Search

Manuscript binarization is used to convert each pixel in the script image into text and background. Many manuscript binarization methods have been proposed, such as the Otsu, Bernsen, Sauvola, Niblack, Phansalkar and Singh methods. These methods only focus on one problem of a degraded manuscript. In this research, a deep learning approach based on the U-Net method is applied for binarization of degraded ancient manuscripts. Adding layers to the U-Net architecture can cause more parameters and excessive computational calculations. Residual U-Net (ResUNet) is a development of the U-Net method. ResUNet, with its residual blocks, enables efficient and effective feature extraction, capturing fine details of degraded documents. This is important for identifying and distinguishing text from various artifacts and noise in the document. ResUNet can handle various types of image degradation thanks to its residual blocks that prevent gradient loss and strengthen features over the network. Convolutional Long Short-Term Memory (ConvLSTM) is a variant of LSTM (Long Short-Term Memory) designed for spatial data such as images. ConvLSTM combines the ability of LSTM to learn long-term dependencies with the power of CNN in processing spatial data. The combination of ResUNet and ConvLSTM for binarization of degraded documents is a powerful strategy that leverages the power of both architectures to improve quality and accuracy in separating text from degraded background. The aim of this research is to determine the performance evaluation results of the combination of ResUNet and ConvLSTM architectures on the binarization of degraded ancient Javanese manuscripts. The trial was conducted using datasets taken from several museums. The dataset consists of 1200 images of Javanese ancient manuscripts that were damaged in the form of perforated paper, ink bleed through from the previous page, and red or brownish spots. The proposed method produces a loss value of 0.0559, F-Measure 92.89%, PSNR 18.52 dan IoU 0.85. [ABSTRACT FROM AUTHOR]

This paper presents an alternative approach of teaching, learning and solving systems of two linear equations for two unknowns that yield no solutions. We conducted a desk-based research on methods that have been used by in-service mathematics teachers for teaching systems of two linear equations in ordinary secondary schools. It was found that five common methods (substitution, elimination, graphical, inverse matrix, Cramer's rule) have been used for teaching a system of two linear equations for two unknowns that yield no solution and all methods yield the same answer regardless of having different ways of approaching the system. We realized that a crossing method (alternative approach) is not found in the literature and yet not used by teachers for teaching students a system of two linear equations that yield no solution. But this crossing method yields similar answers with that resulted when using the five common methods. We present this alternative method in this paper by comparing with the answers obtained using five methods while focusing on two systems of two linear equations that yield no solution. This new approach has implications in teaching, learning and solving systems of two linear equations that yield no solutions in ordinary secondary schools, including mathematics teachers and educators can use this method for teaching students in solving systems of two linear equations for two unknowns that yield no solutions. [ABSTRACT FROM AUTHOR]

The recognition of food images is of great significance for nutrition monitoring, food retrieval and food recommendation. However, the accuracy of recognition had not been high enough due to the complex background of food images and the characteristics of small inter-class differences and large intra-class differences. To solve these problems, this paper proposed a food image recognition method based on transfer learning and ensemble learning. Firstly, generic image features were extracted by using the convolutional neural network models (VGG19, ResNet50, MobileNet V2, AlexNet) pre-trained on the ImageNet dataset. Secondly, the 4 pre-trained models were transferred to the food image dataset for model fine-tuning. Finally, different basic learner combination strategies were adopted to establish the ensemble model and classify feature information. In this paper, several kinds of experiments were performed to compare the results of food image recognition between single models and ensemble models on food-11 dataset. The experimental results demonstrated that the accuracy of the ensemble model was the highest, reaching 96.88%, which was superior to any base learner. Therefore, the convolutional neural network model based on transfer learning and ensemble learning has strong learning ability and generalization ability, and it is feasible and practical to apply the method to food image recognition. [ABSTRACT FROM AUTHOR]

This paper responds to challenges around how to generate robust evidence in keeping with the principles of an asset-based approach based on mobilization of community strengths. The design of a collaborative evaluation of a multi-site Asset Based Community Development program is described and emergent learning discussed. A qualitative mixed method design was used to capture changes at community and program level drawing on diverse sources of evidence. Shared principles on the conduct of the evaluation were developed with program leads and community practitioners and opportunities for shared learning were built in. The paper distils learning on evaluation into six design features including the asset-based model as a framework, understandings of evidence and outcomes, ethical conduct, and the centrality of a collaborative and developmental approach. The paper concludes that these features form a coherent approach to asset-based evaluation which can link the theory and practice of Asset Based Community Development. [ABSTRACT FROM AUTHOR]

Multimodal Sentiment Analysis (MSA) has become an essential area of research to achieve more accurate sentiment analysis by integrating multiple perceptual modalities such as text, vision, and audio. However, most previous studies failed to align the various modalities well and ignored the differences in semantic information, leading to inefficient fusion between modalities and generating redundant information. In order to solve the above problems, this paper proposes a transformer-based network model, Tri-CLT. Specifically, this paper designs Integrating Fusion Block to fuse modal features to enhance their semantic information and mitigate the secondary complexity of paired sequences in the transformer. Meanwhile, the cross-modal attention mechanism is utilized for complementary learning between modalities to enhance the model performance. In addition, contrastive learning is introduced to improve the model's representation of learning ability. Finally, this paper conducts experiments on CMU-MOSEI aligned and unaligned data, and the experimental results show that the proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

The stratospheric airship, as a near-space vehicle, is increasingly utilized in scientific exploration and Earth observation due to its long endurance and regional observation capabilities. However, due to the complex characteristics of the stratospheric wind field environment, trajectory planning for stratospheric airships is a significant challenge. Unlike lower atmospheric levels, the stratosphere presents a wind field characterized by significant variability in wind speed and direction, which can drastically affect the stability of the airship's trajectory. Recent advances in deep reinforcement learning (DRL) have presented promising avenues for trajectory planning. DRL algorithms have demonstrated the ability to learn complex control strategies autonomously by interacting with the environment. In particular, the proximal policy optimization (PPO) algorithm has shown effectiveness in continuous control tasks and is well suited to the non-linear, high-dimensional problem of trajectory planning in dynamic environments. This paper proposes a trajectory planning method for stratospheric airships based on the PPO algorithm. The primary contributions of this paper include establishing a continuous action space model for stratospheric airship motion; enabling more precise control and adjustments across a broader range of actions; integrating time-varying wind field data into the reinforcement learning environment; enhancing the policy network's adaptability and generalization to various environmental conditions; and enabling the algorithm to automatically adjust and optimize flight paths in real time using wind speed information, reducing the need for human intervention. Experimental results show that, within its wind resistance capability, the airship can achieve long-duration regional station-keeping, with a maximum station-keeping time ratio (STR) of up to 0.997. [ABSTRACT FROM AUTHOR]

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

The rapid advancement of digital technology has not only affected the world of work but also students' learning. Digital learning competence (DLC) is one of the essential skills students need for effective learning in a digital environment. Despite the significant presence of secondary vocational school students in China, constituting one-third of the high school demographic, research on their digital learning needs remains sparse. Addressing this gap, this paper attempted to propose the elements and structural model of digital learning competence for secondary vocational school students (V-DLC). A corresponding questionnaire was compiled, and an analysis was carried out with 872 valid survey data of secondary vocational school students achieved by convenient sampling. A five-factor model for the V-DLC was established through exploratory and confirmatory factor analyses, cross-validity, and criterion validity tests. This paper suggests that evaluating students' digital learning competence in secondary vocational schools can be achieved by considering the dimensions of cognitive processing and reading, technology use, thinking skills, activity management, and will management, combined with students' learning experiences in school and other fields. Given the global focus on digital learning competence, this framework will pave the way for empirical research on digital learning and guide the enhancement of student learning ability in vocational settings, adapting to the digital era. Furthermore, transitioning to a digitalized vocational education system is essential for preparing students for a digitally-driven workforce, aligning with modern job market demands and global trends. [ABSTRACT FROM AUTHOR]

This paper seeks to examine the questions of what criteria definitions of Artificial Intelligence (AI) use to define AI, what the disagreements that revolve around the term AI are based on, and what correlations can be drawn to other parameters. Framed as a problem of classification, a random sample of 45 definitions from various text sources was subjected to a qualitative content analysis. The criteria found are concluded in five dimensions, namely (1) learning ability, (2) human likeness, (3) state of "mind", (4) complexity of the problem, and (5) successfulness. Further, the results support the view that there is no consensus neither on which of these criteria are crucial to define AI nor on how these criteria must be fulfilled. By opposing the frequencies of the dimensions found with the metadata collected, it can be seen that most of these, e.g., country, scientific field, or gender of the author, are statistically independent of content variables, while the medium in which the definition was published shows a strong correlation. Since different mediums target different purposes and different readers, it must be taken into account that writing a definition of AI is to be seen in the context of its distribution area and its goal. [ABSTRACT FROM AUTHOR]

Hole detection is an important means of crack detection for aero-engine blades, and the current technology still mainly relies on manual operation, which may cause safety hazards for visual reasons. To address this problem, this paper proposes a deep learning-based, aero-engine blade crack detection model. First, the K-means++ algorithm is used to recalculate the anchor points, which reduces the influence of the anchor frame on the accuracy; second, the backbone network of YOLOv5s is replaced with Mobilenetv3 for a lightweight design; then, the slim-neck module is embedded into the neck part, and the activation function is replaced with Hard Sigmoid for redesign, which improves the accuracy and the convergence speed. Finally, in order to improve the learning ability for small targets, the SimAM attention mechanism is embedded in the head. A large number of ablation tests are conducted in real engine blade data, and the results show that the average precision of the improved model is 93.1%, which is 29.3% higher; the number of parameters of the model is 12.58 MB, which is 52.96% less, and the Frames Per Second (FPS) can be up to 95. The proposed algorithm meets the practical needs and is suitable for hole detection. [ABSTRACT FROM AUTHOR]

The Internet of Multimedia Things (IoMT) refers to a network of interconnected multimedia devices that communicate with each other over the Internet. Recently, smart healthcare has emerged as a significant application of the IoMT, particularly in the context of knowledge‐based learning systems. Smart healthcare systems leverage knowledge‐based learning to become more context‐aware, adaptable, and auditable while maintaining the ability to learn from historical data. In smart healthcare systems, devices capture images, such as X‐rays, Magnetic Resonance Imaging. The security and integrity of these images are crucial for the databases used in knowledge‐based learning systems to foster structured decision‐making and enhance the learning abilities of AI. Moreover, in knowledge‐driven systems, the storage and transmission of HD medical images exert a burden on the limited bandwidth of the communication channel, leading to data transmission delays. To address the security and latency concerns, this paper presents a lightweight medical image encryption scheme utilising bit‐plane decomposition and chaos theory. The results of the experiment yield entropy, energy, and correlation values of 7.999, 0.0156, and 0.0001, respectively. This validates the effectiveness of the encryption system proposed in this paper, which offers high‐quality encryption, a large key space, key sensitivity, and resistance to statistical attacks. [ABSTRACT FROM AUTHOR]

Salient object detection (SOD) aims to identify the most visually striking objects in a scene, simulating the function of the biological visual attention system. The attention mechanism in deep learning is commonly used as an enhancement strategy which enables the neural network to concentrate on the relevant parts when processing input data, effectively improving the model's learning and prediction abilities. Existing saliency object detection methods based on RGB deep learning typically treat all regions equally by using the extracted features, overlooking the fact that different regions have varying contributions to the final predictions. Based on the U2Net algorithm, this paper incorporates the split coordinate channel attention (SCCA) mechanism into the feature extraction stage. SCCA conducts spatial transformation in width and height dimensions to efficiently extract the location information of the target to be detected. While pixel-level semantic segmentation based on annotation has been successful, it assigns the same weight to each pixel which leads to poor performance in detecting the boundary of objects. In this paper, the Canny edge detection loss is incorporated into the loss calculation stage to improve the model's ability to detect object edges. Based on the DUTS and HKU-IS datasets, experiments confirm that the proposed strategies effectively enhance the model's detection performance, resulting in a 0.8% and 0.7% increase in the F1-score of U2Net. This paper also compares the traditional attention modules with the newly proposed attention, and the SCCA attention module achieves a top-three performance in prediction time, mean absolute error (MAE), F1-score, and model size on both experimental datasets. [ABSTRACT FROM AUTHOR]

This paper aims to develop a new model of Project-Based Instructional Taxonomy (PBIT) that provides a tool of course design that facilitates Computational Thinking (CT) development as creative action in solving real-life problems. Theoretically, PBIT is built on an integrative framework bringing together with studies on CT education, creativity, Bloom's Taxonomy, and Project-Based Instruction (PBI). This guides the course design to make alignment between diverse elements including education objectives, categories of CT, levels of learning ability, process of project facilitation, and methods of grading. A case will be discussed that focuses on a course Deep Learning and Technologies in AI bachelor program at Northeastern University (NEU) in China. It also shows how PBIT is applied in teaching practice that benefits students' CT development. As the conclusion indicates, this paper has contributions to future research on creativity, PBI, CT, and AI education. [ABSTRACT FROM AUTHOR]

Automatic navigation with collision‐free navigation has become a critical challenge for unmanned surface vehicles (USVs) to expand their application scenarios. Conventional methods for achieving automatic navigation of USVs typically rely on finely modeling the environment, thus exhibiting poor generalization capabilities. Methods based on deep reinforcement learning possess powerful learning abilities and have achieved promising results in USV‐automatic navigation‐tasks. However, the increase in the complexity of network model structures has led to instability during the training process. Therefore, generating more robust navigation strategies, namely ensuring robust reward‐score trends during training and smoother action trajectories of the USV, is crucial for automatic navigation and constitutes the main research question of this study. In this paper, an improved deep deterministic policy gradient (DDPG) algorithm has been proposed for stable automatic navigation of USVs in complex environments. In this algorithm, first, we construct a stable training framework that incorporates the stable feature‐sharing module with constrained gradient backpropagation, which bolsters the USV's scene memorization capacity, reduces model training fluctuations during navigation policy learning, and improves the training stability of the navigation model. Second, we ensure the decision adaptability of the USV by constraining the extent of action change between adjacent time‐steps by using a reward‐function, which improves the USV‐action smoothly. Finally, we design typical USV‐automatic‐navigation‐scenarios to validate the performance of the Algorithm. Experimental results validate our algorithm's capability to achieve collision‐free navigation, outperforming the traditional DDPG algorithm in terms of convergence speed, effective sailing distance, and rudder angle maneuver consumption, among other performance metrics. [ABSTRACT FROM AUTHOR]

In steel production, defect detection is crucial for preventing safety risks, and improving the accuracy of steel defect detection in industrial environments remains challenging due to the variable types of defects, cluttered backgrounds, low contrast, and noise interference. Therefore, this paper introduces a steel surface defect detection model, DBCW-YOLO, based on YOLOv5. Firstly, a new feature fusion strategy is proposed to optimize the feature map fusion pair model using the BiFPN method to fuse information at multiple scales, and CARAFE up-sampling is introduced to expand the sensory field of the network and make more effective use of the surrounding information. Secondly, the WIoU uses a dynamic non-monotonic focusing mechanism introduced in the loss function part to optimize the loss function and solve the problem of accuracy degradation due to sample inhomogeneity. This approach improves the learning ability of small target steel defects and accelerates network convergence. Finally, we use the dynamic heads in the network prediction phase. This improves the scale-aware, spatial-aware, and task-aware performance of the algorithm. Experimental results on the NEU-DET dataset show that the average detection accuracy is 81.1, which is about (YOLOv5) 6% higher than the original model and satisfies real-time detection. Therefore, DBCW-YOLO has good overall performance in the steel surface defect detection task. [ABSTRACT FROM AUTHOR]

This paper demonstrates the regulation of women's pregnant bodies through and by discourses of care. It illustrates how present practices reflect those of slavery where the dressing of the body, styling of the hair, and dancing, communicated gender difference that complicated sexual difference. 1 The presentation explores the body as material, fleshy, changing, and regulated. It demonstrates that even when motherhood is seen as a social construct, there is a sexual attachment to certain practices of mothering (such as pregnancy and breastfeeding) that speaks to its materiality which intersect with the ideological aspect of motherhood. Michel Foucault argues that the social actor is a mere body, and power is exercised upon individuals as bodies are categorized, trained in procedures, and placed in hierarchies. The body therefore becomes docile through its ability to learn, and to internalize discourses that regulate thoughts and behaviors. Using the narratives of ten CARICOM mothers residing in Barbados, this paper unpacks the body politic of motherhood, noting specifically how motherhood operates as institution. [ABSTRACT FROM AUTHOR]

INTRODCTION: By analyzing the problem of self-monitoring in English online learning and constructing a strategyintegrated evaluation method, we can not only enrich the theoretical research results of self-monitoring in online learning, but also improve the independent learning ability and self-monitoring ability of students in English online learning. OBJECTIVES: To address the problem of poor optimization performance of current fusion optimization methods.METHODS:This paper proposes an online learning self-monitoring strategy fusion method based on improved nuclear reaction heuristic intelligent algorithm. First, the problems and enhancement strategies of online learning selfmonitoring are analyzed; then, the online learning self-monitoring strategy fusion model is constructed by improving the nuclear reaction heuristic intelligent algorithm; finally, the proposed method is verified to be effective and feasible through the analysis of simulation experiments. RESLUTS: The results show that the fusion method of learning self-monitoring strategies on the line at the 20th iteration number starts to converge to optimization with less than 0.1s optimization time, and the error of the statistical score value before and after weight optimization is controlled within 0.05. CONCLUSION:Addressing the Optimization of Convergence of Self-Monitoring Strategies for English Online Learning. [ABSTRACT FROM AUTHOR]

This paper explores the teachers' experiences of remote assessment in the Junior High School of Rizal Technological University. The qualitative study was used to determine the assessment methods used during the remote learning in terms of written and performance task and identify the most effective among other difficulties faced by the teachers in comparison with face-to-face. Data of the paper were obtained by conducting interviews that use open-ended questions from 10 participants who teach in the School Year 2021-2022. The analysis of the study was done according to themes and categories and participants' answers were quotes excerpted from the transcripts. The study's conclusion emphasizes the significance of carefully planning exams to guarantee academic integrity. With emphasis on the need to focus on cognitive, emotional, and psychomotor abilities when designing learning exams, especially for online learning, as well as the use of technology tools to monitor results and prevent dishonest behavior during online assessments. Finally, a complementary technique for evaluating students while they are engaged in online learning through teaching resources or learning management systems must be available. [ABSTRACT FROM AUTHOR]

This systematic literature review aimed to provide updated information on lifelong learning in educational research by examining theoretical documents and empirical papers from 2000 to 2022. This review sought to identify concepts, theories, and research trends and methods linked to lifelong learning in educational research in different countries. Our review findings showed that theoretical papers, such as reports, policies, and concepts of lifelong learning, are generally much more extensive than empirical studies. Word cloud analysis revealed that the most prominent concepts were lifelong learning skills, lifelong learning competencies, and the three types of lifelong learning (formal, nonformal, and informal). Following the inductive analysis, this study investigated three common research trends: conceptual framework or policies of lifelong learning, lifelong learning abilities, and influencing factors of lifelong learning and/or lifelong learning abilities. Regarding methodology, this study identified only three studies that used mixed methods, which is insufficient in the field. In addition, heterogeneity was also observed between research instruments in lifelong learning. Different data analysis techniques can be applied in this field, including content analysis, descriptive analysis, and inferential analysis. Finally, the participants involved in the examined studies were students, primary and secondary school teachers, undergraduates, postgraduates, student teachers, European Union Lifelong Learning experts, young adults, teacher educators, administrators, and academic staff. [ABSTRACT FROM AUTHOR]

Driver distraction detection not only helps to improve road safety and prevent traffic accidents, but also promotes the development of intelligent transportation systems, which is of great significance for creating a safer and more efficient transportation environment. Since deep learning algorithms have very strong feature learning abilities, more and more deep learning-based driver distraction detection methods have emerged in recent years. However, the majority of existing deep learning-based methods are optimized only through the constraint of classification loss, making it difficult to obtain features with high discrimination, so the performance of these methods is very limited. In this paper, to improve the discrimination between features of different classes of samples, we propose a high-discrimination feature learning strategy and design a driver distraction detection model based on Swin Transformer and the highly discriminative feature learning strategy (ST-HDFL). Firstly, the features of input samples are extracted through the powerful feature learning ability of Swin Transformer. Then, the intra-class distance of samples of the same class in the feature space is reduced through the constraint of sample center distance loss (SC loss), and the inter-class distance of samples of different classes is increased through the center vector shift strategy, which can greatly improve the discrimination of different class samples in the feature space. Finally, we have conducted extensive experiments on two publicly available datasets, AUC-DD and State-Farm, to demonstrate the effectiveness of the proposed method. The experimental results show that our method can achieve better performance than many state-of-the-art methods, such as Drive-Net, MobileVGG, Vanilla CNN, and so on. [ABSTRACT FROM AUTHOR]

This paper contributes to the dialogue around how to increase inclusion in higher education, taking the lecturer perspective as the point of departure. Theoretically, disability is understood as an interaction, which means that lecturers partake in the constitution of dis/ability in learning situations. Two qualitative interviews were conducted with an interdisciplinary lecturer employed in an institution of higher education in Norway. These data are used for this single case study to illustrate and reflect on the challenges of diversity in learning situations. Findings suggest that the lecturer struggles to encounter an increasingly diverse student population inclusively. Overall, her experiences unpack the outcome of a structural lack of prioritization to ensure accessibility for disabled students at an institutional level at the university where she is employed. This article emphasizes that the responsibility to ensure an inclusive teaching practice in higher education must be recognized and treated as an institutional obligation. To signal its priority, all institutions of higher education should make inclusive training obligatory for lecturers, as well as assigning hours to work on enhancing the development of inclusive skills in this group. [ABSTRACT FROM AUTHOR]

The combination of UAV camera and intelligent algorithm is a promising method for non-contact bridge crack detection. In this paper, an inspection tool based on UAV Image Acquisition Technology (UAVIAT) and Improved Intelligent Target Detection Technology (IITDT) called Improved Intelligent Real-Time Crack Detection Method for Bridges (IIRTCDMB) is proposed for efficient crack detection. The contributions of this paper are (1) The Squeeze-Excitement (SE) attention module is integrated into the target detection algorithm - You Only Look Once version 7 (YOLOv7) model to improve the learning ability of the feature channel. A Focal-efficient intersection over union (Focal-EIoU) loss function is also introduced to improve the regression accuracy of the model. As a result, a new crack image detection algorithm, YOLOv7-CD, is proposed. (2) A training process based on two-stage transfer learning (TSTL) is established, and hyper-parameter optimization of YOLOv7-CD is carried out. The feasibility and excellent performance of the proposed method are verified by applying it on the Cuntan Yangtze River Bridge. The results show that the average precision (AP) of the YOLOv7-CD model is improved by 3.19% compared with the original YOLOv7 model. After TSTL and hyperparameter optimization, the AP of the YOLOv7-CD model for bridge crack detection reaches 98.01%, which is higher than that of the popular target detection models. The IIRTCDMB proposed in this paper can acquire bridge surface images more safely and efficiently, and provide inspectors with more accurate structural crack information with lower computational and hardware requirements, which can provide technical support for the assessment of structural safety conditions and the formulation of maintenance programs. [ABSTRACT FROM AUTHOR]

Physical activity breaks in the classroom are an efficient way of promoting healthy behaviors in students, enhancing the development of their cognitive and academic abilities. The effects of active breaks, which are exclusive to the academic environment, are almost entirely positive, only a few papers did not show significant improvements, but they did not show any negative impact on academic performance either. This research was carried out to identify the properties and consequences of active breaks and physical activity during classes in school age. We have examined multiple databases, and we have selected 41 papers accounting for a time span of 15 years. Psychology, medicine, and education databases were the most browsed Most papers revealed positive outcomes for improving skills related to mathematics, language, reading, comprehension, as well as cognitive and executive functions. Overall, the results of this review corroborate the theory that physical education in schools is positively associated with academic performance in children. Education researchers keep investigating in order to fully assess the positive impact on academic performance, behavior during classes, and cognitive functions. [ABSTRACT FROM AUTHOR]

Can technology be the innovation that brings salvation or, in contrast, conserve or even empower the present educational enterprise? The present paper analyses the relationship between educational technologies and educational schooling. In the beginning, both education and technology are redefined. Technology is defined as the collective creative intelligence of mankind dedicated to solving existential problems and providing human needs. This definition draws on the Ellul Technique and Heidegger’s extension of man’s definitions. Technology is in the hands of the inventors and users, and it can be constructed or destroyed accordingly. The education enterprise was configured during the Industrial Revolution in the 19th century and, therefore, is based on mechanical principles. The mechanical perception of learning is responsible for the current factory schooling education model. An alternative model of schooling appropriate for live learners is suggested and compared with the present model. The nature of the effect of technology depends on the choice between the two alternatives: The factory or the living learner model. Detailed accounts of the choices indicated that the present factory model was chosen for all aspects examined. The conclusion is embarrassing. At present, most of the impact of educational technology is by conservation, disguised as an innovation. First, a far-reaching transformation of the conceptual framework of the factory model is required, and technology should be redirected to enable real innovation. [ABSTRACT FROM AUTHOR]

Deep learning network has the advantages of strong learning ability, strong adaptability, and good portability. Therefore, synthetic aperture radar (SAR) automatic target recognition (ATR) based on deep network is widely used in both military and civilian fields. However, due to the imaging conditions, radar angle, imaging distance, and other reasons, it is difficult to obtain efficient and usable SAR image datasets. SAR images’ recognition under small sample conditions is still a challenging problem. In this paper, a SAR target recognition method based on multi-view differential feature fusion network is proposed to address this problem. Considering the correspondence between RCS and target features, the network extracts dissimilarities between features from SAR images of different angles of the same target and fuses them with the original features of one angle to form new features, which enriches the available training data. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) public dataset show that the proposed method has a higher target recognition rate than other deep network methods, as well as single angle input recognition methods. [ABSTRACT FROM AUTHOR]

In unsupervised domain adaptation (UDA), knowledge is transferred from label-rich source domains to relevant but unlabeled target domains. Current most popular state-of-the-art works suggest that performing domain alignment from the class perspective can alleviate domain shift. However, most of them based on domain adversarial which is hard to train and converge. In this paper, we propose a novel contrastive learning to improve diversity and discriminability for domain adaptation, dubbed as IDD_ICL, which improve the discriminativeness of the model while increasing the sample diversity. To be precise, we first design a novel implicits contrastive learning loss at sample-level by implicit augment sample of the source domain. While augmenting the diversity of the source domain, we can cluster the samples of the same category in the source domain together, and disperse the samples of different categories, thereby improving the discriminative ability of the model. Furthermore, we show that our algorithm is effective by implicitly learning an infinite number of similar samples. Our results demonstrate that our method doesn't require complex technologies or specialized equipment, making it readily adoptable and applicable in practical scenarios. [ABSTRACT FROM AUTHOR]

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

As one of the advanced automotive chassis technologies, the steer-by-wire system offers a high level of precision, responsiveness, and controllability in the driving experience. It can also adjust and optimize parameters to adapt to the preferences of different drivers. However, when faced with the steer-by-wire system, both experienced drivers and novice drivers are in the novice stage, exhibiting learning or adaptation behaviors when using this steering system. In this paper, a small-scale pilot evaluation was conducted by means of a questionnaire survey and driving-simulator experiment, and the learning behavior and adaptability of four experienced and four novice drivers to the steer-by-wire system were analyzed when using the traditional steering system. The study found that experienced drivers show significant changes in their adaptation to the steering system, mainly due to their habitual driving with traditional steering systems. In contrast, novice drivers show no significant changes in their adaptation to the steering system, which is attributed to their lack of driving experience and skills, resulting in less sensitivity to changes in the steering system. Additionally, the study found that novice drivers under the steer-by-wire system grasp control over speed and steering-wheel angle more quickly. This research provides a reference for improving drivers' learning and adaptation abilities to the steer-by-wire system and optimizing the design of the steer-by-wire system. [ABSTRACT FROM AUTHOR]

Multi-label Short Text Classification (MSTC) is a challenging subtask of Multi-Label Text Classification (MLTC) for tagging a short text with the most relevant subset of labels from a given set of labels. Recent studies have attempted to address MSTC task using MLTC methods and Pre-trained Language Models (PLM) based fine-tuning approaches, but suffering the low performance from the following three reasons, 1) failure to address the issue of data sparsity of short texts, 2) lack of adaptation to the long-tail distribution of labels in multi-label scenarios and 3) an implicit weakness in the encoding length for PLM, which limits the ability of the prompt learning paradigm. Therefore, in this paper, we propose KSSVPT, a Knowledge and Separating Soft Verbalizer based Prompt Tuning method for MSTC to address the above challenges. Firstly, to mitigate the sparsity issue in short texts, we propose a novel approach that enhances the semantic information of short texts by integrating external knowledge into the soft prompt template. Secondly, we construct a new soft prompt verbalizer for MSTC, called separating soft prompt verbalizer, to adapt to the long-tail distribution issue aggravated by multiple labels. Thirdly, we propose a mechanism of label cluster grouping in building a prompt template to directly alleviate limited encoding length and capture the label correlation. Extensive experiments conducted on six benchmark datasets demonstrate the superiority of our model compared to all competing models for MLTC and MSTC in the tackling of MSTC task. [ABSTRACT FROM AUTHOR]

Neuromorphic computation draws inspiration from the remarkable features of the human brain including low energy consumption, parallelism, adaptivity, cognitive functions, and learning ability. These qualities hold the promise of unlocking groundbreaking computational techniques that surpass the limitations of traditional computing systems. This paper reports a remarkable photo‐synaptic behavior in the field of rare earth ion‐doped luminescent oxides by using long‐persistent luminescence (LPL). This system utilizes electron trap states to regulate the synaptic behavior, operating through a fundamentally different mechanism from that of electronic‐based synaptic devices. To realize this strategy, Tb3+ doped CaSnO3, which shows a significant LPL property under UV‐light excitation, is prepared. The luminescent system shows key neuromorphic characteristics such as paired‐pulse facilitation, pulse‐number/timing dependent potentiation, and pulse‐number/timing dependent short‐ to long‐term plasticity transition, which are required for realizing synaptic devices. This feature expands the way for advanced neuromorphic technologies employing light stimuli. [ABSTRACT FROM AUTHOR]

A long-standing research goal is to develop computing technologies that mimic the brain's capabilities by implementing computation in electronic systems directly inspired by its structure, function, and operational mechanisms, using low-power, spike-based neural networks. The Loihi neuromorphic processor provides a low-power, large-scale network of programmable silicon neurons for brain-inspired artificial intelligence applications. This paper exploits the Loihi processors and a theory-guided methodology to enable unsupervised learning of spike patterns. Our method ensures efficient and rapid selection of the network's hyperparameters, enabling the neuromorphic processor to generate attractor states through real-time unsupervised learning. Precisely, we follow a fast design process in which we fine-tune network parameters using mean-field theory. Moreover, we measure the network's learning ability regarding its error correction and pattern completion aptitude. Finally, we observe the dynamic energy consumption of the neuron cores for each millisecond of simulation equal to 23 μ J/time step during the learning and recall phase for four attractors composed of 512 excitatory neurons and 256 shared inhibitory neurons. This study showcases how large-scale, low-power digital neuromorphic processors can be quickly programmed to enable the autonomous generation of attractor states. These attractors are fundamental computational primitives that theoretical analysis and experimental evidence indicate as versatile and reusable components suitable for a wide range of cognitive tasks. [ABSTRACT FROM AUTHOR]

Objectives: Convolutional neural network (CNN) was widely used in landslide susceptibility assessment because of its powerful feature extraction capability. However, with the demand for scene diversification and high accuracy, the algorithm of CNN was constantly improved. The practice of improving accuracy by deepening the network hierarchy or combining other models tended to increase the number of model parameters and the amount of calculation greatly, which led to the difficulty of model training or the overfitting of results, thus limiting its practical application. We want to solve the above problems from the model structure. of feature maps, one-dimensional CNN（1D-CNN） and two-dimensional CNN（2D-CNN） were connected to maintain network depth, limit model parameters, and reduce computation. The parameters sharing of multidimensional convolution kernels was used to capture the deep coupling features of different dimensions and different landslide factors, so as to make full use of features and avoid overfitting. Taking Sedongpu gully in Xizang,China as the experimental area, this paper selected 11 kinds of landslide influencing factors to analyze the landslide susceptibility. Results: The results show that the multi-dimensional CNN coupling structure had the same training efficiency as the shallow 2D-CNN with fewer parameters due to the reduced computational effort. While compared with the deep 2D-CNN with the approximate number of parameters, the training time of the proposed method was significantly reduced and the training cost was lower. In addition, the coupled model had a stronger feature learning ability than the independent 1D-CNN and 2D-CNN, and therefore obtained higher model accuracy. Under each confusion matrix metric of the testing data, the coupled model received higher scores, and thus obtained more reliable landslide susceptibility assessment results. Conclusions: The multidimensional CNN coupling model proposed in this paper is a reliable method applicable to landslide susceptibility assessment. This study provides new theoretical guidance and technical support for further landslide hazard monitoring and prevention [ABSTRACT FROM AUTHOR]

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

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

Accurately capturing children's word learning abilities is critical for advancing our understanding of language development. Researchers have demonstrated that utilizing more complex statistical methods, such as mixed-effects regression and hierarchical linear modeling, can lead to a more complete understanding of the variability observed within children's word learning abilities. In the current paper, we demonstrate how a person-centered approach to data analysis can provide additional insights into the heterogeneity of word learning ability among children while also aiding researchers' efforts to draw individual-level conclusions. Using previously published data with 32 typically developing and 32 late-talking infants who completed a novel noun generalization (NNG) task to assess word learning biases (i.e., shape and material biases), we compare this person-centered method to three traditional statistical approaches: (1) a t-test against chance, (2) an analysis of variance (ANOVA), and (3) a mixed-effects regression. With each comparison, we present a novel question raised by the person-centered approach and show how results from the corresponding analyses can lead to greater nuance in our understanding of children's word learning capabilities. Person-centered methods, then, are shown to be valuable tools that should be added to the growing body of sophisticated statistical procedures used by modern researchers. [ABSTRACT FROM AUTHOR]

Automotive electronics and related software market is growing significantly and expected to gain high demand of skilled employees in the next decade. The market drivers being the customer preferences, government regulations, technology adoption and recent participants like autonomous and electric vehicle technologies. Hence, industries are showing lot of interest in collaborations with academia for technology innovations and for getting industry ready employees. This paper presents the experiences and outcomes of collaborations with automotive industries in automotive embedded systems courses like, Automotive electronics, AUTOSAR, Multicore core architecture and programming, and Human-Machine-Interface offered to the students of Electronics and Communication Engineering program at KLE Technological University. These courses involve core technical concepts, computing, and design of hardware/ software architecture. The traditional mode of teaching is found to be less effective and hence, innovative pedagogical techniques are used with the help of industries for teaching these courses. The techniques helped to enhance students' ability to solve complex engineering problems and to build higher cognitive learning ability. The collaborative contributions from both industry experts and academic faculty in design and delivery of automotive embedded courses have resulted in building industry specific skills among students which in turn resulted into a greater number of in campus placements and reduction in on job training. [ABSTRACT FROM AUTHOR]

Mindfulness meditation is a technique for regulating attention and emotions, which can help individuals enhance self-awareness and reduce stress. This paper aims at review the positive effects of mindfulness meditation on English learners and teachers, including improving English learning abilities and enhancing motivation, confidence, and enjoyment in English learning. Through systematic literature searches and screening methods from databases such as CNKI, Wan fang, Pub Med, and Web of Science, relevant papers on mindfulness meditation and English learning from the past decade were selected. Their research purposes, methods, innovations, and conclusions were analyzed. This paper specifically explores the literature review on the impact of mindfulness meditation on English learning, summarizing both the theory and practice of mindfulness meditation, and proposing future research directions and suggestions. Mindfulness meditation has a positive impact on English learning and classroom teaching, but its specific effects are influenced by various factors such as the type, duration, and frequency of mindfulness meditation. More empirical research is needed to validate its effects on English learning and to explore the optimal integration methods. [ABSTRACT FROM AUTHOR]

Virtual Reality (VR) has demonstrated significant advantages in various educational fields as it allows learners to actively learn in high interactivity and realism under their learning pace. However, for low‐achieving students, VR learning environments may introduce some challenges, which are problems encountered during their learning process, which lead to difficulties in self‐regulating their learning progress and becoming disoriented in the lack of guidance. This study aims to explore the improvement of self‐regulated VR learning environment based on the Cognitive Theory of Multimedia Learning and enhance the performance of low‐achieving students. We designed a VR course on electronic circuit hardware and programming, providing participants with a series of learning aids in the VR learning environment, including feedback, hints and guidance. Feedback aids provide correct or incorrect feedback after each task or test, guidance aids display progress following each task or test and hint aids offer guidance when inactivity is detected. A quasi‐experiment was conducted by using questionnaires and practical tasks to assess the participants' cognitive levels, practical hands‐on skills, self‐regulated learning abilities and learning engagement after VR learning. The results demonstrated significant improvements in all learning indicators for low‐achieving students. Practitioner notes What is already known about this topic Virtual Reality (VR) presents itself as a promising tool for self‐regulated learning (SRL). SRL abilities are of paramount importance within the learning environment of VR. In the context of the self‐regulated Virtual Reality (SRVR) learning environment, low‐achieving students have received little attention. What this paper adds It examines the effectiveness of learning aid mechanisms within the SRVR learning environment. These mechanisms support cognitive levels and increase engagement in SRVR learning. Low‐achieving learners benefit from the presence of learning aid mechanisms in the SRVR learning environment. Implications for practice and/or policy Providing learning aid mechanisms within the SRVR learning environment can potentially augment learning. Learning aids mechanism have the potential to provide comprehensive support within the SRVR setting. What is already known about this topic Virtual Reality (VR) presents itself as a promising tool for self‐regulated learning (SRL). SRL abilities are of paramount importance within the learning environment of VR. In the context of the self‐regulated Virtual Reality (SRVR) learning environment, low‐achieving students have received little attention. What this paper adds It examines the effectiveness of learning aid mechanisms within the SRVR learning environment. These mechanisms support cognitive levels and increase engagement in SRVR learning. Low‐achieving learners benefit from the presence of learning aid mechanisms in the SRVR learning environment. Implications for practice and/or policy Providing learning aid mechanisms within the SRVR learning environment can potentially augment learning. Learning aids mechanism have the potential to provide comprehensive support within the SRVR setting. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks (PINNs) are an emerging technology that can be used both in place of and in conjunction with conventional simulation methods. In this paper, we used PINNs to perform a forward simulation without leveraging known data. Our simulation was of a 2D natural convection-driven cavity using the vorticity-stream function formulation of the Navier-Stokes equations. We used both 2D simulations across the x and z domains at constant Rayleigh (Ra) numbers and 3D simulations across the x, z and Ra domains. The 3D simulation was tested for a PINN's ability to learn solutions in a higher-dimensional space than standard simulations. The results were validated against published solutions at Ra values of 10 3 , 10 4 , 10 5 , and 10 6 . Both the 2D simulations and 3D simulations successfully matched the expected results. For the 2D cases, more training iterations were needed for the model to converge at higher Ra values (10 5 and 10 6 ) than at lower Ra (10 3 and 10 4 ) indicating increased nonlinear fluid-thermal coupling. The 3D case was also able to converge but, but it required more training than any of the 2D cases due to the curse of dimensionality. These results showed the validity of standard simulations via PINNs and the feasibility of higher-order parameter space solutions that are not possible using conventional methods. They also showcased the additional computational demand associated with increasing the dimensionality of the learned parameter space. [ABSTRACT FROM AUTHOR]

This study investigated the seamless mobile learning practices of UK government workers at various life stages, to understand how context impacted decisions about how, when and where learning was undertaken. Following Hedegaard, the context was understood as involving settings embedded within institutions. Drawing on analysis of data from public domain blogs and reports and anonymised trace data showing e‐learning visits via a mobile device, a picture of institutional practice and values was developed. Against this backdrop, a survey of 50 individuals followed by semi‐structured interviews provided information about seamless mobile learning projects. Mobile learning was often fragmented and ad hoc, rather than part of a longer, seamless learning project. A distinction between just‐in‐time learning and just‐in‐case learning was apparent, with the latter often postponed. For mobile workers, mobile learning focused on current work setting, whereas workers who could work in many interchangeable settings might move to somewhere they could concentrate. Mobile learning was sometimes motivated by a sense of a lack of time and a need to stay 'on top of things' as much as by interest in a topic. Sustained seamless mobile learning projects occurred if there was institutional support for learning that was also of individual interest and if learners had the ability to orchestrate their learning. Learners reported these seamless mobile learning projects to be enjoyable and compelling. This paper contributes to the evidence of seamless mobile learning practice over the life course and illustrates the value of considering an individual's relation to various institutions in conceptualisations of seamless mobile learning. It also offers pointers for the future design of seamless mobile learning tools including a need to offer learners the opportunity to sometimes separate ongoing learning which is related to distinct institutions.Practitioner notesWhat is already known about this topicMobile devices accompany their owners across settings that were previously considered separate, such as work, college and households.This has the potential to impact work/home and other boundaries.From a pedagogical perspective, mobile devices may support seamless learning, in which experiences across distinct settings result in a holistic and unified understanding.What this paper addsIt introduces the concept of the institution to conceptions of seamless learning.It illustrates the ways in which different institutions (workplaces or educational institutions) can shape individual experiences and decisions about when and where to learn.It provides evidence that some working adults engage in seamless learning projects and describe this as compelling and enjoyable, but that others prefer to separate distinct life spheres.Implications for practice and/or policyThere may be value in institutions and designers supporting people who want to engage in seamless mobile learning.However, it is important to be aware that not everyone wants to engage in seamless learning.Seamless learning is more likely to occur when individual and institutional priorities are aligned across several institutions, so there will be challenges for a single institution seeking to promote it. [ABSTRACT FROM AUTHOR]

In view of the existing traffic signal detection algorithms, which require a large amount of computation and model, are difficult to deploy at the embedded end, and are difficult to detect long-distance traffic signals with a high miss rate, this paper designs a lightweight traffic signal detection algorithm for the embedded end, which aims at lightweight and real-time requirements. GhostNet network Ghost module and Ghost bottleneck layer structure are adopted to reduce the number of model parameters and improve the detection speed. To solve the feature similarity problem, the weighted bidirectional feature pyramid network is used to make the algorithm more sensitive to the target. The dense void space pyramid pool is used to optimize the extraction of global context information. Aiming at the problem of small target recognition, the information extraction of small target is enhanced through the improvement of multi-scale detection. Finally, the learning ability of the model is improved through knowledge distillation, and the detection performance is improved. Experimental results show that the recognition accuracy and recall rate of traffic lights by this detection algorithm reach 97.0% and 99% respectively, 2.7 and 3 percentage points higher than that of YOLOv5s. The model size is reduced to 8.06 MB, 58% of that of YOLOv5s, and the recognition rate is increased from 51 frames per second to 56 frames per second. Through testing in the embedded terminal, the improved algorithm can recognize the traffic signal in real time and accurately. [ABSTRACT FROM AUTHOR]

This paper considers the influence of course design on the capability of a vocational college to implement a student-centred learning approach to enhance academic student engagement. It is based on an action research project involving a course redesign within a vocational agricultural education setting that created a more student-centred approach and in turn enhanced academic student engagement compared to its traditional delivery. Phase 1 of research looked at academic student engagement in a traditional lecture format utilising a multi-methodological analysis. This analysis identified that one type of module presented a significant challenge with 0/16 classes rated as 'high engagement', primarily due to the subject content. Phase 2 redesigned a module of this type using a more student-centred learning approach to evaluate if this could enhance academic student engagement. Observations carried out on 24 classes of the redesigned module rated 21/24 as 'high engagement'. The redesign process enabled the use of a more student-centred learning approach albeit limited by requirements to comply with traditional quality assurance requirements of the current course design. This action research contributes a greater understanding of how the principles of course design need to be considered in seeking to enhance academic student engagement in vocational education. [ABSTRACT FROM AUTHOR]

Deep learning has recently unleashed the ability for Machine learning (ML) to make unparalleled strides. It did so by confronting and successfully addressing, at least to a certain extent, the knowledge bottleneck that paralyzed ML and artificial intelligence for decades. The community is currently basking in deep learning's success, but a question that comes to mind is: have all of the issues previously affecting machine learning systems been solved by deep learning or do some issues remain for which deep learning is not a bulletproof solution? This question in the context of the class imbalance becomes a motivation for this paper. Imbalance problem was first recognized almost three decades ago and has remained a critical challenge at least for traditional learning approaches. Our goal is to investigate whether the tight dependency between class imbalances, concept complexities, dataset size and classifier performance, known to exist in traditional learning systems, is alleviated in any way in deep learning approaches and to what extent, if any, network depth and regularization can help. To answer these questions we conduct a survey of the recent literature focused on deep learning and the class imbalance problem as well as a series of controlled experiments on both artificial and real-world domains. This allows us to formulate lessons learned about the impact of class imbalance on deep learning models, as well as pose open challenges that should be tackled by researchers in this field. [ABSTRACT FROM AUTHOR]

In response to the issues of low model recognition accuracy and weak generalization in mechanical equipment fault diagnosis due to scarce data, this paper proposes an innovative solution, a cross-device secondary transfer-learning method based on EGRUN (efficient gated recurrent unit network). This method utilizes continuous wavelet transform (CWT) to transform source domain data into images. The EGRUN model is initially trained, and shallow layer weights are frozen. Subsequently, random overlapping sampling is applied to the target domain data to enhance data and perform secondary transfer learning. The experimental results demonstrate that this method not only significantly improves the model's ability to learn fault features but also enhances its classification accuracy and generalization performance. Compared to current state-of-the-art algorithms, the model proposed in this study shows faster convergence speed, higher diagnostic accuracy, and superior robustness and generalization, providing an effective approach to address the challenges arising from scarce data and varying operating conditions in practical engineering scenarios. [ABSTRACT FROM AUTHOR]

Motivation Gene set enrichment (GSE) analysis allows for an interpretation of gene expression through pre-defined gene set databases and is a critical step in understanding different phenotypes. With the rapid development of single-cell RNA sequencing (scRNA-seq) technology, GSE analysis can be performed on fine-grained gene expression data to gain a nuanced understanding of phenotypes of interest. However, with the cellular heterogeneity in single-cell gene profiles, current statistical GSE analysis methods sometimes fail to identify enriched gene sets. Meanwhile, deep learning has gained traction in applications like clustering and trajectory inference in single-cell studies due to its prowess in capturing complex data patterns. However, its use in GSE analysis remains limited, due to interpretability challenges. Results In this paper, we present DeepGSEA, an explainable deep gene set enrichment analysis approach which leverages the expressiveness of interpretable, prototype-based neural networks to provide an in-depth analysis of GSE. DeepGSEA learns the ability to capture GSE information through our designed classification tasks, and significance tests can be performed on each gene set, enabling the identification of enriched sets. The underlying distribution of a gene set learned by DeepGSEA can be explicitly visualized using the encoded cell and cellular prototype embeddings. We demonstrate the performance of DeepGSEA over commonly used GSE analysis methods by examining their sensitivity and specificity with four simulation studies. In addition, we test our model on three real scRNA-seq datasets and illustrate the interpretability of DeepGSEA by showing how its results can be explained. Availability and implementation https://github.com/Teddy-XiongGZ/DeepGSEA [ABSTRACT FROM AUTHOR]

Video anomaly detection has always been a challenging task in computer vision due to data imbalance and susceptibility to scene variations such as lighting and occlusions. In response to this challenge, this paper proposes an unsupervised video anomaly detection method based on an attention-enhanced memory network. The method utilizes a dual-stream network structure of autoencoders, enhancing the model's learning ability for important features in appearance and motion by introducing coordinate attention mechanisms and variance attention mechanisms, emphasizing significant characteristics of static objects and rapidly moving regions. By adding memory modules to both the appearance and motion branches, the network structure's memory information is reinforced, enabling it to capture long-term spatiotemporal dependencies in videos and thereby improving the accuracy of anomaly detection. Furthermore, by optimizing the network structure's activation functions to handle negative inputs, it enhances its nonlinear modeling capabilities, enabling better adaptation to complex environments, including variations in lighting and occlusions, further improving the effectiveness of anomaly detection. The paper conducts comparative experiments and ablation studies using three public available datasets and various models. The results demonstrate that compared to baseline models, the AUC performance is improved by 3.9%, 4.7%, and 1.7% on UCSD Ped2, CHUK Avenue, and ShanghaiTech datasets, respectively. When compared with the other models, the average AUC performance is improved by 4.3%, 5.4%, and 6.2%, with an average improvement of 8.75% in the ERR metric, validating the effectiveness and adaptability of the proposed method. The code can be obtained at the following URL: https://github.com/AcademicWhite/AEMNet. [ABSTRACT FROM AUTHOR]

Depression is a serious mental illness that affects millions worldwide and consequently has attracted considerable research interest in recent years. Within the field of automated depression estimation, most researchers focus on neural network architectures while ignoring other research directions. Within this paper, we explore an alternate approach and study the impact of input representations on the learning ability of the models. In particular, we work with graph-based representations to highlight different aspects of input transcripts, both at the interview and corpus levels. We use sentence similarity graphs and keyword correlation graphs to exemplify the advantages of graphical representations over sequential models for binary classification problems within depression estimation. Additionally, we design multi-view architectures that split interview transcripts into question and answer views in order to take into account dialogue structure. Our experiments show the benefits of multi-view based graphical input encodings over sequential models and provide new state-of-the-art results for binary classification on the gold standard DAIC-WOZ dataset. Further analysis establishes our method as a means for generating meaningful insights and visual summaries of interview transcripts that can be used by medical professionals. [ABSTRACT FROM AUTHOR]

Whilst teaching about the nature of science (NOS) is a significant goal of science education, there remains debate about specifying the NOS and appropriate pedagogies and approaches to researching the NOS. A neglected, but conceptually and practically significant, problem is the proliferation of NOS-related learning goals such as NOS beliefs, views, understandings and knowledge. In this theoretical paper, we argue that such goals are often poorly defined, and different goals cohere with different pedagogical and research strategies. We propose a novel three-part taxonomy of NOS learning goals (as NOS beliefs, knowledge and understandings) and contend that different approaches are appropriate for teaching and assessing NOS beliefs, views and knowledge. An NOS belief refers to a positive attitudinal stance towards some proposition that lacks justificatory support or cannot easily be judged true or false. NOS knowledge indicates justified true beliefs related to the NOS. NOS understanding denotes a grasping of how a collection of NOS knowledge is related. The goals vary by the extent to which they can be judged true or false and the degree of justification they require. For NOS beliefs, a range of stances is acceptable; NOS knowledge must be a true and justified belief; in the case of NOS understanding, teaching and assessment should focus on the appreciation of relationships between justified true beliefs. The novel taxonomy brings needed clarity to a confused aspect of NOS research and may lead to the development of NOS pedagogies and assessment tools more precisely targeted to well-defined learning goals. [ABSTRACT FROM AUTHOR]

Behavior trees have attracted great interest in computer games and robotic applications. However, it lacks the learning ability for dynamic environments. Previous works combining behavior trees with reinforcement learning either need to construct an independent sub-scenario or train the learning method over the whole game, which is not suited for complex multi-agent games. In this paper, a framework is proposed, named as MARL-BT, that embeds multi-agent reinforcement learning methods into behavior trees. Following the running mechanism of behavior trees, we design the way of collecting samples and the training procedure. Further, we point out a special phenomenon in MARL-BT, i.e., the unexpected interruption, and present an action masking technique to remove its harmful effect on learning performance. Finally, we make extensive experiments on the 11 versus 11 full game in Google Research Football. The introduced MARL-BT framework could get an 11.507% improvement compared to pure BT for certain scenarios. The action masking technique could greatly improve the performance of the learning method, i.e., the final reward is improved around 100% times for a sub-task. [ABSTRACT FROM AUTHOR]