Search Results (53)

Deformation monitoring of roadway surrounding rock is the key link to ensure the safety production of the coal mine. The traditional monitoring method can only obtain the displacement information of discrete measuring points, and it is difficult to fully reflect the spatial distribution characteristics and evolution law of surrounding rock deformation. Based on the engineering background of the extra-thick coal seam roadway in the Yushupo Coal Mine, Shanxi Province, China, this study proposes a set of full-space deformation monitoring methods for roadway surrounding rock based on explosion-proof mobile 3D laser scanning technology. Firstly, a hierarchical denoising method based on improved statistical filtering is established. The quality of point cloud data is effectively improved by region clipping, a connectivity analysis guided by multi-dimensional geometric features and adaptive density threshold three-level processing strategy. Secondly, a hierarchical point cloud registration method combining physical anchor geometric constraints and deep learning patch guided matching is proposed to reduce the registration error to millimeter level. Finally, the deformation evaluation of surrounding rock is carried out by combining the overall deformation identification with the quantitative analysis of local section slices. The engineering application results show that the deformation of the roadway floor is the most significant during the monitoring period, the maximum deformation is 90.0 mm, and the average deformation is 46.9 mm. The maximum deformation of the roof is 35.0 mm, and the convergence of both sides is asymmetric. Compared with the total station, the results show that the maximum displacement error in each direction does not exceed 5 mm, and the standard deviation is within 1.3 mm, which meets the engineering accuracy requirements of coal mine roadway deformation monitoring. This study provides a complete technical scheme for panoramic and high-precision monitoring of surrounding rock deformation in coal mine roadway. Full article

Differentiating AI-generated, real, or imitated artworks is becoming a tedious and computationally challenging problem in digital art analysis. AI-generated art has become nearly indistinguishable from human-made works, posing a significant threat to copyrighted content. This content is appearing on online platforms, at exhibitions, and in commercial galleries, thereby escalating the risk of copyright infringement. This sudden increase in generative images raises concerns like authenticity, intellectual property, and the preservation of cultural heritage. Without an automated, comprehensible system to determine whether an artwork has been AI-generated, authentic (real), or imitated, artists are prone to the reduction of their unique works. Institutions also struggle to curate and safeguard authentic pieces. As the variety of generative models continues to grow, it becomes a cultural necessity to build a robust, efficient, and transparent framework for determining whether a piece of art or an artist is involved in potential copyright infringement. To address these challenges, we introduce ArtUnmasked, a practical and interpretable framework capable of (i) efficiently distinguishing AI-generated artworks from real ones using a lightweight Spectral Artifact Identification (SPAI), (ii) a TagMatch-based artist filtering module for stylistic attribution, and (iii) a DINOv3–CLIP similarity module with patch-level correspondence that leverages the one-shot generalization ability of modern vision transformers to determine whether an artwork is authentic or imitated. We also created a custom dataset of ∼24K imitated artworks to complement our evaluation and support future research. The complete implementation is available in our GitHub repository. Full article

Wireless Body Area Networks (WBANs) enable real-time health monitoring essential for timely clinical intervention, yet their performance is frequently hindered by sensor degradation, noise interference, and strict low-latency constraints in resource-limited environments. Conventional preprocessing approaches indiscriminately reprocess all incoming data, including uncorrupted samples, thereby increasing computational overhead, introducing latency, and potentially distorting valid physiological trends. This study introduces a unified real-time monitoring framework tailored for WBAN systems. The key contributions include: (1) an adaptively gated multi-stage preprocessing pipeline that selectively restores corrupted samples while preserving clean data, (2) an overlap-aware sliding-window mechanism enabling low-latency operation, and (3) a clinically informed risk assessment strategy for early-warning support. By avoiding unnecessary modification of intact signals, the framework maintains physiological integrity while substantially improving reconstruction and predictive reliability. Across multiple vital signs, the proposed approach achieves substantial reconstruction gains, with Mean Squared Error (MSE) reductions ranging from 53% to 67% under strong degradation conditions. An adaptive ARIMA-based forecasting layer captures short-term physiological dynamics with directional accuracies of approximately 65–70% for one-step (10 s) ahead prediction. Early-warning behavior is intentionally conservative, prioritizing false alarm suppression over aggressive alerting. Per-signal evaluation reveals high sensitivity for blood pressure signals, whereas glucose and certain high-variability modalities exhibit conservative sensitivity under modality-specific thresholds. Importantly, the aggregated multi-modal risk decision achieves strong overall system-level performance, with sensitivity and specificity of 0.89 and 0.92, respectively. Overall, the proposed framework establishes a robust, low-latency, and computationally efficient foundation for dependable physiological monitoring in WBAN environments, leveraging selective processing to optimize both resource utilization and clinical reliability. Full article

In order to achieve better accuracy, modern models have become increasingly large, leading to an exponential increase in computational load, making it challenging to apply them to edge computing. Binary neural networks (BNNs) are models that quantize the filter weights and activations to 1-bit. These models are highly suitable for small chips like advanced RISC machines (ARMs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs) and other edge computing devices. To design a model that is more friendly to edge computing devices, it is crucial to reduce the floating-point operations (FLOPs). Batch normalization (BN) is an essential tool for binary neural networks; however, when convolution layers are quantized to 1-bit, the floating-point computation cost of BN layers becomes significantly high. This paper aims to reduce the floating-point operations by removing the BN layers from the model and introducing the scaled weight standardization convolution (WS-Conv) method to avoid the significant accuracy drop caused by the absence of BN layers, and to enhance the model performance through a series of optimizations, adaptive gradient clipping (AGC) and knowledge distillation (KD). Specifically, our model maintains a competitive computational cost and accuracy, even without BN layers. Furthermore, by incorporating a series of training methods, the model’s accuracy on CIFAR-100 is 0.6% higher than the baseline model, fractional activation BNN (FracBNN), while the total computational load is only 46% of the baseline model. With unchanged binary operations (BOPs), the FLOPs are reduced to nearly zero, making it more suitable for embedded platforms like FPGAs or other edge computers. Full article

The safe and stable operation of power systems and other dynamic systems relies on accurate perception of their dynamic processes. Voltage, current, and other measurement signals carry critical information about the system’s state. However, under conditions such as equipment damage, aging, and non-ideal operational conditions of devices under test, over-range phenomena may occur, leading to biased estimation issues in adaptive filters. To address this problem, this paper proposes a variable-parameter subband adaptive filtering algorithm with signal clipping distortion awareness. The algorithm first uses the Expectation-Maximization (EM) process to achieve high-fidelity restoration of damaged signals. Then, by integrating an intelligent steady-state detector and a dual-mode control mechanism, the adaptive filter can adjust key parameters such as step-size, forgetting factor, and regularization parameter based on state perception results. Finally, theoretical analysis proves the unbiased nature of the proposed method. Validation using real-world data from a high-penetration renewable energy power system shows that the algorithm achieves fast tracking during transient events and provides high-precision estimation during steady-state operation, offering an effective solution for real-time, high-accuracy processing of dynamic measurement data in power systems. Full article

This essay analyzes Chinese theater director Li Jianjun’s play The Metamorphosis (Bianxingji) under Pierre Bourdieu’s idea of cultural capital. Reimagining Kafka’s Gregor Samsa as a package delivery rider in contemporary China, the play stages a failed narrative of storytelling through live-feed video and informs the impossibility of representing the riders’ labor resulting from the fragmented realities of postsocialist China. It thus challenges the middle-class writers’ efforts to transform delivery riders’ labor into a form of cultural capital and confronts the audience with the exploitative potential of their spectating position. Ultimately, the impossibility of representation staged by the play articulates the inequality and stratification that structures China at the postsocialist moment. The play interweaves three layers of narratives: Geligaoer’s family’s various forms of labor, documentary clips of real-life delivery riders in contemporary China, and an interplay between an external voice and the performers’ bodily movements. This layered narrative foregrounds the artificiality of storytelling and can be situated within the ongoing discussions in the recent decade in China, in which scholars and journalists attempt to secure their middle-class identities by transforming the riders’ laboring condition into a form of cultural capital. In contrast, the play stages the failure of the narrative of storytelling through a projection screen and live-feed cameras to inform the impossibility of a transparent representation of the delivery riders. By excluding the audience from the riders’ subjectivity, the play blocks the audience’s identification with the latter. Through the heavy beauty filter projected on the screen as a metaphor, the play confronts the audience with their own middle-class identity and warns them of the violence inherent in their spectating position. Full article

Despite its increasing use in veterinary rehabilitation, practical constraints—such as skin preparation and single-use electrodes—limit the wider adoption of surface electromyography (sEMG). Having conventional pre-gelled Ag/AgCl electrodes as reference, we made a pioneering comparison of the performance of reusable soft polymeric dry electrodes for recording paraspinal muscle activity in dogs during treadmill walking. Twelve clinically healthy Dachshunds from both genders were evaluated under two conditions, namely: (i) dry electrodes on untrimmed hair; and (ii) pre-gelled electrodes after trichotomy. Signals were acquired from the longissimus dorsi muscle at 1 kHz, processed with standardized filtering and rectification, and analyzed in both time and frequency domains. Dry electrodes yielded higher amplitude and Root Mean Square (RMS) values, but slightly lower power spectral density metrics when compared to pre-gelled electrodes. Nevertheless, frequency-domain results were broadly comparable between configurations. Dry electrodes reduce the preparation time, avoid hair clipping, and allow reusability without major signal degradation. While pre-gelled electrodes may still offer marginally superior stability during movement, our results suggest that soft polymeric dry electrodes present a feasible, less invasive, and more sustainable alternative for canine sEMG. These findings support further validation of dry electrodes in clinical populations, particularly for neuromuscular assessment in intervertebral disk disease. Full article

Diagnosing dementia and recognizing substantial cognitive decline are challenging tasks. Thus, the objective of this study was to classify electroencephalograms (EEGs) recorded during a working memory task in 15 patients with mild cognitive impairment (MCogImp), 5 patients with vascular dementia (VasD), and 15 healthy controls (NC). Before creating spectrogram pictures from the EEG dataset, the data were subjected to preprocessing, which included preprocessing using conventional filters and the discrete wavelet transformation. The convolutional neural network (CNN) MobileNetV2 was employed in our investigation to identify features and assess the severity of dementia. The features were extracted from five layers of the MobileNetV2 CNN architecture—convolutional layers (‘Conv-1’), batch normalization (‘Conv-1-bn’), clipped ReLU (‘out-relu’), 2D Global Average Pooling (‘global-average-pooling2d1’), and fully connected (‘Logits’) layers. This was carried out to find the efficient features layer for dementia severity from EEGs. Feature extraction from MobileNetV2’s five layers was carried out using a decision tree (DT) and k-nearest neighbor (KNN) machine learning (ML) classifier, in conjunction with a MobileNetV2 deep learning (DL) network. The study’s findings show that the DT classifier performed best using features derived from MobileNetV2 with the 2D Global Average Pooling (global-average-pooling2d-1) layer, achieving an accuracy score of 95.9%. Second place went to the characteristics of the fully connected (Logits) layer, which achieved a score of 95.3%. The findings of this study endorse the utilization of deep processing algorithms, offering a viable approach for improving early dementia identification with high precision, hence facilitating the differentiation among NC individuals, VasD patients, and MCogImp patients. Full article

3D Multi-Object Tracking (3D MOT) is a critical task in autonomous systems, where accurate and robust tracking of multiple objects in dynamic environments is essential. Traditional approaches primarily rely on visual or geometric features, often neglecting the rich semantic information available in textual modalities. In this paper, we propose Text-Guided 3D Multi-Object Tracking (TG3MOT), a novel framework that incorporates Vision-Language Models (VLMs) into the YONTD architecture to improve 3D MOT performance. Our framework leverages RegionCLIP, a multimodal open-vocabulary detector, to achieve fine-grained alignment between image regions and textual concepts, enabling the incorporation of semantic information into the tracking process. To address challenges such as occlusion, blurring, and ambiguous object appearances, we introduce the Target Semantic Matching Module (TSM), which quantifies the uncertainty of semantic alignment and filters out unreliable regions. Additionally, we propose the 3D Feature Exponential Moving Average Module (3D F-EMA) to incorporate temporal information, improving robustness in noisy or occluded scenarios. Furthermore, the Gaussian Confidence Fusion Module (GCF) is introduced to weight historical trajectory confidences based on temporal proximity, enhancing the accuracy of trajectory management. We evaluate our framework on the KITTI dataset and compare it with the YONTD baseline. Extensive experiments demonstrate that although the overall HOTA gain of TG3MOT is modest (+0.64%), our method achieves substantial improvements in association accuracy (+0.83%) and significantly reduces ID switches (−16.7%). These improvements are particularly valuable in real-world autonomous driving scenarios, where maintaining consistent trajectories under occlusion and ambiguous appearances is crucial for downstream tasks such as trajectory prediction and motion planning. The code will be made publicly available. Full article

With the development of satellite technology, remote sensing images have become increasingly accessible, making multi-modal remote sensing retrieval increasingly important. However, most existing methods rely on global visual and textual features to compute similarity, ignoring the positional correspondence between image regions and textual descriptions. To address this issue, we propose a novel cross-modal retrieval model named PR-CLIP, which leverages a cross-modal positional information reconstruction task to learn position-aware correlations between modalities. Specifically, PR-CLIP first uses a cross-modal positional information extraction module to extract the complementary features between images and texts. Then, the unimodal positional information filtering module filters out the complementary information from the unimodal features to generate embeddings for reconstruction. Finally, the cross-modal positional information reconstruction module reconstructs the unimodal embeddings of the images and texts based on the complete embeddings of the opposite modality, guided by a cross-modal positional consistency loss to ensure reconstruction quality. During the inference stage of retrieval, PR-CLIP directly calculates the similarity between the unimodal features without executing the modules of the reconstruction task. By combining the advantages of dual-stream and single-stream models, PR-CLIP achieves a good balance between performance and efficiency. Extensive experiments on multiple public datasets demonstrated the effectiveness of PR-CLIP. Full article

Understanding the feeding ecology and habitat use of vulnerable shark species is crucial for effective conservation. This study focuses on two large filter-feeding sharks, the megamouth shark (Megachasma pelagios) and whale shark (Rhincodon typus), in Northwestern Pacific waters. Stable isotope analysis (δ¹³C and δ¹⁵N) was conducted on white muscle samples (n = 91) of M. pelagios and fin clips (n = 90) of R. typus, collected via large-mesh drift nets and set nets in Taiwanese waters. In this study, we investigated feeding strategies, ontogenetic dietary shifts, habitat use, and isotopic niche variation in both species. For R. typus, the observed positive correlation between δ¹³C and δ¹⁵N supports the previously proposed active suction filter feeding, as well as implying both a diet with an increasing proportion of higher trophic level prey and an ontogenetic shift. In contrast, M. pelagios displayed a negative correlation, consistent with a previous study associating such patterns with primary or secondary consumers, further aligning with its reported planktonic prey dominance. Both species had increasing δ¹³C with growth, signifying a shift to nutrient-rich habitats. Only R. typus exhibited ontogenetic diet changes (δ¹⁵N). SIBER (Stable Isotope Bayesian Ellipses in R) analysis revealed distinct feeding strategies and habitat use between the two species, potential sexual segregation, and wider isotopic niche widths for males in both species. The findings underscore the importance of considering species-specific behaviors and sex-based differences in conservation strategies. Full article

Online video platforms have enabled unprecedented access to diverse content, but minors and other vulnerable viewers can also be exposed to highly graphic or violent materials. This study addresses the need for a nuanced method of filtering gore by developing a segmentation-based approach that selectively blurs blood. We recruited 37 participants to watch both blurred and unblurred versions of five gory video clips. Eye-based physiological and gaze data, including eye openness ratio, blink frequency, and eye fixations, were recorded via a webcam and eye tracker. Our results demonstrate that partial blood blurring substantially lowers perceived gore in more brutal scenes. Additionally, participants exhibited distinctive physiological reactions when viewing clips with higher gore, such as decreased eye openness and more frequent blinking. Notably, individuals with a stronger fear of blood showed an even greater tendency to blink, suggesting that personal sensitivities shape responses to graphic content. These findings highlight the potential of segmentation-based blurring as a balanced content moderation strategy, reducing distress without fully eliminating narrative details. By allowing users to remain informed while minimizing discomfort, this approach could prove valuable for video streaming services seeking to accommodate diverse viewer preferences and safeguard vulnerable audiences. Full article

Filtered orthogonal frequency division multiplexing (F-OFDM), employed in visible light communication (VLC) systems, has been considered a promising technique for overcoming OFDM’s large out-of-band emissions and thus reducing bandwidth efficiency. However, due to Hermitian symmetry (HS) imposition, a challenge in VLC involves increasing power consumption and doubling inverse fast Fourier transform IFFT/FFT length. This paper introduces the non-Hermitian symmetry (NHS) Flip-F-OFDM technique to enhance bandwidth efficiency, reduce the peak–average-power ratio (PAPR), and lower system complexity. Compared to the traditional HS-based Flip-F-OFDM method, the proposed method achieves around 50% reduced system complexity and prevents the PAPR from increasing. Therefore, the proposed method offers more resource-saving and power efficiency than traditional Flip-F-OFDM. Then, the proposed scheme is assessed with HS-free Flip-OFDM, asymmetrically clipped optical (ACO)-OFDM, and direct-current bias optical (DCO)-OFDM. Concerning bandwidth efficiency, the proposed method shows better spectral efficiency than HS-free Flip-OFDM, ACO-OFDM, and DCO-OFDM. Full article

Boundary contour determination during seedling image segmentation is critical for accurate object detection and morphological characterization in agricultural machine vision systems. The traditional manual annotation for segmentation is labor-intensive, time-consuming, and prone to errors, especially in controlled environments with complex backgrounds. These errors can affect the accuracy of detecting phenotypic traits, like shape, size, and width. To address these issues, this study introduced a method that integrated image features and a support vector machine (SVM) to improve boundary contour determination during segmentation, enabling real-time detection and monitoring. Seedling images (pepper, tomato, cucumber, and watermelon) were captured under various lighting conditions to enhance object–background differentiation. Histogram equalization and noise reduction filters (median and Gaussian) were applied to minimize the illumination effects. The peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM) were used to select the clip limit for histogram equalization. The images were analyzed across 18 different color spaces to extract the color features, and six texture features were derived using the gray-level co-occurrence matrix (GLCM) method. To reduce feature overlap, sequential feature selection (SFS) was applied, and the SVM was used for object segmentation. The SVM model achieved 73% segmentation accuracy without SFS and 98% with SFS. Segmentation accuracy for the different seedlings ranged from 81% to 98%, with a low boundary misclassification rate between 0.011 and 0.019. The correlation between the actual and segmented contour areas was strong, with an R² up to 0.9887. The segmented boundary contour files were converted into annotation files to train a YOLOv8 model, which achieved a precision ranging from 96% to 98.5% and a recall ranging from 96% to 98%. This approach enhanced the segmentation accuracy, reduced manual annotation, and improved the agricultural monitoring systems for plant health management. The future direction involves integrating this system with advanced methods to address overlapping image segmentation challenges, further enhancing the real-time seedling monitoring and optimizing crop management and productivity. Full article

Background: Emotions significantly influence decision-making, social interactions, and medical outcomes. Leveraging emotion recognition through Electroencephalography (EEG) signals offers potential advancements in personalized medicine, adaptive technologies, and mental health diagnostics. This study aimed to evaluate the performance of three neural network architectures—ShallowFBCSPNet, Deep4Net, and EEGNetv4—for emotion classification using the SEED-V dataset. Methods: The SEED-V dataset comprises EEG recordings from 16 individuals exposed to 15 emotion-eliciting video clips per session, targeting happiness, sadness, disgust, neutrality, and fear. EEG data were preprocessed with a bandpass filter, segmented by emotional episodes, and split into training (80%) and testing (20%) sets. Three neural networks were trained and evaluated to classify emotions from the EEG signals. Results: ShallowFBCSPNet achieved the highest accuracy at 39.13%, followed by Deep4Net (38.26%) and EEGNetv4 (25.22%). However, significant misclassification issues were observed, such as EEGNetv4 predicting all instances as “Disgust” or “Neutral” depending on the configuration. Compared to state-of-the-art methods, such as ResNet18 combined with differential entropy, which achieved 95.61% accuracy on the same dataset, the tested models demonstrated substantial limitations. Conclusions: Our results highlight the challenges of generalizing across emotional states using raw EEG signals, emphasizing the need for advanced preprocessing and feature-extraction techniques. Despite these limitations, this study provides valuable insights into the potential and constraints of neural networks for EEG-based emotion recognition, paving the way for future advancements in the field. Full article