Search Results (571)

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

Creative insight is a core phenomenon of human cognition, often characterized by the sudden emergence of novel and contextually appropriate ideas. Classical models based on symbolic search or associative networks struggle to capture the non-linear, context-sensitive, and interference-driven aspects of insight. In this work, we propose a computational model of insight generation grounded in continuous-time quantum walks over weighted semantic graphs, where nodes represent conceptual units and edges encode associative relationships. By exploiting the principles of quantum superposition and interference, the model enables the probabilistic amplification of semantically distant but contextually relevant concepts, providing a plausible account of non-local transitions in thought. The model is implemented using standard Python 3.10 libraries and is available both as an interactive fully reproducible Google Colab notebook and a public repository with code and derived datasets. Comparative experiments on ConceptNet-derived subgraphs, including the Candle Problem, 20 Remote Associates Test triads, and Alternative Uses, show that, relative to classical diffusion, quantum walks concentrate more probability on correct targets (higher AUC and peaks reached earlier) and, in open-ended settings, explore more broadly and deeply (higher entropy and coverage, larger expected radius, and faster access to distant regions). These findings are robust under normalized generators and a common time normalization, align with our formal conditions for transient interference-driven amplification, and support quantum-like dynamics as a principled process model for key features of insight. 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

This paper applies a Convolutional Neural Network (CNN)-based vehicle security enhancement model, with a specific focus on the South African context. While conventional security systems, including immobilizers, alarms, steering locks, and GPS trackers, provide a baseline level of protection, they are increasingly being circumvented by technologically adept adversaries. These limitations have spurred the development of advanced security solutions leveraging artificial intelligence (AI), with a particular emphasis on computer vision and deep learning techniques. This paper presents a CNN-based Vehicle Security Enhancement Model (CNN-based VSEM) that integrates facial recognition with GSM and GPS technologies to provide a robust, real-time security solution in South Africa. This study contributes a novel integration of CNN-based authentication with GSM and GPS tracking in the South African context, validated on a functional prototype.The prototype, developed on a Raspberry Pi 4 platform, was validated through practical demonstrations and user evaluations. The system achieved an average recognition accuracy of 85.9%, with some identities reaching 100% classification accuracy. While misclassifications led to an estimated False Acceptance Rate (FAR) of ~5% and False Rejection Rate (FRR) of ~12%, the model consistently enabled secure authentication. Preliminary latency tests indicated a decision time of approximately 1.8 s from image capture to ignition authorization. These results, together with positive user feedback, confirm the model’s feasibility and reliability. This integrated approach presents a promising advancement in intelligent vehicle security for regions with high rates of vehicle theft. Future enhancements will explore the incorporation of 3D sensing, infrared imaging, and facial recognition capable of handling variations in facial appearance. Additionally, the model is designed to detect authorized users, identify suspicious behaviour in the vicinity of the vehicle, and provide an added layer of protection against unauthorized access. Full article

Background: Children with neurodevelopmental disorders (NDDs) commonly experience executive function (EF) impairments that impact daily life and academics. While bilingualism has generally been associated with cognitive advantages in typically developing (TD) children, its relationship with EF in children with NDDs remains unclear and represents a critical knowledge gap for families and clinicians considering bilingual exposure in these populations. Methods: For this scoping review, we searched PubMed, ProQuest, CogNet, PsycINFO, Scopus, ERIC, Embase, CINAHL, Linguistics Abstracts Online, and Google Scholar for studies published between database inception and December 2024, without language restrictions. We included quantitative, qualitative, and mixed-methods studies that (i) involved participants aged 4–12 years with diagnosed NDDs; (ii) examined children with bilingual language exposure; (iii) employed validated instruments for measuring cognitive or executive function; (iv) presented original empirical findings; and (v) were published in English. We excluded studies lacking comparisons between groups and longitudinal studies. Data on study characteristics, participants, EF assessments, and main findings were extracted. This study is registered with OSF Registries. Findings: Fifteen cross-sectional studies met the inclusion criteria, all of which focused exclusively on children with autism spectrum disorder (ASD), with no studies examining other NDDs. The studies involved 982 children with ASD (463 monolingual; 404 bilingual) and 644 TD children. Most studies (n = 11) revealed that, compared with monolingual children with ASD, bilingual children with ASD demonstrated advantages in working memory, cognitive flexibility, and inhibitory control on performance-based tasks. However, findings were inconsistent for spatial inhibition tasks, and parent-reported measures sometimes failed to detect bilingual-related differences. Interpretation: Bilingualism is associated with specific EF benefits for children with ASD, adding to evidence that questions longstanding concerns about the negative impacts of bilingual exposure in NDD populations. The evidence suggests that bilingual exposure could potentially serve as a complementary approach to traditional interventions for addressing EF impairments in children with ASD, although this evidence is limited to cross-sectional designs and requires further studies. However, the exclusive focus on ASD limits generalisability across the broader spectrum of NDDs. Further research is needed across diverse NDD populations employing comprehensive, multi-method EF assessments that combine performance-based tasks with parent-reported measures to better inform parenting, clinical, and educational practices. Full article

Maintaining the freshness of shrimp is a critical issue in quality and safety control within the food processing industry. Traditional methods often rely on destructive techniques, which are difficult to apply in online real-time monitoring. To address this challenge, this study aims to propose a non-destructive approach for shrimp freshness assessment based on imaging and deep learning, enabling efficient and reliable freshness classification. The core innovation of the method lies in constructing an improved GoogLeNet architecture. By incorporating the ELU activation function, L2 regularization, and the RMSProp optimizer, combined with a transfer learning strategy, the model effectively enhances generalization capability and stability under limited sample conditions. Evaluated on a shrimp image dataset rigorously annotated based on TVB-N reference values, the proposed model achieved an accuracy of 93% with a test loss of only 0.2. Ablation studies further confirmed the contribution of architectural and training strategy modifications to performance improvement. The results demonstrate that the method enables rapid, non-contact freshness discrimination, making it suitable for real-time sorting and quality monitoring in shrimp processing lines, and providing a feasible pathway for deployment on edge computing devices. This study offers a practical solution for intelligent non-destructive detection in aquatic products, with strong potential for engineering applications. 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

Illegal mining poses significant environmental and economic challenges, and effective monitoring is essential for regulatory enforcement. This study evaluates the potential of the U-Net deep learning model for detecting mining activities using Sentinel-2 satellite imagery over the Strzegom region in Poland. We prepared annotated datasets representing various land cover classes, including active and inactive mineral extraction sites, agricultural areas, and urban zones. U-Net was trained and tested on these data, and its classification accuracy was assessed against common Google Earth Engine (GEE) classifiers such as Random Forest, CART, and SVM. Accuracy metrics, including Overall Accuracy, Producer’s Accuracy, and F1-score, were computed. Additional analyses compared model performance for detecting licensed versus potentially illegal mining areas, supported by integration with publicly available geospatial datasets (MOEK, MIDAS, CORINE). The results show that U-Net achieved higher detection accuracy for mineral extraction sites than the GEE classifiers, particularly for small and spatially heterogeneous areas. This approach demonstrates the feasibility of combining deep learning with open geospatial data for supporting mining activity monitoring and identifying potential cases of unlicensed extraction. Full article

In this paper, a wideband metasurface absorber is proposed by utilizing transfer learning and a conditional deep convolutional generative adversarial network (CDCGAN). This approach involves introducing a forward prediction neural network to predict the spectral curve of a metasurface absorber, as well as a generative adversarial network for the inverse design of a metasurface absorber. After comparing different pre-trained models, a transfer learning network (TLN) based on GoogleNet-InceptionV3 is incorporated into the design process to reduce the amount of training data required. Based on the pixelated metasurface with a common effect of metallic pixels and resistive film pixels, a broadband electromagnetic absorber was designed through the CDCGAN model. For the application target of the C-band, a pixelated broadband metasurface Absorber I has been designed, which can achieve an absorption effect of less than −8 dB in the range of 6.5–8 GHz, and the absorption performance reaches less than −15 dB near the resonant frequency point of 7 GHz. Further lightweight optimization design was carried out, and the metasurface Absorber II was designed for application in the X-band, which has an absorption bandwidth below −8 dB at 9–12 GHz. The reflectivity curve measured by the experiment is in good agreement with that of the simulation result. Of note, our methodology aims to reversely engineer suitable absorbing structures based on customer-defined spectrums, which may bear some significance to the rapid design of broadband metasurface absorbers. Full article

Background/Objectives: Artificial Intelligence (AI) is improving dentistry through increased accuracy in diagnostics, planning, and workflow automation. AI tools, including machine learning (ML) and deep learning (DL), are being adopted in oral medicine to improve patient care, efficiency, and lessen clinicians’ workloads. AI in dentistry, despite its use, faces an issue of acceptance, with its obstacles including ethical, legal, and technological ones. In this article, a review of current AI use in oral medicine, new technology development, and integration barriers is discussed. Methods: A narrative review of peer-reviewed articles in databases such as PubMed, Scopus, Web of Science, and Google Scholar was conducted. Peer-reviewed articles over the last decade, such as AI application in diagnostic imaging, predictive analysis, real-time documentation, and workflows automation, were examined. Besides, improvements in AI models and critical impediments such as ethical concerns and integration barriers were addressed in the review. Results: AI has exhibited strong performance in radiographic diagnostics, with high accuracy in reading cone-beam computed tomography (CBCT) scan, intraoral photographs, and radiographs. AI-facilitated predictive analysis has enhanced personalized care planning and disease avoidance, and AI-facilitated automation of workflows has maximized administrative workflows and patient record management. U-Net-based segmentation models exhibit sensitivities and specificities of approximately 93.0% and 88.0%, respectively, in identifying periapical lesions on 2D CBCT slices. TensorFlow-based workflow modules, integrated into vendor platforms such as Planmeca Romexis, can reduce the processing time of patient records by a minimum of 30 percent in standard practice. The privacy-preserving federated learning architecture has attained cross-site model consistency exceeding 90% accuracy, enabling collaborative training among diverse dentistry clinics. Explainable AI (XAI) and federated learning have enhanced AI transparency and security with technological advancement, but barriers include concerns regarding data privacy, AI bias, gaps in AI regulating, and training clinicians. Conclusions: AI is revolutionizing dentistry with enhanced diagnostic accuracy, predictive planning, and efficient administration automation. With technology developing AI software even smarter, ethics and legislation have to follow in order to allow responsible AI integration. To make AI in dental care work at its best, future research will have to prioritize AI interpretability, developing uniform protocols, and collaboration between specialties in order to allow AI’s full potential in dentistry. 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

Artificial intelligence (AI) has become the mainstream of analysis tools in remote sensing. Various semantic segmentation models have been introduced to segment land cover from aerial or satellite images, and remarkable results have been achieved. However, they often lack universal performance on unseen images, making them challenging to provide as a service. One of the primary reasons for the lack of robustness is overfitting, resulting from errors and inconsistencies in the ground truth (GT). In this study, we propose a method to mitigate these inconsistencies by utilizing redundant models and verify the improvement using a public dataset based on Google Earth images. Redundant models share the same network architecture and hyperparameters but are trained with different combinations of training and validation data on the same dataset. Because of the variations in sample exposure during training, these models yield slightly different inference results. This variability allows for the estimation of pixel-level confidence levels for the GT. The confidence level is incorporated into the GT to influence the loss calculation during the training of the enhanced model. Furthermore, we implemented a consensus model that employs modified masks, where classes with low confidence are substituted by the dominant classes identified through a majority vote from the redundant models. To further improve robustness, we extended the same approach to fuse the dataset with different class compositions based on imagery from the Korea Multipurpose Satellite 3A (KOMPSAT-3A). Performance evaluations were conducted on three network architectures: a simple network, U-Net, and DeepLabV3. In the single-dataset case, the performance of the enhanced and consensus models improved by an average of 2.49% and 2.59% across the network architectures. In the multi-dataset scenario, the enhanced models and consensus models showed an average performance improvement of 3.37% and 3.02% across the network architectures, respectively, compared to an average increase of 1.55% without the proposed method. Full article

As Android malware grows increasingly sophisticated, traditional detection methods struggle to keep pace, creating an urgent need for robust, interpretable, and real-time solutions to safeguard mobile ecosystems. This study introduces YoloMal-XAI, a novel deep learning framework that transforms Android application files into RGB image representations by mapping DEX (Dalvik Executable), Manifest.xml, and Resources.arsc files to distinct color channels. Evaluated on the CICMalDroid2020 dataset using YOLO11 pretrained classification models, YoloMal-XAI achieves 99.87% accuracy in binary classification and 99.56% in multi-class classification (Adware, Banking, Riskware, SMS, and Benign). Compared to ResNet-50, GoogLeNet, and MobileNetV2, YOLO11 offers competitive accuracy with at least 7× faster training over 100 epochs. Against YOLOv8, YOLO11 achieves comparable or superior accuracy while reducing training time by up to 3.5×. Cross-corpus validation using Drebin and CICAndMal2017 further confirms the model’s generalization capability on previously unseen malware. An ablation study highlights the value of integrating DEX, Manifest, and Resources components, with the full RGB configuration consistently delivering the best performance. Explainable AI (XAI) techniques—Grad-CAM, Grad-CAM++, Eigen-CAM, and HiRes-CAM—are employed to interpret model decisions, revealing the DEX segment as the most influential component. These results establish YoloMal-XAI as a scalable, efficient, and interpretable framework for Android malware detection, with strong potential for future deployment on resource-constrained mobile devices. Full article