In recent years, deep learning techniques have emerged as powerful tools for analyzing and predict- ing complex patterns in sequential data across various fields. This study employs an ensemble of advanced deep learning models: Long Short-Term Memory (LSTM), Bi-Directional LSTM, Gated Recurrent Unit (GRU), LSTM Convolutional Neural Network (CNN), and LSTM with Self-Attention, to enhance prediction accuracy in time series forecasting. These models are applied to three distinct financial datasets: Tata Motors, HDFC Bank, and INFY.NS, we conduct a thorough comparative analysis to assess their performance. Utilizing K-fold cross-validation, we convert loss (MSE) into RMSE and MAPE, which help estimate accuracy .we achieved train accuracies of 97.46% for Tata Motors, 75.93% for INFY.NS, and 56.60% for HDFC Bank. Our empirical results highlight the strengths and limitations of each model within the ensemble framework and pro- vide valuable insights into their effectiveness in capturing complex patterns in financial time series data. This research underscores the potential of deep learning-based ensemble techniques for improving stock price forecasting and offers significant implications for investors and the development of sophisticated trading and risk management systems.

The current society’s development is the intensive growth of human needs. That leads to an increase in production volumes. That requires an appropriate level of product transportation. Currently, there are various kinds, including automobile, railway, water, and air transport. According to the International Maritime Organization, maritime transport is the undisputed leader in international transportation; however, on land, road freight transportation surpasses other types in demand. That is due to the mobility of cars and the availability of a well-developed road infrastructure, which allows cargo to be delivered directly from the seller to the customer. In this regard, there is a need to plan routes for vehicles, solve transport tasks, and ensure the rational use of the carrying capacity of means of transport. When organizing cargo transportation, tasks include building optimal routes, minimizing transportation costs, and avoiding the underutilization of the truck. Continuous improvement of cargo delivery is a serious strategic objective of competing transport companies. It is necessary to regulate the costs of the services provided. Cost management and optimization are serious tools in organizing a transport company, which contribute to increasing its efficiency. That is due to the relevance of the research topic. The article discusses the theoretical and methodological aspects of cost optimization in transport companies, presents some optimization models, and justifies their application. Practice shows that these models can be applied to the activities of cargo carriers to significantly reduce unproductive costs and ensure the achievement of strategic goals, such as achieving market leadership positions and increasing competitiveness.

The rapid proliferation of Internet of Things (IoT) devices has revealed weaknesses in its centralized communication architectures, rendering them vulnerable to security risks such as Distributed Denial of Service (DDoS) attacks. This scenario highlights the need for secure and efficient communication frameworks to safeguard IoT networks. In this paper, we present a blockchain-based framework designed to improve IoT communication networks' security, scalability, and performance. Our methodology utilizes decentralized architecture to mitigate risks linked to centralized sources of failure while enhancing performance metrics, including latency, throughput, energy consumption, and transaction success rates. We present an innovative approach that integrates a plateau effect in latency and consensus time, guaranteeing performance stability as the number of devices increases. The proposed model demonstrates decreases in latency by 26.57% and reductions in energy usage by 35.29% compared to existing Ethereum frameworks, based on extensive simulations conducted under diverse network conditions with one thousand devices, underscoring the framework's effectiveness in managing network congestion. This research offers a viable answer to the problems of IoT communication, facilitating future investigations into the optimization of blockchain integration for improving IoT security and efficiency.

Cardiovascular disease (CVD) remains a leading global cause of mortality, underscoring the importance of its early detection. This research leverages advanced Machine Learning (ML) algorithms to predict Coronary Heart Disease (CHD) risk by analysing critical factors. A comprehensive evaluation of ten ML techniques, including K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), AdaBoost, Multi-Layer Perceptron Neural Network (MLPNN), and Extremely Randomized Trees (ERT), was conducted. The ERT algorithm demonstrated superior performance, achieving the highest test accuracy of 88.52%, with precision, recall, and F1-scores of 0.89, 0.88, and 0.88, respectively, for class 0 (no CHD), and 0.88, 0.91, and 0.89, respectively, for class 1 (CHD). The model was optimized using hyperparameters such as a bootstrap setting of False, no maximum depth, a minimum sample split of 2, a minimum leaf size of 4, and 300 estimators. This study provides a detailed comparison of these techniques using metrics such as precision, recall, and F1-score, offering critical insights for optimizing predictive models in clinical applications. By advancing early detection methodologies, this work aims to support healthcare practitioners in reducing the global burden of cardiac diseases.

Precision agriculture transform the agricultural sector by integrating advanced technologies to enhance productivity and sustainability. In crop farming, precision agriculture can significantly improve practices through precise monitoring and data-driven decision-making, addressing challenges such as optimizing resource usage and improving crop health. This study presents the development and implementation of an IoT-based Crop Recommendation System designed to optimize farming practices through a mobile application. This system uses different sensors to continuously extract data regarding the temperature, pH, NPK value and other relevant parameters. These parameters can be analyzed in real-time to help farmers make informed decisions on irrigation, fertilization, and crop selection, tailored to specific field conditions. This information is stored to create individual datasets, offering researchers valuable insights into optimal conditions for various crops. This can improve yield and promote sustainable farming practices. In this study, we evaluated a series of machine learning algorithms for their ability to predict an optimal crop based on environmental parameters. Among these algorithms, Naive Bayes demonstrated superior performance, achieving an accuracy of 99.55%, precision of 99.58%, recall of 99.55%, and F1-score of 99.54%. These findings highlight the effectiveness of our approach in integrating machine learning with the IoT for precise crop management. Implemented through a user-friendly mobile application, the proposed system enhances accessibility and usability for farmers.

The service sector, particularly banks, has undergone a significant shift in recent years. This has resulted in increased pressure and stress for bank employees who strive to provide timely and efficient services while meeting management objectives and ensuring customer satisfaction. This research employs a comprehensive methodological approach to examine the Quality of Work Life (QWL) and Job Satisfaction (JS) within the banking sector in Andhra Pradesh. The research focuses on confirming the construct validity of QWL and JS through Confirmatory Factor Analysis (CFA) and assessing the reliability of the measurement model using Cronbach's Alpha. Discriminant validity is examined to ensure that these constructs represent distinct concepts. The research employs Structural Equation Modeling (SEM) to explore the correlation between QWL and JS, as well as their interactions with factors such as Motivation and Compensation, Work Factors, Safety and Welfare, Relationship and Support, Nature of Job, and Career Growth and Development. The outcomes of this research offer valuable insights into the banking industry in Andhra Pradesh. By validating the QWL and JS constructs and understanding their relationships, the research serves as a foundation for organizations to enhance employee well-being and job satisfaction. The study provides practical recommendations, tailored to the specific needs of bank employees in Andhra Pradesh, to improve work-life balance, career development, compensation, safety, relationships at work, and overall employee well-being.

The paper conducted a comprehensive analysis of the time series of stock prices of three leading energy companies – Shell, BP and ExxonMobil – for the period from January 2021 to January 2025. At the initial stage, data quality was checked: dates were set as indices, the absence of duplicates and missing values was confirmed, and descriptive statistics (mean, variance, skewness and kurtosis) were calculated. Next, the trends of adjusted closing prices (AdjClose) were analysed using moving averages (SMA14, SMA50), exponential smoothing, moving volatility (30-day standard deviation) and cumulative returns. It was found that еhe price dynamics growth has accelerated since 2022 against the background of the energy crisis caused by the war in Ukraine: ExxonMobil’s cumulative return reached ≈250% by mid-2022 and ≈350% at the beginning of 2025, Shell and BP, respectively ≈220% and ≈200% by 2024. Correlation analysis showed that BP and Shell have the most significant interdependence (r = 0.87, R² = 0.75). The autocorrelation method established high non-stationarity of the time series (ACF about one at low lags). K-Means clustering (k = 2) allowed us to distinguish periods of active growth and relative price consolidation, although the feature selection behind this clustering requires further clarification. The initially reported financial metrics (Sharpe,  
Sortino, and Calmar ratios) were significantly overstated due to unit errors, specifically, using percentage values as absolute figures. After applying appropriate annualization and decimal scaling performance indicators were obtained for ExxonMobil – CAGR = 36.84%, Sharpe ≈ 1.24, Sortino ≈ 1.9–2.5, Max Drawdown = 20.51%, Calmar ≈ 1.80; Shell: CAGR = 21.29%, Sharpe ≈ 0.76, Sortino ≈ 1.2–1.5, Max Drawdown = 25.04%, Calmar ≈ 0.85; BP: CAGR = 14.54%, Sharpe ≈ 0.53, Sortino ≈ 0.9–1.2, Max Drawdown = 26.23%, Calmar ≈ 0.55. The study confirms that ExxonMobil showed the most stable and substantial growth during the examined period, while BP exhibited the highest volatility. Shell demonstrated an intermediate performance level. The close correlation between Shell and BP is attributed to the similarity in their geographical market activity and stock behaviour. The choice of these methods of analysis is due to the desire to assess the behaviour of stocks during the period of increased market volatility caused by the energy crisis, geopolitical risks and changes in investor priorities. Technical analysis allows you to identify short- and medium-term patterns, clustering allows you to automatically separate market phases without the need for subjective hypotheses, and statistical metrics will enable you to compare the performance of assets within the industry. This research contributes to the broader field of financial analysis by demonstrating how machine learning and technical analytics tools can be applied to assess the resilience and relationships of assets during periods of market turmoil. The results can be helpful for institutional investors, financial analysts, and portfolio managers looking to adapt strategies to dynamic energy market conditions.