Predictive Analysis

This study examines how machine learning techniques can improve the early detection of infectious diseases by analyzing large-scale clinical and epidemiological datasets. Early diagnosis is essential for controlling disease transmission and improving treatment outcomes, yet traditional diagnostic systems often struggle with delayed identification and limited predictive capacity. Recent advancements in artificial intelligence, particularly machine learning algorithms, have enabled the development of predictive models capable of identifying disease patterns before symptoms become clinically severe. This research synthesizes findings from existing computational health studies and evaluates how machine learning frameworks contribute to early disease detection across diverse healthcare environments. Evidence from predictive analytics studies demonstrates that machine learning algorithms-such as neural networks, decision trees, and hybrid learning models-can analyze complex medical datasets to detect infection patterns with significantly improved accuracy compared with traditional statistical approaches (Srivastava et al. 2025; Mishra et al. 2022). The findings indicate that machine learning systems enhance diagnostic efficiency, enable real-time disease surveillance, and improve healthcare decision-making processes (Santangelo et al. 2023; Towfek and Elkanzi 2024). However, limitations remain concerning data quality, model transparency, and clinical integration. The study concludes that machine learning represents a transformative tool for infectious disease detection but requires further validation, improved datasets, and ethical deployment frameworks to achieve reliable clinical implementation (Al Meslamani et al. 2024; Tran et al. 2022).

The recent booming growth of Big Data analytics has revolutionized the contemporary surveillance of the health of human populations by providing real-time epidemiology that can spot outbreaks more quickly than conventional surveillance mechanisms. This paper examines how mobility data and environmental data can be integrated to better predict the outbreak of infectious diseases at hand. Based on massive data sets obtained through the movements of mobile phones, satellite derived environmental signals, and sensor generated weather forecasts, we have created a spatial-temporal predictive model based on the state-of-the-art machine learning models. The approach included the preprocessing of the heterogeneous data, the development of the outbreak risk models, and the assessment of the predictive performance in the form of the accuracy, sensitivity, and the space correlation measures. Findings indicate that changes in population mobility have a strong relationship with the dynamics of disease transmission, and the environmental factors especially temperature, humidity, and air quality are effective modulating factors of an outbreak. Together, such data sources enhance accuracy in prediction and contribute to the creation of real-time outbreak risk maps. These results demonstrate how Big Data, real-time epidemiology, and predictive analytics can enhance the quality of decisions in the field of public health, improve resource distribution, and contribute to proactive control. This paper finds that mobility and environmental data integration offer a powerful base upon which the next generation system of public health surveillance could be built.

Asphyxiation associated with metabolic acidosis is one of the common causes of fetal deaths. The paper aims to develop a feature extraction and prediction algorithm capable of identifying most of the features in the SISPORTO software package and late and variable decelerations. The resulting features were used for classification based on umbilical cord pH data. The algorithms developed here were used to predict cord pH levels. The prediction system assists the obstetricians in assessing the state of the fetus better than the category methods, as only about 30% of the patients in the pathological category suffer from acidosis, while the majority of acidotic babies were in the suspect category, which is considered lower risk. By predicting the direct indicator of acidosis, umbilical cord pH, this work demonstrates a methodology, which uses fetal heart rate and uterine activity, to identify acidosis. This paper introduces a forecasting model based on deep learning to predict heart rate and uterine contractions, integrated with the classification algorithm, resulting in a robust tool for predictive fetal monitoring. The hybrid algorithm resulted in a model capable of providing future conditions of the fetus, which obstetricians can use for diagnosis and planning interventions. The ensemble classification algorithm had a test accuracy of 85% (n = 24) in predicting fetal acidosis on the features extracted from the cardiotocography data. When integrated with the classification model, the results from the prediction model (long short-term memory network) can effectively identify fetal acidosis 2 or 4 min in the future.

This study introduces a novel, cloud-based predictive analytics framework tailored for pension fund performance management in Zimbabwe. Addressing limitations in traditional actuarial models, the proposed system leverages realtime data pipelines and explainable artificial intelligence (XAI) techniques to enhance forecasting accuracy and transparency. Using regression, classification, and deep learning models, it forecasts member contributions, identifies risks of contribution drops, and predicts member churn. The system's cloud deployment ensures scalability and interactive integration with tools like Power BI for decision support. This solution significantly advances sustainable pension fund management for emerging economies.

Successful attempt has been made to derive a model for calculating the concentration of upgraded iron designated for production of stainless steel based biomedical devices used in orthopaedics. The iron component of the iron oxide ore was upgraded during the pyrobeneficiation of the ore using powdered potassium chlorate. The model-predicted %Fe upgrades were found to agree with a direct relationship between %Fe values and weight-input of KClO3 as exhibited by %Fe upgrades obtained from the experiment. It was found that the model; %Fe = γ ((ln(T/β)) 2.1277 ) is dependent on the weight-inputs of KClO3, iron oxide ore and the treatment temperature. The validity of the model is rooted in the expression (%Fe/γ) N = ln(T/β) where both sides of the expression are correspondingly approximately equal to 3. The maximum deviation of the model-predicted values of %Fe from those of the corresponding experimental values was found to be less than 21% which is quite within the range of acceptable d...

Mass concrete is a type of concrete used for structures with large dimensions that require precautionary measures to be taken in order to control the heat. The heat generated in the core of such a structure, due to hydration of cementitious materials, is dissipated at a slow rate leading to the formation of high temperature differential. This increases the risk of temperature-induced stresses and cracking that is dependent on many factors such as the materials and proportion of concrete mix, environmental and construction conditions, etc. In order to prevent cracking, a thermal control plan is essential before the placement of concrete that in turn requires prior knowledge of the temperature development in the mass concrete member. In this context, this study presents the analysis of a case in which the construction of a mass concrete bridge foundation was investigated and a computer program, ConcreteWorks (CW), was used to predict its overall thermal performance. Predictions of tem...

Blockchain and artificial intelligence (AI) are revolutionizing animal disease surveillance by enhancing data integrity, early detection, and response capabilities. Blockchain's decentralized ledger ensures secure, transparent data sharing among stakeholders, crucial for disease monitoring and supply chain management in veterinary health. AI, through machine learning and natural language processing, analyzes diverse datasets to predict outbreaks and monitor disease spread effectively. Integrating IoT sensors further enhances real-time monitoring of animal health parameters, facilitating early intervention. These technologies enable proactive measures such as automated data sharing and predictive modelling, essential for mitigating disease risks and optimizing resource allocation. Challenges include interoperability, data privacy, and regulatory compliance, necessitating standardized frameworks and collaborative governance. Despite these challenges, the synergistic application of blockchain and AI promises to transform global animal health surveillance, supporting a One Health approach that integrates human, animal, and environmental health for enhanced public health outcomes.

Public health systems, socioeconomic stability, and national security are all under constant and growing threat from emerging infectious diseases. Particularly among highly mobile and environmentally sensitive populations, traditional epidemiological monitoring techniques, which mostly rely on manual reporting and delayed laboratory confirmation, frequently fail to identify epidemics in their early phases. The potential of artificial intelligence (AI)-driven epidemiological monitoring as a revolutionary strategy for the early identification of newly emerging infectious diseases and the reinforcement of national health security is examined in this paper. This summarizes recent developments in AI applications for epidemiological intelligence, emphasizing how automated risk scoring, pattern recognition, and spatiotemporal modeling might spot aberrant illness trends before they spread widely. The study looks at how AIdriven surveillance helps national health security by facilitating better coordination between public health, border control, and emergency management organizations, as well as proactive readiness and quick response decision-making through Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. Despite these benefits, there are issues with data quality, interoperability, algorithmic bias, ethical governance, and data privacy when implementing AI-based surveillance systems. These restrictions are particularly noticeable in low-and middle-income nations, where technical capacity and digital infrastructure may be limited. All things considered, AI-driven epidemiological monitoring is a significant development in contemporary disease intelligence, providing strategic value for early outbreak identification, pandemic prevention, and national health security resilience in a world growing more interconnected by the day.

Although the educational level of the Portuguese population has improved in the last decades, the statistics keep Portugal at Europe's tail end due to its high student failure rates. In particular, lack of success in the core classes of Mathematics and the Portuguese language is extremely serious. On the other hand, the fields of Business Intelligence (BI)/Data Mining (DM), which aim at extracting high-level knowledge from raw data, offer interesting automated tools that can aid the education domain. The present work intends to approach student achievement in secondary education using BI/DM techniques. Recent real-world data (e.g. student grades, demographic, social and school related features) was collected by using school reports and questionnaires. The two core classes (i.e. Mathematics and Portuguese) were modeled under binary/five-level classification and regression tasks. Also, four DM models (i.e. Decision Trees, Random Forest, Neural Networks and Support Vector Machines) and three input selections (e.g. with and without previous grades) were tested. The results show that a good predictive accuracy can be achieved, provided that the first and/or second school period grades are available. Although student achievement is highly influenced by past evaluations, an explanatory analysis has shown that there are also other relevant features (e.g. number of absences, parent's job and education, alcohol consumption). As a direct outcome of this research, more efficient student prediction tools can be be developed, improving the quality of education and enhancing school resource management.

Background: Alzheimer's disease (AD) diagnosis typically occurs when 60-80% of neurons are already compromised, limiting therapeutic intervention effectiveness. Current diagnostic methods (neuroimaging, CSF biomarkers) are either invasive, expensive, or detect changes too late in the disease progression. There is an urgent need for non-invasive, cost-effective, and early-stage biomarkers that can identify AD pathology 10-15 years before clinical symptoms manifest. Objective: To develop and validate a comprehensive framework for early AD detection using high-resolution electroencephalography (EEG) and advanced neurophysiological biomarkers, achieving diagnostic accuracy >85% for mild cognitive impairment (MCI) and early-stage AD. Methods: We propose a novel framework integrating: (1) ultra-dense EEG acquisition (256+ channels, 2kHz sampling), (2) innovative neurophysiological biomarkers including Neural Coherence Index (NCI), Information Integration Measure (IIM), and Network Disorganization Score (NDS), (3) real-time processing pipeline with machine learning classification, and (4) comprehensive validation protocol across healthy controls (N=40), MCI patients (N=40), and mild AD patients (N=30). Expected Results: Primary endpoint targets diagnostic accuracy (AUC >0.85) for HC vs MCI vs AD discrimination. Secondary endpoints include sensitivity >80% for MCI identification, specificity >85% vs healthy controls, and reproducibility (ICC >0.8). Exploratory analyses will examine correlations with established CSF biomarkers and longitudinal progression prediction. Significance: This framework represents a paradigm shift toward precision medicine in AD, offering clinically implementable, non-invasive early detection that could transform therapeutic intervention timing and personalized treatment strategies. The proposed biomarkers bridge fundamental neuroscience research with immediate clinical applications, potentially enabling population-scale cognitive health screening. Conclusion: The integration of high-resolution EEG technology with novel neurophysiological biomarkers provides a scientifically rigorous and clinically viable approach to early AD detection, with potential for broad implementation in routine clinical practice within 3-5 years.

The convergence of the Internet of Things (IoT) and Machine Learning (ML) has transformed environmental monitoring, enabling real-time data acquisition, predictive analytics, and decision support for sustainable management of natural resources. IoT-based sensor networks offer continuous, low-cost, and scalable monitoring of air and water quality, while ML algorithms enhance accuracy through anomaly detection, calibration, and predictive modeling. This paper explores the applications, challenges, and cybersecurity threats associated with IoT-ML frameworks for environmental monitoring. Two case studies are presented: (i) Smart Air Quality Monitoring in Urban Cities, where low-cost IoT sensors combined with ML models such as Random Forest and LSTM provided improved forecasting of Air Quality Index (AQI), and (ii) IoT-enabled Water Quality Monitoring for Smart Agriculture, where classification and regression models supported irrigation management through predictive water safety assessment. Both cases demonstrate significant improvements in accuracy, cost-efficiency, and timeliness compared to traditional monitoring methods, but they also reveal challenges including sensor calibration, energy constraints, data imbalance, and security vulnerabilities such as spoofing, denial-of-service, and ransomware. The study underscores the importance of integrating cybersecurity frameworks with IoT-ML systems to ensure resilience, reliability, and trustworthiness. By analyzing technical, operational, and security aspects, this paper provides a holistic perspective on leveraging IoT and ML for sustainable environmental management.

India is an agricultural country where the agriculture sector is the backbone of the
economy, contributing to more than 20.2% of the country's GDP. However, the agriculture sector
is facing numerous challenges such as water scarcity, climate change, and low productivity due
to outdated farming practices. Therefore, there is a dire need to introduce modern technology in
the agriculture sector to enhance its productivity and efficiency. This project presents an IOT
Based Smart Agriculture Monitoring System aimed at increasing agricultural productivity by
automating and optimizing crop management. The system uses various sensors to monitor
environmental conditions in real-time. The data collected is processed by a microcontroller and
transmitted wirelessly to a web application that provides farmers with visualized information
about their crops. The system is designed to be affordable and easy to use, allowing farmers to
monitor their crops remotely and take necessary actions to optimize their growth. By providing
farmers with real-time data on their crops, the system can help them make informed decisions
regarding water and fertilizer usage, pest control, and harvesting times. This in turn can lead to
increased crop yields, reduced costs, and improved profitability. The project also has future
implications, including the integration of machine learning and artificial intelligence technologies
to further optimize crop management. With the increasing demand for food production and the
need to address the challenges of climate change and food security, this project serves as a
promising solution for sustainable agriculture.

boosting are used to predict the disease epidemic curves. Predictions are then displayed to stakeholders in a disease situation awareness interface, alongside disease incidents, syndromic and zoonotic details extracted from news sources and medical publications. Data on Influenza Like Illness (ILI) provided by CDC was used to validate the capability of IPAS system, with plans to expand to other illnesses in the future. This paper presents the ILI prediction modeling results as well as IPAS system features.

With an emphasis on liver segmentation in medical pictures, this research investigates the use of artificial intelligence (AI) in the field of smart healthcare. In medical image analysis, liver segmentation is a crucial task, especially for liver disease diagnosis, surgical planning, and therapy monitoring. While AI-powered approaches, particularly those that make use of deep learning, offer the potential for increases in accuracy and efficiency, traditional image analysis methods are frequently slow and prone to errors. We provide a summary of the state-of-the-art techniques, difficulties, and developments in AI-based liver segmentation, with a focus on deep learning frameworks like transfer learning and convolutional neural networks (CNNs). The goal is to demonstrate how AI has the ability to transform liver disease detection and therapy by providing intelligent medical solutions. With an emphasis on diseases including pneumonia, lung cancer, and fractures, the suggested method uses Convolutional Neural Networks (CNNs) to precisely identify anomalies and patterns. The technology improves diagnostic accuracy, decreases human error, and expedites clinical workflows by automating the diagnostic process. Furthermore, the system can get better over time by adjusting to new datasets and medical procedures because to the incorporation of continuous learning techniques. By facilitating prompt intervention and increasing diagnosis speed and accuracy, AI-based liver segmentation holds the potential to revolutionize medical practice. When handling complex liver pictures, deep learning models particularly those that make use of transfer learning and 3D segmentation networks have demonstrated greater performance, frequently attaining higher accuracy than conventional not withstanding these difficulties, recent techniques. However, addressing the inherent diversity in liver pictures resulting from variations in patient anatomy, disease development, and imaging modality (CT, MRI, Ultrasound) presents a difficulty. Developments have shown that AI models can effectively generalize to various patient populations and imaging situations when trained on sizable and varied datasets.

The ability to accurately predict the properties of materials is crucial for numerous applications across various industries, including materials science, engineering, and manufacturing. With the advent of machine learning (ML) techniques, researchers have gained powerful tools to model and predict material properties based on their composition, structure, and processing conditions. This review paper provides a comprehensive overview of material property prediction using machine learning. It covers the historical development, available ML models, recent trends, and prospects in this rapidly evolving domain.

This paper focuses on the data-driven diagnosis of polycystic ovary syndrome (PCOS) in women. For this, machine learning algorithms are applied to a dataset freely available in Kaggle repository. This dataset has 43 attributes of 541 women, among which 177 are patients of PCOS disease. Firstly, univariate feature selection algorithm is applied to find the best features that can predict PCOS. The ranking of the attributes is computed and it is found that the most important attribute is the ratio of Follicle stimulating hormone (FSH) and Luteinizing hormone (LH), Next, holdout and cross validation methods are applied to the dataset to separate the training and testing data. A number of classifiers such as gradient boosting, random forest, logistic regression, and hybrid random forest and logistic regression (RFLR) are applied to the attributed are good enough to predict the PCOS disease

In our society, there's a growing need for awareness and support, especially for individuals facing visual impairments. This endeavor revolves around creating a specialized mobile application precisely catering to their unique needs. Harnessing the capabilities of computer vision and deep learning, the app functions as a versatile aid, offering realtime support and enhancing accessibility for its users. Through the Smartphone's camera, the application can identify and describe various objects, allowing users to gain a better understanding of their immediate environment. Furthermore, the integration of optical character recognition (OCR) technology enables the app to convert printed text into audio, providing users with access to a wide range of printed materials. The navigation assistance feature utilizes advanced algorithms to detect obstacles and provide users with alerts, ensuring safe and efficient navigation.

This paper addresses demanding situations in Intrusion Detection Systems (IDS) by way of combining the Adaptive Synthetic Sampling (ADASYN) method with a break up-primarily based Resnet framework. ADASYN balances sample distribution, overcoming biases in the direction of large samples. Our method extracts multiscale functions, reduces interchannel redundancy, and enhances the version's capability using a smooth hobby operation. We recommend a Residual Neural Network (ResNN) version for intrusion detection, displaying massive enhancements in recognition accuracy and execution performance. Ongoing work targets to optimize performance further, highlighting the capacity for extra strong IDS solutions.

Fingerprint evidence found at crime scenes provides vital impressions left when these skin secretions touch surfaces clues in serial criminal investigations. A fingerprint identification system employing deep machine learning and Convolutional Neural Networks (CNNs) could automate the analysis process. Images obtained from various physical and chemical crime scene investiga2tion techniques are entered into the database. However, partial latent prints lifted from scenes are often difficult to classify. The system operates in three phases: preprocessing fingerprint images, feature extraction, and matching. Preprocessing enhances image quality before feature extraction identifies distinctive minutiae points-ridge endings and bifurcations. False minutiae removal further refines the data. The preprocessed fingerprint data serves as input to train and test the CNN model. As the system persist due to the immutable individuality of fingerprint ridge arrangements [5]. While criminals attempt concealment, fingerprint traces stubbornly remain where other evidence would dissipate [6]. Without these durable biometric markers, crime scenes would often lack the critical traces needed to connect acts to perpetrators [7]. Latent prints lifted from crime scenes first undergo photographic documentation and chemical enhancement techniques in order to visualize trace details [8]. Computer analysis then further improves clarity, isolating minute identifying features known as minutiae [9]. Algorithmic extraction of differentiating traits classifies new latent prints, it continuously incorporates the prints enables training of automated comparison systems using along with confirmed suspect identity matches to improve accuracy. Automated classification and matching facilitate identification. The approach scales as the database grows in size without proportionate growth in human effort. Rapid fingerprint evidence analysis accelerates investigations, potentially solving more crimes by linking serial cases through a central digital repository. I aimed to restate the key technical ideas and flow using alternative vocabulary and phrasing while preserving semantic meaning. Please let me know if you need any clarification or have additional requirements for rephrasing the passage.

For agriculture to be sustainable, it is essential to monitor a plant's health and look for diseases. It is quite challenging to manually monitor plant diseases. To improve the agriculture industry and the prosperity of our nation, plant disease must be effectively identified. Several diseases cause the plant's leaves to die. Farmers have a harder time seeing these diseases because it's difficult to care for those plants without knowing about them. The method described in this paper uses Tensor Flow to identify illnesses in plant leaf pictures. CNN training is used on the model proposed to automatically diagnose disease using the object detection API tensor flow. This data is acquired from multiple sources. In order to treat the sickness, the proposed effort will also identify the causes and manifestations of the illness. In the work proposed, to identify plant diseases, sophisticated deep machine learning models based on specific CNN topologies were developed using photos of healthy or diseased plants' leaves. In comparison to existing models, CNN's numerous layers offer a great rating and a 96 percent accuracy level.

This project offers a comprehensive evaluation of recent advancements in Neural Radiance Field (NeRF), a significant development in Computer Vision. NeRF models, known for their neural network-based scene representation and novel view synthesis, find applications in robotics, urban mapping, autonomous navigation, and virtual reality/augmented reality. The survey categorizes findings into architecture and application-based taxonomies, introducing NeRF theory and training via differentiable volume rendering. A benchmark compares key NeRF models' performance and speed, aiming to objectively assess strengths, weaknesses, and applicability across real-life scenarios. Results cover comparisons with photogrammetry in noise level, geometric accuracy, and image baselines across diverse scenes. NeRFs outperform in scenarios with texture-less, reflective, and refractive surfaces, while photogrammetry excels with cooperative textures.

The structure developed involves the etching of Moore’s curve onto a conventional rectangular patch and subsequently encasing it in a rectangular loop along with a defected ground structure. The proposed antenna exhibits dual-band Since the Internet of Things (IoT) enabled medical diagnostic system requires unprecedented precision and automation for better health care delivery, therefore in such systems, the performance of antennas for efficiently transferring data (vital functions of the human body) is an important task. To address these concerns, a mechanically robust, novel hybrid wearable on-body antenna inspired by Moore’s fractal based geometry and conventional rectangular loop for a diagnostic health monitoring system is proposed. with bandwidth ranging from 1.38 - 1.8 GHz and 2.25 - 4.88 GHz respectively, covering WMTS, ISM, and Personal Communication band besides covering a portion of UWB band also. The two operating bands of the antenna offer a fractional bandwidth of 38.5% and 73.7% respectively. It is observed that the average specific absorption rate (SAR) over the multi-layer phantom is 0.025 W/kg for an input power of ≈ 24 dBm. In comparison to the recently reported wearable antennas, the design proposed has a compact footprint of 0.135 λo x 0.093λo x 0.004λo besides offering a dual- band of operation, peak gain of 2.2 dBi, overall radiated efficiency of 95% and SAR below 0.025 W/kg. The design is fabricated using Rogers 5880 substrate (semi-flex) of thickness 0.75 mm.

The aim of this study was to identify variables associated with direct recovery of the ball during defensive transitions in elite soccer and to propose a model with certain guarantees of success based on a multivariate analysis in which binary logistic regression was used to explore interaction between variables. 1,722 defensive transitions were analysed in the final stages of the FIFA World Cup 2014 in Brazil and investigated the following variables: duration of defensive transition; possession loss zone; position of players at the start and end of the defensive transitions, defensive organization, general defensive approach, period of the match, position of defence line, zone in which the offensive transition ends, match status, and outcome of the defensive transition. The variables found to significantly associated with ball recovery were the area of the pitch in which the ball is lost prior to the transition (p < .05), the duration of the transition (p < .01), the position of the defence lines (p < .01), the zone in which the transition ends (p < .001) and end spatial interaction configuration (p < .001). The model that provided the best guarantees of recovering possession was characterized by a defensive transition lasting 15 seconds or less that ends in the holding midfield with the attacking team under pressure.

En el presente trabajo se realiza un análisis de las transiciones ofensivas (transición defensa-ataque) realizadas por las mejores selecciones nacionales europeas de fútbol. Los principales objetivos planteados en la investigación son determinar si es posible predecir el resultado de las transiciones ofensivas del juego, y si es así, identificar qué variables permitirán realizar dichas predicciones. Para abordar estos objetivos se ha utilizado el modelo multivariable de regresión logística. La muestra consta de 14 partidos, 743 transiciones ofensivas de la fase final de la Eurocopa de Austria-Suiza 2008. La utilización de este modelo permite concluir que es posible realizar una predicción del resultado de las transiciones ofensivas que se suceden en el transcurso del encuentro y también, determinar cuáles son las variables que posibilitan realizar dicha predicción. Los datos demuestran que se puede pronosticar el resultado final de las transiciones ofensivas en función de la configu...

Agriculture plays a pivotal role in determining a nation's prosperity, particularly in a country like India where over 68% of the population relies on it for their livelihoods. Crop infections pose a significant threat, not only to the livelihoods of farmers but also to the overall economic stability of the nation. Effective measures must be taken to diagnose and treat plant diseases promptly in order to mitigate substantial losses and safeguard crop yields. In this study, we propose a novel approach combining image processing and machine learning techniques to identify and classify plant leaf diseases. Our method utilizes a multi-class Support Vector Machine (SVM) classifier, incorporating texture analysis using Gray-Level Co-occurrence Matrix (GLCM) features. The results of our predictive model exhibit promising outcomes, achieving an impressive accuracy rate exceeding 90% during the simulation phase, which holds great potential for practical implementation in the agricultural sector.

The mining industry has changed significantly in recent decades with the introduction of advanced technologies such as artificial intelligence (AI) and machine learning (ML). These innovations contribute to the creation of expert systems that help in optimizing processes, increasing the safety and sustainability of operations. This article is a literature review of modern AI and ML methods and technologies used in the mining industry. Discusses various intelligent and expert systems used to improve productivity, reduce operating costs, improve occupational safety, environmental sustainability, machine automation, predictive analytics, quality monitoring and control, and inventory and logistics management. The advantages and disadvantages of different approaches are analyzed, as well as their potential impact on the future of the mining industry. The review highlights the importance of integrating AI and ML into mining processes to achieve more efficient and safer solutions.

This paper classify the various existing predicting models that are used for monitoring and improving students' performance at schools and higher learning institutions. It analyses all the areas within the educational data mining methodology. Two databases were chosen for this study and a systematic mapping study was performed. Due to the very infant stage of this research area, only 114 articles published from 2012 till 2016 were identified. Within this, a total of 59 articles were reviewed and classified. There is an increased interest and research in the area of educational data mining, particularly in improving students' performance with various predictive and prescriptive models. Most of the models are devised for pedagogical improvements ultimately. It is a huge scarcity in producing portable predictive models that fits into any educational environment. There is more research needed in the educational big data.

Feature selection plays a key influence in machine learning (ML); the main objective of feature selection is to eliminate irrelevant and redundant variables in different classification problems to improve the performance of the learning algorithms. Classification accuracy is improved by reducing the number of selected features. Many real-world problems, such as taxi fare can be predicted by ML. This paper proposes feature selection using genetic algorithm (GA) optimization to predict taxi fare. Experiments are performed on real datasets of taxi fare, and this paper uses eight classifiers to evaluate the selected features. The performance of the classifiers is assessed using various performance metrics. The results are compared with feature selection without optimization. The proposed method records high classification accuracy when evaluated by three types of classifiers (random forest, AdaBoost, and Gradient Boost). The results indicate that the prediction accuracy of the proposed method is 99.7% on taxi fare dataset.

At present, people in the countryside use a manual agricultural machine for harvesting. This contributes to global warming and agricultural safety problems as manual irrigation increases farmers&#39; time on the farm. The use of manual machinery causes smoke during irrigation, which increases the heating of the earth&#39;s surface and thus reduces the green energy effect. So they do not spend a lot of money on buying crude oil when they use the system. On the other hand, there are bandits who come into conflict with farmers and animals that attack farmers in the bush, which makes it difficult for farmers to reach their farms. A simple but effective IoT system, as we have proposed in this study, helps to solve these problems to a large extent. In this study, we use a combination of a Raspberry Pi as the main processor and sensor modules as devices to collect agricultural data for further insights and analysis. Apart from automatic irrigation through the power-saving water pump, the d...

This article presents a novel approach to analyzing and modeling design challenges, addressing the impact of dynamically changing technologies. Based on extensive research and industrial experience, the author developed hypotheses defining key modeling parameters: time, displacement, mass, and temperature. Through advanced mathematical formulas and numerical calculations, the author demonstrates how each parameter can be effectively integrated to model randomly changing technological processes. Calculations and the structuring of measurement space into virtual cubes enable precise forecasting and adaptability to variable conditions, significantly enhancing the accuracy and responsiveness of industrial processes. By analyzing historical data and iterative scenario modeling, this methodology facilitates rapid switching between design variants, allowing designers to identify optimization paths and adjust processes in response to unpredictable changes. The author suggests that these foundations may serve as a robust basis for developing intelligent machines with artificial intelligence technology, capable of automatic response and adaptation in dynamically evolving operational environments.

The student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this thesis. The Graduate College will ensure this thesis is globally accessible and will not permit alterations after a degree is conferred.

Mass concrete is a type of concrete used for structures with large dimensions that require precautionary measures to be taken in order to control the heat. The heat generated in the core of such a structure, due to hydration of cementitious materials, is dissipated at a slow rate leading to the formation of high temperature differential. This increases the risk of temperature-induced stresses and cracking that is dependent on many factors such as the materials and proportion of concrete mix, environmental and construction conditions, etc. In order to prevent cracking, a thermal control plan is essential before the placement of concrete that in turn requires prior knowledge of the temperature development in the mass concrete member. In this context, this study presents the analysis of a case in which the construction of a mass concrete bridge foundation was investigated and a computer program, ConcreteWorks (CW), was used to predict its overall thermal performance. Predictions of tem...

"SynthoChemAI" is a compound term derived from "Synthesis," "Chemistry," and "Artificial Intelligence." It refers to the application of AI in the field of chemical synthesis, aiming to optimize processes, predict outcomes, and discover new chemical compounds. Synthetic chemistry is undergoing a revolution thanks to the integration of deep learning technologies and artificial intelligence (AI). This is especially true for reaction prediction. In comparison to conventional heuristic methods, this paper examines the notable developments in AI-driven models that improve prediction accuracy and efficiency of chemical reactions. These models speed up drug discovery and materials development by identifying the best reaction pathways by utilising large chemical databases like Reaxys and PubChem. We go over the state of deep learning applications today, including different model architectures and how well they work in practical situations. Nonetheless, there are still problems to be solved, such as interpretability of the model, data quality, and the requirement for integration with experimental chemistry. The paper also discusses upcoming trends that need to be taken into account as AI technologies proliferate, such as hybrid models that incorporate AI with traditional approaches and reinforcement learning. In the end, our work highlights the revolutionary potential of deep learning in synthetic chemistry, opening the door to more effective and inventive research methodologies that have the potential to have a big influence on materials science and global health.

The healthcare industry faces increasing pressure to deliver high-quality patient care while managing limited resources efficiently. Predictive analytics, enabled by critical and emerging technologies (CETs) such as artificial intelligence (AI), machine learning (ML), cloud computing, and the Internet of Things (IoT), is transforming healthcare operations. This paper reviews the application of CETs in predictive analytics to improve patient outcomes and optimize resource allocation. By synthesizing data from academic research, healthcare case studies, and industry reports, we examine the potential of these technologies in predicting patient outcomes, preventing adverse events, and managing healthcare resources. Furthermore, the paper discusses the challenges and limitations of adopting predictive analytics in healthcare and provides recommendations for future research and implementation.

The integration of Artificial Intelligence (AI) and Natural Language Processing (NLP) in digital health record systems is transforming healthcare by making Electronic Health Records (EHRs) more accurate, accessible, and usable. EHRs, traditionally structured around rigid data formats, often fail to capture unstructured information critical to patient care, such as physician notes, patient histories, and complex medical research. Through AI and NLP, healthcare systems can now process and interpret these unstructured data sources, turning them into actionable insights. This article explores how these advancements streamline healthcare workflows, alleviate administrative burdens, and enable healthcare providers to make data-driven decisions with greater precision and speed. AIdriven predictive analytics and NLP algorithms facilitate the extraction and organization of vital patient information, fostering improved patient care by anticipating risks and optimizing treatment strategies. By ensuring that healthcare providers have real-time access to comprehensive patient data, AI and NLP empower a more patient-centered approach to care that emphasizes personalization and responsiveness to individual patient needs. As a result, healthcare professionals are better equipped to make informed decisions, enhancing outcomes and reducing errors. This article underscores the significant role of AI and NLP in reshaping digital health records to support a future where healthcare delivery is not only more efficient but also more aligned with the nuanced needs of each patient.

With the increase of component complexity, protection against single event effects becomes a critical point for the dependability of space systems. In this paper, machine learning is investigated to improve the detection of radiation faults. An algorithm named DYD 2 that meets space application requirements is proposed. In addition, a study to improve the characterisation of single event effects through feature extraction is described. Finally, results of experimentation based on a heavyion campaign test are discussed.

This study investigates the transformative potential of big data analytics in healthcare, focusing on its application for forecasting patient outcomes and enhancing clinical decision-making. The primary challenges addressed include data integration, quality, privacy issues, and the interpretability of complex machine-learning models. An extensive literature review evaluates the current state of big data analytics in healthcare, particularly predictive analytics. The research employs machine learning algorithms to develop predictive models aimed at specific patient outcomes, such as disease progression and treatment responses. The models are assessed based on three key metrics: accuracy, interpretability, and clinical relevance. The findings demonstrate that big data analytics can significantly revolutionize healthcare by providing datadriven insights that inform treatment decisions, anticipate complications, and identify high-risk patients. The predictive models developed show promise for enhancing clinical judgment and facilitating personalized treatment approaches. Moreover, the study underscores the importance of addressing data quality, integration, and privacy to ensure the ethical application of predictive analytics in clinical settings. The results contribute to the growing body of research on practical big data applications in healthcare, offering valuable recommendations for balancing patient privacy with the benefits of data-driven insights. Ultimately, this research has implications for policy-making, guiding the implementation of predictive models and fostering innovation aimed at improving healthcare outcomes.

Artificial Intelligence has renovated the health care sector, enabling predictive analytics, early diagnosis, personal treatment, and prevention from diseases. This review article will consider the advanced methodologies of AI in the form of machine learning algorithms, neural networks, and big data analytics for predicting health outcomes like diabetes, cardiovascular diseases, and cancer with greater accuracy. It is personalization of health predictions by integration of genomic, lifestyle, and clinical data. It underlines the fact that in personalized interventions, neural networks and reinforcement learning have really been doing very well. The study goes a step further to evaluate machine learning models in the form of decision trees and support vector machines for their high degree of predictive accuracy with regard to patient data on EHRs for chronic diseases. Although AI would mean greater precision of diagnosis, more actionable insight into health, several barriers to that include algorithmic bias, data privacy, transparency, and model interpretability. These are some of the key ethical and technical concerns that must be discussed and debated to ensure trust and equity in the adoption of clinical AI. It also focuses on big data and AI synergy in such a way that the structured and unstructured health data contributed by both can be used for patient vital monitoring, forecasting of epidemics, and identification of high-risk groups. This is a multidisciplinary approach in underlining the transformative potential of AI through the promotion of robust strategies toward refining predictive models and optimization of big data use in healthcare systems.

In the manufacturing industry, it is of prime importance to be able to retrieve the health status of production lines and to know how products navigate across operations. Products that are suspected to be faulty are deviated from the nominal path and inspected more closely. The fact that some products deviate from the nominal path and others fail at some check operations might indicate a risk for quality. This paper proposes a method to obtain the process model automatically, following the principles of the process mining field. The found model not only shows the product transitions from one operation to another, but also includes the time constraints bounding the "normal" time for each transition. From this model, products can be clustered according to the path they follow along the process. The clustering results for the product batch and the product itself are ultimately used to compute a quality index. The whole method is applied to a SMT PCB production line from Vitesco Technologies.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

A real challenge for manufacturing industry is to be able to control not only the manufacturing process but also the production quality. Products that are suspected to be faulty are deviated from their nominal path in the production line and inspected more closely. The fact that some products deviate from the nominal path and others fail at some check operations can be used as an indicator of poor product quality. Based on this idea, this paper proposes a method to compute a product quality index or more exactly a penalty index taking into account both product path and production batches. The method relies on categorizing the products according to how they follow the production path and process mining techniques. The originality of the proposed index is to be built from advanced data analysis techniques enhanced by expert know-how. The quality index highlights risk of customer return, which is highly relevant information for the after sales service. The significance of the method is illustrated on a printed circuit board production line using surface mount technology at Vitesco Technologies. Data is collected from the real manufacturing execution system. The results obtained over more than 10000 single electronic boards show that 91.7% of the products are in good compliance with respect to the requirements. For the other products, the method identifies the root causes of poor quality that may call for maintenance or reconfiguration actions.

In the modern healthcare landscape, understanding and leveraging customer insights has become critical for enhancing patient care, optimizing healthcare delivery, and improving organizational performance. This paper explores the development and application of AI-driven models designed to generate actionable customer insights within healthcare contexts. By focusing on customer insights, which encompass a deep understanding of patients' preferences, behaviors, and experiences, healthcare providers can move toward more patient-centered approaches, leading to enhanced outcomes and increased satisfaction. Despite the significance of these insights, the healthcare industry has faced challenges in effectively capturing and analyzing patient data due to its complexity and the stringent privacy and security regulations surrounding it. Our study addresses this gap by proposing an AIbased framework that integrates multiple data sources, including electronic health records (EHR), patient feedback, and other healthcare interactions, to extract meaningful insights. The framework leverages advanced machine learning techniques, including natural language processing (NLP) and predictive modeling, to interpret patient feedback and predict individual patient needs and preferences. Through this approach, the model is capable of identifying trends and predicting outcomes that can support decision-making at both the clinical and administrative levels. For instance, by analyzing historical data, the model can identify patterns indicating patient dissatisfaction or disengagement, allowing healthcare providers to proactively address these issues and improve the overall patient experience. The research utilizes both real-world healthcare data and simulated data to test the model’s performance across diverse scenarios, such as patient retention, satisfaction prediction, and engagement analysis. The simulated data environment allows for a controlled exploration of various patient interaction scenarios without compromising patient confidentiality, while real world data provides insights grounded in actual patient behaviors and outcomes. Key findings from these experiments demonstrate that the AI-driven model achieves high accuracy in predicting patient satisfaction and identifying patients at risk of noncompliance or disengagement. These insights enable healthcare providers to implement personalized interventions that can lead to better patient engagement, improved health outcomes, and optimized resource allocation. Moreover, the paper discusses the implications of using AI for customer insights in healthcare, particularly regarding ethical considerations, data privacy, and patient autonomy. Given the sensitive nature of healthcare data, our framework incorporates privacy-preserving techniques such as data anonymization and secure data handling protocols, ensuring compliance with regulations like HIPAA (Health Insurance Portability and Accountability Act). The study also highlights potential limitations, including biases that can arise from data sources and challenges associated with integrating insights into existing healthcare workflows. In conclusion, this research presents a novel approach to generating actionable customer insights in healthcare through AI-driven models. By effectively combining patient feedback, EHR, and predictive analytics, our model demonstrates significant potential for supporting healthcare providers in making more informed, patientcentered decisions. The model's success in a simulated environment suggests its potential applicability across various healthcare settings, from hospitals to outpatient clinics, and underscores the transformative role AI can play in enhancing patient experience and operational efficiency in healthcare. Future research will focus on refining these models, expanding the data sources, and exploring real-time implementation to further improve predictive accuracy and ensure broad applicability across diverse healthcare systems.

Recently, many people in the Middle East and North Africa enjoy watching a variety of Korean contents such as Korean dramas, films, broadcasting programs and listening to Korean Pops. The Korean wave refers to the phenomenon of Korean entertainment and popular culture rolling over the world with TV dramas, films and pop music. Also it is known as "Hallyu " literally meaning 'flow from Korea' in Korean. This study examines the analysis of pattern on Arab countries (Middle East and North Africa) Consumers' consumption of the Korean Contents using social media, Facebook data. Then we focus on developing Predictive System using a Data Mining Technique.

This systematic review explores the potential and advancements of AI technology in the detection and diagnosis of dengue fever. Dengue, a mosquito-borne viral infection, poses significant public health challenges, particularly in tropical and subtropical regions. Traditional diagnostic methods are often timeconsuming and resource-intensive, creating the need for innovative approaches. AI technologies, including machine learning and deep learning models, have demonstrated promising capabilities in enhancing early detection, improving diagnostic accuracy, and predicting outbreaks by analyzing large datasets such as clinical records, lab results, and environmental factors. This review synthesizes the current literature on AI applications in dengue detection, evaluating their effectiveness, limitations, and potential for integration into healthcare systems. Our findings suggest that while AI offers substantial improvements over conventional methods, further research is necessary to address challenges related to data availability, model generalization, and real-world implementation.

This systematic review explores the potential and advancements of AI technology in the detection and diagnosis of dengue fever. Dengue, a mosquito-borne viral infection, poses significant public health
challenges, particularly in tropical and subtropical regions. Traditional diagnostic methods are often timeconsuming and resource-intensive, creating the need for innovative approaches. AI technologies,
including machine learning and deep learning models, have demonstrated promising capabilities in enhancing early detection, improving diagnostic accuracy, and predicting outbreaks by analyzing large
datasets such as clinical records, lab results, and environmental factors. This review synthesizes the current literature on AI applications in dengue detection, evaluating their effectiveness, limitations, and potential for integration into healthcare systems. Our findings suggest that while AI offers substantial improvements over conventional methods, further research is necessary to address challenges related to data availability, model generalization, and real-world implementation.

Soil moisture information plays an important role in environmental monitoring, agricultural production and hydrological studies. Particularly, agricultural yield depends on several growing parameters like temperature, humidity, soil moisture and pH of the soil, etc. In this paper, we have designed and developed a system for measuring and monitoring soil moisture, humidity and temperature by interfacing low-cost soil moisture sensor FC-28, temperature and humidity sensor: DHT11, and using Internet of Things (IoT), Cloud computing and Mobile computing technologies. We have also implemented an online cloud computing system to keep check over soil parameters. Various methods, both laboratory and field including remote sensing are available to measure soil moisture content, but the quickest and better one is with the use of soil moisture sensor electronic devices. For successful irrigation, it is necessary to monitor soil moisture, its temperature and humidity content continuously in the...

En el presente trabajo se realiza un análisis de las transiciones ofensivas (transición defensa-ataque) realizadas por las mejores selecciones nacionales europeas de fútbol. Los principales objetivos planteados en la investigación son determinar si es posible predecir el resultado de las transiciones ofensivas del juego, y si es así, identificar qué variables permitirán realizar dichas predicciones. Para abordar estos objetivos se ha utilizado el modelo multivariable de regresión logística. La muestra consta de 14 partidos, 743 transiciones ofensivas de la fase final de la Eurocopa de Austria-Suiza 2008. La utilización de este modelo permite concluir que es posible realizar una predicción del resultado de las transiciones ofensivas que se suceden en el transcurso del encuentro y también, determinar cuáles son las variables que posibilitan realizar dicha predicción. Los datos demuestran que se puede pronosticar el resultado final de las transiciones ofensivas en función de la configu...

This research paper explores the application of AI-driven predictive analytics for detecting failures in medical devices. With
the increasing reliance on medical devices for patient care, ensuring their reliability and functionality is paramount. AI-based
predictive analytics offers a proactive approach to identify potential failures before they occur, thereby enhancing patient safety and
reducing maintenance costs. This paper examines the data characteristics, AI techniques, model development, implementation
case study, benefits, challenges, and future research directions in the context of medical device failure detection.

The proposed research presents an AI-enhanced CRM framework designed to improve customer segmentation,
predictive accuracy, and personalized engagement. Leveraging advanced Recency-Frequency-Monetary (RFM) segmentation,
KMeans clustering, and Gradient Boosting, the model achieves a predictive accuracy of 84.3%, outperforming conventional
CRM approaches. Additionally, reinforcement learning enables real-time personalization, dynamically adapting to customer
behaviors and enhancing engagement, retention, and satisfaction. Comparative analysis with existing literature underscores the
model’s superiority in scalability, segmentation granularity, and predictive reliability. This framework offers a robust, data-driven
solution for modern CRM, effectively addressing customer needs through tailored interactions.

Adam Gershowitz’s article calling for post-trial plea bargaining in capital cases reasons that governors should commute sentences to life in prison, in exceptional cases, to limit the costs of protracted post-trial litigation over imposition of the death penalty. The commutation power, in his view, resembles pre-trial plea bargaining in that both the state and the criminal defendant can benefit—the state saves resources while the defendant gets off death row. Gershowitz’s article, therefore, affords a window into the increasing use of predictive analytics in deciding whether to bring or resolve litigation. Sifting through data on all prior capital cases can yield clues as to the likelihood of success or the length of litigation in future capital cases. Not surprisingly, the past can, to some extent, help us predict the future and thereby inform the governor’s commutation decision. Deployment of predictive analytics is more familiar in the private sector. The life insurance industry ...