26729 research outputs found
Sort by
PIGNUS: a deep learning model for IDS in industrial internet-of-things
Get PDFThe heterogeneous nature of the Industrial Internet of Thing (IIoT) has a considerable impact on the development of an effective Intrusion Detection System (IDS). The proliferation of linked devices results in multiple inputs from industrial sensors. IDS faces challenges in analyzing the features of the traffic and identifying anonymous behavior. Due to the unavailability of a comprehensive feature mapping method, the present IDS solutions are non-usable to identify zero-day vulnerabilities.
In this paper, we introduce the first comprehensive IDS framework that combines an efficient feature-mapping technique and cascading model to solve the above-mentioned problems. We call our proposed solution deeP learnIG model intrusioN detection in indUStrial internet-of things (PIGNUS). PIGNUS integrates Auto Encoders (AE) to select optimal features and Cascade Forward Back Propagation Neural Network (CFBPNN) for classification and attack detection. The cascading model uses interconnected links from the initial layer to the output layer and determines the normal and abnormal behavior patterns and produces a perfect classification. We execute a set of experiments on five popular IIoT datasets: gas pipeline, water storage tank, NSLKDD+, UNSW-NB15, and X-IIoTID. We compare PIGNUS to the state-of-the-art models in terms of accuracy, False Positive Ratio (FPR), precision, and recall. The results show that PIGNUS provides more than accuracy, which is better on average than the existing models. In the other parameters, PIGNUS shows improved FPR, better recall, and better in precision. Overall, PIGNUS proves its efficiency as an IDS solution for IIoTs. Thus, PIGNUS is an efficient solution for IIoTs
Ageing perspective on cognitive outcomes from ancillary reproductive hormone adjustments
Get PDFIn addition to primary reproductive functions, gonadal hormones play an important role in regulating neural mechanisms across the human lifespan. The ageing-related decline in their activity has been linked to cognitive impairments in otherwise healthy women, contributing to higher incidents of post-menopause dementia. Given the growing utility of gonadal steroids for birth control, as well as for compensatory treatment of menopause and oophorectomy symptoms, and adjuvant transgender therapy, their long-term effects on neural mechanisms warrant comprehensive assessment. In this article, we present an ageing perspective on the cognitive outcomes of contraceptive and ancillary medical use of gonadal hormones and discuss their effects on the risk of cognitive impairments and late-life dementia. Despite rising data supporting the ameliorative effects of reproductive hormones on cognitive facilities, their impact varies depending on study design and type of intervention, implying dynamic neuro-endocrine interactions with complex compensatory mechanisms. Elucidating differential effects of reproductive hormone adjustments on cognition is expected not only to shed light on important aspects of brain ageing and dementia but to facilitate their use in personalized medicine with better safety and therapeutic outcomes
Virtual risk management—exploring effects of childhood risk experiences through innovative methods (ViRMa) for primary school children in Norway: study protocol for the ViRMa project
Get PDFBackground:
Research indicates that risky play benefits children’s risk assessment and risk management skills and offers several positive health effects such as resilience, social skills, physical activity, well-being, and involvement. There are also indications that the lack of risky play and autonomy increases the likelihood of anxiety. Despite its well-documented importance, and the willingness of children to engage in risky play, this type of play is increasingly restricted. Assessing long-term effects of risky play has been problematic because of ethical issues with conducting studies designed to allow or encourage children to take physical risks with the potential of injury.
Objective:
The Virtual Risk Management project aims to examine children’s development of risk management skills through risky play. To accomplish this, the project aims to use and validate newly developed and ethically appropriate data collection tools such as virtual reality, eye tracking, and motion capturing, and to provide insight into how children assess and handle risk situations and how children’s past risky play experiences are associated with their risk management.
Methods:
We will recruit 500 children aged 7-10 years and their parents from primary schools in Norway. Children’s risk management will be measured through data concerning their risk assessment, risk willingness, and risk handling when completing a number of tasks in 3 categories of virtual reality scenarios: street crossing, river crossing, and playing on playground equipment. The children will move around physically in a large space while conducting the tasks and wear 17 motion-capturing sensors that will measure their movements to analyze motor skills. We will also collect data on children’s perceived motor competence and their sensation-seeking personality. To obtain data on children’s risk experiences, parents will complete questionnaires on their parental style and risk tolerance, as well as information about the child’s practical risk experience.
Results:
Four schools have been recruited to participate in data collection. The recruitment of children and parents for this study started in December 2022, and as of April 2023, a total of 433 parents have consented for their children to participate.
Conclusions:
The Virtual Risk Management project will increase our understanding of how children’s characteristics, upbringing, and previous experiences influence their learning and ability to handle challenges. Through development and use of cutting-edge technology and previously developed measures to describe aspects of the children’s past experiences, this project addresses crucial topics related to children’s health and development. Such knowledge may guide pedagogical questions and the development of educational, injury prevention, and other health-related interventions, and reveal essential areas for focus in future studies. It may also impact how risk is addressed in crucial societal institutions such as the family, early childhood education, and schools
AI enhanced collaborative human-machine interactions for home-based telerehabilitation
Get PDFThe use of robots in a telerehabilitation paradigm could facilitate the delivery of rehabilitation on demand while reducing transportation time and cost. As a result, it helps to motivate patients to exercise frequently in a more comfortable home environment. However, for such a paradigm to work, it is essential that the robustness of the system is not compromised due to network latency, jitter, and delay of the internet. This paper proposes a solution to data loss compensation to maintain the quality of the interaction between the user and the system. Data collected from a well-defined collaborative task using a virtual reality (VR) environment was used to train a robotic system to adapt to the users’ behaviour. The proposed approach uses nonlinear autoregressive models with exogenous input (NARX) and long-short term memory (LSTM) neural networks to smooth out the interaction between the user and the predicted movements generated from the system. LSTM neural networks are shown to learn to act like an actual human. The results from this paper have shown that, with an appropriate training method, the artificial predictor can perform very well by allowing the predictor to complete the task within 25 s versus 23 s when executed by the human
Down the back of a chair: what can a method of scrabbling with Le Guin’s Carrier Bag Theory of Fiction offer conceptualisations of ‘the child’ in the Anthropocene?
Get PDFIn this chapter, the authors work with Ursula Le Guin’s (1986) Carrier Bag Theory of Fiction to offer a reconfiguration of “the book” in childhood contexts. Attending to the relational agencies generated from messy entanglements of (hence hyphenated) reader-book-child-chair-cat-lice-mites, they feel their way around to arrive at other ideas about what books are, what books do, and what else they might potentiate in contemporary imaginations of “the child”. Le Guin retells the story of human origin by redefining technology as a cultural “carrier bag” rather than a weapon of domination. The authors offer a scrabbling methodology of “research-creation”: a method of scrabbling “down the back of the chair” (both literally and metaphorically). This feminist methodology attunes to assemblages of odds and ends, hair and dust mites, children’s literature and child readers and facilitates an exploration of the intersectional, relational meanings that might tell us something else about childhood in the Anthropocene
Editorial
No full textThis issue of the European Journal for Philosophy of Communication (Empedocles), includes articles on spirituality and atheism in Soviet Russia; music, rhythm and sound in suffering and mourning in individual and collective contexts; trust in health communication in deaf contexts and, finally, the role of affect and intuition in social cognition and public communication, focusing on misinformation and public debate
Empirical investigation into impact of IT adoption on supply chain agility in fast food sector in Pakistan
Get PDFInformation technology and supply chain agility are in vogue. The present study aims to investigate the impact of information technology (IT) on supply chain agility and its outcomes such as cost reduction and operational performance in fast food companies’ chains. A total of 240 employees from fast food chains were selected as respondents. Data was collected using five-point Likert scale questionnaire developed from previous studies. The statistical results confirmed that adoption of IT is playing a vibrant role in achieving supply chain agility and supply chain agility helps to reduce cost and improves operational performance of firms. The study model provides a useful framework to examine the impact of IT adoption on supply chain agility and its outcomes. In conclusion, the firms have to focus on their supply chain management and make it efficient and agile by implementing the advanced technologies to gain operational performance. Implications have been discussed
Classification of gastrointestinal cancer through explainable AI and ensemble learning
No full textDespite the effectiveness of AI-assisted cancer detection systems, acquiring authorisation for their deployment in clinical settings has proven challenging owing to their inadequate level of explainability in their underlying mechanisms. Due to the lack of transparency in AI-driven systems’ decision-making, many medical practitioners are still reluctant to employ AI-assisted diagnoses. Explainable Artificial Intelligence (XAI) is a new topic in AI that has the potential to solve the computational black boxes that AI systems posed, allowing for an explanation of a model prediction. Consequently, in this research work, we have explored the Shapley Additive explanations (SHAP), which is a model prediction explanation approach on our developed ensemble model based on the averaging techniques by concatenating the predictions of three convolutional neural network (InceptionV3, Inception-ResNetV2, and VGG16). The models were trained on the pathological findings of Kvasir-V2 datasets and have achieved an accuracy of 93.17% and F1-scores of 97%. Post-training of the ensemble model, images from the three classes were analysed using SHAP to provide an explainability on their deterministic features. The results obtained indicate a favourable and optimistic improvement in the investigation of XAI approaches in healthcare more specifically in the detection of gastrointestinal cancer
Test–retest reliability of the magnitude and direction of asymmetry in the countermovement jump, drop jump, and countermovement rebound jump
Get PDFThis study aimed to investigate the test–retest reliability of three bilateral jump tests to assess asymmetry and determine the consistency of both the magnitude and direction of asymmetry between two testing sessions. Thirty-three participants performed the countermovement jump (CMJ), drop jump (DJ), and countermovement rebound jump (CMRJ—jump 1: CMRJ1; jump 2: CMRJ2) over two sessions. Inter-limb asymmetry was calculated for kinetic metrics, including the mean propulsive force, net braking impulse, and net propulsive impulse. Test reliability was computed using intraclass correlation coefficients (ICC), coefficients of variation (CV), and standard error of measurement. Furthermore, analysis of variance was used to determine the systematic bias between jump types and sessions. Kappa coefficients were utilised to assess the consistency of asymmetry favouring the same limb. Results showed poor to excellent reliability for all jump tests between sessions (ICC range = 0.19–0.99, CV range = 2.80–11.09%). A significantly higher magnitude of asymmetry was revealed for the net braking impulse during the DJ compared to the CMRJ2 (p ≥ 0.014, g ≤ 0.53). When computing the direction of asymmetry between test sessions, Kappa coefficients revealed that levels of agreement were substantial (Kappa = 0.63–0.70) for the CMJ, moderate to almost perfect (Kappa = 0.59–0.94) for the CMRJ1, moderate to almost perfect (Kappa = 0.58–0.81) for the DJ, and slight to moderate for the CMRJ2 (Kappa = 0.19–0.57). These results underscore the variable nature of both the magnitude and direction of asymmetry during jump testing. Thus, practitioners should carefully choose evaluation methods and metrics characterised by low variability to ensure robust asymmetry assessments
Divine Vision: William Blake in Felpham
No full textLondon, 1800. Things aren’t going too well for William Blake. He lacks work, his wife worries over the bills, he’s seeing visions of the Apocalypse, and his planned epic poem on the divine remains unwritten. When Blake gets an offer from famous poet William Hayley to leave London and settle in a cottage at the seaside village of Felpham, he jumps at the chance. In Felpham, things don’t quite work out the way Blake had them planned…
What ensues involves talent wasted, offences to the local gentry, an argument with a drunken soldier, a trial for sedition, and a visionary meeting with the Lamb of God in an English cottage garden. “And did those feet…” indeed!
Divine Vision is the first stage play to explore William Blake’s only period of living outside London, and the events leading to his writing the poem which we now know as the iconic hymn “Jerusalem”