Search Results (92)

Encrypted network traffic classification remains a critical component in network security monitoring. However, existing approaches face two fundamental limitations: (1) conventional methods rely on manual feature engineering and are inadequate in handling high-dimensional features; and (2) they lack the capability to capture dynamic temporal patterns. This paper introduces TransECA-Net, a novel hybrid deep learning architecture that addresses these limitations through two key innovations. First, we integrate ECA-Net modules with CNN architecture to enable automated feature extraction and efficient dimension reduction via channel selection. Second, we incorporate a Transformer encoder to model global temporal dependencies through multi-head self-attention, supplemented by residual connections for optimal gradient flow. Extensive experiments on the ISCX VPN-nonVPN dataset demonstrate the superiority of our approach. TransECA-Net achieved an average accuracy of 98.25% in classifying 12 types of encrypted traffic, outperforming classical baseline models such as 1D-CNN, CNN + LSTM, and TFE-GNN by 6.2–14.8%. Additionally, it demonstrated a 37.44–48.84% improvement in convergence speed during the training process. Our proposed framework presents a new paradigm for encrypted traffic feature disentanglement and representation learning. This paradigm enables cybersecurity systems to achieve fine-grained service identification of encrypted traffic (e.g., 98.9% accuracy in VPN traffic detection) and real-time responsiveness (48.8% faster than conventional methods), providing technical support for combating emerging cybercrimes such as monitoring illegal transactions on darknet networks and contributing significantly to adaptive network security monitoring systems. Full article

This paper presents a traffic sign recognition (TSR) system based on the deep convolutional neural network (CNN) architecture, which proves to be extremely accurate in recognizing traffic signs under challenging conditions such as bad weather, low-resolution images, and various environmental-impact factors. The proposed CNN is compared with other architectures, including GoogLeNet, AlexNet, DarkNet-53, ResNet-34, VGG-16, and MicronNet-BF. Experimental results confirm that the proposed CNN significantly improves recognition accuracy compared to existing models. In order to make our model interpretable, we utilize explainable AI (XAI) approaches, specifically Gradient-weighted Class Activation Mapping (Grad-CAM), that can give insight into how the system comes to its decision. The evaluation of the Tsinghua-Tencent 100K (TT100K) traffic sign dataset showed that the proposed method significantly outperformed existing state-of-the-art methods. Additionally, we evaluated our model on the German Traffic Sign Recognition Benchmark (GTSRB) dataset to ensure generalization, demonstrating its ability to perform well in diverse traffic sign conditions. Design issues such as noise, contrast, blurring, and zoom effects were added to enhance performance in real applications. These verified results indicate both the strength and reliability of the CNN architecture proposed for TSR tasks and that it is a good option for integration into intelligent transportation systems (ITSs). Full article

This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in Agaricus bisporus, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices. Full article

Background: The morphological type of the acromion may play a role in the etiopathogenesis of various pathologies, such as shoulder impingement syndrome and rotator cuff disorders. Therefore, it is important to determine the acromion’s morphological types accurately and quickly. In this study, it was aimed to detect the acromion shape, which is one of the etiological causes of chronic shoulder disorders that may cause a decrease in work capacity and quality of life, on shoulder MR images by developing a new model for image retrieval in Content-Based Image Retrieval (CBIR) systems. Methods: Image retrieval was performed in CBIR systems using Convolutional Neural Network (CNN) architectures and textural-based methods as the basis. Feature maps of the images were extracted to measure image similarities in the developed CBIR system. For feature map extraction, feature extraction was performed with Histogram of Gradient (HOG), Local Binary Pattern (LBP), Darknet53, and Densenet201 architectures, and the Minimum Redundancy Maximum Relevance (mRMR) feature selection method was used for feature selection. The feature maps obtained after the dimensionality reduction process were combined. The Euclidean distance and Peak Signal-to-Noise Ratio (PSNR) were used as similarity measurement methods. Image retrieval was performed using features obtained from CNN architectures and textural-based models to compare the performance of the proposed method. Results: The highest Average Precision (AP) value was reached in the PSNR similarity measurement method with 0.76 in the proposed model. Conclusions: The proposed model is promising for accurately and rapidly determining morphological types of the acromion, thus aiding in the diagnosis and understanding of chronic shoulder disorders. Full article

An analytical model can quickly predict performance and energy efficiency based on information about the neural network model and neural accelerator architecture, making it ideal for rapid pre-synthesis design space exploration. This paper proposes a new analytical model specifically targeted for convolutional neural networks used in always-on applications. To validate the proposed model, the performance and energy efficiency estimated by the model were compared with actual hardware and post-synthesis gate-level simulations of hardware synthesized with a state-of-the-art electronic design automation (EDA) synthesis tool. Comparisons with hardware created for the Eyeriss neural accelerator showed average execution time and energy consumption error rates of 3.33% and 13.54%, respectively. Comparisons with hardware synthesis results showed an error of 3.18% to 9.44% for two example neural accelerator configurations used to execute MobileNet, EfficientNet, and DarkNet neural network models. Finally, the utility of the proposed model was demonstrated by using it to evaluate the effects of different channel sizes, pruning rates, and batch sizes in several neural network designs for always-on vision, text, and audio processing. Full article

The objective of this study was to develop an artificial intelligence (AI)-driven model for the detection of helmet usage among workers in tractor and agricultural machinery factories with the aim of enhancing occupational safety. A transfer learning approach was employed, utilizing nine pre-trained neural networks for the extraction of deep features. The following neural networks were employed: MobileNetV2, ResNet50, DarkNet53, AlexNet, ShuffleNet, DenseNet201, InceptionV3, Inception-ResNetV2, and GoogLeNet. Subsequently, the extracted features were subjected to iterative neighborhood component analysis (INCA) for feature selection, after which they were classified using the k-nearest neighbor (kNN) algorithm. The classification outputs of all networks were combined through iterative majority voting (IMV) to achieve optimal results. To evaluate the model, an image dataset comprising 662 images of individuals wearing helmets and 722 images of individuals without helmets sourced from the internet was constructed. The proposed model achieved an accuracy of 90.39%, with DenseNet201 producing the most accurate results. This AI-driven helmet detection model demonstrates significant potential in improving occupational safety by assisting safety officers, especially in confined environments, reducing human error, and enhancing efficiency. Full article

Background/Objectives: This paper presents a Residual Neural Network (ResNet) based framework tailored for structured traffic accident data, aiming to improve accident severity prediction. The proposed model leverages residual learning to effectively model intricate relationships between numerical and categorical variables, resulting in a notable increase in prediction accuracy. Methods: A comparative analysis was performed with other Deep Learning (DL) architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Darknet, and Extreme Inception (Xception), showing superior performance of the proposed Resnet. Key factors influencing accident severity were identified, with Shapley Additive Explanations (SHAP) values helping to address the need for transparent and explainable Artificial Intelligence (AI) in critical decision-making areas. Results: The generalizability of the ResNet model was assessed by training it, initially, on a UK road accidents dataset and validating it on a distinct dataset from India. The model consistently demonstrated high predictive accuracy, underscoring its robustness across diverse contexts, despite regional differences. Conclusions: These results suggest that the adapted ResNet model could significantly enhance traffic safety evaluations and contribute to the formulation of more effective traffic management strategies. Full article

This paper presents a novel methodology for plant disease detection using YOLOv8 (You Only Look Once version 8), a state-of-the-art object detection model designed for real-time image classification and recognition tasks. The proposed approach involves training a custom YOLOv8 model to detect and classify various plant conditions accurately. The model was evaluated using a testing subset to measure its performance in detecting different plant diseases. To ensure the model’s robustness and generalizability beyond the training dataset, it was further tested on a set of unseen images sourced from Google Images. This additional testing aimed to assess the model’s effectiveness in real-world scenarios, where it might encounter new data. The evaluation results were auspicious, demonstrating the model’s capability to classify plant conditions, such as diseases, with high accuracy. Moreover, the use of YOLOv8 offers significant improvements in speed and precision, making it suitable for real-time plant disease monitoring applications. The findings highlight the potential of this methodology for broader agricultural applications, including early disease detection and prevention. Full article

Over the years, research in the field of cultural heritage preservation and document analysis has exponentially grown. In this study, we propose an advanced approach for non-destructive estimation of paper fibers using macro images. Expanding on studies that implemented EfficientNet-B0, we explore the effectiveness of six other deep learning networks, including DenseNet-201, DarkNet-53, Inception-v3, Xception, Inception-ResNet-v2, and NASNet-Large, in conjunction with enlarged patch sizes. We experimentally classified three types of paper fibers, namely, kozo, mitsumata, and gampi. During the experiments, patch sizes of 500, 750, and 1000 pixels were evaluated and their impact on classification accuracy was analyzed. The experiments demonstrated that Inception-ResNet-v2 with 1000-pixel patches achieved the highest patch classification accuracy of 82.7%, whereas Xception with 750-pixel patches exhibited the best macro-image-based fiber estimation performance at 84.9%. Additionally, we assessed the efficacy of the method for images containing text, observing consistent improvements in the case of larger patch sizes. However, limitations exist in background patch availability for text-heavy images. This comprehensive evaluation of network architectures and patch sizes can significantly advance the field of non-destructive paper analysis, offering valuable insights into future developments in historical document examination and conservation science. Full article

This paper presents an object detection model for logistics-centered objects deployed and used by autonomous warehouse robots. Using the Robot Operating System (ROS) infrastructure, our work leverages the set of provided models and a dataset to create a complex system that can meet the guidelines of the Autonomous Mobile Robots (AMRs). We describe an innovative method, and the primary emphasis is placed on the Logistics Objects in Context (LOCO) dataset. The importance is on training the model and determining optimal performance and accuracy for the implemented object detection task. Using neural networks as pattern recognition tools, we took advantage of the one-stage detection architecture YOLO that prioritizes speed and accuracy. Focusing on a lightweight variant of this architecture, YOLOv4 Tiny, we were able to optimize for deployment on resource-constrained edge devices without compromising detection accuracy, resulting in a significant performance boost over previous benchmarks. The YOLOv4 Tiny model was implemented with Darknet, especially for its adaptability to ROS Melodic framework and capability to fit edge devices. Notably, our network achieved a mean average precision (mAP) of 46% and an intersection over union (IoU) of 50%, surpassing the baseline metrics established by the initial LOCO study. These results demonstrate a significant improvement in performance and accuracy for real-world logistics applications of AMRs. Our contribution lies in providing valuable insights into the capabilities of AMRs within the logistics environment, thus paving the way for further advancements in this field. Full article

The Dark Web is a subset of the Deep Web, requiring special browsers, the Dark Net refers to encrypted networks, the Deep Web encompasses non-indexed online content, and darknet includes unused IP address networks. The Dark Net has become a hotbed of cybercrime, with individuals and groups using the anonymity and encryption provided by the network to carry out a range of criminal activities. One of the most concerning trends in recent years has been the weaponization of cybercrimes, as criminals use their technical skills to create tools and techniques that can be used to launch attacks against individuals, businesses, and governments. This paper examines the weaponization of cybercrimes on the Dark Net, focusing on the question of detection and application. This paper uses a Systematic Literature Review (SLR) method to appraise the Dark Web, examine the crimes and their consequences and identify future measures to reduce crime threats. Data from 88 relevant articles from 2011 to 2023 were extracted and synthesized, along with the latest data from 2024 to answer research questions, providing comprehensive knowledge on growing crimes; assessing social, economic, and ethical impacts; and analyzing established techniques and methods to locate and apprehend criminals. Full article

Image processing with artificial intelligence has shown significant promise in various medical imaging applications. The present study aims to evaluate the performance of 16 different convolutional neural networks (CNNs) in predicting age and gender from panoramic radiographs in children and young adults. The networks tested included DarkNet-19, DarkNet-53, Inception-ResNet-v2, VGG-19, DenseNet-201, ResNet-50, GoogLeNet, VGG-16, SqueezeNet, ResNet-101, ResNet-18, ShuffleNet, MobileNet-v2, NasNet-Mobile, AlexNet, and Xception. These networks were trained on a dataset of 7336 radiographs from individuals aged between 5 and 21. Age and gender estimation accuracy and mean absolute age prediction errors were evaluated on 340 radiographs. Statistical analyses were conducted using Shapiro–Wilk, one-way ANOVA, and Tukey tests (p < 0.05). The gender prediction accuracy and the mean absolute age prediction error were, respectively, 87.94% and 0.582 for DarkNet-53, 86.18% and 0.427 for DarkNet-19, 84.71% and 0.703 for GoogLeNet, 81.76% and 0.756 for DenseNet-201, 81.76% and 1.115 for ResNet-18, 80.88% and 0.650 for VGG-19, 79.41% and 0.988 for SqueezeNet, 79.12% and 0.682 for Inception-Resnet-v2, 78.24% and 0.747 for ResNet-50, 77.35% and 1.047 for VGG-16, 76.47% and 1.109 for Xception, 75.88% and 0.977 for ResNet-101, 73.24% and 0.894 for ShuffleNet, 72.35% and 1.206 for AlexNet, 71.18% and 1.094 for NasNet-Mobile, and 62.94% and 1.327 for MobileNet-v2. No statistical difference in age prediction performance was found between DarkNet-19 and DarkNet-53, which demonstrated the most successful age estimation results. Despite these promising results, all tested CNNs performed below 90% accuracy and were not deemed suitable for clinical use. Future studies should continue with more-advanced networks and larger datasets. Full article

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the “vanishing gradient” problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the “dying relu” problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters. Full article

This study focuses on training a custom, small Convolutional Neural Network (CNN) using a limited dataset through data augmentation that is aimed at developing weights for subsequent fine-tuning on specific defects, namely improperly polished aluminum surfaces. The objective is to adapt the network for use in computationally restricted environments. The methodology involves using two computers—a low-performance PC for network creation and initial testing and a more powerful PC for network training using the Darknet framework—after which the network is transferred back to the initial low-performance PC. The results demonstrate that the custom lightweight network suited for a low-performance PC effectively performs object detection under the described conditions. These findings suggest that using tailored lightweight networks for recognizing specific types of defects is feasible and warrants further investigation to enhance the industrial defect detection processes in limited computational settings. This approach highlights the potential for deploying AI-driven quality control in environments with constrained hardware capabilities. Full article

The modern distribution network system is gradually becoming more complex and diverse, and traditional fault location methods have difficulty in quickly and accurately locating the fault location after a single-phase ground fault occurs. Therefore, this study proposes a new solution based on the Markov transfer field and deep learning to predict the fault location, which can accurately predict the location of a single-phase ground fault in the distribution network. First, a new phase-mode transformation matrix is used to take the fault current of the distribution network as the modulus 1 component, avoiding complex calculations in the complex field; then, the extracted modulus 1 component of the current is transformed into a Markov transfer field and converted into an image using pseudo-color coding, thereby fully exploiting the fault signal characteristics; finally, the Darknet-19 network is used to automatically extract fault features and predict the distance of the fault occurrence. Through simulations on existing models and training and testing with a large amount of data, the experimental results show that this method has good stability, high accuracy, and strong anti-interference ability. This solution can effectively predict the distance of ground faults in distribution networks. Full article