Search Results (3,472)

Knowledge distillation (KD) techniques aim to transfer knowledge from complex teacher neural networks to simpler student networks. In this study, we propose a novel knowledge distillation method called Multiloss Joint Gradient Control Knowledge Distillation (MJKD), which functions by effectively combining feature- and logit-based knowledge distillation methods with gradient control. The proposed knowledge distillation method discretely considers the gradients of the task loss (cross-entropy loss), feature distillation loss, and logit distillation loss. The experimental results suggest that logits may contain more information and should, consequently, be assigned greater weight during the gradient update process in this work. The empirical findings on the CIFAR-100 and Tiny-ImageNet datasets indicate that MJKD generally outperforms traditional knowledge distillation methods, significantly enhancing the generalization ability and classification accuracy of student networks. For instance, MJKD achieves a 63.53% accuracy on Tiny-ImageNet for the ResNet18 MobileNetV2 pair. Furthermore, we present visualizations and analyses to explore its potential working mechanisms. Full article

In recent years, unmanned aerial vehicles (UAVs) vision systems based on deep neural networks (DNNs) have made remarkable advancements, demonstrating impressive performance. However, due to the inherent characteristics of DNNs, these systems have become increasingly vulnerable to adversarial attacks. Traditional black-box attack methods typically require a large number of queries to generate adversarial samples successfully. In this paper, we propose a novel adversarial attack technique designed to achieve efficient black-box attacks with a minimal number of queries. We define a perturbation generator that first decomposes the image into four frequency bands using wavelet decomposition and then searches for adversarial perturbations across these bands by minimizing a weighted loss function on a set of fixed surrogate models. For the target victim model, the perturbation images generated by the perturbation generator are used to query and update the weights in the loss function, as well as the weights for different frequency bands. Experimental results show that, compared to state-of-the-art methods on various image classifiers trained on ImageNet (such as VGG-19, DenseNet-121, and ResNext-50), our method achieves a success rate over 98% for targeted attacks and nearly a 100% success rate for non-targeted attacks with only 1–2 queries per image. Full article

Background: The global healthcare system faces challenges in diagnosing and managing lung and colon cancers, which are significant health burdens. Traditional diagnostic methods are inefficient and prone to errors, while data privacy and security concerns persist. Objective: This study aims to develop a secure and transparent framework for remote consultation and classification of lung and colon cancer, leveraging blockchain technology and Microsoft Azure cloud services. Dataset and Features: The framework utilizes the LC25000 dataset, containing 25,000 histopathological images, for training and evaluating advanced machine learning models. Key features include secure data upload, anonymization, encryption, and controlled access via blockchain and Azure services. Methods: The proposed framework integrates Microsoft Azure’s cloud services with a permissioned blockchain network. Patients upload CT scans through a mobile app, which are then preprocessed, anonymized, and stored securely in Azure Blob Storage. Blockchain smart contracts manage data access, ensuring only authorized specialists can retrieve and analyze the scans. Azure Machine Learning is used to train and deploy state-of-the-art machine learning models for cancer classification. Evaluation Metrics: The framework’s performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, demonstrating the effectiveness of the integrated approach in enhancing diagnostic accuracy and data security. Results: The proposed framework achieves an impressive accuracy of 100% for lung and colon cancer classification using DenseNet, ResNet50, and MobileNet models with different split ratios (70–30, 80–20, 90–10). The F1-score and k-fold cross-validation accuracy (5-fold and 10-fold) also demonstrate exceptional performance, with values exceeding 99.9%. Real-time notifications and secure remote consultations enhance the efficiency and transparency of the diagnostic process, contributing to better patient outcomes and streamlined cancer care management. Full article

As malware samples grow in complexity and employ advanced evasion techniques, traditional detection methods are insufficient for accurately classifying large volumes of sophisticated malware variants. To address this issue, image-based malware classification techniques leveraging machine learning algorithms have been developed as a more optimal solution to this challenge. However, accurately classifying content distribution-based features with unique pixel intensities from grayscale images remains a challenge. This paper proposes an enhanced image-based malware classification system using convolutional neural networks (CNNs) using ResNet-152 and vision transformer (ViT). The two architectures are then compared to determine their classification abilities. A total of 6137 benign files and 9861 malicious executables are converted from text files to unsigned integers and then to images. The ViT examined unsigned integers as pixel values, while ResNet-152 converted the pixel values into floating points for classification. The result of the experiments demonstrates a high-performance accuracy of 99.62% with effective hyperparameters of 10-fold cross-validation. The findings indicate that the proposed model is capable of being implemented in dynamic and complex malware environments, achieving a practical computational efficiency of 47.2 s for the identification and classification of new malware samples. Full article

Lumpy Skin Disease (LSD) poses a significant threat to agricultural economies, particularly in livestock-dependent countries like India, due to its high transmission rate leading to severe morbidity and mortality among cattle. This underscores the urgent need for early and accurate detection to effectively manage and mitigate outbreaks. Leveraging advancements in computer vision and artificial intelligence, our research develops an automated system for LSD detection in cattle using deep learning techniques. We utilized two publicly available datasets comprising images of healthy cattle and those with LSD, including additional images of cattle affected by other diseases to enhance specificity and ensure the model detects LSD specifically rather than general illness signs. Our methodology involved preprocessing the images, applying data augmentation, and balancing the datasets to improve model generalizability. We evaluated over ten pretrained deep learning models—Xception, VGG16, VGG19, ResNet152V2, InceptionV3, MobileNetV2, DenseNet201, NASNetMobile, NASNetLarge, and EfficientNetV2S—using transfer learning. The models were rigorously trained and tested under diverse conditions, with performance assessed using metrics such as accuracy, sensitivity, specificity, precision, F1-score, and AUC-ROC. Notably, VGG16 and MobileNetV2 emerged as the most effective, achieving accuracies of 96.07% and 96.39%, sensitivities of 93.75% and 98.57%, and specificities of 97.14% and 94.59%, respectively. Our study critically highlights the strengths and limitations of each model, demonstrating that while high accuracy is achievable, sensitivity and specificity are crucial for clinical applicability. By meticulously detailing the performance characteristics and including images of cattle with other diseases, we ensured the robustness and reliability of the models. This comprehensive comparative analysis enriches our understanding of deep learning applications in veterinary diagnostics and makes a substantial contribution to the field of automated disease recognition in livestock farming. Our findings suggest that adopting such AI-driven diagnostic tools can enhance the early detection and control of LSD, ultimately benefiting animal health and the agricultural economy. Full article

Students’ behavioral and emotional engagement in the classroom environment may reflect the students’ learning experience and subsequent educational outcomes. The existing research has overlooked the measurement of behavioral and emotional engagement in an offline classroom environment with more students, and it has not measured the student engagement level in an objective sense. This work aims to address the limitations of the existing research and presents an effective approach to measure students’ behavioral and emotional engagement and the student engagement level in an offline classroom environment during a lecture. More precisely, video data of 100 students during lectures in different offline classes were recorded and pre-processed to extract frames with individual students. For classification, convolutional-neural-network- and transfer-learning-based models including ResNet50, VGG16, and Inception V3 were trained, validated, and tested. First, behavioral engagement was computed using salient features, for which the self-trained CNN classifier outperformed with a 97%, 91%, and 83% training, validation, and testing accuracy, respectively. Subsequently, the emotional engagement of the behaviorally engaged students was computed, for which the ResNet50 model surpassed the others with a 95%, 90%, and 82% training, validation, and testing accuracy, respectively. Finally, a novel student engagement level metric is proposed that incorporates behavioral and emotional engagement. The proposed approach may provide support for improving students’ learning in an offline classroom environment and devising effective pedagogical policies. Full article

Underwater surveillance is an imminent and fascinating exploratory domain, particularly in monitoring aquatic ecosystems. This field offers valuable insights into underwater behavior and activities, which have broad applications across various domains. Specifically, underwater surveillance involves detecting and tracking moving objects within aquatic environments. However, the complex properties of water make object detection a challenging task. Background subtraction is a commonly employed technique for detecting local changes in video scenes by segmenting images into the background and foreground to isolate the object of interest. Within this context, we propose an innovative dual-stream encoder–decoder framework based on the VGG-16 and ResNet-50 models for detecting moving objects in underwater frames. The network includes a feature fusion module that effectively extracts multiple-level features. Using a limited set of images and performing training in an end-to-end manner, the proposed framework yields accurate results without post-processing. The efficacy of the proposed technique is confirmed through visual and quantitative comparisons with eight cutting-edge methods using two standard databases. The first one employed in our experiments is the Underwater Change Detection Dataset, which includes five challenges, each challenge comprising approximately 1000 frames. The categories in this dataset were recorded under various underwater conditions. The second dataset used for practical analysis is the Fish4Knowledge dataset, where we considered five challenges. Each category, recorded in different aquatic settings, contains a varying number of frames, typically exceeding 1000 per category. Our proposed method surpasses all methods used for comparison by attaining an average F-measure of 0.98 on the Underwater Change Detection Dataset and 0.89 on the Fish4Knowledge dataset. Full article

Forests play a critical role in the provision of ecosystem services, and understanding their compositions, especially tree species, is essential for effective ecosystem management and conservation. However, identifying tree species is challenging and time-consuming. Recently, unmanned aerial vehicles (UAVs) equipped with various sensors have emerged as a promising technology for species identification due to their relatively low cost and high spatial and temporal resolutions. Moreover, the advancement of various deep learning models makes remote sensing based species identification more a reality. However, three questions remain to be answered: first, which of the state-of-the-art models performs best for this task; second, which is the optimal season for tree species classification in a temperate forest; and third, whether a model trained in one season can be effectively transferred to another season. To address these questions, we focus on tree species classification by using five state-of-the-art deep learning models on UAV-based RGB images, and we explored the model transferability between seasons. Utilizing UAV images taken in the summer and fall, we captured 8799 crown images of eight species. We trained five models using summer and fall images and compared their performance on the same dataset. All models achieved high performances in species classification, with the best performance on summer images, with an average F1-score was 0.96. For the fall images, Vision Transformer (ViT), EfficientNetB0, and YOLOv5 achieved F1-scores greater than 0.9, outperforming both ResNet18 and DenseNet. On average, across the two seasons, ViT achieved the best accuracy. This study demonstrates the capability of deep learning models in forest inventory, particularly for tree species classification. While the choice of certain models may not significantly affect performance when using summer images, the advanced models prove to be a better choice for fall images. Given the limited transferability from one season to another, further research is required to overcome the challenge associated with transferability across seasons. Full article

Tumors in the brain can be life-threatening, making early and precise detection crucial for effective treatment and improved patient outcomes. Deep learning (DL) techniques have shown significant potential in automating the early diagnosis of brain tumors by analyzing magnetic resonance imaging (MRI), offering a more efficient and accurate approach to classification. Deep convolutional neural networks (DCNNs), which are a sub-field of DL, have the potential to analyze rapidly and accurately MRI data and, as such, assist human radiologists, facilitating quicker diagnoses and earlier treatment initiation. This study presents an ensemble of three high-performing DCNN models, i.e., DenseNet169, EfficientNetB0, and ResNet50, for accurate classification of brain tumors and non-tumor MRI samples. Our proposed ensemble model demonstrates significant improvements over various evaluation parameters compared to individual state-of-the-art (SOTA) DCNN models. We implemented ten SOTA DCNN models, i.e., EfficientNetB0, ResNet50, DenseNet169, DenseNet121, SqueezeNet, ResNet34, ResNet18, VGG16, VGG19, and LeNet5, and provided a detailed performance comparison. We evaluated these models using two learning rates (LRs) of 0.001 and 0.0001 and two batch sizes (BSs) of 64 and 128 and identified the optimal hyperparameters for each model. Our findings indicate that the ensemble approach outperforms individual models, having 92% accuracy, 90% precision, 92% recall, and an F1 score of 91% at a 64 BS and 0.0001 LR. This study not only highlights the superior performance of the ensemble technique but also offers a comprehensive comparison with the latest research. Full article

Background: Prostate cancer is the second most common new cancer diagnosis in the United States. It is usually slow-growing, and when it is low-grade and confined to the prostate gland, it can be treated either conservatively (through active surveillance) or with surgery. However, if the cancer has spread beyond the prostate, such as to the lymph nodes, then that indicates a more aggressive cancer, and surgery may not be adequate. Methods: The challenge is that it is often difficult for radiologists reading prostate-specific imaging such as magnetic resonance images (MRIs) to differentiate malignant lymph nodes from non-malignant ones. An emerging field is the development of artificial intelligence (AI) models, including machine learning and deep learning, for medical imaging to assist in diagnostic tasks. Earlier research focused on implementing texture algorithms to extract imaging features used in classification models. More recently, researchers began studying the use of deep learning for both stand-alone feature extraction and end-to-end classification tasks. In order to tackle the challenges inherent in small datasets, this study was designed as a scalable hybrid framework utilizing pre-trained ResNet-18, a deep learning model, to extract features that were subsequently fed into a machine learning classifier to automatically identify malignant lymph nodes in patients with prostate cancer. For comparison, two texture algorithms were implemented, namely the gray-level co-occurrence matrix (GLCM) and Gabor. Results: Using an institutional prostate lymph node dataset (42 positives, 84 negatives), the proposed framework achieved an accuracy of 76.19%, a sensitivity of 79.76%, and a specificity of 69.05%. Using GLCM features, the classification achieved an accuracy of 61.90%, a sensitivity of 74.07%, and a specificity of 42.86%. Using Gabor features, the classification achieved an accuracy of 65.08%, a sensitivity of 73.47%, and a specificity of 52.50%. Conclusions: Our results demonstrate that a hybrid approach, i.e., using a pre-trainined deep learning model for feature extraction, followed by a machine learning classifier, is a viable solution. This hybrid approach is especially useful in medical-imaging-based applications with small datasets. Full article

In this paper, a deep learning-based device modeling framework for design-technology co-optimization (DTCO) is proposed. A ResNet surrogate model is utilized as an alternative to traditional compact models, demonstrating high accuracy in both single-task (I–V or C–V) and multi-task (I–V and C–V) device modeling. Moreover, transfer learning is applied to the ResNet model, using the BSIM-CMG compact model for a 12 nm FinFET SPICE model as the pre-trained source. Through this approach, superior modeling accuracy and faster training speed are achieved compared to a ResNet surrogate model initialized with random weights, thereby meeting the rapid and efficient demands of the DTCO process. The effectiveness of the ResNet surrogate model in circuit simulation for 12 nm FinFET devices is demonstrated. Full article

Agriculture stands as the cornerstone of Africa’s economy, supporting over 60% of the continent’s labor force. Despite its significance, the quality assessment of agricultural products remains a challenging task, particularly at a large scale, consuming valuable time and resources. The African plum is an agricultural fruit that is widely consumed across West and Central Africa but remains underrepresented in AI research. In this paper, we collected a dataset of 2892 African plum samples from fields in Cameroon representing the first dataset of its kind for training AI models. The dataset contains images of plums annotated with quality grades. We then trained and evaluated various state-of-the-art object detection and image classification models, including YOLOv5, YOLOv8, YOLOv9, Fast R-CNN, Mask R-CNN, VGG-16, DenseNet-121, MobileNet, and ResNet, on this African plum dataset. Our experimentation resulted in mean average precision scores ranging from 88.2% to 89.9% and accuracies between 86% and 91% for the object detection models and the classification models, respectively. We then performed model pruning to reduce model sizes while preserving performance, achieving up to 93.6% mean average precision and 99.09% accuracy after pruning YOLOv5, YOLOv8 and ResNet by 10–30%. We deployed the high-performing YOLOv8 system in a web application, offering an accessible AI-based quality assessment tool tailored for African plums. To the best of our knowledge, this represents the first such solution for assessing this underrepresented fruit, empowering farmers with efficient tools. Our approach integrates agriculture and AI to fill a key gap. Full article

Fruit photosynthesis occurs in an internal microenvironment seldom encountered by a leaf (hypoxic and extremely CO₂-enriched) due to its metabolic and anatomical features. In this study, the anatomical and photosynthetic traits of fully exposed green fruits of Quercus coccifera L. were assessed during the period of fruit production (summer) and compared to their leaf counterparts. Our results indicate that leaf photosynthesis, transpiration and stomatal conductance drastically reduced during the summer drought, while they recovered significantly after the autumnal rainfalls. In acorns, gas exchange with the surrounding atmosphere is hindered by the complete absence of stomata; hence, credible CO₂ uptake measurements could not be applied in the field. The linear electron transport rates (ETRs) in ambient air were similar in intact leaves and pericarps (i.e., when the physiological internal atmosphere of each tissue is maintained), while the leaf NPQ was significantly higher, indicating enhanced needs for harmless energy dissipation. The ETR measurements performed on leaf and pericarp discs at different CO₂/O₂ partial pressures in the supplied air mixture revealed that pericarps displayed significantly lower values at ambient gas levels, yet they increased by ~45% under high CO₂/O₂ ratios (i.e., at gas concentrations simulating the fruit’s interior). Concomitantly, NPQ declined gradually in both tissues as the CO₂/O₂ ratio increased, yet the decrease was more pronounced in pericarps. Furthermore, net CO₂ assimilation rates for both leaf and pericarp segments were low in ambient air and increased almost equally at high CO₂, while pericarps exhibited significantly higher respiration. It is suggested that during summer, when leaves suffer from photoinhibition, acorns could contribute to the overall carbon balance, through the re-assimilation of respiratory CO₂, thereby reducing the reproductive cost. Full article

Interactive segmentation methods utilize user-provided positive and negative clicks to guide the model in accurately segmenting target objects. Compared to fully automatic medical image segmentation, these methods can achieve higher segmentation accuracy with limited image data, demonstrating significant potential in clinical applications. Typically, for each new click provided by the user, conventional interactive segmentation methods reprocess the entire network by re-inputting the click into the segmentation model, which greatly increases the user’s interaction burden and deviates from the intended goal of interactive segmentation tasks. To address this issue, we propose an efficient segmentation network, ESM-Net, for interactive medical image segmentation. It obtains high-quality segmentation masks based on the user’s initial clicks, reducing the complexity of subsequent refinement steps. Recent studies have demonstrated the strong performance of the Mamba model in various vision tasks; however, its application in interactive segmentation remains unexplored. In our study, we incorporate the Mamba module into our framework for the first time and enhance its spatial representation capabilities by developing a Spatial Augmented Convolution (SAC) module. These components are combined as the fundamental building blocks of our network. Furthermore, we designed a novel and efficient segmentation head to fuse multi-scale features extracted from the encoder, optimizing the generation of the predicted segmentation masks. Through comprehensive experiments, our method achieved state-of-the-art performance on three medical image datasets. Specifically, we achieved 1.43 NoC@90 on the Kvasir-SEG dataset, 1.57 NoC@90 on the CVC-ClinicDB polyp segmentation dataset, and 1.03 NoC@90 on the ADAM retinal disk segmentation dataset. The assessments on these three medical image datasets highlight the effectiveness of our approach in interactive medical image segmentation. Full article

The global spread of Coronavirus (COVID-19) has prompted imperative research into scalable and effective detection methods to curb its outbreak. The early diagnosis of COVID-19 patients has emerged as a pivotal strategy in mitigating the spread of the disease. Automated COVID-19 detection using Chest X-ray (CXR) imaging has significant potential for facilitating large-scale screening and epidemic control efforts. This paper introduces a novel approach that employs state-of-the-art Convolutional Neural Network models (CNNs) for accurate COVID-19 detection. The employed datasets each comprised 15,000 X-ray images. We addressed both binary (Normal vs. Abnormal) and multi-class (Normal, COVID-19, Pneumonia) classification tasks. Comprehensive evaluations were performed by utilizing six distinct CNN-based models (Xception, Inception-V3, ResNet50, VGG19, DenseNet201, and InceptionResNet-V2) for both tasks. As a result, the Xception model demonstrated exceptional performance, achieving 98.13% accuracy, 98.14% precision, 97.65% recall, and a 97.89% F1-score in binary classification, while in multi-classification it yielded 87.73% accuracy, 90.20% precision, 87.73% recall, and an 87.49% F1-score. Moreover, the other utilized models, such as ResNet50, demonstrated competitive performance compared with many recent works. Full article