The RPL protocol is a routing protocol for low power and lossy networks. In such a network, energy is a very scarce resource; so many studies are focused on minimizing global energy consumption. End-to-end latency is another important performance indicator of the network, but existing research tends to focus more on energy consumption and ignore the end-to-end delay of data transmission. In this paper, we propose a kind of energy equalization routing protocol to maximize the surviving time of the restricted nodes so that the energy consumed by each node is close to each other. At the same time, a multi-path forwarding route is proposed based on the cache utilization. The data is sent to the sink node through different parent nodes at a certain probability, not only by selecting the preferred parent node, thus avoiding buffer overflow and reducing end-to-end delay. Finally, the two algorithms are combined to accommodate different application scenarios. The experimental results show that the proposed three improved schemes improve the reliability of the routing, extend the lifetime of the network, reduce the end-to-end delay, and reduce the number of DAG reconfiguration.

An adaptive spatial clustering (ASC) algorithm is proposed in this present study, which employs sweep-circle techniques and a dynamic threshold setting based on the Gestalt theory to detect spatial clusters. The proposed algorithm can automatically discover clusters in one pass, rather than through the modification of the initial model (for example, a minimal spanning tree, Delaunay triangulation or Voronoi diagram). It can quickly identify arbitrarily-shaped clusters while adapting efficiently to non-homogeneous density characteristics of spatial data, without the need of prior knowledge or parameters. The proposed algorithm is also ideal for use in data streaming technology with dynamic characteristics flowing in the form of spatial clustering in large data sets.

This study examines the exchange rate rebound effects of the Central Bank intervention in the selected ECOWAS economies. An empirical understanding of these effects is very important to trade adjustment as well as the macroeconomic stability in these countries. Using the panel data modelling framework, the study finds that the impact of the Central Bank intervention on exchange rate is insignificant and it does not lead to the exchange rate rebound. In addition, money supply as well as monetary policy rate implemented by the monetary authorities significantly influences the level of exchange rate in a positive direction.

Visualizing geo-spatial data embedded into a three-dimensional terrain is challenging. The problem becomes even more complex when uncertainty information needs to be presented as well. This paper addresses the question of how to visually communicate all three aspects: the 3D terrain, the geo-spatial data, and the data-associated uncertainty. We argue that visualizing all aspects with a high degree of detail will likely exceed the visual budget. Therefore, we propose a visualization strategy based on prioritizing a selected aspect and presenting the remaining two with less detail. We discuss various design options that allow us to obtain differently prioritized visual representations. Our approach has been implemented as a tool for rapid visualization prototyping in the context of avionics applications. Practical solutions are described for a use case related to the visualization of 3D terrain and uncertain weather data.

The main contribution of this paper is to develop a graphical tool to evaluate the suitability of a candidate parametric model to fit a data set. The practical motivation is to check the adequacy of the so called SAINT model proposed in Jarner and Kryger (2011). This model has been implemented in practice by an important European pension fund concerned with setting annuity reserves for all current or former employees of Denmark. So, one particular relevant question is whether this mortality model is actually fitting old-age. Our graphical test can be described as follows. First we transform the data by means of the parametric model which is being evaluated. Should the model be correct, the transformed data will be in accordance with an Exponential distribution with rate 1. Then we construct a family of local linear hazard estimates based on the data on the transformed scale. Finally we use the statistical tool SiZer to assess the goodness-of-fit of the Exponential distribution to the data on the transformed scale. If the model is correct the SiZer map should not reveal any significant feature in the family of kernel estimates. Our method allow us to establish a diagnostic regarding the validity of the SAINT model when describing mortality patterns in four different countries.

Lithium ascorbate (LiAsc) is a non-toxic lithium salt (LD50>5000 mg/kg) with normothymic and neuroprotective properties. Chemoreactomic modeling of LiAsc predicted possible hepatoprotective effects which were tested here on a rat model of a non-alcoholic fatty liver disease (NAFLD) with multiorgan pathology caused by combined intake of excess saturated fats (palm oil), carbohydrates (fructose) and inorganic iron salt (ferrous sulfate). Dynamics of biochemical parameters (biomarkers of liver function, kidneys, hematopoiesis, inflammation, thrombus formation, etc.) and histological evidence of hemosiderosis in the model upon reproduction of the model are described. Experimental confirmations of the hepatoprotective effects of LiAsc were obtained. Comparison of the effects of LiAsc with the effects of myoinositol (a substance with known hepatoprotective properties) shown a number of differences in pharmacological action. Both LiAsc and MI lowered ferritin, transferrin saturation, serum iron, AST, ALT, serum creatinine, leukocytes (LiAsc to a greater extent) and normalized lowered serum protein and glomerular filtration rate. However, only LiAsc lowered heightened reticulocytes (absolute and fraction) and platelets towards the corresponding reference intervals, normalized levels of vitamin B12 in blood and lowered the number of Kupffer cells in liver that were overloaded with iron (contained Prussian blue in morphometric studies). In a clinical perspective, hepatoprotective properties of a neuroprotector and it’s potential to reduce hemosiderosis might be useful for treating patients with hepatic encephalopathy.

This study explores the optimization of the admission process at the Escuela Colombiana de Ingeniería Julio Garavito through data anal- ysis. By integrating advanced tools like Power BI, Python Flask, and data mining techniques, a model has been developed to improve student selection and retention, enabling more informed and effective decisions. The results indicate that applying data science not only facilitates efficient data management but also promotes more inclusive and equitable educational poli- cies. This pioneering approach in the field of higher education in Colombia offers a frame- work for future research and technological de- velopments, highlighting the vital importance of data science in improving educational and administrative processes.

Data security in the Internet of things (IoT) is often implemented by means of encryption, which can be burdensome for some entities. We propose in this paper a solution based on routing, by which data are forwarded only to entities that are intended to receive them. An IoT network can be seen as a partial order of equivalence classes of entities, and each entity can be labeled according to the position of its equivalence class in the partial order. The partial order can be constructed according to requirements of secrecy (or confidentiality), integrity and conflicts. Routing tables among entities can be compiled by using the labels. The method is demonstrated in this paper for Software defined networking (SDN) routers and controllers. We propose a centralized IoT architecture with a cloud structure using SDN as networking infrastructure, where storage entities (i.e. cloud servers) are associated with application entities. A small ‘hospital’ example is shown for illustration. Procedures for network reconfigurations are discussed. We also demonstrate the method for the normal case where different partial orders coexist among a set of entities. The method proposed does not impose an overhead on the normal functioning of an SDN network, since it requires calculations only when the network must be reconfigured, because of administrative intervention or policies.

How crucial is big data in contemporary molecular design? In this publication we elucidate fundamental concepts and terminology in this field, critically addressing overlooked issues. We thoroughly examine the size, accessibility, quality, and structural aspects of big data alongside the primary methodologies employed for their analysis. Within chemical compounds, properties and descriptors represent two distinct data types, forming the basis for categorizing molecular big data. The primary objective of chemistry is property production, which means we are searching for novel drugs or materials rather than chemical compounds, and big data is the central issue of this philosophy. The increasing availability of data in computer-aided technology propels advancements in artificial intelligence (AI), machine learning (ML), and deep learning (DL). Accordingly, a broad chemical audience must comprehend these methods to understand data-centered chemistry. Thus, we aim to systemize big data issues through a simple illustrative framework with fundamental descriptor categories: coding, computer-generated descriptors, and property correlates. Although we employ computer-generated descriptors as big data for predictions, the measured data are irreplaceable for achieving high-quality and reliable outcomes and controlling molecular effects. The scarcity of property data remains a significant hurdle limiting comprehensive studies on the structure-property relationships within big data. Accordingly, guided by pragmatics not-so-big data is an option for drug design. We presented also a brief review of the recent big data literature.

The paper investigates into the intricacies of semiconductor manufacturing, a highly complex process entailing a wide array of subprocesses and diverse equipment. Semiconductors are miniaturized integrated circuits comprising numerous components. The semiconductor manufacturing process begins with the thin disc-shaped silicon wafers. On each wafer, up to thousands of identical chips can be prepared depending upon the diameter of the wafer to build up the circuits layer by layer in a wafer fab. The size of the semiconductors requires a high number of units to be produced, thus necessitating a large amount of data to control for improving the semiconductor manufacturing process. Therefore, the collection and analysis of the equipment data, process data, and machine history data throughout the manufacturing process are required to diagnose faults, monitor the process, and manage the manufacturing process effectively. This research is focused on improving the semiconductor manufacturing process through a rigorous analysis of collected manufacturing process data, employing statistical process control (SPC), data mining techniques, and data-driven decision models. The project's primary objective is to increase the manufacturing process stability and productivity by utilizing the latest data-driven technologies in the scientific community. A structured review was undertaken, exploring contemporary data-driven methodologies in semiconductor manufacturing process improvement, specifically pertaining to process capability, product yield rate, and process stability. This review accentuates a comprehensive evaluation of data-driven methodologies applicable to conventional semiconductor manufacturing facilities, aiming to drive substantial process improvements. It features a detailed demonstration facilitating the selection of optimal semiconductor manufacturing processes to enhance overall operational performance. This study of process improvement in the semiconductor manufacturing steps through the application of data-driven methodologies will be effective in delivering advanced, real-time, and proactive control decisions throughout the manufacturing facilities. This endeavor is expected to promptly provide critical insights for enterprise manufacturing decision-makers to reduce manufacturing cycle time, improve the product yield rate, and increase the overall efficiency of the manufacturing process.

Objective: Determine the feasibility of utilizing longitudinal electronic dental record (EDR) data to track change over time in patient periodontal disease (PD) and to generate three patient cohorts: 1) patients whose disease did not change over time, 2) patients whose PD progressed, and 3) patients whose disease improved over time using informatics approaches. Methods: We conducted a retrospective study of 28,908 patients who received a comprehensive oral evaluation between January 1, 2009, and December 31, 2014, at the Indiana University School of Dentistry (IUSD) clinics. We developed and tested three automated computer applications to: 1) diagnose periodontitis cases from periodontal charting, 2) retrieve clinician-documented diagnoses from clinical notes, and 3) track disease change over time. We also evaluated the density of longi-tudinal EDR data for the following follow-up times: 1) none, 2) up to 5 years, 3) >5 and <=10 years, and 4) >10 and <=15 years Results: Thirty-four percent (n=9,954) of the study cohort had up to five years of follow-up visits with an average of 2.78 visits with periodontal charting information. An average of three patient visits per year that contained periodontal charts (63,552) were utilized to obtain a diagnosis, which is considered excellent. For clinician-documented diagnoses from clinical notes, 42% of patients (n=5,562) had at least two PD diagnoses to determine their disease change. In this cohort with cli-nician-documented diagnoses, 72% percent of patients (n=3,919) did not have a disease status change between their first and last visits, 669 (13%) patients' disease status progressed, and 589 (11%) patients’ disease improved. Conclusions: This study demonstrated the feasibility of utilizing longitudinal EDR data to track disease changes over 15 years during the observation study period. We found excellent longitudinal data when diagnoses generated from periodontal charting were considered (three visits per pa-tient). This information can be now utilized for studying the clinical course of periodontitis.

The analysis of the human movement patterns based on the mobile network data makes it possible to examine a very large population cost-effectively, and led to several discoveries about human dynamics. However, the application of this data source is still not common practice. The goal of this study was to analyze the commuting tendencies of the Budapest Metropolitan Area using mobile network data and propose an automatized alternative to the current, questionnaire-based method. Commuting is predominantly analyzed by the census, but that is performed only once in a decade in Hungary. To analyze commuting, the home and the work locations of the subscribers are determined based on their appearances during and outside the working hours. The home locations were compared to census data at a settlement level. Then, the settlement and district level commuting tendencies were identified and compared to the findings of census-based sociological studies. It has been found that commuting analysis based on mobile network data strongly correlates with the census-based findings, even though home and work locations have been estimated by statistical methods. All the examined aspects, including commuting from sectors of the agglomeration to the districts of Budapest and demographic distribution of the commuters, show that mobile network data can be an automatized, fast, cost-effective, and relatively accurate way of commuting analysis, that could provide a powerful tool to the sociologists interested in commuting.

In recent years, local governments have been using transportation card data to monitor the use of public transport and improve the service. However, local governments that are applying a single-fare scheme are experiencing difficulties in using data for accurate identification of real travel patterns, policy decision support, etc. because the information on alighting stops of users is missing. This policy limits its functionality of utilizing data such as accurate identification of real travel patterns, policy decision support, etc. Various studies to overcome this limitation have been conducted in South Korea and other countries to develop es-timation methodologies of alighting stops. Even existing studies introduce an advanced method, we found the margin for better accuracy by combining various estimation methodologies for estimating alighting stops. This study reviewed previously conducted studies to classify data with missing alighting stop information into trip types and then applied an appropriate alighting stop estimation methodology for the characteristics of each trip type by stage. The proposed method is evaluated by utilizing transportation card data of the Seoul metropolitan area and checked the accuracy for each standard of allowable error for sensitivity analysis. Furthermore, the number of trips, accuracy, and valid tag rate were checked for each type to examine the need for classifying the trip types. Finally, our evaluation also examines the impact of classifying trip types on estimation accuracy. The evaluation criteria are accuracy of the number of trips and valid tag rate. The analysis shows that the stage-by-stage estimation methodology based on the trip type proposed in this study can es-timate users’ destinations more accurately than previous studies. Furthermore, based on the construction of nearly 100% valid tag data, this study differs from prior studies.

Abstract: Spatially explicit, fine-grained datasets describing historical urban extents are rarely available prior to the era of operational remote sensing. However, such data are necessary to better understand long-term urbanization and land development processes and for the assessment of coupled nature-human systems, e.g., the dynamics of the wildland-urban interface. Herein, we propose a framework that jointly uses remote sensing derived human settlement data (i.e., the Global Human Settlement Layer, GHSL) and scanned, georeferenced historical maps to automatically generate historical urban extents for the early 20th century. By applying unsupervised color segmentation to the historical maps, spatially constrained to the urban extents derived from the GHSL, our approach generates historical settlement extents for seamless integration with the multi-temporal GHSL. We apply our method to study areas in countries across four continents, and evaluate our approach for two U.S. study sites against historical settlement extents derived from the Historical Settlement Data Compilation for the US, HISDAC-US, achieving Area-under-the-Curve values >0.9. Our results are largely in agreement with model-based urban areas from the HYDE database, and demonstrate that the integration of remote sensing derived observations and historical cartographic data sources opens up new, promising avenues for assessing urbanization, and long-term land cover change in countries where historical maps are available.

In this paper we explore extending the concept of common cross-study Common Data Element concepts beyond simple demographics to cover disease-specific concepts relevant to imaging. We test interactively linking the resulting database to the associated images in a federated manner. We examine the use of existing standards, not only for terminology, but for interchange of serialized data in forms familiar to imaging and clinical trials specialists and their dedicated systems. Our intent is to perform preliminary work to inform both the upcoming Imaging Data Commons specifically, as well as more general integration projects beyond imaging.

Health information technology has been widely used in healthcare, which has contributed a huge amount of data. Health data has four characteristics: high volume; high velocity; high variety and high value. Thus, they can be leveraged to i) discover associations between genes, diseases and drugs to implement precision medicine; ii) predict diseases and identify their corresponding causal factors to prevent or control the diseases at an earlier time; iii) learn risk factors related to clinical outcomes (e.g., patients’ unplanned readmission), to improve care quality and reduce healthcare expenditure; and iv) discover care coordination patterns representing good practice in the implementation of collaborative patient-centered care. At the same time, there are major challenges existing in data-driven healthcare research, which include: i) inefficient health data exchanges across different sources; ii) learned knowledge is biased to specific institution; iii) inefficient strategies to evaluate plausibility of the learned patterns and v) incorrect interpretation and translation of the learned patterns. In this paper, we review various types of health data, discuss opportunities and challenges existing in the data-driven healthcare research, provide solutions to solve the challenges, and state the important role of the data-driven healthcare research in the establishment of smart healthcare system.

This paper offers a comprehensive examination of the process involved in developing and automating supervised end-to-end machine learning workflows for forecasting and classification purposes. It offers a complete overview of the components (i.e. feature engineering, model selection, etc), principles (i.e. bias-variance decomposition, model complexity, overfitting, model sensitivity to feature assumptions and scaling, output interpretability, etc), models (i.e. neural networks, regression models, etc), methods (i.e. Cross-Validation, data augmentation, etc), metrics (i.e. Mean Squared Error, F1-score, etc) and tools that rule most supervised learning applications with numerical and categorical data, as well as their integration, automation, and deployment. The end goal and contribution of this paper is the education and guidance of the non-AI expert academic community over complete and rigorous machine learning pipelines and data science practices, from problem scoping to design and state-of-the-art automation tools, including basic principles and reasoning in the choice of methods. The paper delves into the critical stages of supervised machine learning workflow development, many of which are often omitted by researchers due to brevity, and covers foundational concepts essential for understanding and optimizing a functional machine learning workflow, thereby offering a holistic view of task-specific application development for applied researchers who are not AI experts.

The integration of connected autonomous vehicles into the transportation system introduces significant enhancements in driving experience and convenience. Yet, it simultaneously raises important concerns regarding the security and privacy of passenger data. As individuals increasingly depend on these connected vehicles, particularly rental cars with advanced infotainment systems, safeguarding their personal information becomes a paramount imperative, presenting significant challenges that must be addressed to maintain user trust and comply with privacy regulations. This paper investigates risks associated with personal information stored in connected vehicle technology, emphasizing the importance of robust security and privacy practices. In the advent of cyber threats and the need for data protection, we examine a risk management framework (RMF) as suggested by NIST, which aims to address these quintessential concerns preemptively. Our research moves beyond the limitations of manual safeguarding methods, supporting the necessity for an advanced automated technical solution. To address these issues, we introduce and meticulously assess the efficacy of “Vehicle Inactive Profile Removal” (VIPR), an innovative technical solution conceived to actively eliminate the risks and potential oversights that stem from the prevalent tendency of renters to leave personal data unerased in the infotainment systems of rented connected vehicles. We provide a thorough evaluation of VIPR through various scenarios, including vehicle return to a rental depot, subsequent rentals, and ridesharing contexts. Our proof of concept includes an array of experiments to demonstrate how VIPR proficiently and autonomously removes previous renters’ “Inactive” profiles from a simulated infotainment system. The results highlight how VIPR constitutes a critical step towards enhancing the privacy and security of personal data, thereby promoting a safer, more responsible use of connected vehicle technology in society.

Alzheimer’s is a degenerative brain condition brought on by intricate brain changes after cell injury. The prevalence of Alzheimer’s disease is highest in those over 65. Presently, AD is detected by manual examination of a patient’s Magnetic Resonance Imaging (MRI) scan and neuropsychological assessments. Due to its subpar accuracy and performance, solutions based on artificial intelligence (AI) have not been made more widely available. This paper proposes a deep Convolutional Neural Network (CNN) with the pre-trained MobileNet-V2 architecture as the model’s base for feature extraction and reducing the parameter size and training time. The proposed model accurately classifies various early stages of AD. The proposed approach visualizes the class activation maps in the form of a heat map on brain MRI scans via the Grad-CAM algorithm that lifts the black-box nature of the deep model. To handle the imbalance problem of the AD data set acquired from Kaggle, the oversampling algorithm SMOTE interpolates new images to even the class samples. The proposed multi-class classification deep model is named Bio-AD and evaluated using different quality metrics. The Bio-AD model has the following values for evaluation metrics: 97.92%, 99.87%, 97.87%, 98%, 98%, and 0.0646 for accuracy, Area Under the Curve (AUC), F1-score, Precision, Recall, and loss respectively. The proposed Bio-AD model is compared with DenseNet-169, VGG-19, and InceptionResNet-V2 using different quality metrics and outperformed in comparison with all other models using the AD data set.

In the era of cloud computing, guaranteeing the safety and effectiveness of data management is of utmost importance. This investigation presents a novel approach that amalgamates sharding concept, encryption, zero-knowledge proofs (zkp), and blockchain technology for secure data retrieval and data access control to improve data security, efficiency in cloud storage and migration. Further we utilize user-specific digital wallets for secure encryption keys in order to encrypt the file before storing into the cloud. As Large files ( greater than 50 MB) or Big data file ( grater than 1 TB) computational complexity is more we leverage on sharding concept to enhance both space and time complexity in cloud storage, hence the large files are divided into shards and stored in different database servers. We also employed blockchain smart contract to enhance secure retrieval of the file and also a secure access method which ensures the privacy of the user. The zk-snark protocol is utilized to ensure the safe transfer of data between different cloud services. By utilizing this approach, data privacy is preserved, as only the proof of the data’s authenticity is shared with the verifier at the destination cloud, rather than the actual data itself. The suggested method tackles important concerns related to data protection, privacy, and efficient resource utilization in cloud computing settings by ensuring it meets all the cloud policies require to store data. As the environment maintains privacy of the user data and by not storing the raw data of the user anywhere, the entire environment is setup as a Zero trust model.

Artificial intelligence (AI) techniques have grown rapidly in recent years in the context of computing with smart mobile phones that typically allows the devices to function in an intelligent manner. Popular AI techniques include machine learning and deep learning methods, natural language processing, as well as knowledge representation and expert systems, can be used to make the target mobile applications intelligent and more effective. In this paper, we present a comprehensive view on mobile data science and intelligent apps in terms of concepts and AI-based modeling that can be used to design and develop intelligent mobile applications for the betterment of human life in their diverse day-to-day situation. This study also includes the concepts and insights of various AI-powered intelligent apps in several application domains, ranging from personalized recommendation to healthcare services, including COVID-19 pandemic management in recent days. Finally, we highlight several research issues and future directions relevant to our analysis in the area of mobile data science and intelligent apps. Overall, this paper aims to serve as a reference point and guidelines for the mobile application developers as well as the researchers in this domain, particularly from the technical point of view.

This study explored market actors’ perspectives on data sharing within Poland’s food passports pilot, which tested the feasibility of a digital system that provides reliable and comprehensive information on the origin, journey, and quality of agri-food products. Using thematic analysis, we identified factors influencing stakeholders’ willingness and motivations to share data. Our findings highlight the necessity of a clear value proposition for all actors within the production and distribution chain to invest resources and time in additional data exchange systems. For farmers, reducing burdensome reporting procedures and providing direct financial incentives were key motivators. Agri-food processing, transport and packaging companies viewed data collaboration as a practical tool to ensure high-quality raw materials and promote premium-priced food. Appropriate data management policies were critical for all stakeholders. While sustainability was recognized as important, opportunities for collaboration going beyond economic considerations were not widely explored. Additionally, concerns about data interpretation emerged as a significant issue. These findings suggest the need for data-sharing strategies that better align economic benefits with broader sustainability goals. Further research is also needed to examine how concerns about potential data misinterpretation limit stakeholders’ willingness to engage in data sharing initiatives.

One of the factors leading to the slow decline in poverty in Indonesia is the lack of government at-tention to reduce income inequality. Fiscal policy and economic growth can effectively reduce poverty after lowering income inequality, so the inequality channel must be considered. Socioec-onomic and infrastructure differences between provinces can influence the effectiveness of eco-nomic growth and fiscal policy in reducing poverty. This study aims to assess the effects of eco-nomic growth and fiscal policy on spending and taxes on direct and indirect poverty reduction through lowering income inequality and how these variables influence poverty by province. This study employed secondary data, including panel data for 2010-2023 from 34 provinces in Indo-nesia, which were analyzed using an autoregressive cross-lagged SEM model. The study finds that economic growth and fiscal policy on spending on education and health are statistically sig-nificant in reducing poverty directly in non-Java but do not affect it through income inequality. Taxes increase income inequality, and the social safety net does not reduce poverty outside Java. Increased spending on education and health should continue, with improvements in targeting so-cial safety nets and tax reforms needed to make the system more progressive and reduce inequality

This study investigates student performance with the aim to forecast students' academic outcomes using data analytics and machine learning techniques. There is a big drop out per cent especially in the technological study programs at the universities, however, focusing on the successful study process there is important to analyze and to predict some risks on students’ to assure low dropout percent. While Student Performance Prediction (SPP) has potential benefits, such as personalized learning and early interventions, several challenges make the task complex in relation to (1) data quality and availability and (2) incomplete and inconsistent data. Predicting performance requires a range of different data types: academic records, attendance, and engagement in class, socio-economic background, and even behavioral factors. Moreover, according to the fourth Sustainable Development Goal (SDG) we focus on the quality in education.This paper presents a case study of data mining method for SPP by using classification, regression, and clustering are generally used in education to predict student’s performance which is important to control drop out of studies percent. The case presented is to predict risks and to assure academic success and quality based on the CRISP-DM data mining.

The WHO is so passionate about good health for all meanwhile the emerging counselling discipline is a complimentary arm whose interest is to fully complement those efforts through helping humankind in issues that may be affecting the health and the overall well-being. The researcher has discovered through studies and general knowledge that men tend to delay in seeking health help compared to women. Men appear to be reluctant in seeking professional assistance in problems pertaining to their health, marriages, work place, infertility, sexual dysfunction and other social life ills subsequently leading to depression, suicides, excessive uptake of alcohol, violence, mental psychosis and physical disabilities or premature death. Studies have shown that men are socially constructed to be strong from a tender age and they grow into adulthood believing that they are strong both physical and emotional hence they are supposed to withstand any situation affecting them. Masking and faking have been regarded as sign of being a real man, however these social constructs, perceptions and expectations appear to be the root cause of problems manifesting daily in men’s behavior towards seeking health help. This study therefore endeavors to find out more about the factors or determinants influencing men’s reluctance to seeking help in areas concerning their health in Industrial site of Victoria Falls. The study serves as additional educational awareness guide for the significant other, while issues unraveled help in gender mainstreaming programs for gender equality when it comes to societal hegemonizing of men’s health. Moreover, the exploration of influencing factors or determinants, causes and effects of men’s reluctance in seeking health help were scrutinized as well as possible solutions. There has been much realization of more various literature on women’s issues than men because women in general have been known to open up and talk through their issues unlike men hence the aim is to focus on men in order to understand the attitude and perceptions underlying the reluctance to seek medical care regularly and promptly. When communities get to understand that men too, feel the pain both emotionally and physically, may be then, men would not fear stigmatization but come out to seek health help promptly and communities would realize that some cultural expectations placed on men result in more harm than good.

Since its origin in the thermodynamics of the 19th century, the concept of entropy has also permeated other fields of physics and mathematics, such as Classical and Quantum Statistical Mechanics, Information Theory, Probability Theory, Ergodic Theory and the Theory of Dynamical Systems. Specifically, we are referring to the classical entropies: the Boltzmann-Gibbs, von Neumann, Shannon, Kolmogorov-Sinai and topological entropies. In addition to their common name, which is historically justified (as we briefly describe in this review), other commonality of the classical entropies is the important role that they have played and are still playing in the theory and applications of their respective fields and beyond. Therefore, it is not surprising that, in the course of time, many other instances of the overarching concept of entropy have been proposed, most of them tailored to specific purposes. Following the current usage, we will refer to all of them, whether classical or new, simply as entropies. Precisely, the subject of this review is their applications in data analysis and machine learning. The reason for these particular applications is that entropies are very well suited to characterize probability mass distributions, typically generated by finite-state processes or symbolized signals. Therefore, we will focus on entropies defined as positive functionals on probability mass distributions and provide an axiomatic characterization that goes back to Shannon and Khinchin. Given the plethora of entropies in the literature, we have selected a representative group, including the classical ones. The applications summarized in this review finely illustrate the power and versatility of entropy in data analysis and machine learning.

Accurate solar power forecasting is pivotal for the effective planning, management, and operation of power systems, ensuring a sustainable energy supply for consumers while optimizing the integration of renewable energy sources and the functioning of electricity markets. Recent advancements have focused on developing predictive models that offer precise daily forecasts for solar power generation, which are critical for power usage planning and production efficiency. These models typically leverage a diverse range of data inputs, including solar power metrics and meteorological variables such as temperature, humidity, precipitation, solar radiation, and wind speed—factors that significantly influence solar power generation due to their weather-dependent nature. This study introduces a novel hybrid forecasting model that synergizes the capabilities of the Prophet model and Gated Recurrent Units (GRU), leveraging their respective strengths to enhance predictive performance. The proposed model is rigorously evaluated across short-term (2 days, 7 days) and medium-term (15 days, 30 days) forecasting horizons. Experimental results demonstrate that the hybrid model significantly outperforms the existing models, delivering superior accuracy in solar power generation forecasts.

Optical communication systems pose significant challenges, including the effects of nonlinear noises. The nonlinearities, including Kerr-induced phase noise, become more problematic in m-QAM as the orden of the format increases becoming a highly densed set of data-symbols and therefore, requiring advanced signal processing for successful separation of symbols at the demodulation stage. Machine learning techniques have recently been applied to improve signal integrity in such scenarios. This paper explores the application of a spectral clustering algorithm adapted to deal with data streaming to mitigate nonlinear noise in long-haul optical channels dominated by nonlinear phase noise, offering a promising solution to a pressing issue. We demonstrate that the spectral clustering algorithm outperforms the k-means algorithm in the face of nonlinear phase noise in -90, -100, and -110 dBc/Hz scenarios at 1 MHz in a simulated 10 GHz symbol rate channel.

Wind power has emerged as a crucial substitute for conventional fossil fuels. The combination of advanced technologies such as the internet of things (IoT) and machine learning (ML) has given rise to a new generation of energy systems that are intelligent, reliable, and efficient. The wind en-ergy sector utilizes IoT devices to gather vital data, subsequently converting them into practical insights. The aforementioned information aids among others in the enhancement of wind turbine efficiency, precise anticipation of energy production, optimization of maintenance approaches, and detection of potential risks. In this context, the main goal of this work is to combine the IoT with ML in the wind energy sector by processing weather data acquired from sensors to forecast wind power generation. To this end, three different regression models are evaluated. The models under comparison include Linear Regression, Random Forest, and Lasso Regression, evaluated us-ing metrics such as coefficient of determination (R²), adjusted R², mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). After examining a dataset from IoT devices that included weather data, the models provided substantial insights regarding their ca-pabilities and responses to preprocessing, as well as each model's reaction in terms of statistical performance deviation indicators. Ultimately, the preprocessing and the data analysis show that Random Forest regression is more suitable for weather condition datasets than the other two re-gression models. Both the advantages and shortcomings of the three regression models indicate that their integration with IoT devices will facilitate successful energy forecasting.

Machine unlearning is a critical process designed to allow machine learning models to forget or remove specific data upon request, particularly for privacy protection. While the primary objective of unlearning is to safeguard sensitive information, it introduces substantial privacy and security risks. This paper explores the two major categories of threats to machine unlearning: privacy attacks and security attacks. Privacy attacks, such as membership inference and model inversion, exploit residual information to infer or reconstruct sensitive data that should have been erased. Security attacks, particularly specific data poisoning, involve the injection of malicious data into the training process, which may leave lingering effects even after the unlearning process. In this paper, we provide an in-depth examination of these threats and propose several defense mechanisms. Differential privacy, adversarial training, and query limitations are highlighted as key defenses against privacy attacks, while data validation, adversarial examples, and post-unlearning audits are critical in mitigating security risks. Additionally, we discuss emerging methodologies like data provenance tracking and fine-tuning as crucial for ensuring unlearning processes are thorough and effective. Through these analyses, we aim to provide a comprehensive framework for strengthening the security and privacy of machine unlearning systems, enabling their broader adoption across industries such as healthcare, finance, and AI-driven technologies.

As telecommunication networks continue to grow, the volume, variety, and velocity of such `big data' poses an immense challenge for security and service analysts. A primary data format in such networks are Call Detail Records (CDRs), and more recently, eXtended Detail Records (XDRs), that capture a variety of information such as caller, receiver, duration, carrier, datetime, amongst other attributes. In this short paper, we investigate the current research trends and challenges that exist within this data-rich domain. As part of this, we look at the domain-specific tasks that analysts will seek to address, we look at how machine learning has been utilised to date within this domain, and we present our current findings on open research problems that are ripe for further investigation.

The study put forward a data fusion approach for urban remote sensing that combines SAR (Synthetic Aperture Radar) and optical satellite data. By integrating datasets from different sensors and spatial-temporal scales, the technique aims to extract more accurate information. The fusion approach utilizes two methods: feature-based fusion, where relevant features are extracted and fused, and simple layer stacking (SLS), where the original datasets are directly stacked as multiple layers. This study extracted features using SAR textures (using Sentinel-1) and modified indices (using Landsat-8), and then classified these features using an XGBoost algorithm implemented in Python and Google Earth Engine. Researchers examined five cities, each representing a distinct climatic zone and urban dynamic: Cape Town, Guangzhou, Los Angeles, Mumbai, and Osaka. An accuracy assessment was conducted using random validation points, achieving an overall accuracy of 89.5% using the proposed MSFI method. A comparison was also performed with three well-known global products. The proposed approach, outperformed all three global products achived 89% accuracy while ESA (84%), ESRI (81%) and Dynamic World (82%). Additionally, Land surface temperature analysis was accomplished to investigate the relationship between extracted UIS and Land Surface Temperature (LST) across selected cities to show the practical use of proposed MSFI method. Los Angeles, a warm temperate city, showed the highest LST among all five cities. The datasets, along with the GEE and Python codes, are available at https://github.com/mnasarahmad/sls.

The increasing importance of hydropower generation has led to the development of new smart technologies and the need for reliable and efficient equipment in this field. As long as hydropower power plants are more complex to build up than other power plants, the operation regimes and maintenance activities become essential for the hydropower companies to optimize their performance, such that including the data-driven approaches in the decision-making process represents a challenge. In the paper, a comprehensive and multi-task framework integrated into a Knowledge Discovery module based on Data Mining to support the decisions of the operators from the control rooms and facilitate the transition from the classical to smart Supervisory Control and Data Acquisition (SCADA) system in hydropower plants has been designed, developed, and tested. It integrates tasks related to detecting the outliers through advanced statistical procedures, identifying the operating regimes through the patterns associated with typical operating profiles, and developing strategies for loading the generation units that consider the number of operating hours and minimize the water amount used to satisfy the power required by the system. The proposed framework has been tested using the SCADA system's database of a hydropower plant belonging to the Romanian HydroPower Company. The framework can offer the operators from the control room comparative information for a time horizon longer than one year. The tests demonstrated the utility of a Knowledge Discovery module to ensure the transition toward smart SCADA systems that will help the decision-makers improve the management of the hydropower plants.

Digital twin technology, a cutting-edge approach that creates dynamic digital replicas of physical systems, is increasingly integral to various industrial applications. However, the effective deployment of digital twins often faces challenges associated with data availability, quality, and interoperability, which can impede the development and operational efficacy of these virtual counterparts. This paper presents a systematic review of the application of artificial intelligence (AI) in enhancing and managing digital twin technologies across multiple domains such as industry, healthcare, urban planning, business, education, technology, and others. It specifically examines how machine learning models, particularly neural networks and deep generative models, are being employed to optimize the creation, maintenance, and functionality of digital twins. The review explores the role of artificial intelligence in overcoming data-related limitations by providing robust, scalable data solutions for digital twins. Additionally, it addresses critical considerations of real-time data processing and system interoperability within these applications. This survey not only identifies the prevailing challenges and opportunities within this emerging field but also highlights potential future research directions that could further the integration of AI with digital twin technology. Through a detailed exploration of the intersection between AI and digital twins, this paper aims to contribute significantly to the knowledge base and encourage further innovations in this interdisciplinary area.

This article explores the specific impact of artificial intelligence (AI) -driven data visualisation technologies in the user experience of the Internet industry. Through the introduction of machine learning and data mining technologies, AI has significantly improved the intelligence and automation of data visualization tools, promoting innovation in visualization methods and improving the quality and efficiency of data cleaning, processing, and analysis. In addition, AI has also promoted the development of personalised data visualization, providing users with a richer and more intuitive way to present data. This paper analyses the applications of AI-driven data visualization in machine learning, natural language processing, and computer vision. It demonstrates the positive effects of AI data visualization on user understanding and optimisation of models through practical feedback from Yellowbrick tools.

The paper analyzes the relationship between urban waste recycling and technological innovation systems in Europe. Data from the Global Innovation Index for 34 European countries in the period 2013-2022 was used. To analyze the characteristics of European countries in terms of waste recy-cling capacity, the k-Means algorithm optimized with the Elbow method and the Silhouette Coef-ficient was used. The results show that the optimal number of clusters is 3. Panel data results show that waste recycling increases with domestic market scale, gross capital formation, and the diffu-sion of Information and Communication Technologies (ICTs), while it decreases with the infra-structure index, business sophistication index, and the average expenditure in research and devel-opment of large companies.

In response to the increasing complexity and sophistication of cyber threats, particularly those enhanced by advancements in artificial intelligence, traditional security methods are proving insufficient. This paper explores the zero-trust cybersecurity framework, which operates on the principle of "never trust, always verify" to mitigate vulnerabilities within organizations. Specifically, it examines the applicability of zero-trust principles in environments where large volumes of information are exchanged, such as schools and libraries, highlighting the importance of continuous authentication, least privilege access, and breach assumption. The findings highlight avenues for future research that may help preserve the security of vulnerable organizations.

Evapotranspiration is a critical component of the hydrological cycle, and it has a decisive impact on the ecosystem balance in arid and semi-arid regions. The Yinchuan Plain, located in the Gobi of Northwest China, has a strong surface ET. In order to assess the ET pattern in this region, we obtained the ETa of Yinchuan Plain between 1987 and 2020 using the GEE platform. We employed the Surface Energy Balance Model (SEBAL), specifically geeSEBAL, to analyze the change pattern of ET over different seasons, years, and land types. The results show that: ① In spring, the daily ETa of the Yinchuan Plain is highest in the central lake wetland area, with a maximum value of 4.32 mm day-1. In summer, it is concentrated around the croplands and water bodies, with a maximum value of 6.90 mm day-1; In Autumn and winter, it is mainly concentrated around the water bodies and impervious areas, with maximum values of 3.93 and 1.56 mm day-1, respectively. ② From 1987 to 2020, the ET of the Yinchuan Plain showed an obvious upward and downward trend in some areas with significant land use changes, but the overall ET of the region remained relatively stable without dramatic fluctuations. ③ The evapotranspiration of different underlying land use types in the Yinchuan Plain region is as follows: water body&gt;cultivated land&gt;impervious&gt;grassland&gt;bare land. Our results showed that geeSEBAL is highly applicable in the Yinchuan Plain area. It allows for the accurate and detailed inversion of ET in the study area, which facilitates the study of regional hydrological cycle and water governance.

Background: IoT and Big Data are newer technologies that can provide substantial support for healthcare systems and help overcome their shortcomings. The aim of this paper was to analyze literature production descriptively, thematically, and chronologically from an interdisciplinary perspective in a holistic way to identify the most prolific research entities and themes. Methods: The synthetic knowledge synthesis qualitatively and quantitatively analyzes the production of literature through a combination of descriptive bibliometrics, bibliometric mapping and content analysis. For this analysis the Scopus bibliometric database was used. Results: In the Scopus database, 2272 publications were found, which were published between 1985 and June 10, 2024. The first article in this field was published in 1985. Until 2012 the production of literature was steady increasing, after that exponential growth began, which reached its peak in 2023. The most productive countries were the USA, India, China, the United Kingdom, South Korea, Germany and Italy. The content analysis resulted in 8 themes (four from the perspective of computer science and four from the perspective of medicine) and 21 thematic concepts (eight from the perspective of computer science and 13 from the perspective of medicine). Conclusions: The results show that IoT and Big Data have become key technologies in preventive health. The study outcomes might represent a starting point for the further development of research that combines multidisciplinary aspects of healthcare.

Single nucleotide polymorphisms in the mitochondrial genome have been investigated in relation to breast cancer. Certain variants could be associated with an increased risk of this malignant disease. These associations underline the importance of mitochondrial function in cancer biology and highlight the potential for mtDNA-based biomarkers and future therapies. The general objective of this research was to develop a model which is capable of identifying nonlinear patterns in breast cancer mitochondrial sequences. Association rules were used to explore mtDNA variant positions. The analysis included 41 breast cancer patients and 28 control samples. An a priori algorithm identified significant association rules with lift > 1 and confidence > 0.5. A total of 5562 rules for cancer and 157,140 for control sequences were refined after redundancy removal. A total of 150 associations were identified, of which only 78 showed significant support and confidence, while 315 and 1438 positions showed strong associations with breast cancer. Association rules analysis revealed significant patterns, especially in sequences associated with the control region and a specific locus around genes coding for tRNAs and NADH dehydrogenase subunits. However, further research is necessary to establish causality, clinical relevance, and to confirm these findings.

A thorough understanding of the type and severity of cataracts is crucial for accurately estimating the optimal phacoemulsification energy. In preceding research efforts, an innovative clinical prototype known as the Eye Scan Ultrasound System (ESUS) was developed to facilitate the automated characterization of cataracts. To evaluate the effectiveness of the prototype as a medical tool, extensive data must be collected from several patients with and without cataracts. However, obtaining an adequate number of patients and data for training and testing machine learning models is challenging. To overcome this limitation, the authors implemented a simulated prototype model of the ESUS system, to augment the data. The proposed model encompasses the electric-to-acoustic signal conversion in the ultrasonic transducer, the wave propagation through the eye, and the subsequent acoustic-to-electric signal conversion. Electrical modelling of the transducer was done using a two-port network and the wave propagation was modelled by using the k-Wave MATLAB toolbox. This holistic modelling approach enabled the generation of synthetic data augmentation, presenting great similarity with real data. The synthetic data can then be employed together with real data for the purpose of cataract classification.

Object detection algorithms for open water aerial images present challenges such as small object size, unsatisfactory detection accuracy, numerous network parameters, and enormous computational demands. Current detection algorithms struggle to meet the accuracy and speed requirements while being deployable on small mobile devices. This paper proposes DFLM-YOLO, a lightweight small-object detection network based on the YOLOv8 algorithm with multiscale feature fusion. Firstly, to solve the class imbalance problem of the SeaDroneSee dataset, we propose a data augmentation algorithm called Small Object Multiplication (SOM). SOM enhance dataset balance by increasing the number of objects in specific categories, thereby improving model accuracy and generalization capabilities. Secondly, we optimize the backbone network structure by implementing Depthwise Separable Convolution (DSConv) and the newly designed FC-C2f, which reduces the model's parameters and inference time. Finally, we design the Lightweight Multiscale Feature Fusion Network (LMFN) to address the challenges of multiscale variations by gradually fusing the four feature layers extracted from the backbone network in three stages. In addition, LMFN incorporates the Dilated Re-param Block structure to increase the effective receptive field and improve the model's classification ability and detection accuracy. Experimental results on the SeaDroneSea dataset indicate that DFLM-YOLO improves mAP by 12.4% compared to the original YOLOv8s, while reducing parameters by 67.2%. This achievement provides a new solution for UAVs to conduct object detection missions in open water efficiently.

The exponential growth of user-contributed data provides a comprehensive basis for assessing collective perceptions of landscape change. A variety of possible public data sources exist, such as geospatial data from social media or Volunteered Geographic Information (VGI). Key challenges with such ‘opportunistic’ data sampling are variability in platform popularity and bias due to changing user groups and contribution rules. In this study, we use five case studies to demonstrate how intra- and inter-dataset comparisons can help to assess the temporality of landscape scenic resources, such as identifying seasonal characteristics for a given area, or testing hypotheses about shifting popularity trends observed in the field. By focusing on the consistency and reproducibility of temporal patterns for selected scenic resources and comparisons across different dimensions of data, we aim to contribute to the development of systematic methods for disentangling the perceived impact of events and trends from other technological and social phenomena included in the data. The proposed techniques may help to draw attention to overlooked or underestimated patterns of landscape change, fill in missing data between periodic surveys, or corroborate and support field observations. Despite limitations, the results already provide a comprehensive basis for developing indicators with a high degree of timeliness for monitoring perceived landscape change over time.

Linear Hashing is an important algorithm for many key-value stores. Spiral Storage was invented to overcome the poor fringe behavior of Linear Hashing, but after an influential study by Larson, seems to have been discarded. Since almost 50 years have passed, we repeat Larson’s comparison with in-memory implementation of both to see whether his verdict still stands. Our study shows that Spiral Storage has slightly better look-up performance, but slightly poorer insert performance.

Aquaculture contributes to the sustainable development of food security, marine resource conservation, and economy. Shifting aquaculture feed from fish meal and oil to terrestrial plant-derivatives may result in cost savings. However, many carnivorous fish cannot be sustained on plant-derived materials, necessitating the need for the identification of important factors for farmed fish growth and to investigate whether components derived from terrestrial plants can be used in feed. Herein, we focused on the carnivorous fish leopard coral grouper (P. leopardus) to identify the essential growth factors and clarify their intake timing from feeds. Furthermore, we evaluated the functionality of starch, which are easily produced by terrestrial plants. Results reveal that carbohydrates, which are not considered essential for carnivorous fish, can be introduced as a major part of artificial diet. The development of artificial feed using starch offers the possibility of increasing the growth of carnivorous fish in aquaculture.

Nonlinear optimization (NOPT) is a meaningful tool for solving complex tasks in fields like engineering, economics, and operations research, among others. However, NOPT has problems when it comes to dealing with data variability and noisy input measurements that lead to incorrect solutions. Furthermore, nonlinear constraints may result in outcomes that are either infeasible or suboptimal, such as non-convex optimization. This paper introduces a novel regularized physics-informed neural network (RPINN) framework as a new NOPT tool for both supervised and unsupervised data-driven scenarios. By using custom activation functions and regularization penalties in an artificial neural network (ANN), RPINN can handle data variability and noisy inputs. Besides, it uses physics principles to build the network architecture, computing the optimization variables based on network weights and learned features. In addition, it uses automatic differentiation training to make the system scalable and cut down on computation time through batch-based back-propagation. The test results for both supervised and unsupervised NOPT tasks show that our RPINN can provide solutions that are competitive compared to state-of-the-art solvers. In turn, RPINN’s robustness against noisy input measurements makes it particularly valuable in environments with fluctuating information. Additionally, RPINN’s ANN-based foundation offers significant flexibility and scalability.

As previous study in many countries shown that stroke patient onsets are not distributed randomly, but associate with meteorological factors. However, the relationship between stroke occurence and meteorological factors remain unknown in mountain area in Guizhou China. This paper firstly introduces multi-source fusion data which is integrated by the mountain meteorological factor, geographic mapping elevation information data and stroke population monitoring of Guizhou province. Mainly elaborates from a few aspects, which concludes data collection, data sorting, data extraction, data cleaning and data production in detail. A completed and detailed meteorological stroke data set was successfully established and multi-source data fusion was realized by the use of Gbase and unified data service interface of Guizhou meteorological big data cloud platform. And we report the impact of meteorological variables in Guizhou mountain area climate on stroke. In this study, we performed a statistical fusion data between January 2017 and December 2020 about stroke incidence rate and meteorological factors respectively, for instance, concerning the mean (Mean), maximum (Max), minimum (Min), median (Median), standard deviation (Std) . We calculated stroke rates (date stroke occurence)/(year stroke occurence) and we investigated the distribution of days included in the label. Results: the distribution of the incidence rate basically conforms to the normal distribution with the label Max 0.007399, label Min 0.000204, label Mean 0.002738, label Median 0.002643, label Std 0.00076. We observed a positive significant correlation of stroke incidence rate directly proportional to the daily temperature difference (between 0 and 20 degrees Celsius), as the value of this factor exhibits variation larger, the incidence rate is gradually increasing. And we investigated from the Pearson correlation coefficients that stroke incidence increasing when meteorological factors at low humidity (less than 40% (RH 80%), temperature higher than 31℃); the 24-hour daily temperature difference varies between 6 and 10℃ (6

Achieving Net Zero emissions target is driving up the need for offshore wind as an alternate energy source. Ireland has the capacity to produce upwards of 30GWof power through offshore wind alone. Wind resource assessments are extremely vital in determining the long term trends of a site. The instruments used for this often suffer breakdowns or miss readings which impacts the long term trend analysis. Wind time series data from Ireland’s Marine Institute is used which is shown to have significant gaps in it’s 20 years of service. Data imputation is necessary to fill in these gaps as accurately as possible. This paper compares LSTMs and ARIMA as two competing methodologies for data imputation. LSTMs are shown to be marginally superior to ARIMA imputation with a mean squared error of 0.45 compared to that of ARIMA of 0.60.

To address the challenge of recognizing ship states accurately amidst the complexities of marine environments, this study proposes a novel ship state recognition approach leveraging a graph convolutional neural network (GCNN). Initially, the method extracts canonical and efficient ship motion trajectories from AIS data. Subsequently, a state recognition network tailored for ship motion trajectories is devised and implemented employing graph convolution. Notably, the accuracy of this model is enhanced through the introduction of novel weights and optimization of the Adj parameter. Experimental evaluations conducted on a ship state dataset demonstrate significant performance improvements. Specifically, the proposed recognition network achieves a recognition accuracy of 98.3% for regulated ship trajectories, marking an impressive 8.4% enhancement over traditional convolutional neural networks. This advancement holds promise for enhancing ship state recognition accuracy across diverse maritime applications including maritime supervision, navigation safety, and ship management.

Artificial Intelligence (AI) tools and techniques are comparatively recent advances of present-day globalized world. With their easy availability and friendly user interface AI has affected every sphere of human being. These tools are increasingly becoming popular because of the numerous benefits occurred to the society in many ways. However, there are not only the positive side of these technologies, but also many negative sides. Along with the development and adoption of AI, cyber-attacks are increased and disrupting the information system. Threat actors may misuse artificial intelligence. Hence, these tool designers are working and applying the ability of generative AI can tip the scales in cybersecurity. So, in the age of AI, there is always tension between the cyber attackers and the defenders to make a balanced information system. It is a general rule that defenders must be well in advance in their favor and keep ahead of adversaries. The United National and several governments for example the US, UK, and the big AI giants like Microsoft along with OpenAI, are working on emerging cyberattacks. This research paper explores the concept of information resilience in ML and AI systems, focusing on strategies to enhance their ability to withstand uncertainties, adversarial attacks, and data perturbations.

This research aims to explore factors that influence sustainable music learning system from psychological perspective, and innovatively constructs a combination of qualitative and quantitative approaches. For first time, combines nonlinear system and identifies relevant factors affecting music learning by establishing data system for questionnaire answering and a quantitative model for actual academic performance. Existing research mainly looks at several factors that affect fragmented music learning system from perspective of teachers' teaching rules, emphasizing phased teaching state and learning goals of teachers as main body, thus ignoring music learning students, who are a large group of music learning objects. The research fills gap in this type of research object, focusing on sustainable music learning system from emotional perspective and students who occupy a dominant position in music learning, so as to more accurately explore impact of their emotional influencing factors on music learning system. The most prominent innovation of this study lies in construction of stochastic nonlinear system for psychological influencing factors of student music learning and a quantitative model for actual learning effect. Through analysis of nonlinear system, weight values of several negative emotions on music learning system are obtained. The comprehensive impact of emotional factors and practical learning on music learning system can be obtained by weighting them together.

In response to the issues of sensor noise and accumulated motion errors that lead to low positioning accuracy and insufficient robustness during large maneuvers or continuous flight of small unmanned aerial vehicles (UAVs) in complex environments, this paper proposes a multi-source and multimodal data fusion method. Initially, it employs a multimodal data fusion of various sensors including GPS (Global Positioning System), IMU (Inertial Measurement Unit), and visual sensors to complement the strengths and weaknesses of each hardware component, thereby eliminating motion errors to enhance accuracy. To mitigate the impact of sudden changes in sensor data, the method introduces a digital twin UAV data source. By utilizing the Extended Kalman Filter algorithm, it fuses data from both the real UAV and its digital twin, and the filtered positional information is fed back into the control system of the real UAV. This enables real-time correction of UAV positional deviations caused by sensor noise and environmental disturbances. The multi-source multimodal fusion Kalman filter method proposed in this paper significantly improves the positioning accuracy of UAVs in complex scenarios and the overall stability of the system. This method holds significant value in maintaining high-precision positioning in variable environments and has important practical implications for enhancing UAV navigation and application efficiency.

This study investigates the spatial and temporal dynamics of Paomo restaurants in Xi'an's central urban area from 2012 to 2023, leveraging Point of Interest (POI) data through a series of sophisticated analytical techniques. Methods including nearest neighbor distance, kernel density estimation, and band set statistical analysis were employed to thoroughly examine the evolutionary patterns and key drivers influencing the spatial distribution of these eateries. Our results highlight a notable trend of expansion from the central city to the periphery, characterized by significant spatial agglomeration. Initially concentrated in the city center, the distribution of Paomo restaurants has progressively shifted towards multiple distinct cores, reflecting the dual influence of urban policy initiatives and the dynamics of market competition. Furthermore, the research identifies several pivotal factors shaping this spatial distribution, particularly transportation access, residential quality of life, and the availability of commercial services. These findings demonstrate the profound effects of urban spatial reconfiguration and socioeconomic development on the specialized catering industry. The insights gleaned from this analysis offer valuable guidance for urban planners and policymakers, providing strategic recommendations for the spatial planning of specialty catering services to optimize urban layouts and foster sustainable economic progress.

This research aims to explore factors that influence sustainable music learning system from psychological perspective, and innovatively constructs a combination of qualitative and quantitative approaches. For first time, combines nonlinear system and identifies relevant factors affecting music learning by establishing data system for questionnaire answering and a quantitative model for actual academic performance. Existing research mainly looks at several factors that affect fragmented music learning system from perspective of teachers' teaching rules, emphasizing phased teaching state and learning goals of teachers as main body, thus ignoring music learning students, who are a large group of music learning objects. The research fills gap in this type of research object, focusing on sustainable music learning system from emotional perspective and students who occupy a dominant position in music learning, so as to more accurately explore impact of their emotional influencing factors on music learning system. The most prominent innovation of this study lies in construction of stochastic nonlinear system for psychological influencing factors of student music learning and a quantitative model for actual learning effect. Through analysis of nonlinear system, weight values of several negative emotions on music learning system are obtained. The comprehensive impact of emotional factors and practical learning on music learning system can be obtained by weighting them together.

The Simultaneous Localization And Mapping (SLAM) scanner is an easy and portable Light Detection And Ranging (LiDAR) data acquisition device. Its main output is a 3D point cloud covering the scanned scene. Regarding the importance of accuracy in the survey domain, this paper aims to assess the accuracy of two SLAM scanners: the NavVis VLX and the BLK2GO Scanner. This assessment is conducted for both outdoor and indoor environments. In this context, two types of reference data are used: the Total Station (TS) and the static scanner Z+F Imager 5016. To carry out the assessment, four comparisons are tested: cloud to cloud, cloud to mesh, mesh to mesh, and edge detection board assessment. However, the results of the assessments confirm that the accuracy of indoor SLAM scanner measurements (5 mm) is greater than that of outdoor ones (between 10 mm and 60 mm). Moreover, the comparison of cloud to cloud provides the best accuracy regarding direct accuracy measurement without manipulations. Finally, based on the high accuracy, scanning speed, flexibility, and the accuracy differences between tested cases, it is confirmed that SLAM scanners are effective tools for data acquisition.

: In the realm of data management, data preservation stands as a critical undertaking aimed at preserving and upholding the integrity of data. Regardless of whether it concerns personal or enterprise data, the detrimental effects of malicious alterations implemented by attackers cannot be overlooked. Particularly in conventional industrial control environments, the prevalent practice involves the transmission of data from sensors to databases for storage purposes. However, it is essential to recognize that this process exposes the data to various vulnerabilities. Thus, to ensure the long-term security and reliability of the data, it becomes imperative to implement robust data preservation strategies within these industrial control systems. However, the reliance of these databases on physical hard disks introduces inherent vulnerabilities, including the potential for data loss due to disk damage or targeted malicious attacks. Consequently, it becomes imperative to prioritize the implementation of robust data preservation measures. These measures are crucial in mitigating the risk of disruptions and protecting critical data from compromise. By establishing effective data backup systems, employing advanced security protocols, and implementing proactive monitoring mechanisms, organizations can bolster their data preservation capabilities and safeguard against potential threats to data integrity and availability. As a result, many enterprises opt to store their data with third-party providers to ensure data integrity. However, this approach carries inherent risks. If the third-party service experiences an attack or if the data is tampered with, it becomes challenging to verify the integrity of the data. To address these concerns and ensure data preservation within the context of the Internet of Things (IoT), a growing number of individuals are integrating IoT with Distributed Ledger Technology (DLT). By leveraging DLT, the integrity of data can be ensured, reducing reliance on centralized third-party storage and enhancing security in the IoT ecosystem. In this article, IOTA is the DLT, which employs Directed Acyclic Graph (DAG) to store transaction information. Compared to Ethereum or other blockchain technologies, IOTA offers notable advantages in terms of transaction verification speed, making it highly suitable for real-time IoT environments. However, the conventional transmission path from sensors to IOTA nodes entails a complex route, involving multiple hardware devices before reaching the intended destination. This complexity poses challenges in ensuring data integrity during transmission and introduces vulnerabilities such as man-in-the-middle attacks or SQL injection attacks. To address these issues, we propose a method to streamline the transmission path between sensors and IOTA, specifically tailored for industrial fields with numerous IoT devices. Our approach involves preprocessing the data stored on the server using our method before uploading, ensuring data confidentiality, and leveraging IOTA to guarantee data integrity. To achieve the shortest path between IoT and DLT nodes, it becomes necessary to establish IOTA nodes on lower-level devices, such as Raspberry Pi or IoT controllers. By simplifying the transmission path, we can reduce the potential for tampering and enhance overall data security. Implementing our proposed method enables the assurance of data confidentiality and integrity during both transmission and storage on the server, strengthening the trustworthiness of the IoT, and IOTA integration.

The described data set contains features from the machine control of a five-axis milling machine. The features were recorded during thirteen series productions. Each series production includes a changeover process in which the machine was set up for the production of a different product. In addition to the timestamps and the twenty recorded features derived from Numerical Control (NC) control variables, the data set also contains labels for the different production phases. For this purpose, up to 23 phases were assigned, which are based on a generalized milling process. The data set consists of thirteen .csv files, each representing a series production. The data set was recorded in a production company in the contract manufacturing sector for components with real series orders in ongoing industrial production.

Solar flares are characterized by sudden bursts of electromagnetic radiation from the Sun’s surface, and caused by the changes in magnetic field states in solar active regions. Earth and its surrounding space environment can suffer from various negative impacts caused by solar flares ranging from electronic communication disruption to radiation exposure-based health risks to the astronauts. In this paper, we address the solar flare prediction problem from magnetic field parameter-based multivariate time series (MVTS) data using multiple state-of-the-art machine learning classifiers that include MINImally RandOm Convolutional KErnel Transform (MINIROCKET), Support Vector Machine (SVM), Canonical Interval Forest (CIF), Multiple Representations SEQuence Learner (Mr-SEQL), and Long Short-Term Memory (LSTM)-based deep learning model. Our experiment is conducted on the on the Space Weather ANalytics for Solar Flares (SWAN-SF) benchmark data set, which is a partitioned collection of MVTS data of active region magnetic field parameters spanning over 9 years of operation of the Solar Dynamics Observatory (SDO). The MVTS instances of the SWAN-SF dataset are labeled by GOES X-ray flux-based flare class labels, and attributed to extreme class imbalance because of the rarity of the major flaring events (e.g., X and M). As a performance validation metric in this class-imbalanced dataset, we used the true skill statistic (TSS) score. Finally, we demonstrate the advantages of the MVTS learning algorithm MINIROCKET, which outperformed the aforementioned classifiers without the need for essential data preprocessing steps such as normalization, statistical summarization, and class imbalance handling heuristics.

The study focused on the technical and scale efficiency of smallholder pineapple farmers in the Central Region of Ghana. The input-oriented Data Envelopment Analysis (DEA) was used to estimate technical, pure and scale efficiencies of the smallholder pineapple farmers, of which a random sampling procedure was used to select 320 respondents. The study revealed that the farmers were technically inefficient with mean technical efficiency under Constant Returns to Scale (CRS), pure efficiency under Variable Returns to Scale (VRS) and the Scale Efficiency levels of 0.505, 0.641 and 0.772, respectively, due to farmers’ inability to exploit fully the available technology while experiencing evident post-harvest losses resulting from low adoption of post-harvest technologies. Such findings are meaningful and could help the farming communities and relevant policymakers to understand the issues in farming production and hence undertake necessary actions to potentially improve farmers’ technical and scale efficiencies in the study area.

This is an exercise to explore the concentration of Lithium, Lithium-7 isotope and the possible presence of black dirty ice in the lunar surface using spectral data obtained from the Clementine mission. The main interest in tracing the lithium and presence of dark ice in the lunar surface are closely related to future human settlement missions in the Moon. We investigate the distribution of Lithium and 7 Li isotope on the Lunar surface, employing spectral data from the Clementine images. We utilized Visible (VIS-NIR) imagery at wavelengths of 450, 750, 900, 950, and 1000 nm, along with Near-Infrared (NIR-SWIR) at 1100, 1250, 1500, 2000, 2600, and 2780 nm, encompassing 11 bands in total. This dataset offers a comprehensive coverage of about 80% of the lunar surface, with resolutions ranging from 100 to 500 meters, spanning latitudes from 80°S to 80°N. In order to extract quantitative abundance of Lithium, ground truth sites were used to calibrate the Clementine images. Samples (12045, 15058, 15475, 15555, 62255, 70035, 74220 and 75075) returned from Apollo missions 12, 15, 16 and 17 have been correlated to the Clementine VIS-NIR bands and five spectral ratios. The 5 spectral ratios calculated synthesize the main spectral features of sample spectra that were grouped by their Lithium and 7 Li content using Principal Component Analysis. The ratios spectrally characterize substrates of anorthosite, silica-rich basalts, olivine-rich basalts and High-T mare basalts and Orange soils. Our findings reveal a strong linear correlation between the spectral parameters and the lithium content in the 8 Apollo samples. With the values of the 11 Clementine bands and the 5 spectral ratios for each of the 8 lunar soils we performed linear regression models to estimate the concentration of Lithium and 7 Li. Also, we calculated Digital Terrain Models (DTMs; Altitude, Slope, Aspect, DirectInsolation and WindExposition) from LOLA-DTM to discover relations between relief and spatial distribution of the extended models of lithium and 7 Li. The analysis was conducted in a mask polygon extracted from Lunar Orbiter Laser Altimeter (LOLA) and located around the Apollo 15 landing site. This analysis seeks to uncover potential 7 Li enrichment through spallation processes, influenced by varying exposure to solar wind. To explore the possibility of find ice mixed with regolithe (black ice) we used a spectral library (350-2500nm) form ices dirty with different concentration of volcanic particles.

Analytical data platform have been used for decades for improving the organizational performance. Starting from the data warehouses used primarily for structured data processing, through the data lakes oriented for raw data storage and post-hoc data analyses, to the data lakehouses − a combination of raw storage and business intelligence pre-processing for improving the platform efficacy. But in recent years a new architecture called Data Mesh has emerged. The main promise of this architecture is to remove the barriers between operational and analytical teams in order to boost the overall value extraction from the big data. A number of attempts has been made to formalise and to implement it in existing projects. Although being defined as a socio-technical paradigm, data mesh still lacks the technology support for enabling its widespread adoption. To overcome this limitation, we propose a new view of the platform requirements alongside the formal governance definition that we believe can help in successful adoption of the data mesh. It is based on fundamental aspects such as decentralized data domains and federated computational governance. In addition, we also present a blockchain-based implementation of a mesh platform as a practical validation to our theoretical proposal. Overall, this article demonstrates a novel research direction of the information system decentralization technologies.

In response to the growing challenges in drone security and airspace management, this study introduces an advanced drone classifier, capable of detecting and categorizing Unmanned Aerial Vehicles (UAVs) based on acoustic signatures. Utilizing a comprehensive database of drone sounds across EU-defined classes (C0 to C3), this research leverages machine learning (ML) techniques for effective UAV identification. The study primarily focuses on the impact of data augmentation methods—pitch shifting, time delays, harmonic distortion, and ambient noise integration—on classifier performance. These techniques aim to mimic real-world acoustic variations, thus enhancing the classifier's robustness and practical applicability. Results indicate that moderate levels of augmentation significantly improve classification accuracy. However, excessive application of these methods can negatively affect performance. The study concludes that sophisticated acoustic data augmentation can substantially enhance ML-driven drone detection, providing a versatile and efficient tool for managing drone-related security risks. This research contributes to UAV detection technology, presenting a model that not only identifies but also categorizes drones, underscoring its potential for diverse operational environments.

The development of storage standards for databases of different nature and origin makes it possible to aggregate and interact with different data sources in order to obtain and show complex and thematic information to the end user. This article aims to analyze some possibilities opened up by new applications and hypothesize their possible developments. With this work, using the currently available Web technologies, we would like to verify the potential of the use of Linked Open Data in the world of WebGIS and illustrate an application that allows the user to interact with Linked Open Data through their representation on a map. Italy has a artistic and cultural heritage unique in the world and the italian Ministry of Cultural Heritage and Activities and Tourism has created and made freely available a dataset in Linked Open Data format that represents it. With the aim of enhancing and making this heritage more usable, the National Research Council (CNR) has created an application that presents this heritage via WebGIS on a map. Following criteria definable by the user, such as the duration, the subject of interest and the style of the trip, tourist itineraries are created through the places that host this heritage. New possibilities open up where the tools made available by the Web can be used together, according to pre-established sequences, to create completely new applications. This can be compared to the use of words, all known in themselves, which, according to pre-established sequences, allow us to create ever new texts.

The development of U.S. Army and NATO data link systems is introduced first, and then the development trend of future intelligent data link is summarized into integration, generalization, multifunctionality and high security. A unit-level combat system architecture based on the global combat cloud, which is capable of realizing the flexible scheduling of global combat resources and maximizing the overall combat effectiveness, is proposed. Intelligent data link is an important part of this solution, providing strong information support for future urban unit-level warfare.

It is essential to deal with data scattered among heterogeneous information sources, which can be structured, semi-structured, or unstructured, to give consumers a cohesive perspective of the data. Information gathering is challenging as a result, and one of the major causes of this is that data sources are developed to support specific applications. A method to simplify this procedure is to use ontology representation as an intermediate step. An ontology represents a knowledge structure that reasonably reflects the real world's complexity and is ideally used in many industries today. This research aims to enhance the functionality of a global ontology system by implementing and integrating a natural language query system. Leveraging NLP-based approaches, we constructed SPARQL queries for our ontologies to facilitate natural language translation into a well-structured query format. A dedicated query component was developed to transform natural language questions into SPARQL queries, with the selection of the optimal query graph to generate the final queries. In the subsequent phase, we explored the integration of distinct sentence encoders to improve latent sentence representations during query construction. The generated SPARQL queries were executed on the global ontology output and then translated into source-specific questions. This innovative approach enables unified access to heterogeneous data sources through a user-friendly natural language querying interface.

(1) Background: Aim was to investigate real-world effectiveness (hypothesizing non-inferiority) and safety profile of risdiplam in paediatric and adult nusinersen-risdiplam spinal muscular atrophy (SMA) switch cohort. (2) Methods: A retrospective and anonymous collection of relevant demographic and clinical data for all Croatian SMA patients switched from nusinersen to risdiplam up to September 2023 (reimbursed by Croatian Health Insurance Fund – CHIF) was performed using CHIF database and associated reimbursement documentation. Patients were included in effectiveness and safety analysis if they met the following inclusion criteria: i) risdiplam reimbursed by CHIF; ii) patient received at least 6 doses of nusinersen before switch to risdiplam; iii) no relevant pause between the latter disease modifying drugs (DMDs); iv) availability of all prespecified studied data and parameters. (3) Results: 17 patients met inclusion criteria [58.9% female; median age 12.75 (3.0-44.5) yr.]. In our ‘switch’ cohort, we have demonstrated a non-inferiority of risdiplam to nusinersen, in SMA 1 (+1.0 in CHOP INTEND; p=0.067), SMA 3p (+0.7 in HFMSE; p=0.897) and SMA 3a (+0.8 in RHS; p=0.463) subpopulations, during a one-year follow-up period. There were no reports on respiratory function worsening, feeding worsening, and no lethal events. No new safety concerns were identified, except of the weight gain that arose as a new potential adverse drug reaction ‘signal’ in two patients. (4) Conclusions: We have reported a pivotal real-world findings on switching SMA patients from nusinersen to risdiplam and demonstrated its effectiveness (non-inferiority), safety and tolerability in a heterogenous paediatric and adult ‘switch’ cohort, which will further increase the quality and standards of care as well as safety of a notable portion of SMA patients; especially for those who demand switch from nusinersen to other DMDs from clinical or personal reasons.

Urbanization triggers the emergence of slums in urban areas. Palembang is one of the Indonesian cities with slum settlements. This research aimed to analyze the interpolation of slum positions in Palembang and their distribution pattern using kernel density analysis and by modeling spatial data on accuracy values. It employed a quantitative method with a survey approach. Samples were selected using proportional random sampling from families in 64 slum areas across the 13 districts in the city, and their positions were recorded with a GPS device and then processed and mapped in ArcGIS. The data were analyzed with inverse distance weighted, kernel density, and spatial data modeling. Results showed that slum areas near the riverbanks had high population density, while those located further were lower. The values obtained from the kernel density analysis varied from 0 to 58.1123, while the inverse distance weighted showed a value range of 2.26745–380.991. The spatial data modelling analysis demonstrated that the distribution of slum areas was widely spread along the Musi River, with an accuracy value of 96.8%, which falls within the range of >0.9-1.

Road collisions are among the world’s critical issues causing many casualties, deaths, and economic losses. To deal with this scenario, precise analysis is required. In this paper, we use Machine Learning (ML) techniques to assess and predict road traffic collisions. An ensemble machine learning model with two layers was developed to analyze simulation data from the driving simulator. The first (base) layer integrates supervised learning techniques namely, k- Nearest Neighbors (k-NN) AdaBoost, Naive Bayes (NB), and Decision Trees (DT). The second layer predicts road collisions by combining the base layer outputs by employing the stacking ensemble method using logistic regression as a meta-classifier. The data for this study were imbalanced; therefore, we performed a SMOTE resampling strategy to handle the dataset imbalance. To simplify the model, the PSO algorithm was used to select the most important features in our dataset. The two-layer ensemble model proposed had the best outcomes with an accuracy of 88%, F1 score of 83%, and an AUC of 86% as compared with k-NN, DT, NB, and AdaBoost.

In today's world, wherein more than 80% of world trade is carried out by maritime routes, the safety and security of the seas where this trade takes place is of vast importance for nations and the in-ternational community. For this reason, ensuring the sustainable safety and security of the seas has become an integral part of the mission of all maritime-related entities. The utilization of big data extracted from the seas and maritime activities into meaningful information with artificial intelli-gence applications and developing applications that can be used in maritime surveillance will be of great importance for augmenting maritime safety and security. In this article, data sources which can be used by a maritime surveillance system based on big data and artificial intelligence tech-nologies and which can be established around sensitive sea areas and critical coastal facilities, are identified and a model proposal using this maritime big data is put forward.

Measurements of systems taken along a continuous functional dimension, such as time or space, are ubiquitous in many fields, from the physical and biological sciences to economics and engineering. Such measurements can be viewed as realisations of an underlying smooth process sampled over the continuum. However, traditional methods for independence testing and causal learning are not directly applicable to such data, as they do not take into account the dependence along the functional dimension. By using specifically designed kernels, we introduce statistical tests for bivariate, joint, and conditional independence for functional variables. Our method not only extends the applicability to functional data of the Hilbert-Schmidt independence criterion (HSIC) and its d-variate version (d-HSIC), but also allows us to introduce a test for conditional independence by defining a novel statistic for the conditional permutation test (CPT) based on the Hilbert-Schmidt conditional independence criterion (HSCIC), with optimised regularisation strength estimated through an evaluation rejection rate. Our empirical results of the size and power of these tests on synthetic functional data show good performance, and we then exemplify their application to several constraint- and regression-based causal structure learning problems, including both synthetic examples and real socio-economic data.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.

In this study, we conducted experiments to assess the forecasting capabilities for the tropical cyclone (TC) genesis over the South China Sea using the ensemble-based data assimilation system (EPS-DA) by WRF-LETKF. These experiments covered forecast lead times of up to 5 days and spanned a period from 2012 to 2019, involving a total of 45 TC formation events. The evaluation involved forecast probability assessments and positional and timing error analysis. Results indicated that successful forecasting depends on lead time and initial condition quality. For TC formation from an embryo vortex to tropical depression intensity, the EPS-DA system demonstrated improved accuracy as the forecast cycle approached the actual formation time. TC centers converged toward observed locations, highlighting the potential of assimilation up to 5 days before formation. We examined statistical variations in dynamic and thermodynamic variables relevant to TC processes, offering an objective system assessment. Our study emphasized early warnings of TC development appear linked to formation-time environmental conditions, particularly strong vorticity and enhanced moisture processes.

Wireless sensor networks (WSN) are widely used in various fields such as military, industrial and transportation for real-time monitoring, sensing and data collection of different environments or objects. However, the development of WSN is hindered by several limitations, including energy, storage space, computing power and data transmission rate. Among these, the availability of power energy plays a crucial role as it directly determines the lifespan of WSN. To extend the life cycle of WSN, two key approaches are power supply improvement and energy conservation. Therefor, we proposed an energy harvesting system and a low energy consumption mechanism for WSN. Firstly, we delved into the energy harvesting technology of WSN, explored the utilization of solar energy and mechanical vibration energy to ensure a continuous and dependable power supply to the sensor nodes, and analyzed the voltage output characteristics of bistable piezoelectric cantilever. Secondly, we proposed a neighbor discovery mechanism that utilizes a separation beacon, is based on reply to ACK, and can facilitate the identification of neighboring nodes. This mechanism operates at a certain duty cycle ratio, significantly reduces idle listening time and results in substantial energy savings. In comparison to the Disco and U-connect protocols, our proposed mechanism achieves a remarkable reduction of 66.67% and 75% in the worst discovery delay, respectively. Furthermore, we introduced a data fusion mechanism based on integer wavelet transform. This mechanism effectively eliminates data redundancy caused by spatio-temporal correlation, results in a data compression rate of 5.42. Additionally, it significantly reduces energy consumption associated with data transmission by the nodes.

This study explores the potential of data science software solutions like Customer Relationship Management Software (CRM) for increasing the revenue generation of businesses. We focused on those businesses in Accommodation and Food Service sector across the European Union (EU). The investigation is contextualized within the rising trend of data-driven decision making, examining the potential correlation between data science application and business revenue. Employing a comprehensive evaluation of Eurostat datasets from 2014 to 2021, we used both univariate and multivariate analyses, we assessed e-commerce sales data across countries, focusing on the usage of big data and CRM tools. Big data utilization showed a clear, positive relationship with enhanced e-commerce sales. However, CRM tools exhibited a dualistic impact: while their use in marketing showed no significant effect on sales, their application in non-marketing functions had a negative correlation. These findings underscore the potential role of CRM and data science solutions in enhancing business performance in the EU's Accommodation and Food Service industry.

Continuous glucose monitoring devices allow diabetes condition management. However, when limited data is available, one option is to increase their size by generating synthetic samples. From a homemade wearable prototype was created a real dataset with 18 instances and 53 attributes that capture characteristics of capillary and venous blood glucose, oxygen concentration, pulse rate, skin temperature, and 24 modules and 24 phases related to bio-impedance. The objective of this article is to generate synthetic datasets, and also it investigates the ideal features subset and optimal model for non-invasive diabetes prediction. Gaussian-Copulas (GC), conditional generative adversarial networks (CG), variational autoencoders, and Copula-GAN techniques' were used to generate five synthetic datasets. Experiments show that GC1 and GC2 datasets follow min/max boundaries and are not copies of the original data. Multilayer perceptron regressor outperformed (train and test) with 2.17, 2.51 in MAE; 9.29, 13.59 in MSE; 3.05, 3.69 in RMSE, and 0.95, 0.92 in R2 in GC1, and 2.64, 3.02 in MAE; 11.43, 15.11 in MSE; 3.38, 3.89 in RMSE, and 0.94, 0.92 in R2 in GC2 with eight features. Future work is necessary to explore autoencoder and generative architectures, datasets with diverse characteristics, and the effect of the number of features.

Machinery parts gradually wear out over time due to regular usage. To improve machinery health and prevent critical issues, a reliable prognosis framework can be implemented by monitoring the behaviour of machinery parts and issuing warnings before they reach a critical state. To achieve this, vibration data from roller bearings experiencing various fault conditions have been collected. Different techniques from the literature were combined to analyze the distinct configurations in the vibration data sets and identify the main defects in roller bearings. The significant features extracted from this analysis were then used to create optimized stochastic model equations, separately regressing inner and outer race fault features to healthy bearing features under random conditions. These models can help engineers design more dependable systems, optimize their performance, and minimize the risk of failures and downtime.

Prevention and management of cytomegalovirus (CMV) reactivation is important to improve outcome of allogeneic hematopoietic cell transplantation (allo-HCT) recipients. The aim of this study was to analyze real-world data for incidence and characteristics of CMV infections until 1-year after allo-HCT under 100-day letermovir prophylaxis. A single-center retrospective study was conducted between November 2020 and October 2021. During the study period, 358 patients underwent allo-HCT, 306 of whom received letermovir prophylaxis. Cumulative incidence of clinically significant CMV infection (CS-CMVi) was 11.4%, 31.7%, and 36.9% at 14-weeks, 24-weeks, and 1-year post-HCT, respectively. In multivariate analysis, risk of CS-CMVi increased with graft-versus-host disease (GVHD) ≥ grade 2 (adjusted odds ratio 3.640 [2.036–6.510]; P &lt; 0.001). One-year non-relapse mortality was significantly higher in letermovir breakthrough CS-CMVi patients than those with subclinical CMV reactivation who continued letermovir (P = 0.002). There were 18 (15.9%) refractory CMV infection in this study population. In summary, letermovir prophylaxis is effective in preventing CS-CMVi until day 100, which increased after cessation of letermovir. GVHD is still a significant risk factor in letermovir prophylaxis era. Further research is needed to establish individualized management strategies especially in patients with significant GVHD or letermovir breakthrough CS-CMVi.

Although learning analytics (LA) holds great potential to improve teaching and learning, LA research and practice are currently riddled with limitations that impact every stage of the LA life cycle. The present paper offers an overview of these challenges before proposing strategies to overcome them and exploring how the recent innovations brought forth by language models can improve LA research and practice. In particular, we encourage the empowerment of teachers during LA development, as this would strengthen the theoretical foundation of LA solutions and increase their interpretability and usability. Furthermore, we provide examples of how process data can be used to understand learning processes and generate more interpretable LA insights. Furthermore, we explore how LLMs could come into play in LA to generate interpretable insights, timely and actionable feedback, increase personalization, and support teachers’ tasks more broadly.

We have developed additive logistic models for the occurrence of lightning, large (≥ 2 cm), and very large (≥ 5 cm) hail to investigate the evolution of these hazards in the past, in the future, and for forecasting applications. The models, trained with lightning observations, hail reports, and predictors from atmospheric reanalysis, assign an hourly probability to any location and time on a 0.25° × 0.25° × 1-hourly grid as a function of reanalysis-derived predictor parameters, selected following an ingredients- based approach. The resulting hail models outperform the Significant Hail Parameter and the simulated climatological spatial distributions and annual cycles of lightning and hail are consistent with observations from storm report databases, radar, and lightning detection data. As a corollary result, CAPE released above the -10°C isotherm was found to be a more universally skilful predictor for large hail than CAPE. In the period 1950–2021, the models applied to the ERA5 reanalysis indicate significant increases of lightning and hail across most of Europe, primarily due to rising low-level moisture. The strongest modelled hail increases occur in northern Italy with increasing rapidity after 2010. Here, very large hail has become 3 times more likely than it was in the 1950s. Across North America trends are comparatively small, apart from isolated significant increases in the direct lee of the Rocky Mountains and across the Canadian Plains. In the southern Plains, a period of enhanced storm activity occurred in the 1980s and 1990s.

This study aims to identify the knowledge structure and research trends of soccer psychology research during the last 33 years (1990–2022). Data were obtained from 1,863 papers from the Web of Science database. The data were collected through keyword text mining and data preprocessing to determine the keywords needed for analysis. Based on the keywords, latent Dirichlet allocation-based topic modeling analysis was performed to analyze the topic distribution of papers and explore research trends by topic area. The topic modeling process included four topic area and fifty topics. The “Coaching Essentials in Football” topic area had the highest frequency, but it was not statistically identified as a trend. However, coaching, including training, is expected to continue to be an important research topic, as it is a key requirement for success in the highly competitive elite football world. Interest in the research field of “Psychological Skills for Performance Development” has waned in recent years. This may be due to the predominance of other subject areas rather than a lack of interest. Various high-tech interventions and problem-solving attempts are being made in this field, providing opportunities for qualitative and quantitative expansion. “Motivation, cognition, and emotion” is a largely underrated subject area in soccer psychology. This could be because survey-based psychological evaluation attempts have decreased as the importance of rapid field application has been emphasized in recent soccer-related studies. However, measuring psychological factors contributes to the study of football psychology through a new methodology and theoretical background. Recognizing the important role of psychological factors in player performance and mental management, as well as presenting new research directions and approaches that can be directly applied to the field, will advance soccer psychology research.

Nonparametric density estimation for nonnegative data is considered in a situation where a random sample is not directly available but the data are instead observed from the length-biased sampling. Due to the boundary bias problem of the location-scale kernel, the approach in this paper is an application of asymmetric kernel. Two nonparametric density estimators are proposed. The mean integrated squared error, strong consistency, and asymptotic normality of the estimators are investigated. Some simulations illustrate the finite sample performance of the estimators.

A novel simplifying Volterra structure algorithm is proposed for intensity modulation direct detection (IM-DD) optical fiber short distance communication system by using the decision feedback equalization algorithm (DFE). Based on this algorithm, the signal damage for four-level pulse amplitude modulation signal (PAM-4) is compensated, which is caused by device bandwidth limitation and dispersion during transmission. Experiments have been carried out using a 25GHz Electro-absorption Modulated Laser (EML), showing that PAM-4 signals can transmit over 10km in standard single-mode fiber (SSMF). The 112Gbps and 128Gbps signals can reach the error rate threshold of KP4-FEC (BER=2*10-4) and HD-FEC (BER=3.8*10-3), respectively. The simplified principle and process of proposed Volterra-based equalization algorithm are presented. Experimental results show that the algorithm complexity is greatly reduced by 75%, which provides an effective theoretical support for the commercial application of this algorithm.

Data-Flow and Higher-Order Mutation are white-box testing techniques. To our knowledge, no work has been proposed to compare data flow and higher-order mutation. This paper compares all def-uses data-flow and second-order mutation criteria. This compassion investigates the subsumption relation between these two criteria and evaluates the effectiveness of test data developed for each. To compare the two criteria, a set of test data satisfying each criterion is generated, which is used to explore whether one criterion subsumes the other criterion and assess the effectiveness of the test set that was developed for one methodology in terms of the other. The results showed that the mean mutation coverage ratio of the all du-pairs adequate test cover is 80.9%, and the mean data flow coverage ratio of the 2nd-order mutant adequate test cover is 98.7%. Consequently, 2nd-order mutation “ProbSubsumes” the all du-pairs data flow. The failure detection efficiency of the mutation (98%) is significantly better than the failure detection efficiency of data flow (86%). Consequently, 2nd-order mutation testing is “ProbBetter” than all du-pairs data flow testing. In contrast, the size of the test suite of 2nd-order mutation is more significant than the size of the test suite of all du-pairs.

CNN-based off-the-shelf features have shown themselves as a good baseline for trademark retrieval. However, in recent years, the computer vision area was transitioning from CNNs to a new architecture – Vision Transformer. In this paper, we investigate the performance of off-the-shelf features extracted with vision transformers and explore the effects of pre, post-processing, and pre-training on big datasets. We propose a method of joint usage of global and local features, which leverages the best aspects of both approaches. Experimental results on METU Trademark Dataset show that off-the-shelf features extracted with ViT-based models outperform off-the-shelf features from CNN-based models. The proposed method achieves the mAP value of 31.23, surpassing previous state-of-the-art results. We assume that the proposed approach for the trademark similarity evaluation will allow one to improve the protection of such data with the help of artificial intelligence methods. Moreover, this approach will allow one to identify cases of unfair use of such data and form an evidence base for litigation.

This contribution shows the possibilities of a low-cost multipurpose data logger that was built around an Arduino Mega 2560 single board computer. To transform the Arduino Mega into such a data logger, a sensor shield was designed that contains an SD-card, real-time clock, and different kinds of connectors so that sensors can easily be attached to the device. The software considers a wide range of predefined sensors from which a user can choose. To assess the performance of such a device, short-term monitoring campaigns in relation to outdoor air quality, human activity in an office, motion of a journey on a bike, and exhaust gas monitoring of a diesel generator were realized. Besides the possibilities to apply the data logger in different kinds of applications, a method is proposed to assess the credibility of such a system. The assessment based on the various short-term campaigns showed that the system scores positively on most of the performance indicators, but that unexpected (black swan) events affect the assessment over the longer term. This makes the development of low-cost scientific instruments harder than expected. The stability and long-term performance of this type of design requires continuous evaluation and engineering correction.

The practical utility of remote sensing techniques relies on validating them with ground-truth data. Validation requires similar spatial-temporal scales for ground measurements and remote sensing resolution. Evapotranspiration (ET) estimates are commonly compared to weighing lysimeter data, which provide precise but localized measurements. To address this limitation, we propose using superconducting gravimeters (SG) to obtain ground-truth ET data at larger spatial scales. SG measure gravity acceleration with high resolution (tenths of nm/s2) within a few hundred meters. Similar to lysimeters, gravimeters provide direct estimates of water mass changes for determining ET without soil disturbance. To demonstrate the practical applicability of SG data, we conducted a case study in Buenos Aires Province, Argentina (-34.87, -58.14). We estimated cumulative ET values for 8-day and monthly intervals using gravity and precipitation data from the study site. Comparing these values with MODIS-based ET products (MOD16A2), we found a very good agreement at the monthly scale, with an RMSE of 32.6 mm/month (1.1 mm/day). This study represents progress in using SG for hydrogeological applications. The future development of lighter and smaller gravimeters is expected to further expand their use.

Nonnegative matrix factorization (NMF) has been shown to be a strong data representation technique, with applications in text mining, pattern recognition, image processing, clustering and other fields. In this paper, we propose a hypergraph regularized Lp smooth nonnegative matrix factorization (HGSNMF), by incorporating hypergraph regularization and Lp smoothing constraint terms into the standard NMF. The hypergraph regularization term can capture the intrinsic geometry structure of the high dimension space data more comprehensively than simple graph, the Lp smoothing constraint may yield a smooth and more accurate solution to the optimization problem. The updating rules are given using multiplicative update techniques, and the convergence of HGSNMF is theoretically investigated. The experimental results on four different data sets show that the proposed method has better clustering effect than the related state-of-the-art methods in the vast majority of cases.

With the prevalence and evolution of social media platforms, social media data have emerged as a crucial source for obtaining spatio-temporal information about various urban events. Providing accurate spatio-temporal information of these events enhances the capacities of urban management and emergency response. However, existing research mostly focuses on the textual content while mining this spatio-temporal information, often neglecting data from other modalities like images and videos.To address this, our study introduces a novel method for extracting spatio-temporal information from multi-modal social media data (MIST-SMMD), serving as a valuable supplement to current urban event monitoring methods. Leveraging deep learning and Geographic Information System (GIS) technologies, we extract spatio-temporal information from large-scale, multi-modal Weibo data about urban waterlogging events at both coarse and fine granularities.Through an in-depth experimental evaluation of the “July 20 Zhengzhou extreme rainstorm” event, the results show that in coarse-grained spatial information extraction solely using textual data, our method achieves a Spatial Precision of 87.54% within a 60m range and 100% Spatial Precision within a 201m range. In the fine-grained spatial information extraction, by incorporating other modalities such as images and videos, the Spatial Error saw a significant improvement, with MAESE increasing by 95.53% and RMSESE by 93.62%.These outcomes illustrate the capability of the MIST-SMMD method in extracting spatio-temporal information of urban events at both coarse and fine granularities. They also confirm the notable advantage of multi-modal data in enhancing the accuracy of spatial information extraction.

Data scarcity is a significant challenge in the field of Machine Learning (ML), as data collection can be expensive, time-consuming, and difficult, particularly in developing countries. This challenge is exaggerated on the need to use dataset for livestock disease predictions for early intervention and surveillance. To address this challenge, this paper presents a data synthesis method that has been used to accurately generate new data samples from few real-world data. With much data available to train the ML models, overfitting is eliminated. We present the use of Generative Adversarial Networks mainly the Conditional Tabular Generative Adversarial Network to synthesize categorical data for training machine learning models for prediction of the Pestes des Petits Ruminants (PPR) disease. The results showed that training score became 0.89 and the cross-validation score was 0.87 after synthesized data was used with Random Forest algorithm. The resulting dataset can be used to support the prediction and surveillance of the Pestes des Petits Ruminants (PPR) disease. The proposed method can also be applied to any domain with categorical data, and has the potential to improve the performance of machine learning models with increased data availability.

Plant Factory Transplanter (PFT) is a key component of the plant factory system. Its operation status directly affects the quality and survival rate of planted seedlings, which in turn affects the overall yield and economic efficiency. To monitor the operation status and transplanting quality of a transplanting machine in a timely manner, the primary task is to use a computerized and easy-to-use method to monitor the transplanting units. Inspired by the latest developments in augmented reality and robotics, a DT model-based and data-driven online monitoring method for plant factory transplanting equipment is proposed. First, a data-driven and virtual model approach is combined to construct a multi-domain digital twin of the transplanting equipment. Then, taking the vibration frequency domain signal above the transplanting manipulator and the image features of the transplanting seedling tray as input variables, the evaluation method and configuration method of the PFT digital twin system are proposed. Finally, the effect of the transplanter is evaluated, and the cycle can be repeated to optimize the transplanter to achieve optimal operation parameters. The results show that the digital twin model can effectively use the sensor data to identify the mechanical vibration characteristics and avoid affecting transplanting quality due to mechanical resonance. At a transplanting rate of 3000 plants/h, the transplanting efficiency can be maintained at a high level and the vibration signal of X, Y, Z-axis above the transplanting manipulator is relatively calm. In this case, Combined the optimal threshold method with the traditional Wiener algorithm, the identification rate of healthy potted seedlings can reach 94.3%. Through comprehensively using the optimal threshold method and 3D block matching filtering algorithm for image threshold segmentation and denoising, the recognition rate of healthy seedlings has reached over 96.10%. In addition, the developed digital twin can predict the operational efficiency and optimal timing of the detected transplanter, even if the environmental and sensor data are not included in the training. The proposed digital twin model can be used for damage detection and operational effectiveness assessment of other plant factory equipment structures.

This paper proposes a data-driven approach to the calculation of ship overtaking boundary conditions in narrow channels based on ship overtaking characteristics by the Automatic Identification System (AIS) data. First, we collect the ship tracking process data in a narrow channel by processing the original AIS data, followed by a normality test and correlation analysis, and finally, the boundary conditions are obtained using a weighted K-means clustering algorithm. to identify the relevant data. We applied the proposed approach to estimate the overtaking boundary conditions of ships in the straight channel section of Shanghai South Passage. The method yields boundary conditions that significantly reduce collision risk when a ship engages in pursuit behavior in narrow waterways, providing a scientific basis for the overtaking of Marine Autonomous Surface Ships (MASS) in autonomous navigation within such environments, further promoting the automation level of USVs and autonomous vessels.

We explore several aspects of replica synchronization with the goas of retrieving the value of parameters for the Lorenz system. The idea is that of having a computer replica (slave) of a natural system (master, simulated in this paper), and exploit the fact that slave synchronizes with the master only if they evolve with the same parameters. As a byproduct, in the synchronized phase the state variables of the slave and that of the master are the same, thus allowing to perform measurements impossible on the real system. We review some aspects of master-slave synchronization using a subset of variables, with intermittent coupling. We show how synchronization can be achieved when some of the state variables are available for direct measurement using a simulated annealing approach, and also when they are accessible only through a scalar function, using a pruned-enriching ensemble approach, similar to genetic algorithms without cross-over.

Biofilm is a complex community of microorganisms that are attached to surfaces and encased in a self-produced extracellular matrix. Machine learning (ML) techniques have been applied to various aspects of biofilm research, such as predicting biofilm formation, identifying key genes, and designing new therapeutic strategies. In this study, we conducted a bibliometric analysis of machine learning in biofilm research to provide a comprehensive overview of the current state of the field. We searched the Web of Science database for articles published included "machine learning biofilm". A total of 126 articles were identified and analysed. Our results showed that the number of publications on machine learning in biofilm has been increasing rapidly over the past decade, indicating a growing interest in the application of ML techniques to biofilm research. The analysis also revealed that the most common research topics in this area were related to biofilm formation, prediction, and control. Furthermore, the most frequently used ML techniques in biofilm research were artificial neural networks and support vector machines. Overall, our study provides valuable insights into the current trends and future directions of machine learning in biofilm research. It also highlights the importance of interdisciplinary collaboration between biofilm researchers and ML experts to drive innovation in this field.

As public health laboratories expand their genomic sequencing and bioinformatics capacity for the surveillance of different pathogens, labs must carry out robust validation, training, and optimization of wet- and dry-lab procedures. Achieving these goals for algorithms, pipelines and instruments often requires that lower-quality datasets be made available for analysis and comparison alongside those of higher-quality. This range of data quality in reference sets can complicate the sharing of sub-optimal datasets that are vital for the community and for the reproducibility of assays. Sharing of useful, but sub-optimal datasets requires careful annotation and documentation of known issues to enable appropriate interpretation, avoid being mistaken for better quality information, and for these data (and their derivatives) to be easily identifiable in repositories. Unfortunately, there are currently no standardized attributes or mechanisms for tagging poor-quality datasets, or datasets generated for a specific purpose, to maximize their utility, searchability, accessibility and reuse. The Public Health Alliance for Genomic Epidemiology (PHA4GE) is an international community of scientists from public health, industry and academia focused on improving the reproducibility, interoperability, portability and openness of public health bioinformatic software, skills, tools and data. To address the challenges of sharing lower quality datasets, PHA4GE has developed a set of standardized contextual data tags, namely fields and terms, that can be included in public repository submissions as a means of flagging pathogen sequence data with known quality issues, increasing their discoverability. The contextual data tags were developed through consultations with the community including input from the International Nucleotide Sequence Data Collaboration (INSDC), and have been standardized using ontologies, community-based resources for defining the tag properties and the relationships between them. The standardized tags are agnostic to the organism and the sequencing technique used and thus can be applied to data generated from any pathogen using an array of sequencing techniques. The list of standardized tags is maintained by PHA4GE and can be found at https://github.com/pha4ge/contextual_data_QC_tags. Definitions, ontology IDs, examples of use, as well as a JSON representation, are provided. The PHA4GE QC tags were tested, and are now implemented, by the FDA’s GenomeTrakr laboratory network as part of its routine submission process for SARS-CoV-2 wastewater surveillance. We hope that these simple, standardized tags will help improve communication regarding quality control in public repositories, in addition to making datasets of variable quality more easily identifiable. Suggestions for additional tags can be submitted to PHA4GE via the New Term Request Form in the GitHub repository. By providing a mechanism for feedback and suggestions, we also expect that the tags will evolve with the needs of the community.

The coronavirus disease (COVID-19) vaccine is key to reducing the probability of contracting COVID-19. The vaccine is generally known to prevent severe illness, death, and hospitalization as a result of the disease and for considerably reducing COVID-19 infection risk. Accordingly, this might significantly change an individual’s perceived risk of altering everyday behaviors. For instance, the proliferation of vaccination is anticipated to reduce preventive behaviors such as staying at home, handwashing, and wearing a mask. We corresponded with the same individuals monthly for 18 months from March 2020 (early stage of COVID-19) to September 2021 in Japan to independently construct large sample panel data (N=54,007), with a participation rate of 54.7 %. We used a fixed effects model, controlling for key confounders, to determine whether vaccination was associated with a change in preventive behaviors. The major findings are as follows. Contrary to the prediction, (1) based on the whole sample, being vaccinated against COVID-19 led people to stay at home; however, it did not change the habit of handwashing and wearing a mask. Especially after the second shot, respondents were likelier to stay at home by 0.107 (95% CIs: 0.059–0.154) points on a 5-point scale compared to before the vaccination. Dividing the entire sample into young and old, (2) those aged ≤ 40 years were more likely to go out after being vaccinated, and (3) people over 40 years of age were more likely to stay at home (similar to the first result). Preventive behaviors impact all individuals during the current pandemic. Informal social norms motivate people to increase or maintain preventive behaviors even after being vaccinated in societies where these behaviors are not enforced.

Reliable and accurate flood prediction is a challenging task in poorly gauged basins due to data scarcity. Data is an essential component of any AI/ML model today, and the performance of such models hugely depends on the availability of sufficient amount of trusted, representative data. However, unlike a few well-studied rivers, most of the rivers in developing countries are still insufficiently monitored, which significantly hinges the design and development of advanced flood prediction models and early warning systems. This paper presents a multi-modal, sensor-based and near-real time river monitoring system to produce a multi-feature data set for the Kikuletwa river in Northern Tanzania, an area that heavily suffers from frequent floods. Our deployed system, which gather information about river depth levels and weather at several locations, aims at widening the ground truth of the river characteristics and eventually improve the accuracy of flood predictions. We provide details on the monitoring system used to gather the data as well as report on the methodology and the nature of the data. Finally, we present the relevance of the data set in the context of flood prediction, discussing the most suitable AI/ML-based forecasting approaches, while also highlighting some applications of the data set beyond flood warning systems.

Sparse reward long horizon task is a major challenge for deep reinforcement learning algorithm. One of the key barriers is data-inefficiency. Even in the simulation environment, it usually takes weeks to training the agent. In this study, a data-efficiency training framework is proposed, where a curriculum learning is design for the agent in the simulation scenario. Different distributions of the initial state are set for the agent to get more informative reward during the whole training process. A fine-tuning of the parameters in the output layer of the neural network for value function is conduct to bridge the gap between sim-to-real. An experiment of UAV maneuver control is conducted in the proposed training framework to verify the method more efficient. We demonstrate that data-efficiency is different for the same data in different training stages.

The popularity of cloud computing is growing owing to its large data storage capacity and high computation power. It provides online, on-demand, scalable application solution, removes hardware and software barriers for non-specialist, rapidly integrates and deploys desired and necessary facilities, supports quick upgrading and addition of features. Users get benefitted with the selection of the appropriate cloud computing platform for their projects. Here, our paper provides a comprehensive overview of the services provided to the users by the most common cloud computing service providers. This paper could be used as a reference while selecting the best service provider based on the requirements of the projects.

Climate change is currently one of the main problems facing agriculture to achieve sustainability. It causes situations such as drought, increased rainfall, and increased diseases, causing a decrease in food production. In order to combat these problems, Agricultural Big Data contributes with tools that allow improving the understanding of complex, multivariate, and unpredictable agricultural ecosystems through the collection, storage, processing, and analysis of vast amounts of data from diverse heterogeneous sources. This research aims to discuss the advancement of technologies used in Agricultural Big Data architectures in the context of climate change. The study aims to highlight the tools used to process, analyze, and visualize the data and discuss the use of the architectures in the crop, water, climate, and soil management, especially to analyze the context, whether it is in Resilience Mitigation or Adaptation. The PRISMA protocol guided the study, finding 33 relevant papers. Despite the advances in this line of research, few papers were found that mention the components of the architectures, in addition to the lack of standards and the use of reference architectures, which allow the proper development of Agricultural Big Data in the context of climate change.

Risk management of electric power transmission lines requires knowledge from different areas such as environment, land, investors, regulations, and engineering. Despite the widespread availability of databases for most of those areas, integrating them into a single database or model is a challenging problem. Instead, in this paper, we use a single source, the Brazilian National Electric Energy Agency’s (ANEEL) weekly reports, which contains decisions about the electrical grid, comprising most of the areas. Since the data is unstructured (text), we employed NLP techniques such as stemming and tokenization to identify keywords related to common causes of risks provided by an expert group on energy transmission. Then, we used models to estimate the probability of each risk. Our results show that we were able to estimate the probability of 97 risks out of 233.