19200 research outputs found
Sort by
A fog-edge-enabled intrusion detection system for smart grids
No full textThe Smart Grid (SG) heavily depends on the Advanced Metering Infrastructure (AMI) technology, which has shown its vulnerability to intrusions. To effectively monitor and raise alarms in response to anomalous activities, the Intrusion Detection System (IDS) plays a crucial role. However, existing intrusion detection models are typically trained on cloud servers, which exposes user data to significant privacy risks and extends the time required for intrusion detection. Training a high-quality IDS using Artificial Intelligence (AI) technologies on a single entity becomes particularly challenging when dealing with vast amounts of distributed data across the network. To address these concerns, this paper presents a novel approach: a fog-edge-enabled Support Vector Machine (SVM)-based federated learning (FL) IDS for SGs. FL is an AI technique for training Edge devices. In this system, only learning parameters are shared with the global model, ensuring the utmost data privacy while enabling collaborative learning to develop a high-quality IDS model. The test and validation results obtained from this proposed model demonstrate its superiority over existing methods, achieving an impressive percentage improvement of 4.17% accuracy, 13.19% recall, 9.63% precision, 13.19% F1 score when evaluated using the NSL-KDD dataset. Furthermore, the model performed exceptionally well on the CICIDS2017 dataset, with improved accuracy, precision, recall, and F1 scores reaching 6.03%, 6.03%, 7.57%, and 7.08%, respectively. This novel approach enhances intrusion detection accuracy and safeguards user data and privacy in SG systems, making it a significant advancement in the field
Fabric Defect Detection in Real World Manufacturing Using Deep Learning
No full textDefect detection is very important for guaranteeing the quality and pricing of fabric. A considerable amount of fabric is discarded as waste because of defects, leading to substantial annual losses. While manual inspection has traditionally been the norm for detection, adopting an automatic defect detection scheme based on a deep learning model offers a timely and efficient solution for assessing fabric quality. In real-time manufacturing scenarios, datasets lack high-quality, precisely positioned images. Moreover, both plain and printed fabrics are being manufactured in industries simultaneously; therefore, a single model should be capable of detecting defects in all kinds of fabric. So training a robust deep learning model that detects defects in fabric datasets generated during production with high accuracy and lower computational costs is required. This study uses an indigenous dataset directly sourced from Chenab Textiles, providing authentic and diverse images representative of actual manufacturing conditions. The dataset is used to train a computationally faster but lighter state-of-the-art network, i.e., YOLOv8. For comparison, YOLOv5 and MobileNetV2-SSD FPN-Lite models are also trained on the same dataset. YOLOv8n achieved the highest performance, with a mAP of 84.8%, precision of 0.818, and recall of 0.839 across seven different defect classes
A new approach to mathematical and data education:A new approach to mathematical and data education that better prepares all young people for their futures, whether for jobs or to play active roles in wider society.
Get PDFMathematics, data and statistics are ever-present and increasingly influence our daily lives, whether as employees, citizens or consumers. They support decision-making by governments, guide industry and business, and feature prominently in research and innovation in all sectors. We must therefore ensure that all young people learn how to engage confidently with a data and digitally rich world
The repeatability of a cycling exercise-heat stress test in a male population
Get PDFINTRODUCTION: There is considerable inter-individual variability in the physiological responses to environmental stressors and so to accurately assess and monitor changes in an individual's ability to cope with exercise-heat stress, a reliable protocol is required. The aim of this study was to examine the repeatability of a 90-min steady-state heat exercise bout with physiological and subjective variables, and performance during an incremental test to exhaustion post 90-min steady-state exercise.METHOD: Sixteen mixed ability males (Age: 39 ± 15yrs; Height: 176.5 ± 4.8 cm; BM: 79.7 ± 10.3 kg; V˙O 2peak: 46.2 ± 8.6 ml/kg/min; PPO: 309 ± 39W) who trained at least three times a week undertook two 90-min steady-state - followed by an incremental protocol to exhaustion - cycling heat stress tests (HSTs) in a hot-humid environment (35 °C, 60%RH). Heart rate (HR), rectal (T‾r e) and skin temperature (T‾ sk), rating of perceived exertion (RPE), thermal sensation (TS), and thermal comfort (TC) were measured throughout. Data was analysed using Intraclass Correlation Coefficients (ICC), technical error of measurement (TEM), Bland-Altman plots, t-tests, and Cohen's d to indicate magnitude of change. RESULTS: Physiological variables indicated good repeatability evident through moderate to strong ICC ratings, low magnitudes of change (d), lower mean biases compared to their respective calculated TEMs, and statistical non-significance, except HR90, ₸ sk90, and ₸ sk. Hydration status showed good repeatability except for urine osmolality (osm u90) and resting urine colour (col u). Perceptual variables showed encouraging repeatability apart from resting TS and mean TS. Performance data showed good repeatability overall, however 11 participants progressed to the incremental test to exhaustion in the second visit compared to 7 in the first. CONCLUSION: Current data demonstrated favourable physiological, perceptual, and performance repeatability during repeated cycling HSTs in hot-humid conditions. However, given more participants progressed to the incremental trial to exhaustion protocol in the second visit, at least one familiarisation trial may improve the reliability of exercise capacity assessment.</p
A Comparative Investigation of Transfer Learning Frameworks Using OCT Pictures for Retinal Disorder Identification
No full text
A comprehensive toxicological analysis of panel of unregulated e-cigarettes to human health
No full textElectronic cigarettes, commonly referred to as e-cigarettes have gained popularity over recent years especially among young individuals. In the light of the escalating prevalence of the use of these products and their potential for long-term health effects, in this study as the first of its kind a comprehensive toxicological profiling of the liquid from a panel of unregulated e-cigarettes seized in the UK was undertaken using an in vitro co-culture model of the upper airways. The data showed that e-cigarettes caused a dose dependent increase in cell death and inflammation manifested by enhanced release of IL1ß and IL6. Furthermore, the e-cigarettes induced oxidative stress as demonstrated by a reduction of intracellular glutathione and an increase in generation of reactive oxygen species. Moreover, the assessment of genotoxicity showed significant DNA strand breaks (following exposure to Tigerblood flavoured e-cigarette). Moreover, relevant to the toxicological observations, was the detection of varying and
Developing guidelines on EFT for same-sex/gender relationships: Recommendations from a Delphi study
Get PDFEmotionally focused therapy (EFT) is one of few empirically supported treatments for relationship distress. While evidence-based approaches are critical for ensuring safe and effective treatment, EFT has not been adapted for use with same-sex/same-gender (SS/SG) relationships. This study used the Delphi method to generate consensus on treatment guidelines for using EFT with SS/SG relationships. Forty therapists with clinical expertise in EFT for SS/SG relationships were recruited. Data were collected in three phases. In phase one, participants responded to open-ended questions regarding how EFT should be adapted for SS/SG relationships. Phases two and three involved participants rating the importance of the recommended guidelines. Data were analyzed using thematic analysis and descriptive statistics. The final recommendations included 49 guidelines on EFT for SS/SG relationships. The data reflected modifications to therapists' foundational knowledge and development, practice set up and orientation, and the three stages and nine steps of EFT
