Search Results (448)

To address the challenges of weak fault features and strong non-stationarity in early-stage vibration signals, this study proposes a novel fault diagnosis method combining enhanced variational mode decomposition (VMD) with a structurally improved GoogLeNet. Specifically, an improved wild horse optimizer (IWHO) with tent chaotic mapping is employed to automatically optimize critical VMD parameters, including the number of modes K and the penalty factor α, enabling precise decomposition of non-stationary signals to extract weak fault features. The vibration signal is decomposed, and the top five intrinsic mode functions (IMFs) are selected based on the kurtosis criterion. Time–frequency features are then extracted from these IMFs and input into a modified GoogLeNet classifier. The GoogLeNet structure is improved by replacing standard n × n convolution kernels with cascaded 1 × n and n × 1 kernels, and by substituting the ReLU activation function with a parameterized TReLU function to enhance adaptability and convergence. Experimental results on two public rolling bearing datasets demonstrate that the proposed method effectively handles non-stationary signals, achieving 99.17% accuracy across four fault types and maintaining over 95.80% accuracy under noisy conditions. Full article

Code duplication, commonly referred to as code cloning, is not inherent in software systems but arises due to various factors, such as time constraints in meeting project deadlines. These duplications, or “code clones”, complicate the program structure and increase maintenance costs. Code clones are categorized into four types: Type-1, Type-2, Type-3, and Type-4. This study aims to address the adverse effects of code clones by introducing LeONet, a hybrid Deep Learning approach that enhances the detection of code clones in software systems. The hybrid approach, LeONet, combines LeNet-5 with Oreo’s Siamese architecture. We extracted clone method pairs from the BigCloneBench Java repository. Feature extraction was performed using Abstract Syntax Trees, which are scalable and accurately represent the syntactic structure of the source code. The performance of LeONet was compared against other classifiers including ANN, LeNet-5, Oreo’s Siamese, LightGBM, XGBoost, and Decision Tree. LeONet demonstrated superior performance among the classifiers tested, achieving the highest F1 score of 98.12%. It also compared favorably against state-of-the-art approaches, indicating its effectiveness in code clone detection. The results validate the effectiveness of LeONet in detecting code clones, outperforming existing classifiers and competing closely with advanced methods. This study underscores the potential of hybrid deep learning models and feature extraction techniques in improving the accuracy of code clone detection, providing a promising direction for future research in this area. Full article

Background/Objectives: Accurate classification of brain tumors is critical for treatment planning and prognosis. While deep convolutional neural networks (CNNs) have shown promise in medical imaging, few studies have systematically compared multiple architectures or integrated ensemble strategies to improve diagnostic performance. This study aimed to evaluate various CNN models and optimize classification performance using a majority voting ensemble approach on T1-weighted MRI brain images. Methods: Seven pretrained CNN architectures were fine-tuned to classify four categories: glioblastoma, meningioma, pituitary adenoma, and no tumor. Each model was trained using two optimizers (SGDM and ADAM) and evaluated on a public dataset split into training (70%), validation (10%), and testing (20%) subsets, and further validated on an independent external dataset to assess generalizability. A majority voting ensemble was constructed by aggregating predictions from all 14 trained models. Performance was assessed using accuracy, Kappa coefficient, true positive rate, precision, confusion matrix, and ROC curves. Results: Among individual models, GoogLeNet and Inception-v3 with ADAM achieved the highest classification accuracy (0.987). However, the ensemble approach outperformed all standalone models, achieving an accuracy of 0.998, a Kappa coefficient of 0.997, and AUC values above 0.997 for all tumor classes. The ensemble demonstrated improved sensitivity, precision, and overall robustness. Conclusions: The majority voting ensemble of diverse CNN architectures significantly enhanced the performance of MRI-based brain tumor classification, surpassing that of any single model. These findings underscore the value of model diversity and ensemble learning in building reliable AI-driven diagnostic tools for neuro-oncology. Full article

Despite the transformative potential of AI, the concept of neural networks that can produce other neural networks by generating model weights (hypernetworks) has been largely understudied. One of the possible reasons is the lack of available research resources that can be used for the purpose of hypernetwork research. Here we describe a dataset of neural networks, designed for the purpose of hypernetwork research. The dataset includes ${10}^4$ LeNet-5 neural networks trained for binary image classification separated into 10 classes, such that each class contains 1000 different neural networks that can identify a certain ImageNette V2 class from all other classes. A computing cluster of over ${10}^4$ cores was used to generate the dataset. Basic classification results show that the neural networks can be classified with accuracy of 72.0%, indicating that the differences between the neural networks can be identified by supervised machine learning algorithms. The ultimate purpose of the dataset is to enable hypernetwork research. The dataset and the code that generates it are open and accessible to the public. Full article

Federated learning allows models to be trained on edge devices with local data, eliminating the need to share data with a central server. This significantly reduces the amount of data transferred from edge devices to central servers, which is particularly important in rural areas with limited bandwidth resources. Despite the potential of federated learning to fine-tune deep learning models using data collected from edge devices in low-resource environments, its application in the field of bird monitoring remains underexplored. This study proposes a federated learning pipeline tailored for bird species classification in wetlands. The proposed approach is based on lightweight convolutional neural networks optimized for use on resource-constrained devices. Since the performance of federated learning is strongly influenced by the models used and the experimental setting, this study conducts a comprehensive comparison of well-known lightweight models such as WideResNet, EfficientNetV2, MNASNet, GoogLeNet and ResNet in different training settings. The results demonstrate the importance of the training setting in federated learning architectures and the suitability of the different models for bird species recognition. This work contributes to the wider application of federated learning in ecological monitoring and highlights its potential to overcome challenges such as bandwidth limitations. Full article

Deep neural network (DNN) watermarking is a suitable method for protecting the ownership of deep learning (DL) models. It secretly embeds an identifier within the model, which can be retrieved by the owner to prove ownership. In this paper, we first provide a unified framework for white-box DNN watermarking schemes that encompasses current state-of-the-art methods and outlines their theoretical inter-connections. Next, we introduce DICTION, a new white-box dynamic robust watermarking scheme derived from this framework. Its main originality lies in a generative adversarial network (GAN) strategy where the watermark extraction function is a DNN trained as a GAN discriminator, while the target model acts as a GAN generator. DICTION can be viewed as a generalization of DeepSigns, which, to the best of our knowledge, is the only other dynamic white-box watermarking scheme in the literature. Experiments conducted on four benchmark models (MLP, CNN, ResNet-18, and LeNet) demonstrate that DICTION achieves a zero bit error rate (BER) while maintaining model accuracy within 0.5% of the baseline. DICTION shows superior robustness, tolerating up to 95% weight pruning compared to 80% for existing methods, and it demonstrates complete resistance to fine-tuning and overwriting attacks where competing methods fail, with a BER of >0.3. Full article

Formation Microresistivity Scanner Imaging (FMI) plays a crucial role in identifying lithology, sedimentary structures, fractures, and reservoir evaluation. However, during the lithology identification process of FMI images relying on transfer learning networks, the limited dataset size of existing models and their relatively primitive architecture substantially compromise the accuracy of well-log interpretation results and practical production efficiency. This study employs the VGG-19 transfer learning model as its core framework to conduct preprocessing, feature extraction, and analysis of FMI well-log images from glutenite formations in an oilfield in Xinjiang, with the objective of achieving rapid and accurate intelligent identification and classification of formation lithology. Simultaneously, this paper emphasizes a systematic comparative analysis of the recognition performance between the VGG-19 model and existing models, such as GoogLeNet and Xception, to screen for the model exhibiting the strongest region-specific applicability. The study finds that lithology can be classified into five types based on physical structures and diagnostic criteria: gray glutenite, brown glutenite, fine sandstone, conglomerate, and mudstone. The research results demonstrate the VGG-19 model exhibits superior accuracy in identifying FMI images compared to the other two models; the VGG-19 model achieves a training accuracy of 99.64%, a loss value of 0.034, and a validation accuracy of 95.6%; the GoogLeNet model achieves a training accuracy of 96.1%, a loss value of 0.05615, and a validation accuracy of 90.38%; and the Xception model achieves a training accuracy of 91.3%, a loss value of 0.0713, and a validation accuracy of 87.15%. These findings are anticipated to provide a significant reference for the in-depth application of VGG-19 transfer learning in FMI well-log interpretation. Full article

As cities grow denser, the demand for efficient parking systems becomes more critical to reduce traffic congestion, fuel consumption, and environmental impact. This paper proposes a smart parking solution that combines deep learning and algorithmic sorting to identify the nearest available parking slot in real time. The system uses several pre-trained convolutional neural network (CNN) models—VGG16, ResNet50, Xception, LeNet, AlexNet, and MobileNet—along with a lightweight custom CNN architecture, all trained on a custom parking dataset. These models are integrated into a mobile application that allows users to view and request nearby parking spaces. A merge sort algorithm ranks available slots based on proximity to the user. The system is validated using benchmark datasets (CNR-EXT and PKLot), demonstrating high accuracy across diverse weather conditions. The proposed system shows how applied mathematical models and deep learning can improve urban mobility through intelligent infrastructure. Full article

In recent years, significant advancements in artificial intelligence, particularly in the field of deep learning, have increasingly been integrated into agricultural applications, including critical processes such as disease detection. Tomato, being one of the most widely consumed agricultural products globally and highly susceptible to a variety of fungal, bacterial, and viral pathogens, remains a prominent focus in disease detection research. In this study, we propose a deep learning-based approach for the detection of tomato diseases, a critical challenge in agriculture due to the crop’s vulnerability to fungal, bacterial, and viral pathogens. We constructed an original dataset comprising 6414 images captured under real production conditions, categorized into three image types: leaves, green tomatoes, and red tomatoes. The dataset includes five classes: healthy samples, late blight, early blight, gray mold, and bacterial cancer. Twenty-one deep learning models were evaluated, and the top five performers (EfficientNet-b0, NasNet-Large, ResNet-50, DenseNet-201, and Places365-GoogLeNet) were selected for feature extraction. From each model, 1000 deep features were extracted, and feature selection was conducted using MRMR, Chi-Square (Chi²), and ReliefF methods. The top 100 features from each selection technique were then used for reclassification with traditional machine learning classifiers under five-fold cross-validation. The highest test accuracy of 92.0% was achieved with EfficientNet-b0 features, Chi² selection, and the Fine KNN classifier. EfficientNet-b0 consistently outperformed other models, while the combination of NasNet-Large and Wide Neural Network yielded the lowest performance. These results demonstrate the effectiveness of combining deep learning-based feature extraction with traditional classifiers and feature selection techniques for robust detection of tomato diseases in real-world agricultural environments. Full article

Powdery mildew is one of the most common diseases affecting strawberry yield and quality. Accurate and timely detection is essential to reduce pesticide usage and labor costs. However, recognizing strawberry powdery mildew in complex field environments remains a significant challenge. In this study, an HSV-based image segmentation method was employed to enhance the extraction of disease regions from complex backgrounds. A total of 14 widely used deep learning models—including SqueezeNet, GoogLeNet, ResNet-50, AlexNet, and others—were systematically evaluated for their classification performance. To address sample imbalance, data augmentation was applied to 2372 healthy and 553 diseased leaf images, resulting in 11,860 training samples. Experimental results showed that InceptionV4, DenseNet-121, and ResNet-50 achieved superior performance across metrics such as accuracy, F1-score, recall, and loss. Models such as MobileNetV2, AlexNet, VGG-16, and InceptionV3 demonstrated certain strengths, and models like SqueezeNet, VGG-19, EfficientNet, and even ResNet-50 showed room for further improvement in performance. These findings demonstrate that CNN models originally developed for other crop diseases can be effectively adapted to detect strawberry powdery mildew under complex conditions. Future work will focus on enhancing model robustness and deploying the system for real-time field monitoring. Full article

This study investigated the abundance and richness of insect pests and beneficial insects on 20 squash cultivars across three seasons in middle Georgia, U.S. Insects were sampled using yellow sticky cards, pan traps and sweep nets. Bemisia tabaci Gennadius (sweet potato whitefly) was prevalent in all seasons, while other key pests showed distinct seasonal peaks. Diaphania hyalinata Linnaeus (melonworm) peaked mid-July in summer 2021 (21 June–1 August), while Thysanoptera species, Acalymma vittatum Fabricius (striped cucumber beetle), and Diabrotica balteata LeConte (banded cucumber beetle) peaked late July-early August. In fall 2021 (4 October–14 November), Epilachna borealis (squash beetle), D. hyalinata, and D. nitidalis Stoll (pickleworm) were more active in early to mid-October, whereas D. undecimpunctata howardi Barber (spotted cucumber beetle) peaked in late November. In fall 2022 (17 October–20 November), D. balteata and D. undecimpunctata howardi peaked mid October to early November, while Anasa tristis DeGeer (squash bug) peaked in mid–late November. Orius insidiosus Say (minute pirate bug) peaked in late summer 2021 and remained stable in fall 2021. Pollinators were most active in mid-fall. Cultivars influenced insect abundance. ‘Saffron’ and ‘Amberpic 8455’ harbored the most O. insidiosus and fewer D. balteata and Thysanoptera species. ‘Golden Goose Hybrid’ had the highest moth numbers. These patterns suggest that cultivar traits influenced pest susceptibility and beneficial arthropods’ activity. Temperature and relative humidity were positively correlated with A. vittatum and E. borealis numbers, but rainfall negatively affected bees. These findings underscore the importance of cultivar selection and weather condition considerations in integrated pest management. Full article

Adzuki bean rust disease is an important factor restricting the yield of the adzuki bean. Late prevention and control at the early stage of the disease will lead to crop failure. Traditional diagnosis methods of adzuki bean rust disease mainly rely on field observations and laboratory tests, which are inefficient, time-consuming, highly dependent on professional knowledge, and cannot meet the requirements of modern agriculture for rapid and accurate diagnosis. To address this issue, a diagnosis method of adzuki bean rust disease was proposed using spectroscopy and deep learning methods. First, visible/near-infrared (UV/VNIR) spectroscopy was used to extract the spectral information of leaves, and discrete wavelet transform (DWT) was applied to preprocess and smooth the original canopy spectral data to effectively reduce the impact of noise interference. Second, the competitive adaptive reweighted sampling (CARS) algorithm was implemented in the range of 425–825 nm to determine the optimal characteristic wavenumbers, thereby reducing data redundancy. Finally, 51 characteristic wavenumbers were selected and imported into the LeNet-5 deep learning model for simulation and evaluation. The results showed that the accuracy, precision, recall, and F1 score on the test set were 99.65%, 98.04%, 99.01%, and 98.52%, respectively. The proposed DWT-CARS-LeNet-5 model can diagnose adzuki bean rust quickly, accurately, and non-destructively. This method can provide a cutting-edge solution for improving the accuracy of prevention and control of adzuki bean rust disease in agricultural practice. Full article

Background: Post-traumatic stress disorder (PTSD) is a serious psychiatric condition that can lead to severe anxiety, depression, and cardiovascular complications if left untreated. Early and accurate diagnosis is critical. This study aims to develop and evaluate an artificial intelligence-based classification system using electrocardiogram (ECG) signals for the detection of PTSD. Methods: Raw ECG signals were transformed into time–frequency images using Continuous Wavelet Transform (CWT) to generate 2D scalogram representations. These images were classified using deep learning-based convolutional neural networks (CNNs), including AlexNet, GoogLeNet, and ResNet50. In parallel, statistical features were extracted directly from the ECG signals and used in traditional machine learning (ML) classifiers for performance comparison. Four different segment lengths (5 s, 10 s, 15 s, and 20 s) were tested to assess their effect on classification accuracy. Results: Among the tested models, ResNet50 achieved the highest classification accuracy of 94.92%, along with strong MCC, sensitivity, specificity, and precision metrics. The best performance was observed with 5-s signal segments. Deep learning (DL) models consistently outperformed traditional ML approaches. The area under the curve (AUC) for ResNet50 reached 0.99, indicating excellent classification capability. Conclusions: This study demonstrates that CNN-based models utilizing time–frequency representations of ECG signals can effectively classify PTSD with high accuracy. Segment length significantly influences model performance, with shorter segments providing more reliable results. The proposed method shows promise for non-invasive, ECG-based diagnostic support in PTSD detection. Full article

Wind turbine wake modeling is critical for the design and optimization of wind farms. Traditional methods often struggle with the trade-off between accuracy and computational cost. Recently, data-driven neural networks have emerged as a promising solution, offering both high fidelity and fast inference speeds. To advance this field, a novel machine learning model has been developed to predict wind farm mean flow fields through an adaptive multi-fidelity framework. This model extends transfer-learning-based high-dimensional multi-fidelity modeling to scenarios where varying fidelity levels correspond to distinct physical models, rather than merely differing grid resolutions. Built upon a U-Net architecture and incorporating a wind farm parameter encoder, our framework integrates high-fidelity large-eddy simulation (LES) data with a low-fidelity engineering wake model. By directly predicting time-averaged velocity fields from wind farm parameters, our approach eliminates the need for computationally expensive simulations during inference, achieving real-time performance ($1.32\times {10}^{-5}$ GPU hours per instance with negligible CPU workload). Comparisons against field-measured data demonstrate that the model accurately approximates high-fidelity LES predictions, even when trained with limited high-fidelity data. Furthermore, its end-to-end extensible design allows full differentiability and seamless integration of multiple fidelity levels, providing a versatile and scalable solution for various downstream tasks, including wind farm control co-design. Full article

Malware continues to evolve rapidly, posing significant challenges to network security. Traditional signature-based detection methods often struggle to cope with advanced evasion techniques such as polymorphism, metamorphism, encryption, and stealth, which are commonly employed by cybercriminals. As a result, these conventional approaches frequently fail to detect newly emerging malware variants in a timely manner. To address this limitation, Zero-Shot Learning (ZSL) has emerged as a promising alternative, offering improved classification capabilities for previously unseen malware samples. ZSL models leverage auxiliary semantic information and binary feature representations to enhance the recognition of novel threats. This study proposes a Transductive Zero-Shot Learning (TZSL) model based on the Vector Quantized Variational Autoencoder (VQ-VAE) architecture, integrated with a malware knowledge graph constructed from sandbox behavioral analysis of ransomware families. The model is further optimized through hyperparameter tuning to maximize classification performance. Evaluation metrics include per-family classification accuracy, precision, recall, F1-score, and Receiver Operating Characteristic (ROC) curves to ensure robust and reliable detection outcomes. In particular, the harmonic mean (H-mean) metric from the Generalized Zero-Shot Learning (GZSL) framework is introduced to jointly evaluate the model’s performance on both seen and unseen classes, offering a more holistic view of its generalization ability. The experimental results demonstrate that the proposed VQ-VAE model achieves an F1-score of 93.5% in ransomware classification, significantly outperforming other baseline models such as LeNet-5 (65.6%), ResNet-50 (71.8%), VGG-16 (74.3%), and AlexNet (65.3%). These findings highlight the superior capability of the VQ-VAE-based TZSL approach in detecting novel malware variants, improving detection accuracy while reducing false positives. Full article