The rise of low-cost drones, or Unmanned Aerial Vehicles (UAVs), has transformed industries like agriculture, disaster response, and infrastructure inspection. However, this increase poses considerable issues for safety, security, and airspace management. To address these challenges, radiofrequency (RF)-based approaches are emerging as potential options for real-time UAV identification and classification since they are non-intrusive and compatible with existing systems. This research offers a unique Artificial Neural Network (ANN) model for UAV classification that includes efficient preprocessing and feature extraction approaches. The suggested architecture reduces feature dimensionality using Principal Component Analysis (PCA) and improves classification performance with statistical and frequency-domain characteristics like Root Mean Square (RMS) and Zero-Crossing Rate (ZCR). Experimental evaluations of the DroneRF dataset show that the proposed ANN is superior, with classification accuracies of 99.46%, 98.52%, and 83.40% for 2-class, 4-class, and 10-class tasks, respectively. This work is a big step toward robust, real-time drone detection and classification systems.

Ad hoc protocols like AODV, DSDV, and OLSR have been studied in healthcare, but their application to CGM networks with real-time integrated Machine Learning (ML) presents unique challenges due to distinct traffic patterns and node configurations. This paper explores how CGM, ML, and communication protocols jointly enable continuous monitoring and timely intervention, where transmission reliability directly affects ML performance in anomaly detection. Using NS3, we evaluate AODV, DSDV, and OLSR based on throughput, delay, and packet delivery ratio (PDR) under varying network sizes and data rates. Results show AODV offers minimal delay and packet loss, enhancing ML accuracy, while DSDV and OLSR perform better in dense networks. We also identify challenges related to scalability and data security, highlighting directions for future optimization of CGM-ML systems through hybrid and energyefficient protocols.

Heart disease continues to be the foremost cause of mortality across both developed and developing nations, posing a critical public health challenge. This life-threatening condition often necessitates urgent hospitalization and rapid diagnosis in emergency departments to avert fatal outcomes. Such outcomes can arise from a diverse range of complications associated with heart disease, including cardiogenic shock, pulmonary edema, myocardial rupture, the progression of congestive heart failure, thromboembolism, asystole, and ventricular fibrillation. Although numerous studies have focused on predicting heart disease, relatively few have addressed the complexity of multi-label classification for this issue. In this paper, we propose an innovative framework that integrates a K-Nearest Neighbors-based imputation technique with a Gradient Boosting algorithm to classify multiple heart disease complications. The experimental findings reveal that our approach achieves superior accuracy compared to existing methods. Additionally, we present a comprehensive comparative analysis of the proposed data pre-processing methodology by applying various machine learning algorithms. Moreover, we provide a detailed comparison between our multi-label classification strategy and previously established approaches. A diverse set of evaluation metrics, including accuracy, precision, recall, F1-score, and Hamming loss, is utilized to demonstrate the robustness and effectiveness of the proposed framework.

The goal of our research is to develop a model that achieves higher accuracy in predicting stock price movements, enabling investors to make informed decisions on buying or selling stocks to maximize their benefits. We propose a novel stock price prediction framework that integrates deep learning techniques and sentiment analysis. To achieve more convincing results, we incorporated sentiment data derived from newspaper articles. Using FinBERT (Financial-BERT), we analyzed the sentiments embedded in these articles and incorporated them into our LSTM model. Our model achieved the highest testing accuracy of 65.2 % which is higher than the research results we found. These results highlight the significant role of sentiment in influencing stock price movements and demonstrate the performance of our LSTM-based framework.

Continuous Glucose Monitoring (CGM) systems have become essential for real-time diabetes management; however, ensuring reliable, energy-efficient, and low-latency communication under dynamic patient mobility remains a major challenge for intelligent healthcare networks. This paper proposes a cross-layer energy- and mobility-aware communication framework for CGM systems that integrates adaptive routing analysis, Machine Learning (ML)-based glucose prediction, and hardware acceleration within a unified architecture. The proposed framework evaluates the impact of network behavior on ML accuracy by jointly analyzing throughput, delay, Packet Delivery Ratio (PDR), energy consumption, and mobility adaptation in static and dynamic healthcare scenarios. In addition, the framework is implemented on a Nexys A7-100T FPGA platform to validate real-time feasibility through a hardware-integrated routing and ML inference architecture optimized for edge healthcare applications. Experimental results obtained using NS-3 simulation and FPGA-based validation demonstrate that the proposed framework achieves up to 25% lower energy consumption, improved communication reliability, reduced latency, and enhanced ML prediction accuracy under mobile conditions. The hardware implementation further demonstrates efficient resource utilization and low-latency processing suitable for wearable and edge-based medical devices. The results show interdependence between communication reliability and ML performance, highlighting the importance of energy- and mobility-aware cross-layer optimization for scalable, reliable, and intelligent CGM healthcare systems.