Human gesture image recognition is the process of identifying, deciphering, and classifying human gestures in images or video frames using computer vision algorithms. These gestures can vary from the simplest hand motions, body positions, and facial emotions to complicated gestures. Two significant problems affecting the performance of human gesture picture recognition methods are ambiguity and invariance. Ambiguity occurs when gestures have the same shape but different orientations, while invariance guarantees that gestures are correctly classified even when scale, lighting, or orientation varies. To overcome this issue, hand-crafted features can be combined with deep learning to greatly improve the performance of hand gesture image recognition models. This combination improves the model’s overall accuracy and dependability in identifying a variety of hand movements by enhancing its capacity to record both shape and texture properties. Thus, in this study, we propose a hand gesture recognition method that combines Reset50 model feature extraction with the Tamura texture descriptor and uses the adaptability of GAM to represent intricate interactions between the features. Experiments were carried out on publicly available datasets containing images of American Sign Language (ASL) gestures. As Tamura-ResNet50-OptimizedGAM achieved the highest accuracy rate in the ASL datasets, it is believed to be the best option for human gesture image recognition. According to the experimental results, the accuracy rate was 96%, which is higher than the total accuracy of the state-of-the-art techniques currently in use.

The increasing use of blockchain smart contracts has introduced new security challenges, as small coding errors can lead to major financial losses. While rule-based static analyzers remain the most common detection tools, their limited adaptability often results in false positives and outdated vulnerability patterns. This study presents a comprehensive comparative analysis of machine learning (ML) and deep learning (DL) methods for smart contract vulnerability detection using the BCCC-SCsVuls-2024 benchmark dataset. Six models (Random Forest, k-Nearest Neighbors, Simple and Deep Multilayer Perceptron, and Simple and Deep one-dimensional Convolutional Neural Networks) were evaluated under a unified experimental framework combining RobustScaler normalization and Principal Component Analysis (PCA) for dimensionality reduction. Our experimental results from a five-fold cross-validation show that the Random Forest classifier achieved the best overall performance with an accuracy of 89.44% and an F1-score of 93.20%, outperforming both traditional and neural models in stability and generalization. PCA-based feature analysis revealed that opcode-level features, particularly stack and memory manipulation instructions (PUSH, DUP, SWAP, and RETURNDATASIZE), were the most influential in defining contract behavior.

Sentiment analysis is a critical tool for understanding public opinion, especially in regions like Iraq where social media serves as a primary platform for expression. However, the complexities of the Iraqi Arabic dialect, including informal structures, slang, and spelling variations, pose significant challenges for traditional Natural Language Processing (NLP) models. This study addresses these challenges by developing a deep learning-based sentiment analysis model tailored specifically for Iraqi Arabic. Utilizing a dataset of 2,000 annotated tweets, we implement a Convolutional Neural Network (CNN) architecture optimized for binary sentiment classification. The model achieves an accuracy of 87.5% on the test set, demonstrating its effectiveness in capturing sentiment-bearing features in Iraqi dialect text. Key contributions include the creation of a labeled dataset for Iraqi Arabic and the development of a robust preprocessing and modeling pipeline. The findings highlight the potential of deep learning techniques for dialect-specific sentiment analysis, with applications in policymaking, business intelligence, and social media monitoring in Iraq and other Arabic-speaking regions.

To address the challenges of managing heterogeneous wireless environments (HWNs), which integrate diverse access networks like 5G, LTE, and Wi-Fi, this research introduces an AI-powered digital twin framework. The framework creates real-time virtual replicas of HWNs to enable dynamic monitoring, simulation, and optimization. Leveraging advanced AI techniques, including reinforcement learning, predictive analytics, and anomaly detection, the framework achieves significant improvements in network performance. Simulations demonstrate a 25% reduction in latency, a 20% improvement in throughput, and a 20% decrease in energy consumption compared to state-of-the-art approaches. Additionally, user-centric Quality of Service (QoS) and Quality of Experience (QoE) models ensure enhanced user satisfaction by tailoring network performance to evolving demands. The authors validated the framework's scalability and adaptability across diverse scenarios, such as dynamic handover management, energy-efficient resource allocation, and fault recovery. These results highlight the potential of the proposed framework to revolutionize network management in next-generation networks, such as 6G. Concluding, this research underscores the framework’s ability to provide real-time optimization, significant energy savings, and improved user satisfaction while addressing challenges like computational overhead. Future work includes integrating renewable energy sources, strengthening cybersecurity features, and expanding capabilities to support emerging technologies like semantic communication.