Search Results (1,116)

Inspired by the human ability to learn continuously and adapt to changing environments, researchers have proposed Online Open-World Object Detection (OLOWOD). This emerging paradigm faces the challenges of detecting known categories, discovering unknown ones, continuously learning new categories, and mitigating catastrophic forgetting. To address these challenges, we propose Category Prototype-guided Streaming Multi-Level Perturbation, PSMP, a plug-and-play method for OLOWOD. PSMP, comprising semantic-level, enhanced data-level, and enhanced feature-level perturbations jointly guided by category prototypes, operates at different representational levels to collaboratively extract latent knowledge across tasks and improve adaptability. In addition, PSMP constructs the “contrastive tension” based on the relationships among category prototypes. This mechanism inherently leverages the symmetric structure formed by class prototypes in the latent space, where prototypes of semantically similar categories tend to align symmetrically or equidistantly. By guiding perturbations along these symmetric axes, the model can achieve more balanced generalization between known and unknown categories. PSMP requires no additional annotations, is lightweight in design, and can be seamlessly integrated into existing OWOD methods. Extensive experiments show that PSMP achieves an improvement of approximately 1.5% to 3% in mAP for known categories compared to conventional online training methods while significantly increasing the Unknown Recall (UR) by around 4.6%. Full article

Automated movement intention is crucial for brain–computer interface (BCI) applications. The automatic identification of movement intention can assist patients with movement problems in regaining their mobility. This study introduces a novel approach for the automatic identification of movement intention through finger tapping. This work has compiled a database of EEG signals derived from left finger taps, right finger taps, and a resting condition. Following the requisite pre-processing, the captured signals are input into the proposed model, which is constructed based on graph theory and deep convolutional networks. In this study, we introduce a novel architecture based on six deep convolutional graph layers, specifically designed to effectively capture and extract essential features from EEG signals. The proposed model demonstrates a remarkable performance, achieving an accuracy of 98% in a binary classification task when distinguishing between left and right finger tapping. Furthermore, in a more complex three-class classification scenario, which includes left finger tapping, right finger tapping, and an additional class, the model attains an accuracy of 92%. These results highlight the effectiveness of the architecture in decoding motor-related brain activity from EEG data. Furthermore, relative to recent studies, the suggested model exhibits significant resilience in noisy situations, making it suitable for online BCI applications. Full article

As an example of pedagogical approaches that blend online and face-to-face instruction, the flipped classroom model has seen exponential growth in business schools. To explore its effectiveness, expectancy-value theory and cognitive load theory were employed to develop a framework linking students’ perceived usefulness of the online and in-person content to their pre-class preparation, class participation, perceived learning, and skills development. A preliminary test of this framework was conducted using a flipped Organizational Behavior course within a business diploma program at a publicly funded Canadian college. The perceived usefulness of the online component was positively associated with students’ pre-class preparation, which, in turn, was positively related to both their perceived learning and skills development. Implications for practice and directions for future research are discussed. Full article

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

Internal crack defects in high-strength low-alloy (HSLA) steels during continuous casting pose significant challenges to downstream processing and product reliability. However, due to the inherent class imbalance in industrial defect datasets, conventional machine learning models often suffer from poor sensitivity to minority class instances. This study proposes a predictive framework that integrates conditional tabular generative adversarial network (CTGAN) for synthetic minority sample generation and CatBoost for classification. A dataset of 733 process records was collected from a continuous caster, and 25 informative features were selected using mutual information. CTGAN was employed to augment the minority class (crack) samples, achieving a balanced training set. Feature distribution analysis and principal component visualization indicated that the synthetic data effectively preserved the statistical structure of the original minority class. Compared with the other machine learning methods, including KNN, SVM, and MLP, CatBoost achieved the highest metrics, with an accuracy of 0.9239, precision of 0.9041, recall of 0.9018, and F1-score of 0.9022. Results show that CTGAN-based augmentation improves classification performance across all models. These findings highlight the effectiveness of GAN-based augmentation for imbalanced industrial data and validate the CTGAN–CatBoost model as a robust solution for online defect prediction in steel manufacturing. Full article

The contemporary digital era has fundamentally reshaped pupil education. It has transformed learning into a dynamic environment with enhanced access to information. The focus shifts to the educator, who must employ teaching strategies, practices, and methods to engage and motivate the pupils. New possibilities are emerging for adopting active pedagogical approaches. One example is the use of educational online escape games. In the theoretical part of this paper, we present online escape games as a tool that broadens pedagogical opportunities for schools in primary school chemistry education. These activities are known to foster pupils’ transversal or soft skills. We investigate the practical dimension of implementing escape games in education. This pilot study aims to analyse primary school teachers’ perceptions of online escape games. We collected data using Q methodology and conducted the Q-sort through digital technology. Data analysis utilised both the PQMethod programme and ChatGPT 4-o, with a subsequent comparison of their respective outputs. Although some numerical differences appeared between the ChatGPT and PQMethod analyses, both methods yielded the same factor saturation and overall results. Full article

In an era where online interactions increasingly shape social dynamics, the pervasive issue of cyberbullying poses a significant threat to the well-being of individuals, particularly among vulnerable groups. Despite extensive research on text-based cyberbullying detection, the rise of visual content on social media platforms necessitates new approaches to address cyberbullying using images. This domain has been largely overlooked. In this paper, we present a novel dataset specifically designed for the detection of visual cyberbullying, encompassing four distinct classes: abuse, curse, discourage, and threat. The initial prepared dataset (cyberbullying visual indicators dataset (CVID)) comprised 664 samples for training and validation, expanded through data augmentation techniques to ensure balanced and accurate results across all classes. We analyzed this dataset using several advanced deep learning models, including VGG16, VGG19, MobileNetV2, and Vision Transformer. The proposed model, based on DenseNet201, achieved the highest test accuracy of 99%, demonstrating its efficacy in identifying the visual cues associated with cyberbullying. To prove the proposed model’s generalizability, the 5-fold stratified K-fold was also considered, and the model achieved an average test accuracy of 99%. This work introduces a dataset and highlights the potential of leveraging deep learning models to address the multifaceted challenges of detecting cyberbullying in visual content. Full article

In vitro meat presents a promising alternative to conventional meat production by addressing environmental and animal welfare concerns. However, broader market adoption depends on increasing consumer acceptance. Labels on product packaging have been shown to be effective in influencing consumer behavior in previous studies. This paper examines the impact of different front-of-package labels on German consumers’ choices regarding in vitro chicken meat, with the goal of identifying effective labeling strategies. To investigate this, an online choice experiment was conducted with 200 participants from Germany. In addition to the label, products varied in terms of price, origin, and calorie content. The data were analyzed using latent class analysis, which identified four distinct consumer segments characterized by their preferences, attitudes, and personal characteristics. The results were used to simulate market scenarios, evaluating the effectiveness of different labeling strategies for in vitro chicken meat. These insights provide a foundation for targeted marketing approaches that promote consumer acceptance and inform the introduction of in vitro meat products in Germany. Full article

Background/Objectives: This study aimed to determine whether the movement patterns and mental health of university teachers changed after returning to on-site class activities following the COVID-19 lockdown. Specifically, it compared levels of physical activity (PA), sedentary behavior time (SBT), active breaks (ABs), and symptoms of depression, anxiety, and stress among university teachers during online and on-site teaching periods. We also analyzed the association between movement patterns with psychological and anthropometric variables. Methods: University teachers who engaged in online teaching activities because of the COVID-19 restrictions and returned to on-site classes were included. Each teacher wore an accelerometer and answered the Depression Anxiety Stress Scales. The following parameters were assessed: SBT, light (LPA), moderate (MPA), and vigorous (VPA) (min/day); moderate–vigorous PA (MVPA) (min/week); steps/day and ABs/day. Results: Thirty-seven teachers with complete data from both phases were included. Once the on-site teaching activities resumed, LPA (9 min/day), MPA (6 min/day), total PA (20 min/day), MVPA (49 min/week), and steps/day (1100) significantly increased. While SBT showed no changes, ABs/day bouts increased. Depression and stress symptoms improved upon returning to on-site teaching activities. A positive association was identified between SBT and waist circumference (WC). There were negative associations between steps/day and MVPA with body mass index (BMI), steps/day with WC, and LPA with stress symptoms. Conclusions: Upon returning to on-site teaching activities, PA levels, steps/day, and ABs/day bouts all increased, although SBT remained elevated compared with during the lockdown. The teachers’ psychological symptoms improved. PA was associated with better health markers, while SBT was associated with increased WC. Full article

As part of the post-conflict reconstruction and recovery, the development of Kabul New City aims to bring relief to the existing capital city, Kabul, which has experienced exponential population growth, putting heavy pressure on its existing resources. Kabul New City is divided into four subsectors, and each of them is being developed and is expected to reach a target population by 2025, as defined by the master plan. The study’s objective is to determine which of the four zones are in demand and need to be prioritized for development, as per the model results. The data collection involves an online questionnaire, and the responses are collected from residents of Kabul and Herat. Agent-based modeling (ABM) is an emerging method of simulating urban dynamics. Cities are evolving continuously and are forming unique spatial patterns that result from the movement of residents in search of new locations that accommodate their needs and preferences. An agent-based model is developed using the weighted random selection process based on household size and income levels. The agents are the residents of Kabul and Herat, and the environment is the land use classification image using the Sentinel 2 image of Kabul New City. The barren class is treated as the developable area and is divided into four sub-sectors. The model simulates three alternative growth rate scenarios, i.e., ambitious, moderate, and steady. The results of the simulation reveal that the sub-sector Dehsabz South, being closer to Kabul city, is in higher demand. Barikab is another sub-sector high in demand, which has connectivity through the highway and is an upcoming industrial hub. Full article

Emerging digital technologies are transforming how consumers participate in financial markets, yet their benefits depend critically on the speed, reliability, and transparency of the underlying platforms. Online stock trading platforms must maintain high efficiency underload to ensure a good user experience. This paper presents performance analysis under various load conditions based on the containerized stock exchange system. A comprehensive data logging pipeline was implemented, capturing metrics such as API response times, database query times, and resource utilization. We analyze the collected data to identify performance patterns, using both statistical analysis and machine learning techniques. Preliminary analysis reveals correlations between application processing time and database load, as well as the impact of user behavior on system performance. Association rule mining is applied to uncover relationships among performance metrics, and multiple classification algorithms are evaluated for their ability to predict user activity class patterns from system metrics. The insights from this work can guide optimizations in similar distributed web applications to improve scalability and reliability under a heavy load. By framing performance not merely as a technical property but as a determinant of financial decision-making and well-being, the study contributes actionable insights for designers of consumer-facing fintech services seeking to meet sustainable development goals through trustworthy, resilient digital infrastructure. Full article

Sentiment analysis is a sub-field within Natural Language Processing (NLP), concentrating on the extraction and interpretation of user sentiments or opinions from textual data. Despite significant advancements in the analysis of online content, a continuing challenge persists in the handling of sentiment datasets that are high-dimensional and frequently include substantial amounts of irrelevant or redundant features. Existing methods to address this issue typically rely on dimensionality reduction techniques; however, their effectiveness in removing irrelevant features and managing noisy or redundant data has been inconsistent. This research seeks to overcome these challenges by introducing an innovative methodology that integrates ensemble feature selection techniques based on information gain with feature hashing. Our proposed approach aims to enhance the conventional feature selection process by synergistically combining these two strategies to more effectively tackle the issues of irrelevant features, noisy classes, and redundant data. The novel integration of information gain with feature hashing facilitates a more precise and strategic feature selection process, resulting in improved efficiency and effectiveness in sentiment analysis tasks. Through comprehensive experimentation and evaluation, we demonstrate that our proposed method significantly outperforms baseline approaches and existing techniques across a wide range of scenarios. The results indicate that our method offers substantial advancements in managing high-dimensional sentiment data, thereby contributing to more accurate and reliable sentiment analysis outcomes. Full article

Precise grading of manufactured sand is vital to concrete performance, yet standard sieve tests, though accurate, are too slow for online quality control. Thus, we devised an image-based inspection method combining a dual-camera module with a Temporal Interval Sampling Strategy (TISS) to enhance throughput while maintaining precision. In this design, a global wide-angle camera captures the entire particle field, whereas a local high-magnification camera focuses on fine fractions. TISS selects only statistically representative frames, effectively eliminating redundant data. A lightweight segmentation algorithm based on geometric rules cleanly separates overlapping particles and assigns size classes using a normal-distribution classifier. In tests on ten 500 g batches of manufactured sand spanning fine, medium, and coarse gradations, the system processed each batch in an average of 7.8 min using only 34 image groups. It kept the total gradation error within 12% and the fineness-modulus deviation within ±0.06 compared to reference sieving. These results demonstrate that the combination of complementary optics and targeted sampling can provide a scalable, real-time solution. Full article

Online learning has become increasingly prevalent in real-world applications, where data streams often comprise heterogeneous feature types—both nominal and numerical—and labels may not arrive synchronously with features. However, most existing online learning methods assume homogeneous data types and synchronous arrival of features and labels. In practice, data streams are typically heterogeneous and exhibit asynchronous label feedback, making these methods insufficient. To address these challenges, we propose a novel algorithm, termed Online Asynchronous Learning over Streaming Nominal Data (OALN), which maps heterogeneous data into a continuous latent space and leverages a model pool alongside a hint mechanism to effectively manage asynchronous labels. Specifically, OALN is grounded in three core principles: (1) It utilizes a Gaussian mixture copula in the latent space to preserve class structure and numerical relationships, thereby addressing the encoding and relational learning challenges posed by mixed feature types. (2) It performs adaptive imputation through conditional covariance matrices to seamlessly handle random missing values and feature drift, while incrementally updating copula parameters to accommodate dynamic changes in the feature space. (3) It incorporates a model pool and hint mechanism to efficiently process asynchronous label feedback. We evaluate OALN on twelve real-world datasets; the average cumulative error rates are 23.31% and 28.28% under the missing rates of 10% and 50%, respectively, and the average AUC scores are 0.7895 and 0.7433, which are the best results among the compared algorithms. And both theoretical analyses and extensive empirical studies confirm the effectiveness of the proposed method. Full article

Objectives: The increasing reliance on online platforms for dental education necessitates an assessment of the quality and reliability of available resources. This study aimed to evaluate YouTube videos as educational tools for Class IV resin composite restorations. Methods: The first 100 YouTube videos were screened, and 73 met the inclusion criteria. The videos were evaluated using the Video Information and Quality Index (VIQI) and specific content criteria derived from the dental literature. Videos with a score below the mean were identified as low-content videos. Results: No significant differences were noted between high- and low-content videos when examining the number of views, number of likes, duration, days since upload, viewing rate, interaction index, and number of subscribers (p > 0.05). The high-content videos demonstrated higher mean values compared with the low-content videos in flow (4.11 vs. 3.21; p < 0.0001), accuracy (4.07 vs. 3.07; p < 0.0001), quality (4 vs. 2.66; p < 0.0001), and precision (4.16 vs. 2.86; p < 0.0001). The overall VIQI score was significantly higher (p < 0.0001) for high-content videos (Mean 16.34; SD 2.46) compared with low-content videos (Mean 11.79; SD 2.96). For content score, high-content videos (Mean 9.36; SD 1.33) had a higher score (p < 0.0001) than low-content videos (Mean 4.90; SD 2.04). The key areas lacking sufficient coverage included occlusion, shade selection, and light curing techniques. Conclusions: While a significant portion of YouTube videos provided high-quality educational content, notable deficiencies were identified. This analysis serves as a call to action for both content creators and educational institutions to prioritize the accuracy and completeness of online dental education. Full article