With the rapid development of wireless communication networks, using AI to predict complex city-scale network traffic has become a significant research challenge. This paper, based on a Graph Convolutional Network (GCN) architecture, proposes a novel wireless network traffic prediction algorithm focused on predicting city-level communication traffic data at an hourly granularity. The algorithm enhances prediction accuracy through two key innovations: first, we introduce a hierarchical attention architecture that combines dynamic and static attention mechanisms. The static attention mechanism, based on wireless channel models, captures fixed spatial relationships between base stations, such as inter-station distances and stable connections. The dynamic attention mechanism, on the other hand, dynamically adjusts to account for time-varying traffic patterns, such as rush hours and holiday effects, enabling the model to adapt to temporal variations in network traffic. These two attention mechanisms are seamlessly integrated within the model through feature concatenation and interactive learning, allowing the model to capture both spatial and temporal characteristics of network traffic simultaneously. Secondly, we innovatively introduce a strategy for adjusting the aggregation iterations of the Graph Convolutional Network (GCN) based on the Laplacian matrix. By leveraging the spectral information provided by the Laplacian matrix, we dynamically determine the depth of the graph convolutional network, thereby avoiding issues of over-smoothing or underfitting and ensuring stable performance in complex network structures. Experimental results demonstrate that the proposed algorithm significantly outperforms existing methods across multiple dataset, particularly in predicting network traffic data with intricate spatiotemporal characteristics.

Text CAPTCHAs are crucial security measures employed on global websites to deter unauthorized intrusions. The presence of anti-attack features incorporated into text CAPTCHAs limits the effectiveness of breaking them, despite CAPTCHA recognition being an effective method for assessing their security. This study introduces a novel color augmentation technique called Variational Color Shift (VCS) to boost the recognition accuracy of different networks. VCS generates a color shift range of every input image and then resamples the image within that range to generate a new image, thus expanding the number of samples of the original dataset to improve training effectiveness. In contrast to Random Color Shift (RCS) which treats the color offsets as hyperparameters, VCS uses the estimated offsets to reparametrize the points sampling from the unit uniform distribution to reconstruct new image pixels, which makes the offsets learnable. To reduce the computational effort of VCS, we also propose two variants of VCS: Sim-VCS and Dilated-VCS. In addition, to solve the overfitting problem caused by many disturbances in CAPTCHAs, we propose an Auto Encoder (AE) based on a Large Separable Kernel Attention (AE-LSKA) to replace the convolutional module in the text CAPTCHA recognizer. This new module employs an AE) to compress the interference while expanding the receptive field using Large Separable Kernel Attention (LSKA), which reduces the impact of local interference on the model training and improves the overall perception of characters. The experimental results show that the recognition rate of the model after integrating the AE-LSKA module is improved by at least 15 percentage points on both M-CAPTCHA and P-CAPTCHA datasets. In addition, experimental results demonstrate that color augmentation using VCS is more effective in enhancing recognition.

Due to the inherent limitations of a single viewpoint, reconstructing 3D human meshes 1 from a single image has long been a challenging task. While deep learning networks enable us to 2 approximate the shape of unseen sides, capturing the texture details of the non-visible side remains 3 difficult with just one image. Traditional methods utilize Generative Adversarial Networks (GANs) 4 to predict the normal maps of the non-visible side, thereby inferring detailed textures and wrinkles 5 on the model’s surface. However, we have identified challenges with existing normal prediction 6 networks when dealing with complex scenes, such as a lack of focus on local features and insufficient 7 modeling of spatial relationships.To address these challenges, we introduce EMAR—Enhanced 8 Multi-scale Attention-driven Single Image 3D Human Reconstruction. This approach incorporates 9 a novel Enhanced Multi-Scale Attention (EMSA) mechanism, which excels at capturing intricate 10 features and global relationships in complex scenes. EMSA surpasses traditional single-scale attention 11 mechanisms by adaptively adjusting the weights between features, enabling the network to more 12 effectively leverage information across various scales.Furthermore, we have improved the feature 13 fusion method to better integrate representations from different scales. This enhanced feature fusion 14 allows the network to more comprehensively understand both fine details and global structures 15 within the image. Finally, we have designed a hybrid loss function tailored to the introduced attention 16 mechanism and feature fusion method, optimizing the network’s training process and enhancing the 17 quality of reconstruction results.Our network demonstrates significant improvements in performance 18 for 3D human model reconstruction. Experimental results show that our method exhibits greater 19 robustness to challenging poses compared to traditional single-scale approaches.

This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an Attention Mechanism designed to predict students' academic performance. The model concurrently addresses two tasks: predicting overall performance (total score) as a regression task and categorizing performance levels (remarks) as a classification task. By processing both tasks simultaneously, the model optimizes computational efficiency and resource use. The dataset includes detailed student performance records across various metrics such as Continuous Assessment, Practical Skills, Demeanor, Presentation Quality, Attendance, and Participation. The model's performance was evaluated using comprehensive metrics. For the regression task, it achieved a Mean Absolute Error (MAE) of 0.0249, Mean Squared Error (MSE) of 0.0012, and Root Mean Squared Error (RMSE) of 0.0346. For the classification task, it attained perfect scores with an accuracy, precision, recall, and F1 score of 1.0. These results highlight the model's high accuracy and robustness in predicting both continuous and categorical outcomes. The Attention Mechanism enhances the model's capabilities by identifying and focusing on the most relevant features. This study demonstrates the effectiveness of the Multi-Task LSTM with Attention Mechanism in educational data analysis, offering a reliable tool for predicting student performance and potential broader applications in similar multi-task learning contexts. Future work will explore further enhancements and wider applications to improve predictive accuracy and efficiency.

The detection accuracy of bridge superficial defect using the deep neural network approach decreases significantly under light variation and weak texture condition. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network-attention-YOLO (DAC-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s-1.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

Past research suggests a continuity between perception and memory, as reflected in influences of orienting of spatial attention by cues presented after a visual target offset (post-target cues) on target perception. Conducting two experiments, we tested and confirmed this claim. Our study revealed an elevated reliance on post-target cues for target detection with diminishing target visibility, leading to better performance in validly versus invalidly cued trials, indicative for contrast gain. We demonstrated this post-target cueing impact on target perception without a postcue response prompt, meaning that our results truly reflected a continuity between perception and memory rather than a task-specific impact of having to memorize the target due to a response prompt. We further showed an influence of attention by the post-target cues with cues presented away from a clearly visible target, meaning that visual interactions at the target location provided no better explanation of our results. Our results generalize prior research with liminal targets and confirm the view of a perception-memory continuum, so that visual target processing is not shielded against visuospatial orienting of attention elicited by events following offset of the visual target.

Street view images can help us better understand the city environment and potential characteristics. With the development of computer vision and deep learning, the technology of semantic segmentation algorithms has become more mature. However, DeeplabV3+, which is commonly used in semantic segmentation, has shortcomings such as a large number of parameters, high requirements for computing resources, and easy loss of detailed information. Therefore, this paper proposes LM-DeeplabV3+, which aims to greatly reduce parameters and computations of the model while ensuring the segmentation accuracy. Firstly, the lightweight network MobileNetV2 is selected as the backbone network, and the ECA attention mechanism is introduced after MobileNetV2 extracts shallow features to improve the ability of feature representation; secondly, the ASPP module is improved, and on its basis, the EPSA attention mechanism is introduced to achieve cross-dimensional channel attention and important feature interaction; thirdly, a loss function named CL loss is designed to balance the training offset of multiple categories and better indicate the segmentation quality. This paper conducted experimental verification on the Cityspaces dataset, and the results showed that the mIoU reached 74.9%, which was an improvement of 3.56% compared to DeeplabV3+; the mPA reached 83.01%, which was an improvement of 2.53% compared to DeeplabV3+.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method Let-Net(Large kernel and attention mechanism Network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to broaden the receptive field and incorporates depthwise convolution with residual connections to reduce parameter count. Secondly, Let-Net integrates an attention mechanism to enhance the information flows in channels and spaces for more comprehensive and distinctive FV feature extraction. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

The Trail Making Test (TMT) is one of the most commonly administered tests in clinical and research neuropsychological settings. The two parts of the test [part A (TMT-A) and part B (TMT-B)] enable the evaluation of visuoperceptual tracking and processing speed (TMT-A), as well as divided attention, set-shifting and cognitive flexibility (TMT-B). The main cognitive processes that are assessed using TMT, i.e. processing speed, divided attention and cognitive flexibility, are often affected in patients with stroke. Considering the wide use of TMT in research and clinical settings since its introduction in neuropsychological practice, the purpose of our review was to provide a comprehensive overview on the use of TMT in stroke patients in an attempt to mainly identify its role for the evaluation of post-stroke cognitive dysfunction and progression over time, the identification of the underlying neuroanatomical pathology related to impaired TMT performance, and the association with other stroke outcomes, such motor function, driving ability and quality of life. Our comprehensive review underscores that the TMT stands as an invaluable asset in the stroke assessment toolkit, contributing nuanced insights into diverse cognitive, functional, and emotional dimensions. As research progresses, continued exploration of the TMT potential across these domains is encouraged, fostering a deeper comprehension of post-stroke dynamics, and enhancing patient-centered care across hospitals, rehabilitation centers, research institutions, and community health settings. Its integration into both research and clinical practice reaffirms TMT status as an indispensable instrument in stroke-related evaluations, enabling holistic insights that extend beyond traditional neurological assessments.

In recent years, there has been significant growth in the ubiquity and popularity of three dimensional(3D) point clouds, with an increasing focus on the classification of 3D point clouds. To extract richer features from point clouds, many researchers have turned their attention to various point set regions and channels within irregular point clouds. However, this approach has limited capability in attending to crucial regions of interest in 3D point clouds and may overlook valuable information from neighboring features during feature aggregation. Therefore, this paper proposes a novel 3D point cloud classification method based on global attention and adaptive graph convolution. The method consists of two main branches: the first branch com-putes attention masks for each point, while the second branch employs adaptive graph convolu-tion to extract global features from the point set. It dynamically learns features based on point interactions, generating adaptive kernels to effectively and precisely capture diverse relationships among points from different semantic parts. Experimental results demonstrate that the proposed model achieves 93.8% in overall accuracy and 90.8% in average accuracy on the ModeNet40 dataset.

Machinery degradation assessment can offer meaningful prognosis and health management in-formation. Although numerous machine prediction models based on artificial intelligence have emerged in recent years, they still face a series of challenges: (1) Many models continue to rely on manual feature extraction. (2) Deep learning models still struggle with long sequence prediction tasks. (3) Health indicators are inefficient for remaining useful life (RUL) prediction with cross-operational environments when dealing with high-dimensional datasets as inputs. This research proposes a health indicator construction methodology based on a transformer self-attention transfer network (TSTN). This methodology can directly deal with the high-dimensional raw dataset and keep all the information without missing when the signals are taken as the input of the diagnosis and prognosis model. First, we design an encoder with a long-term and short-term self-attention mechanism to capture crucial time-varying information from a high-dimensional dataset. Second, we propose an estimator that can map the embedding from the encoder output to the estimated degradation trends. Then, we present a domain dis-criminator to extract invariant features from different machine operating conditions. The case studies with the FEMTO-ST bearing dataset and the Monte Carlo method for RUL prediction during the degradation process are conducted. The experiment results fully exhibited the signif-icant advantages of the proposed method compared to other state-of-the-art techniques.

To address the deficiency of existing relation extraction models in effectively extracting relational triplets pertaining to railway traffic knowledge in Tibet, this paper constructs a Tibet Railway Traffic text dataset and provides an enhanced relation extraction model. The proposed model incorporates subject feature enhancement and relational attention mechanisms. It leverages a pre-trained model as the embedding layer to obtain vector representations of text. Subsequently, the subject is extracted and its semantic information is augmented using an LSTM neural network. Furthermore, during object extraction, the multi-head attention mechanism enables the model to prioritize relations associated with the aforementioned features. Finally, objects are extracted based on the subjects and relations. The proposed method has been comprehensively evaluated on multiple datasets, including the Tibet Railway Traffic text dataset and two public datasets. The results on the Tibet dataset achieves an F1-score of 93.3\%, surpassing the baseline model CasRel by 0.8\%, indicating a superior applicability of the proposed model. On the other hand, the model achieves F1-scores of 91.1\% and 92.6\% on two public datasets, NYT and WebNLG, respectively, outperforming the baseline CasRel by 1.5\% and 0.8\%, which highlights the good generalization ability of the proposed model.

The Gestalt psychologists’ theory of insight problem-solving was based on a direct parallelism between perceptual experience and higher-order forms of cognition (e.g., problem-solving). Simi-larly to the sudden recognition of an ambiguous figure, they contended that problem-solving in-volves a restructuring of one's initial representation of the problem’s elements, leading to a sud-den leap of understanding phenomenologically indexed by the "Aha!" feeling. Over the last centu-ry, different scholars discussed the validity of the Gestalt psychologists’ perspective foremost us-ing the behavioral measures available at the time. However, in the last 2 decades, scientists gained a deeper understanding of insight problem-solving due to the advancements in cognitive neuroscience. This review aims to provide a retrospective reading of Gestalt theory based on the knowledge accrued by adopting novel paradigms and investigating their neurophysiological correlates. Among several key points that the Gestalt psychologists underscored, we focus specif-ically on the role of the visual system in marking a discrete switch of knowledge into awareness, as well as the perceptual experience and the holistic standpoints. While the main goal of this paper is to read the previous theory in light of new evidence, we also hope to initiate an academic dis-cussion and encourage further research about the points we raise.

Mindfulness interventions have been implemented in many countries. This study aimed to examine the psychometric properties of English and Thai-version of the 15-item mindfulness attention awareness scale (MAAS) across five samples. A descriptive correlation research was conducted in the Philippines and Thailand, and five data sets were generated using self-reported and online questionnaires. Exploratory factor analyses were used to explore the factorial structure of the MAAS. Confirmatory factor analyses were performed to test measurement invariance across samples. Concurrent validity was tested by examining relationships between the MAAS and psychological well-being (PWB). A unidimensional structure of the MAAS was documented across the five samples. The MAAS demonstrated measurement invariance across samples for both English and Thai versions. Concurrent validity was displayed through significant correlations with PWB. This study produced evidence to support the construct validity, concurrent validity, and reliability of the English and Thai versions of MAAS. This study was not registered.

Remote sensing imagery is of great significance for policy decisions, especially for disaster assessment and disaster relief. To ensure the privacy and inviolability of personal buildings, the information containing these buildings must be anonymized during the remote sensing mapping process. Traditional processing methods for these targets in remote sensing mapping are mainly based on manual retrieval and image editing tools, which are inefficient. Deep learning provides a new direction for target hiding. Although the image inpainting method based on deep learning is faster than the manual method, the cost of training calculation is a disadvantage. And the element-wise product operation used in the model increases the risk of vanished or exploded gradients. We propose a Residual Attention Target Hiding (RATH) model for remote sensing target hiding based on deep learning. RATH uses residual attention modules to replace gated convolutions, reducing parameters and mitigating gradient issues. The residual attention module preserves gated convolution performance but provides an adjustable kernel size. RATH retains gated convolutions for dynamic feature selection and balances model depth and width. Furthermore, this paper modifies the contextual attention layer by adjusting the fusion process to enlarge the fusion patch size. Finally, we extend the edge-guided function to preserve the original target information and confound viewers. Ablation studies on an open dataset prove RATH’s efficiency for image inpainting and target hiding. RATH achieves state-of-the-art results with lower complexity. And it has the highest similarity for edge-guided target hiding. RATH enables robust, efficient target hiding for privacy protection in remote sensing imagery while balancing performance and complexity. Experiments show RATH's superiority over existing methods in hiding arbitrary-shaped targets.

This paper proposes a Grouped Contrastive Learning of self-supervised Sentence Representation (GCLSR), which can learn an effective and meaningful representation of sentences. Previous works maximize the similarity between two vectors to be the objective of contrastive learning, suffering from the high-dimensionality of the vectors. In addition, most previous works have adopted discrete data augmentation to obtain positive samples and directly employed contrastive framework of computer vision to perform contrastive training, which could hamper contrastive training because text data is discrete and sparse compared with image data. To address those issues, we propose a grouped contrastive learning framework, i.e., GCLSR, which divides the high-dimensional feature vector into several groups and respectively computes the groups’ contrastive losses to make use of more local information, eventually obtaining a more fine-grained sentence representation. In addition, in GCLSR, we design a new self-attention mechanism and a continuous as well as partial word vector augmentation (PWVA). For the discrete and sparse text data, the usage of self-attention could help model focus the informative words by measuring the importance of every word in a sentence. By using the PWVA, GCLSR can obtain high-quality positive samples used for contrastive learning. Experimental results demonstrate that our proposed GCLSR achieves an encouraging result on the challenging datasets of the standard semantic textual similarity (STS) task and transfer task.

Target recognition mainly includes three approaches: optical image-based, echo detection-based, and passive signal analysis-based methods. Among them, the passive signal-based method is closely integrated with practical applications due to its strong environmental adaptability. Based on passive radar signal analysis, we design an "end-to-end" model that cascades a noise estimation network with a recognition network to identify working modes in noise environment. The noise estimation network is implemented based on U-Net, which adopts a method of feature extraction and reconstruction to adaptively estimate the noise mapping level of the sample, which can help the recognition network to reduce noise interference. Focusing on the characteristics of radar signal, the recognition network is realized based on Multi-Scale Convolutional Attention Network (MSCANet). Firstly, the deep group convolution is used to isolate the channel interaction in the shallow network. Then, through the multi-scale convolution module, finer-grained features of the signal are extracted without increasing the complexity of the model. Finally, the self-attention mechanism is used to suppress the influence of low-correlation and negative-correlation channels and spaces. This method overcomes the problem that the conventional method is seriously disturbed by noise. We validated the proposed method in 81 kinds of noise environments, achieving an average accuracy of 94.65%. Additionally, we discussed the performance of six machine learning algorithms and four deep learning algorithms. Compared to these methods, proposed MSCANet achieved an accuracy improvement of approximately 17%. Our method demonstrates better generalization and robustness.

Fine-grained image classification remains an ongoing challenge in the computer vision field, which is particularly intended to identify objects within sub-categories. It is a difficult task since there is a minimal and substantial intra-class variance. The current methods address the issue by first locating selective regions with Region Proposal Networks (RPN), object localization, or part localization, followed by implementing a CNN Network or SVM classifier to those selective regions. This approach, however, makes the process simple by implementing a single-stage end-to-end feature encoding with a localization method, which leads to improved feature representations of individual tokens/regions by integrating the transformer encoder blocks into the Yolov5 backbone structure. These Transformer Encoder Blocks, with their self-attention mechanism, effectively captured the global dependencies and enabled the model to learn relationships between distant regions. This improved the model ability to understand context and captured long-range spatial relationships in the image. We also replaced the Yolov5 detection heads with three transformer heads at the output for object recognition using the discriminative and informative features maps from transformer encoder blocks. We established the potential of the single stage detector for the fine-grained image recognition task, by achieving state of the art 93.4% accuracy, as well as outperforming the existing Yolov5 model. The effectiveness of our approach is assessed using the Stanford car dataset, which includes 16,185 images of 196 different classes of vehicles with significantly identical visual appearances.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and patho-logical detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse at-tention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edge features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy re-duces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation tech-niques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare profes-sionals.

Forest fires are one of the world's deadliest natural disasters. Early detection of forest fires can help minimize the damage to ecosystems and forest life. In this paper, we propose an improved fire detection method YOLOv5-IFFDM for YOLOv5. Firstly, the fire and smoke detection accuracy and the network perception accuracy of small targets are improved by adding attention mechanism in the backbone network. Secondly, the loss function is improved and the SoftPool pyramid pooling structure is used to improve the regression accuracy and detection effect of the model and the robustness of the model. In addition, random Mosaic augmentation technique is used to enhance the data to increase the generalization ability of the model, and re-clustering of flame and smoke detection a priori frames are used to improve the accuracy and speed. Finally, the parameters of the convolutional and normalization layers of the trained model are homogeneously merged to further reduce the model responsibility to improve the detection speed. Experimental results on homemade forest fire and smoke datasets show that this algorithm has high detection accuracy and fast detection speed, with average accuracy of fire up to 90.5% and smoke up to 84.3%, and detection speed up to 75 FPS (frames per second transmission), which can meet the requirements of real-time and efficient fire detection.

This article presents a low-cost and flexible solution for acoustic startle response (ASR) tests that can be used in any laboratory with CED Power1401 or a similar Spike2-based interface. ASR is a reflexive response to an unexpected, loud acoustic stimulus, and prepulse inhibition (PPI) is a phenomenon in which the startle response is reduced when preceded by a weak prestimulus of the same modality. Measuring PPI is important because changes in PPI have been observed in patients with various psychiatric and neurological disorders. Commercial ASR testing systems are expensive, and their closed source code affects their transparency and result reproducibility. The proposed setup is easy to install and use, and simultaneous recording of ASR and brain activity (electrocorticogram or intracerebral local field potential) is possible. The Spike2 script is customizable and supports a wide range of PPI protocols. The article presents data obtained in female rats, both wild-type (WT) and dopamine transporter knockout (DAT-KO), showing the same tendency as the data obtained in males, with ASR on single pulse higher than ASR on prepulse+pulse, and PPI reduced in DAT-KO rats compared to WT.

The multi-modal data fusion method based on IA-net and CHMM technical proposed is designed to solve the problem that the incompleteness of target behavior information in complex family environment leads to the low accuracy of human behavior recognition.The two improved neural networks(STA-ResNet50、STA-GoogleNet)are combined with LSTM to form two IA-Nets respectively to extract RGB and skeleton modal behavior features in video. The two modal feature sequences are input CHMM to construct the probability fusion model of multi-modal behavior recognition.The experimental results show that the human behavior recognition model proposed in this paper has higher accuracy than the previous fusion methods on HMDB51 and UCF101 datasets. New contributions: attention mechanism is introduced to improve the efficiency of video target feature extraction and utilization. A skeleton based feature extraction framework is proposed, which can be used for human behavior recognition in complex environment. In the field of human behavior recognition, probability theory and neural network are cleverly combined and applied, which provides a new method for multi-modal information fusion.

Abstract Epilepsy is a disorder of the brain and a seriously debilitating condition, which has been associated with injury, social stigmatisation and in some cases, sudden unexpected and premature death. A sense of profound isolation is felt by many individuals with epilepsy, and this community has expressed an urgent desire for an early warning system to allow them time to prepare for seizure onset. Surveys of dog owners with epilepsy have previously reported that some dogs can predict the onset of a seizure. The current study used an experimental design to investigate the alleged propensity of untrained pet dogs to react to human epileptic seizures. We hypothesised that seizures are associated with specific volatile organic compounds resulting in detectable odours which are the biomarker that triggers these reported behavioural changes in the dogs. Here we provide details of the first empirical test to demonstrate that pet dogs display several significant behavioural changes when they are exposed to seizure-related odours that apparently emanate from their owners. Using a repeated measures design experiment, recordings were made of the reactions of 19 untrained pet dogs to odours from sweat samples provided by three people with epilepsy and by two people without epilepsy (controls). The seizure-associated sweat samples were captured pre-seizure, during seizure and post-seizure. All samples were randomly delivered to individual dogs in a test area, using two bespoke pieces of apparatus called Remote Odour Delivery Mechanisms (RODM). One RODM delivered only experimental odours, the other delivered only control odours. Behavioural changes by the dogs on encountering the odour samples were recorded by video for later analysis. Consistent with our hypothesis, seizure-associated odours evoked significant behavioural changes in the dogs which were affiliative in nature and directed at their owners.

Over the past decade, China has witnessed fast-paced technological advancements in the media industry, as well as major shifts in the health agenda portrayed in the media. Therefore, a key starting point when discussing health communication lies in whether media attention and public attention towards health issues are structurally aligned, and to what extent the news media guide public attention. Based on data mined from 73,060 sets of the Baidu Search Index and Media Index on 20 terms covering different types of cancer from 2011 to 2020, the Granger test demonstrates that, in the last decade, public attention and media attention towards cancer in China has gone through two distinct phases. During the first phase, 2011-2015, Chinese news media still held the key in transferring the salience of issues on most cancer types to the public. In the second phase, from 2016-2020, public attention towards cancer has gradually diverged from media coverage, mirroring the imbalance and mismatch between the demand of active public and the supply of cancer information from news media. This study provides an overview of the dynamic transition on cancer issues in China over a ten-year span, along with descriptive results on public and media attention towards specific cancer types.

Abstract Women victims of abuse can suffer neuropsychological sequelae that affect memory and attention, as well psychopathological disorders such as depression. These consequences affect their daily life and physical and psychological health. Objective: To analyze sequelae that affect attention and memory, as well a possible association of these sequelae to depression. Method: A total of 68 women victims of gender-based violence participated in the study. The participants were between 15 and 62 years of age and resided in Spain at the time of data collection. The Luria DNA Battery (Neuropsychological Diagnosis of Adults) by Manga and Ramos (2000); and the Beck Depression Inventory were applied. Results: Women victims of gender-based violence suffer neuropsychological sequelae, presenting low short-term memory and attentional control; and score low on the Luria-DNA battery. Of these women, 60% suffer from some relevant type of depression, and there are significant differences according to their degree of memory. Through the HJ-Biplot, a direct relationship was found between memory and attentional control with the total score of the Luria battery. On the other hand, an inverse relationship was found between short-term memory and depression. Lastly, three well-differentiated gender clusters of women victims of gender-based violence were identified. Conclusions: A lower rate of depression is observed in women victims of abuse when they have a more intact short-term memory.

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

The latest research cumulates staggering information about the correlation between the microbiota-gut-brain axis and neurodevelopmental disorders. This review aims to shed light on the potential influence of the microbiome on the development of the most prevalent neurodevelopmental disease, attention-deficit-hyperactive disorder (ADHD). As the etiology and pathophysiology of ADHD are still unclear, finding viable biomarkers and effective treatment still represent a challenge. Therefore, we focused on factors that have been associated with a higher risk of developing ADHD while simultaneously influencing the microbial composition. We reviewed the effect of a differing microbial composition on neurotransmitter concentrations important in the pathophysiology of ADHD. Additionally, we deduced factors that correlate with a high prevalence of ADHD while simultaneously affecting the gut microbiome such as emergency c-sections, and premature birth as the former leads to a decrease of the gut microbial diversity and the latter causes neuroprotective Lactobacillus levels to be reduced. Also, we assessed nutritional influences such as breastfeeding, ingestion of short-chain fatty acids (SCFAs) and polyunsaturated fatty acids (PUFAs) on the host’s microbiome and development of ADHD. Finally, we discussed the potential significance of Bifidobacterium as a biomarker for ADHD, the importance of preventing premature birth as prophylaxis and nutrition as a prospective therapeutic measurement against ADHD.

Visual question answering (VQA) is receiving increasing attention from researchers in both the computer vision and natural language processing fields. There are two key components in the VQA task: feature extraction and multi-modal fusion. For feature extraction, we introduce a novel co-attention scheme by combining Sentence-guide Word Attention (SWA) and Question-guide Image Attention (QIA) in a unified framework. To be specific, the textual attention SWA relies on the semantics of the whole question sentence to calculate contributions of different question words for text representation. For the multi-modal fusion, we propose a “Cross-modal Multistep Fusion (CMF)” network to generate multistep features and achieve multiple interactions for two modalities, rather than focusing on modeling complex interactions between two modals like most current feature fusion methods. To avoid the linear increase of the computational cost, we share the parameters for each step in the CMF. Extensive experiments demonstrate that the proposed method can achieve competitive or better performance than the state-of-the-art.

On using a 3D model to teach students a topic in astronomy, feedback was evaluated via a questionnaire. Analysis of students' responses to the questions revealed that user interface had a significant impact on their attitudes, which in turn could increase users' willingness to use immersive technology in e-learning. The results also showed that improving visual features through immersive technology and augmented reality tools were effective. The results confirm all hypotheses about positive relationships between facilitating conditions and usability of metaverse technology for students' attention and study motivation.

In recent years there has been an increasing interest in developing novel materials based on natural biopolymers as a renewable alternative of petroleum-based plastics. The availability of proteins derived from agricultural by-products, along with their favourable properties, has fostered a renewed interest in protein-based materials, promoting research in innovative technologies. In this study we propose the use of rapeseed protein-rich meal as main ingredient for the preparation of novel sustainable materials combining excellent environmental properties such as biodegradability and renewable origin. Application as sustainable products in the present high-tech society needs modification of basic native properties of these natural compounds. The original route proposed in this paper consists in the preparation via compression moulding of flexible biomaterials stabilized by crosslinkers/chain extenders. Investigation of the effects of different denaturing and disulfide bond reducing agents, crosslinkers, and preparation conditions on the material mechanical behaviour demonstrated that the novel materials have appreciable strength and stiffness. The results show the potential of utilizing full meal from vegetable by-products to prepare protein-based materials with granted ecofriendly characteristics and mechanical properties adequate to specific structural applications.

Speech emotion recognition (SER) is important in facilitating natural human-computer interactions. In speech sequence modelling, a vital challenge is to learn context-aware sentence expression and temporal dynamics of para-linguistic features to achieve unambiguous emotional semantic understand-ing. In previous studies, the SER method based on the single-scale cascade feature extraction module could not effectively preserve the temporal structure of speech signals in the deep layer, downgrading the sequence modeling performance. In this paper, we propose a novel multi-scale feature pyramid network to mitigate the above limitations. With the aid of the bi-directional feature fusion of the pyramid network, the emotional representation with adequate temporal semantics is obtained. Experiments on the IEMOCAP corpus demonstrate the effectiveness of the proposed methods and achieve competitive results under speaker-independent validation.

This paper explores the use of GNN architectures, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), and GraphSAGE, in modeling blockchain data. A specific focus is given to their applications in cryptocurrency transaction networks, where GNNs can detect fraudulent activities and track illicit fund flows by learning from transaction patterns and network structure. Additionally, future directions for GNN research in blockchain are discussed, including scalability challenges, privacy-preserving models, and multi-chain graph analysis. Through these advancements, GNNs offer significant potential for enhancing the security, transparency, and efficiency of blockchain and cryptocurrency ecosystems. This paper also shows an example of fraud detection for Ethereum cryptocurrencies.

Vehicle logo detection plays a crucial role in various computer vision applications, such as vehicle classification and detection. In this research, we propose an improved vehicle logo detection method leveraging the MAMBA structure. The MAMBA structure integrates multiple attention mechanisms and bidirectional feature aggregation to enhance the discriminative power of the detection model. Specifically, we introduce the Multi-Head Attention for Multi-Scale Feature Fusion (MHAMFF) module to capture multi-scale contextual information effectively. Moreover, we incorporate the Bidirectional Aggregation Mechanism (BAM) to facilitate information exchange between different layers of the detection network. Experimental results on a benchmark dataset (VLD-45 dataset) demonstrate that our proposed method outperforms baseline models in terms of both detection accuracy and efficiency. Furthermore, extensive ablation studies validate the effectiveness of each component in the MAMBA structure. Overall, the proposed MAMBA-based vehicle logo detection approach shows promising potential for real-world applications in intelligent transportation systems.

This study analyzes the scholarly landscape of data literacy through citation and co-citation analyses of documents, sources, and authors. Using Scopus data and VOSviewer, the study identifies significant contributions and thematic trends. A minimum criterion of 10 citations per document was applied, filtering the dataset to 205 documents, with a focus on 81 interlinked documents. Citation analysis covered document, source, and author metrics, while co-citation analysis examined cited authors, sources, and references. The study found 997 documents on data literacy, narrowed down to 205 significant ones, with 81 interlinked documents showing a high average citation rate. Key sources included the ACM International Conference Proceeding Series and Teachers College Record, and prominent authors like Ellen B. Mandinach and Kim Schildkamp emerged as central figures. Data literacy research spans fields like education, sociology, and information science, highlighting its interdisciplinary nature. The study's focus on citation metrics may introduce selection bias, emphasizing widely cited works. Future research could explore less-cited but influential works and broader datasets to mitigate biases. Policymakers can use these insights to integrate data literacy into educational curricula and design targeted professional development programs. Promoting interdisciplinary collaboration and supporting open access to scholarly literature can enhance data literacy initiatives. This study provides a comprehensive citation and co-citation analysis of data literacy research, offering valuable insights into key contributions and thematic trends, informing policy and practice, and underscoring the importance of data literacy in contemporary education and society.

In recent years, electroencephalogram (EEG) emotion recognition has emerged as a research hotspot in the field of artificial intelligence (AI). Despite advancements in EEG-based emotion recognition, room for enhancing performance persists due to EEG signal redundancy and limitations in feature extraction, leading to inefficient models and emotional information loss. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification, and 97.69% and 98.05% in ternary classification, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

Attention-Deficit/Hyperactivity Disorder (ADHD) is traditionally conceptualized within a framework emphasizing deficits in attention regulation and executive function. However, emerging evidence from the fields of predictive coding and active inference offers a novel lens through which to understand ADHD not merely as a disorder of attention but as a distinctive mode of neurodevelopmental variation. This article synthesizes current research and theoretical models to propose a redefined understanding of ADHD. By integrating insights from Ryan Smith, Paul B. Badcock, and Karl J. Friston (2020), we explore the premise that individuals with ADHD exhibit unique differences in how their brains generate and update predictions about the environment, leading to the characteristic behavioral patterns observed in ADHD. We argue that ADHD involves a divergence in the brain's predictive models and its ability to minimize prediction error, impacting sensory processing, attention allocation, and motor control. This perspective illuminates the adaptive aspects of ADHD, suggesting that what are often labeled as deficits could also reflect an adaptive fit to certain environmental contexts, underscoring the role of neurodiversity in human evolution. Furthermore, we discuss the implications of this reconceptualization for clinical practice, including diagnosis, treatment, and support for individuals with ADHD, emphasizing approaches that align with their unique neurocognitive profiles. This article calls for a shift in the narrative surrounding ADHD, advocating for a model that appreciates the complexity and adaptiveness of neurodevelopmental diversity.

Accurate crop diseases classification is crucial for ensuring food security and enhancing agricultural productivity. However, existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhances multimodal synergy for better crop disease classification than traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to using solely the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing prompt quality. Secondly, we integrate the cross-attention and the SE (Squeeze-and-Excitation) attention into the training-free mode VLCD (Vision-Language model for Crop Diseases classification) and the training-required mode VLCD-T (VLCD-Training) respectively for prompt text processing, enhancing classifier weights by emphasizing key text features. Experimental outcomes conclusively prove our method’s heightened classification effectiveness in few-shot crop disease scenarios, tackling data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

Mulberry leaves, when infected by pathogens, can suffer significant yield loss or even death if early disease detection and timely spraying are not performed. To enhance the detection performance of mulberry leaf diseases in natural environments and to precisely locate early small lesions, we propose a high-precision, high-efficiency disease detection algorithm named YOLOv8-RFMD. Based on improvements to You Only Look Once version 8 (YOLOv8), we first proposed the Multi Dimension Feature Attention (MDFA) module, which integrates important features at the pixel-level, spatial and channel dimensions. Building on this, we designed the RFMD Module, which consists of the Conv-BatchNomalization-SiLU (CBS) module, Receptive-Field Coordinated Attention (RFCA) Conv, and MDFA, replacing the Bottleneck in the model’s Residual block. We then employed Adown down sampling structure to reduce the model size and computational complexity. Finally, to improve the detection precision of small lesion features, we replaced the complete intersection over union (CIOU) loss function with the Normalized Wasserstein Distance (NWD) loss function. Results show that the YOLOv8-RFMD model achieves an mAP50 of 94.3% and an mAP50:95 of 67.8% on experimental data, representing increases of 2.9% and 4.3% respectively compared to the original model. The model size is reduced by 0.53 MB to just 5.45 MB, and the number of floating-point operations is reduced by 0.3 G to only 7.8 G. The improved model meets the deployment requirements of mobile embedded devices and can provide a theoretical reference for the automated spraying operations of mulberry leaves.

Ensuring the accuracy of wind power prediction is paramount for the reliable and stable operation of power systems. This study introduces a novel approach aimed at enhancing the precision of wind power prediction through the development of a multiscale hybrid model. This model integrates advanced methodologies including Improved Intrinsic Mode Function with Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Permutation Entropy(PE), Least Squares Support Vector Regression (LSSVR), Regularized Extreme Learning Machine(RELM), Multi-head Attention (MHA), and Bidirectional Gated Recurrent Unit (BiGRU). Firstly, the ICEEMDAN technique is employed to decompose the non-stationary raw wind power data into multiple relatively stable sub-modes, while concurrently utilizing PE to assess the complexity of each sub-mode. Secondly, the dataset is reconstituted into three distinct components: high-frequency, mid-frequency, and low-frequency, to alleviate data complexity. Following this, the LSSVR, RELM, and MHA-BiGRU models are individually applied to predict the high, mid,and low-frequency components, respectively. Thirdly, the parameters of the low-frequency prediction model are optimized utilizing the Dung Betele Optimizer(DBO) algorithm. Ultimately, the predicted results of each component are aggregated to derive the final prediction. Empirical findings illustrate the exceptional predictive performance of the multiscale hybrid model incorporating LSSVR, RELM,and MHA-BiGRU. In comparison to other benchmark models, the proposed model exhibits a reduction in Root Mean Square Error(RMSE) values of over 10%, conclusively affirming its superior predictive accuracy.

In this essay, I revisit Neural Networks (NNs) through the lens of evolutionary dynamics. From the two most important features of NNs, I recover the two most general equations of evolutionary dynamics. These two equations may thus serve as a connection between NNs and a body of knowledge that has been built over multiple centuries and has found application across a vast range of disciplines. This connection may therefore also help explain why NNs with the two features in question are applicable across a much broader range of domains than initially envisioned.

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate that MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

IIt is important that Master’s Degree students in psychology, regardless of their future specialisa-tion, know about Attention Deficit Hyperactivity Disorder (ADHD). The aim is evaluate and an-alyse the ADHD-related knowledge held by students of Early Childhood Education and Primary Education. The findings that were obtained in this study (on the chronicity of the disorder, changes in manifestations throughout the life cycle, and the importance of early and multidisci-plinary intervention) have clear implications in relation to the specific training in ADHD for fu-ture teachers. It is essential to broaden the specific training in relation to ADHD in studies for the Master’s Degrees in Early Childhood Education and Primary Education and through contin-uous training.

The images captured by UAVs during inspection often contain numerous small targets related to transmission lines, which are critical and vulnerable elements for ensuring the safe operation of these lines. However, due to various factors such as the small size of the targets, low resolution, complex background, and potential line aggregation, achieving accurate and real-time detection becomes challenging. To address these issues, this paper proposes a detection algorithm called P2-ECA-EIOU-YOLOv5 (P2E-YOLOv5). Firstly, in order to address the challenges posed by the complex background and environmental interference that impact small targets, an ECA attention module is integrated into the network. This module effectively enhances the network's focus on small targets while concurrently mitigating the influence of environmental interference. Secondly, considering the characteristics of small target size and low resolution, a new high-resolution detection head is introduced, which is more sensitive to small targets. Lastly, the network utilizes the EIOU-Loss as the regression Loss function to improve the positioning accuracy of small targets, as they tend to aggregate. Experimental results demonstrate that the proposed P2E-YOLOv5 detection algorithm achieves an accuracy P of 96.0% and an average accuracy (mAP) of 97.0% for small target detection in transmission lines.

Infrared detection plays an important role in the military, aerospace, and other fields, which has the advantages of all-weather, high stealth, and strong anti-interference. However, infrared dim small target detection suffers from complex backgrounds, low signal-to-noise ratio, blurred targets with small area percentages, and other challenges. In this paper, we proposed a multiscale YOLOv5-AFAM algorithm to realize high-accuracy and real-time detection. Aiming at the problem of target intra-class feature difference and inter-class feature similarity, the Adaptive Fusion Attention Module - AFAM was proposed to generate feature maps that are calculated to weigh the features in the network and make the network focus on small targets. This paper proposed a multiscale fusion structure to solve the problem of small and variable detection scales in infrared vehicle targets. In addition, the downsampling layer is improved by combining Maxpool and convolutional downsampling to reduce the number of model parameters and retain the texture information. For multiple scenarios, we constructed an infrared dim and small vehicle target detection dataset, ISVD. The multiscale YOLOv5-AFAM was conducted on the ISVD dataset, compared to YOLOv7, mAP@0.5 achieves a small improvement while the parameters are only 17.98% of it. By contrast with the YOLOv5s model, mAP@0.5 was improved by 4.3% with a 6.6% reduction in the parameters. Experiments results demonstrate that the multiscale YOLOv5-AFAM has a higher detection accuracy and detection speed on infrared dim and small vehicles.

Many theoretical models of iron-based superconductors have been proposed but Tc calculations based on the models are usually missing. We have chosen two models of iron-based superconductors in the literature and then compute the Tc values accordingly: Recently two models have been announced which suggest that superconducting electron concentration involved in the pairing mechanism of iron-based superconductors may have been underestimated, and that the antiferromagnetism and the induced xy potential may even have a dramatic amplification effect on electron-phonon coupling. We use bulk FeSe, LiFeAs and NaFeAs data to calculate the Tc based on these models and test if the combined model can predict the superconducting transition temperature (Tc) of the nanostructured FeSe monolayer well. To substantiate the recently announced xy potential in the literature, we create a two-channel model to separately superimpose the dynamics of the electron in the upper and lower tetrahedral plane. The results of our two-channel model support the literature data. While scientists are still searching for a universal DFT functional that can describe the pairing mechanism of all iron-based superconductors, we base on the ARPES data to propose an empirical combination of DFT functional for revising the electron-phonon scattering matrix in the superconducting state, which ensures that all electrons involved in iron-based superconductivity are included in the computation. Our computational model takes into account this amplifying effect of antiferromagnetism and the correction of the electron-phonon scattering matrix together with the abnormal soft out-of-plane lattice vibration of the layered structure, which allows us to calculate theoretical Tc values of LiFeAs, NaFeAs and FeSe as a function of pressure that correspond reasonably well to the experimental values. More importantly, by taking into account the interfacial effect between an FeSe monolayer and its SrTiO3 substrate as an additional gain factor, our calculated Tc value is up to 91 K high, and provides evidence that the strong Tc enhancement recently observed in such monolayers with Tc reaching 100 K may be contributed from the electrons within the ARPES range.

Coastal zones, although vital for human livelihoods and environmental services, are increasingly vulnerable to climate change, especially communities dependent on marine ecosystems. These areas face significant threats from urbanization, population growth, and climate impacts, leading to biodiversity loss and ecosystem degradation. Recognizing these challenges, the United Nations declared 2021--2030 the Decade for Ecosystem Restoration, led by the UNEP and FAO, with the aim of restoring degraded ecosystems to achieve sustainable development goals (SDGs). The link between healthy ecosystems and disaster risk reduction (DRR) has gained global prominence, especially through the Sendai Framework for Disaster Risk Reduction (SFDRR), which emphasizes the importance of ecosystems in mitigating risks. Despite this, many tools for assessing risks in different ecosystem scenarios remain inaccessible to key stakeholders in disaster management. Advances in spatial modelling have supported ecosystem management, policy-making, and ecosystem health assessment, particularly following the Millennium Ecosystem Assessment. These models have been applied in regions such as the Great Bahamas, Haiti, and the Republic of Congo, helping shape ecosystem-based approaches to development. Improving access to spatial tools and models is crucial to enabling effective ecosystem-based DRR and climate adaptation strategies.

One of the efficient data mining tools is density-based clustering, including the density grid-based clustering. However, a common drawback always existing in clusters made by the density grid-based method is the existence of weakly connected grids deriving mainly from noise. Appearing such an unwanted connection with a high frequency reduces the accuracy of the obtained cluster data space (CDS) and its application efficiency. Here, we present an essential improvement to overcome this problem. First, we describe a concept of the weak-connected grid cell (WCG) and present a fuzzy-type approximation to depict the density-based distribution of data points at grid nodes. Then, we propose a strategy of searching WCG for density grid-based clustering (SWCG-DGB) to set up a CDS, filter noise, and tune the created CDS. A buffer is deployed during this phase to collect border points and filter noise, which improves the computational time significantly, especially for noisy datasets. Results from numerical surveys reflected the compared efficiency of this method in clustering validity, including the accuracy of the number of clusters.

Mycobacterium tuberculosis (Mtb) is the etiological agent of tuberculosis (TB), a disease that alt-hough preventable and curable, remains a global epidemic due to the emergence of resistance and a latent form responsible for a long period of treatment. Drug discovery in TB is a challenging task due to the heterogeneity of the disease, the emergence of resistance and an uncomplete knowledge of the pathophysiology of the disease. The limited permeability of the cell wall and the presence of multiple efflux pumps remain a major barrier to achieve effective intracellular drug accumulation. While the complete genome sequence of Mtb has been determined and several potential protein targets have been validated, the lack of adequate models for in vitro and in vivo studies is a limit-ing factor in TB drug discovery programs. In current therapeutic regimens, less than 0.5% of bac-terial proteins are targeted being the biosynthesis of the cell wall and the energetic metabolism two of the most important processes exploited for TB chemotherapeutics. This review provides an overview on the current challenges in TB drug discovery and emerging Mtb druggable proteins, and how chemical probes for protein profiling enabled the identification of new targets and bi-omarkers, paving the way to disruptive therapeutic regimens and diagnostic tools.

Lake Rawapening, Semarang Regency, Indonesia, has incorporated a holistic plan in its management practices. However, despite successful target achievements, some limitations remain that a review of its management plan is needed. This paper identifies and analyzes existing lake management strategies as a standard specifically in Lake Rawapening by exploring various literature, both legal frameworks and scholarly articles indexed in Google Scholar and published in Water by MDPI about lake management in many countries. There are two major types of lake management, namely pillar-based and object-based. While the former is the foundation of a conceptual paradigm that does not comprehensively consider the roles of finance and technology in the lake management, the latter indicates the objects to manage so as to create standards or benchmarks for the implementation of various programs. Overall, Lake Rawapening management should include more programs on erosion-sedimentation control and monitoring of operational performance using information systems.

Nature-based solutions (NbS) are increasingly recognised for their potential to address both the climate and biodiversity crises. These outcomes are interdependent, and both rely on the capacity of NbS to support and enhance the health of an ecosystem: its biodiversity, the condition of its abiotic and biotic elements, and its capacity to function normally despite environmental change. However, while understanding of ecosystem health outcomes of nature-based interventions for climate change mitigation is growing, the outcomes of those implemented for adaptation remain poorly understood with evidence scattered across multiple disciplines. To address this, we conducted a systematic review of the outcomes of 109 nature-based interventions for climate change adaptation using 33 indicators of ecosystem health across eight broad categories (e.g. diversity, biomass, ecosystem functioning and population dynamics). We showed that 88% of interventions with positive outcomes for climate change adaptation also reported measurable benefits for ecosystem health. We also showed that interventions were associated with a 67% average increase in local species richness. All eight studies that reported benefits in terms of both climate change mitigation and adaptation also supported ecosystem health, leading to a triple win. However, there were also trade-offs, mainly for forest management and creation of novel ecosystems such as monoculture plantations of non-native species. Our review highlights two major limitations of research to date. First, only a limited selection of metrics are used to assess ecosystem health and these rarely include key aspects such as functional diversity and habitat connectivity. Second, taxonomic coverage is poor: 67% of outcomes assessed only plants and 57% did not distinguish between native and non-native species. Future research addressing these issues will allow the design and adaptive management of NbS to support healthy and resilient ecosystems, and thereby enhance their effectiveness for meeting both climate and biodiversity targets.

Internet of thing (IoT) has been used in different aspect of life as industry, and daily life. Aligned with IoT, Quantum computers have been generated with high features that can accomplish complicated tasks with high speed. IoT and Quantum computers don’t match in resources and due to this collaboration between the two terms, it was found there are many challenges with quantum computers brought some security concerns. This paper will examine all challenges and future direction that face the use of IoT through using different quantum cryptograph methods. The first part on the paper discussed the vulnerabilities of existing cryptographic methods like RSA and ECC. these two methods were used as basic level for IoT security protocols. These cryptographic algorithms could be easily attacked by quantum computers so to ensure that IoT devices are secure must develop quantum resistant cryptographic algorithms. Next this paper will examine the challenges in implementing quantum resistant cryptographic algorithm in any IoT device through quantum resistant cryptographic algorithms such as lattice-based cryptography, code-based cryptography, multivariate cryptography, and hash-based signatures. Then, the paper discussed the future direction of securing IoT in quantum computing. In conclusion, securing IoT devices in quantum presents many challenges that require to be addressed where quantum resistant algorithms can be a solution that mitigate threats.

In the context of smart agriculture, accurately estimating plant leaf chemical parameters is crucial for optimizing crop management and improving agricultural yield. Hyperspectral imaging, with its ability to capture detailed spectral information across various wavelengths, has emerged as a powerful tool in this regard. However, the complex and high-dimensional nature of hyperspectral data poses significant challenges in extracting meaningful features for precise estimation. To address this challenge, this study proposes an end-to-end estimation network for multiple chemical parameters of Astragalus leaves based on attention mechanism (AM) and multivariate hyperspectral features (AM-MHENet). We leveraging HybridSN and multilayer perception (MLP) to extract prominent features from the hyperspectral data of Astragalus membranaceus var. mongholicus (AMM) leaves and stems, as well as the surface and deep soil surrounding AMM roots. This methodology allows us to capture the most significant characteristics present in these hyperspectral data with high precision. The AM is subsequently used to assign weights and integrate the hyperspectral features extracted from different parts of the AMM. The MLP is then employed to simultaneously estimate the chlorophyll content (CC) and nitrogen content (NC) of AMM leaves. Compared with estimation networks that utilize only hyperspectral data from AMM leaves as input, our proposed end-to-end AM-MHENet demonstrates superior estimation performance. Specifically, AM-MHENet achieves an R2 of 0.983 with an RMSE of 0.73 for the estimation of CC in AMM leaves. For NC estimation, AM-MHENet achieves an R2 value of 0.977 with an RMSE of 0.27. These results underscore AM-MHENet’s effectiveness in significantly enhancing the accuracy of both CC and NC estimation in AMM leaves. Moreover, these findings indirectly suggest a strong correlation between the development of AMM leaves and stems, as well as the surface and deep soil surrounding the roots of AMM, and directly highlight the ability of AM to effectively focus on the relevant spectral features within the hyperspectral data. This findings from this study could offer valuable insights into the simultaneous estimation of multiple chemical parameters in plants, thereby making a contribution to the existing body of research in this field.

Attention mechanisms have become a fundamental component of deep learning, including the field of computer vision. The key idea behind attention in computer vision is to help the model focus on the relevant spatial regions of the input image, rather than treating all regions equally. The traditional approaches to attention mechanisms in computer vision often suffer from distribution inconsistencies in the attention maps, resulting in sharp transitions that negatively affect model’s focus and lead to poor generalization on complex shapes. The problem of spatial incoherence is particularly pronounced in the task of semantic segmentation, where accurate pixel-level predictions require a detailed understanding of the spatial relationships within the image. In this paper, we propose an attention mechanism called Smooth Attention designed for convolutional neural networks to address the problem of spatial inconsistency in attention maps through multidimensional spatial smoothing. We conduct a series of experiments to evaluate the effectiveness of the proposed mechanism and demonstrate its superior performance compared to traditional methods.

Drug development is a lengthy process with a high failure rate. Increasingly, machine learning is utilized to facilitate the drug development processes. These models aim to enhance our understanding of drug characteristics, including their activity in biological contexts. However, a major challenge in drug response (DR) prediction is model interpretability as it aids in the validation of findings. This is important in biomedicine, where models need to be understandable in comparison with established knowledge of drug interactions with proteins. drGAT, a graph deep learning model, leverages a heterogeneous graph composed of relationships between proteins, cell lines, and drugs. drGAT is designed with two objectives: DR prediction as a binary sensitivity prediction and elucidation of drug mechanism from attention coefficients. drGAT has demonstrated superior performance over existing models, achieving 78\% accuracy (and precision), and 76\% F1 score for 269 DNA-damaging compounds of the NCI60 drug response dataset. To assess the model's interpretability, we conducted a review of drug-gene co-occurrences in Pubmed abstracts in comparison to the top 5 genes with the highest attention coefficients for each drug. We also examined whether known relationships were retained in the model by inspecting the neighborhoods of topoisomerase-related drugs. For example, our model retained TOP1 as a highly weighted predictive feature for irinotecan and topotecan, in addition to other genes that could potentially be regulators of the drugs. Our method can be used to accurately predict sensitivity to drugs and may be useful in the identification of biomarkers relating to the treatment of cancer patients.

Our study is part of the ongoing discussion concerning influencer marketing as there seems to have been a shift and social media marketing is bigger than ever. Social media outlets are excellent vehicles for fostering relationships with consumers who can be susceptible to influencer advertising. Therefore, companies now pay for posts on users’ profiles to generate popularity for products. How this approach affects consumers’ buying behavior is an interesting research question. We reference Herbert Simon’s economics of attention as an appropriate theoretical construct for describing the reality of the internet. Based on unique survey data from 513 Polish respondents, the study applies econometric methods and supervised and unsupervised machine learning techniques to identify the primary consumer groups with different characteristics of engagement and sensitivity to influencer activities, revealing the possible drivers of purchase intent. The findings provide valuable insights into consumers’ informational preferences, demonstrating how social media influencers may attract attention and drive sales.

Traffic sign detection plays a pivotal role in autonomous driving systems. The intricacy of the detection model necessitates high-performance hardware. Real-world traffic environments exhibit considerable variability and diversity, posing challenges for effective feature extraction by the model. Therefore, it is imperative to develop a detection model that is not only highly accurate but also lightweight. In this paper, we proposed YOLO-ADual, a novel lightweight model. Our method leverages the C3Dual and Adown lightweight modules as replacements for CPS and CBL modules in YOLOv5. The Adown module effectively mitigates feature loss during downsampling while reducing computational costs. Meanwhile, C3Dual optimizes the processing power for kernel feature extraction, enhancing computation efficiency while preserving network depth and feature extraction capability. Furthermore, the inclusion of the CBAM module enables the network to focus on salient information within the image, thus augmenting its feature representation capability. Our proposed algorithm achieves a mAP@0.5 of 70.1% while significantly reducing the number of parameters and computational requirements to 51.83% and 64.73% of the original model, respectively. Compared to various lightweight models, our approach demonstrates competitive performance in terms of both computational efficiency and accuracy.

Multimodal emotion classification (MEC) involves analyzing and identifying human emotions by integrating data from multiple sources, such as audio, video, and text. This approach leverages the complementary strengths of each modality to enhance the accuracy and robustness of emotion recognition systems. However, one significant challenge is effectively integrating these diverse data sources, each with unique characteristics and levels of noise. Additionally, the scarcity of large, annotated multimodal datasets in Bangla limits the training and evaluation of models. In this work, we unveiled a pioneering multimodal Bangla dataset, MAViT-Bangla (Multimodal Audio Video Text Bangla dataset). This dataset, comprising 1002 samples across audio, video, and text modalities, is a unique resource for emotion recognition studies in the Bangla language. It features emotional categories such as anger, fear, joy, and sadness, providing a comprehensive platform for research. Additionally, we developed a framework for emotion recognition that employs a cross-modal attention mechanism among unimodal features. This mechanism fosters the interaction and fusion of features from different modalities, enhancing the model’s ability to capture nuanced emotional cues. The effectiveness of this approach was demonstrated by achieving an F1-score of 0.64, a significant improvement over unimodal methods.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

：Non-Euclidean data, such as social networks, and citation relationships between documents, has node information and structural information. Graph Convolutional Network(GCN) can automatically learn node features and association information between nodes. The core ideology of the graph convolutional network is to aggregate node information by using edge information, thereby generating a new node feature. In the process of updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node, the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the Adaptive Attention Mechanism(AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution(MHGC). Finally, we adopt cross-entropy(CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on AAM, MHGC and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). Experiments show that the classification accuracy has achieved outstanding performances on Cora, Citeseer and Pubmed datasets.

The segmentation of abnormal regions is vital in smart manufacturing. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby impeding the rapid production of industrial assembly lines. To alleviate this issue, we propose the two-stage Illumination-aware Sauce-packet Leakage Segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: Illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose an image enhancement to relieve the impact of uneven illumination, enhancing the texture details of ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the Multi-scale Feature Fusion Module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by adaptive weighting of spatial and channel dimensions. Furthermore, we generated a self-built dataset of sauce-packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method. Our code is available at https://github.com/LSJ5106/SauceDetect.

Pavement crack detection is one of the key links in highway pavement maintenance management. In the current road crack detection, the network model easily ignores the shallow geometric features of cracks and cannot extract the key feature information of cracks. Aiming at the above problems, an EC-YOLOX network model is proposed. The CFPN is constructed to cross-fuse different scale features to solve the feature scale invariance. In the strengthen feature extraction layer, ECANet is fused to enhance the ability to pay attention to key information. The WEIoU loss function is proposed, which assigns different penalty terms to the target box in the vertical and horizontal directions. In terms of data, geometric distortion constraint correction is performed on the single-point perspective pavement image. The experimental data show that the accuracy of EC-YOLOX on the self-built data set reaches 76.34% mAP@0.5, which is 4.45% higher than that of YOLOX. The loss curve of EC-YOLOX is smoother than that of YOLOX, and the minimum training loss value is 2.136, which is 0.648 lower than the minimum loss value 2.784 of YOLOX. Many experiments have verified the effectiveness of EC-YOLOX in improving the detection effect in pavement crack detection.

Objective: This study investigated the effects of an easily implemented 8-week program centered around jump rope exercise (JRE) on executive function among children with ADHD. Methods: Using the Stroop Color Word Test to assess inhibitory control, the n-back task (1- and 2-back) to assess working memory, and task switching to assess cognitive flexibility. Results: After the intervention, there were within-group effects only for the experimental group, with higher accuracy on the 1-back working memory task (t= -2.79，p= 0.011< 0.05，Cohen’s d= 0.60) and on task switching after compared with before the JRE intervention (t= -4.00，p=0.01<0.05，Cohen’s d= 0.85), but with no change in reaction time. There was no significant within-group difference on the Stroop test (P> 0.05). Additionally, there were no between-group effects as assessed by one-way analyses of variance. Conclusion: 8-week program focused on JRE improved two aspects of executive function, working memory and cognitive flexibility, with no significant effect on a third aspect, inhibitory control, among children with ADHD aged 7 to 12 years.

Accurate estimation of Remaining Useful Life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention based hierarchical transformer (STAR) frame-work. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrate hierarchical encoder-decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms current state-of-the-art models for RUL prediction.

Traffic congestion and frequent traffic accidents have become main problems affecting urban traffic. Effective location prediction of vehicle trajectory can help alleviate traffic congestion, reduce the occurrence of traffic accidents, and optimize the urban traffic system. Vehicle trajectory is closely related to the surrounding Points of Interest (POI). POI can be considered as the spatial feature and can be fused with trajectory points to improve prediction accuracy. A Local Dynamic Graph Spatiotemporal- Long Short-Term Memory (LDGST-LSTM) is proposed in this paper to extract and fuse the POI knowledge and realize next location prediction. POI semantic information is learned by constructing the traffic knowledge graph, and spatial and temporal features are extracted by combining Graph Attention Network (GAT) and temporal attention mechanism. Moreover, the weights of POI that influence location prediction are visualized to improve the interpretability of the proposed model. The effectiveness of LDGST-LSTM is verified on two datasets, including Chengdu taxi trajectory data in October 2018 and August 2014. The accuracy and robustness of the proposed model are significantly improved compared with the benchmark models.

Underwater image processing faces significant challenges due to the absorption and scattering of light as it travels through water. A self-supervised learning network based on the self-attention mechanism is proposed for underwater visual applications in this paper. The goal is to improve the effectiveness and stability of feature extraction from underwater images. By incorporating self-attention mechanism, the sensitivity of the original network architecture to degraded features of blurred underwater images is enhanced. The network proposed in this paper is trained using transfer learning and evaluated on various underwater image datasets. With distributive, quantitative, and qualitative advantages compared with other methods, experimental results have demonstrated that the algorithm presented shows a slighter decline in feature extraction ability for blurred images as the turbidity of water increases.

Social communication skills, especially eye contact and joint attention, are highly impaired in autism spectrum disorder (ASD) and predict functional outcomes. Applied Behavior Analysis is one of the best evidence-based treatments for ASD, but it is not accessible to most families in low- and middle-income countries (LMICs) as it is a costly and intensive and needs to be delivered by highly specialized professionals. Parental training has emerged as an effective alternative. The aim of this study was to test the efficacy of a parental intervention group via video modeling to acquire eye contact and joint attention. Four graded measures of eye contact and joint attention (full physical prompt, partial physical prompt, gestural prompt, and independent) were assessed in 34 children with ASD and intellectual disability (ID). There was a progressive reduction in the level of prompt required over time to acquire eye contact and joint attention, and a positive correlation between the time of exposure to the intervention and acquisition of the abilities. This parent training using video modelling to teach eye contact and joint attention skills to children with ASD and ID is a low-cost intervention that can be applied in low- resource settings.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

Synthetic Aperture Radar (SAR) is an active sensor that uses microwave for sense, it is unrestricted by weather and illumination conditions, and it can observe targets all day and weather. Aircraft targets are important monitoring objects in military and civilian fields, and how to efficiently detect and recognize aircraft targets is an important topic in the field of SAR image interpretation. Based on the features of SAR images, such as complex background, high resolution, and multi-scale, we proposed an improved method based on YOLOv5s. Firstly, this paper proposed the structure of the multi-scale receptive field and channel attention fusion, which is applied to the shallow layer of the backbone of YOLOv5s, it can adjust the weights of the multi-scale receptive field during the training process to enhance the extraction ability of feature information. Secondly, we proposed four de-coupled detection heads to replace the original part in YOLOv5s, which can improve the efficiency and accuracy of SAR image interpretation for small targets. Thirdly, in the case of the limited amount of SAR images, this paper proposed multi methods of data augmentation, which can enhance the diversity and generalization of the network. Fourthly, this paper proposed the K-means++ to re-place the original K-means to improve the network convergence speed and detection accuracy. Finally, Experiments demonstrate that the improved YOLOv5s can enhance the accuracy of SAR image interpretation by 9.3%, and the accuracy of small targets is improved more obviously, reaching 13.1%.

Most natural language processing (NLP) tasks operate an input sentence as a sequence with token-level embeddings and features, despite its clausal structures. Taking Abstract Meaning Representation (AMR) parsing as an example, recent parsers are empowered by Transformers and pre-trained language models, but long-distance dependencies (LDDs) introduced by long sequences are still open problems. We argue that LDDs are not superficially blamed on the sequence length but are essentially related to the internal clause hierarchy. Typically, non-verb words in a clause cannot depend on words outside, and verbs from different but related clauses have much longer dependencies than those in the same clause. With this intuition, we introduce a type of clausal feature, hierarchical clause annotation (HCA), into AMR parsing and propose two HCA-based approaches, HCA-based self-attention (HCA-SA) and HCA-based curriculum learning (HCA-CL), to integrate HCA trees of complex sentences for addressing LDDs. We conduct extensive experiments on two in-distribution (ID) AMR datasets (AMR 2.0 and AMR 3.0) and three out-of-distribution (OOD) ones (TLP, New3, and Bio). Experimental results show that our HCA-based approaches achieve significant and explainable improvements against the baseline model and outperform the state-of-the-art (SOTA) model when encountering sentences with complex clausal structures that introduce most LDD cases.

Compressed Sensing (CS) MRI has shown great potential in enhancing time efficiency. Deep learning techniques, specifically Generative Adversarial Networks (GANs), have emerged as potent tools for speedy CS-MRI reconstruction. Yet, as the complexity of deep learning recon-struction models increases, this can lead to prolonged reconstruction time and challenges in achieving convergence. In this study we present a novel GAN-based model that delivers superior performance without escalating model complexity. Our generator module, built on the U-net architecture, incorporates dilated residual (DR) networks, thus expanding the network's receptive field without increasing parameters or computational load. At every step of the downsampling path, this revamped generator module includes a DR network, with the dilation rates adjusted according to the depth of the network layer. Moreover, we have introduced a channel attention mechanism (CAM) to distinguish between channels and reduce background noise, thereby fo-cusing on key information. This mechanism adeptly combines global maximum and average pooling approaches to refine channel attention. We conducted comprehensive experiments with the designed model using public domain MRI datasets of the human brain. Ablation studies af-firmed the efficacy of the modified modules within the network. Compared to other relevant models, our proposed model exhibits exceptional performance, achieving not only excellent sta-bility but also outperforming other networks in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The model presents a promising pathway for enhancing the efficiency and quality of CS-MRI reconstruction.

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that affects attention and behavioral control, characterized by constant presence of inattention and hyperactivity. This article describes a study that used a database with results from tests of voluntary and automatic attentional orientation activity in a complex network of ADHD patients, in order to understand the characteristics of the elements and attentional variability of patients. Centrality metrics and the Louvain method were applied to obtain the network communities. The most important elements of the network were identified and differences in reaction times of the activities were observed in the identified communities. The study provides useful information to understand of deficit hyperactivity disorder spectrum in patients with ADHD.

Speech emotion recognition is a critical component for achieving natural human-robot interaction. The modulation-filtered cochleagram is a feature based on auditory modulation perception, which contains multi-dimensional spectral-temporal modulation representation. In this study, we propose an emotion recognition framework that utilizes a multi-level attention network to recognize emotions from the modulation-filtered cochleagram. The channel-level attention and spatial-level attention modules are used to capture emotional saliency maps of channel and spatial feature representations from the 3D convolution feature maps, respectively. Furthermore, the temporal-level attention module captures significant emotional regions from the concatenated feature sequence of the emotional saliency maps. Our experiments on the IEMOCAP dataset demonstrate that the modulation-filtered cochleagram significantly improves the prediction performance of categorical emotion compared to other evaluated features. Moreover, our emotion recognition framework achieves a better unweighted accuracy of 71% in categorical emotion recognition than several existing approaches in the experiments. In summary, our study demonstrates the effectiveness of the modulation-filtered cochleagram in speech emotion recognition, and our proposed multi-level attention framework provides a promising direction for future research in this field.

Effortful control (EC) describes individual differences in self-regulation, with a strong attentional basis. Moreover, during early childhood EC has a central role on children’s socio-emotional adjustment and academic achievement. The aim of the current study was to predict the development of EC at 36 months of age from early attentional and environmental measures taken in infancy using a machine learning approach. A sample of 75 infants participated in a longitudinal study running different waves of data collection at 6, 9 and 36 months of age. Attentional tasks were administered at 6 months of age and two additional measures were collected at 9 months of age. Parents reported household environment variables during wave 1, and their child’s EC at 36 months. A machine -learning algorithm was implemented to identify children with low EC scores at 36 months of age. An “attention only” model showed greater predictive sensitivity than the “environmental only” model. However, a model including both attentional and environmental variables was able to classify the groups (Low-EC vs Average-to-High EC) with 100% accuracy. Sensitivity analyses indicate that socio-economic variables together with attention control processes at 6-months, and self-restraint capacity at 9-months, are the most important predictors of EC. Results suggest a foundational role of executive attention processes in the development of EC in complex interaction with household environment and provide a new tool to identify early markers of socio-emotional regulation development.

Background & aims It is documented that low protein and amino-acid dietary intake is related to poorer cognitive health and increased risk of dementia. Degradation of the neuromodulatory pathways, (comprising the cholinergic, dopaminergic, serotoninergic and noradrenergic systems) is observed in neurodegenerative diseases and impairs the proper biosynthesis of key neuromodulators from micro-nutrients and amino acids. How these micro-nutrients are linked to neuromodulatory pathways in healthy adults is less studied. The Locus Coeruleus–Noradrenergic System (LC-NA) is the earliest subcortical structure affected in Alzheimer’s disease, showing marked neurodegeneration, but is also sensitive for age-related changes. The LC-NA system is critical for supporting attention and cognitive control, functions that are enhanced both by tyrosine administration and chronic tyrosine intake. The purpose of this study was to 1) investigate whether the dietary intake of tyrosine, the key precursor for noradrenaline (NA), is related to LC integrity 2) whether LC integrity mediates the reported association between tyrosine intake and higher cognitive performance (measured with Trail Making Test – TMT), and 3) whether LC integrity relates to an objective measure of brain maintenance (BrainPAD). Methods The analyses included 398 3T MRIs of healthy participants from the Berlin Aging Study II to investigate the relationship between LC integrity and habitual dietary tyrosine intake-daily average (HD-Tyr-IDA). As a control procedure, the same analyses were repeated on other main seeds of the neuromdulatory subcortical system (Dorsal and Medial Raphe, Ventral Tegmental Area and Nucleus Basalis of Meynert). In the same way, the relationships between the five nuclei and BrainPAD were tested. Results Results show that HD-Tyr-IDA is positively associated with LC integrity. Similarly, LC integrity disproportionally relates to better brain maintenance (BrainPAD). Mediation analyses reveal that only LC, relative to the other nuclei tested, mediates the relationship between HD-Tyr-IDA I and performance in the TMT and between HD-Tyr-IDA and BrainPAD. Conclusions These findings provide the first evidence linking tyrosine intake with LC-NA system integrity and its correlation with neuropsychological performance. This study strengthens the role of diet for maintaining brain and cognitive health and supports the noradrenergic theory of cognitive reserve. Within this framework, adequate tyrosine intake might increase the resilience of LC-NA system functioning, by preventing degeneration and supporting noradrenergic metabolism required for LC function and neuropsychological performance.

Research shows that stress, a common problem in dense cities, can be relieved in the natural environment. As great significance has been attached to the urban environment and public health in the society, this paper aims to study the relation and interaction between the perceived sensory dimension of urban park green space, attention restoration and state empathy. Therefore, we conducted an on-site questionnaire survey in four typical parks in Chengdu in terms of age, sex, daily stress, frequency of access in parks and other basic information of the respondents. The main part consists of perceived dimension, state empathy and attention restoration. The software SPSS24.0 is applied to the test of the validity and reliability of the PSD Scale, and then the important correlation between the perceived sensory dimensions in the parks and visitors' attention restoration is analyzed through multiple linear regression. Finally, the moderation effect of state empathy is tested by PROCESS. The findings show that (1) only seven dimensions in the PSD Scale are effective; (2) Serene and Refuge in the perceived sensory dimensions have significant effect on the restorative components of attention. (3) Except the dimensions of Rich in Species and Refuge, empathy enhanced the moderation effect in the interaction between the other five dimensions the Perceived Restorative Scale(PRS), especially in the interaction between the dimension Social and PRS. However, this study needs to be further explored to provide scientific basis and design strategy guidance for the research on the restoration potential of urban park green space in high-density urban areas.

We find that the overnight returns of Korean exchange-traded index funds (ETFs) are significantly positive, whereas the subsequent intraday returns are negative. These intraday return reversals are caused by relatively higher opening prices than the closing prices. In the Korean ETF market, where institutional investors are dominant participants, the return reversals are not explained by the attention hypothesis as in Berkman et al. [1]. Hence, we investigate whether the disagreement hypothesis can explain return reversals. Under the disagreement situations between positive and negative traders at the open, positive traders can have a positive influence on the ETF prices by increasing their investments. However, negative traders, who give up investments due to limited short selling opportunities in the ETF market, have no effects on the prices. Comparing ETF markets with KOSPI 200 Futures where there are no restrictions on short selling, we find that short selling constraints are significant factors for the return reversals. This implies that disagreement among the investors can cause return reversals even in the markets without noise traders. Using unique Korean market data, we conclude that return reversals cannot be completely explained by the attention hypothesis, and that disagreement among investors is also a significant factor for the return reversals. This study contributes to the existing literature by showing that the attention hypothesis does not explain return reversals in the ETF market completely, and suggesting the disagreement hypothesis as an alternative.

Gene therapy is a medical approach capable of correcting genetic and epigenetic alterations in pathological conditions, including cancer. Different strategies have been pursued for cancer gene therapy, aiming to restore the function of tumor suppressor genes or inhibit oncogenes. These comprise the use of CRISPR/Cas9 gene editing technology and therapeutic oligonucleotides, such as microRNAs, anti-microRNAs, small interfering RNAs, DNAzymes, and epigenetic modifiers. However, despite great potential, their broad clinical use is hindered due to the lack of safe and efficient systems for targeted delivery to cancer cells. To this purpose, aptamers could represent an ideal tool. They are short single-stranded oligonucleotides that bind receptors selectively present or overexpressed on cancer cell membranes, often undergoing cell-specific internalization. Thanks to this last feature, numerous internalizing aptamers have been investigated as targeting moiety to deliver therapeutic oligonucleotides, viral vectors, and nanoparticle-based systems in preclinical studies. Here, we summarize the state-of-the-art of aptamer applications in cancer gene therapy, providing key examples and discussing their advantages, limitations, and clinical perspectives.

Due to their increased surface area, extent of swelling and active substance loading capacity and flexibility, nanogels made from natural and synthetic polymers have gained significant interest in the scientific and industrial areas. Especially, customized design and implementation of non-toxic, biocompatible, and biodegradable micro/nano carriers makes their usage very feasible for a range of biomedical applications, including drug delivery, tissue engineering, and bioimaging. The design and application methodologies of nanogels have been outlined in this review. Additionally, the most recent advancements in nanogel biomedical applications have been discussed, with a particular emphasis on applications for the delivery of drugs and biomolecules.

Vision-based tactile sensors (VBTS) have become the de facto method of giving robots the ability to obtain tactile feedback from their environment. Unlike other solutions to tactile sensing, VBTS offers high spatial resolution feedback without compromising on instrumentation costs or incurring additional maintenance expenses. However, conventional cameras used in VBTS have a fixed update rate and output redundant data, leading to computational overhead downstream. In this work, we present a neuromorphic vision-based tactile sensor (N-VBTS) that employs observations from an event-based camera for contact angle prediction. Particularly, we design and develop a novel graph neural network, dubbed TactiGraph, that asynchronously operates on graphs constructed from raw N-VBTS streams exploiting their spatiotemporal correlations to perform predictions. Although conventional VBTS uses an internal illumination source, TactiGraph is reported to perform efficiently in both scenarios, with and without an internal illumination source. Rigorous experimental results revealed that TactiGraph achieved a mean absolute error of 0.62∘ in predicting the contact angle and was faster and more efficient than both conventional VBTS and other N-VBTS, with lower instrumentation costs. Specifically, N-VBTS requires only 5.5% of the compute-time needed by VBTS when both are tested on the same scenario.

For disciplines like biological science, security, and the medical field, link prediction is a popular research area. To demonstrate the link prediction many methods have been proposed. Some of them that have been demonstrated through this review paper are TransE, Complex, DistMult, and DensE models. Each model defines link prediction with different perceptions. We argue that the practical performance potential of these methods, having similar parameter values, using the fine-tuning technique to evaluate their reliability and reproducibility of results. We describe those methods and experiments; provide theoretical proofs and experimental examples, demonstrating how current link prediction methods work in such settings. We use the standard evaluation metrics for testing the model's ability.

Zoos are increasingly putting in place formalized animal welfare assessment programs to allow monitoring of welfare over time, as well as to aid in resource prioritization. These programs tend to rely on assessment tools that incorporate resource-based and observational animal- focused measures since it is rarely feasible to obtain measures of physiology in zoo-housed animals. A range of assessment tools are available which commonly have a basis in the Five Domains framework. A comprehensive review of the literature was conducted to bring together recent studies examining welfare assessment methods in zoo animals. A summary of these methods is provided with advantages and limitations of the approach es presented. We then highlight practical considerations with respect to implementation of these tools into practice, for example scoring schemes, weighting of criteria, and innate animal factors for consideration. It is concluded that would be value in standardizing guidelines for development of welfare assessment tools since zoo accreditation bodies rarely prescribe these. There is also a need to develop taxon or species- specific assessment tools to inform welfare management.

The augmenting commitment in the entrepreneurial learning process, both at academic and industry level, has led to new mechanisms and methodologies. Entrepreneurship literature has shown evidence of raising interest in the problem-based learning (PBL) methodology with regard to upcoming events from the surrounding learning context. This paper presents a Systematic Bibliographic Literature Review (SBLR) with respect to the application of PBL throughout distinct entrepreneurial processes either in higher education, or in industry. It aimed to identify relevant entrepreneurial opportunities for PBL. Bibliographic databases were searched for documents published between 2002 and May 2024 to categorize key topics discussed in the literature on PBL and entrepreneurship. The review process identified 142 empirical and non-empirical papers on entrepreneurship related PBL. Data analysis revealed diverse subthemes for PBL uses in entrepreneurship in both higher education institutions and industry. The research questions “What is the interplay of problem-based learning methodology with entrepreneurship?” guided the study. The central output of the research is the discovery of the varying uses of PBL to cope with diverse events arising within entrepreneurship context. Future research directions are suggested.

Herein we report the expansion of the chemical space available from the chitin, accessible via the biogenic N-platforms 3A5AF, M4A2C and di-HAF. The biologically active heteroaromatics furo[3,2-d]pyrimidin-4-one and furo[3,2-d]pyrimidin-4-amine can be selectively accessed from 3A5AF and M4A2C, respectively. The chiral pool synthon di-HAF is a viable substrate for the Achmatowicz rearrangement, providing streamlined access to 2-aminosugars possessing a versatile hydroxymethyl group at C5.

Human induced climate change led to the recognition of Community-Based Adaptation (CBA) as one of the remedies in building adaptive capacity and resilience of communities. It recognizes the resources and the skills as well as the agency of communities in shaping the optimal strategy. CBA interventions are vital in addressing community needs and contextual specificities, enable participatory and inclusive engagement and thereby facilitate more profound adaptation impacts. Agent-based modelling (ABM) harbors the potential to be the ideal tool to support developing of tailored adaptation strategies while considering capacities, resources, skills, priorities, needs and the cultural context of local communities. ABM allows to capture the complex relationships among various components within community decision making on CBA actions, the CBA actions themselves and the environment. There exist plenty of tools, however they provide for varying degrees of freedom in agent definition, sensitivity analysis, scalability, experiment design and output analysis to name a few. A set of required key criteria for CBA modelling is developed and all available ABM modelling and simulation tools are assessed for their suitability for CBA. NetLogo emerges as the most fitting tool for incorporating and handling the special features of CBA. It is closely followed by GAMA and Envision. The article provides insights and guidance to researchers and practitioners in selecting ABM tools aligned with the specific requirements of their CBA simulations and projects.

Due to the rapid growth of the Internet of Things (IoT), securing communications between a huge number of devices has become very difficult. Access controls and authentication secure the connection between IoT devices and protect sensitive data from unauthorized users or malicious attackers. In this paper, we provide a comprehensive review to emphasize the critical role of authentication and access control in securing IoT environments. This paper explores different types of access controls, like Attribute-Based Access Control and Role-Based Access Control. Furthermore, it demonstrates different authentication techniques, like passwords and biometrics. Based on the previous mechanisms, we discuss different IoT security challenges regarding authentication and access control mechanisms and highlight future directions. In addition, this paper investigates the integration between access control and authentication to safeguard IoT communications.

The evolution of photovoltaic cells is intrinsically linked to advancements in the materials from which they are fabricated. This review paper provides an in-depth analysis of the latest developments in silicon-based, organic, and perovskite solar cells, which are at the forefront of photovoltaic research. We scrutinize the unique characteristics, advantages, and limitations of each material class, emphasizing their contributions to efficiency, stability, and commercial viability. Silicon-based cells are explored for their enduring relevance and recent innovations in crystalline structures. Organic photovoltaic cells are examined for their flexibility and potential for low-cost production, while perovskites are highlighted for their remarkable efficiency gains and ease of fabrication. The paper also addresses the challenges of material stability, scalability, and environmental impact, offering a balanced perspective on the current state and future potential of these material technologies.

The aim of this study was to investigate the impact of Process Oriented Guided Inquiry Learning (POGIL)-based instruction versus lecture-based instruction on Grade 12 students’ performance in circular motion unit. A quasi-experimental, pretest-posttest design, the impact of POGIL-based instruction versus lecture-based instruction on students’ performance as measured by three types of cognitive outcomes: Knowing, Applying and Reasoning (KAR). The total number of participants was approximately 110 students (N=110); 54 were assigned to treatment groups (25 girls and 29 boys) and 56 were assigned to control groups (27 girls and 29 boys). The treatment group was taught a unit of circular motion in physics using POGIL-based instruction while the control group was taught the unit using lecture-based instruction. The findings of the study showed statistically significant differences between students of the control group and the treatment group in favor of the later regarding their circular motion performance, suggesting the superiority of the POGIL in enhancing student understanding of the circular motion.

This article investigates the prospect of implementing multidisciplinary and multicultural student teamwork (MMT) involving Case-based Learning (CBL) and Problem-based Learning (PBL) as a sustainable teaching practice. Based on a mixed methods approach, which includes direct observation (both physical and virtual), questionnaire distribution and focus-group interviews the study reveals that MMT through CBL and PBL can both facilitate and hinder sustainable learning. Our findings show that while MMT enhances knowledge sharing, it also poses a wide range of challenges, raising questions about its social significance as a sustainable teaching practice. The study suggests the implementation of certain mechanisms, such as ‘Teamwork Training’ and ‘Pedagogical Mentors’, aiming to strengthen the sustainable orientation of MMT through CBL and PBL.

In MBSE there is yet no converged terminology. The term ’system model’ is used in different contexts in literature. In this study we elaborated the definitions and usages of the term ’system model’, to find a common definition. 104 publications have been analyzed in depth for their usage and definition as well as their meta-data e.g., the publication year and publication background to find some common patterns. While the term is gaining more interest in recent years it is used in a broad range of contexts for both analytical and synthetic use cases. Based on this three categories of system models have been defined and integrated into a more precise definition.

This article discusses the use of game design as a method for interdisciplinary project-based teaching in secondary school education to convey informatics and society topics. There is a lot of knowledge about learning games but little background on project-based teaching using game design as a method. We present the results of an analysis of student-created games and an evaluation of a student-authored database on learning contents found in commercial off-the-shelf games. We further contextualise these findings using a group discussion with teachers. Results underline the effectiveness of project-based teaching to raise awareness for informatics and society topics. We further outline informatics and society topics that are particularly interesting to students, genre preferences and potentially engaging game mechanics stemming from our analyses.

The ubiquity of mobile sensors (such as GPS, accelerometer and gyroscope) together with increasing computational power have enabled an easier access to contextual information, which proved its value in next generation of the recommender applications. The importance of contextual information has been recognized by researchers in many disciplines, such as ubiquitous and mobile computing, to filter the query results and provide recommendations based on different user status. A context-aware recommendation system (CoARS) provides a personalized service to each individual user, driven by his or her particular needs and interests at any location and anytime. Therefore, a contextual recommendation system changes in real time as a user’s circumstances changes. CoARS is one of the major applications that has been refined over the years due to the evolving geospatial techniques and big data management practices. In this paper, a CoARS is designed and implemented to combine the context information from smartphones’ sensors and user preferences to improve efficiency and usability of the recommendation. The proposed approach combines user’s context information (such as location, time, and transportation mode), personalized preferences (using individuals past behavior), and item-based recommendations (such as item’s ranking and type) to personally filter the item list. The context-aware methodology is based on preprocessing and filtering of raw data, context extraction and context reasoning. This study examined the application of such a system in recommending a suitable restaurant using both web-based and android platforms. The implemented system uses CoARS techniques to provide beneficial and accurate recommendations to the users. The capabilities of the system is evaluated successfully with recommendation experiment and usability test.

The electric network frequency (ENF), often referred to as the industrial heartbeat, plays a crucial role in the power system. In recent years, it has found applications in multimedia evidence identification for court proceedings and audio-visual temporal source identification. This paper introduces a ENF region classification model named UniTS-SinSpec within the UniTS framework. The model integrates the si-nusoidal activation function and spectral attention mechanism while also redesigning the model frame-work. Training is conducted using a public dataset on the open science framework platform (OSF), with final experimental results demonstrating that after parameter optimization, the UniTS-SinSpec model achieves an average validation accuracy of 97.47%, surpassing current state-of-the-art and baseline models. Accurate classification can significantly aid in ENF temporal source identification. Future re-search will focus on expanding dataset coverage and diversity to verify the model's generality and ro-bustness across different regions, time spans, and data sources. Additionally, it aims to explore extensive application potential of ENF region classification in preventing crimes such as telecommunications fraud, terrorism, and child pornography.

Since the beginning of the internet era, there has been an explosion of growth in structured data (such as numbers, symbols, and labels) as well as unstructured data (including images, videos, and text). Efficient and accurate mixed query of these two types of data is a key technology to achieve high-quality information retrieval, and it is also a major challenge that needs to be solved urgently in the industry. In this study, we employ an advanced Transformer model that combines strategies and fine-tuning techniques for multi-task learning. Specifically, the model is first pre-trained on a large-scale, general-purpose dataset to learn different types of data representations and basic language comprehension skills. After that, we fine-tuned the parameters of the model to better suit these specific data processing tasks for specific application scenarios, such as image annotation, video content analysis, and structured data query. At the heart of the model is the self-attention mechanism, which allows the model to automatically emphasize the important parts and ignore irrelevant information when processing the input data. In addition, we have introduced task-specific adaptation layers that are designed to add additional processing power to the original Transformer architecture, such as a semantic analysis layer for unstructured text data and a relational extraction layer for structured data. This combination of general pre-training and task-specific fine-tuning allows the model to flexibly process and integrate information from different data sources, improving processing efficiency and accuracy. Experimental results show that the model performs well in a variety of data processing tasks, significantly improves the accuracy and efficiency of information retrieval, and verifies the strong potential and adaptability of large language models in processing mixed data types.

YOLOv8, as an efficient object detection method, can swiftly and precisely identify objects within images. However, traditional algorithms encounter difficulties when detecting small targets in remote sensing images, such as missing information, background noise, and interactions among multiple objects in complex scenes, which may affect performance. To tackle these challenges, we propose an enhanced algorithm optimized for detecting small objects in remote sensing images, named HP-YOLOv8. Firstly, we design the C2f-D-Mixer (C2f-DM) module as a replacement for the original C2f module. This module integrates both local and global information, significantly improving the ability to detect features of small objects. Secondly, we introduce a feature fusion technique based on attention mechanisms, named Bi-Level Routing Attention in Gated Feature Pyramid Network (BGFPN). This technique utilizes an efficient feature aggregation network and reparameterization technology to optimize information interaction between different scale feature maps, and through the Bi-level Routing Attention (BRA) mechanism, it effectively captures critical feature information of small target objects. Finally, we propose the Smooth Mean Perpendicular Distance Intersection over Union (SMPDIoU) loss function. The method comprehensively considers the shape and size of detection boxes, enhances the model's focus on the attributes of detection boxes and provides a more accurate bounding box regression loss calculation method. To demonstrate our approach's efficacy, we conduct comprehensive experiments across the RSOD, NWPU VHR-10, and VisDrone2019 datasets. The experimental results show that the HP-YOLOv8 achieves 95.11%, 93.05%, and 53.49% in the mAP@0.5 metric, and 72.03%, 65.37%, and 38.91% in the more stringent mAP@0.5:0.95 metric, respectively.

Focusing on the problem of identifying and classifying aero-engine models, this paper measures the infrared spectrum data of aero-engine hot jets using a telemetry Fourier transform infrared spectrometer. Simultaneously, infrared spectral data sets with the six different types of aero-engines are created. For the purpose of classifying and identifying infrared spectral data, a CNN architecture based on the continuous wavelet transform peak seeking attention mechanism (CWT-AM-CNN) is suggested. This method calculates the peak value of middle wave band by continuous wavelet transform, and the peak data is extracted by the statistics of the wave number locations with high frequency. Attention mechanism is used for the peak data, and the attention mechanism is weighted to the feature map of the feature extraction block. The training set, vali-dation set and prediction set are divided in the ratio of 8:1:1 for the infrared spectral data sets. For three different data sets, CWT-AM-CNN proposed in this paper is compared with the classical classifier algorithm based on CO2 feature vector and the popular AE, RNN and LSTM spectral processing networks. The prediction accuracy of the proposed algorithm in the three data sets is as high as 97%, and the lightweight network structure design not only guarantees high precision, but also has a fast running speed, which can realize the rapid and high-precision classification of the infrared spectral data of the aero-engine hot jets.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.

Land cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. In this article, we focus on the land cover segmentation tasks and complete the following research work: Firstly, to address the issues of uneven distribution of foreground and background and significant differences in target scales in remote sensing images, we propose a decoder called MDCFD based on multi-dilation rate convolution fusion. The decoder utilizes dilated convolution to expand the receptive field, enhancing the model's ability to capture global features and thus improving the model's ability to distinguish between foreground and background. Meanwhile, we design a multi-dilation rate convolution fusion module (MDCFM), which fuses the outputs of different dilation rate convolution layers. Secondly, aiming at the problems of diverse scenes, significant differences between categories, and many background interferences in remote sensing images, we propose a hybrid attention module called LKSHAM based on large kernel convolution. This module combines spatial attention and channel attention mechanisms and combines the two attention modules in series. By introducing large kernel convolution, the model's ability to extract contextual information is improved. At the same time, we adopt a strategy of decomposing large kernel convolution into multiple depthwise convolutions to reduce computational complexity. The improved network models designed by this paper can achieve an improvement of over 1.1% in the mIoU metric on segmentation tasks on the Potsdam and Vaihingen datasets.

Videogames have been the focus of research since their widespread popularity, with particular emphasis on their effects on cognitive and affective abilities, especially in children and adolescents. Despite numerous correlational studies, robust evidence on the causal relationship between videogames and cognition remains scarce, hindered by the absence of a comprehensive assessment tool for gaming skills across various genres. This study aimed to develop and validate the Gaming Skill Questionnaire (GSQ) and to assess the impact of gaming skills in six different genres (Sport, First-Person Shooters, Role-Playing Games, Action-Adventure, Strategy, and Puzzle Games) on adolescents’ cognitive and affective abilities. The GSQ exhibited strong reliability and validity, highlighting its potential as a valuable tool. Gaming skills positively affected executive function, memory, overall cognition, cognitive flexibility, and emotion recognition, except for empathy. Various game genres had different effects on cognitive and affective abilities, with verbal fluency influenced mainly by sports, executive functions by action, strategy, and puzzle, and emotion recognition positively impacted by action and puzzle but negatively by sports and strategy games. Both age and gaming skills influenced cognitive flexibility, with gaming having a greater effect. These intriguing genre-specific effects on cognitive and affective functioning postulate further research with GSQ's contribution.