Search Results (2,923)

Video action recognition aims to achieve the automatic classification of human behaviors by analyzing the actions in videos, with its core lying in accurately capturing the spatial detail features of images and the temporal dynamic features among video frames. In response to the problems of limited action recognition accuracy in videos containing complex temporal dynamics and large network model parameters, this paper proposes an innovative multi-feature fusion information modeling method. This paper designs a plug-and-play multi-feature action extraction (MFAE) module. The module adopts a multi-branch parallel processing strategy and integrates the functions of modeling and extracting temporal features, spatial features, and motion features to ensure the efficient modeling of the spatio-temporal information, inter-frame differences, and temporal dependencies of video actions. Meanwhile, the network employs a lightweight channel attention module (TiedSE), which reduces the complexity of the network model and decreases the number of network parameters. Finally, the effectiveness of the model is demonstrated on the Jester dataset, SomethingV2 dataset, and UCF101 dataset, achieving accuracies of 94.01%, 66.19%, and 96.74% with only 1.45 M parameters, significantly fewer than existing algorithms. The proposed method balances accuracy and computational efficiency in video action recognition, overcoming the shortcomings of traditional algorithms in temporal modeling and demonstrating its effectiveness in the task of video action recognition. Full article

This systematic review analyzed the role of microlearning in basic education, identifying the most widely used Digital Information and Communication Technologies, relevant learning theories, and the role of social technologies from a Science, Technology, Society, and Environment (STSE) perspective. Following PRISMA 2020, searches were conducted in Web of Science, Scopus, ERIC, and IEEE Xplore databases. Studies on microlearning were selected based on previously defined eligibility criteria. The review process in Rayyan involved deduplication, screening, and full-text analysis. Data were qualitatively analyzed using content analysis, and methodological quality was assessed with CASP and the Downs and Black. The findings highlight that microlearning, integrated with digital tools such as online platforms, mobile apps, and short videos, significantly enhances student motivation, performance, and interaction; content in short modules facilitates knowledge retention and connects concepts to real-life situations. Promising trends include mobile technologies and gamification, which foster active, meaningful learning. Grounded in theories like Self-Determination, Constructionism, and Constructivism, microlearning personalizes teaching and promotes engagement, critical thinking, and accessibility, contributing to inclusive and sustainable education. From a STSE perspective, social technologies enhance autonomy, social interaction, and ethical–environmental awareness. In Brazil, further research on digital platforms and gamified strategies is needed to drive innovative educational practices. Full article

This study investigates the current industry practices for storage tank assessment and the possibilities for improving inspection methods using the latest technologies on the market. This article presents the main methods and technologies for non-destructive testing (NDT), along with new methods that make them more efficient and economical. To further analyze the state of a tank and determine its lifetime expectancy, analysis methods are presented based on NDT results. The key aspects that can be improved and made more efficient are NDT procedures using robots/drones and autonomous devices; automated inspection procedures, like remote video inspection combined with local thickness measurement or 3D scanning of the tank elements for deformations; advanced analysis methods using the input from the NDT and inspection data collected using analytical calculations according to applicable standards; Finite Element Analysis (FEA); and digitalized models of equipment (Digital Twin) accompanied by artificial intelligence for data processing. The best way to make the process more efficient is to develop and use dedicated standardized software for tank condition assessment. Full article

This study provides a comprehensive analysis of the evolution of Autism Spectrum Disorder (ASD) diagnostics, tracing its progression from psychoanalytic origins to the integration of advanced artificial intelligence (AI) technologies. The study explores, through scientific data bases like Pub Med, Scopus, and Google Scholar, how theoretical frameworks, including psychoanalysis, behavioral psychology, cognitive development, and neurobiological paradigms, have shaped diagnostic methodologies over time. Each paradigm’s associated assessment tools, such as the Autism Diagnostic Observation Schedule (ADOS) and the Vineland Adaptive Behavior Scales, are discussed in relation to their scientific advancements and limitations. Emerging technologies, particularly AI, are highlighted for their transformative impact on ASD diagnostics. The application of AI in areas such as video analysis, Natural Language Processing (NLP), and biodata integration demonstrates significant progress in precision, accessibility, and inclusivity. Ethical considerations, including algorithmic transparency, data security, and inclusivity for underrepresented populations, are critically examined alongside the challenges of scalability and equitable implementation. Additionally, neurodiversity- informed approaches are emphasized for their role in reframing autism as a natural variation of human cognition and behavior, advocating for strength-based, inclusive diagnostic frameworks. This synthesis underscores the interplay between evolving theoretical models, technological advancements, and the growing focus on compassionate, equitable diagnostic practices. It concludes by advocating for continued innovation, interdisciplinary collaboration, and ethical oversight to further refine ASD diagnostics and improve outcomes for individuals across the autism spectrum. Full article

Debugging is a growing topic in K-12 computer science (CS) education research. Although some previous studies have examined debugging behaviors, only a few have focused on an in-depth analysis of elementary students’ debugging behaviors in block-based programming environments. This qualitative study explored the debugging behaviors of four students, including their strategies and challenges. The study employed thematic video analysis of students’ computer screens as they engaged in block-based programming activities. The findings reveal five types of debugging strategies and three primary challenges during the debugging process. This study aims to help researchers and educators understand elementary students’ debugging strategies and the challenges they face. Suggestions for teaching debugging strategies to elementary students and the implications for future research are discussed. Full article

The precise real-time detection of polytetrafluoroethylene (PTFE) emulsion rotary vibration sieve levels is critical for improving production efficiency, ensuring product quality, and safeguarding personnel safety. This research presents a deep-learning-oriented video surveillance model for the intelligent level detection of vibrating screens, waste drums, and emulsion outlets, effectively addressing the limitations of traditional methods. With the introduction of TransResNet, which combines Vision Transformer (ViT) with ResNet, we can utilize the advantages of both approaches. ViT has excellent global information capture capability for processing image features, while ResNet excels in local feature extraction. The combined model effectively recognizes level changes in complex backgrounds, enhancing overall detection performance. During model training, synthetic data generation is used to alleviate the marker scarcity problem and generate synthetic images under different liquid level states to further enrich the training dataset, solve the issue of unequal data distribution, and enhance the model’s capacity to generalize. In order to validate the efficacy of our proposed model, we carried out a performance test with real-world data obtained from a material production site. The test results show that the model achieves 96%, 99%, and 99% accuracy at three test points, respectively: the vibrating screen, waste drum, and emulsion. These results not only prove the efficiency of the model but also highlight its significant value in practical applications. Full article

This study aims to assess and compare the shrinkage, accuracy, and accuracy stability of a novel 3D-printing model resin and eight commercially available 3D-printing model resin materials. The experimental model resin was developed by our 3D-printing proprietary resin technology. Eight commercially available 3D-printing model resins were included for comparison. The AcuVol video imaging technique was used to test volumetric shrinkage. Full-arch tooth models were printed for each model resin via digital light processing (DLP) technology. The 3D average distance between the scanned model and the designed CAD digital file was applied to determine the dimensional accuracy of the 3D-printed full-arch tooth models. One-way ANOVA and Tukey’s post hoc test (p < 0.05) were utilized to analyze the average values of volumetric shrinkage and 3D average distance (dimensional accuracy). The experimental model resin showed significantly lower volumetric shrinkage (7.28%) and significantly higher or higher accuracy and accuracy stability (11.66–13.77 µm from the initial day to four weeks) than the other commercially available model resins (7.66–11.2%, 14.03–41.14 µm from the initial day to four weeks). A strong correlation was observed between volumetric shrinkage and dimensional accuracy (Pearson correlation coefficient R = 0.7485). For clinically successful modelling applications in restorations, orthodontics, implants, and so on, the new 3D-printing model resin is a promising option. Full article

Remote photoplethysmography is a technology that estimates heart rate by detecting changes in blood volume induced by heartbeats and the resulting changes in skin color through imaging. This technique is fundamental for the noncontact acquisition of physiological signals from the human body. Despite the notable progress in remote-photoplethysmography algorithms for estimating heart rate from facial videos, challenges remain in accurately assessing heart rate during cardiovascular exercises such as treadmill or elliptical workouts. To address these issues, research has been conducted in various fields. For example, an understanding of optics can help solve these issues. Careful design of video production is also crucial. Approaches in computer vision and deep learning with neural networks can also be applied. We focused on developing a practical approach to improve heart rate estimation algorithms under constrained conditions. To address the limitations of motion blur during high-motion activities, we introduced a novel motion-based algorithm. While existing methods like CHROM, LGI, OMIT, and POS incorporate correction processes, they have shown limited success in environments with significant motion. By analyzing treadmill data, we identified a relationship between motion changes and heart rate. With an initial heart rate provided, our algorithm achieved over a 15 bpm improvement in mean absolute error and root mean squared error compared to existing methods, along with more than double the Pearson correlation. We hope this research contributes to advancements in healthcare and monitoring. Full article

Digital Holographic Microscopy (DHM) is a method of converting hologram images into three-dimensional (3D) images by image processing, which enables us to obtain the detailed shapes of the objects to be observed. Three-dimensional imaging of the microscopic objects by DHM can contribute to the early diagnosis and the detection of the diseases in the medical field by observing the shape of the cells. DHM requires several experimental components. One of them is the laser, which is a problem because its high power may cause the deformation and the destruction of the cells and the death of the microorganisms. Since the greatest advantage of DHM is the detailed geometrical information of the object by 3D measurement, the loss of such information is a serious problem. To solve this problem, a Neutral Density (ND) filter has been used to reduce power after the laser irradiation. However, the image acquired by the image sensor becomes too dark to obtain sufficient information, and the effect of noise increased due to the decrease in the amount of light. Therefore, in this paper, we propose the Frame-Stacking Method (FSM) for dark DHM for reproducing 3D profiles that enable us to observe the shape of the objects from the images taken in low-power environments when the power is reduced. The proposed method realizes highly accurate 3D profiles by the frame decomposition of the low-power videos into images and superimposing and rescaling the obtained low-power images. On the other hand, the continuous irradiation of the laser beam for a long period may destroy the shape of the cells and the death of the microorganisms. Therefore, we conducted experiments to investigate the relationship between the number of superimposed images corresponding to the irradiation time and the 3D profile, as well as the characteristics of the power and the 3D profile. Full article

In the context of evolving healthcare technologies, this study investigates the application of AI and machine learning in video-based health monitoring systems, focusing on the challenges and potential of implementing such systems in real-world scenarios, specifically for knowledge workers. The research underscores the criticality of addressing technological, ethical, and practical hurdles in deploying these systems outside controlled laboratory environments. Methodologically, the study spanned three months and employed advanced facial recognition technology embedded in participants’ computing devices to collect physiological metrics such as heart rate, blinking frequency, and emotional states, thereby contributing to a stress detection dataset. This approach ensured data privacy and aligns with ethical standards. The results reveal significant challenges in data collection and processing, including biases in video datasets, the need for high-resolution videos, and the complexities of maintaining data quality and consistency, with 42% (after adjustments) of data lost. In conclusion, this research emphasizes the necessity for rigorous, ethical, and technologically adapted methodologies to fully realize the benefits of these systems in diverse healthcare contexts. Full article

Metamorphism is a complex geologic process that is often poorly covered in introductory geology courses. This study explores the effectiveness of a video-based instructional intervention in improving student understanding of metamorphism and its relationship to plate tectonics. The intervention includes an innovative assessment procedure featuring embedded QR codes, allowing participants to complete pre- and post-tests seamlessly. Data were collected from 75 participants, with results showing modest to major improvements in conceptual understanding, particularly about geothermal gradients. However, minimal improvement was observed in questions requiring deeper knowledge of specific tectonic settings. A qualitative analysis of written responses revealed limited changes in participants’ use of key terms before and after the video intervention. These findings suggest that while video-based instruction can reinforce core concepts, greater attention is needed to address cognitive load and support learning of more challenging topics. This study underscores the importance of integrating accessible, dynamic teaching tools and refining instructional design to better engage students with metamorphic processes, which are essential to understanding Earth’s dynamic systems. Full article

Research Subject: The research subject was the error of optoelectronic video endoscopy systems in measuring the chord length of low-pressure cylinder steam turbine blades during shaft rotation. Objective: The objective was to reduce the error of the optoelectronic system in measuring the chord length of turbine rotor blades on a closed cylinder during shaft rotation. Methodology: Analytical research and computer modeling of the information transformation process during blade image formation and processing were carried out. Theoretical and experimental evaluations of the system error were conducted. Main Results: The structure of the components contributing to the error in estimating the chord length of low-pressure turbine blades was analyzed. The contribution of individual components to the total error was identified, and methods for reducing the most significant error components were proposed. Practical Significance: The effectiveness of the proposed methods for error reduction was validated through computer simulations and experimental studies on two system prototypes. The results showed that the standard deviation of the random error component in chord measurement during dynamic operation did not exceed 0.27 mm. Full article

Background: Embodied cognition is an emerging concept in cognitive science that emphasizes the integral role of perception, action, and bodily experience in shaping human thought and understanding. Recently, a new instrument has been developed called the Automated Test of Embodied Cognition (ATEC), which provides a comprehensive measure of eight domains of embodied cognition. Method: An embodied cognition in an alcohol use disorder (AUD) sample (N = 49) was assessed using ATEC, which employs cognitively demanding physical tasks, like an exercise video, to measure executive functions (EFs), memory, and other cognitive processes “in action”. Results: Embodied delayed recall was the most frequent impairment (84%), and EF impairments were also common. Among the EF domains, self-regulation was the most frequently impaired at 43%. Using the ATEC total score, 43% of the sample were rated as having a mild or greater level of overall impairment. Strong support for concurrent validity was found for ATEC EF and memory domains when correlated with neurocognitive assessments conceptually related to them. Significant categorical agreement (impaired/not impaired) was also found between neurocognitive testing and ATEC total score. Using the ATEC total score, younger age, higher education, and better premorbid IQ were found to be potential protective factors against cognitive decline. Conclusions: Findings support ATEC’s potential for future studies related to AUD and other disorders that may lead to cognitive decline. Embodied cognition may provide new insights into how AUD affects cognition and functioning and be useful to determine what interventions may improve recovery. Full article

Inverse synthetic aperture ladar (ISAL) systems combine laser coherent detection technology with inverse synthetic aperture imaging methods, offering advantages such as compact size, long detection range, and high resolution. The traditional optical delay line technique is widely used in frequency-modulated continuous wave (FMCW) ISAL imaging systems, but its flexibility is limited, posing challenges for high-precision signal processing. Additionally, frequency modulation errors, atmospheric disturbances, and other errors inevitably affect image quality. Therefore, this paper proposes a signal processing method based on digital delay for FMCW ISAL, aiming to achieve the high-resolution imaging of targets across several kilometers. Firstly, the paper introduces the FMCW ISAL system. By introducing digital delay technology, it enables the flexible and real-time adjustment of reference signal delay. Next, to address the frequency offset issue caused by the introduction of digital delay technology, a preprocessing method for unified frequency shift correction is proposed to ensure signal consistency. Then, a set of internal calibration signal datasets is generated based on digital delay technology. Following this, a frequency modulation error iteration estimation method based on gradient descent is introduced. Without the need for target echo signals, the method accurately estimates the frequency modulation phase errors of both the transmitted and reference signals using only the internal calibration signals. Finally, this paper effectively decomposes the motion of the target, derives the echo model for the FMCW ISAL system, and constructs compensation functions to eliminate the intra-pulse Doppler shift and the residual video phase (RVP). Additionally, the Phase Gradient Autofocus (PGA) algorithm is used after two-dimensional imaging to eliminate the impact of atmospheric disturbances. We conducted two sets of experiments on point targets and surface targets to verify the effectiveness of error compensation in improving imaging quality. The results show that the two-dimensional resolution of point targets was optimized to 3 cm (range) × 0.6 cm (azimuth), while the resolution and entropy of the surface targets were both improved by 0.1. These results demonstrate that the proposed method effectively enhances target imaging quality and provides a new technical approach for high-precision signal processing in FMCW ISAL imaging. Full article

Computer vision-based state recognition is widely employed in substations, but conventional video monitoring systems often encounter challenges during emergency situations, such as smoke from fires. In such scenarios, LiDAR emerges as an appealing alternative, capable of capturing the depth information of the target. However, when smoke concentration is high, the quality of collected point cloud data deteriorates, impacting the assessment of the disconnector open–close status. This paper delves into the impact of a smoky environment on point cloud data and introduces a two-stage discrimination process. Firstly, a feature extraction method using sliced point clouds is employed to construct edge features of the conductive arm. Building upon this foundation, an open–close position identification method based on edge pre-processing is employed to obtain the final measurement results. Field experiments demonstrate that the proposed method effectively mitigates smoke interference and accurately determines the disconnector’s open–close status with high reliability and precision. This approach could serve as a reference for the development of continuous disconnector closing state monitoring technology. Full article