Search Results (303)

The spatial characteristics of the dry beach in tailings ponds are critical indicators for the safety assessment of tailings dams. This study presents a method for dry beach extraction that combines deep learning-based semantic segmentation with 3D reconstruction, overcoming the limitations of 2D methods in spatial analysis. The workflow includes four steps: (1) High-resolution 3D point clouds are reconstructed from UAV images, and the projection matrix of each image is derived to link 2D pixels with 3D points. (2) AlexNet and GoogLeNet are employed to extract image features and automatically select images containing the dry beach boundary. (3) A DeepLabv3+ network is trained on manually labeled samples to perform semantic segmentation of the dry beach, with a lightweight incremental training strategy for enhanced adaptability. (4) Boundary pixels are detected and back-projected into 3D space to generate consistent point cloud boundaries. The method was validated on two-phase UAV datasets from a tailings pond in Yunnan Province, China. In phase I, the model achieved high segmentation performance, with a mean Accuracy and IoU of approximately 0.95 and a BF of 0.8267. When applied to phase II without retraining, the model maintained stable performance on dam boundaries, while slight performance degradation was observed on hillside and water boundaries. The 3D back-projection converted 2D boundary pixels into 3D coordinates, enabling the extraction of dry beach point clouds and supporting reliable dry beach length monitoring and deposition morphology analysis. Full article

Activation functions are fundamental to the representational capacity and optimization dynamics of deep neural networks. Although numerous nonlinearities have been proposed, ranging from classical sigmoid and tanh to modern smooth and trainable functions, no single activation is universally optimal, as each involves trade-offs among gradient flow, stability, computational cost, and expressiveness. This study introduces TRex, a novel activation function that combines the efficiency and linear growth of rectified units with the smooth gradient propagation of saturating functions. TRex features a non-zero, smoothed negative region inspired by tanh while maintaining near-linear behavior for positive inputs, preserving gradients and reducing neuron inactivation. We evaluate TRex against five widely used activation functions (ReLU, ELU, Swish, Mish, and GELU) across eight convolutional architectures (AlexNet, DenseNet-121, EfficientNet-B0, GoogLeNet, LeNet, MobileNet-V2, ResNet-18, and VGGNet) on two benchmark datasets (MNIST and Fashion-MNIST) and a real-world medical imaging dataset (SkinCancer). The results show that TRex achieves competitive accuracy, AUC, and convergence stability across most deep, connectivity-rich architectures while maintaining computational efficiency comparable to those of other smooth activations. These findings highlight TRex as a contextually efficient activation function that enhances gradient flow, generalization, and training stability, particularly in deeper or densely connected architectures, while offering comparable performance in lightweight and mobile-optimized models. Full article

Background: Accurate sex estimation is crucial in forensic identification when DNA analysis is impractical or remains are fragmented. Traditional anthropometric approaches often rely on single bone measurements and yield moderate levels of accuracy. Objective: This study aimed to evaluate deep convolutional neural networks (CNNs) for automated sex estimation using entire foot radiographs, an approach rarely explored. Methods: Digital foot radiographs from 471 adults (238 men, 233 women, aged 18–65 years) without deformities or prior surgery were retrospectively collected at a single tertiary center. Six CNN architectures (AlexNet, ResNet-18, ResNet-50, ShuffleNet, GoogleNet, and InceptionV3) were trained using transfer learning (70/15/15 train–validation–test split, data augmentation). The model performance was assessed using accuracy, sensitivity, specificity, precision, and F1-score. Results: InceptionV3 achieved the highest accuracy (97.1%), surpassing previously reported methods (typically 72–89%), with balanced sensitivity (97.5%) and specificity (96.8%). ResNet-50 followed closely (95.7%), whereas simpler networks, such as AlexNet, underperformed (90%). Conclusions: Deep learning applied to whole-foot radiographs delivers state-of-the-art accuracy for sex estimation, enabling rapid, reproducible, and cost-effective forensic identification when DNA analysis is delayed or unavailable, such as in mass disasters or clinical emergency settings. Full article

Atmospheric gravity waves (AGWs) are treated as density structure perturbations of the atmosphere and play an important role in atmospheric dynamics. Utilizing All-Sky Airglow Imagers (ASAIs) with OI-Filter 557.7 nm, AGW phase velocity and propagation direction were extracted using classified images by visual inspection, where airglow images were collected from the OMTI network at Shigaraki (34.85 E, 134.11 N) from October 1998 to October 2002. Nonetheless, a large dataset of airglow images are processed and classified for studying AGW seasonal variation in the middle atmosphere. In this article, a machine learning-based approach for image recognition of AGWs from ASAIs is suggested. Consequently, three convolutional neural networks (CNNs), namely AlexNet, GoogLeNet, and ResNet-50, are considered. Out of 13,201 deviated images, 1192 very weak/unclear AGW signatures were eliminated during the quality control process. All networks were trained and tested by 12,007 classified images which approximately cover the maximum solar cycle during the time-period mentioned above. In the testing phase, AlexNet achieved the highest accuracy of 98.41%. Consequently, estimation of AGW zonal and meridional phase velocities in the mesosphere region by a cascade forward neural network (CFNN) is presented. The CFNN was trained and tested based on AGW and neutral wind data. AGW data were extracted from the classified AGW images by event and spectral methods, where wind data were extracted from the Horizontal Wind Model (HWM) as well as the middle and upper atmosphere radar in Shigaraki. As a result, the estimated phase velocities were determined with correlation coefficient (R) above 0.89 in all training and testing phases. Finally, a comparison with the existing studies confirms the accuracy of our proposed approaches in addition to AGW velocity forecasting. Full article

The escalating prevalence of malware poses a significant threat to digital infrastructure, demanding robust yet efficient detection methods. In this study, we evaluate multiple Convolutional Neural Network (CNN) architectures, including basic CNN, LeNet, AlexNet, GoogLeNet, and DenseNet, on a dataset of 11,000 malware images spanning 452 families. Our experiments demonstrate that CNN models can achieve reliable classification performance across both multiclass and binary tasks. However, we also uncover a critical weakness in that even minimal image perturbations, such as pixel modification lower than 1% of the total image pixels, drastically degrade accuracy and reveal CNNs’ fragility in adversarial settings. A key contribution of this work is spatial analysis of malware images, revealing that discriminative features concentrate disproportionately in the bottom-left quadrant. This spatial bias likely reflects semantic structure, as malware payload information often resides near the end of binary files when rasterized. Notably, models trained in this region outperform those trained in other sections, underscoring the importance of spatial awareness in malware classification. Taken together, our results reveal that CNN-based malware classifiers are simultaneously effective and vulnerable to learning strong representations but sensitive to both subtle perturbations and positional bias. These findings highlight the need for future detection systems that integrate robustness to noise with resilience against spatial distortions to ensure reliability in real-world adversarial environments. Full article

This paper presents a digital approach for the identification of apple varieties bred in Kazakhstan using deep learning methods and transfer learning. The main objective of this study is to develop and evaluate an algorithm for automatic varietal classification of apples based on color images obtained under controlled conditions. Five representative cultivars were selected as research objects: Aport Alexander, Ainur, Sinap Almaty, Nursat, and Kazakhskij Yubilejnyj. The fruit samples were collected in the pomological garden of the Kazakh Research Institute of Fruit and Vegetable Growing, ensuring representativeness and taking into account the natural variability of the cultivars. Two convolutional neural network (CNN) architectures—GoogLeNet and SqueezeNet—were fine-tuned using transfer learning with different optimization settings. The data processing pipeline included preprocessing, training and validation set formation, and augmentation techniques to improve model generalization. Network performance was assessed using standard evaluation metrics such as accuracy, precision, and recall, complemented by confusion matrix analysis to reveal potential misclassifications. The results demonstrated high recognition efficiency: the classification accuracy exceeded 95% for most cultivars, while the Ainur variety achieved 100% recognition when tested with GoogLeNet. Interestingly, the Nursat variety achieved the best results with SqueezeNet, which highlights the importance of model selection for specific apple types. These findings confirm the applicability of CNN-based deep learning for varietal recognition of Kazakhstan apple cultivars. The novelty of this study lies in applying neural network models to local Kazakhstan apple varieties for the first time, which is of both scientific and practical importance. The practical contribution of the research is the potential integration of the developed method into industrial fruit-sorting systems, thereby increasing productivity, objectivity, and precision in post-harvest processing. The main limitation of this study is the relatively small dataset and the use of controlled laboratory image acquisition conditions. Future research will focus on expanding the dataset, testing the models under real production environments, and exploring more advanced deep learning architectures to further improve recognition performance. Full article

Breast cancer is one of the leading causes of death among women of all ages and backgrounds globally. In recent years, the growing deficit of expert radiologists—particularly in underdeveloped countries—alongside a surge in the number of images for analysis, has negatively affected the ability to secure timely and precise diagnostic results in breast cancer screening. AI technologies offer powerful tools that allow for the effective diagnosis and survival forecasting, reducing the dependency on human cognitive input. Towards this aim, this research introduces a deep meta-learning framework for swift analysis of mammography images—combining a Siamese network model with a triplet-based loss function—to facilitate automatic screening (recognition) of potentially suspicious breast cancer cases. Three pre-trained deep CNN architectures, namely GoogLeNet, ResNet50, and MobileNetV3, are fine-tuned and scrutinized for their effectiveness in transforming input mammograms to a suitable embedding space. The proposed framework undergoes a comprehensive evaluation through a rigorous series of experiments, utilizing two different, publicly accessible, and widely used datasets of digital X-ray mammograms: INbreast and CBIS-DDSM. The experimental results demonstrate the framework’s strong performance in differentiating between tumorous and normal images, even with a very limited number of training samples, on both datasets. Full article

Interpreting chemical analysis results to identify ignitable liquid (IL) residues in fire debris samples is challenging, owing to the complex chemical composition of ILs and the diverse sample matrices. This work investigated a transfer learning approach with convolutional neural networks (CNNs), pre-trained for image recognition, to classify gas chromatography and mass spectrometry (GC/MS) data transformed into scalogram images. A small data set containing neat gasoline samples with diluted concentrations and burned Nylon carpets with varying weights was prepared to retrain six CNNs: GoogLeNet, AlexNet, SqueezeNet, VGG-16, ResNet-50, and Inception-v3. The classification tasks involved two classes: “positive of gasoline” and “negative of gasoline.” The results demonstrated that the CNNs performed very well in predicting the trained class data. When predicting untrained intra-laboratory class data, GoogLeNet had the highest accuracy (0.98 ± 0.01), precision (1.00 ± 0.01), sensitivity (0.97 ± 0.01), and specificity (1.00 ± 0.00). When predicting untrained inter-laboratory class data, GoogLeNet exhibited a sensitivity of 1.00 ± 0.00, while ResNet-50 achieved 0.94 ± 0.01 for neat gasoline. For simulated fire debris samples, both models attained sensitivities of 0.86 ± 0.02 and 0.89 ± 0.02, respectively. The new deep transfer learning approach enables automated pattern recognition in GC/MS data, facilitates high-throughput forensic analysis, and improves consistency in interpretation across various laboratories, making it a valuable tool for fire debris analysis. Full article

Gunshot sound classification plays a crucial role in public safety, forensic investigations, and intelligent surveillance systems. This study evaluates the performance of deep learning models in classifying firearm sounds by analyzing twelve time–frequency spectrogram representations, including Mel, Bark, MFCC, CQT, Cochleagram, STFT, FFT, Reassigned, Chroma, Spectral Contrast, and Wavelet. The dataset consists of 2148 gunshot recordings from four firearm types, collected in a semi-controlled outdoor environment under multi-orientation conditions. To leverage advanced computer vision techniques, all spectrograms were converted into RGB images using perceptually informed colormaps. This enabled the application of image processing approaches and fine-tuning of pre-trained Convolutional Neural Networks (CNNs) originally developed for natural image classification. Six CNN architectures—ResNet18, ResNet50, ResNet101, GoogLeNet, Inception-v3, and InceptionResNetV2—were trained on these spectrogram images. Experimental results indicate that CQT, Cochleagram, and Mel spectrograms consistently achieved high classification accuracy, exceeding 94% when paired with deep CNNs such as ResNet101 and InceptionResNetV2. These findings demonstrate that transforming time–frequency features into RGB images not only facilitates the use of image-based processing but also allows deep models to capture rich spectral–temporal patterns, providing a robust framework for accurate firearm sound classification. Full article

Predicting short-term buy and sell signals in financial markets remains a significant challenge for algorithmic trading. This difficulty stems from the data’s inherent volatility and noise, which often leads to spurious signals and poor trading performance. This paper presents a novel algorithmic trading model for silver that combines fine-tuned Convolutional Neural Networks (CNNs) with a decision filter based on the Relative Strength Index (RSI). The technique allows for the prediction of buy and sell points by turning time series data into chart images. Daily silver price per ounce data were turned into chart images using technical analysis indicators. Four pre-trained CNNs, namely AlexNet, VGG16, GoogLeNet, and ResNet-50, were fine-tuned using the generated image dataset to find the best architecture based on classification and financial performance. The models were evaluated using walk-forward validation with an expanding window. This validation method made the tests more realistic and the performance evaluation more robust under different market conditions. Fine-tuned VGG16 with the RSI filter had the best cost-adjusted profitability, with a cumulative return of 115.03% over five years. This was nearly double the 61.62% return of a buy-and-hold strategy. This outperformance is especially impressive because the evaluation period was mostly upward, which makes it harder to beat passive benchmarks. Adding the RSI filter also helped models make more disciplined decisions. This reduced transactions with low confidence. In general, the results show that pre-trained CNNs fine-tuned on visual representations, when supplemented with domain-specific heuristics, can provide strong and cost-effective solutions for algorithmic trading, even when realistic cost assumptions are used. 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

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

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

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

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