Search Results (7)

Modern cybersecurity threats continue to evolve in both complexity and prevalence, demanding advanced solutions for intrusion detection. Traditional AI-based detection systems face significant challenges in model selection, as performance varies considerably across different network environments and attack scenarios. To overcome these limitations, we propose a comprehensive ensemble learning approach that systematically integrates feature selection, model optimization, and rigorous evaluation components. Our framework evaluates fourteen distinct machine learning approaches, ranging from individual classifiers to sophisticated ensemble methods including bagging, boosting, and hybrid stacking/blending architectures. These techniques are applied to multiple base algorithms such as neural networks and tree-based models. Extensive testing was conducted on two complementary benchmark datasets (RoEduNet-SIMARGL2021 and CICIDS-2017) to assess detection capabilities across varied threat landscapes. Our experimental results revealed several key findings. Ensemble techniques universally surpass standalone models in detection accuracy, with random forest achieving the best performance on RoEduNet-SIMARGL2021, while the blending and bagging methods approach yielded perfect scores (F1 > 0.996) on CICIDS-2017. Feature selection via information gain demonstrated particular value, reducing model training times by 94% while maintaining detection accuracy. Among ensemble methods, XGBoost showed exceptional computational efficiency, whereas stacking and blending architectures delivered maximum accuracy at the expense of greater resource requirements. This research provides practical guidance for security professionals in model selection based on specific operational constraints and threat profiles. To support community advancement, we have made our complete framework publicly available, facilitating reproducibility and future innovation in intrusion detection systems. Full article

This study investigates the integration of biologically inspired noise injection with a time-distributed adaptation of the AlexNet architecture to enhance the performance and robustness of human activity recognition (HAR) systems. It is a critical field in computer vision which involves identifying and interpreting human actions from video sequences and has applications in healthcare, security and smart environments. The proposed model is based on an adaptation of AlexNet, originally developed for static image classification and not inherently suited for modelling temporal sequences for video action classification tasks. While our time-distributed AlexNet efficiently captures spatial and temporal features and suitable for video classification. However, its performance can be limited by overfitting and poor generalisation to unseen scenarios, to address these challenges, Gaussian noise was introduced at the input level during training, inspired by neural mechanisms observed in biological sensory processing to handle variability and uncertainty. Experiments were conducted on the EduNet, UCF50 and UCF101 datasets. The EduNet dataset was specifically designed for educational environments and we evaluate the impact of noise injection on model accuracy, stability and overall performance. The proposed bio-inspired noise-injected time-distributed AlexNet achieved an overall accuracy of 91.40% and an F1 score of 92.77%, outperforming other state-of-the-art models. Hyperparameter tuning, particularly optimising the learning rate, further enhanced model stability, reflected in lower standard deviation values across multiple experimental runs. These findings demonstrate that the strategic combination of noise injection with time-distributed architectures improves generalisation and robustness in HAR, paving the way for resource-efficient and real-world-deployable deep learning systems. Full article

New technology has made it possible to monitor and analyze the condition of ice-covered transmission lines based on images. However, the collected images are frequently accompanied by noise, which results in inaccurate monitoring. Therefore, this paper proposes an enhanced denoising Unet++ for ice-covered transmission line images (EDUNet++). This algorithm mainly comprises three modules: a feature encoding and decoding module (FEADM), a shared source feature fusion module (SSFFM), and an error correction module (ECM). In the FEADM, a residual attention module (RAM) and a multilevel feature attention module (MFAM) are proposed. The RAM incorporates the cascaded residual structure and hybrid attention mechanism, that effectively preserve the mapping of feature information. The MFAM uses dilated convolution to obtain features at different levels, and then uses feature attention for weighting. This module effectively combines local and global features, which can better capture the details and texture information in the image. In the SSFFM, the source features are fused to preserve low-frequency information like texture and edges in the image, hence enhancing the realism and clarity of the image. The ECM utilizes the discrepancy between the generated image and the original image to effectively capture all the potential information in the image, hence enhancing the realism of the generated image. We employ a novel piecewise joint loss. On the dataset of ice-covered transmission lines, PSNR (peak signal to noise ratio) and SSIM (structural similarity) achieved values of 29.765 dB and 0.968, respectively. Additionally, the visual effects exhibited more distinct detailed features. The proposed method exhibits superior noise suppression capabilities and robustness compared to alternative approaches. Full article

The video camera is essential for reliable activity monitoring, and a robust analysis helps in efficient interpretation. The systematic assessment of classroom activity through videos can help understand engagement levels from the perspective of both students and teachers. This practice can also help in robot-assistive classroom monitoring in the context of human–robot interaction. Therefore, we propose a novel algorithm for student–teacher activity recognition using 3D CNN (STAR-3D). The experiment is carried out using India’s indigenously developed supercomputer PARAM Shivay by the Centre for Development of Advanced Computing (C-DAC), Pune, India, under the National Supercomputing Mission (NSM), with a peak performance of 837 TeraFlops. The EduNet dataset (registered under the trademark of the DRSTA^TM dataset), a self-developed video dataset for classroom activities with 20 action classes, is used to train the model. Due to the unavailability of similar datasets containing both students’ and teachers’ actions, training, testing, and validation are only carried out on the EduNet dataset with 83.5% accuracy. To the best of our knowledge, this is the first attempt to develop an end-to-end algorithm that recognises both the students’ and teachers’ activities in the classroom environment, and it mainly focuses on school levels (K-12). In addition, a comparison with other approaches in the same domain shows our work’s novelty. This novel algorithm will also influence the researcher in exploring research on the “Convergence of High-Performance Computing and Artificial Intelligence”. We also present future research directions to integrate the STAR-3D algorithm with robots for classroom monitoring. Full article

The COVID-19 pandemic has sped up the acceptance of online education as a substitute for conventional classroom instruction. E-Learning emerged as an instant solution to avoid academic loss for students. As a result, educators and academics are becoming more and more interested in comprehending how students behave in e-learning settings. Behavior analysis of students in an e-learning environment can provide vision and influential factors that can improve learning outcomes and guide the creation of efficient interventions. The main objective of this work is to provide a system that analyzes the behavior and actions of students during e-learning which can help instructors to identify and track student attention levels so that they can design their content accordingly. This study has presented a fresh method for examining student behavior. Viola–Jones was used to recognize the student using the object’s movement factor, and a region-shrinking technique was used to isolate occluded items. Each object has been checked by a human using a template-matching approach, and for each object that has been confirmed, features are computed at the skeleton and silhouette levels. A genetic algorithm was used to categorize the behavior. Using this system, instructors can spot kids who might be failing or uninterested in learning and offer them specific interventions to enhance their learning environment. The average attained accuracy for the MED and Edu-Net datasets are 90.5% and 85.7%, respectively. These results are more accurate when compared to other methods currently in use. Full article

Human action recognition in videos has become a popular research area in artificial intelligence (AI) technology. In the past few years, this research has accelerated in areas such as sports, daily activities, kitchen activities, etc., due to developments in the benchmarks proposed for human action recognition datasets in these areas. However, there is little research in the benchmarking datasets for human activity recognition in educational environments. Therefore, we developed a dataset of teacher and student activities to expand the research in the education domain. This paper proposes a new dataset, called EduNet, for a novel approach towards developing human action recognition datasets in classroom environments. EduNet has 20 action classes, containing around 7851 manually annotated clips extracted from YouTube videos, and recorded in an actual classroom environment. Each action category has a minimum of 200 clips, and the total duration is approximately 12 h. To the best of our knowledge, EduNet is the first dataset specially prepared for classroom monitoring for both teacher and student activities. It is also a challenging dataset of actions as it has many clips (and due to the unconstrained nature of the clips). We compared the performance of the EduNet dataset with benchmark video datasets UCF101 and HMDB51 on a standard I3D-ResNet-50 model, which resulted in 72.3% accuracy. The development of a new benchmark dataset for the education domain will benefit future research concerning classroom monitoring systems. The EduNet dataset is a collection of classroom activities from 1 to 12 standard schools. Full article

Cybersecurity is an arms race, with both the security and the adversaries attempting to outsmart one another, coming up with new attacks, new ways to defend against those attacks, and again with new ways to circumvent those defences. This situation creates a constant need for novel, realistic cybersecurity datasets. This paper introduces the effects of using machine-learning-based intrusion detection methods in network traffic coming from a real-life architecture. The main contribution of this work is a dataset coming from a real-world, academic network. Real-life traffic was collected and, after performing a series of attacks, a dataset was assembled. The dataset contains 44 network features and an unbalanced distribution of classes. In this work, the capability of the dataset for formulating machine-learning-based models was experimentally evaluated. To investigate the stability of the obtained models, cross-validation was performed, and an array of detection metrics were reported. The gathered dataset is part of an effort to bring security against novel cyberthreats and was completed in the SIMARGL project. Full article