Search Results (6,825)

Cardiovascular diseases (CVDs), which remain globally one of the most common causes of death, are usually diagnosed based on the electrocardiogram (ECG) signal. To support human experts, modern deep-learning models are used for CVD classification problems as an early warning. This article proposes a novel multi-branch architecture focused on processing various modalities of the ECG signal in parallel branches, replacing typical single-input architectures. Each branch is given separate input in the form of the raw signal, domain knowledge, the wavelet transform of the signal, or the signal with drift removed. The proposed method is based on deep-learning core models that can incorporate various modern neural networks. It was thoroughly tested on N-BEATS, LSTM, and GRU neural networks. The proposed architecture allows the retention of the speed of the neural network. At the same time, the combination of independently computed branches improves model performance, which finally exceeds the performance obtained by classical single-branch architectures. Full article

Histone post-translational modifications (PTMs) have emerged as promising epigenetic biomarkers with increasing forensic relevance. Unlike conventional genetic markers such as short tandem repeats (STRs), histone modifications can offer additional layers of biological information, capturing individual-specific regulatory states and remaining detectable even in degraded forensic samples. This review highlights recent advances in understanding histone PTMs in forensic contexts, focusing on three key domains: analysis of degraded biological evidence, differentiation of monozygotic (MZ) twins, and postmortem interval (PMI) estimation. We summarize experimental findings from human cadavers, animal models, and typical forensic samples including bone, blood, and muscle, illustrating the stability and diagnostic potential of marks such as H3K4me3, H3K27me3, and γ-H2AX. Emerging technologies including CUT&Tag, MALDI imaging, and nanopore-based sequencing offer novel opportunities to profile histone modifications at high resolution and low input. Despite technical challenges, these findings support the feasibility of histone-based biomarkers as complementary tools for forensic identification and temporal analysis. Future work should prioritize methodological standardization, inter-laboratory validation, and integration into forensic workflows. However, the forensic applicability of these modifications remains largely unvalidated, and further studies are required to assess their reliability in casework contexts. Full article

This paper addresses the core contradiction in fault diagnosis of gearboxes in heavy-duty equipment, where it is challenging to achieve both lightweight and robustness in dynamic industrial environments. Current diagnostic algorithms often struggle with balancing computational efficiency and diagnostic accuracy, particularly in noisy and variable operating conditions. Many existing methods either rely on complex architectures that are computationally expensive or oversimplified models that lack robustness to environmental interference. A novel, lightweight, and robust diagnostic network, YConvFormer, is proposed. Firstly, a time–frequency joint input channel is introduced, which integrates time-domain waveforms and frequency-domain spectrums at the input layer. It incorporates an Efficient Channel Attention mechanism with dynamic weighting to filter noise in specific frequency bands, suppressing high-frequency noise and enhancing the complementary relationship between time–frequency features. Secondly, an axial-enhanced broadcast attention mechanism is proposed. It models long-range temporal dependencies through spatial axial modeling, expanding the receptive field of shock features, while channel axial reinforcement strengthens the interaction of harmonics across frequency bands. This mechanism refines temporal modeling with minimal computation. Finally, the YConvFormer lightweight architecture is proposed, which combines shallow feature processing with global–local modeling, significantly reducing computational load. The experimental results on the XJTU and SEU gearbox datasets show that the proposed method improves the average accuracy by 6.55% and 19.58%, respectively, compared to the best baseline model, LiteFormer. Full article

The ship waterjet propulsion system is a crucial power unit for high-performance vessels, and the operational state of its core component, the waterjet pump, is directly related to navigation safety and mission reliability. To enhance the intelligence and accuracy of pump fault diagnosis, this paper proposes a novel diagnostic framework that integrates a supervised autoencoder (SAE) with a large language model (LLM). This framework first employs an SAE to perform task-oriented feature learning on raw vibration signals collected from the pump’s guide vane casing. By jointly optimizing reconstruction and classification losses, the SAE extracts deep features that both represent the original signal information and exhibit high discriminability for different fault classes. Subsequently, the extracted feature vectors are converted into text sequences and fed into an LLM. Leveraging the powerful sequential information processing and generalization capabilities of LLM, end-to-end fault classification is achieved through parameter-efficient fine-tuning. This approach aims to avoid the traditional dependence on manually extracted time-domain and frequency-domain features, instead guiding the feature extraction process via supervised learning to make it more task-specific. To validate the effectiveness of the proposed method, we compare it with a baseline approach that uses manually extracted features. In two experimental scenarios, direct diagnosis with full data and transfer diagnosis under limited-data, cross-condition settings, the proposed method significantly outperforms the baseline in diagnostic accuracy. It demonstrates excellent performance in automated feature extraction, diagnostic precision, and small-sample data adaptability, offering new insights for the application of large-model techniques in critical equipment health management. Full article

The increasing complexity of real-world engineering problems, ranging from manufacturing scheduling to resource optimization in smart grids, has driven demand for adaptive and high-performing heuristic methods. Automatic Heuristic Design (AHD) and neural-enhanced metaheuristics have shown promise in automating strategy development, but often suffer from limited flexibility and scalability due to static operator libraries or high retraining costs. Recently, Large Language Models (LLMs) have emerged as a powerful alternative for exploring and evolving heuristics through natural language and program synthesis. This paper proposes a novel LLM-based memetic framework that synergizes LLM-driven exploration with domain-specific local refinement and memory-aware reflection, enabling a dynamic balance between heuristic creativity and effectiveness. In the experiments, the developed framework outperforms other LLM-based state-of-the-art approaches across the designed AGV-drone scheduling scenario and two benchmark combinatorial problems. The findings suggest that LLMs can serve not only as general-purpose optimizers but also as interpretable heuristic generators that adapt efficiently to complex and heterogeneous domains. Full article

Vehicular ad hoc networks (VANETs) are a critical aspect of intelligent transportation systems, improving safety and comfort for drivers. These networks enhance the driving experience by offering timely information vital for safety and comfort. Yet, VANETs come with their own set of challenges concerning security, privacy, and design reliability. Traditionally, vehicle authentication occurs every time a vehicle enters the domain of the roadside unit (RSU). In our study, we suggest that authentication should take place only when a vehicle has not covered a set distance, increasing system efficiency. The rise of the Internet of Things (IoT) has seen an upsurge in the use of IoT devices across various fields, including smart cities, healthcare, and vehicular IoT. These devices, while gathering environmental data and networking, often face reliability issues without a trusted intermediary. Our study delves deep into implementing Teegraph in VANETs to enhance authentication. Given the integral role of VANETs in Intelligent Transportation Systems and their inherent challenges, we turn to Hashgraph—an alternative to blockchain. Hashgraph offers a decentralized, secure, and trustworthy database. We introduce an efficient authentication system, which triggers only when a vehicle has not traversed a set distance, optimizing system efficiency. Moreover, we shed light on the indispensable role Hashgraph can occupy in the rapidly expanding IoT landscape. Lastly, we present Teegraph, a novel Hashgraph-based technology, as a superior alternative to blockchain, ensuring a streamlined, scalable authentication solution. Our approach leverages the logical key hierarchy (LKH) and packet update keys to ensure data privacy and integrity in vehicular networks. Full article

Anomaly detection in industrial imaging is critical for ensuring quality and reliability in automated manufacturing processes. While recently several methods have been reported in the literature that have demonstrated impressive detection performance on standard benchmarks, they necessarily rely on computationally intensive CNN architectures and post-processing techniques, necessitating access to high-end GPU hardware and limiting practical deployment in resource-constrained settings. In this study, we introduce a novel anomaly detection framework that leverages feature maps from a lightweight convolutional neural network (CNN) backbone, MobileNetV2, and cascaded detection to achieve notable accuracy as well as computational efficiency. The core of our method consists of two main components. First is a PCA-based anomaly detection module that specifically exploits near-zero variance features. Contrary to traditional PCA methods, which tend to focus on the high-variance directions that encapsulate the dominant patterns in normal data, our approach demonstrates that the lower variance directions (which are typically ignored) form an approximate null space where normal samples project near zero. However, the anomalous samples, due to their inherent deviations from the norm, lead to projections with significantly higher magnitudes in this space. This insight not only enhances sensitivity to true anomalies but also reduces computational complexity by eliminating the need for operations such as matrix inversion or the calculation of Mahalanobis distances for correlated features otherwise needed when normal behavior is modeled as Gaussian distribution. Second, our framework consists of a cascaded multi-stage decision process. Instead of combining features across layers, we treat the local features extracted from each layer as independent stages within a cascade. This cascading mechanism not only simplifies the computations at each stage by quickly eliminating clear cases but also progressively refines the anomaly decision, leading to enhanced overall accuracy. Experimental evaluations on MVTec and VisA benchmark datasets demonstrate that our proposed approach achieves superior anomaly detection performance (99.4% and 91.7% AUROC respectively) while maintaining a lower computational overhead compared to other methods. This framework provides a compelling solution for practical anomaly detection challenges in diverse application domains where competitive accuracy is needed at the expense of minimal hardware resources. Full article

This paper presents WaveCORAL-DCCA, an unsupervised domain adaptation (UDA) framework specifically developed to address data distribution shifts and operational variabilities (OVs) in rotor fault diagnosis. The framework introduces the novel integration of discrete wavelet transformation for robust time–frequency feature extraction and an enhanced deep canonical correlation analysis (DCCA) network with correlation alignment (CORAL) loss for superior domain-invariant representation learning. This combination enables more effective alignment of source and target feature distributions without requiring any labelled data from the target domain. Comprehensive validation on both experimental and numerically simulated rotor datasets across three health conditions—i.e., normal, unbalanced, and misaligned—demonstrates that WaveCORAL-DCCA achieves an average diagnostic accuracy of 95%. Notably, it outperforms established UDA benchmarks by at least 5–17% in cross-domain scenarios. These results confirm that WaveCORAL-DCCA provides robust generalisation across machines, fault severities, and operational conditions, even with scarce target domain samples, offering a scalable and practical solution for industrial rotor fault diagnosis. Full article

Retinal vessel segmentation in fundus images is critical for diagnosing microvascular and ophthalmologic diseases. However, the task remains challenging due to significant vessel width variation and low vessel-to-background contrast. To address these limitations, we propose WDM-UNet, a novel spatial-wavelet dual-domain fusion architecture that integrates spatial and wavelet-domain representations to simultaneously enhance the local detail and global context. The encoder combines a Deformable Convolution Encoder (DCE), which adaptively models complex vascular structures through dynamic receptive fields, and a Wavelet Convolution Encoder (WCE), which captures the semantic and structural contexts through low-frequency components and hierarchical wavelet convolution. These features are further refined by a Gated Fusion Transformer (GFT), which employs gated attention to enhance multi-scale feature integration. In the decoder, depthwise separable convolutions are used to reduce the computational overhead without compromising the representational capacity. To preserve fine structural details and facilitate contextual information flow across layers, the model incorporates skip connections with a hierarchical fusion strategy, enabling the effective integration of shallow and deep features. We evaluated WDM-UNet in three public datasets: DRIVE, STARE, and CHASE_DB1. The quantitative evaluations demonstrate that WDM-UNet consistently outperforms state-of-the-art methods, achieving 96.92% accuracy, 83.61% sensitivity, and an 82.87% F1-score in the DRIVE dataset, with superior performance across all the benchmark datasets in both segmentation accuracy and robustness, particularly in complex vascular scenarios. Full article

Building performance simulation is crucial for the design and optimization of sustainable buildings. However, the increasing complexity of building systems necessitates advanced modeling techniques capable of handling multi-domain interactions. This paper presents a novel application of the bond graph (BG) methodology to simulate and analyze the thermal behavior of an integrated trigeneration system within an experimental test cell. Unlike conventional simulation approaches, the BG framework enables unified modeling of thermal and hydraulic subsystems, offering a physically consistent and energy-based representation of system dynamics. The study investigates the system’s performance under both dynamic and steady-state conditions across two distinct climatic periods. Validation against experimental data reveals strong agreement between measured and simulated temperatures in heating and cooling scenarios, with minimal deviations. This confirms the method’s reliability and its capacity to capture transient thermal behaviors. The results also demonstrate the BG model’s effectiveness in supporting predictive control strategies, optimizing energy efficiency, and maintaining thermal comfort. By integrating hydraulic circuits and thermal exchange processes within a single modeling framework, this work highlights the potential of bond graphs as a robust and scalable tool for advanced building performance simulation. Full article

With the advancement of low-carbon and sustainable development initiatives, electric scooters, recognized as essential transportation tools and leisure products, have gained significant popularity, particularly among young people. However, the current electric scooter market is plagued by severe product similarity. Once the initial novelty fades for users, the usage frequency declines, resulting in considerable resource wastage. This research collected user needs via surveys and employed the KJ method (affinity diagram) to synthesize fragmented insights into cohesive thematic clusters. Subsequently, a hierarchical needs model for electric scooters was constructed using analytical hierarchy process (AHP) principles, enabling systematic prioritization of user requirements through multi-criteria evaluation. By establishing a house of quality (HoQ), user needs were transformed into technical characteristics of electric scooter products, and the corresponding weights were calculated. After analyzing the positive and negative correlation degrees of the technical characteristic indicators, it was found that there are technical contradictions between functional zoning and compact size, lightweight design and material structure, and smart interaction and usability. Then, based on the theory of inventive problem solving (TRIZ), the contradictions were classified, and corresponding problem-solving principles were identified to achieve a multi-functional innovative design for electric scooters. This research, leveraging a systematic industrial design analysis framework, identified critical pain points among electric scooter users, established hierarchical user needs through priority ranking, and improved product lifecycle sustainability. It offers novel methodologies and perspectives for advancing theoretical research and design practices in the electric scooter domain. Full article

Zinc finger proteins are frequently implicated in a wide range of neurodevelopmental disorders (NDDs). In this study, we report a case of mild intellectual disability (ID), global developmental delay (GDD), and developmental coordination disorder (DCD) in an individual with unaffected parents. Trio-based whole-exome sequencing (WES) identified a de novo variant (c.1530dup, p.Glu511ArgfsTer16) in the ZNF496 gene of the proband. According to ACMG guidelines, this novel variant is classified as pathogenic. It creates a frameshift that introduces a premature stop codon, resulting in a truncated protein of 525 amino acids (compared to the wild-type 587 residues). Notably, NMDEscPredictor analysis predicted that the transcript escapes nonsense-mediated decay (NMD) despite the frameshift. Computational analyses suggest the potential pathogenetic effects of the identified variant. As documented, ZNF496 interacts with JARID2, a gene associated with NDDs, ID and facial dysmorphism (MIM: #620098). In silico analyses suggest that the identified mutation disrupts this interaction by deleting ZNF496’s C2H2 domain, potentially dysregulating JARID2 target genes. To our knowledge, this is the first reported association between ZNF496 and NDDs, and the variant has been submitted to the ClinVar database (SCV006100880). Functional studies are imperative to validate ZNF496’s role in NDDs and confirm the mutation’s impact on ZNF496-JARID2 interactions. Full article

Fasciola hepatica remains a global health and economic concern, and treatment still relies heavily on triclabendazole. At the parasite–host interface, F. hepatica calcium-binding proteins (FhCaBPs) have a unique EF-hand/DLC-like domain fusion found only in trematodes. This makes it a parasite-specific target for small compounds and vaccinations. To enable novel therapeutic strategies, we report the first elevated-resolution structure of a full-length FhCaBP4. The apo structure was determined at 1.93 Å resolution, revealing a homodimer architecture that integrates an N-terminal, calmodulin-like, EF-hand pair with a C-terminal dynein light chain (DLC)-like domain. Structure-guided in silico mutagenesis identified a flexible, 16-residue β4–β5 loop (LTGSYWMKFSHEPFMS) with an FSHEPF core that demonstrates greater energetic variability than its FhCaBP2 counterpart, likely explaining the distinct ligand-binding profiles of these paralogs. Molecular dynamics simulations and AlphaFold3 modeling suggest that EF-hand 2 acts as the primary calcium-binding site, with calcium coordination inducing partial rigidification and modest expansion of the protein structure. Microscale thermophoresis confirmed calcium as the major ligand, while calmodulin antagonists bound with lower affinity and praziquantel demonstrated no interaction. Thermal shift assays revealed calcium-dependent stabilization and a merger of biphasic unfolding transitions. These results suggest that FhCaBP4 functions as a calcium-responsive signaling hub, with an allosterically coupled EF-hand–DLC interface that could serve as a structurally tractable platform for drug targeting in trematodes. Full article

In this study, we investigate the nonlinear dynamical behavior of a one-dimensional linear piecewise-smooth discontinuous (LPSD) map with a negative slope, motivated by its occurrence in systems exhibiting discontinuities, such as power electronic converters. The objective of the proposed research is to develop an analytical approach. Analytical conditions are derived for the existence of stable period-1 and period-2 orbits within the third quadrant of the parameter space defined by slope coefficients $a<0$ and $b<0$. The coexistence of multiple attractors is demonstrated. We also show that a novel class of orbits exists in which both points lie entirely in either the left or right domain. These orbits are shown to eventually exhibit periodic behavior, and a closed-form expression is derived to compute the number of iterations required for a trajectory to converge to such orbits. This method also enhances the ease of analyzing system stability by mapping the state–variable dynamics using a non-smooth discontinuous map. The analytical findings are validated using bifurcation diagrams, cobweb plots, and basin of attraction visualizations. Full article

Emotion analysis based on electroencephalogram (EEG) sensors is pivotal for human–machine interaction yet faces key challenges in spatio-temporal feature fusion and cross-band and brain-region integration from multi-channel sensor-derived signals. This paper proposes MB-MSTFNet, a novel framework for EEG emotion recognition. The model constructs a 3D tensor to encode band–space–time correlations of sensor data, explicitly modeling frequency-domain dynamics and spatial distributions of EEG sensors across brain regions. A multi-scale CNN-Inception module extracts hierarchical spatial features via diverse convolutional kernels and pooling operations, capturing localized sensor activations and global brain network interactions. Bi-directional GRUs (BiGRUs) model temporal dependencies in sensor time-series, adept at capturing long-range dynamic patterns. Multi-head self-attention highlights critical time windows and brain regions by assigning adaptive weights to relevant sensor channels, suppressing noise from non-contributory electrodes. Experiments on the DEAP dataset, containing multi-channel EEG sensor recordings, show that MB-MSTFNet achieves 96.80 ± 0.92% valence accuracy, 98.02 ± 0.76% arousal accuracy for binary classification tasks, and 92.85 ± 1.45% accuracy for four-class classification. Ablation studies validate that feature fusion, bidirectional temporal modeling, and multi-scale mechanisms significantly enhance performance by improving feature complementarity. This sensor-driven framework advances affective computing by integrating spatio-temporal dynamics and multi-band interactions of EEG sensor signals, enabling efficient real-time emotion recognition. Full article