Search Results (431)

Malicious domains are part of the landscape of the internet but are becoming more prevalent and more dangerous both to companies and to individuals. They can be hosted on various technologies and serve an array of content, including malware, command and control and complex phishing sites that are designed to deceive and expose. Tracking, blocking and detecting such domains is complex, and very often it involves complex allowlist or denylist management or SIEM integration with open-source TLS fingerprinting techniques. Many fingerprinting techniques, such as JARM and JA3, are used by threat hunters to determine domain classification, but with the increase in TLS similarity, particularly in CDNs, they are becoming less useful. The aim of this paper was to adapt and evolve open-source TLS fingerprinting techniques with increased features to enhance granularity and to produce a similarity-mapping system that would enable the tracking and detection of previously unknown malicious domains. This was achieved by enriching TLS fingerprints with HTTP header data and producing a fine-grain similarity visualisation that represented high-dimensional data using MinHash and Locality-Sensitive Hashing. Influence was taken from the chemistry domain, where the problem of high-dimensional similarity in chemical fingerprints is often encountered. An enriched fingerprint was produced, which was then visualised across three separate datasets. The results were analysed and evaluated, with 67 previously unknown malicious domains being detected based on their similarity to known malicious domains and nothing else. The similarity-mapping technique produced demonstrates definite promise in the arena of early detection of malware and phishing domains. Full article

Fine-grained object detection aims to accurately localize the object bounding box while identifying the specific model of the object, which is more challenging than conventional remote sensing object detection. Transformer-based object detector (DETR) can capture remote inter-feature dependencies by using attention, which is suitable for fine-grained object detection tasks. However, most existing DETR-like object detectors are not specifically optimized for remote sensing detection tasks. Therefore, we propose an oriented fine-grained object detection method based on transformers. First, we combine denoising training and angle coding to propose a baseline DETR-like object detector for oriented object detection. Next, we propose a new attention mechanism for extracting finer-grained features by constraining the angle of sampling points during the attentional process, ensuring that the sampling points are more evenly distributed across the object features. Then, we propose a multiscale fusion method based on bilinear pooling to obtain the enhanced query and initialize a more accurate object bounding box. Finally, we combine the localization accuracy of each query with its classification accuracy and propose a new classification loss to further enhance the high-quality queries. Evaluation results on the FAIR1M dataset show that our method achieves an average accuracy of 48.5856 mAP and the highest accuracy of 49.7352 mAP in object detection, outperforming other methods. Full article

Bryophytes, including liverworts, mosses, and hornworts, play an irreplaceable role in soil moisture retention, erosion prevention, and pollution monitoring. The precise identification of bryophyte species enhances our understanding and utilization of their ecological functions. However, their complex morphology and structural symmetry make identification difficult. Although deep learning improves classification efficiency, challenges remain due to limited datasets and the inadequate adaptation of existing methods to multi-scale features, causing poor performance in fine-grained multi-classification. Thus, we propose MOSSNet, a lightweight neural network for bryophyte feature detection. It has a four-stage architecture that efficiently extracts multi-scale features using a modular design with symmetry consideration in feature representation. At the input stage, the Convolutional Patch Embedding (CPE) module captures representative features through a two-layer convolutional structure. In each subsequent stage, Dual-Branch Multi-scale (DBMS) modules are employed, with one branch utilizing convolutional operations and the other utilizing the Dilated Convolution Enhanced Attention (DCEA) module for multi-scale feature fusion. The DBMS module extracts fine-grained and coarse-grained features by a weighted fusion of the outputs from two branches. Evaluating MOSSNet on the self-constructed dataset BryophyteFine reveals a Top-1 accuracy of 99.02% in classifying 26 bryophyte species, 7.13% higher than the best existing model, while using only 1.58 M parameters, 0.07 G FLOPs. Full article

Currently, there is no publicly available dataset for the classification of potato pest and disease-related queries. Moreover, traditional query classification models generally adopt a single maximum-pooling strategy when performing down-sampling operations. This mechanism only extracts the extreme value responses within the local receptive field, which leads to the degradation of fine-grained feature representation and significantly amplifies text noise. To address these issues, a dataset construction method based on prompt engineering is proposed, along with a question classification method utilizing a gated fusion–convolutional neural network (GF-CNN). By interacting with large language models, prompt words are used to generate potato disease and pest question templates and efficiently construct the Potato Pest and Disease Question Classification Dataset (PDPQCD) by batch importing named entities. The GF-CNN combines outputs from convolutional kernels of varying sizes, and after processing with max-pooling and average-pooling, a gating mechanism is employed to regulate the flow of information, thereby optimizing the text feature extraction process. Experiments using GF-CNN on the PDPQCD, Subj, and THUCNews datasets show F1 scores of 100.00%, 96.70%, and 93.55%, respectively, outperforming other models. The prompt engineering-based method provides a new paradigm for constructing question classification datasets, and the GF-CNN can also be extended for application in other domains. Full article

For fine-grained recognition, capturing distinguishable features and effectively utilizing local information play a key role, since the objects of recognition exhibit subtle differences in different subcategories. Finding subtle differences between subclasses is not straightforward. To address this problem, we propose a weakly supervised fine-grained classification network model with Local Diversity Guidance (LDGNet). We designed a Multi-Attention Semantic Fusion Module (MASF) to build multi-layer attention maps and channel–spatial interaction, which can effectively enhance the semantic representation of the attention maps. We also introduce a random selection strategy (RSS) that forces the network to learn more comprehensive and detailed information and more local features from the attention map by designing three feature extraction operations. Finally, both the attention map obtained by RSS and the feature map are employed for prediction through a fully connected layer. At the same time, a dataset of ancient towers is established, and our method is applied to ancient building recognition for practical applications of fine-grained image classification tasks in natural scenes. Extensive experiments conducted on four fine-grained datasets and explainable visualization demonstrate that the LDGNet can effectively enhance discriminative region localization and detailed feature acquisition for fine-grained objects, achieving competitive performance over other state-of-the-art algorithms. Full article

Currently, the demand for refined crop monitoring through remote sensing is increasing rapidly. Due to the similar spectral and morphological characteristics of different crops and vegetation, traditional methods often rely on deeper neural networks to extract meaningful features. However, deeper networks face a key challenge: while extracting deep features, they often lose some boundary details and small-plot characteristics, leading to inaccurate farmland boundary classifications. To address this issue, we propose the Detail and Deep Feature Multi-Branch Fusion Network for High-Resolution Farmland Remote-Sensing Segmentation (DFBNet). DFBNet introduces an new three-branch structure based on the traditional UNet. This structure enhances the detail of ground objects, deep features across multiple scales, and boundary features. As a result, DFBNet effectively preserves the overall characteristics of farmland plots while retaining fine-grained ground object details and ensuring boundary continuity. In our experiments, DFBNet was compared with five traditional methods and demonstrated significant improvements in overall accuracy and boundary segmentation. On the Hi-CNA dataset, DFBNet achieved 88.34% accuracy, 89.41% pixel accuracy, and an IoU of 78.75%. On the Netherlands Agricultural Land Dataset, it achieved 90.63% accuracy, 91.6% pixel accuracy, and an IoU of 83.67%. These results highlight DFBNet’s ability to accurately delineate farmland boundaries, offering robust support for agricultural yield estimation and precision farming decision-making. Full article

The rising prevalence of social media turns them into huge, rich repositories of human emotions. Understanding and categorizing human emotion from social media content is of fundamental importance for many reasons, such as improvement of user experience, monitoring of public sentiment, support for mental health, and enhancement of focused marketing strategies. However, social media text is often unstructured and ambiguous; hence, extracting meaningful emotional information is difficult. Thus, effective emotion classification needs advanced techniques. This article proposes a novel model, EmoBERTa-X, to enhance performance in multilabel emotion classification, particularly in informal and ambiguous social media texts. Attention mechanisms combined with ensemble learning, supported by preprocessing steps, help in avoiding issues such as class imbalance of the dataset, ambiguity in short texts, and the inherent complexities of multilabel classification. The experimental results on the GoEmotions dataset indicate that EmoBERTa-X has outperformed state-of-the-art models on fine-grained emotion-detection tasks in social media expressions with an accuracy increase of 4.32% over some popular approaches. Full article

Encrypted traffic classification poses significant challenges in network security due to the growing use of encryption protocols, which obscure packet payloads. This paper introduces a novel framework that leverages dual embedding mechanisms and Graph Neural Networks (GNNs) to model both temporal and spatial dependencies in traffic flows. By utilizing metadata features such as packet size, inter-arrival times, and protocol attributes, the framework achieves robust classification without relying on payload content. The proposed framework demonstrates an average classification accuracy of 96.7%, F1-score of 96.0%, and AUC-ROC of 97.9% across benchmark datasets, including ISCX VPN-nonVPN, QUIC, and USTC-TFC2016. These results mark an improvement of up to 8% in F1-score and 10% in AUC-ROC compared to state-of-the-art baselines. Extensive experiments validate the framework’s scalability and robustness, confirming its potential for real-world applications like intrusion detection and network monitoring. The integration of dual embedding mechanisms and GNNs allows for accurate fine-grained classification of encrypted traffic flows, addressing critical challenges in modern network security. Full article

Background/Objectives: Coma prognosis is challenging, as patient presentation can be misleading or uninformative when using behavioral assessments only. Event-related potentials have been shown to provide valuable information about a patient’s chance of survival and emergence from coma. Our prior work revealed that the mismatch negativity (MMN) in particular waxes and wanes across 24 h in some coma patients. This “cycling” aspect of the presence/absence of neurophysiological responses may require fine-grained tools to increase the chances of detecting levels of neural processing in coma. This study implements multivariate pattern analysis (MVPA) to automatically quantify patterns of neural discrimination between duration deviant and standard tones over time at the single-subject level in seventeen healthy controls and in three comatose patients. Methods: One EEG recording, containing up to five blocks of an auditory oddball paradigm, was performed in controls over a 12 h period. For patients, two EEG sessions were conducted 3 days apart for up to 24 h, denoted as day 0 and day 3, respectively. MVPA was performed using a support-vector machine classifier. Results: Healthy controls exhibited reliable discrimination or classification performance during the latency intervals associated with MMN and P3a components. Two patients showed some intervals with significant discrimination around the second half of day 0, and all had significant results on day 3. Conclusions: These findings suggest that decoding analyses can accurately classify neural responses at a single-subject level in healthy controls and provide evidence of small but significant changes in auditory discrimination over time in coma patients. Further research is needed to confirm whether this approach represents an improved technology for assessing cognitive processing in coma. Full article

Deep learning techniques have become the mainstream approach for fine-grained crop classification in unmanned aerial vehicle (UAV) remote sensing imagery. However, a significant challenge lies in the long-tailed distribution of crop samples. This imbalance causes neural networks to focus disproportionately on majority class features during training, leading to biased decision boundaries and weakening model performance. We designed a minority sample enhanced sampling (MES) method with the goal of addressing the performance limitations that are caused by class imbalance in many crop classification models. The main principle of MES is to relate the re-sampling probability of each class to the sample pixel frequency, thereby achieving intensive re-sampling of minority classes and balancing the training sample distribution. Meanwhile, during re-sampling, data augmentation is performed on the sampled images to improve the generalization. MES is simple to implement, is highly adaptable, and can serve as a general-purpose sampler for semantic segmentation tasks, functioning as a plug-and-play component within network models. To validate the applicability of MES, experiments were conducted on four classic semantic segmentation networks. The results showed that MES achieved mIoU improvements of +1.54%, +4.14%, +2.44%, and +7.08% on the Dali dataset and +2.36%, +0.86%, +4.26%, and +2.75% on the Barley Remote Sensing Dataset compared with the respective benchmark models. Additionally, our hyperparameter sensitivity analysis confirmed the stability and reliability of the method. MES mitigates the impact of class imbalance on network performance, which facilitates the practical application of deep learning in fine-grained crop classification. Full article

Effective leak detection and leak size identification are essential for maintaining the operational safety, integrity, and longevity of industrial pipelines. Traditional methods often suffer from high noise sensitivity, limited adaptability to non-stationary signals, and excessive computational costs, which limits their feasibility for real-time monitoring applications. This study presents a novel acoustic emission (AE)-based pipeline monitoring approach, integrating Empirical Wavelet Transform (EWT) for adaptive frequency decomposition with customized one-dimensional DenseNet architecture to achieve precise leak detection and size classification. The methodology begins with EWT-based signal segmentation, which isolates meaningful frequency bands to enhance leak-related feature extraction. To further improve signal quality, adaptive thresholding and denoising techniques are applied, filtering out low-amplitude noise while preserving critical diagnostic information. The denoised signals are processed using a DenseNet-based deep learning model, which combines convolutional layers and densely connected feature propagation to extract fine-grained temporal dependencies, ensuring the accurate classification of leak presence and severity. Experimental validation was conducted on real-world AE data collected under controlled leak and non-leak conditions at varying pressure levels. The proposed model achieved an exceptional leak detection accuracy of 99.76%, demonstrating its ability to reliably differentiate between normal operation and multiple leak severities. This method effectively reduces computational costs while maintaining robust performance across diverse operating environments. Full article

Identifying and classifying objects in aerial images are two significant and complex issues in computer vision. The fine-grained classification of objects in overhead images has become widespread in various real-world applications, due to recent advancements in high-resolution satellite and airborne imaging systems. The task is challenging, particularly in low-resource cases, due to the minor differences between classes and the significant differences within each class caused by the fine-grained nature. We introduce Classification of Objects for Fine-Grained Analysis (COFGA), a recently developed dataset for accurately categorizing objects in high-resolution aerial images. The COFGA dataset comprises 2104 images and 14,256 annotated objects across 37 distinct labels. This dataset offers superior spatial information compared to other publicly available datasets. The MAFAT Challenge is a task that utilizes COFGA to improve fine-grained classification methods. The baseline model achieved a mAP of 0.6. This cost was 60, whereas the most superior model achieved a score of 0.6271 by utilizing state-of-the-art ensemble techniques and specific preprocessing techniques. We offer solutions to address the difficulties in analyzing aerial images, particularly when annotated and imbalanced class data are scarce. The findings provide valuable insights into the detailed categorization of objects and have practical applications in urban planning, environmental assessment, and agricultural management. We discuss the constraints and potential future endeavors, specifically emphasizing the potential to integrate supplementary modalities and contextual information into aerial imagery analysis. Full article

This study explores land use classification in Trento using supervised learning techniques combined with call detail records (CDRs) as a proxy for human activity. Located in an alpine environment, Trento presents unique geographic challenges, including varied terrain and sparse network coverage, making it an ideal case for testing the robustness of supervised learning approaches. By analyzing spatiotemporal patterns in CDRs, we trained and evaluated several classification algorithms, including k-nearest neighbors (kNN), support vector machines (SVM), and random forests (RF), to map land use categories, such as home, work, and forest. A comparative analysis highlights the performance of each method, emphasizing the strengths of RF in capturing complex patterns, its good generalization ability, and the usage of kNN with different distance measures. Our supervised machine-learning approach outperforms unsupervised clustering techniques by capturing complex patterns and achieving higher accuracy. Results demonstrate the potential of CDRs for urban planning, offering a cost-effective approach for fine-grained land use monitoring with the particularities of Trento, as its landscape combines urban areas, agricultural fields, and forested regions, reflecting its alpine setting, in contrast with other metropolitan regions. Full article

As a pivotal area of research in the field of computer vision, the technology for food identification has become indispensable across diverse domains including dietary nutrition monitoring, intelligent service provision in restaurants, and ensuring quality control within the food industry. However, recognizing food images falls within the domain of Fine-Grained Visual Classification (FGVC), which presents challenges such as inter-class similarity, intra-class variability, and the complexity of capturing intricate local features. Researchers have primarily focused on deep information in deep convolutional neural networks for fine-grained visual classification, often neglecting shallow and detailed information. Taking these factors into account, we propose a Multi-level Attention Feature Fusion Network (MAF-Net). Specifically, we use feature maps generated by the Convolutional Neural Networks (CNNs) backbone network at different stages as inputs. We apply a self-attention mechanism to identify local features on these feature maps and then stack them together. The feature vectors obtained through the attention mechanism are then integrated with the original input to enhance data augmentation. Simultaneously, to capture as many local features as possible, we encourage multi-scale features to concentrate on distinct local regions at each stage by maximizing the Kullback-Leibler Divergence (KL-divergence) between the different stages. Additionally, we present a novel approach called subclass center loss (SCloss) to implement label smoothing, minimize intra-class feature distribution differences, and enhance the model’s generalization capability. Experiments conducted on three food image datasets—CETH Food-101, Vireo Food-172, and UEC Food-100—demonstrated the superiority of the proposed model. The model achieved Top-1 accuracies of 90.22%, 89.86%, and 90.61% on CETH Food-101, Vireo Food-172, and UEC Food-100, respectively. Notably, our method not only outperformed other methods in terms of the Top-5 accuracy of Vireo Food-172 but also achieved the highest performance in the Top-1 accuracies of UEC Food-100. Full article

This paper proposes a novel blind channel estimation method using convolutional neural network (CNN)-based resource grouping. The traditional K-means-based blind channel estimation scheme suffers limitations in reflecting fine-grained channel variations in both the time and frequency domains. To address these limitations, we propose dynamic resource grouping based on CNN architecture utilizing a two-step learning process that adapts to various channel conditions. The first step of the proposed method identifies the optimal number of subcarriers for each channel condition, providing a foundation for the second step. The second step adjusts the number of orthogonal frequency division multiplexing (OFDM) symbols, a parameter for determining the proposed pattern in the time domain, to adapt to dynamic channel variations. Simulation results demonstrate that the proposed CNN-based blind channel estimation method achieves high channel estimation accuracy across various signal-to-noise ratio (SNR) levels, attaining the highest accuracy of 82.5% at an SNR of 10 dB. Even when classification accuracy is relatively low, the CNN effectively mitigates signal distortion, delivering superior performance compared to conventional methods in terms of mean squared error (MSE) across diverse channel conditions. Notably, the proposed method maintains robust performance under high-mobility scenarios and severe channel variations. Full article