Intrusion detection system (IDS) plays an essential role in computer networks protecting computing resources and data from outside attacks. Recent IDS faces challenges improving flexibility and efficiency of the IDS for unexpected and unpredictable attacks. Deep neural network (DNN) is considered popularly for complex systems to abstract features and learn as a machine learning technique. In this paper, we propose a deep learning approach for developing the efficient and flexible IDS using one-dimensional Convolutional Neural Network (1D-CNN). Two-dimensional CNN methods have shown remarkable performance in detecting objects of images in computer vision area. Meanwhile, the 1D-CNN can be used for supervised learning on time-series data. We establish a machine learning model based on the 1D-CNN by serializing Transmission Control Protocol/Internet Protocol (TCP/IP) packets in a predetermined time range as an invasion Internet traffic model for the IDS, where normal and abnormal network traffics are categorized and labeled for supervised learning in the 1D-CNN. We evaluated our model on UNSW_NB15 IDS dataset to show the effectiveness of our method. For comparison study in performance, machine learning-based Random Forest (RF) and Support Vector Machine (SVM) models in addition to the 1D-CNN with various network parameters and architecture are exploited. In each experiment, the models are run up to 200 epochs with a learning rate in 0.0001 on imbalanced and balanced data. 1D-CNN and its variant architectures have outperformed compared to the classical machine learning classifiers. This is mainly due to the reason that CNN has the capability to extract high-level feature representations that represent the abstract form of low-level feature sets of network traffic connections.

In the modern era of active network throughput and communication, the study of Intrusion Detection Systems (IDS) is a crucial role to ensure safe network resources and information from outside invasion. Recently, IDS has become a needful tool for improving flexibility and efficiency for unexpected and unpredictable invasions of the network. Deep learning (DL) is an essential and well-known tool to solve complex system problems and can learn rich features of enormous data. In this work, we aimed at a DL method for applying the effective and adaptive IDS by applying the architectures such as Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU). CNN models have already proved an incredible performance in computer vision tasks. Moreover, the CNN can be applied to time-sequence data. We implement the DL models such as CNN, LSTM, RNN, GRU by using sequential data in a prearranged time range as a malicious traffic record for developing the IDS. The benign and attack records of network activities are classified, and a label is given for the supervised-learning method. We applied our approaches to three different benchmark data sets which are UNSW NB15, KDDCup ’99, NSL-KDD to show the efficiency of DL approaches. For contrast in performance, we applied CNN and LSTM combination models with varied parameters and architectures. In each implementation, we trained the models until 100 epochs accompanied by a learning rate of 0.0001 for both balanced and imbalanced train data scenarios. The single CNN and combination of LSTM models have overcome compared to others. This is essentially because the CNN model can learn high-level features that characterize the abstract patterns from network traffic records data.

The timely and accurate detection of brain tumors is crucial for effective medical intervention, especially in resource-constrained settings. This study proposes a lightweight and efficient RetinaNet variant tailored for medical edge device deployment. The model reduces computational overhead while maintaining high detection accuracy by replacing the computationally intensive ResNet backbone with MobileNet and leveraging depthwise separable convolutions. The modified RetinaNet achieves an average precision (AP) of 32.1, surpassing state-of-the-art models in small tumor detection (AP_S: 14.3) and large tumor localization (AP_L: 49.7). Furthermore, the model significantly reduces computational costs, making real-time analysis feasible on low-power hardware. Clinical relevance is a key focus of this work. The proposed model addresses the diagnostic challenges of small, variable-sized tumors often overlooked by existing methods. Its lightweight architecture enables accurate and timely tumor localization on portable devices, bridging the gap in diagnostic accessibility for underserved regions. Extensive experiments on the BRATS dataset demonstrate the model robustness across tumor sizes and configurations, with confidence scores consistently exceeding 81%. This advancement holds the potential for improving early tumor detection, particularly in remote areas lacking advanced medical infrastructure, thereby contributing to better patient outcomes and broader accessibility to AI-driven diagnostic tools.

Forest fires pose an escalating global threat, severely impacting ecosystems, public health, and economies. Timely detection, especially during early stages, is critical for effective intervention. In this study, we propose a novel deep learning-based framework that augments the YOLOv4 object detection architecture with a modified EfficientNetV2 backbone and Efficient Channel Attention (ECA) modules. The backbone substitution leverages compound scaling and Fused-MBConv/MBConv blocks to improve representational efficiency, while the lightweight ECA blocks enhance inter-channel dependency modeling without incurring significant computational overhead. Additionally, we introduce a domain-specific preprocessing pipeline employing Canny edge detection, CLAHE + Jet transformation, and pseudo-NDVI mapping to enhance fire-specific visual cues in complex natural environments. Experimental evaluation on a hybrid dataset of forest fire images and video frames demonstrates substantial performance gains over baseline YOLOv4 and contemporary YOLO variants (YOLOv5–YOLOv9), with the proposed model achieving 97.01% precision, 95.14% recall, 93.13% mAP, and 92.78% F1-score. Furthermore, our model outperforms fourteen state-of-the-art approaches across standard metrics, confirming its efficacy, generalizability, and suitability for real-time deployment in UAV-based and edge computing platforms. These findings highlight the synergy between architectural optimization and domain-aware preprocessing for high-accuracy, low-latency wildfire detection systems.

The increasing frequency and severity of agricultural fires pose significant threats to food security, economic stability, and environmental sustainability. Traditional fire-detection methods, relying on satellite imagery and ground-based sensors, often suffer from delayed response times and high false-positive rates, limiting their effectiveness in mitigating fire-related damages. In this study, we propose an advanced deep learning-based fire-detection framework that integrates the Single-Shot MultiBox Detector (SSD) with the computationally efficient MobileNetV2 architecture. This integration enhances real-time fire- and smoke-detection capabilities while maintaining a lightweight and deployable model suitable for Unmanned Aerial Vehicle (UAV)-based agricultural monitoring. The proposed model was trained and evaluated on a custom dataset comprising diverse fire scenarios, including various environmental conditions and fire intensities. Comprehensive experiments and comparative analyses against state-of-the-art object-detection models, such as You Only Look Once (YOLO), Faster Region-based Convolutional Neural Network (Faster R-CNN), and SSD-based variants, demonstrated the superior performance of our model. The results indicate that our approach achieves a mean Average Precision (mAP) of 97.7%, significantly surpassing conventional models while maintaining a detection speed of 45 frames per second (fps) and requiring only 5.0 GFLOPs of computational power. These characteristics make it particularly suitable for deployment in edge-computing environments, such as UAVs and remote agricultural monitoring systems.

Background/Objectives: The early and accurate detection of Coronary Artery Disease (CAD) is crucial for preventing life-threatening complications, particularly among athletes engaged in high-intensity endurance sports. This demographic faces unique cardiovascular risks, as prolonged and intense physical exertion can exacerbate underlying CAD conditions. Studies indicate that while athletes typically exhibit enhanced cardiovascular health, this demographic is not immune to Coronary Artery Disease (CAD) risks. Research has shown that approximately 1–2% of competitive athletes suffer from CAD-related complications, with sudden cardiac arrest being the leading cause of mortality in athletes over 35 years old. High-intensity endurance sports can exacerbate underlying CAD conditions due to the prolonged physical stress placed on the cardiovascular system, making early detection crucial. This study aimed to develop and evaluate a lightweight deep learning model for CAD detection tailored to the unique challenges of diagnosing athletes. Methods: This study introduces a lightweight deep learning model specifically designed for CAD detection in athletes. By integrating ResNet-inspired residual connections into the VGG16 architecture, the model achieves a balance of high diagnostic accuracy and computational efficiency. By incorporating ResNet-inspired residual connections into the VGG16 architecture, the model enhances gradient flow, mitigates vanishing gradient issues, and improves feature extraction of subtle morphological variations in coronary lesions. Its lightweight design, with only 1.2 million parameters and 3.5 GFLOPs, ensures suitability for real-time deployment in resource-constrained clinical environments, such as sports clinics and mobile diagnostic systems, where rapid and efficient diagnostics are essential for high-risk populations. Results: The proposed model achieved superior performance compared to state-of-the-art architectures, with an accuracy of 90.3%, recall of 89%, precision of 90%, and an AUC-ROC of 0.912. These metrics highlight its robustness in detecting and classifying CAD in athletes. The model lightweight architecture, with only 1.2 million parameters and 3.5 GFLOPs, ensures computational efficiency and suitability for real-time clinical applications, particularly in resource-constrained settings. Conclusions: This study demonstrates the potential of a lightweight, deep learning-based diagnostic tool for CAD detection in athletes, achieving a balance of high diagnostic accuracy and computational efficiency. Future work should focus on integrating broader dataset validations and enhancing model explainability to improve adoption in real-world clinical scenarios.