Auto Image Comment via Deep Attention

Background and Aim: Student-centered learning is a major driver behind educational policy and practice in the modern era, and with the move toward adopting learner-centered learning in the classroom, especially in mathematics learning, understanding where such games are offered and the potential They have not yet been discovered, it is vital. The purpose of this research was to investigate the effectiveness of educational games based on social constructivism in interaction with learning styles on improving the emotional efficiency and learning rate of secondary school girl students in mathematics. Research method: The research method was semi-experimental with a pre-test, post-test with a control group and a 2-month follow-up phase. The statistical population was all secondary school female students studying in public schools in Hamadan city in 1402-1401. In the first stage, using a simple random sampling method, a school was selected from the 1st district of Hamedan city and 100 people who met the conditions to enter the research were selected, and then by a simple random method, they were divided into 2 experimental groups (25 people in the deep learning group and 25 people in the deep learning group). surface learning) and 2 control groups (25 deep learning group and 25 surface learning group) were replaced. The groups of the first experiment underwent 6 90-minute sessions of educational games based on the social constructivism approach; But the control groups did not receive any intervention and remained on the waiting list. Biggs et al.'s (2001) two-factor learning process questionnaire, McCutch and Sikel's (2003) school attitude questionnaire, and a researcher-made questionnaire on the learning rate of mathematics lessons were used to collect information. The analysis of the information obtained from the implementation of the questionnaires was carried out through SPSS software version 24 in two descriptive and inferential sections (mixed variance analysis and Benferroni's post hoc test). Risult: The results showed that educational games based on the social constructivism approach in the post-test and follow-up phase had a significant effect on emotional efficiency and the amount of mathematical learning compared to the control groups (P<0.05). Also, the results showed that educational games based on the social constructivism approach in the group of students with a deep learning style had more effectiveness than students with a superficial learning style on emotional efficiency and the amount of mathematical learning (P<0.05). ). Conclusion: Based on the results of the present research, it can be said that educational games based on the social constructivism approach can be used as a suitable educational method to improve the emotional efficiency and learning rate, especially in secondary school students with Deep learning style should be used in secondary schools.

Background. Modern machine vision systems largely rely on convolutional neural networks, which demonstrate high performance in image analysis due to their ability to extract hierarchical feature representations. Improvement in recognition quality is commonly achieved by increasing network depth and the number of parameters; however, this approach is associated with higher computational costs, increased sensitivity to noise, and reduced robustness to variations in scale and illumination. This circumstance highlights the need for architectural solutions that enable more efficient feature extraction without a significant increase in computational complexity. A promising direction involves the use of multiscale convolutional operations that capture both local and global image context, as well as the integration of attention mechanisms that provide adaptive concentration of computational resources on the most informative regions and features. Purpose. To formulate an architectural approach to the design of convolutional neural networks based on the combination of multiscale convolutional processing and attention mechanisms, aimed at improving the efficiency of machine vision algorithms while maintaining an acceptable level of computational cost. Materials and methods. The article examines three convolutional neural network architectures, including a baseline CNN, a multiscale CNN, and an extended model incorporating an attention mechanism. Operations of two dimensional convolution, batch normalization, and nonlinear activation are analyzed, along with methods for aggregating features obtained at different spatial scales. An analytical assessment of computational complexity is performed with consideration of the number of parameters, network depth, and the volume of operations during the forward pass. Results. The application of multiscale convolutional processing expands the receptive field of the network and improves robustness to variations in object size through simultaneous analysis of features at different levels of detail. The integration of attention mechanisms provides adaptive redistribution of feature weights, reduces the influence of noise and irrelevant components, and enhances the selectivity of image analysis.

Human action recognition is essential in many real-world scenarios, such as video surveillance, human–computer interaction, and behavior analysis. Despite the progress in deep learning, issues such as occlusion, distraction from the background, and motion pattern variability still exist, thus restricting the generalization ability of current models. Most methods are based only on spatial or temporal features and cannot efficiently capture both in one framework, causing lower accuracy in realistic situations. In response to these shortcomings, a multilevel feature extraction approach was proposed by integrating spatial and temporal features to improve the action recognition precision. The method captures RGB frames, optical flow, spatial saliency maps, and temporal saliency maps to enable an overall inspection of video streams. Efficient feature extraction was achieved by applying a pre-trained Inception V3 model and then bidirectional gated recurrent units (Bi-GRUs) to include sequential modeling. An attention mechanism was also included to boost the classification process by focusing on key temporal segments. UCF101 and HMDB51 benchmark datasets evaluated the efficiency of the strategy. The model’s accuracy was 98.13% on UCF101 and 81.45% on HMDB51, which validated the superior discrimination ability of the model in processing heterogeneous human actions. These results confirm that the provided framework is an efficient and discriminative action recognition approach, thus suitable for applications requiring extensive motion analysis and real-time deployment.

The rapid serial visual presentation-based brain–computer interface (RSVP-BCI) system achieves the recognition of target images by extracting event-related potential (ERP) features from electroencephalogram (EEG) signals and then building target classification models. Currently, how to reduce the training and calibration time for classification models across different subjects is a crucial issue in the practical application of RSVP. To address this issue, a zero-calibration (ZC) method termed Attention-ProNet, which involves meta-learning with a prototype network integrating multiple attention mechanisms, was proposed in this study. In particular, multiscale attention mechanisms were used for efficient EEG feature extraction. Furthermore, a hybrid attention mechanism was introduced to enhance model generalization, and attempts were made to incorporate suitable data augmentation and channel selection methods to develop an innovative and high-performance ZC RSVP-BCI decoding model algorithm. The experimental results demonstrated that our method achieved a balance accuracy (BA) of 86.33% in the decoding task for new subjects. Moreover, appropriate channel selection and data augmentation methods further enhanced the performance of the network by affording an additional 2.3% increase in BA. The model generated by the meta-learning prototype network Attention-ProNet, which incorporates multiple attention mechanisms, allows for the efficient and accurate decoding of new subjects without the need for recalibration or retraining.

In order to solve the problem of excessive model parameters and low real‐time performance in driver distraction driving detection tasks, this work proposes a detection model based on cascaded convolutional network and attention mechanism. The model adopts a two‐stage architecture. In the first stage, the pre‐trained MobileNet is used as the backbone network for basic feature extraction to achieve efficient image feature extraction and significantly reduce the computational complexity. In the second stage, the basic features extracted in the first stage are enhanced by combining the Cascaded ResNet structure with the spatial attention mechanism, so as to improve the capture ability of key features. Finally, the features extracted in the two stages are fused to complete the driver's distraction behavior recognition. The experimental results on the public datasets American University in Cairo (AUC) Distracted Driver and StateFarm Distracted Driver (SFD) show that the proposed model achieves the recognition accuracy of 95.72% and 99.87%, respectively, which is significantly better than the existing mainstream methods while maintaining a low number of parameters. The model has low parameter quantity, high detection accuracy and high real‐time performance.

Facial expression recognition (FER) in uncontrolled, in-the-wild settings is a challenging task due to variations in pose, illumination, occlusion, and background clutter. The state-of-the-art methods on FER employ fixed size pooling in attention networks, resulting in suboptimal robustness in unconstrained environments. In this work, a novel Multi-Scale Attention Network (MSAN) is integrated with the YOLOv8 backbone architecture for expression classification. The YOLOv8 backbone provides efficient feature extraction with a lightweight, detection-oriented architecture, enabling real-time processing and strong spatial feature representation. The Convolutional Block Attention Mechanism (CBAM) is employed in the proposed work. The standard convolutional blocks in YOLOv8 backbone are replaced with MSAN, wherein the fixed-size pooling in the spatial attention mechanism of CBAM is replaced with a Pyramid Pooling Mechanism (PPM). The PPM employs adaptive average pooling at multiple resolutions to capture multi-scale contextual information, which is subsequently fused into a unified feature representation. This enables the spatial attention mechanism in MSAN to capture both global facial context and local region-level cues simultaneously, leading to superior robustness to scale variations, partial occlusions, and diverse expression variations. The work is evaluated on benchmark wild datasets including RAF-DB, FER2013, and AffectNet, with all experiments performed using 5-fold cross-validation. Experimental results demonstrate that the multi-scale attention network with PPM in YOLOv8 backbone achieved improvement in classification accuracy and robustness when compared with the state-of-the-art methods for expression classification in the wild. These findings highlight the effectiveness of integrating MSAN into lightweight detection-based backbones for real-world FER applications.

The widely distributed “Step-type” landslides in the Three Gorges Reservoir (TGR) area have caused serious casualties and heavy economic losses. The prediction research of landslide displacement will be beneficial to the establishment of local geological hazard early warning systems for the realization of scientific disaster prevention and mitigation. However, the number of observed data like landslide displacement, rainfall, and reservoir water level in this area is very small, which results in difficulties for the training of advanced deep learning model to obtain more accurate prediction results. To solve the above problems, a Two-stage Combined Deep Learning Dynamic Prediction Model (TC-DLDPM) for predicting the typical “Step-type” landslides in the TGR area under the condition of small samples is proposed. The establishment process of this method is as follows: (1) the Dynamic Time warping (DTW) method is used to enhance the small samples of cumulative displacement data obtained by the Global Positioning System (GPS); (2) A Difference Decomposition Method (DDM) based on sequence difference is proposed, which decomposes the cumulative displacement into trend displacement and periodic displacement, and then the cubic polynomial fitting method is used to predict the trend displacement; (3) the periodic displacement component is predicted by the proposed TC-DLDPM model combined with external environmental factors such as rainfall and reservoir water level. The TC-DLDPM model combines the advantages of Convolutional Neural Network (CNN), Attention mechanism, and Long Short-term Memory network (LSTM) to carry out two-stage learning and parameter transfer, which can effectively realize the construction of a deep learning model for high-precision under the condition of small samples. A variety of advanced prediction models are compared with the TC-DLDPM model, and it is verified that the proposed method can accurately predict landslide displacement, especially in the case of drastic changes in external factors. The TC-DLDPM model can capture the spatio-temporal characteristics and dynamic evolution characteristics of landslide displacement, reduce the complexity of the model, and the number of model training calculations. Therefore, it provides a better solution and exploration idea for the prediction of landslide displacement under the condition of small samples.

Multi-view 3D reconstruction aims to discover 3D characteristics based on visual information captured across multiple viewpoints. Transformer networks have shown remarkable success in various computer vision tasks, including multi-view 3D reconstruction. However, the reconstruction of accurate 3D shapes faces challenges when trying to efficiently extract and merge features across views. The existing frameworks struggled to capture the subtle relationships between the views, resulting in a poor reconstruction. To address this issue, we present a new framework, WGA-SWIN, for 3D reconstruction using multi-view objects. Our method introduces a Window Grouping Attention (WGA) mechanism that uses group tokens from different views for each window attention operation, enabling efficient inter-view and intra-view feature extraction. Diversity among various groups in a model contributes to the richness of feature learning, which results in advanced and dependable feature learning, resulting in more comprehensive and robust representations. Within the encoder swin transformer blocks, we integrated WGA to utilize both hierarchical design and shifted window attention mechanisms for efficient multi-view feature extraction. In addition, we developed a progressive hierarchical decoder that combines swin transformer blocks with 3D convolutions to utilize voxel representation, resulting in a high resolution for obtaining high-quality 3D reconstructions with fine structural details. The experimental results on the benchmark datasets ShapeNet and Pix3D demonstrate that our work achieves state-of-the-art (SOTA) performance, outperforming existing methods in both single-view and multi-view 3D reconstruction, beyond the capabilities of current technologies. We lead by 0.95% and 1.07% in both IoU and F-Scores respectively, which demonstrates the robustness of our method.

With the rapid development of Internet technology, numerous malicious URLs have appeared, which bring a large number of security risks. Efficient detection of malicious URLs has become one of the keys for defense against cyber attacks. Deep learning methods bring new developments to the identification of malicious web pages. This paper proposes a malicious URL detection method based on a bidirectional gated recurrent unit (BiGRU) and attention mechanism. The method is based on the BiGRU model. A regularization operation called a dropout mechanism is added to the input layer to prevent the model from overfitting, and an attention mechanism is added to the middle layer to strengthen the feature learning of URLs. Finally, the deep learning network DA-BiGRU model is formed. The experimental results demonstrate that the proposed method can achieve better classification results in malicious URL detection, which has high significance for practical applications.

Sentiment analysis is a subfield of Natural Language Processing (NLP) which tries to process a text to extract opinions or attitudes towards topics or entities. Recently, the use of deep learning methods for sentiment analysis has received noticeable attention from researchers. Generally, different deep learning methods have shown superb performance in sentiment analysis problem. However, deep learning models are different in nature and have different strengths and limitations. For example, convolutional neural networks are useful for extracting local structures from data, while recurrent models are able to learn order dependence in sequential data. In order to combine the advantages of different deep models, in this paper we have proposed a novel approach for aspect-based sentiment analysis which utilizes deep ensemble learning. In the proposed method, we first build four deep learning models, namely CNN, LSTM, BiLSTM and GRU. Then the outputs of these models are combined using stacking ensemble approach where we have used logistic regression as meta-learner. The results of applying the proposed method on the real datasets show that our method has increased the accuracy of aspect-based prediction by 5% to 20% compared to the basic deep learning methods.

With the diversification of network traffic and the popularization of encrypted communication, traditional traffic classification methods have been difficult to cope with the challenges of new encryption protocols and hidden traffic. Deep learning, as a powerful feature extraction and classification tool, has been widely used in network traffic classification. In this paper, a deep network traffic classification model based on multi-scale feature fusion and attention mechanism (MSF-AttNet) is proposed. Features of different time scales are extracted through multi-scale convolution, and the adaptive weighting of channel attention and temporal self-attention mechanisms is combined to significantly improve the classification accuracy and interpretability of the model. Experiments show that MSF-AttNet outperforms traditional methods and other deep learning models on the ISCX VPN-nonVPN dataset.

The Accurate and the early detection of the neurodegenerative brain disorders such as the Alzheimer’s disease(AD) is crucial today for an effective patient care and prevention of disease progression. Computer Assisted Diagnosis (CAD) based on the neuroimaging data is an active research that was enhanced recent years by the deep learning methods. Brain modalities hold the key to achieve a comprehensive understanding of the brain changes and disorders. Magnetic Resonance Imaging(MRI) is a powerful brain modality and biomarker to capture the brain changes. It has been widely adopted for the AD diagnosis. Most of the recent studies are based on the Convolution Neural Network (CNN)using the MRI modality for the AD detection. However the CNN requires a huge amount of data. Furthermore, current CNN models cannot provide a good feature representation due to the lack of an adaptive channel weighting. The main drawback of the CNN network is its inability to learns the importance of the image features and the main correlations among them. Current methods that are based on the CNN does not ensure a valuable information extraction about which brain regions are related to the AD detection. To deal with these challenges, we proposed 2 contributions. Firstly, we used a Deep Convolution Generative Adversarial neural network(DCGAN) for data augmentation to enhance the training and to tackle the lack of data. We proposed also a new method for AD detection based on the integration of the Efficient Channel Attention(ECA-Net) into the Residual network. The ECA module improve the residual network by an attention mechanism to extract the most relevant features and ensure an adaptive weighting channel mechanism. Our method provide an efficient feature representation and extraction with low computational cost. The proposed method was validated using the ADNI (Alzheimer’s disease neuroimaging initiative) and the Open Access Series of Imaging Studies (OASIS). The experimental results outlines that our proposed method achieved the highest classification accuracy comparing with different methods by reaching an accuracy rate of 95%KeywordsAlzheimer’s diseaseData augmentationAttention mechanismDCGANECA-ResNet101

This study was conducted to examine the learning styles and the status of academic stress prevalent among Higher Secondary School Certificate (HSSC), Advanced Level (A Level), and International Baccalaureate Diploma Programme (IBDP) students hailing from Punjab, Pakistan – methodologically entailing a ‘descriptive research using a survey design’ framework. Data was gathered from 983 students enrolled in the local HSSC, A Level and IBDP streams employing a systematic random sampling technique via a self-developed questionnaire. This input was organized, coded, and analysed using SPSS software, applying both inferential and descriptive statistics, with the results revealing significant differences in the learning styles among the three student cohorts. Most of the pupils in the HSSC stream consistently adopted surface learning style, while most A Level student deployed strategic learning style. The majority of IBDP students, however, regularly adopted both strategic and deep learning styles. Moreover, a significant difference in academic stress levels was found between the three groups, with HSSC students experiencing more perceived stress compared to A Level and IBDP students. Education stakeholders have, therefore, been recommended to train students to adopt appropriate learning styles to improve their academic performance and reduce concurrent academic stress.

Recently, cargo ship detection in remote sensing images based on deep learning is of great significance for cargo ship monitoring. However, the existing detection network is not only unable to realize autonomous operation on spaceborne platforms due to the limitation of computing and storage, but the detection result also lacks the directional information of the cargo ship. In order to address the above problems, we propose a novel cargo ship detection and directional discrimination method for remote sensing images based on a lightweight network. Specifically, we design an efficient and lightweight feature extraction network called the one-shot aggregation and depthwise separable network (OSADSNet), which is inspired by one-shot feature aggregation modules and depthwise separable convolutions. Additionally, we combine the RPN with the K-Mean++ algorithm to obtain the K-RPN, which can produce a more suitable region proposal for cargo ship detection. Furthermore, without introducing extra parameters, the directional discrimination of the cargo ship is transformed into a classification task, and the directional discrimination is completed when the detection task is completed. Experiments on a self-built remote sensing image cargo ship dataset indicate that our model can provide relatively accurate and fast detection for cargo ships (mAP of 91.96% and prediction time of 46 ms per image) and discriminate the directions (north, east, south, and west) of cargo ships, with fewer parameters (model size of 110 MB), which is more suitable for autonomous operation on spaceborne platforms. Therefore, the proposed method can meet the needs of cargo ship detection and directional discrimination in remote sensing images on spaceborne platforms.

Fire hazards have increased in recent years and detecting fire at an early stage is of utmost importance. An upward smoke movement can help identify location of a fire incident. Therefore smoke detection using vision based machine learning techniques have been quite useful. Recent techniques deploy deep learning models for smoke detection in an outdoor environment. Despite advancements in the field, smoke detection in challenging environments is still a concern in real time applications. Further, deep learning models have large memory footprint that hinders their usage in IoT based smoke detection systems. In this paper, a convolutional neural network with attention mechanism and residual learning is proposed for smoke detection using images of outdoor scenes. The model is lightweight with only 1.23 million parameters, reasonably lower than the existing deep learning models. The model achieves a detection rate of $$99.13\%$$ , and an accuracy of $$99.20 \%$$ on a publicly available dataset. Its performance is also compared with eight existing deep learning smoke detection models that shows its superiority over other models. Features extracted through the model are clustered using t-SNE visualization technique to demonstrate the model’s efficacy in distinguishing features of smoke and non-smoke images.