissue-specific eQTL pairs to identify those RNAs with potentially enhancer function. SomaGene, as a powerful R package, can provide the opportunity to cancer scientists to study the roles of non-coding RNAs in different cancer genomes.

The aim of this paper is to apply all the existing pyranometric method, to estimate the sunshine duration from the global solar irradiation, in order to find in their original form the most suitable method for a tropical site. Then, in a second step, one of these methods will be optimized to well fit tropical sites. Five methods in the literature (Step Algorithm, Carpentras Algorithm, Slob & Monna Algorithm, Slob & Monna 2 Algorithm, and Linear Algorithm) were applied with eleven years of global and diffuse solar radiation data. As a result, in their original form, the Step Algorithm is on the first rank. But in the second step, after improving its main coefficients, the Carpentras Algorithm was found to be the best algorithm for tropical site in the southern hemisphere.

(1) Background: Targeted (TT) and immune checkpoint inhibitor (ICI) therapies have become available in the routine care of metastatic melanoma in recent years. (2) Objective: We compared mortality in patients with metastatic melanoma and different systemic therapies. (3) Methods: A retrospective cohort study, based on pseudonymized health insurance data of about 2 million individuals from Saxony, Germany, was conducted for the years 2010 to 2020. Only patients with an advanced stage, i.e. distant metastases were considered for the main analysis. Relative survival since metastasis and predicted survivor curves derived from a Cox model were used to assess potential differences in mortality. (4) Results: Relative survival was highest in the subgroup with sequential use of ICI and TT. All treatments except interferon had significant hazard ratios (HR) in the Cox model with time-dependent effects indicating a protective effect after treatment initiation (HR 0.01-0.146) but decreasing over time (HR 1.351-2.310). The predicted survivor curves revealed best survival under ICI-TT treatment and worst survival under TT treatment alone. (5) Conclusions: We found real-world evidence for survival benefits of patients with metastatic melanoma who received sequential ICI and TT treatment. It is conceivable that the observed high survival differences were overestimated due to bias, such as confounding by indication.

Ethnopharmacology experts face several challenges when identifying and retrieving documents and resources related to their scientific focus. The volume of sources that need to be monitored, the variety of formats utilized, the different quality of language use across sources, present some of what we call “big data” challenges in the analysis of this data. This study aims to understand if and how experts can be supported effectively through intelligent tools in the task of ethnopharmacological literature research. To this end, we utilize a real case study of ethnopharmacology research, aimed at the Southern Balkans and Coastal zone of Asia Minor. Thus, we propose a methodology for more efficient research in ethnopharmacology. Our work follows an “Expert-Apprentice” paradigm in an automatic URL extraction process, through crawling, where the apprentice is a Machine Learning (ML) algorithm, utilizing a combination of Active Learning (AL) and Reinforcement Learning (RL), and the Expert is the human researcher. ML-powered research improved 3.1 times the effectiveness and 5.14 times the efficiency of the domain expert, fetching a total number of 420 relevant ethnopharmacological documents in only 7 hours versus an estimated 36-hour human-expert effort. Therefore, utilizing Artificial Intelligence (AI) tools to support the researcher can boost the efficiency and effectiveness of the identification and retrieval of appropriate documents.

Cloud computing transformed IT organizations with its on-demand model, notably Infrastructure as a Service (IaaS). Cloud providers manage extensive physical devices, consuming substantial energy and bandwidth for data traffic during virtual machine deployment. Balancing energy and bandwidth are critical. This thesis presents BOHGOA integrated with ACO to optimize virtual machine placement in clouds, simultaneously considering bandwidth and energy. It yields Pareto-optimal solutions for this trade-off. Using CloudSim, BOHGOA outperformed GA, ACO, and FFD algorithms, reducing bandwidth consumption by 54.14%, 32.11%, 57.47% (240 VMs) and 38.12%, 22.76%, 47.05% (500 VMs) respectively. Additionally, it decreased physical machine energy usage by 37.70%, 34.01%, 40.14% (240 VMs) and 27.50%, 22.28%, 30.52% (500 VMs) respectively. These results underscore BOHGOA's effectiveness in optimizing cloud VM placement.

This research explores the feasibility of a data-driven optimization algorithm for placing sparse arrays of artificial hair-cell airflow velocity sensors to enable agile and robust flight-by-feel control of unmanned aircraft. The Sparse Sensor Placement Optimization for Prediction (SSPOP) algorithm exploits the information-rich features of large flow datasets to find a near-optimal set of locations for flow sensors on a wing. The flow information from these sensors can be used to predict flight state parameters such as the angle of attack, mimicking the fly-by-feel control systems observed in nature. We evaluate the effectiveness of this approach for a blunt-edged 45∘ swept delta wing. Exploiting the information in the complex airflow patterns over this wing, the SSPOP algorithm selects a sensor location design point (DP) which reliably ranks within the top 1% of all possible DPs by root mean square error in angle of attack prediction. This performance was consistent across models of various artificial hair lengths, and one model with variable hair lengths. This bioinspired dimension-reducing method for sensor placement optimization exhibits reliability and flexibility benefits when compared with a conventional greedy search algorithm and gradient-based optimization using auto-differentiation. The successful application of SSPOP in complex 3D flows paves the way for experimental evaluation of data-driven sparse sensor placement optimization for artificial hair-cell airflow sensors and is a major step toward biomimetic flight-by-feel.

The development of knowledge graphs for water resources as a tool for studying sustainable regional development is a relevant task, as the increasing deterioration of water bodies affects the ecology, economy of the country, as well as the health of the population living near water bodies. Solving this problem requires the development of water resource monitoring methods based on semantic data analysis is required to detect and track sources of pollution and provide recommendations to support decision-making. This research proposes a method of semantic analysis for modeling knowledge graphs and constructing rules that enable the integration of data from heterogeneous sources, semantic compatibility, support for reasoning and inference, facilitate queries and search, and represent knowledge in the field of water resource monitoring. As a result, an ontology based on the SWRL language is created, which enables the expression of complex relationships and derivation of new knowledge, SSN for interaction between the ontology and sensor data, and Time Ontology, which models and analyzes information related to temporal aspects.After populating the ontology and establishing logical connections, SPARQL queries are implemented to retrieve new knowledge about water resources.

Internet of Things (IoT) technologies can greatly benefit from machine learning techniques and Artificial Neural Networks for data mining and vice versa. In the agricultural field, this convergence could result in the development of smart farming systems suitable for use as decision support systems by peasant farmers. This work presents the design of a smart farming system for crop production, which is based on low-cost IoT sensors and popular data storage services and data analytics services on the Cloud. Moreover, a new data mining method exploiting climate data along with crop production data is proposed for the prediction of production volume from heterogeneous data sources. This method was initially validated using traditional machine learning techniques and open historical data of the northeast region of the state of Puebla, Mexico, which were collected from data sources from the National Water Commission and the Agri-food Information Service of the Mexican Government.

The role of the databases is to allow persisting data, no matter if they are of the SQL or NoSQL type. In SQL databases, data is structured in a set of tables in the relational database model, grouped in rows and columns. The CRUD operations (create, read, update, and delete) are used to manage the information contained in the relational databases. Several dialects of the SQL language exist, as well as frameworks for mapping Java classes (models) to a relational database. The question is what we should choose for our Java application and why. A comparison between the most used relational database management systems, mixed with the most used frameworks should give us some guidance about when to use what. The evaluation is done on timing for each CRUD operation, from thousands to millions of entries, using the possible combinations between the relational database system and the framework. The experiments included the possibilities to warm up the Java Virtual Machine before the execution of the queries. Also, the research investigated the time spent inside different methods of the code, to determine the critical regions. Thus, the conclusions provide a comprehensive overview of the performances of Java applications accessing databases depending on the suite of decisions considering the database type, the framework in use, the type of operation, and supporting architects and developers for their technological decisions and for improving the speed of their programs.

Serious crime modelling typically needs to be undertaken securely behind a firewall where police knowledge and capabilities can remain undisclosed. Data informing an ongoing incident is often sparse, with a large proportion of relevant data only coming to light after the incident culminates or after police intervene - by which point it is too late to make use of the data to aid real-time decision making for the incident in question. Much of the data that is available to police to support real-time decision making is highly confidential so cannot be shared with academics, and is therefore missing to them. In this paper, we describe the development of a formal protocol where a graphical model is used as a framework for securely translating a model designed by an academic team to a model for use by a police team. We then show, for the first time, how libraries of these models can be built and used for real-time decision support to circumvent the challenges of data missingness and tardiness seen in such a secure environment. The parallel development described by this protocol ensures that any sensitive information collected by police, and missing to academics, remains secured behind a firewall. The protocol nevertheless guides police so that they are able to combine the typically incomplete data streams that are open source with their more sensitive information in a formal and justifiable way. We illustrate the application of this protocol by describing how a new entry - a suspected vehicle attack - can be embedded into such a police library of criminal plots.

Three-dimensional reconstruction plays an important role in assisting doctors and surgeons in diagnosing bone defects’ healing progress. Common three-dimensional reconstruction methods include surface and volume rendering. As the focus is on the shape of the bone, volume rendering is omitted. Many improvements have been made on surface rendering methods like Marching Cubes and Marching Tetrahedra, but not many on working towards real-time or near real-time surface rendering for large medical images, and studying the effects of different parameter settings for the improvements. Hence, in this study, an attempt towards near real-time surface rendering for large medical images is made. Different parameter values are experimented on to study their effect on reconstruction accuracy, reconstruction and rendering time, and the number of vertices and faces. The proposed improvement involving three-dimensional data smoothing with convolution kernel Gaussian size 0.5 and mesh simplification reduction factor of 0.1, is the best parameter value combination for achieving a good balance between high reconstruction accuracy, low total execution time, and a low number of vertices and faces. It has successfully increased the reconstruction accuracy by 0.0235%, decreased the total execution time by 69.81%, and decreased the number of vertices and faces by 86.57% and 86.61% respectively.

Monitoring seaweed growth rates and biomass is crucial for optimizing harvest strategies in aquaculture systems. While such a task can be performed manually on a small farm, such as the Integrated Multi-Trophic Aquaculture (IMTA) system at Harbor Branch Oceanographic Institute at Florida Atlantic University (HBOI), a commercial farm will have to rely on the automated sensor to perform such a task. This study introduces an advanced LSTM-based approach for forecasting seaweed growth and biomass. Utilizing a combination of real and synthetic data, LSTM models are trained and evaluated for their predictive performance. Synthetic sensor data was generated using mathematical equations that simulate realistic aquaculture conditions, with added noise to reflect sensor variability. Building on the foundation of the Pseudorandom Encoded Light for Evaluating Biomass (PEEB) sensor deployed at the seaweed tank in the HBOI IMTA system, we refine the process of biomass estimation by introducing non-linear regression models for predicting seaweed growth and biomass. The results showed that the LSTM model trained with a loss function under physics constraint, combining MSE and physical laws, outperformed models trained with MSE alone, achieving a significantly lower error in predicting seaweed growth. The variation trend of the predicted biomass from the network matched well with the sensor measurement after moving average preprocessing, demonstrating the robustness of the proposed technique in handling noisy sensor data. This study highlights the potential of integrating machine learning with physical models to optimize seaweed cultivation and support sustainable aquaculture practices.

Mobile phones have become an integral part of our lives in the last two decades, leaving a digital trace of our activities and communication. This study aims to develop a data processing framework to evaluate human mobility and socioeconomic status based on call detail records. The methodology proposed first calculates radius of gyration and entropy for each user, then estimates the socioeconomic status by the price and age of the subscribers' phones. Finally, an unsupervised machine learning algorithm was used to group the cells into clusters based on their mobility and socioeconomic metrics. The research showed differences between Buda and Pest during a large scale social event using mobile phone ages and prices. Additionally, the clustering results revealed homogenous groups of cells around Budapest, with similar mobility and socioeconomic metrics. The main conclusion is that mobile network data combined with mobile phone properties offer a useful tool for characterising urban mobility and socioeconomic status.

As a consequence of applying advanced maintenance practices, the theoretical probability of failures is relatively low. However, observation of low market intelligence and maintenance management has been reported. The experimental investigation is supported by findings from a survey targeting asset-intensive companies applying hydraulic power systems. Next, the study incorporates multidimensional data analysis using CA-AHC (Correspondance Analysis with Agglomerative Hierarchical Clustering) approach. The non-parametric machine learning models are used from generated feature subspace to extract features affecting maintenance performance indicators. The results support empirical evidence that equipment age increases the probability of failures. However, the novel findings show that number of maintenance personnel, equipment size measured by nominal working energy consumption, and activities dedicated to maintaining fluid cleanliness impact regression results of companies utilising hydraulic applications.

Due to the digitization and Internet of Things revolutions, the present electronic world has a wealth of cybersecurity data. Efficiently resolving cyber anomalies and attacks is becoming a growing concern in today's cyber security industry all over the world. Traditional security solutions are insufficient to address contemporary security issues due to the rapid proliferation of many sorts of cyber-attacks and threats. Utilizing artificial intelligence knowledge, especially machine learning technology, is essential to providing a dynamically enhanced, automated, and up-to-date security system through analyzing security data. In this paper, we provide an extensive view of machine learning algorithms, emphasizing how they can be employed for intelligent data analysis and automation in cybersecurity through their potential to extract valuable insights from cyber data. We also explore a number of potential real-world use cases where data-driven intelligence, automation, and decision-making enable next-generation cyber protection that is more proactive than traditional approaches. The future prospects of machine learning in cybersecurity are eventually emphasized based on our study, along with relevant research directions. Overall, our goal is to explore not only the current state of machine learning and relevant methodologies but also their applicability for future cybersecurity breakthroughs.

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant scattering information of objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. Although significant progress has been achieved in related research, there are still issues such as insufficient utilization of polarimetric information and features. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features inputted into the deep learning network are the power values of polarimetric channels, where these channels are treated equivalently and contain complete polarimetric information. In terms of experimental comparative study, besides polarimetric power combinations, three different data input schemes were employed as data for the input end of the convolutional neural network (CNN), taking into account existing research. The neural networks utilizes the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of different input schemes. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

5G low-earth orbit satellite communications offer enhanced wireless coverage beyond the reach of 5G terrestrial networks, with important implications, particularly for automated and connected vehicles. Such wireless automotive mass-market applications demand well-designed compact user equipment antenna terminals offering non-terrestrial jointly with terrestrial communications. The antenna should be low-profile, conformal, and meet specific parameter values for gain and operational frequency bandwidth, tailored to the intended applications, in line with the aesthetic design requirements of passenger cars. This work presents an original concept for a dual-band nested circularly polarized automotive user terminal that operates at the S-band frequencies around 3.5 GHz and Ka-band frequencies around 28 GHz, namely within the 5G new-radio bands n78 and n257, respectively. The proposed terminal is designed to be integrated into the plastic components of a passenger vehicle. The arrays consist of 2×2 aperture-coupled corner-truncated microstrip slot patch antenna elements for the n78 band and of 4×4 single-layer edge-truncated microstrip circular slot patch antenna elements for the n257 band. The embedded arrays offer, across the two bands, respectively 9.9 and 13.7 dBi measured realized gain and 3-dB axial ratio bandwidths of 100 and 1500 MHz for the n78 and n257 bands along the broadside direction. Detailed link budget calculations anticipate uplink data rates of 21 and 6 Mbit/s, respectively, deeming it suitable for various automotive mobility and internet-of-things applications.

Ecosystem surveillance monitoring is critical to managing natural resources and especially so under changing environments. Despite this importance, the design and implementation of monitoring programs across large temporal and spatial scales has been hampered by the lack of appropriately standardised methods and data streams. To address this gap, we outline a surveillance monitoring method based on permanent plots and voucher samples suited to rangeland environments around the world that is repeatable, cost-effective, appropriate for large-scale comparisons and adaptable to other global biomes. The method provides comprehensive data on vegetation composition and structure along with soil attributes relevant to plant growth, delivered as a combination of modules that can be targeted for different purposes or available resources. Plots are located in a stratified design across vegetation units, landforms and climates to enhance continental and global comparisons. Changes are investigated through revisits. Vegetation is measured to inform on composition, cover and structure. Samples of vegetation and soils are collected and tracked by barcode labels and stored long-term for subsequent analysis. Technology is used to enhance the accuracy of field methods, including differential GPS r plot locations, instrument based Leaf Area Index (LAI) measures, and three dimensional photo-panoramas for advanced analysis. A key feature of the method is the use of electronic field data collection to enhance data delivery into a publicly-accessible database.Our method is pragmatic, whilst still providing consistent data, information and samples on key vegetation and soil attributes. The method is operational and has been applied at more than 704 field locations across the Australian rangelands as part of the Ecosystem Surveillance program of the Terrestrial Ecosystem Research Network (TERN). The methodology enables continental analyses, and has been tested in communities broadly representative of rangelands globally, with components being applicable to other biomes. Here we also recommend the consultative process and guiding principles that drove the development of this method as an approach for development of the method into other biomes. The consistent, standardised and objective method enables continental, and potentially global analyses than were not previously possible with disparate programs and datasets.

This paper presents a thermal runaway prognosis scheme based on the big-data platform and entropy method for battery systems in electric vehicles. It can simultaneously realize the diagnosis and prognosis of thermal runaway caused by the temperature fault through monitoring battery temperature during vehicular operations. A vast quantity of real-time voltage monitoring data was collected in the National Service and Management Center for Electric Vehicles (NSMC-EV) in Beijing to verify the effectiveness of the presented method. The results show that the proposed method can accurately forecast both the time and location of the temperature fault within battery packs. Furthermore, a temperature security management strategy for thermal runaway is proposed on the basis of the Z-score approach and the abnormity coefficient is set to make real-time precaution of temperature abnormity.

Deflectometry is a key component in the precise measurement of specular (mirrored) surfaces, however traditional methods often lack an end-to-end approach that performs 3D reconstruction in a single shot with high accuracy and generalizes across different free-form surfaces. This paper introduces a novel deep neural network (DNN)-based approach for end-to-end 3D reconstruction of free-form specular surfaces using single-shot deflectometry. Our proposed network, VUDNet, innovatively combines discriminative and generative components to accurately interpret orthogonal fringe patterns and generate high-fidelity 3D surface reconstructions. By leveraging a hybrid architecture integrating a Variational Autoencoder (VAE) and a modified U-Net, VUDNet excels in both depth estimation and detail refinement, achieving superior performance in challenging environments. Extensive data simulation using Blender, leading to a dataset which we are making available, ensures robust training and enables the network to generalize across diverse scenarios. Experimental results demonstrate the strong performance of VUDNet, setting a new standard for 3D surface reconstruction. The implementation of VUDNet is available on GitHub at https://github.com/hadious/VUDNet.

Deflectometry is a key component in the precise measurement of specular (mirrored) surfaces, however traditional methods often lack an end-to-end approach that performs 3D reconstruction in a single shot with high accuracy and generalizes across different free-form surfaces. This paper introduces a novel deep neural network (DNN)-based approach for end-to-end 3D reconstruction of free-form specular surfaces using single-shot deflectometry. Our proposed network, VUDNet, innovatively combines discriminative and generative components to accurately interpret orthogonal fringe patterns and generate high-fidelity 3D surface reconstructions. By leveraging a hybrid architecture integrating a Variational Autoencoder (VAE) and a modified U-Net, VUDNet excels in both depth estimation and detail refinement, achieving superior performance in challenging environments. Extensive data simulation using Blender, leading to a dataset which we are making available, ensures robust training and enables the network to generalize across diverse scenarios. Experimental results demonstrate the strong performance of VUDNet, setting a new standard for 3D surface reconstruction. The implementation of VUDNet is available on GitHub at https://github.com/hadious/VUDNet.

Early disease detection is crucial for maximizingcrop yields and minimizing financial losses in agriculture. Inorder to categorise leaf diseases in pepper, tomato, and potato plants, this study suggests a revolutionary CNN design. The algorithm collects disease-specific features from input photos by using data augmentation techniques to artificially enlarge the training dataset. ReLU-activated convolutional layers gradually capture features at different levels, from low to high, while max pooling layers minimise spatial dimensionality. After thecharacteristics are extracted, a fully-connected layers with a softmax activation function classify them into illness groups. A well chosen dataset containing labelled healthy and sick leaves is used to train and validate the model. Generalizability to untesteddata is ensured via performance evaluation on an independent testing set. The field of deep learning for agricultural applications benefits from this research. This strategy has the ability to rev- olutionise agricultural practices by enabling automated disease identification. This might result in early interventions, better crop health, and eventually sustainable agricultural production.

In this study, an extensive data set was based on existing literature records in order to enable the suitability of several predictive models, from Multiple Linear Regression (MLR) to Neural Networks (NN). The main objective was to, through regression analyses, generate model computations to correlate tensile properties (UTS- Ultimate Tensile Strength, YTS – Yield Tensile Strength and EF – Elongation-to-Fracture) to a given alloy composition and microstructural spacing. This investigation led to positive results, as the highest accuracies of the trained modules (in 80% of the database) were found to be above ~82% (UTS and EF) and a maximum of ~98% (YTS), when analyzing the results to a test data set. Later, these models were used to define trends for possible next solder alloy commercial compositions. Overall, using the standard model’s setup, the Random Forest and Decision Tree models showed the highest accuracy results, with 0.958 for YTS as opposed to 0.907 for MLR. Moreover, Multilayer Perceptron (MLP)-optimized models yielded the best results for each variable, with the highest increases in accuracy associated with the YTS and EF. The present contribution might imply an important milestone towards alloy design research based on data science guidelines to unlock the full potential of former experiments and their extensive set of results.

This paper presents a hybrid probability distribution known as the FCD, which is based on the hazard functions of the Fréchet and Chen distributions. A notable characteristic of the FCD is its ability to model monotonic (increasing and decreasing) and non-monotonic (bathtub-shaped) behaviors, commonly linked to electrical and electronic device failure times in reliability analysis. The paper explores the statistical properties relevant to the reliability analysis of these devices. It proposes a Maximum Likelihood Estimator (MLE) and Bayesian Analysis equations for estimating the parameters of the FCD. Three case studies of electronic device lifetimes with varying behaviors were analyzed to validate the proposed methodology. The FCD was compared to other distributions with similar characteristics, and the results from each case study demonstrated that the proposed distribution yields competitive outcomes, closely reflecting the behavior of the devices analyzed, making it a valuable option for reliability engineering practitioners in warranty and maintenance time evaluations

Big data analytics has fundamentally transformed how organizations enhance customer experience by leveraging vast amounts of data to tailor interactions, streamline services, and drive strategic decisions. This research explores the multifaceted role of big data in improving customer experiences, focusing on its impact on personalization, customer service, operational efficiency, and strategic decision-making. By analyzing recent advancements and applications, the study highlights how big data analytics enables highly personalized recommendations, targeted marketing efforts, and dynamic content that significantly enhance customer engagement. Additionally, it examines the improvements in customer service through real-time support, sentiment analysis, and predictive assistance, which collectively contribute to a more responsive and customer-centric approach. The research also addresses how big data analytics optimizes operational efficiency by streamlining workflows, improving resource allocation, and reducing costs, thus enhancing overall organizational performance. Strategic decision-making benefits from data-driven insights into market trends, pricing strategies, and competitive positioning, allowing organizations to adapt and thrive in a competitive environment. However, the study also acknowledges the challenges associated with data quality, privacy, and investment, emphasizing the need for robust measures to address these issues. Furthermore, the integration of big data with emerging technologies such as artificial intelligence, the Internet of Things, and blockchain presents new opportunities and complexities in enhancing customer experience. Overall, this research underscores the transformative potential of big data analytics while highlighting the importance of addressing its associated challenges to fully capitalize on its benefits.

The rapid urbanization in China has significantly contributed to the vast expansion of urban built-up areas. Precisely extracting and monitoring these areas is crucial for understanding and optimizing the developmental process and spatial attributes of smart, compact cities. However, most existing studies tend to focus narrowly on a single city or global scale with a single dimension, often ignoring mesoscale analysis across multiple urban agglomerations. In contrast, our study employs GIS and image processing techniques to integrate multi-source data for the identification of built-up areas. We specifically compare and analyze two representative urban agglomerations in China: the Yangtze River Delta (YRD) in the east and the Chengdu-Chongqing (CC) region in the west. We use different methods to extract built-up areas from socio-economic factors, natural surfaces, and traffic network dimensions. Additionally, we utilize a high-precision built-up area dataset of China as a reference for verification and comparison. Our findings reveal several significant insights: (1) The multi-source data fusion approach effectively enhances the extraction of built-up areas within urban agglomerations, achieving higher accuracy than previously employed methods. (2) Our research methodology performs particularly well in the CC urban agglomeration. The average precision rate in CC is 96.03%, while the average precision rate in YRD is lower at 80.33%. This study provides an objective and accurate assessment of distribution characteristics and internal spatial structure of built-up areas within urban agglomerations. This method offers a new perspective for identifying and monitoring built-up areas in Chinese urban agglomerations.

The ongoing expansion in volume, velocity and variety of geospatial data has stimulated the development of artificial intelligence applications and associated online cartographic visualizations. In this context, the cartographic communication through peer-reviewed media evolved to incorporate Findability, Accessibility, Interoperability and Re-usability (FAIR) principles. In this paper, we review the functionalities proposed by current international peer-reviewed media for accessing, exploring and re-using geospatial data, and situate them on a diagram conceived for peer-reviewed cartography in the artificial intelligence era. We then present an overview of the cartographic infrastructure and workflow currently available in the Terra Digitalis journal for the online publication of massive spatiotemporal data. This free and opensource based solution allows a smooth integration, from data submission to final peer reviewed publication, of dynamic, interactive 2D and 3D maps. As a proof of concept, we present two maps derived from massive spatiotemporal data, related, respectively, to a climate numerical model (raster data) and a bike sharing system’s origin-destination dataset (vector data). We argue that the combination of technologies used in the journal provides an efficient and low-cost solution, unmatched by other publication media, to boost the accessibility and FAIR principles for geospatial big data.

At the beginning of 2019, the petroleum crisis impacted many economies dependent on this industry. The Mexican government started programs to identify points and government officials involved in the gasoline stealing from PEMEX (Petróleos Mexicanos), the country’s leading government petroleum company. The programs consisted of supervising and monitoring the Mexican country network of gasoline ducts to detect points where gasoline was being stolen. Consequently, large urban regions faced a lack and shortage of gasoline. This situation generated several reactions in social media and many open data in news media. Although the government provided open data about stealing gasoline locations related to crimes, it did not analyze the collected data to identify patterns, insights, and the spatio-temporal characterization of this phenomenon. This paper presents a study to deal with the regional semantics described in the social media locations of gasoline stealing. Thus, a framework to discover the trends that emerge from social media and how it is correlated with the government’s open data is also presented—the proposed methodology used machine learning techniques based on linguistic and semantic technologies. The analysis was applied to a dataset of 24,317 geo-referenced tweets. The obtained results reflected the Mexican thinking opinion regarding discovered social topics, polarization maps, and regional insights. According to discovered trends, there were long fuel lines between 1.5 and 5 kilometers (on average) at fuel stations in different Mexican states.

This work analyzes a new indoor laboratory data set looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the confines of an indoor laboratory setting using multiple distributed sensor nodes on different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOC), CO, CO2, H2, UV, air temperature and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen on exploring innovative advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out in dependence of the manhattan distance between the fire source and the sensor node. We found that especially larger particles (> 0.5 μm) and VOCs show a significant dependency with respect to the intensity as a function of the manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand popagation effects.

The current availability of electronic health records represents an excellent research opportunity on multimorbidity, one of the most relevant public health problems nowadays. However, it also poses a methodological challenge due to the current lack of tools to access, harmonize and reuse research datasets. In FAIR4Health, a European Horizon 2020 project, a workflow to implement the FAIR (Findability, Accessibility, Interoperability, and Reusability) principles on health datasets was developed, as well as two tools aimed at facilitating the transformation of raw datasets into FAIR ones and the preservation of data privacy. As part of this project, we conducted a multicentric retrospective observational study to apply the aforementioned FAIR implementation workflow and tools to five European health datasets for research on multimorbidity. We applied a federated frequent pattern growth association algorithm to identify the most frequent combinations of chronic diseases and their association with mortality risk. We identified several multimorbidity patterns clinically plausible and consistent with the bibliography, some of which were strongly associated with mortality. Our results show the usefulness of the solution developed in FAIR4Health to overcome the difficulties in data management and highlight the importance of implementing a FAIR data policy to accelerate responsible health research.

Conventional data visualization software have greatly improved the efficiency of the mining and visualization of biomedical data. However, when one applies a grid computing approach the efficiency and complexity of such visualization allows for a hypothetical increase in research opportunities. This paper will present data visualization examples presented in conventional networks, then go into higher details about more complex techniques related to leveraging parallel processing architecture. Part of these complex techniques include the attempt to build a basic general adversarial network (GAN) in order to increase the statistical pool of biomedical data for analysis as well as an introduction to the project utilizing the decentralized-internet SDK. This paper is meant to show you said conventional examples then go into details about the deeper experimentation and self contained results.

Fusing data from many sources helps to achieve higher results of analysis. In this work, we present a new algorithm to fuse data from multiple cameras with data from multiple lidars. This algorithm was developed to increase the sensitivity and specificity of autonomous vehicle perception systems, where the most accurate sensors measuring the vehicle’s surroundings are cameras and lidar devices. Perception systems based on data from one type of sensor do not use complete information and have lower quality. The camera provides two-dimensional images; lidar produces three-dimensional point clouds. We developed a method for matching pixels on a pair of stereoscopic images using dynamic programming inspired by an algorithm to match sequences of amino acids used in bioinformatics. We improve the quality of the basic algorithm using additional data from edge detectors. We also improve the algorithm performance by reducing the size of matched pixels determined by available car speeds. We perform point cloud densification in the final step of our method, fusing lidar output data with stereovision output. We implemented our algorithm in C++ with Python API, and we provided the open-source library named Stereo PCD. This library very efficiently fuses data from multiple cameras and multiple lidars. In the article, we present the results of our approach to benchmark databases in terms of quality and performance. We compare our algorithm with other popular methods.

WBAN is a blessing to mankind because it can monitor people's health and activities regardless of place or time. It brings feasibility in patients’ treatment. The main problems with WBAN, however, are related to the security and privacy of health data. To prevent data misuse, health information should be safeguarded. On the other hand, the medical professional needs to receive the patient's health information promptly. As security of health data impact human life greatly so secure an efficient method is required. Efficient cryptographic technique for data protection of wireless body area network is proposed. This research aims to provide data protection in WBAN to increase data security and efficient transmission. The suggested approach offers effective security with quick key generation, quick encryption, and secure data transmission across the network. The proposed methodology is considered to be secure and will consume less time. The proposed method further uses a less complex encryption algorithm. The less complex the approach is the higher performance it will provide in wireless network. The proposed methodology will prevent many attacks, which makes the proposed approach highly suitable for wireless body area network’s security.

The interest on the use of renewable energy resources is increasing, especially towards wind and hydro powers, which should be efficiently converted into electric energy via suitable technology tools. To this aim, self--tuning control techniques represent viable strategies that can be employed for this purpose, due to the features of these nonlinear dynamic processes working over a wide range of operating conditions, driven by stochastic inputs, excitations and disturbances. Some of the considered methods were already verified on wind turbine systems, and important advantages may thus derive from the appropriate implementation of the same control schemes for hydroelectric plants. This represents the key point of the work, which provides some guidelines on the design and the application of these control strategies to these energy conversion systems. In fact, it seems that investigations related with both wind and hydraulic energies present a reduced number of common aspects, thus leading to little exchange and share of possible common points. This consideration is particularly valid with reference to the more established wind area when compared to hydroelectric systems. In this way, this work recalls the models of wind turbine and hydroelectric system, and investigates the application of different control solutions. The scope is to analyse common points in the control objectives and the achievable results from the application of different solutions. Another important point of this investigation regards the analysis of the exploited benchmark models, their control objectives, and the development of the control solutions. The working conditions of these energy conversion systems will be also taken into account in order to highlight the reliability and robustness characteristics of the developed control strategies, especially interesting for remote and relatively inaccessible location of many installations.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

A significant attention has been made to the accurate detection of diabetes which is a big challenge for the research community to develop a diagnosis system to detect diabetes in a successful way in the IoT e-healthcare environment. Internet of Things (IOT) has emerging role in healthcare services which delivers a system to analyze the medical data for diagnosis of diseases applied data mining methods. The existing diagnosis systems have some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we have proposed a IOT based diagnosis system using machine learning methods, such as preprocessing of data, feature selection, and classification for the detection of diabetes disease in e- healthcare environment. Model validation and performance evaluation metrics have been used to check the validity of the proposed system. We have proposed a filter method based on the Decision Tree (Iterative Dichotomiser 3) algorithm for highly important feature selection. Two ensemble learning Decision Tree algorithms, such as Ada Boost and Random Forest are also used for feature selection and compared the classifier performance with wrapper based feature selection algorithms also. Machine learning classifier Decision Tree has been used for the classification of healthy and diabetic subjects. The experimental results show that the Decision Tree algorithm based on selected features improves the classification performance of the predictive model and achieved optimal accuracy. Additionally, the proposed system performance is high as compared to the previous state-of-the-art methods. High performance of the proposed method is due to the different combinations of selected features set and GL, DPF, and BMI are more significantly important features in the dataset for prediction of diabetes disease. Furthermore, the experimental results statistical analysis demonstrated that the proposed method would be effectively detected diabetes disease and can easily be deployed in IOT wireless sensor technologies based e-healthcare environment.

Dataspaces are decentralized and open ecosystems that guarantee trustworthy and secure sharing of data among their participants. In recent years, dataspaces have gained popularity due to their design for managing and sharing heterogeneous data from various sources and domains; and their capability to incrementally solve data integration issues. Leveraging dataspace and advanced technologies plays a vital role in solving many real-world applications effectively and efficiently in real-time. Drone technology is one type of technology that can be deployed to gather data from different resources in harsh or smart environments. Beyond fifth-generation (B5G) communication networks significantly contribute to drones’ development and widespread use by providing low latency and high throughput. Therefore, data sharing among drones in B5G networks offer significant potential to enhance commercial and civilian applications. However, several security issues for collaboration and data sharing, such as data privacy leakage, because of sensitive data and the lack of trustworthy centralized monitoring. Furthermore, sharing data is one of the essential requirements for drone collaboration to achieve their tasks effectively and efficiently in real-time. This conceptual framework presents a novel dataspace in the sky, focusing on securing drone data sharing in B5G for Industry 4.0 toward Industry 5.0. We present how Federated Learning (FL) assists drones in collaboration effectively and efficiently, sharing models instead of raw data. However, because of the fragility of the central curator, the reliability of contribution recording, and the poor quality of shared local models, there are still significant security and privacy issues for drone-assisted smart environments in B5G. Therefore, we present the conceptual framework for leveraging blockchain and FL to secure and manage data sharing of collaborative drones’ dataspace in space in a decentralized fashion. The decentralisation of dataspaces would significantly expand the drive and market for the development of citizen-friendly mobility services.

In this study, we address the need for improved landslide forecasting by exploring innovative machine learning approaches to classify shallow landslide events. Focusing on Ometepe Island, Nicaragua, known for its susceptibility to hydrometeorological incidents and seismic activities, we constructed a comprehensive shallow landslide database using coherence layers derived from SAR images. We applied coherence thresholds ranging from 0.9 to 0.99, in conjunction with 7-day aggregated spatio-temporal precipitation data. By employing machine learning models such as Logistic Regression, Random Forest, and Support Vector Classifier, we established a correlation between precipitation patterns and landslide occurrences. The Support Vector Classifier with a Sigmoidal kernel proved to be the most effective, achieving an F1 score of 0.67. Our results demonstrate a linkage between precipitation and landslide events, confirming the critical role of rainfall over 7-day periods in triggering these events. The study also indicates that, while rainfall is a crucial factor, it is not the sole trigger for landslides, as seismic activities also play a significant role. This research contributes valuable insights into landslide prediction and risk assessment, underscoring the potential of machine learning in enhancing environmental hazard analysis.

The Mine Internet of Things (MIoT), as a key technology for reconstructing post-disaster communication networks, enables to realize the safety monitoring and controlling of the affected roadway. However, due to the challenging underground mine environment, the MIoT suffers from severe signal attenuation, vulnerable nodes, and limited energy, which result in low network reliability of the post-disaster MIoT. To improve the transmission reliability as well as to reduce energy consumption, a directional-area-forwarding-based energy-efficient opportunistic routing (DEOR) for the post-disaster MIoT is proposed. DEOR defines a forwarding zone (FZ) for each node to route packets toward the sink. The candidate forwarding set (CFS) is constructed by the nodes within the FZ that satisfy the energy constraint and the neighboring node degree constraint. The nodes in CFS are prioritized based on the routing quality evaluation by taking the local attributes of nodes into consideration, such as the directional angle, transmission distance, and residual energy. DEOR adopts a recovery mechanism to address the issue of void nodes. The simulation results validate that the proposed DEOR outperforms ORR, OBRN and ECSOR in terms of energy consumption, average hop count, packet delivery rate, and network lifetime.

This qualitative research explores Supplier Relationship Management (SRM) within the context of subscription-based e-commerce models. Through in-depth interviews and thematic analysis, the study investigates key elements such as trust, collaboration, technology integration, sustainability, risk management, cultural alignment, innovation, cost management, globalization, supplier selection, and performance measurement. Findings reveal that trust is foundational in fostering reliable interactions and open communication between e-commerce businesses and suppliers. Collaboration emerges as crucial for innovation and operational efficiency, facilitating co-development and shared risk management. Technology integration, including AI and blockchain, enhances supply chain visibility and decision-making capabilities. Sustainability considerations drive businesses to engage with suppliers adhering to environmental standards, enhancing brand reputation and consumer loyalty. Effective risk management strategies mitigate disruptions and ensure supply chain resilience. Cultural alignment fosters harmonious partnerships and mutual understanding across diverse global markets. Innovation through supplier collaboration drives product development and market responsiveness. Cost management practices optimize operational efficiency and strategic supplier relationships. Globalization necessitates adaptive strategies to manage diverse cultural and regulatory landscapes. Strategic supplier selection and continuous performance measurement drive ongoing improvement and alignment with business objectives. This study contributes empirical insights and practical implications for enhancing SRM in subscription-based e-commerce, informing strategies to navigate challenges and leverage opportunities in a competitive marketplace.

There have been multiple technological advancements that promise to gradually enable devices to measure and record signals with high resolution and accuracy in the domain of Brain Computer Interfaces (BCI). Multi-modal BCIs have been able to gain significant traction given the potential to enhance signal processing by integrating different recording modalities. In this review, we explore the integration of multiple neuroimaging and neurophysiological modalities including Electroencephalography (EEG), Magnetoencephalography (MEG), Functional Magnetic Resonance Imaging (fMRI), Electrocorticography (ECoG), and Single-Unit Activity (SUA). This multimodal approach leverages the high temporal resolution of EEG and MEG with the spatial precision of fMRI, the invasive yet precise nature of ECoG, and the single-neuron specificity provided by SUA. The paper highlights the advantages of integrating multiple modalities, such as increased accuracy and reliability, and discusses the challenges and limitations of multimodal integration. Furthermore, we explain the data acquisition approaches for each of these modalities. We also demonstrate various software programs that help in extracting, cleaning, and refining the data. We conclude this paper with discussion on the available literature highlighting recent advances, challenges, and future directions for each of these modalities.

Background: Patients with locally advanced/metastatic urothelial cancer have been conventionally treated with platinum-based chemotherapy. Recently, numerous new treatments have been proposed to improve overall survival (OS) and reduce adverse effects, but no head-to-head direct comparison is available. Methods: We considered: a) monotherapy with immune checkpoint inhibitors (ICI); b) combinations of an ICI with chemotherapy; c) combinations of an ICI with other drugs. An indirect comparison was performed to identify the regimens most effective in prolonging OS compared to each other and to chemotherapy. Results: A total of 6 articles were included. In our final analysis, nivolumab plus chemotherapy showed better OS compared to chemotherapy (HR= 0.70, 95%CI: .59-0.82); while durvalumab plus tremelimumab showed no OS benefit (HR=0.95, 95%CI 0.82-1.11). More interestingly, enfortumab vedotin plus pembrolizumab significantly prolonged OS compared to both chemotherapy alone (HR=0.53, 95%CI 0.45-0.63) and nivolumab plus chemotherapy (HR= 0.76, 95%CI 0.60-0.97). Discussion and conclusion: Among new treatments for locally advanced and metastatic urothelial cancer, enfortumab vedotin + pembrolizumab showed the best efficacy in terms of OS. Our results support the use of this combination as first-line treatment in this setting.

Air quality is a topic of growing relevance on the global agenda. Two key indicators of air quali-ty, nitrogen dioxide (NO2) and carbon monoxide (CO), represent significant hazards to human health and the environment putting the sustainability of natural resources at risk. Therefore, it is imperative to regularly monitor and reduce atmospheric pollutant concentrations to mitigate their harmful consequences. This study presents an analysis of NO2 total and CO emissions in Argentina, utilizing remote sensing data. The research aims to determine the spatiotemporal distribution of NO2 and CO emissions in Argentina from 2019 to 2021. Subsequently, it seeks to establish the influence of land uses and land cover on the emission of NO2 and CO through dif-ferent climatic, anthropic, and natural indicators. The study was carried out in Argentina during the period 2019-2021, where random points were placed for the different land covers with a total of 800 points surveyed. The year with the highest CO concentration (mol/m-2) was 2020. The values were highest for tree covers and herbaceous wetland coverage in the northern part of the country. For total NO2, the highest concentrations were reached during the years 2020 and 2021. Regarding its distribution, throughout the evaluated period, the highest concentrations of total NO2 were found in the built-up and cropland coverages, with the capital of the country and the northern region of the Buenos Aires province being the most affected areas. In addition, the concentration of CO was influenced by climatic variables (atmospheric pressure, wind speed, maximum environment temperature, Palmer index), natural (height, humidity, NDVI), and ur-ban variables (distances to mining extraction, airports, power plants, urban index) for the differ-ent uses and land covers. Finally, the concentrations of total NO2 were influenced by climatic variables (Palmer index and wind speed), natural (height and NDVI), and urban variables (dis-tance to airports, power plants, industries, service stations, and open dumpsites) for the differ-ent uses and land cover. This study contributes to sustainable environmental management, ena-bling the formulation of effective strategies for mitigating emissions and promoting the long-term health and well-being of communities.

With the emergence of blockchain and smart contracts, traditional digital applications 1 such as identity management, supply chain management, banking and finance etc. are expected 2 to be transformed into Decentralized Applications (DApps). Blockchain interoperability is a new 3 and exciting aspect of blockchain technology that is quickly gaining popularity in many industries. 4 However, the widespread use of blockchains has not yet been achieved because DApps running on the 5 blockchain using smart contracts require access to authentic off-chain data. Users are more conscious 6 of their personal data privacy and consequently are more reluctant to share their data, posing a 7 challenge in the adoption of DApps. To solve this challenge, we present a novel quantum-resistant, 8 data authentication and zero-knowledge proof scheme named zk-DASTARK. Based on our proposed 9 scheme, we present a novel framework which can be used to feed authenticated off-chain data to 10 DApps without compromising user data privacy. Our proposed framework is quite efficient against 11 well-known off-chain data authentication frameworks. The proposed framework is implemented on 12 state-of-the-art quantum-resistant IOTA Blockchain and is highly efficient as it takes approximately 13 60 ms to generate a proof and approximately 10 ms to verify a proof.

Machine Learning (ML) methods have become important to enhance the performance of decision-support predictive models. However, class imbalance is one of the main challenges for developing ML models, because it limits the generalization of these models, and biases the learning algorithms. In this paper, we consider oversampling methods for generating synthetic categorical clinical data aiming to improve the predictive performance in ML models, and the identification of risk factors for cardiovascular diseases (CVDs). We performed a comparative study of several categorical synthetic data generation methods, including Generative Adversarial Networks (GANs). Then, we assessed the impact of combining oversampling strategies and linear and nonlinear supervised ML methods. Lastly, we conducted a post-hoc model interpretability based on the importance of the risk factors. Experimental results show the potential of GAN-based models for generating high-quality categorical synthetic data, yielding probability mass functions that are highly close to real data, maintaining relevant insights, and contributing to increase the predictive performance. The GAN-based model and a linear classifier outperforms other oversampling techniques, improving 2\% the area under the curve. These results demonstrate the capability of synthetic data to help both in determining risk factors and building models for CVD prediction.

Fault line detection timely and accurately when single-phase-to-earth fault occurs in resonant grounding system is still a focus of research. This paper presents a new approach for fault detection based on data fusion and it has non-artificial setting. Firstly, the fault criterion for interphase difference energy ratio and time-frequency correlation coefficient of each line is proposed. Subsequently, the paper establish a coordinate system with the interphase difference energy ratio as X axis and the time-frequency correlation coefficient as Y axis, and it uses the Euclidean distance algorithm to get the characteristic distance of each line by fusing two-dimensional information. Finally, comparing the sound distance and the fault distance of each line to discriminate the fault line. Electromagnetic Transients Program (EMTP) simulation results and adaptability analysis have confirmed the effectiveness and reliability of the proposed scheme.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose an Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE) , to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress detection methodologies in terms of precision, recall and interpretability. Results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity, and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

Biocultural heritage preservation relies on ethnobotanical knowledge and the paleoethnobotanical data used in (re)constructing histories of human-biota interactions. Biocultural heritage, defined as the knowledge and practices of Indigenous and Local peoples and their biological relatives, is often guarded information, meant for specific audiences and withheld from other social circles. As such, these forms of heritage and knowledge must also be included in the ongoing data sovereignty discussions and movement. In this paper we share the process and design decisions behind creating an online database for ethnobotanical knowledge and associated paleoethnobotanical data, using a content management system designed to foreground Indigenous and local perspectives. Our main purpose is to suggest the Mukurtu content management system, originally designed for physical items of cultural importance, be considered as a potential tool for digitizing and ethically circulating biocultural heritage, including paleoethnobotanical resources. With this database, we aim to create access to biocultural heritage and paleoethnobotanical considerations for a variety of audiences while also respecting the protected and sensitive natures of Indigenous and local knowledges.

The home is becoming a key location for healthcare delivery, including the use of technology driven by autonomous systems (AS) to monitor and support healthcare plans. Using the example of a smart mirror, this paper describes the outcomes of focus groups with people with multiple sclerosis (MS; n=6) and people who have had a stroke (n=15) to understand their attitudes towards the use of AS for healthcare in the home. We thematic analysis to analyse the data. The results indicate that the use of such technology depends on the level of adaptability and responsiveness to the users’ specific circumstances, including their relationships with the healthcare system. A smart mirror would need to support manual entry, responsive goal setting, effective aggregation of data sources and integration with other technology, have a range of input methods, be supportive rather than prescriptive in messaging, and give the user full control of their data. Barriers to adoption include a perceived lack of portability and practicality, lack of accessibility and inclusivity, a sense of redundancy, being overwhelmed by multiple technological devices, and a lack of trust in data sharing. These results inform the development and deployment of future health technologies based on the lived experiences of people with health conditions who require ongoing care.

The understanding of various health-oriented vital sign data generated from body sensor networks (BSN) and discovery of the association between the generated parameters is an important task that may assist and promote important decision making in healthcare. For example, in a smart home scenario where the occupants’ health status is continuously monitored remotely, it is essential to provide required assistance when an unusual or critical situation is detected in their vital sign data. In this paper, we present an efficient approach to mine the incomplete (partial) periodic patterns obtained from BSN data. In addition, we employ a correlation test on the generated patterns and introduce the productive-associated partial periodic frequent patterns as the set of correlated partial periodical frequent items. The combination of these measures has the advantage of empowering healthcare providers and patients for quality of diagnosis, and also for better treatment and smart care, especially for the elderly people at smart home. We developed an efficient algorithm named PPFP-Growth (Productive Periodic Frequent Pattern growth) to discover all productive associated partial periodic patterns using these measures. PPFP-Growth is efficient, and the productiveness measure removes uncorrelated periodic items. An experimental evaluation on synthetic and real datasets shows the efficiency of the proposed PPFP-Growth algorithm, and can filter a huge number of partial periodic patterns to reveal only the correlated ones.

Tuberculosis (TB) is an infectious disease declared a global emergency by the World Health Organization and continues as one of the world’s top ten causes of death. TB diagnosis is more critical in developing countries where demanded infrastructure for detection, and treatment complicates the efforts against the disease. These aspects related to limited resources are significant, especially in areas away from the main cities, with few mechanisms to make a timely diagnosis that contributes to successfully addressing the possible patients. Artificial intelligence has begun to be essential in providing additional strategies in the diagnosis processes for health professionals’ support. This paper uses natural language processing (NLP) and machine learning (ML) techniques to create models that can supply TB diagnosis when the needed infrastructure is unavailable. Two different sources were explored: text extracted from electronic medical records (EMR) and patient clinical data (CD). Four proposals using five different machine learning models were implemented. The first two models employed ML and each data source independently. Then, two additional approaches developed a data fusion from both sources. This strategy’s employment was analyzed with physicians according to their pertinence in the process and understanding of the EMR. Finally, the results of the data fusion were compared to each source, obtaining better performance at using only the CD, where an area under the ROC curve of 69.9±2.3% was obtained. However, the advantage of analyzing physician’s reports is the availability of this information contrasted to clinical-specific data, which can be more useful in places far from the main cities without enough basic structure for its obtaining.

Design plays a critical role and creates a positive user experience, establishing a solid brand identity and staying competitive in the digital world. This research investigates the impact of user data collecting and analysis in improving user experience. The Data-driven User interface design can create an optimized and relevant UI with individual preferences, which leads to increasing user engagement and usability. The proposal explores methodologies to implement data collection and user research for tailoring digital products.

In this short communication, a concept has been presented to model geographical data to predict future temperature of Tabuk, region. Machine learning has been applied to the weather station data to develop a prediction model. The preliminary results are promising and encouraging and are envisaging to further this research towards the determination of unknown temperature rise in the region. This is important to mention here, that the problem has been formulated as a Regression problem, NOT as a classification problem. Hence, applying Convolutional neural networks is not possible, due to the non-existence of classes or converting the temperature values to classes does not make any sense. Hence, this is defined as a regression problem which achieved encouraging desirable results.

This review study explores and analyzes distributed database management systems (DDBMS), focusing on the important role of transparency methods in improving the functioning and interaction between users and systems. Transparency in DDBMS refers to several important factors, such as data, replication, performance, scaling, and network transparency. Each one of these components plays a role in concealing the intricate operations that underlie distributed systems from the end user. This not only speeds interactions but also enhances the reliability of the system. The article highlights the criticality of data independence as well as replication transparency in particular. Data independence enables adaptable modifications to the system's architecture and alterations to be made without causing any disruption to user activities. On the other hand, replication transparency ensures that the data remains consistently accurate across distributed nodes, even in the absence of user awareness. Moreover, the article investigates the progression of DDBMS through the incorporation of cutting-edge technologies such as quantum computation and artificial intelligence, which are anticipated to significantly augment the capabilities of data processing. The text proposes potential avenues for further investigation, emphasizing how these advancements may enhance the fundamental resilience of database management systems (DBMS) and expand their applicability in intricate, data-rich settings.

This work develops a new method for vector data augmentation. The proposed method applies the Principal Component Analysis (PCA) and determines the Eigenvectors of a set of training vectors for a Machine Learning (ML) method and uses them to generate the distilled vectors. The training and the PCA distilled vectors have the same dimension. The user chooses the number of vectors to be distilled and augmented to the set of training vectors. A statistical approach determines the lowest number of vectors to be distilled such that when augmented to the original vectors the extended set trains a ML classifier to achieve a required accuracy. Hence, the novelty of this study is, the distillation of vectors with the PCA method and their use to augment the original set of vectors. The advantage that comes from the novelty is that it increases the statistics of ML classifiers. To validate the advantage, we conducted experiments with four public databases and applied four classifiers: Neural Network, Logistic Regression, Support Vector Machine with linear and polynomial kernels. For the purpose of augmentation, we conduct several distillations including nested (double distillation). The latter notion means that new vectors were distilled from already distilled vectors. We train the classifiers with three sets of vectors: original vectors; original augmented with vectors distilled by PCA; original augmented with distilled and double distilled, by PCA, vectors. The experimental results are presented in the paper, and they confirm the advantage that the PCA distilled vectors increase the classification statistics of ML methods, if the distilled vectors augment the original training vectors.

A population dynamics epidemic model is developed that incorporates age of infection and age of vaccination. The model analyzes pre-symptomatic and symptomatic periods of an infected individual in terms of infection age. The model analyzes the efficacy of vaccination in terms of vaccination age. The model is applied to the 2003 SARS epidemic in Taiwan and the current COVID-19 epidemic in New York State.

The overall seismicity of Pakistan from 24 B.C to 2020 is analysed in terms of its multifractal behaviour. Seismic events of magnitude ML=3.0 and above are spatially clustered into four distinct groups, each one corresponding to a different region of high seismic activity. The Multifractal Detrended Fluctuation Analysis (MFDA) method applied on each cluster reveals pronounced inter-cluster heterogeneity in terms of the resulting generalised Hurst exponent and fractality spectrum, possibly due to the particular tectonic characteristics of the regions under investigation. Additional results on the variability of the Gutenberg–Richter b‐value across the defined clusters further corroborate the uniqueness of the seismic profile of each region.

The development of autonomous vehicles is becoming increasingly popular and gathering real world data is considered a valuable task. Many datasets have been published recently in the autonomous vehicle sector, with synthetic datasets gaining particular interest due to availability and cost. For a real implementation and correct evaluation of vehicles at higher levels of autonomy it is also necessary to consider human interaction, which is precisely something that lacks in existing datasets. In this article the UPCT dataset is presented, a public dataset containing high quality, multimodal data obtained using state of the art sensors and equipment installed onboard the UPCT’s CICar autonomous vehicle. The dataset includes data from a variety of perception sensors including 3D LiDAR, cameras, IMU, GPS, encoders, as well as driver biometric data and driver behaviour questionnaires. In addition to the dataset, the software developed for data synchronisation and processing has been made available. The quality of the dataset was validated using an end-to-end neural network model with multiple inputs to obtain speed and steering wheel angle and obtained very promising results.

Social media data is widely used to gain insights about social incidents, whether on a local or global scale. Within the process of analyzing and evaluating the data, it is common practice to download and store it locally. Considerations about privacy protection of social media users are often neglected thereby. However, protecting privacy when dealing with personal data is demanded by laws and ethics. In this paper we introduce a method to store social media data using the cardinality estimator HyperLogLog. Based on an exemplary disaster management scenario, we show that social media data can be analyzed by counting occurrences of posts, without becoming in possession of the actual raw data. For social media data analyses like these, that are based on counting occurrences, cardinality estimation suffices the task. Thus, the risk of abuse, loss or public exposure of the data can be mitigated and privacy of social media users can be preserved. The ability to do unions and intersections on multiple data sets further encourages the use of this technology. We provide a proof-of-concept implementation for our introduced method, using data provided by the Twitter API.

We describe an efficient and cost effective data access mechanism for Sentinel-1 TOPS 1 mode bursts. Our data access mechanism enables burst-based data access and processing, thereby 2 eliminating ESA’s Sentinel-1 SLC data packaging conventions as a bottleneck to large scale processing. 3 Pipeline throughput is now determined by available compute resources and efficiency of the analysis 4 algorithms. For targeted infrastructure monitoring studies, we are able to generate coregistered, 5 geocoded stacks of SLCs for any AOI in the world in a few minutes. In addition, we describe our 6 global scale radar backscatter and interferometric products and associated pipeline design decisions 7 that ensure geolocation consistency across the suite of derived products from Sentinel-1 data. Finally, 8 we discuss the benefits and limitations of working with geocoded SAR SLC data.

According to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is raising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data. To solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, Freesurfer MRI segmentation data, and psychological data. For Alzheimer’s disease vs cognitively normal prediction, the random forest classifier provides 100% accuracy. Furthermore, Alzheimer’s disease and non-Alzheimer’s dementia should be classified properly because their symptoms are similar. To the best of our knowledge, we are the first to present a three-class classification on Alzheimer’s disease vs cognitively normal vs non-Alzheimer’s dementia and achieved 99.86% accuracy using an ensemble model. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work..

Daily thousands of people and goods move along Brazilian Federal highways. Traffic accidents are numerous on these highways and have a significant impact, whether on the economy or the health system. Identifying predictor variables, the probability of an event occurring and how to mitigate them are of paramount importance for the actions of the transit authorities that manage these roads. The main contribution of this study is the development of a predictive machine learning model which uses open data to shows graphically the critical points in the highways. This model is fully reproducible and can be applied to any region worldwide helping to minimize the number of accidents and to prevent deaths by automotive collisions. For this study, 43 variables were analyzed supporting the identification of the causes of accidents with fatal victims on the main highways in the south of Brazil. RoadLytics is proposed as a supervised machine learning model, using the Random Forest algorithm to analyze about 33 thousand occurrences between 2017 and 2020. An exploratory analysis of the data was carried out to support the modeling and to facilitate data visualization. In this sense, heat maps were developed to support the analysis and identification of potential risk areas. The results show that BR386 highway registers the highest number of fatal occurrences, regardless of the season. Additionally, concerning the weather conditions, the analysis shows that 52% of accidents occurred in favorable conditions, such as clear skies, victimizing 501 people. The driver’s lack of attention is the main reason for the accidents’ occurrences. Applying the developed model, an accuracy of 77% was achieved for the classification of fatal accidents.

Objectives We tested the hypothesis that poor adherence is associated with a greater risk of alcohol-caused mortality and morbidities within the first year of discontinuing this medication. Materials and Methods Retrospective cohort study of 3319 individuals who received Acamprosate® in the East of Scotland in a 10-year period using a health informatics approach with record linkage of dispensing data, hospital utilization (SMR) and General Register Office of Scotland (GROS) data. Primary outcome was adherence between one to six months of initiating Acamprosate® medication. Secondary outcome was all cause morbidities and mortality. Results Of the total 3319 individuals identified, good adherence index of >80% was found in 59% of those prescribed Acamprosate® after three months and 6% after six months. There were significant linear trends of poorer adherence with increased risk of alcohol-caused mortality (HR1.2), medical morbidities especially neoplasm (HR 4.1|) and poisoning (HR 1.4) and psychiatric morbidities especially stress (HR 35.1), psychotic (HR 5.6) and neurotic disorders and directly alcohol induced conditions (7.4 HR) after adjustment for other factors within a one-year period of initiation of Acamprosate® treatment. Discussion and Conclusions Further exploratory studies using this digitalized approach should be encouraged in order to capture role of compliance to Acamprosate® and other types of medication that are known to reduce relapse into alcohol dependence and its direct relationship to mortality and morbidities in this population.

Classification of human actions from uni-modal and multi-modal datasets is an ongoing research problem in computer vision. This review is aimed to scope current literature on data-fusion and action-recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The rise in number of action recognition datasets intersects with advances in deep-learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality - such as RGB, depth, skeleton, and infrared - has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this article we will focus solely on areas such as data fusion and recognition techniques in the context of vision with a uni-modal and multi-modal perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions.

Identifying groups that share common features among datasets through clustering analysis is a typical problem in many fields of science, particularly in post-omics and systems biology research. In respect of this, quantifying how a measure can cluster or organize intrinsic groups is important since currently there is no statistical evaluation of how ordered is, or how much noise is embedded in the resulting clustered vector. Many of the literature focuses on how well the clustering algorithm orders the data, with several measures regarding external and internal statistical measures; but none measure has been developed to statistically quantify the noise in an arranged vector posterior a clustering algorithm, i.e., how much of the clustering is due to randomness. Here, we present a quantitative methodology, based on autocorrelation, to assess this problem.

Multiagent technologies give a new way to study and control complex systems. Local interactions between agents often lead to group synchronization also known as clusterization, which usually is a more rapid process in comparison with relatively slow changes in external environment. Usually, the goal of system control is defined by the behaviour of a system on long time intervals. When these time intervals are much longer than the time of cluster formation, clusters may be considered as new variables in a ``slow'' time model. We call such variables ``mesoscopic'' to emphasize their scale laying between the level of the whole system (macroscopic scale) and the level of individual agents (microscopic scale). Thus, it allows us to reduce significantly the dimensionality of a system by omitting considerations of each separated agent, so that we may hope to reduce the required amount of control inputs. Thus, we are often able to consider a system as a collection of ``flowing'' (morphing) clusters emerged form behaviour of a huge amount of individual agents. In this paper, we contrast such approach to the one where a system is considered as a network of elementary agents. We develop a mathematical framework for analysis of cluster flows in multiagent networks and use it to analyze the Kuramoto model as an attracting example of a complex networked system. In this model, a clusterization leads to sparse representation of dynamic trajectories in the whole quantized state space. With that in mind, compressive sensing allows to restore the trajectories in a high-dimensional discrete state space based on significantly lower amount of randomized integral mesoscopic observations. We propose a corresponding algorithm of quantized dynamic trajectory compression. It could allow us to efficiently transmit the state space data to a data center for further control synthesis. The theoretical results are illustrated for a simulated multiagent network with multiple clusters.

With a data revolution underway for some time, there is an increasing demand for formal privacy protection mechanisms that are not so destructive. Hereof microaggregation is a popular high-utility approach designed to satisfy the popular k-anonymity criteria while applying low distortion to data. However, standard performance metrics are commonly based on mean square error, which will hardly capture the utility degradation related to a specific application domain of data. In this work, we evaluate the performance of k-anonymous microaggregation in terms of the loss in classification accuracy of the machine learned models built from perturbed data. Systematic experimentation is carried out on four microaggregation algorithms that are tested over four data sets. The empirical utility of the resulting microaggregated data is assessed using the learning algorithm that obtains the highest accuracy from original data. Validation tests are performed on a test set of non perturbed data. The results confirm k-anonymous microaggregation as a high-utility privacy mechanism in this context and distortion based on mean squared error as a poor predictor of practical utility. Finally, we corroborate the beneficial effects for empirical utility of exploiting the statistical properties of data when constructing privacy preserving algorithms.

Contract between grower and integrator has been used extensively in broiler industry all over the world. One important advantages of contract is risk management, in which contract shifts a portion of grower risk to integrator. Thus, this paper attempted to measure the amount of risk shifted from grower to integrator and the consequences of this benefit to grower. Using a panel data of actual production records of 46 Indonesian broiler growers for the period of January 2014 through December 2017, we systematically measure the amount of risk shifted to integrator and its consequences to grower. The results showed that 78.43% grower risk is shifted to integrator. However, to acquire this benefit grower receive 15% less income. Furthermore, grower face the possibility of losing their asset and stopping their production as the consequences of entering contract.

Universities, like cities, have embraced novel technologies and data-based solutions to improve their campuses with ‘smart’ becoming a welcomed concept. Campuses in many ways are small-scale cities. They increasingly seek to address similar challenges and to deliver improved experiences to their users. How can data be used in making this vision a reality? What can we learn from smart campuses that can be scale up to smart cities? A short research study was conducted over a three-month period at a public university in the United Kingdom employing stakeholder interviews and user surveys, aiming at gaining insight into these questions. Based on the study, the authors suggest that making data publicly available could bring many benefits to different groups of stakeholders and campus users. These benefits come with risks and challenges such as data privacy and protection and infrastructure hurdles. However, if these challenges can be overcome, open data could contribute significantly to improving campuses and user experiences, and potentially set an example for smart cities.

Data that have been processed to allow analysis with a minimum of additional user effort are often referred to as Analysis Ready Data (ARD). The ability to perform large scale Landsat analysis relies on the ability to access observations that are geometrically and radiometrically consistent, and have had non-target features (clouds) and poor quality observations flagged so that they can be excluded. The United States Geological Survey (USGS) has processed all of the Landsat 4 and 5 Thematic Mapper (TM), Landsat 7 Enhanced Thematic Mapper Plus (ETM+), Landsat 8 Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS) archive over the conterminous United States (CONUS), Alaska, and Hawaii, into Landsat ARD. The ARD are available to significantly reduce the burden of pre-processing on users of Landsat data. Provision of pre-prepared ARD is intended to make it easier for users to produce Landsat-based maps of land cover and land-cover change and other derived geophysical and biophysical products. The ARD are provided as tiled, georegistered, top of atmosphere and atmospherically corrected products defined in a common equal area projection, accompanied by spatially explicit quality assessment information, and

Bio-molecular reagents like antibodies required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Bio-Resource Exchange that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, in order to index donations outside of our portal, we mined scientific articles to find instances of donations of antibodies and attempted to extract information about these donations at the finest granularity. Specifically, we extracted the name of the donor, his/her affiliation and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we propose two approaches – a rule based algorithm and a bootstrapped relation learning algorithm. The algorithms extracted donor names, affiliations and antibody names with average accuracies of 57% and 62% respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future. Contact: madhavi@pitt.edu, madhavi@cs.cmu.edu Database URL: http://tonks.dbmi.pitt.edu/brx Supplementary information: Supplementary data are available at Database online.

This work offers a new log generalized odd log-logistic exponential regression model for analyzing weekly dengue fever cases in 2022 with a location-systematic component. To achieve this, a data set of 49 observations of dengue fever cases in the Federal District of Brazil is employed. A review of the mathematical properties of the generalized odd log-logistic exponential distribution is provided, the maximum likelihood method is used to estimate the parameters, and, through Monte Carlo simulations, the accuracy of the estimators is investigated. The model's fit is assessed using global influence metrics and residual analysis. For the time scenario studied, the proposed regression identified factors that have an impact on dengue fever cases, which may contribute to improve disease control. Finally, several interpretations are addressed, and a discussion presents results that aid in better understanding the data set and future research on different data.

Heart failure is associated with a significant mortality rate, and an elevated prevalence of this condition has been noted among hypertensive patients. The identification of predictive factors for heart failure progression in hypertensive individuals is crucial for early intervention and improved patient outcomes. In this study, we aimed to identify these predictive factors utilizing medical history data for hypertension patients. Specifically, we focused solely on utilizing medical data preceding the diagnosis of hypertension to enable patients to anticipate the onset of potential heart failure at the time of hypertension diagnosis. Age-specific and ICD system-specific predictive factors were identified utilizing the MIMIC-IV database through the application of two analytical approaches: chi-square tests and XGBoost modeling. Our findings reveal 21 overall predictive factors, encompassing conditions such as atrial fibrillation, the use of anticoagulants, kidney failure, obstructive pulmonary disease, and anemia. These factors were assessed through a comprehensive review of the existing literature. We anticipate that the results will offer valuable insights for the risk assessment of heart failure in hypertensive patients.

Multiple governmental agencies and private organisations have made commitments for the colonisation of Mars. Such colonisation requires complex systems and infrastructure that could be very costly to repair or replace in cases of cyber-attacks. This paper surveys deep learning algorithms, IoT cyber security and risk models, and established mathematical formulas to identify the best approach for developing a dynamic and self-adapting system for predictive cyber risk analytics supported with Artificial Intelligence and Machine Learning and real-time intelligence in edge computing. The paper presents a new mathematical approach for integrating concepts for cognition engine design, edge computing and Artificial Intelligence and Machine Learning to automate anomaly detection. This engine instigates a step change by applying Artificial Intelligence and Machine Learning embedded at the edge of IoT networks, to deliver safe and functional real- time intelligence for predictive cyber risk analytics. This will enhance capacities for risk analytics and assists in the creation of a comprehensive and systematic understanding of the opportunities and threats that arise when edge computing nodes are deployed, and when Artificial Intelligence and Machine Learning technologies are migrated to the periphery of the internet and into local IoT networks.

Knowing, with reasonable accuracy, the dry matter (DM) content of Hass avocado fruit will help determine when the fruit must be harvested. The reliability of predictive models based on near infrared spectra for DM quantification depends on the ability of the spectra to be representative of the DM gradient within a whole fruit. The aim of this work was to develop a methodology to determine the optimum number of spectra to develop a robust model for DM content quantification. Three spectra were recorded for each zone of the intact fruit: peduncle, equator, and base. Each scanning point was sampled, and the DM content was determined using oven drying. Two-way ANOVA confirmed the DM gradient within the whole fruit. This gradient was observed within spectra using the RMS (root mean square) criterion and PCA. The PLS models showed that at least one spectrum per zone could be enough to construct an efficient and robust model for dry matter quantification.

While the financial technology (FinTech) sector has revolutionized conventional banking services with technology-driven solutions, it also faces considerable cybersecurity hurdles to guard against data protection and sustain the overall financial performance. The main purpose of this paper is to identify the key cybersecurity challenges encountered by FinTech companies, such as data confidentiality concerns, complex cyber-attacks, difficulties with regulatory compliance and third-party risks or technological innovations. This also assesses the regulatory responses to those challenges, such as data privacy regulations, macroprudential regimes, industry-specific guidance and international regulatory cooperation. Through this analysis, the paper attempts to synthesize current state of cybersecurity domain within FinTech and provides suggestions for strengthening data shelter and financial stability by implementing best practices with regulatory strategies.

Occupational incidents in construction workplaces present a persistent challenge, with severe consequences for both workers and project outcomes. This study aims to examine the specific causal factors contributing to these incidents, focusing on the interaction between worker-related, environmental, and procedural factors. The objective is to identify key contributors to workplace accidents and develop a unified predictive model to mitigate future risks. To achieve this, we employed a machine learning approach on a comprehensive accidentology dataset collected from contractors across multiple construction sites. The dataset includes variables such as worker ex-perience, environmental conditions, adherence to safety protocols, and more. By analyzing direct, indirect, and root causes, the methodology uncovers hidden patterns and interdependencies that traditional analysis might overlook. The study’s findings indicate that worker experience and environmental factors are the most significant contributors to incident occurrence, with a clear interaction effect between these variables. The results not only confirm previous research but also offer enhanced predictive capabilities for future safety measures. This research demonstrates the value of machine learning in generating data-driven insights, ultimately aiding in the develop-ment of targeted interventions to improve safety standards in the construction industry.

The advent of 5G technology represents a transformative leap in the realms of retail marketing and supply chain operations, offering unprecedented enhancements and posing unique challenges. This study explores the multifaceted impacts of 5G, focusing on its influence on customer experiences, operational efficiency, and supply chain management. The integration of 5G enables advanced technologies such as augmented reality (AR) and virtual reality (VR), significantly enhancing the interactivity and personalization of the shopping experience. Real-time data collection and analysis, facilitated by 5G, allow for more precise inventory management and optimized store operations, leading to improved customer satisfaction and reduced operational costs. In the supply chain domain, 5G technology offers enhanced visibility and control through real-time tracking and environmental monitoring, which improves logistics efficiency and product quality management. Despite these advancements, the adoption of 5G technology involves considerable challenges, including high infrastructure costs, data security concerns, and global disparities in technology deployment. Businesses must navigate these obstacles while leveraging the benefits of 5G to achieve competitive advantage. The study also highlights the role of 5G in integrating with other advanced technologies, such as artificial intelligence (AI) and blockchain, to drive further innovation. Additionally, 5G supports sustainability efforts by optimizing energy use and reducing waste. Overall, the successful implementation of 5G requires strategic investment and adaptability, but it holds the potential to revolutionize retail and supply chain operations, enhancing efficiency, customer engagement, and sustainability in a rapidly evolving digital landscape.

In this paper, comprehensive datasets are presented to advance research on information security breaches. The datasets include data on disclosed information security breaches affecting S&P500 companies between 2020 and 2023, collected through manual search of the Internet. Overall, the datasets include 504 companies, with detailed information security breach and financial data available for 97 firms that experienced a disclosed information security breach. This document will describe the datasets in detail, explain the data collection procedure and shows the initial versions of the datasets.

This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.

One of the most promising advancements in healthcare is the application of digital twin technology. Digital twins are virtual replicas of real-world human patients and can be used for monitoring, and diagnosis, and as a tool to design treatment strategies tailored to individual patients. Furthermore, digital twins could also be helpful in finding novel treatment targets and predicting the effects of drugs and other chemical substances in development. This review article delves into the various data sources and methodologies that contribute to the construction of digital twins. Each data source, including blood glucose levels, heart MRI and CT scans, cardiac electrophysiology, written reports, and multi-omics data, comes with different challenges regarding standardization, integration, and interpretation. We showcase how various datasets and methods are used to overcome these obstacles and generate a digital twin. While digital twin technology has seen significant progress, there are still hurdles in the way to achieving a fully comprehensive patient digital twin. Developments in non-invasive and high-throughput data collection, as well as advancements in modeling and computational power will be crucial to improve digital twin systems. We discuss a few critical developments in light of the current state of digital twin technology. Despite challenges, digital twin research holds great promise for personalized patient care and has the potential to shape the future of healthcare innovation.

Artificial Intelligence (AI) describes computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and language translation. Examples of AI techniques are machine learning, neural networks and deep learning. AI can be applied in many different areas, such as econometrics, biometry, e-commerce and the automotive industry. In recent years, AI has found its way into healthcare as well, helping doctors to make better decisions (‘clinical decision support’), localizing tumors in magnetic resonance images, reading and analyzing reports written by radiologists and pathologists, and much more. However, AI has one big risk: it can be perceived as a ‘black box’, limiting trust in its reliability, which is a very big issue in an area in which a decision can mean life or death. As a result, the term Explainable Artificial Intelligence (XAI) has been gaining momentum. XAI tries to ensure that AI algorithms (and the resulting decisions) can be understood by humans. In this narrative review, we will have a look at the current status of XAI in healthcare, describe several issues around XAI, and discuss whether it can really help healthcare to advance, for example by increasing understanding and trust. Finally, alternatives to increase trust in AI are discussed, as well as future research possibilities in the area of XAI.

Cities are undergoing huge shifts in technology and operations in recent days, and `data science' is driving the change in the current age of the Fourth Industrial Revolution (Industry 4.0 or 4IR). Extracting insights or actionable knowledge from city data and building a corresponding data-driven model is the key to making a city system automated and intelligent. Data science is typically the study and analysis of actual happenings with historical data using a variety of scientific methodology, machine learning techniques, processes, and systems. In this paper, we concentrate on and explore ``Smart City Data Science", where city data collected from various sources like sensors and Internet-connected devices, is being mined for insights and hidden correlations to enhance decision-making processes and deliver better and more intelligent services to citizens. To achieve this goal, various machine learning analytical modeling can be employed to provide deeper knowledge about city data, which makes the computing process more actionable and intelligent in various real-world services of today's cities. Finally, we identify and highlight ten open research issues for future development and research in the context of data-driven smart cities. Overall, we aim to provide an insight into smart city data science conceptualization on a broad scale, which can be used as a reference guide for the researchers, professionals, as well as policy-makers of a country, particularly, from the technological point of view.

Precision medicine emphasizes fine-grained diagnostics, taking individual variability into account to enhance treatment effectiveness. Parkinson's Disease (PD) heterogeneity among individuals is a proof that disease subtypes exist, and assigning individuals to subgroups is necessary for a better understanding of disease mechanisms and designing precise treatment approaches. The purpose of this study was to identify PD subtypes using RNA-Seq data in a combined pipeline including unsupervised machine learning, bioinformatics, and network analysis. 210 post mortem brain RNA-Seq samples from PD (n = 115) and Normal Controls (NC, n = 95) were obtained with a systematic data retrieval following PRISMA statements and a fully data-driven clustering pipeline was performed to identify PD subtypes. Bioinformatics and Network analyses were performed to characterize the disease mechanisms of the identified PD subtypes and to identify target genes for drug repurposing. Two PD clusters were identified and 42 DEGs were found (p.adjusted ≤ 0.01). PD clusters had significantly different gene network structures (p < 0.0001) and phenotype-specific disease mechanisms, highlighting the differential involvement of the Wnt/β-catenin pathway regulating adult neurogenesis. NEUROD1 was identified as a key regulator of gene networks and ISX9 and PD98059 were identified as NEUROD1-interacting compounds with disease-modifying potential, reducing the effects of dopaminergic neurodegeneration. This hybrid data analysis approach could enable precision medicine applications by providing insights for the identification and characterization of pathological subtypes. This workflow has proven useful on PD brain RNA-Seq, but its application to other neurodegenerative diseases is encouraged.

In the current age of the Fourth Industrial Revolution ($4IR$ or Industry $4.0$), the digital world has a wealth of data, such as Internet of Things (IoT) data, cybersecurity data, mobile data, business data, social media data, health data, etc. To intelligently analyze these data and develop the corresponding real-world applications, the knowledge of artificial intelligence (AI), particularly, machine learning (ML) is the key. Various types of machine learning algorithms such as supervised, unsupervised, semi-supervised, and reinforcement learning exist in the area. Besides, the deep learning, which is part of a broader family of machine learning methods, can intelligently analyze the data on a large scale. In this paper, we present a comprehensive view on these machine learning algorithms that can be applied to enhance the intelligence and the capabilities of an application. Thus, this study's key contribution is explaining the principles of different machine learning techniques and their applicability in various real-world applications areas, such as cybersecurity, smart cities, healthcare, business, agriculture, and many more. We also highlight the challenges and potential research directions based on our study. Overall, this paper aims to serve as a reference point for not only the application developers but also the decision-makers and researchers in various real-world application areas, particularly from the technical point of view.

This article proposes the use of a multi-scale and multi-sensor approach to collect and modelling 3D data concerning wide and complex areas in order to obtain a variety of metric information in the same 3D archive, based on a single coordinate system. The employment of these 3D georeferenced products is multifaceted and the fusion or integration among different sensors data, scales and resolutions is promising and could be useful for the generation of a model that could be defined as hybrid. The correct geometry, accuracy, radiometry and weight of the data models are hereby evaluated comparing integrated processes and results from Terrestrial Laser Scanner (TLS), Mobile Mapping System (MMS), Unmanned Aerial Vehicle (UAV), terrestrial photogrammetry, using Total Station (TS) and Global Navigation Satellite System (GNSS) as topographic survey. The entire analysis underlines the potentiality of the integration and fusion of different solutions and is a crucial part of the “Torino 1911” project whose main purpose is mapping and virtually reconstructing the 1911 Great Exhibition settled in the Valentino Park in Turin (Italy).

This research is a preliminary phase of a general effort to develop a generic-data transferring capability via human haptic thermal sensation (generic-data refers to a coded language like Morse or Braille). For the capability to be effective, it must include a large variety of short recognizable cues. Hence, we propose the concept of cues based on sequences of thermal pulses, i.e., combinations of warm and cool pulses with several levels of intensity. The objective of this study was to determine the feasibility of basing a generic-data-transfer capability on thermal cues composed of sequences of short pulses. The research included defining the basic characteristics of the stimuli parameters and developing practical methods for generating and measuring them. Several sequences were designed in light of the relevant data known to date, and tests were conducted. The thermal cues presented to the participants were sensed and recognized by touch. The results indicate high feasibility for a capability that is applicable in various scenarios. In addition, the low impact on human skin temperature due to short stimuli duration represents an inherent advantage for later implementation. This report presents promising findings and offers insights for further investigation.

Breast cancer is a significant health issue across the world. Breast cancer is the most widely-diagnosed cancer in women; early-stage diagnosis of disease and therapies increase patient safety. This paper proposes a synthetic model set of features focused on the optimization of the genetic algorithm (CHFS-BOGA) to forecast breast cancer. This hybrid feature selection approach combines the advantages of three filter feature selection approaches with an optimize Genetic Algorithm (OGA) to select the best features to improve the performance of the classification process and scalability. We propose OGA by improving the initial population generating and genetic operators using the results of filter approaches as some prior information with using the C4.5 decision tree classifier as a fitness function instead of probability and random selection. The authors collected available updated data from Wisconsin UCI machine learning with a total of 569 rows and 32 columns. The dataset evaluated using an explorer set of weka data mining open-source software for the analysis purpose. The results show that the proposed hybrid feature selection approach significantly outperforms the single filter approaches and principal component analysis (PCA) for optimum feature selection. These characteristics are good indicators for the return prediction. The highest accuracy achieved with the proposed system before (CHFS-BOGA) using the support vector machine (SVM) classifiers was 97.3%. The highest accuracy after (CHFS-BOGA-SVM) was 98.25% on split 70.0% train, remainder test, and 100% on the full training set. Moreover, the receiver operating characteristic (ROC) curve was equal to 1.0. The results showed that the proposed (CHFS-BOGA-SVM) system was able to accurately classify the type of breast tumor, whether malignant or benign.

Significant amounts of anthropogenic radionuclides were introduced in ocean waters following nuclear atmospheric tests and development of the nuclear industry. Dispersion of artificial dissolved radionuclides has been extensively measured for decades over the European continental shelf. The radionuclide measurement and release fluxes databases provided here represent an exceptional opportunity to validate dispersion hydrodynamic models. MARS hydrodynamic model have been applied at different scales to reproduce in realistic conditions the measured dispersion. Specific methods have been developed to obtain qualitative and quantitative results and perform model/measurement comparisons. Model validation concerns short to large scales with dedicated surveys following the dispersion: it was performed within two and three dimensions framework and from minutes and hours following a release up to several years. Results are presented concerning the dispersion of radionuclides in marine systems deduced from standalone measurements, or according to model comparisons. It allows characterising dispersion over the continental shelf, pathways, transit times, budgets and source terms. This review exhibits the main features retained from the point of view of radiotracers, hydrodynamic models and model/measurement methods with perspectives of applications in other areas or oceanographic domains.

A multi-decadal change analysis of the irrigation ponds in Taoyuan, Taiwan was conducted by using multi-source data including digitized ancient maps, declassified single-band CORONA satellite images, and multispectral SPOT images. Supervised LULC classifications were conducted using four textural features derived from the single-band CORONA images and spectral features derived from SPOT images. Post-classification analysis revealed that the number of irrigation ponds in the study area decreased during the post-World War II farmland consolidation period (1945 – 1965) and the subsequent industrialization period (1970 – 2000). However, efforts on restoration of irrigation ponds in recent years have resulted in gradual increases in the number (9%) and total area (12%) of irrigation ponds in the study area.

Increasingly, there is a focus on utilising renewable energy resources in a bid to fulfil increasing energy requirements and mitigate the climate change impacts of fossil fuels. While most renewable resources are free, the technology used to usefully convert such resources is not and there is an increasing focus on improving the conversion economy and efficiency. To this end, advanced control technologies can have a significant impact and is already a relatively mature technology for wind turbines. Though hydroelectric plants can use simple regulation systems, significant benefits have been shown to accrue from the appropriate use of the same control methods designed for wind turbine plants. This represents the key point of the paper. In fact, to date, the application communities connected with wind and hydraulic energies have had little communication, resulting in little cross fertilisation of control ideas and experience, particularly from the more mature wind area to hydrodynamic systems. Therefore, this paper examines the models and the application of control technology across both domains, both from a comparative and contrasting point of view, with the aim of identifying commonalities in models and control objectives, as well as potential solutions. Key comparative reference points include the articulation of the exployed models, specification of control objectives, development of high--fidelity simulators, and development of solution concepts. Not least, in terms of realistic system requirements are the set of physical and constraints under which such renewable energy systems must operate, and the need to provide reliable and robust control solutions, which respect the often remote and relatively inaccessible location of many onshore and offshore deployments.

Appropriate estimation of soil settlement is of significant importance since it directly influences the performance of building and infrastructures that are built on soil. In particular, the settlement of fine-grained soils is critical because of low permeability and continuous settlement with time. Coefficient of consolidation (C_c) is a key parameter to estimate settlement of fine-grained soil layers. However, estimation of this parameter is time consuming, needs skilled technicians, and specific equipment. In this study, C_c was estimated using several soil parameters such as liquid limit (LL), plastic limit (PL), and initial void ratio (e₀). Estimating such parameters in laboratory is straight forward and needs substantially less time and cost compared to conventional tests to estimate C_c such as oedometer test. This study presents a novel prediction model for C_c of fine-grained soils using gene-expression programming (GEP). GEP is a biologically inspired technique capable of offering closed-form solution for the optimal solution. A database consisted of 108 different data points was used to develop the model. A closed-form equation solution was derived to estimate C_c based on LL, PL, and e₀. The performance of developed GEP-based model was evaluated through coefficient of determination (R²), root mean squared error (RMSE), and mean average error (MAE). High R² and low error values indicated the descent performance of the model. Furthermore, the model was evaluated using the additional performance measures and met all the suggested criteria. Furthermore, the model had a better performance in terms of R², RMSE, and MAE compared to most of existing models. It is expected that the developed model will decrease the time and cost associate with determining C_c of fine-grained soils.Keywords: evolutionary model, gene-expression programming (GEP), prediction, soil compression index, estimation, soil engineering, soil informatics, civil engineering, machine learning, data science, big data, soft computing, deep learning, forecasting, subject classification codes, construction informatics, computational intelligence (CI), artificial intelligence (AI), estimation

The result of the multidisciplinary collaboration of researchers from different areas of knowledge to validate a solar radiation model is presented. The MAPsol is a 3D local-scale adaptive solar radiation model that allows to estimate direct, diffuse and reflected irradiance for clear sky conditions. The model includes the adaptation of the mesh to complex orography and albedo, and considers the shadows cast by the terrain and buildings. The surface mesh generation is based on surface refinement, smoothing and parameterisation techniques and allows the generation of high quality adapted meshes with a reasonable number of elements. Another key aspect of the paper is the generation of a high-resolution digital elevation model (DEM). This high-resolution DEM is constructed from LiDAR data and its resolution if two times more accurate than the publicly available DEMs. The validation process uses direct and global solar irradiance data obtained from pyranometers at the University of Salamanca located in an urban area affected by systematic shading from nearby buildings. This work provides an efficient protocol for studying solar resources, with particular emphasis on areas of complex orography and dense buildings where shadows can potentially make solar energy production facilities less efficient.