Search

The critical components of autonomous driving perception, including drivable area segmentation, lane detection, and traffic target detection, are executed concurrently, imposing substantial computational demands on intelligent vehicles. A balance between accuracy and speed in practical applications is achieved through the utilization of multi-task perception algorithms. Difficulties inherent in multi- task perception algorithms, such as complex road conditions and obscured targets, are addressed by proposing a multi-task perception algorithm based on receptive-field attention convolution (RFAConv) through YOLOP network enhancement. Initially, certain convolutions in the backbone network are substituted with receptive- field attention convolutions, dynamically allocating convolution kernel weights based on the importance of image features within the receptive field to enhance the network' s feature extraction capability. Subsequently, the feature pyramid network is reconstructed by replacing the original cross-stage hierarchical module with an efficient cross-scale fusion module to fully retain effective information during feature fusion. Additionally, a content-aware feature recombination module is employed as an up-sampling method to mitigate information loss during feature fusion up sampling. Finally, the MPDIoU function is utilized to compute the regression loss, addressing issues related to differently sized but proportionate actual and predicted boxes, further enhancing the detection capability for traffic targets. Testing results on the BDD100K dataset demonstrate that the model, compared to other multi- task models and even single- task models, exhibits superior detection accuracy for drivable area segmentation, lane detection, and traffic target detection while concurrently maintaining real-time inference performance of the network. [ABSTRACT FROM AUTHOR]

During high-intensity transportation on heavy-haul railways, rail stripping damage, abrasion, and other forms of damage that compromise driving safety can occur easily. Monitoring and predicting the condition of the rails are crucial steps to ensure the safe operation of the railway. However, current methods for detecting rail damage primarily rely on manual road inspections. These methods often suffer from issues such as strong subjectivity, challenges in quantifying the extent of damage, and difficulty in predicting the degradation trend of the damage. In response to the aforementioned issues, a novel approach was introduced to predict the stripping damage degradation trend of heavy-haul railway rails based on principal component analysis(PCA) and temporal convolutional networks with attention(TCN-Attention). Firstly, time domain and frequency domain features were extracted from the vibration signal associated with rail stripping damage. Subsequently, PCA was applied to reduce the dimensionality of the extracted high-dimensional features. Secondly, leveraging the distinctions in characteristics among time series samples, a degradation index for rail stripping damage was formulated to depict the degradation trend and address the challenge of measuring the damage state. The TCN network model, coupled with the Attention mechanism, was employed to focus on significant features and enhance the prediction accuracy of the model. Finally, the effectiveness of the proposed method was validated using vibration data collected throughout the entire life cycle of the rail, from normal to damaged to failure stages, obtained from a railway locomotive depot. Experimental results demonstrate that the proposed method accurately predicts rail stripping damage and loss of degradation trend. [ABSTRACT FROM AUTHOR]

As a key factor to determine the form of future war, human-machine fusion has attracted the attention of experts in the military field of various countries from its inception to its rise, and it is a necessary means to promote the cooperation between human intelligence and machine intelligence. In this paper, the current research status, relevant important concepts and practical applications of human-machine fusion systems are introduced. Then, the development from unmanned systems to human-machine fusion is analyzed. Moreover, the relevant theories and cooperation strategies of human-computer fusion are summarized. The implementation framework, collaborative mechanism, and development analysis are obtained. The performance optimization methods and key technologies of collaborative optimization are deeply analyzed. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the issue of user preference drift and capture dynamic user preferences more accurately in sequence recommendation, this paper proposed a novel model named SILSSRec. The model initially leveraged categories and frequencies of items as side information to generate personalized user embeddings based on users' historical interaction sequences. Then it created personalized temporal interval embeddings by considering the time intervals between historical and current interactions, and integrated these embeddings with item feature embeddings to form personalized temporal embeddings. The model employed attention mechanisms and gated recurrent networks to extract users' long-term and short-term preferences from the embedding representations. Furthermore, it used contrastive learning to reinforce the feature representation of preferences, and an adaptive aggregation network dynamically combined these two types of preferences to form the final preference representation of users. Experiments on eight public datasets demonstrate that SILSSRec outperforms existing baseline models on evaluation metrics, with an average increase of 3.82% in AUC, 7.2% in recall rate, and 0.3% in precision. The results validate that SILSSRec performs well in various scenarios, effectively mitigating the preference drift issue and enhancing recommendation performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background Upper limb motor dysfunction is a common functional disorder after stroke. Attention may have an impact on the recovery of upper limb motor function, but there is little evidence of correlation between upper limb motor function and attention. Objective To explore the correlation between upper limb motor function and attention after stroke, and to provide a new perspective for clinical rehabilitation of upper limb function. Methods A total of 480 stroke patients who were hospitalized in the Department of Rehabilitation Medicine of 26 units in China from March to October 2023 were selected as the study subjects. The Fugl-Meyer Assessment Upper Limb (FMA-UL) and Montreal Cognitive Assessment (MoCA) were used to evaluate the upper limb motor function and attention of the patients, respectively. Pearson correlation analysis was used to explore the correlation between the total score of FMA-UL and the scores of attention assessment items in MoCA. Results Among the 480 patients, 105 patients did not finish the complete evaluation, so finally, 375 patients with stroke were included. The average FMA-UL score was (31.26±22.49) points. The average MoCA-Attention score was (4.74±1.60) points. The average Attention-Forward Digit Span and Backward Digit Span task score was (1.62±0.63) points; the average Attention-Vigilance task score was (0.74±0.45) points; the average Attention-Serial 7s task score was (2.39±0.95) points. The total FMA-UL score of male patients was higher than that of female patients (P

Copyright of Acta Scientiarum Naturalium Universitatis Sunyatseni / Zhongshan Daxue Xuebao is the property of Sun-Yat-Sen University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In response to the limitations observed in existing communication modulation recognition technologies, including a restricted number of recognition types and a suboptimal overall recognition rate, an automatic modulation recognition method for communication signals based on feature fusion (ACCLNN) was proposed. Initially, the method leveraged ASPP to capture diverse input information across different scales. Spatial features were then extracted through a parallel convolutional neural network (CNN), incorporating the CBAM attention module to enhance feature representation in critical data areas and extract low-level features. Subsequently, a long short-term memory network (LSTM) was employed for temporal feature extraction, accompanied by the introduction of a self-attention module for profound feature extraction. The final step involved fusing low-level features and deep features to achieve comprehensive feature extraction and mapping. Experimental results demonstrate the efficacy of the proposed method in identifying communication signal categories in low signal-to-noise ratio (SNR) environments, achieving an overall recognition rate exceeding 93% . [ABSTRACT FROM AUTHOR]

The key point of current research on few shot object detection based on meta learning is how to make better use of the information of support branch to help query branch to recognize novel objects more effectively. However, many current methods fuse the features from support branch and query branch in the depth direction, ignoring the spatial position relationship between features. Therefore, this study proposes non local support attention network. This method not only adds support information into the proposals features, but also fuses the support information with the features that fed into region proposal network. The spatial position relationship between features is considered at the same time. It also adds the information of negative supports to the detection module to help the model distinguish the objects from different categories. This method obtains good performance on base classes and novel classes of COCO2017 dataset, particularly under the case of incremental learning. Compared with method before improvement, 3.3/3.8/4.7 mAP is increased in AP/AP50/AP75 of novel classes. 2.7/0.5/3.3 mAP is increased in AP/AP50/AP75 of the base classes, and outperformed the performance of SOTA (Sort-Of-The Art) model DAnA (Dual-Awareness Attention) under the same setting. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Industrial Water Treatment is the property of CNOOC Tianjin Chemical Research & Design Institute and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Human gaze behavior, as a non-verbal cue, plays a crucial role in revealing human intentions. Gaze target detection has attracted extensive attention from the machine vision community. However, existing gaze target detection methods usually focus on the texture information extraction of images, ignoring the importance of stereo depth information for gaze target detection, which makes it difficult to deal with scenes with complex texture. In this work, a novel gaze target detection network based on attention mechanism and depth prior is proposed, which adopts two-stage architecture (i.e., a gaze direction prediction stage and a saliency detection stage). In the gaze direction predication stage, a channel-spatial attention mechanism module is established to recalibrate texture features, and a head position encoding branch is designed to achieve texture and head position-aware enhanced high-representation features to accurately predict gaze. Furthermore, a strategy is proposed to introduce the depth representing the stereoscopic or distance information in the 3D scene as a prior into the saliency detection stage. At the same time, the channel-spatial attention mechanism is used to enhance the multi- scale texture features, and the advantages of depth geometric information and image texture information are fully utilized to improve the accuracy of gaze target detection. Experimental results show that the proposed model performs favorably against the state-of-the-art methods on GazeFollow and DLGaze datasets. [ABSTRACT FROM AUTHOR]

Copyright of Psychological Science is the property of Psychological Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of South-Central Minzu University (Natural Science Edition) is the property of Journal of South-Central Minzu University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the increasing demands for healthy diet of people, various kinds of food evaluation assistant softwares emerge as times require, and the topic of food images recognition receives more and more attention. Food images recognition belongs to fine-grained recognition problem, which is more difficult than other image recognition. Moreover, popular food image datasets, such as ISIA Food- 500, ETH Food- 101 and Vireo Food- 172, contain a small number of images, which makes it difficult to train the image recognition system well and further increasing the recognition difficulty. In this paper, an image recognition method based on attention mechanism is proposed. The method introduces the concept of local-attention on the basis of self-attention to describe the fine-grained features of the image and improve the accuracy of image recognition. In addition, an image self- supervised pre- training algorithm is proposed as well, to alleviate the problem of insufficient training samples of food images. The experimental results show that Top-1 accuracy and Top-5 accuracy of the proposed method on ISIA Food-500 dataset are 65.58% and 90.03%, respectively, which is superior to the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

The currently popular image inpainting methods based on deep neural network typically employ large receptive field feature extractors. However, when restoring local patterns and textures, they often generate artifacts or distorted textures, thus failing to recover the overall semantic and visual structure of the image. To address this issue, this paper proposed a novel image inpainting method, called ORFNet, which combined coarse and fine inpainting by employing an optimized receptive field strategy. Initially, it obtained a coarse inpainting result by using a generative adversarial network with a large receptive field. Subsequently, it used a model with a small receptive field to refine local texture details. Finally, it performed a global refinement inpainting by using an encoder-decoder network based on attention mechanisms. Validation on the CelebA, Paris StreetView, and Places2 datasets demonstrates that ORFNet outperforms existing representative inpainting methods. It leads to 1.98 dB increase in PSNR and 2.49% improvement in SSIM, along with average 2.4% reduction in LPIPS. Experimental results confirm the effectiveness of the proposed image inpainting method, showcasing superior performance across various receptive field settings and achieving more realistic and natural visual outcome. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Hebei University of Science & Technology is the property of Hebei University of Science & Technology, Journal of Hebei University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Clinical Nursing in Practice is the property of Journal of Clinical Nursing in Practice (Editorial Board, Shanghai Jiao Tong University Press) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As an important part of time series research, time series anomaly detection has attracted extensive attention and research in academia and industry. In view of the deep local features and complex dependency in time series data, an anomaly detection model with dual attention mechanism is proposed. The model adopts autoencoder structure. The encoder is composed of a squeeze excitation attention block (SEAB) and a probsparse self-attention block (PSAB). SEAB mines local features containing important information by assigning greater weights to sequence segments with strong discriminability using dynamic weighted window partitioning. PSAB adopts sparse self-attention mechanism to retain dot products with higher weights, eliminate redundant timing features, and reduce time complexity, so as to capture the long-term dependence of time series. Experimental results show that the proposed model achieves the highest F1 score of 0.97 among 9 comparison models and outperforms all other comparison models in 8 of 14 tested datasets in terms of F1 score, which can effectively identify abnormal situation in time series data and achieve advanced anomaly detection performance.

Neuroimaging is increasingly widely used in the field of ADHD research, and more and more studies have shown that ADHD patients have structural abnormalities such as reduced cortical volume, thinning thickness, and reduced surface area, which are related to complex clinical symptoms and abnormal brain function in patients. However, the use of neuroimaging to identify biomarkers as an objective diagnostic tool for ADHD still faces many challenges. Multimodal studies can be used to explore the relationship between the structure and function of different brain regions in ADHD patients, and to use neuroimaging to reveal the mechanism of the evolution of clinical symptoms in the whole life cycle of ADHD patients. [ABSTRACT FROM AUTHOR]

In order to develop the test system of civil aviation pilots' neurobehavioral ability, a method for evaluating the neurobehavioral ability was proposed. Firstly, through the research of relevant literature and the evaluation tools of pilot selection, the evaluation index and evaluation method of civil aviation pilots' neurobehavioral ability were proposed. Secondly, Delphi was used to realize the system construction and the development and optimization of each test item, and forty student pilots were recruited and organized to carry out the test item discrimination test and thirty-eight student pilots to carry out the test-retest reliability test. Finally, three groups of difference tests were conducted according to eight hundred ninety-one student pilots' grades, learning levels and test states to explore the characteristics of neurobehavioral ability of student pilots in different grades, different learning levels and different test states. The results show that the evaluation indexes of civil aviation pilots' neurobehavioral ability are composed of six first-class indexes including perceptual ability, attention, memory, alertness, judgment and movement coordination and twelve second-class indexes. The tool has good discrimination, retest reliability, good consistency, reliability and effectiveness. There are significant differences in the scores of some test items among the civil aviation student pilots at different stages ( P < 0. 05 ), and there are differences in all test items among the student pilots at different states, except for the spatial location memory span item, the scores of the normal group are better than those of the sleepy group (P < 0. 05) . It is concluded that the evaluation system can effectively and reliably evaluate the neurobehavioral ability of civil aviation pilots, and it is simple, practical and has a broad application space. [ABSTRACT FROM AUTHOR]

The research on driver’s physiology and psychology in foggy environment has always been an pressing industry problem to be solved. In order to improve the driving safety in dumpling fog environment and clarify the driver’s minimum attention demand in dumpling fog environment, the research progress of driver’s attention under low visibility conditions at home and abroad was reviewed. Firstly, the characteristics of driver’s attention was expounded, the main influencing factors of fog environment on driver’ s attention was clarified, and the relevant research methods and mathematical models was discussed. Secondly, the influence of vehicle speed and visibility on driver’ s minimum attention demand was analyzed, and the relationship between visual physiological load and driver’s minimum attention demand was clarified. Finally, the coupling analysis of the influence of the fog environment on the driver’s minimum attention demand was carried out, which is divided according to the different time and space of the driving vehicle passing through the dumpling fog section. Through the change of spare capacity, the dynamic relationship between visibility, speed and minimum attention demand in the dumpling fog environment was analyzed, and then a theoretical model of the minimum attention demand mutation of the driver during the vehicle passing through the dumpling fog section was established. By summarizing the existing research on the dumpling fog environment, it is found that there is a lack of demand for driver induction. In the subsequent research, considering the multi-factor influence of the fog environment on the driver, selecting the evaluation index that can better reflect the driver’s visual psychological demand for quantitative analysis will become the main goal. [ABSTRACT FROM AUTHOR]

Objective：To investigate the effect of type 2 diabetes mellitus（T2DM） disease status on cognitive function in patients with subjective cognitive decline （SCD），and to explore possible mechanisms based on the structural features of the hippocampus. Method：According to their T2DM disease status, voluntary and eligible SCD subjects in the community of Fuzhou city，Fujian province were recruited and divided into SCD patients with T2DM and SCD patients without T2DM. The effects of different T2DM disease status on cognitive performance scores， hippocampal volume， hippocampal subregion volume and parahippocampal surface area in patients with SCD were compared, and the correlation analysis was performed between the significantly different cognitive performance scores and the hippocampal volume，hippocampal subregion volume and parahippocampal surface area. Result：Compared with SCD patients without T2DM，SCD patients with T2DM had a longer Stroop facilitation effect（SFE） response time，fewer SFE correct numbers，more Go/No go errors，and distracted visual response time was longer. The difference was statistically significant （P<0.05）. Analysis of MRI data showed that the volume and parahippocampal surface area of the left hippocampal subregion of SCD patients with T2DM were significantly lower than those of SCD patients without T2DM. The results of correlation analysis showed that the parahippocampal surface area of SCD patients was significantly positively correlated with the correct number of SFE （P<0.001）. Conclusion：T2DM aggravates cognitive impairment in Stroop facilitation effect， executive inhibitory control function，and cognitive processing domains of visual distraction in SCD patients，and may be related to the atrophy of gray matter structure in some brain regions of the hippocampus. [ABSTRACT FROM AUTHOR]

Brain fog is a symptom that has gained increasing attention worldwide since the start of the COVID-19 pandemic, as patients affected by COVID-19 may experience cognitive dysfunction, colloquially known as brain fog, for a period of time after recovery. Brain fog affects activities of daily living and work performance and has the potential to negatively impact society and the economy. However, a clear definition and concept analysis of brain fog is lacking in the literature. In this article, a concept analysis of brain fog is conducted using Walker and Avant's concept analysis steps to verify the source and definition of brain fog, clarify related concepts similar to brain fog, and establish the defining attributes, antecedents, and consequences of this condition. Model, borderline, contrary, and related cases are listed to illustrate and provide related empirical references in the literature. The authors hope this article will provide a clearer understanding of brain fog, which then may be applied in nursing clinical practice and future research to develop strategies and care methods for improving brain fog symptoms. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the problems of dim light, image affected by lamp light and difficulty in detecting small targets at long distance in highway tunnel, an improved YOLOv5 algorithm for vehicle and personnel detection in highway tunnel was proposed. Firstly, Gaussian mixture clustering was used to obtain a set of anchor boxes that match the dataset targets better, improving the detection accuracy of the model. Secondly, CARAFE operator was introduced in the feature fusion to enlarge the receptive field and reduce the loss of feature detail information in the upsampling process. Finally, by inserting coordinate attention ( CA) into the network, the models ability to extract features from different positions of the image is further enhanced. To verify the effectiveness of the algorithm, experiments were conducted on the Zhejiang Wenli Expressway Tunnel dataset, and the results show that: the mean average precision ( mAP) of the proposed algorithm reaches 95. 7%, which is 3. 8% higher than the original model, and it can achieve more accurate detection for small targets at long distances and targets affected by severe lighting, providing an effective solution for vehicle and personnel detection in highway tunnels under complex environments. [ABSTRACT FROM AUTHOR]

Person re-identification based on supervised learning needs the support of a large number of labeled data, and the model has poor scalability. In practical applications, more attention is paid to how to improve the accuracy of person re-identification in the target domain without labeled data. Therefore, a cross-domain person re-identification method based on pose guided attention mechanism is proposed. First, a pedestrian pose guided attention module is trained using the annotation data in the source domain as an occlusion predictor to distinguish the pedestrian effective area and the occluded area in the image. Then, the predictor is integrated into the training process of the unlabeled target domain dataset to shield the interference information caused by occlusion. The person feature affinity matrix is calculated and soft labels for the unlabeled data are generated to update and optimize the training network of the target domain. Cross-domain experiments are carried out on three large-scale public datasets Market -1501, DukeMTMC-reID and MSMT17 respectively. The results show that on the two evaluation criteria of rank -1 and mean average precision (mAP), the proposed method can perform better compared with the existing methods. [ABSTRACT FROM AUTHOR]

The use of light to promote health, reduce harm, and restore functionality is a novel, non-accumulative physical strategy that contrasts with the predominantly chemical approaches used in Western medicine. This strategy may serve as an independent function for healthcare professionals and warrants further exploration. Photoreactivation, achieved by adjusting patients' physiological clocks at different times, utilizing specific wavelengths, varying color temperatures, and using illuminance, is a potent tool for improving mood and sleep quality, regulating autonomic nervous system balance, enhancing attention, and delaying cognitive decline. Light therapy is a rapidly expanding field in healthcare that offers new opportunities to enhance quality of life, prevent diseases, and improve overall well-being. This article elucidates the fundamental concepts of photoreactivation, explores its application across diverse health domains, examines its future development prospects, and discusses the challenges faced by photoreactivation and related solutions to ensure the responsible use of light to enhance and restore physiological and psychological functions. [ABSTRACT FROM AUTHOR]

Traditional group recommendation has such problems as ineffective predefined strategy, neglect of the interaction between users and projects, and failure to capture the migration of user preferences caused by the passage of time.In response to the above problems, a group recommendation model TAGR (time-attentive group recommendation) that integrates time series and attention mechanisms was proposed. Firstly, high similarity groups were divided through hierarchical clustering. Secondly, a time series model was introduced to capture the process of user preference transfer, obtain the interest preferences of user behavior at each moment, and aggregate the interest preferences at each moment as user preferences. Finally, with attention mechanism, user weights were obtained for preference fusion to represent group preferences, serving as the input of the recommendation model. By comparing with NCF, AGREE and other models on the Goodbook and MovieLens datasets, the proposed model TAGR has been significantly improved in both normalized discount cumulative gain and hit rate. [ABSTRACT FROM AUTHOR]

Copyright of Psychological Science is the property of Psychological Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Guangxi Normal University - Natural Science Edition is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cardiovascular and cerebrovascular diseases are one of the most common cause of death in the world, atherosclerosis is the main pathologic change, and often involving cardiovascular and cerebrovascular concurrently. No consensus has been reached on whether carotid endarterectomy (CEA) combined with coronary artery bypass grafting (CABG) should be performed at concurrent operation or staged operation (CEA after CABG or CABG after CEA) in patients with ischemic cardiovascular and cerebrovascular diseases. However, with the deepening of research on cardiovascular and cerebrovascular diseases, the improvement of surgical techniques and development of intravascular intervention techniques, it provides theoretical basis and technical support for simultaneous surgical intervention. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Data Acquisition & Processing / Shu Ju Cai Ji Yu Chu Li is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the era of online shopping, a variety of product brands make it difficult for consumers to choose, and also breed a large number of online trademark infringement. Therefore, a trademark detection method based on deep learning was proposed. Method was based on YOLOv7-tiny, first of all, in order to improve the multi-scale detection ability, PAnet module in Neck part was changed to a simplified adaptive learning weights, multi-scale feature fusion network SimBiFPN. Then, in order to focus on the key semantic information, the attention mechanism was introduced to change the Conv convolution layer between Neck and Head into full-dimensional dynamic convolution ODConv. Finally, in order to make the algorithm get pixel-level modeling capability, the activation function was changed to FRelu. The dataset of Tianchi platform was selected and then enhanced by Mosaic and Mixup to complete the training and verification of the model. The results show that the mAP of the improved model is raised to 85. 84%, nearly 2 percentage points higher than that of the original model, better than other you only look once(YOLO) models, and the number of parameters of the model is reduced by 41% . The proposed method can be used to improve the efficiency of online shopping and strengthen the fight against trademark infringement. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Image data was collected at the Pig Breeding Base in Fenxi County, Linfen City, Shanxi Province in July 2020. Nine 5-month-old fattening pigs were selected to raise in a closed pig house. Hikvision DS-2CD3345D-I model camera was used in a downward tilt angle of 60 degrees to collect data under incandescent light. This angle was utilized to obtain the rich behavioral features of pigs, in order to avoid large-scale occlusion, compared with the head-up and overhead views. In the process of data collection, the daily behavior videos of pigs were first repeatedly observed, and 185 video clips of pigs with aggressive behavior were extracted; Inter frame difference method was used to extract the key frames from these video clips. Slow pig movement and long rest time were removed as well. An improved YOLOX model was proposed to identify the typical attack behaviors of herd pigs, such as impact, ear biting, and tail biting. The high accuracy and effectiveness were achieved to reduce pig stacking and adhesion in complex pen environments. Firstly, a Normalization based Attention Module (NAM) was added to obtain the global information about the YOLOX neck; Secondly, the loss function IoU Loss in the YOLOX was replaced with the GIoU to improve the recognition accuracy; Finally, the real-time performance of the model was realized to enhance feature extraction and detection efficiency. Feature pyramid structure SPP was lightweight to SPPF. The experiment showed that the integrated NAM modules, GIoU Loss replacing, and SPPF feature pyramid structures in the original backbone network improved the average accuracy of the model by 2.50, 2.12, and 0.98 percentage points, respectively. The model with SPP feature pyramid structure reduced the parameter by 0.1 MB and improved the accuracy by 0.98 percentage points, indicating the minimum impact of the model parameter after the integrated NAM module. The average accuracy of the improved model increased from 90.77% to 97.57%, with an increase of 6.80 percentage points; The parameter quantity decreased from the highest 34.7 to 34.5 MB with a decrease of 0.2 MB. In addition, there was the continuous attack behavior of pigs in the low credibility of single-frame images. Two optimization indicators (proportion of attack activities (PAA) and proportion of attack behavior (PAB))were introduced to further confirm whether the attack behavior occurred. When the PAA and PAB thresholds were 0.2 and 0.4, respectively, the recognition accuracy (Accuracy) reached 98.55%. Video segments with frequent attacks were selected to verify the effectiveness of the optimization. Usually, PAA and PAB posed a significant impact on the recognition of pig aggressive behavior; If the threshold set was too small, it was easy to misjudge frames without attack behavior as having occurred; If the threshold set was too large, the frame without the attack was assumed as the occurrence. The experimental results show that the improved YOLOX model was achieved in the high-precision recognition of pig attack behavior by the integrated PAA and PAB. The finding can provide effective reference and technical support for the intelligent monitoring of herd health pigs. [ABSTRACT FROM AUTHOR]

3D Visual Grounding（3D VG） aims to locate target objects in 3D scenes by understanding the semantics of referring expressions. Researchers proposed text and object classification tasks to optimize textual and visual encoders,which might incur semantic mis-matches between visual and textual features, making it impossible to localize targets in 3D scenes. In addition, the limited amount of data in 3D VG datasets and complex model structures often lead to overfitting. To address issues above, this paper proposed MP3DVG to realize classification and 3D VG tasks by united representations. Based on cross-modal interaction, it designed pre-fusion module to pre-fuse visual and textual embeddings before classification tasks by TGV and VGT respectively, alleviating the adverse effects caused by semantic mis-alignment of different modal features. Aiming at the overfitting of models, it devised periodically initialized auxiliary classifier to adjust sample losses by dynamic loss-adjusters, evaluating differences among sample features online. The experimental results demonstrate the superiority of the proposed method. MP3DVG outperforms MVT on Nr3D and Sr3D datasets by 1.1% and 1.8% respectively, the overfitting of model is improved as well. [ABSTRACT FROM AUTHOR]

Emotion recognition plays a crucial role in human-computer interaction, and continuous emotion recognition has gained significant attention due to its ability to capture a broader range of emotions, including more subtle ones. In the field of multimodal continuous emotion recognition, a continuous emotion recognition method based on perceiver resampling and multimodal fusion is proposed for the problems that the temporal series information obtained by the existing methods contains more redundancy and the obtained multimodal interactive information is not comprehensive. Firstly, the perceiver resampling module removes redundant information, focuses on key information, compresses the key features with temporal relationships into hidden vectors, and reduces the computational complexity of the later fusion. Secondly, the multimodal fusion module captures the interactive information between modalities through cross-attention mechanism, and uses the self-attention mechanism to obtain the hidden information within each modality, so as to make the feature information richer and more comprehensive. The mean CCC values of arousal and valence on the Ulm-TSST and Affwild2 datasets are 63.62% and 50.09%, respectively, which proved the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Hebei University of Science & Technology is the property of Hebei University of Science & Technology, Journal of Hebei University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background Cognitive function is dynamic in post-stroke patients, however, there are limited studies on cognitive recovery after stroke. The definition of cognitive reverters and neuropsychological characteristics according to various definitions have not yet been investigated. Objective To investigate the neuropsychological characteristics of cognitive reverters after stroke based on the traditional definition and new definition according to Montreal Cognitive Assessment (MoCA) with a double threshold. Methods A total of 163 patients hospitalized for first onset acute ischemic stroke were recruited from the Department of Neurology of the Second Hospital of Hebei Medical University from December 2020 to February 2022 as the study subjects. All patients were assessed for cognitive function in the acute period of ischemic stroke using the MoCA at baseline. Cognitive function was assessed again at the 6-month post-stroke follow-up with the detailed neuropsychological tests refined at the same time, including the digit span task (DST) , Stroop color and word test (SCWT) , Chinese version of Boston naming test (BNT) , verbal fluency test (VFT) , clock drawing test (CDT) , and auditory verbal learning test (AVLT) . The enrolled patients were divided into the M1 group (MoCA scores

Brain-computer interface (BCI) technology based on motor imagery electroencephalograph (EEG) signals has developed rapidly, and compared with traditional methods, deep learning has achieved competitive results. However, it is still a challenge to design and train an end-to-end network to fully extract the potential features of motor-imaging EEG signals. Based on the temporal and spatial characteristics of EEG, a multi-scale spatiotemporal self-attention network model based on attention mechanism is proposed to classify motor imagery EEG signals into four categories, such as left hand, right hand, foot and tongue/rest. Since the amplitude and response time of motor imagery EEG signal vary with the subjects, it is impossible to determine the most relevant brain region with motor imagery. Therefore, the self-attention mechanism is used to select the best channel by automatically weighting the higher weight to the motion-related channel and the lower weight to the non-motion-related channel in space. And parallel multi-scale TCN layer is used to extract the temporal feature at different scales and to eliminate the noise in time domain. The fusion module fuses the extracted spatial and temporal features, and finally inputs them to the classification module for classification. The model achieves accuracy of 79.26%, 85.90% and 96.96% on the BCI competition datasets IV-2a, IV-2b and HGD dataset. Compared with the baseline method, this method has a higher accuracy in subject classification. The results show that the method has good performance, robustness and transfer learning ability.

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)