检索结果-内蒙古大学图书馆

Procedia CIRP 2021年 98卷 571-576页

作者： Tomohiko Sakao Peter Funk Johannes Matschewsky Marcus Bengtsson Mobyen Uddin Ahmed Division of Environmental Technology and Management Department of Management and Engineering Linköping University SE-581 83 Linköping Sweden Division of Intelligent Future Technologies School of innovation design and engineering Mälardalen University SE-122 20 Västerås Sweden Operations Volvo Construction Equipment Eskilstuna Sweden Division of Computer Science and Software Engineering School of innovation design and engineering Mälardalen University SE-122 20 Västerås Sweden

This paper presents a vision for a much-needed paradigm shift in Life Cycle engineering (LCE), which is termed Adaptive and Intelligent Life Cycle engineering (AI-LCE). To do so, interdisciplinary analysis of literature in domains of AI and LCE is performed. Needed concepts and methods are described: key enabling technologies are Artificial Intelligence (AI), the Internet of Things, and data lakes, which are becoming cost-effective and increasingly implemented in industry. Both artificial and human intelligence are used in combination. Its advantages compared with the conventional LCE include shorter time for changing activities in the lifecycle and the accuracy of changes made.

关键词： Artificial Intelligence Internet of Things vision time accuracy

FENet: A frequency extraction network for obstructive sleep apnea detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ye, Guanhua Yin, Hongzhi Chen, Tong Chen, Hongxu Cui, Lizhen Zhang, Xiangliang School of Information Technology & Electric Engineering The University of Queensland Australia School of Computer Science University of Technology Sydney Australia School of Software Shandong University China Division of Computer Electrical and Mathematical Sciences & Engineering King Abdullah University of Science and Technology Saudi Arabia

Obstructive Sleep Apnea (OSA) is a highly prevalent but inconspicuous disease that seriously jeopardizes the health of human beings. Polysomnography (PSG), the gold standard of detecting OSA, requires multiple specialized sensors for signal collection, hence patients have to physically visit hospitals and bear the costly treatment for a single detection. Recently, many single-sensor alternatives have been proposed to improve the cost efficiency and convenience. Among these methods, solutions based on RR-interval (i.e., the interval between two consecutive pulses) signals reach a satisfactory balance among comfort, portability and detection accuracy. In this paper, we advance RR-interval based OSA detection by considering its real-world practicality from energy perspectives. As photoplethysmogram (PPG) pulse sensors are commonly equipped on smart wrist-worn wearable devices (e.g., smart watches and wristbands), the energy efficiency of the detection model is crucial to fully support an overnight observation on patients. This creates challenges as the PPG sensors are unable to keep collecting continuous signals due to the limited battery capacity on smart wrist-worn devices. Therefore, we propose a novel Frequency Extraction Network (FENet), which can extract features from different frequency bands of the input RR-interval signals and generate continuous detection results with downsampled, discontinuous RR-interval signals. With the help of the one-to-multiple structure, FENet requires only one-third of the operation time of the PPG sensor, thus sharply cutting down the energy consumption and enabling overnight diagnosis. Experimental results on real OSA datasets reveal the state-of-the-art performance of FENet. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

A Survey on Explainable Artificial Intelligence for Cybersecurity

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rjoub, Gaith Bentahar, Jamal Wahab, Omar Abdel Mizouni, Rabeb Song, Alyssa Cohen, Robin Otrok, Hadi Mourad, Azzam King Hussein School of Computing Sciences Princess Sumaya University for Technology Jordan Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Department of Computer and Software Engineering Polytechnique Montréal Montréal Canada Electrical Engineering and Computer Science Department Khalifa University Abu Dhabi United Arab Emirates Department of EECS Khalifa University Abu Dhabi United Arab Emirates David R. Cheriton School of Computer Science University of Waterloo Canada Cyber Security Systems and Applied AI Research Center Dept. of CSM Lebanese American University Lebanon Division of Science New York University Abu Dhabi United Arab Emirates

The "black-box" nature of artificial intelligence (AI) models has been the source of many concerns in their use for critical applications. Explainable Artificial Intelligence (XAI) is a rapidly growing research field that aims to create machine learning models that can provide clear and interpretable explanations for their decisions and actions. In the field of cybersecurity, XAI has the potential to revolutionize the way we approach network and system security by enabling us to better understand the behavior of cyber threats and to design more effective defenses. In this survey, we review the state of the art in XAI for cybersecurity and explore the various approaches that have been proposed to address this important problem. The review follows a systematic classification of cybersecurity threats and issues in networks and digital systems. We discuss the challenges and limitations of current XAI methods in the context of cybersecurity and outline promising directions for future research. © 2023, CC BY.

关键词： Cybersecurity

Edge AI-Based Dynamic Treatment Strategy Generation Model for Consumer Healthcare Technology

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Byeon, Haewon Alsaadi, Mahmood Quraishi, Aadam Shabaz, Mohammad Ahanger, Tariq Ahamed Keshta, Ismail Saidova, Feruza Soni, Mukesh Karumuri, Srinivasa Rao Inje University Department of AI and Software Gimhae50834 Korea Republic of Al-Maarif University College Department of computer science Al Anbar31001 Iraq Intervention Treatment Institute M.D. Research HoustonTX United States Model Institute of Engineering and Technology J and K Jammu India CoBA Prince Sattam Bin Abdulaziz University Department of Management Information Systems Saudi Arabia AlMaarefa University College of Applied Sciences Computer Science and Information Systems Department Riyadh Saudi Arabia Tashkent State University of Economics Department of Foreign languages Tashkent Uzbekistan Lovely Professional University Division of Research and Development Phagwara India VLSI-Microelectronics Lab Department of Electronics and Communication Engineering Andhra Pradesh Vaddeswaram Guntur522302 India

Edge AI-based reinforcement learning is less reliant on mathematical models and relies on experience to help with the design and optimization of Consumer Technology models, making it ideal for learning dynamic treatment techniques. However, the current research still has the following problems: 1. The optimality of the learned strategy is considered without taking risks into account, leading to strategies with certain risks. 2. The issue of distribution shift is ignored, resulting in learned strategies that are completely different from those of doctors. 3. The patient's historical observational data and treatments are ignored, making it difficult to accurately assess the patient's state, which in turn leads to the inability to learn the optimal strategy. Based on this, we propose the DOSAC-DTR dynamic treatment strategy model, which integrates Dead-ends and offline monitoring into the Actor-Critic framework. First, we consider the risk of treatment actions recommended by the learned strategy and incorporate the concept of Dead-ends into the Actor-Critic framework. Second, to mitigate the distribution shift problem, we integrate physician monitoring into the Actor-Critic framework. This approach achieves better performance, resulting in lower estimated mortality rates and higher Jaccard index scores. © 1975-2011 IEEE.

关键词： Reinforcement learning

Physical Adversarial Attack Meets computer Vision: A Decade Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wei, Hui Tang, Hao Jia, Xuemei Wang, Zhixiang Yu, Hanxun Li, Zhubo Satoh, Shin'ichi Van Gool, Luc Wang, Zheng School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University Wuhan China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing100871 China Colleage of Software and Technology Zhejiang University Hangzhou China School of Cyber Science and Engineering Wuhan University Wuhan China Digital Content and Media Sciences Research Division National Institute of Informatics Japan Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan Computer Vision Lab of ETH Zurich Zürich8092 Switzerland KU Leuven Leuven3000 Belgium INSAIT Sofia Bulgaria

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern. Extensive research has demonstrated that incorporating sophisticated perturbations into input images can lead to a catastrophic degradation in DNNs’ performance. This perplexing phenomenon not only exists in the digital space but also in the physical world. Consequently, it becomes imperative to evaluate the security of DNNs-based systems to ensure their safe deployment in real-world scenarios, particularly in security-sensitive applications. To facilitate a profound understanding of this topic, this paper presents a comprehensive overview of physical adversarial attacks. Firstly, we distill four general steps for launching physical adversarial attacks. Building upon this foundation, we uncover the pervasive role of artifacts carrying adversarial perturbations in the physical world. These artifacts influence each step. To denote them, we introduce a new term: adversarial medium. Then, we take the first step to systematically evaluate the performance of physical adversarial attacks, taking the adversarial medium as a first attempt. Our proposed evaluation metric, hiPAA, comprises six perspectives: Effectiveness, Stealthiness, Robustness, Practicability, Aesthetics, and Economics. We also provide comparative results across task categories, together with insightful observations and suggestions for future research directions. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Corrections to “Fuzzy Logic-Based Substitution-Box for Robust Medical Image Encryption in Telemedicine”

学校读者我要写书评

暂无评论

IEEE Access 2025年 13卷 53717-53717页

作者： Abdul Razaq Louai A. Maghrabi Musheer Ahmad Farrah Aslam Wei Feng Department of Mathematics Division of Science and Technology University of Education Lahore Pakistan Department of Software Engineering College of Engineering University of Business and Technology Jeddah Saudi Arabia Department of Computer Engineering Jamia Millia Islamia New Delhi India Department of Information Sciences Division of Science and Technology University of Education Lahore Pakistan School of Mathematics and Computer Science Panzhihua University Panzhihua China

Presents corrections to the paper, Corrections to “Fuzzy Logic-Based Substitution-Box for Robust Medical Image Encryption in Telemedicine”.

关键词： Telemedicine Encryption Biomedical imaging

A Guide to Image and Video based Small Object Detection using Deep Learning: Case Study of Maritime Surveillance

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rekavandi, Aref Miri Xu, Lian Boussaid, Farid Seghouane, Abd-Krim Hoefs, Stephen Bennamoun, Mohammed The Department of Computer Science and Software Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia The Department of Electrical Electronics and Computer Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia The School of Mathematics and Statistics The University of Melbourne Melbourne Australia submarine optronics undersea combat systems and undersea command and control maritime division Defence Science and Technology Group Australia

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided. © 2022, CC BY-NC-SA.

关键词： Object recognition

The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sami, H. Hammoud, A. Arafeh, M. Wazzeh, M. Arisdakessian, S. Chahoud, M. Wehbi, O. Ajaj, M. Mourad, A. Otrok, H. Abdel Wahab, O. Mizouni, R. Bentahar, J. Talhi, C. Dziong, Z. Damiani, E. Guizani, M. Concordia Institute for Information Systems Engineering Concordia University MontréalQC Canada Department of Electrical Engineering École de Technologie Supérieure Montréal Canada Department of Software and IT engineering École de Technologie Supérieure Montréal Canada Department of Computer and Software Engineering Polytechnique Montréal Montreal Canada Cyber Security Systems and Applied AI Research Center Department of CSM Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi United Arab Emirates Department of EECS Khalifa University Abu Dhabi United Arab Emirates Department of ML Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

The Metaverse offers a second world beyond reality, where boundaries are non-existent, and possibilities are endless through engagement and immersive experiences using the virtual reality (VR) technology. Many disciplines can benefit from the advancement of the Metaverse when accurately developed, including the fields of technology, gaming, education, art & culture, socialization, commerce, and businesses. Nevertheless, developing the Metaverse environment to its full potential is an ambiguous task that needs proper guidance and directions. Existing surveys on the Metaverse focus only on a specific aspect and discipline of the Metaverse and lack a holistic view of the entire process. Moreover, most surveys refrain from providing detailed guidance about the development process of the metaverse, including its impact on technologies, businesses, existing challenges, and potential research directions due to their lack of a macro and micro perception of such a topic. To this end, a more holistic, multi-disciplinary, in-depth, and academic and industry-oriented review is required to provide a thorough study of the Metaverse development pipeline and fill the gap in existing Metaverse surveys. To address these issues, we present in this survey a novel multi-layered pipeline ecosystem composed of (1) the Metaverse computing, networking, communications and hardware infrastructure, (2) environment digitization, and (3) user interactions. For every layer, we discuss the components that detail the steps of its development. Also, for each of these components, we examine the impact of a set of enabling technologies and empowering domains (e.g., Artificial Intelligence, Security & Privacy, Blockchain, Business, Ethics, and Social) on its advancement. In addition, we explain the importance of these technologies to support decentralization, interoperability, user experiences, interactions, and monetization. Our presented study highlights the existing challenges for each component, fo

关键词： Edge computing

Joint Theme and Event Based Rating Model for Identifying Relevant Influencers on Twitter: COVID-19 Case Study

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Srour, Ali Ould-Slimane, Hakima Mourad, Azzam Harmanani, Haidar Jenainati, Cathia Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Software Engineering IT École de Technologie Supérieure MontrealQC Canada Department of English Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi United Arab Emirates

The continuous proliferation of social media platforms and the exponential increase in users’ engagement are impacting social behavior and leading to various challenges, including the detection and identification of key influencers. In fact the opinions of these influencers are at the core of decisionmaking strategies, and are leading trends on the virtual social media landscape. Moreover, influencers might play a crucial role when it comes to misinformation and conspiracy during sensitive, controversial and trending events. However, due to the dynamic and unrestricted nature of social media, and diversity of targeted topics and audiences, identifying and ranking key influencers that are impactful, credible, and knowledgeable about their specialist topic or event remains an evolving and open research paradigm. In this paper, we address the aforementioned problem by proposing a novel influence rating and ranking scheme to identify key and highly influential users for a certain event over Twitter using a mixed theme/event based approach while considering historical data and profile reputation. We further apply our approach to a global pandemic case study, the novel Coronavirus, and conduct performance analysis. The presented experimental results and theoretical analysis explore the relevance of our proposed scheme for identifying and ranking reputable and theme/event related influencers. © 2022, The Authors. All rights reserved.

关键词： Social networking (online)

Integrating AI for infectious disease prediction: A hybrid ANN-XGBoost model for leishmaniasis in Pakistan

学校读者我要写书评

暂无评论

Acta Tropica 2025年 266卷

作者： Niu, Ben Qureshi, Humera Khan, Muhammad Imran Shah, Adil School of Computer Science and Software Engineering Shenzhen Institute of Information Technology Shenzhen China College of Management Shenzhen University Shenzhen China Division of Biostatistics Department of Population Health King Abdullah International Medical Research Center Riyadh Saudi Arabia King Saud Bin Abdulaziz University for Health Sciences Ministry of National Guard Health Affairs (MNGHA) Riyadh Saudi Arabia Health Department Khyber Pakhtunkhwa Peshawar Pakistan

Addressing leishmaniasis infection remains a substantial challenge in KP-Pakistan due to the increased infection prevalence. Understanding its spreading tool offerings is a major challenge. We essentially design effective approaches to pinpoint its emergence and implement upgraded management strategies. This study aims to assess the prevalence of leishmaniasis infection in KP's four high-endemic districts (Bannu, Karark, Lakki Marwat, and Dera Ismail Khan) and estimate the potential future incidence. We executed a broad logical evaluation on data obtained from the pertinent district health departments of KP, using a novel hybrid ANN-XGBoost approach. We assessed its performance by equating it with frequently used models for infectious disease forecasting over time, comprising the ARIMA, LSTM, ANN, and XGBoost. We evaluated the model's precision using manifold indicators: MAE, RMSE, and MAPE. We developed the models using Python 3.11 software. The results show that the hybrid model outperformed all other models, attaining an MAE score of 82.2, an RMSE of 111.6, and a MAPE of 10.6, validating superior forecast accuracy. According to our proposed model, about 1,017 new leishmaniasis cases are expected per month by December 2025. These findings provide valuable insights for disease monitoring and intervention in KP. Advanced machine learning techniques can help policymakers improve resource mapping and come up with targeted management measures to stop the spread of leishmaniasis. Subsequent research should include other environmental and socio-economic variables influencing illness spread to improve predictive models. © 2025

关键词： Infection Khyber pakhtunkhwa Leishmaniasis Pakistan Prediction