Most modern banks have incorporated IoT into their operations to offer customers better services, while the IoT nature of banking systems poses several security threats. There is nothing more irreplaceable than the banking sector, which deals with sensitive financial information; hence, the need for more protective measures against cybercriminals. In response, this research work puts forward a new Multi-instance Coupled Modular Neural Network with Newton-Raphson Optimizer (M-CMNNet-NRO) to achieve efficient attack detection within an IoT-based banking system. The model begins with text processing of raw data gathered from various IoT devices, utilizing Zero-shot Text Normalization (Z-STN), which aims to normalize and standardize textual data without requiring any prior sample data. Then, the Geometric Algebra Transformer (GAT) further delves into the data to incorporate additional features while navigating complex structures and patterns. The M-CMNNet effectively analyzes multiple instances of data simultaneously and can therefore identify new and complex attack patterns as well. To enhance the model's efficiency, the Newton-Raphson-based Optimizer (NRO) further adjusts the weights to improve convergence and performance. The findings show that the integrated model outperforms existing systems, achieving an accuracy of 99.45%, a recall of 99.60%, and an AUC of 99.90%, with the lowest error rate of 0.55%. These are valuable results because they emphasize its stability and fast running, which would make it applicable to the purpose of real-time fraud detection.

Maintenance resources and challenges to remote monitoring contribute very much to challenges in building infrastructure reliability and sustainability of rural electrification projects and especially those based on decentralized solar and grid systems. In order to resolve such problems, this paper proposes a new and transparent predictive maintenance warning system based on a hybrid deep learning model known as ElectroConvLSTM. The model manages to capture the existing spatio-temporal dependencies, combining the CNNs and the LSTM networks, which demonstrates the early warning signs that correlate to the anomalies in performance and irregularities in usage. A feature selection step is proposed using the new Mutual Information-driven Golden Beetle Optimization (MIGBO), with the combination of Golden Jackal Optimization (GJO) and Dung Beetle Optimizer (DBO), as well as Mutual Information for . The proposed setting is aimed at increasing model accuracy, and interpretability. The step helps to make the prediction process more precise and triggers fewer warning events only the most relevant variables participate in the process. The suggested system can help run active, data-driven preservation in rural energy structures, presenting understandable and practical warning to parties. The experiments show outstanding results and it is shown that the MCC is 0.99257, the F1-score is 0.99333 and the accuracy is 0.99229 which indicate that this method is effective. The given solution is very helpful in increasing resource availability of operation in terms of reliability, transparency, and trust in rural electrification systems, which have to face constraints of resources.

Heating, ventilation, and air conditioning (HVAC) systems account for a substantial proportion of global energy consumption. While numerous control strategies have been developed to reduce energy consumption, conventional methods fail to balance energy efficiency and thermal comfort effectively due to the inherent nonlinearities, time-varying dynamics, and multivariable coupling effects of HVAC systems. Although interval type-2 fuzzy logic controllers (IT2 FLCs) can mitigate such uncertainties, their performance is critically dependent on the optimal configuration of membership function (MF) parameters, which conventional methods often fail to achieve. To address these issues, this paper proposes an HVAC-adapted IT2 FLC and develops an improved subtraction-average-based optimization algorithm (ISABO) with adaptive mechanisms to enhance MF parameter tuning. Benchmark tests demonstrate that ISABO achieves faster convergence and higher solution accuracy than the original subtraction-average-based optimization algorithm. The results of the simulation experiments verify the superiority of the proposed method: temperature tracking errors are reduced to near-zero values, humidity ratio deviations decrease to 2.8%, and energy consumption is lowered by 22.8% compared with conventional fuzzy controllers.

In recent days, skeletal bone age assessment gained more attention from researchers for auxiliary diagnosis and prediction in medical issues. Hence, it is essential to undertake more than a few complications existing in the traditional techniques in order to enhance the age assessment efficiency. So, this research work presented an intellectual skeletal bone age estimation method with neural network learning. At first, the needed images are gathered as of the available online source. Further, from gathered images, three sets of features are extracted from Vision Transformer (ViT) features as F1, Local Weber Pattern (LWP) image as F2, and raw image as F3. Subsequently, the resultant features are fed into the Vision Transformer-based Multi-scale MobileNet (ViT-MMNet) designed for assessing a skeletal bone age. In this network, multi-scale MobileNet is considered to execute the prediction process, where the ViT-based features are given to the first convolution layer, LWP-based features are given to the second convolution layer, and finally, in third convolution layer, the original images collected from the datasets are directly given. Finally, detailed experimental validations are conducted for the designed skeletal bone age assessment framework through traditional methods to assure the efficacy of the method.

This investigation explores the impact of digital economy transition (DET) on sustainable innovation total factor productivity (SITFP) across China's prefecture-level cities from 2007 to 2019. Addressing critical gaps in urban-level data and the nonlinearity of effects, the research employs a spatial Durbin model (SDM) to capture direct and spillover influences, complemented by threshold regressions to identify key transition points. Findings indicate that DET not only directly enhances SITFP but also generates significant spillover benefits in neighboring cities, emphasizing the role of interregional digital infrastructure diffusion. Moreover, threshold analyses reveal distinct breakpoints beyond which the positive effects of DET on innovation productivity become more pronounced. The investigation further underscores the function of FER and IER in amplifying digital transformation benefits, with regulatory rigor and public awareness acting as key enablers. Subgroup analyses suggest that economically advanced regions and resource-dependent cities experience the most substantial improvements, while certain areas exhibit weaker or even adverse spillover effects. This observed heterogeneity highlights the importance of tailoring policy interventions to the unique economic and infrastructural characteristics of each region. Through the integration of spatial econometric techniques and threshold modeling at the urban scale, this study advances our understanding of how digital transformation, environmental regulation, and innovation interact in diverse city contexts. The results carry significant policy relevance, advocating for strategic digital investment, strengthened regulatory frameworks, and enhanced cooperation among cities to fully realize the benefits of sustainable innovation.

Aerobic Training (AT) and Resistance Training (RT) are the two common exercise modalities for weight managing and physical health. AT comprises rhythmic, continuous movement that improves cardiovascular endurance and calorie expenditure, whereas RT focuses on muscle strengthening through measured exercises with weights. There is a need for clear comparison research to guide tailored exercise programs for optimal health results. The research aims to compare the influences of RT and AT on weight reduction and body composition in adult individuals. The research proposed the Adaptive Decision Tree (ADT) to identify patterns in participant response and predict fat loss trends. A total of 40 adults aged 20–40 years, with fluctuating fitness backgrounds, were randomly allocated into two equal groups: one engaged in structured AT, and the other in RT-based routines. The intervention was ten weeks long. Participants charted a supervised protocol scheduled at 5 days/week for 30 min at a moderate intensity of AT exercise for the AT group and a full-body RT (3 days/week) routine with progressive overload targeting major muscle groups for the RT group. Pre- and post-intervention data were composed on lean mass, waist-to-hip ratio, body weight, and body fat percentage. Paired and independent t-tests, descriptive statistics, and Pearson correlation coefficient (PCC) were employed to assess within- and between-group differences. The statistical analysis was executed using SPSS v26, with a significance threshold of p < 0.05. Results demonstrated that both groups presented decreased body fat mass and body weight, with the AT group indicating a superior average weight loss (−4.3 ± 1.2 kg) and the RT group showing a greater gain in lean body mass (+1.9 ± 0.8 kg). The ADT model achieved a higher R-squared value of 0.962084, lower RMSE and MAE, indicating strong predictive accuracy for fat loss trends. Overall, the research demonstrated that AT encourages better weight loss than RT training, but RT training affects positive changes in body composition. The shared insights support tailored program design based on individual health goals.

Transformer fault diagnosis faces significant challenges due to the scarcity of labeled data and the imbalance among fault categories. To address these issues, a novel model, SSRL-TFD, is proposed, leveraging self-supervised representation learning specifically designed for small, imbalanced datasets. The model incorporates a two-stage training process along with knowledge transfer, enabling effective learning of key features from large amounts of unlabeled data, thereby enhancing performance in scenarios with limited labeled and imbalanced data. Additionally, the combination of segment slicing and FFT captures both time-domain and frequency-domain information, further strengthening the feature extraction capabilities. Experimental results confirm that SSRL-TFD, through its pretext tasks in the first stage and shallow CNN architecture, successfully extracts intrinsic features from unlabeled signals, alleviating the negative impact of data imbalance. Comparisons with various methods demonstrate superior diagnostic performance and robustness. This approach offers a new solution for transformer fault diagnosis when labeled data is limited, utilizing voiceprint signals.

Adopting behavioural finance as a theory has emerged as an important field due to its opposition to finance principles that rely on rational decision-making and efficient market models. The research investigates behavioural finance elements that affect risk perception (RP) processes and financial decision-making (FDM) in equity market activities. Traditional finance depends on efficient markets with rational behaviour, but behavioural finance focuses on analyzing how psychological biases affect market participants. The Research Investigated the factors such as herding, disposition effect (DE), overconfidence, loss aversion (LA), and mental accounting (MA) that influence FDM with RP acting as a mediator. A total of 300 individual investors participated in the online survey, but researchers validated data from the responses of 270 participants. IBM SPSS version 26 employed SEM to evaluate the data collected. A Multiple Regression Analysis (MRA) evaluated how the behavioural finance factors impact FDM decision-making, while a Confirmatory Factor Analysis (CFA) tested the measurement model reliability. Research data shows that RP experiences meaningful changes due to herding behaviour and disposition effect, LA, and mental accounting, but overconfidence, along with over-optimism, directly affects FDM without changing RP levels. The link between RP and financial decisions is positive, and every behavioural variable affects investment choices indirectly through RP assessment. This demonstrates that behavioural biases affect investment choices, so investigators recommend that psychological factors become integral to the risk management framework creation. Investigator teams examine supplementary behavioural elements that enhance exposure to danger assessment while studying population and ethnic influences on investment actions.

Massive multiple-input multiple-output (MIMO) is an emerging technology that has the potential to significantly increase the spectral efficiency of 5G networks and beyond. On the other hand, multi-user beamforming's spectral efficiency is severely hindered by highly correlated user channels. Because of this, the base station must schedule the suitable user group in each time and frequency resource block in order to maximize spectrum efficiency while adhering to the user fairness constraints. Hence, the resource scheduling problem for huge MIMO systems with the optimal solution is considered as the NP-hard problem. Consequently, this research proposes the Reinforcement Learning-based Actor-Critic and Selective Search Entrapment-enabled Multifactor Channel Quality Index Precoder (RA-S2En-MQP) framework for effective user scheduling and resource allocation in the MIMO system. The proposed model utilizes the Reinforcement Learning-based Actor-Critic (RL-AC) model to prioritize the users for optimal scheduling, which enables flexibility and mitigates risks during resource allocation. Specifically, the Selective Search entrapment-enabled Multifactor Channel Quality Index Precoder technique (S2EnO-MQP) simplifies resource allocation and ensures quality data transmission over the network with the application of the S2EnO algorithm. The proposed S2EnO algorithm combines the selection, searching, and entrapment behaviors to find the optimal solution and improves the spectral efficiency. Experimental results demonstrate that the proposed RA-S2En-MQP model significantly outperforms other existing techniques attaining a high through put of 93.83Mbps, Normalized system utility of 0.95,andhigh Quality of Experience (QoE) of 4.36.

Wireless networks and communications have witnessed tremendous development and growth in recent periods and up until now, as there is a group of diverse networks such as the well-known wireless communication networks and others that are not linked to an infrastructure such as telephone networks, sensors and wireless networks, especially in important applications that work to send and receive important data and information in relatively unsafe environments, cybersecurity technologies pose an important challenge in protecting unsafe networks in terms of their impact on reducing crime. Detecting hacking in electronic networks and penetration testing. Therefore, these environments must be monitored and protected from hacking and malicious attacks. In this manuscript, a correspondence model is designed to discuss the algorithm in the environment of wireless communication systems and distributed computing by adopting the protocol data enhancement to the network using structured construction and diversity algorithm to improve the effectiveness of the intrusion detection system. Next, a multi-label convolutional neural network model is used to detect business transactions. An CNN was trained on the WSN-DS dataset using 5-Fold in CV technique with three hidden layers. The highest Precision values 0.951 of Grayhole attack for multi-classification.