Statistical machine learning

The prediction of software Quality Score is carried out using advanced machine learning models, considering specific software development and execution parameters. The input parameters selected are Code Complexity, Test Coverage (%), and Deployment Frequency, which are major factors in software development. Two advanced regression models, Histogram Gradient Boosting Regressor (HGBR) and Extreme Gradient Boosting Regressor (XGBR), are used to analyze the output parameter, Quality Score. Research Significance: Software quality is a key success criterion for software applications in the modern era, and it has a direct impact on the reliability, maintainability, and satisfaction of software applications. This research has provided a data-driven understanding of the impact of software development metrics on software quality, and it has provided insights into the optimization of software engineering techniques by applying machine learning algorithms. Methodology: The study employs a systematic approach based on the concept of machine learning. First, the study uses a dataset containing software parameters like Code Complexity, Test Coverage (%), Deployment Frequency, and Quality Score. It performs Exploratory Data Analysis (EDA) to understand the relationships between the parameters. It splits the dataset into the training and testing sets.

Diabetes mellitus is a chronic disease with an increasing prevalence and may cause serious complications if not detected early. This study aims to compare the performance of the Decision Tree and Random Forest algorithms in detecting diabetes risk using the Pima Indians Diabetes Database from the UCI Machine Learning Repository. The dataset consists of 768 patient records with 8 predictor features and 1 target label. Data preprocessing was carried out through median imputation for missing values, outlier handling using the Z-Score method, normalization using StandardScaler, and class balancing using SMOTE. Furthermore, the dataset was divided into training and testing data with an 80:20 ratio. Model evaluation was conducted using confusion matrix, accuracy, precision, recall, F1-score, and ROC-AUC. The results showed that the Random Forest algorithm performed better than Decision Tree, achieving an accuracy of 85.3%, precision of 84.5%, recall of 86.3%, F1-score of 85.4%, and AUC of 0.927. Meanwhile, Decision Tree obtained an accuracy of 75.9% and an AUC of 0.807. Based on these results, Random Forest is considered more effective and stable in detecting diabetes risk compared to Decision Tree.

SAP S/4HANA is transforming enterprise resource planning, serving as the intelligent digital hub for modern organizations. This comprehensive analysis examines the key deployment options and migration strategies available to SAP ECC customers to transition to S/4HANA, addressing widespread uncertainty surrounding optimal implementation paths. The research examines three fundamental transformation approaches, providing a structured framework for organizations to assess their digital transformation journey. Through real-world implementation experiences, including successful vertex line architecture improvements and custom automation solutions, the study demonstrates S/4HANA's ability to deliver zero-defect deployments while maintaining seamless integration across key modules including FI, MM, and SD. The platform's advanced features; including real-time analytics, embedded machine learning, and artificial intelligence integration through the SAP Business Technology Platform, enable unprecedented operational efficiency and strategic agility. Supply chain management transformation is highlighted as a key benefit, with S/4HANA's unified platform improving procurement, manufacturing, logistics, and inventory control processes. The research uses machine learning methods, including support vector regression, to analyse migration complexity factors such as estimated costs, downtime requirements, resource utilization, and timeline optimization. The study serves as an essential guide for organizations looking to make informed decisions about their S/4HANA adoption strategy.

Nigeria's economic development remains constrained by persistent inefficiencies in key productive sectors, notably economic, agriculture and manufacturing. Agriculture contributed 23.4% to GDP and employed about 70% of the workforce in 2022, yet its productivity growth averaged on ly 1.2% annually. Similarly, manufacturing output declined to 9.2% of GDP due to inadequate power supply, multiple taxation, and import dependency. Previo us econometric analyses relying on Ordinary Least Squares (OLS) often yield unreliable estimates because of violations of normality, homoscedasticity, and independence assumptions common in volatile economic data. This study applies OLS and robust regression techniques to examine the economic, agriculture and manufacturing development nexus in Nigeria using data from 2005 to 2024. Comparative analyses between OLS, M-Estimator, and Modified M-Estimator models were performed across economic, manufacturing, and agricultural datasets. Findings reveal that robust methods outperform OLS across all performance metrics. The Modified M-Estimator with a tuning constant adjustment (+1) achieved the highest explanatory power (R² ≈ 0.99) and the lowest error meas ures (MSE, AIC, and BIC), indicating superior model stability and predictive accuracy. The study concludes that robust regression provides more reliable parameter estimates under conditions of outliers and heteroscedasticity. It recommends the adoption of Modified M-Estimators in empirical modeling to improve the validity of econometric results and strengthen evidence-based policymaking in Nigeria's development planning.

Traditionally, Enterprise Resource Planning (ERP) systems have relied on static rule-based mechanisms and batch analytics which limits their capacity to react to dynamic enterprise environments. This paper presents the design, implementation and experimental validation of an Adaptive AI-Driven Enterprise Resource Planning (A2ERP) framework that combines real-time data ingestion, online ensemble learning, explainable AI and scalable microservices architecture. This is not like traditional ERP enhancements that add stand-alone AI modules, but rather embeds adaptive intelligence right in the heart of the architecture. The implementation is tested with enterprise simulation datasets from finance, supply chain, HR and CRM modules. Experimental results show that its predictive accuracy (94.6%) is higher, its latency (95 ms) is lower, its throughput (1650 transactions/sec) is higher and its scalability is better than rule-based and batch ML ERP systems. The proposed framework establishes a practical pathway toward intelligent, transparent, and real-time strategic enterprise operations.

This book exists because we have watched too many AI initiatives fail for preventable reasons. Not because the models were poorly designed, not because the algorithms were flawed, but because the data that fed those models was fragmented, inconsistent, and ungoverned. We have watched organizations spend millions of dollars building machine learning systems on data foundations that could not support them, only to discover, after months or years of development, that the outputs could not be trusted because the inputs were never trustworthy. We have also watched organizations build excellent master data management programs that transformed their data quality and governance capabilities, enabling AI initiatives that delivered real value because they operated on a foundation of trusted data. The difference between these outcomes was not talent, budget, or technology. It was the presence or absence of a systematic, sustained commitment to data governance as the prerequisite for everything else. The intellectual foundation of this book is built on five internationally published research papers and three international patent applications that were filed in 2022. These publications represent years of research, experimentation, and production validation. The anomaly detection framework, the NLP metadata enrichment pipeline, the evidence-mapped governance architecture, the regulatory intelligence engineering approach, and the human-supervised AI control architecture described in these papers have all been tested in production environments where the cost of failure was measured in regulatory penalties, patient safety risks, and financial losses. We wrote this book for the technology leaders, data governance professionals, and MDM practitioners who are responsible for building the governed data infrastructure that enterprise AI requires. We wrote it to be comprehensive enough to serve as a reference for experienced practitioners and accessible enough to serve as an introduction for professionals who are new to MDM. We wrote it to bridge the gap between the academic literature on data governance and the practical realities of building and sustaining governance programs in complex organizational environments.
— 6 —
Most importantly, we wrote this book because the work it describes matters. In an era where AI-driven decisions affect credit access, healthcare outcomes, regulatory compliance, and customer experience, the quality and governance of the data that feeds those decisions is not a technical concern. It is an ethical obligation. We hope this book helps you fulfill it.

AI-powered data warehousing represents a significant evolution in cloud storage technologies, reshaping the way organizations handle, analyze, and extract insights from their growing data volumes. As data generation accelerates across a variety of industries, traditional on-premises storage solutions are proving inadequate to meet the growing demands for scalability, high-speed processing, and intelligent data management. Combining Cloud-based machine learning (ML) and artificial intelligence (AI) warehousing addresses these challenges by unlocking powerful capabilities such as real-time analytics, predictive insights, and automated data manipulation.This study explores the transformative role of AI in cloud storage, focusing on key performance indicators such as data volume, query latency, AI optimization, redundancy strategies, and compression performance. Using advanced Machine learning techniques, especially random forest, decision tree regression, and XG boost regression-we evaluated the performance of cloud storage systems under various configurations. Our analysis confirms that AI-integrated solutions outperform conventional methods, especially in optimizing queries, ensuring data quality and dynamically allocating resources. The results highlight that data compression rates and AI optimization levels are the most influential factors affecting cloud storage performance. Correlation analysis reveals strong positive correlations between these variables and overall performance metrics. Among the models tested, Random Forest Regression demonstrated the best accuracy, achieving R² scores of 0.9965 on the training data and 0.9520 on the test data, indicating excellent generalization. XGBoost, while accurate on the training data, showed signs of overfitting. In contrast, decision tree regression struggled with the complexity of the data and revealed its limitations. Furthermore, the study highlights how AI enables real-time data processing, supports intelligent automation through robotic process automation (RPA), and improves cyber security through continuous operational monitoring and anomaly detection. Server less architecture benefit from AI-driven optimization for resource management and cost control, while hybrid and multi-cloud deployments benefit from adaptive workload distribution and seamless data integration. While barriers such as talent shortages and administrative requirements are important considerations, these advances empower organizations to make faster decisions, increase efficiency, and gain a competitive advantage.

Background: Bladder cancer (BC) is a life-threatening malignancy that can be successfully treated if diagnosed in its early stages. Machine learning techniques, by using large biological databases, are suggested as important approaches for identifying accurate diagnostic biomarkers. The present study aimed to introduce a simple and accurate model for the diagnosis of BC.
Methods: RNA-sequencing information of 412 primary bladder tumors versus 19 normal bladder tissues from The Cancer Genome Atlas were analyzed using the TCGAbiolinks R package to identify differentially expressed genes (DEGs). Gene ontology properties and the corresponding pathways of DEGs were investigated using the online ShinyGO tools. To develop a diagnostic model for BC, two binary classifier machine learning algorithms, C5.0 and CHAID, were employed in three subgroups of train, test, and validation sets using SPSS Modeler version 18.1. Their efficacy was evaluated using performance measures for binary classification.
Results: Most of the identified DEGs were associated with microtubule organization, coagulation, and myelination. Based on the constructed models, four important RNAs (Tubulin Polymerization-Promoting Protein: ENSG00000171368, Proteolipid Protein-1: ENSG00000123560, RP11-473E2: ENSG00000228877, and Coagulation Factor X: ENSG00000126218) were identified as important classifiers for diagnosis in both C5.0 and CHAID models. The CHAID model demonstrated superior performance in the testing dataset, achieving an accuracy of 98.75%, an F1-score of 99.36%, and an AUC of 99.4%.
Conclusion: According to the results, machine learning algorithms are beneficial for the diagnosis of BC and potentially useful for improving personalized medicine in BC patients. The developed model may serve as a non-invasive, data-driven tool to support early diagnosis and personalized treatment planning in clinical settings. Further evaluation using laboratory tests is suggested to validate the obtained results.

evidence formation; epistemic mediation; objectivity;
underdetermination; philosophy of science; machine learning; statistical inference;
measurement theory; research integrity; research quality; knowledge prod

Contemporary empirical science increasingly relies on complex data-processing pipelines in which observations are not used directly, but are transformed through multiple stages of measurement, operationalization, modelling, inference, and interpretation. While these procedures are often treated as methodologically neutral, this paper argues that they are epistemically formative: they actively shape what can count as evidence in scientific reasoning.

The forecasting of epidemics, if done accurately, could help in strengthening disease surveillance, outbreak preparedness and public health decision-making, especially in low-resource settings. The current study develops and evaluates the forecasting framework by combining classical time series models and machine learning algorithms. An epidemiological data set of 99840 observations was analyzed for a wide array of epidemiological, environmental, demographic, and health sector variables including weekly cases, deaths, hospitalizations, rainfall, temperature, relative humidity, vaccination, population density and health sector indicators. The experts used Mean Absolute Error, Root Mean Square Error, Mean Absolute Percentage Error, and coefficient of determination (R²) to evaluate the forecasting performance. SARIMA performed best among the traditional time-series models with MAE = 13.51, RMSE = 18.67, MAPE = 12.41%, R² = 0.879, while ARIMA and Holt-Winters did worse. The findings show that the machine learning models performed better when compared to the other models. In fact, LSTM managed to get the highest prediction accuracy, which was found to have an MAE of 8.74, an RMSE of 11.63, an MAPE of 7.54%, and 0.953 R2 XGBoost was next best in prediction accuracy with MAE of 9.26, RMSE of 12.88, MAPE of 8.02% and 0.941 R2. The results of the statistical analysis indicate a significant outperforming of the machine learning models over the traditional methods, specifically ARIMA versus XGBoost (t = 7.94, p < .001) and SARIMA versus LSTM (t = 5.13, p < .001). Applying the independent samples t-test between the accuracy results of XGBoost and LSTM produced t = 1.33, p = .185 meaning no statistically significant difference existed between the two results. Feature importance analysis clearly shows that Lag-1 Cases, Lag-2 Cases, and Lag-4 Cases are the top three predictors of future cases. LSTM took the longest training time (148.4 s) and memory consumption (1,245 MB) in terms of computational performance while SARIMA has much lower computational requirements of 13.8 s, 118 MB. The multi-criteria evaluation carried out under low-resource conditions ranked SARIMA as the foremost model with a score of 89.8 points. This model was the best balance of accuracy, efficiency, timeliness, robustness, interpretability, and operational feasibility. Findings show that while LSTM provides highest accuracy in prediction, SARIMA offers the most practical and scalable forecasting designs for epidemic surveillance and early warning application in low resource public health settings.

Educational institutions generate large volumes of student-related data, including attendance records, internal assessment marks, assignment scores, and semester examination results. However, this data is often underutilized for proactive academic decision-making and early intervention strategies. Traditional approaches rely mainly on end-semester evaluations, which limit the ability of educators to identify students who are at risk of poor academic performance in a timely manner. This research aims to apply predictive analytics and machine learning techniques to forecast student academic performance and to identify at-risk students at an early stage of the academic cycle. The proposed system utilizes historical student data collected from academic records and applies data preprocessing techniques such as data cleaning, normalization, and feature selection to improve model performance. Classification algorithms including Decision Tree, Logistic Regression, and Naïve Bayes are implemented to build predictive models. The performance of these models is evaluated and compared using standard evaluation metrics such as accuracy, precision, recall, and F1-score. The experimental results indicate that machine learning-based predictive models can effectively classify students into performance categories and accurately identify those who are likely to face academic difficulties. The findings of this study highlight the practical value of predictive analytics in educational environments. By identifying at-risk students early, institutions can design targeted academic support mechanisms such as mentoring programs, remedial classes, and personalized learning plans. Furthermore, the proposed approach supports data-driven academic planning, improves student retention rates, and enhances overall learning outcomes. The research demonstrates that integrating predictive models into academic information systems can significantly contribute to improved student performance, institutional efficiency, and informed decisionmaking in higher education.

AI-powered data analytics is transforming decision-making across healthcare, public governance, and corporate strategy by enabling organizations to extract meaningful insights from large and complex datasets. With the rapid growth of digital data from electronic health records, enterprise systems, and online platforms, traditional analytical methods are no longer sufficient for handling high-volume, high-velocity information. Artificial intelligence technologies such as machine learning, deep learning, natural language processing, and predictive analytics provide advanced capabilities for identifying patterns, generating forecasts, and supporting real-time decision-making. In healthcare, AI enhances diagnostic accuracy, optimizes resource allocation, and supports personalized treatment. In public policy, it improves evidence-based governance, strengthens service delivery, and enables proactive crisis management. In corporate strategy, it supports market forecasting, customer intelligence, and operational efficiency. This study explores the conceptual foundations and applications of AI-powered data analytics across these sectors, highlighting its benefits in improving efficiency, accuracy, and responsiveness. However, challenges such as data quality, ethical concerns, and algorithmic transparency remain significant. Overall, AI-powered analytics is becoming a core infrastructure for modern data-driven decision systems.

Neurological and psychiatric conditions including Alzheimer's disease, PTSD, depression, and schizophrenia affect hundreds of millions of people globally, yet existing pharmaceutical treatments are expensive, inconsistent, and out of reach for many. This paper proposes frequency-based music therapy, delivered through an AI-powered mobile application called Querey, as a clinically grounded and non-invasive alternative. Querey is built around three components: a state-based discovery survey, an adaptive AI coach, and a mood stimulation engine rooted in brainwave entrainment and BPM science [9]. Challenges included music licensing constraints, navigating App Store deployment as a first-time developer, and maintaining data accuracy across the personalization pipeline. Experiments showed a mean satisfaction score of 7.5 out of 10 for BPM accuracy, with calming prescriptions outperforming energizing ones, and a twelve-week clinical trial comparing Querey against live therapy and passive listening across diagnosed populations [1]. When technology is designed around how the brain actually works, the results speak for themselves.

The proposed movie review system leverages machine learning and natural language processing (NLP) techniques to evaluate and classify user feedback on films. By analysing textual reviews, the system categorizes sentiment into positive, neutral, and negative sentiments, offering a clear understanding of audience reactions. Key NLP techniques such as tokenization, stemming, and stop word removal prepare the data for further processing. Sentiment prediction is achieved using machine learning models like Naive Bayes and Random Forest. The system detects patterns in movie reviews, providing valuable insights into film performance and audience satisfaction. It supports prospective viewers by offering a summarized sentiment analysis to aid in their decision-making. Additionally, it assists filmmakers and industry professionals by offering data-driven insights into audience feedback, improving decisionmaking in areas like marketing, production, and development. In essence, the system enhances interaction between filmmakers and audiences, fostering growth in the entertainment industry.

Transportation optimization and route planning have become central challenges in large-scale logistics operations,
where rising demand, network complexity, and cost pressures require more intelligent and adaptive decisionmaking systems. At a broader level, traditional optimization approaches such as shortest path algorithms and linear
programming have provided foundational solutions but are increasingly insufficient in handling real-time
variability, stochastic demand, and dynamic constraints inherent in modern supply chains. The emergence of
advanced data analytics frameworks, integrating big data, machine learning, and real-time sensor inputs, has
transformed the landscape of logistics optimization by enabling predictive, prescriptive, and adaptive routing
strategies. Narrowing the focus, this study examines the development of scalable analytics frameworks that
combine graph-based optimization, reinforcement learning, and real-time data streams to enhance route efficiency
and operational performance. These frameworks leverage high-dimensional data sources, including GPS tracking,
traffic patterns, weather conditions, and demand forecasts, to dynamically update routing decisions. The
integration of predictive models with optimization algorithms improves fuel efficiency, reduces delivery time
variability, and enhances resource utilization. Empirical insights suggest that such frameworks significantly
outperform static routing models by enabling continuous adaptation to network disruptions and demand
fluctuations. Overall, advanced data analytics frameworks provide a robust foundation for optimizing
transportation systems, improving resilience, and achieving cost-efficient logistics operations in complex
environments.

A novel approach for determining the freshness of fish and meat involves the use of cantilever
sensors, which analyse the concentration of cadaverine on the surface. The cantilever sensor is
excited with a voltage sweep around its resonance frequency and the frequency shift due to
deposits on the sensor is measured. In this work, we present a draft of a distributed system and
compare AI-based analysis of the stored cantilever sensor data with raw sweep data without
preprocessing. We defined a meat quality index (mqi) range for the measurements, which depends
on the frequency shift between a reference and cadaverine measurement. We investigated, that
the best practice to predict the mqi value is to use classical machine learning models such as
Random Forest, LightGBM, XGBoost where Random Forest performs best with an val. / test
accuracy of up to 72.01 % / 71.67 %, precision of 72.37 % / 72.53 %, recall of 72.01 % / 71.67 %
and F1-Score of 72.06 % / 71.72 %.

This paper presents a rigorous mathematical analysis of optimization algorithms central to deep learning, including Gradient Descent (GD), Stochastic Gradient Descent (SGD), Momentum, Adam, and AMSGrad. We compare and discuss the update rules for each algorithm, delving into their underlying mathematical techniques such as Taylor expansions for approximating loss functions and gradients, and the theory of dynamical systems for understanding acceleration properties. We prove their convergence properties under standard assumptions, including convexity, smoothness (Lipschitz continuity of gradients), and strong convexity. Furthermore, we analyze their rates of convergence for various scenarios, such as O(1/t) for convex and smooth functions in GD, and O(1/ √ t) for stochastic methods in non-convex settings. We also consider the impact of bounded gradients in stochastic settings and the use of Lyapunov functions for proving convergence. Through this analysis, we aim to bridge the gap between theory and practice, offering insights into the design and application of optimization algorithms in deep learning.

Abstrak (Times New Roman 12, Bold, spasi 1, spacing before 12 pt, after 2 pt) Diabetes melitus merupakan penyakit kronis yang prevalensinya terus meningkat dan dapat menyebabkan berbagai komplikasi serius apabila tidak dideteksi sejak dini. Penelitian ini bertujuan untuk membandingkan kinerja algoritma Decision Tree dan Random Forest dalam mendeteksi risiko diabetes menggunakan dataset

In increasingly dynamic and technology-driven environments, healthcare professionals are required to adapt rapidly, making employee agility a critical capability. This study is to analyze the influence of employee training, organizational flexibility, and proactive personality on learning agility, as well as the impact of learning agility on employee agility. This study employs an explanatory quantitative approach, with data collected from 177 physicians in Semarang Regency using purposive sampling techniques. Data were analyzed using Structural Equation Modeling-Partial Least Squares (SEM-PLS). The findings indicate that employee training and organizational flexibility have significant positive effects on learning agility, and that learning agility, in turn, significantly enhances employee agility. However, proactive personality does not exhibit a significant effect on learning agility. These findings suggest that organizational factors and structured training play a more dominant role than individual characteristics in fostering adaptive capabilities among healthcare professionals. In conclusion, strengthening training programs and enhancing organizational flexibility are essential strategies for improving employee agility, particularly within highly structured and rapidly evolving healthcare environments.

Artificial intelligence is undergoing a fundamental transition from information generation to behavioral forecasting. While public discourse remains focused on generative capabilities, predictive systems are increasingly being designed to anticipate human actions, forecast behavioral patterns, and model psychological vulnerabilities at scale. This paper examines the emergence of behavioral forecasting as a dominant paradigm in AI development and analyzes its implications across cybersecurity, operational technology, critical infrastructure protection, and national security. Through systematic analysis of current applications and emerging threat vectors, this research demonstrates that behavioral forecasting represents one of the most consequential technological developments of the twenty-first century. The ability to predict human behavior with increasing accuracy fundamentally reshapes the attack surface in cybersecurity, extends the scope of infrastructure vulnerability beyond traditional technical domains, and introduces unprecedented risks for social engineering, election interference, and cognitive warfare. Simultaneously, predictive systems offer substantial defensive capabilities in anomaly detection, insider threat identification, and infrastructure resilience. The paper identifies critical challenges including explainability of predictive models, ethical governance frameworks, and the need for transparency mechanisms in high-stakes applications. Evidence suggests that organizations capable of developing robust behavioral forecasting systems will gain substantial strategic advantages, while those failing to address associated risks face heightened exposure to sophisticated, algorithmically-optimized attacks. The future of cybersecurity increasingly depends not on reactive defense but on predictive intelligence.

Power distribution networks are increasingly susceptible to faults arising from aging infrastructure, integration of renewable energy sources, and growing grid complexity. Accurate, real-time fault classification is paramount for minimizing outage durations, reducing operational costs, and ensuring the stability of modern smart grids. This paper proposes a Quantum Machine Learning (QML) framework that integrates Variational Quantum Circuits (VQC), Quantum Support Vector Machines (QSVM), and a novel quantumenhanced Long Short-Term Memory (QLSTM) architecture for multi-class fault detection and energy systems optimization. The proposed method encodes three-phase current and voltage measurements into quantum states via amplitude encoding, extracts entanglement-based feature representations, and classifies faults-including single line-to-ground, double lineto-ground, line-to-line, and three-phase faults-with high accuracy. Furthermore, a quantum annealing module is embedded to solve the unit commitment optimization problem under stochastic renewable generation. Simulation results on the IEEE 13-bus and 33-bus test feeders demonstrate that the proposed QML framework achieves a classification accuracy of 98.7%, a precision of 97.9%, and a recall of 98.3%, outperforming state-of-the-art classical deep learning baselines by up to 4.2 percentage points while reducing computational complexity from O(n 3) to O(log n) for certain subroutines. The quantum optimization module converges to near-optimal unit commitment schedules ∼ 35% faster than classical mixedinteger programming solvers. These results highlight the transformative potential of QML as a next-generation tool for intelligent power system management.

Identifying environmentally friendly materials is essential for tackling worldwide sustainability issues, but
conventional methods frequently face drawbacks such as excessive expenses and sluggish advancement owing to
the extensive range of potential designs and intricate connections between properties. We propose a unified machine
learning and big data approach to expedite the development of sustainable materials by methodically integrating
computational, experimental, and data extracted from existing literature. The framework consists of four key
components: multi-source data acquisition, rigorous preprocessing, advanced model development, and robust
validation. Information is gathered from various sources, processed, and standardized to achieve uniformity, with
the creation of informative attributes including atomic traits and structural features. A variety of machine learning
algorithms, such as Random Forests, XGBoost, and Graph Neural Networks, are applied to model nonlinear
relationships and atomic-level interactions, with hyperparameters fine-tuned via grid search. The models are
evaluated using cross-validation and metrics such as RMSE, MAE, and 𝑅
2
to ensure reliability. Our method shows
considerable promise in lowering the time and expense linked to materials discovery by supporting high-throughput
screening and predictive modeling. Moreover, the inclusion of synthetic data generation increases dataset diversity,
which leads to better model generalizability. The proposed framework not only propels progress in the realm of
sustainable materials but also establishes an adaptable model for additional disciplines requiring data-centric
innovation. This work addresses the gap between computational predictions and experimental validation, advancing
the creation of sustainable technologies that have extensive environmental and industrial implications.

The human elements of personality working behind the creation of a write-up play an important part in determining the final dominant mood of a text. This paper presents a tool, PsycheTagger, which extracts the emotive content of a text in English Language in its context and tags each open-class word of the text with one of the predefined psyche categories that represent the emotive content. Working in the lines of statistical Partsof-Speech Taggers, this tool is an example of a semantic tagger. The tagger self-ranks its choices with a probabilistic score, calculated using Viterbi algorithm run on a Hidden Markov Model of the psyche categories. The results of the tagging exercise are critically evaluated on the Likert scale. These results strongly justify the validity and determine high accuracy of tagging using the probabilistic parser.

Artificial intelligence has achieved enormous visibility in recent years, mostly thanks to the success of deep learning and its generative AI applications. Still, current state-of-the-art models remain brittle and struggle to provide reliable predictions under settings that differ, often even marginally, from those that generate their training data. The issue is only compounded when one attempts to enable machines to continually learn from data, in an imitation of humans' lifelong learning experience. While recognizing this issue under various names (e.g., 'overfitting' or 'model adaptation'), traditional machine learning seems unable to address it in radical ways. We argue that a real breakthrough requires a proper mathematical treatment of the 'epistemic' uncertainty stemming from a forcibly partial knowledge of the world, which in turn links to both the continual learning from new data and the injection of knowledge in a neurosymbolic sense. Our position supports the creation of a new continual learning paradigm designed to provide worst-case guarantees on model predictions throughout the learning process, coupled with the extension of neurosymbolic AI under epistemic uncertainty, as the two main channels to reduce the latter via additional knowledge.