Search Results (326)

The classification of missense variant pathogenicity continues to pose significant challenges in human genetics, necessitating precise predictions of functional impacts for effective disease diagnosis and personalized treatment strategies. Traditional methods, often compromised by suboptimal feature selection and limited generalizability, are outpaced by the enhanced classification model, MissenseNet (Missense Classification Network). This model, advancing beyond standard predictive features, incorporates structural insights from AlphaFold2 protein predictions, thus optimizing structural data utilization. MissenseNet, built on the ShuffleNet architecture, incorporates an encoder-decoder framework and a Squeeze-and-Excitation (SE) module designed to adaptively adjust channel weights and enhance feature fusion and interaction. The model’s efficacy in classifying pathogenicity has been validated through superior accuracy compared to conventional methods and by achieving the highest areas under the Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves (Area Under the Curve and Area Under the Precision-Recall Curve) in an independent test set, thus underscoring its superiority. Full article

Multimodal brain signal analysis has shown great potential in decoding complex cognitive processes, particularly in the challenging task of inner speech recognition. This paper introduces an innovative I nner Speech Recognition via Cross-Perception (ISRCP) approach that significantly enhances accuracy by fusing electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) data. Our approach comprises three core components: (1) multigranularity encoders that separately process EEG time series, EEG Markov Transition Fields, and fMRI spatial data; (2) a cross-perception expert structure that learns both modality-specific and shared representations; and (3) an attention-based adaptive fusion strategy that dynamically adjusts the contributions of different modalities based on task relevance. Extensive experiments on the Bimodal Dataset on Inner Speech demonstrate that our model outperforms existing methods across accuracy and F1 score. Full article

Adaptive spiral flight and multi-strategy fusion are the foundations of a new FOX optimization algorithm that aims to address the drawbacks of the original method, including weak starting individual ergodicity, low diversity, and an easy way to slip into local optimum. In order to enhance the population, inertial weight is added along with Levy flight and variable spiral strategy once the population is initialized using a tent chaotic map. To begin the process of implementing the method, the fox population position is initialized using the created Tent chaotic map in order to provide more ergodic and varied individual beginning locations. To improve the quality of the solution, the inertial weight is added in the second place. The fox random walk mode is then updated using a variable spiral position updating approach. Subsequently, the algorithm’s global and local searches are balanced, and the Levy flying method and greedy approach are incorporated to update the fox location. The enhanced FOX optimization technique is then thoroughly contrasted with various swarm intelligence algorithms using engineering application optimization issues and the CEC2017 benchmark test functions. According to the simulation findings, there have been notable advancements in the convergence speed, accuracy, and stability, as well as the jumping out of the local optimum, of the upgraded FOX optimization algorithm. Full article

In logistics and manufacturing, smart technologies are increasingly used, and warehouse logistics robots (WLR) have thus become key automation tools. Nonetheless, the path planning of mobile robots in complex environments still faces the challenges of excessively long paths and high energy consumption. To this end, this study proposes an innovative optimization algorithm, IWOA-WLR, which aims to optimize path planning and improve the shortest route and smoothness of paths. The algorithm is based on the Whale Algorithm with Multiple Strategies Fusion (IWOA), which significantly improves the obstacle avoidance ability and path optimization of mobile robots in global path planning. First, improved Tent chaotic mapping and differential dynamic weights are used to enhance the algorithm’s optimization-seeking ability and improve the diversity of the population. In the late stage of the optimization search, the positive cosine inertia threshold and the golden sine are used to perform adaptive position updating during the search strategy to enhance the global optimal search capability. Secondly, the fitness function of the path planning problem is designed, and the path length is taken as the objective function, the path smoothness as the evaluation index, and the multi-objective optimization is realized through the hierarchical adjustment strategy and is applied to the global path planning of WLR. Finally, simulation experiments on raster maps with grid sizes of 15 × 15 and 20 × 20 compare the IWOA algorithm with the WOA, GWO, MAACO, RRT, and A* algorithms. On the 15 × 15 maps, the IWOA algorithm reduces path lengths by 3.61%, 5.90%, 1.27%, 15.79%, and 5.26%, respectively. On the 20 × 20 maps, the reductions are 4.56%, 5.83%, 3.95%, 19.57%, and 1.59%, respectively. These results indicate that the improved algorithm efficiently and reliably finds the global optimal path, significantly reduces path length, and enhances the smoothness and stability of the path’s inflection points. Full article

Dental diseases are among the most prevalent diseases globally, and accurate segmentation of dental calculus images plays a crucial role in periodontal disease diagnosis and treatment planning. However, the current methods are not stable and reliable enough due to the variable morphology of dental calculus and the blurring of the boundaries between the dental edges and the surrounding tissues; therefore, our hope is to propose an accurate and reliable calculus segmentation algorithm to improve the efficiency of clinical detection. We propose a multi-scale attention pyramid pooling network (MAPPNet) to enhance the performance of dental calculus segmentation. The network incorporates a multi-scale fusion strategy in both the encoder and decoder, forming a model with a dual-ended multi-scale structure. This design, in contrast to employing a multi-scale fusion scheme at a single end, enables more effective capturing of features from diverse scales. Furthermore, the attention pyramid pooling module (APPM) reconstructs the features on this map by leveraging a spatial-first and channel-second attention mechanism. APPM enables the network to adaptively adjust the weights of different locations and channels in the feature map, thereby enhancing the perception of important regions and key features. Experimental evaluation of our collected dental calculus segmentation dataset demonstrates the superior performance of MAPPNet, which achieves an intersection-over-union of 81.46% and an accuracy rate of 98.35%. Additionally, on two publicly available datasets, ISIC2018 (skin lesion dataset) and Kvasir-SEG (gastrointestinal polyp segmentation dataset), MAPPNet achieved an intersection-over-union of 76.48% and 91.38%, respectively. These results validate the effectiveness of our proposed network in accurately segmenting lesion regions and achieving high accuracy rates, surpassing many existing segmentation methods. Full article

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have made considerable advances in hyperspectral image (HSI) classification. However, most CNN-based methods learn features at a single-scale in HSI data, which may be insufficient for multi-scale feature extraction in complex data scenes. To learn the relations among samples in non-grid data, GCNs are employed and combined with CNNs to process HSIs. Nevertheless, most methods based on CNN-GCN may overlook the integration of pixel-wise spectral signatures. In this paper, we propose a pyramid cascaded convolutional neural network with graph convolution (PCCGC) for hyperspectral image classification. It mainly comprises CNN-based and GCN-based subnetworks. Specifically, in the CNN-based subnetwork, a pyramid residual cascaded module and a pyramid convolution cascaded module are employed to extract multiscale spectral and spatial features separately, which can enhance the robustness of the proposed model. Furthermore, an adaptive feature-weighted fusion strategy is utilized to adaptively fuse multiscale spectral and spatial features. In the GCN-based subnetwork, a band selection network (BSNet) is used to learn the spectral signatures in the HSI using nonlinear inter-band dependencies. Then, the spectral-enhanced GCN module is utilized to extract and enhance the important features in the spectral matrix. Subsequently, a mutual-cooperative attention mechanism is constructed to align the spectral signatures between BSNet-based matrix with the spectral-enhanced GCN-based matrix for spectral signature integration. Abundant experiments performed on four widely used real HSI datasets show that our model achieves higher classification accuracy than the fourteen other comparative methods, which shows the superior classification performance of PCCGC over the state-of-the-art methods. Full article

To address the issues of inadequate feature extraction for rolling bearings, inaccurate fault diagnosis, and overfitting in complex operating conditions, this paper proposes a rolling bearing diagnosis method based on multi-scale feature fusion and transfer adversarial learning. Firstly, a multi-scale convolutional fusion layer is designed to effectively extract fault features from the original vibration signals at multiple time scales. Through a feature encoding fusion module based on the multi-head attention mechanism, feature fusion extraction is performed, which can model long-distance contextual information and significantly improve diagnostic accuracy and anti-noise capability. Secondly, based on the domain adaptation (DA) cross-domain feature adversarial learning strategy of transfer learning methods, the extraction of optimal domain-invariant features is achieved by reducing the gap in data distribution between the target domain and the source domain, addressing the call for research on fault diagnosis across operating conditions, equipment, and virtual–real migrations. Finally, experiments were conducted to verify and optimize the effectiveness of the feature extraction and fusion network. A public bearing dataset was used as the source domain data, and special vehicle bearing data were selected as the target domain data for comparative experiments on the effect of network transfer learning. The experimental results demonstrate that the proposed method exhibits an exceptional performance in cross-domain and variable load environments. In multiple bearing cross-domain transfer learning tasks, the method achieves an average migration fault diagnosis accuracy rate of up to 98.65%. When compared with existing methods, the proposed method significantly enhances the ability of data feature extraction, thereby achieving a more robust diagnostic performance. Full article

Despite efforts to elucidate the cellular adaptations induced by obesity, cellular bioenergetics is currently considered a crucial target. New strategies to delay the onset of the hazardous adaptations induced by obesity are needed. Therefore, we evaluated the effects of 4 weeks of melatonin treatment on mitochondrial function and lipid metabolism in the livers of leptin-deficient mice. Our results revealed that the absence of leptin increased lipid storage in the liver and induced significant mitochondrial alterations, which were ultimately responsible for defective ATP production and reactive oxygen species overproduction. Moreover, leptin deficiency promoted mitochondrial biogenesis, fusion, and outer membrane permeabilization. Melatonin treatment reduced the bioenergetic deficit found in ob/ob mice, alleviating some mitochondrial alterations in the electron transport chain machinery, biogenesis, dynamics, respiration, ATP production, and mitochondrial outer membrane permeabilization. Given the role of melatonin in maintaining mitochondrial homeostasis, it could be used as a therapeutic agent against adipogenic steatosis. Full article

The Unmanned Aerial Vehicle (UAV) tracking tasks find extensive utility across various applications. However, current Transformer-based trackers are generally tailored for diverse scenarios and lack specific designs for UAV applications. Moreover, due to the complexity of training in tracking tasks, existing models strive to improve tracking performance within limited scales, making it challenging to directly apply lightweight designs. To address these challenges, we introduce an efficient attention mechanism known as Macaron Attention, which we integrate into the existing UAV tracking framework to enhance the model’s discriminative ability within these constraints. Specifically, our attention mechanism comprises three components, fixed window attention (FWA), local squeezing global attention (LSGA), and conventional global attention (CGA), collectively forming a Macaron-style attention implementation. Firstly, the FWA module addresses the multi-scale issue in UAVs by cropping tokens within a fixed window scale in the spatial domain. Secondly, in LSGA, to adapt to the scale variation, we employ an adaptive clustering-based token aggregation strategy and design a “window-to-window” fusion attention model to integrate global attention with local attention. Finally, the CGA module is applied to prevent matrix rank collapse and improve tracking performance. By using the FWA, LSGA, and CGA modules, we propose a brand-new tracking model named MATrack. The UAV123 benchmark is the major evaluation dataset of MATrack with 0.710 and 0.911 on success and precision, individually. Full article

To achieve a rapid and stable dynamic response of the drive anti-slip system for distributed electric vehicles on low-friction surfaces, this paper proposes an adaptive acceleration slip regulation control strategy based on wheel slip rate. An attachment coefficient fusion estimation algorithm based on an improved singular value decomposition unscented Kalman filter is designed. This algorithm combines Sage–Husa with the unscented Kalman filter for adaptive improvement, allowing for the quick and accurate determination of the road friction coefficient and, subsequently, the optimal slip rate. Additionally, a slip rate control strategy based on dynamic adaptive compensation sliding mode control is designed, which introduces a dynamic weight integral function into the control rate to adaptively adjust the integral effect based on errors, with its stability proven. To verify the performance of the road estimator and slip rate controller, a model is built with vehicle simulation software, and simulations are conducted. The results show that under icy and snowy road conditions, the designed estimator can reduce estimation errors and respond rapidly to sudden changes. Compared to traditional equivalent controllers, the designed controller can effectively reduce chattering, decrease overshoot, and shorten response time. Especially during road transitions, the designed controller demonstrates better dynamic performance and stability. Full article

Wheat scab can reduce wheat yield and quality. Currently, unmanned aerial vehicles (UAVs) are widely used for monitoring field crops. However, UAV is constrained by limited computational resources on-board the platforms. In addition, compared to ground images, UAV images have complex backgrounds and smaller targets. Given the aforementioned challenges, this paper proposes a lightweight wheat scab detection network based on UAV. In addition, overlapping cropping and image contrast enhancement methods are designed to preprocess UAV remote-sensing images. Additionally, this work constructed a lightweight wheat scab detection network called LWSDNet using mixed deep convolution (MixConv) to monitor wheat scab in field environments. MixConv can significantly reduce the parameters of the LWSDNet network through depthwise convolution and pointwise convolution, and different sizes of kernels can extract rich scab features. In order to enable LWSDNet to extract more scab features, a scab feature enhancement module, which utilizes spatial attention and dilated convolution, is designed to improve the ability of the network to extract scab features. The MixConv adaptive feature fusion module is designed to accurately detect lesions of different sizes, fully utilizing the semantic and detailed information in the network to enable more accurate detection by LWSDNet. During the training process, a knowledge distillation strategy that integrates scab features and responses is employed to further improve the average precision of LWSDNet detection. Experimental results demonstrate that the average precision of LWSDNet in detecting wheat scab is 79.8%, which is higher than common object detection models and lightweight object detection models. The parameters of LWSDNet are only 3.2 million (M), generally lower than existing lightweight object detection networks. Full article

Visual object tracking, pivotal for applications like earth observation and environmental monitoring, encounters challenges under adverse conditions such as low light and complex backgrounds. Traditional tracking technologies often falter, especially when tracking dynamic objects like aircraft amidst rapid movements and environmental disturbances. This study introduces an innovative adaptive multimodal image object-tracking model that harnesses the capabilities of multispectral image sensors, combining infrared and visible light imagery to significantly enhance tracking accuracy and robustness. By employing the advanced vision transformer architecture and integrating token spatial filtering (TSF) and crossmodal compensation (CMC), our model dynamically adjusts to diverse tracking scenarios. Comprehensive experiments conducted on a private dataset and various public datasets demonstrate the model’s superior performance under extreme conditions, affirming its adaptability to rapid environmental changes and sensor limitations. This research not only advances visual tracking technology but also offers extensive insights into multisource image fusion and adaptive tracking strategies, establishing a robust foundation for future enhancements in sensor-based tracking systems. Full article

The visible-infrared person re-identification (VI-ReID) task aims to retrieve the same pedestrian between visible and infrared images. VI-ReID is a challenging task due to the huge modality discrepancy and complex intra-modality variations. Existing works mainly complete the modality alignment at one stage. However, aligning modalities at different stages has positive effects on the intra-class and inter-class distances of cross-modality features, which are often ignored. Moreover, discriminative features with identity information may be corrupted in the processing of modality alignment, further degrading the performance of person re-identification. In this paper, we propose a progressive discriminative feature learning (PDFL) network that adopts different alignment strategies at different stages to alleviate the discrepancy and learn discriminative features progressively. Specifically, we first design an adaptive cross fusion module (ACFM) to learn the identity-relevant features via modality alignment with channel-level attention. For well preserving identity information, we propose a dual-attention-guided instance normalization module (DINM), which can well guide instance normalization to align two modalities into a unified feature space through channel and spatial information embedding. Finally, we generate multiple part features of a person to mine subtle differences. Multi-loss optimization is imposed during the training process for more effective learning supervision. Extensive experiments on the public datasets of SYSU-MM01 and RegDB validate that our proposed method performs favorably against most state-of-the-art methods. Full article

In the face of contemporary challenges, such as economic instability, environmental degradation, and the urgent global warming crisis, the imperative of sustainability and energy efficiency has reached unparalleled significance. Sustainability encompasses not only the natural environment, but also extends to our immediate surroundings, including the built structures and the communities they serve. Embracing this comprehensive perspective, we embarked on a mission to conceive and construct a model house that harnesses state-of-the-art energy-efficient technologies. Our goal was to seamlessly integrate these features not only to meet our sustainability objectives, but also to mitigate environmental threats.This model embodies a harmonious fusion of indigenous resources, employing locally sourced stone and employing traditional construction techniques. Through this approach, we achieved significant reductions in carbon emissions and established a framework for passive cooling and heating systems. Moreover, the design is intrinsically attuned to its contextual surroundings, preserving the diverse tapestry of regional architectural styles. This study stands as a testament to the potential of innovative design and technology in shaping a sustainable future. The research employs a multi-dimensional approach, encompassing strategies of architectural design with a traditional planning approach, sustainable material selection, energy efficiency, and life cycle assessment across a diverse set of case studies. Building energy analysis is conducted through the application of BIM (Ecotect), providing insights into how BIM can adapt and thrive in various environments. Key findings underscore that thermal performance, minimizing energy loads, and reducing carbon emissions are pivotal aspects in designating a building as both green and energy efficient. Full article

To tackle the complexity and limited applicability of high-precision segmentation models for damaged road markings, this study proposes a Multi-level Adaptive Lightweight Network (MALNet) based on knowledge distillation. By incorporating multi-scale dilated convolution and adaptive spatial channel attention fusion modules, the MALNet model significantly enhances the precision, integrity, and robustness of its segmentation branch. Furthermore, it employs an intricate knowledge distillation strategy, channeling rich, layered insights from a teacher model to a student model, thus elevating the latter’s segmentation ability. Concurrently, it streamlines the student model by markedly reducing its parameter count and computational demands, culminating in a segmentation network that is both high-performing and pragmatic. Rigorous testing on three distinct data sets for damaged road marking detection—CDM_P (Collective Damaged road Marking—Public), CDM_H (Collective Damaged road Marking—Highways), and CDM_C (Collective Damaged road Marking—Cityroad)—underscores the MALNet model’s superior segmentation abilities across all damage types, outperforming competing models in accuracy and completeness. Notably, the MALNet model excels in parameter efficiency, computational economy, and throughput. After distillation, the student model’s parameters and computational load decrease to only 31.78% and 27.40% of the teacher model’s, respectively, while processing speeds increase to 1.9 times, demonstrating a significant improvement in lightweight design. Full article