检索结果-内蒙古大学图书馆

An authentication and plausibility model for big data analytic under LOS and NLOS conditions in 5G-VANET

Science China(Information Sciences) 2020年第12期63卷 67-83页

作者： S.A.SOLEYMANI M.H.ANISI A.Hanan ABDULLAH M.Asri NGADI Sh.GOUDARZI M.Khurram KHAN M.Nazri KAMA School of Computing Faculty of Engineering Universiti Teknologi Malaysia (UTM) School of Computer Science and Electronic Engineering University of Essex Centre of Artificial Intelligence National University of Malaysia (UKM) Center of Excellence in Information Assurance (CoEIA) King Saud University Advanced Informatics School Menara Razak Universiti Teknologi Malaysia (UTM)

The exchange of correct and reliable data among legitimate nodes is one of the most important challenges in vehicular ad hoc networks(VANETs). Malicious nodes and obstacles, by generating inaccurate information, have a negative impact on the security of 5G-VANET. The big data generated in the vehicular network is also an issue in the security of VANET. To this end, a security model based on authentication and plausibility is proposed to improve the safety of network named ‘AFPM’. In the first layer, an authentication mechanism using edge nodes along with 5G is proposed to deal with the illegitimate nodes who enter the network and broadcast wrong information. In the authentication mechanism, because of the growth of the connected vehicles to the edge nodes that lead to generating big data and hence the inappropriateness of the traditional data structures, cuckoo filter, as a space-efficient probabilistic data structure, is used. In the second layer, a plausibility model by performing fuzzy logic is presented to cope with inaccurate information. The plausibility model is based on detection of inconsistent data involved in the event message. The plausibility model not only tackles with inaccurate, incomplete, and inaccuracy data but also deals with misbehaviour nodes under both line-of-sight(LOS) and non-line-of-sight(NLOS) conditions. All obtained results are validated through well-known evaluation measures such as F-measure and communication overhead. The results presented in this paper demonstrate that the proposed security model possesses a better performance in comparison with the existing studies.

关键词： authentication plausibility fuzzy logic cuckoo filter 5G-VANET big data

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network as the Classifier of the Muscle Contraction Pattern During Stepping Activity

Artificial Neural Network as the Classifier of the Muscle Co...

引用

International Conference on Artificial Intelligence and Data Sciences (AiDAS)

作者： Aiman Syabil Mazlan Sofea Nur Batrisyia Suhaizan Zariq Hishamudin Nor Aziyatul Izni Siti Nor Aini Mohd Aslam Sarah'Atifah Saruchi College of Computing Informatics and Mathematics Universiti Teknologi MARA Cawangan Negeri Sembilan Kampus Seremban Seremban Negeri Sembilan Malayia Centre of Foundation Studies Universiti Teknologi MARA Cawangan Selangor Kampus Dengkil Dengkil Selangor Malaysia Faculty of Manufacturing and Mechatronic Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pekan Pahang Malaysia

ISBN: (数字)9798331528553

ISBN: (纸本)9798331528560

Exercise and repetitive movement fatigue are crucial to healthcare and rehabilitation. To improve the quality of rehabilitation and healthcare, precise evaluations and focused interventions are needed. Electromyography (EMG) is an essential technique used to measure muscle activity during various tasks. Despite its popularity, previous studies have yet to determine which EMG features are critical in classifying muscle contraction patterns across different physical activities and obtaining optimal performance. Therefore, this study aims to classify muscle contraction patterns during stepping exercises from $s$ EMG and investigate the efficiency of Artificial Neural Networks as a classifier of this muscle contraction pattern. Sixty participants voluntarily participated in this stepping exercise and their EMG signal was recorded. The raw EMG signal undergoes filtering, rectification, and linear enveloping. Then, each signal from each participant was segmented into a relax signal and a contract signal. Time domain and frequency domain features were then retrieved from every relax and contract signal and fed into the ANN model. The results indicate that ANN yielded 96.5% accuracy performance in classifying the muscle contraction patterns from the sEMG signal. The findings from this study could contribute valuable insights to inform more effective and personalized rehabilitation services in identifying muscle contractions autonomously, thereby improving the overall mobility and quality of life for individuals facing muscle fatigue and financial problems. This study could help in strengthening the healthcare services mentioned in Ekonomi Madani's 17-Big Bolds, Malaysia.

关键词： Training Accuracy Artificial neural networks Medical services Muscles Feature extraction Fatigue Electromyography Time-domain analysis Contracts

来源：评论

学校读者我要写书评

暂无评论

John Hollerton: a life in industrial analytical spectroscopy, part 1

引用

Spectroscopy Europe 2022年第8期34卷 32-35页

作者： Davies, Antony N. Cashyap, Mohan Hollerton, John SERC Sustainable Environment Research Centre Faculty of Computing Engineering and Science University of South Wales United Kingdom MASS Informatics Harpenden United Kingdom Hollerton Scientific Software Consultancy St Albans United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Enhancing UX Design Through Eye- Tracking and Image Processing: Practical Insights and Applications

Enhancing UX Design Through Eye- Tracking and Image Processi...

引用

International Conference on Platform Technology and Service (PlatCon)

作者： Aslina Baharum Rozita Ismail Suhaida Halamy Emelia Abdul Rahim Noorsidi Aizuddin Mat Noor Farhana Diana Deris School of Engineering and Technology Sunway University Bandar Sunway Selangor Malaysia College of Computing and Informatics Universiti Tenaga Nasional Putrajaya Campus Kajang Selangor Malaysia School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Cawangan Sarawak Kota Samarahan Sarawak Malaysia Faculty of Business Management Universiti Teknologi MARA Cawangan Sarawak Kota Samarahan Sarawak Malaysia Mass Appraisal Housing and Planning Research Group Centre for Real Estate Studies Real Estate Department Faculty of Built Environment and Surveying Universiti Teknologi Malaysia Johor Bahru Johor Malaysia Faculty of Social Sciences and Humanities Universiti Teknologi Malaysia Johor Bahru Johor Malaysia

ISBN: (数字)9798350367874

ISBN: (纸本)9798350367881

In the digital age, optimizing user experience (UX) is paramount for the success of various applications and interfaces. Eye-tracking, a method used to monitor and analyze eye movements, has emerged as a powerful tool in UX research. This study investigates the intersection of eye-tracking and image processing, focusing on how insights derived from eye-tracking data can enhance UX design. Through a series of case studies, this research explores the practical applications of eye-tracking in improving user interaction with image-based interfaces. By analyzing user attention patterns, gaze fixation durations, and visual engagement metrics, the study uncovers valuable insights into user behaviour and preferences. These insights inform design decisions related to interface layout, content placement, and visual hierarchy, ultimately leading to more intuitive and engaging user experiences. The findings from this study provide practical guidelines and best practices for integrating eye tracking into the UX design process, offering valuable insights for designers, developers, and researchers seeking to optimize user interaction with image-based applications and interfaces.

关键词： Measurement visualization Tracking Image processing Gaze tracking Predictive models User experience Real-time systems Best practices Optimization

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep Learning with Fundus and Optical Coherence Tomography for Cardiovascular Disease Prediction

arXiv

引用

arXiv 2024年

作者： Maldonado-Garcia, Cynthia Zakeri, Arezoo Frangi, Alejandro F. Ravikumar, Nishant Centre for Computational Imaging and Simulation Technologies in Biomedicine School of Computing University of Leeds Leeds United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences Faculty of Biology Medicine and Health University of Manchester Manchester United Kingdom School of Computer Science Faculty of Science and Engineering University of Manchester Kilburn Building Manchester United Kingdom Christabel Pankhurst Institute University of Manchester Manchester United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom

Early identification of patients at risk of cardiovascular diseases (CVD) is crucial for effective preventive care, reducing healthcare burden, and improving patients’ quality of life. This study demonstrates the potential of retinal optical coherence tomography (OCT) imaging in conjunction with fundus photographs for identifying future adverse cardiac events. We utilized data from 977 patients who experienced CVD within a 5-year interval post-image acquisition, alongside 1,877 control participants without CVD, totaling 2,854 subjects. We propose a novel binary classification network based on a Multi-channel Variational Autoencoder (MCVAE), which learns a latent embedding of patients’ fundus and OCT images to classify individuals into two groups: those likely to develop CVD in the future and those who are not. Our model, trained on both imaging modalities, achieved promising results (AUROC 0.78 ± 0.02, accuracy 0.68 ± 0.002, precision 0.74 ± 0.02, sensitivity 0.73 ± 0.02, and specificity 0.68 ± 0.01), demonstrating its efficacy in identifying patients at risk of future CVD events based on their retinal images. This study highlights the potential of retinal OCT imaging and fundus photographs as cost-effective, non-invasive alternatives for predicting cardiovascular disease risk. The widespread availability of these imaging techniques in optometry practices and hospitals further enhances their potential for large-scale CVD risk screening. Our findings contribute to the development of standardized, accessible methods for early CVD risk identification, potentially improving preventive care strategies and patient outcomes. © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Women's Health Diary: Tracker System for Menstruation, Intermenstrual, Ovulation, and Postnatal Bleeding Using Rules-Based Technique

Women's Health Diary: Tracker System for Menstruation, Inter...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Nursyuhada binti Abdullah Azwa bin Abdul Aziz Wan Azani Mustafa Muntather Almusawi Abbas Hameed Abdul Hussein Faculty of Informatics & Computing Universiti Sultan Zainal Abidin (UniSZA) Besut Campus Terengganu Malaysia Data Science & Analytics (DASA) Special Interest Group (SIG) Universiti Sultan Zainal Abidin (UniSZA) Terengganu Malaysia Centre of Excellence Advanced Computing (CoE AdvComp) Universiti Malaysia Perlis Arau Perlis Malaysia Faculty of Engineering The Islamic University Najaf Iraq College of Pharmacy Ahl Al Bayt University Karbala Iraq

Menstruation, a natural physiological process in women, entails regular vaginal bleeding as part of the monthly menstrual cycle. While existing systems facilitate menstrual cycle tracking, they often lack the capability to differentiate between various types of vaginal bleeding, such as menstruation (haid), intermenstrual bleeding (istihadah), or postnatal bleeding (nifas). To address this limitation, the Women's Health Diary: Tracker System for Menstruation, Intermenstrual, Ovulation, and Postnatal Bleeding) was developed using a rule-based technique. This system employs an iterative method comprising eight phases: initial planning, planning, requirements, analysis and design, implementation, testing, evaluation, and deployment. By ensuring the optimal development and performance of this system, women can effectively manage their menstrual blood, a vital aspect of their overall health. Moreover, this system holds particular significance for every women, as it facilitates tracking and identification of regular and irregular cycles, enabling them to uphold the legitimacy of their worship.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Bioactivity and Corrosion Resistance of Laser Powder Bed-Fused Ti6al4v Using Titania-Reinforced Hydroxyapatite Nanocomposite Coatings Through Electrophoretic Deposition

SSRN

引用

SSRN 2024年

作者： Sohrabpoor, Hamed Salarvand, V. Torabpour, M. Yazdi, M. Saghafi Asadi, P. Brabazon, Dermot Stein, B.D. Raghavendra, R. Department of Intelligent Systems Engineering Luddy School of Informatics Computing and Engineering Indiana University Bloomington BloomingtonIN United States Department of Materials Science and Engineering Imam Khomeini International University Qazvin Iran Department of Mechanical Engineering Engineering Faculty Gebze Technical University Kocaeli Gebze41400 Turkey I-Form Advanced Manufacturing Research Centre & Advanced Processing Technology Research Centre School of Mechanical & Manufacturing Engineering Dublin City University Dublin Ireland Electron Microscopy Center Department of Biology Indiana University BloomingtonIN United States SEAM Research Center South East Technological University Ireland

Hydroxyapatite (HA) coatings are commonly used on titanium alloy substrates for orthopedic and dental implants because of their excellent osteoconductivity and biocompatibility. The disparity in the coefficient of thermal expansion (CTE) between the coating and substrate can result in the formation of cracks in the HA coatings during the coating process. This study examined the effect of titania (TiO2) nanoparticle additions in HA coatings to enhance their properties and prevent cracking. Using electrophoretic deposition (EPD), HA and HA-TiO2 composite coatings were applied to laser powder bed fused Ti6Al4V substrates. Optimal EPD conditions of 45 volts and 120 s were identified to produce consistent, crack-free coatings. Increasing the TiO2 nanoparticle concentration (≥50 wt.%) decreased the coatings' CTE, mitigating cooling-induced cracking. The microstructural analysis confirmed the uniform distribution of HA and TiO2 in the coatings. X-ray diffraction and Fourier-transform infrared spectroscopy data revealed that the HA structure remained intact even with the addition of TiO2. Higher TiO2 reduced the average surface roughness, with the HA-40%TiO2 coating exhibiting the lowest roughness (approximately 50 nm). Electrochemical tests corroborated the surface roughness findings. Incorporating TiO2 into the HA coatings decreased the thermal expansion coefficient, reducing tensile stresses. © 2024, The Authors. All rights reserved.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Implementation of Artificial Intelligence In engineering to Achieve Sustainable Development Goals (SDGs)

Implementation of Artificial Intelligence In Engineering to ...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Muhammad D. Zakaria Azwa Abdul Aziz Azrul Amri Jamal Wan Azani Mustafa Laith H. Alzubaidi A.H. A. Hussein Faculty of Informatics & Computing Universiti Sultan Zainal Abidin (UniSZA) Tembila Campus Terengganu Malaysia Data Science & Analytics (DASA) Special Interest Group (SIG) Universiti Sultan Zainal Abidin (UniSZA) Gong Badak Terengganu Malaysia Centre of Excellence Advanced Computing (CoE AdvComp) Universiti Malaysia Perlis Arau Perlis Malaysia College of Pharmacy Ahl Al Bayt University Karbala Iraq Faculty of Engineering The Islamic University Najaf Iraq

Artificial Intelligence (AI) is implicit to revolutionize the engineering industry by automating tasks, minimizing costs, improving quality, and creating new opportunities for innovation. The article explores the implementation of AI in engineering as a means to achieve the Sustainable Development Goals (SDGs) set forth by the United Nations. AI technologies hold significant potential in optimizing resource utilization, enabling data-driven decision-making, and fostering innovation in various engineering domains. This study provides an overview of AI applications highlighting their alignment with specific SDGs. It examines the advantages, challenges, and ethical considerations connected to AI integration in engineering practices. Moreover, the article provides recommendations for policymakers, researchers, and practitioners to ensure responsible and inclusive AI development. By harnessing the transformative power of AI in engineering, we can increase the process towards SDGs, creating a more sustainable and prosperous future for all.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PPG Segmentation Using Deep Learning

PPG Segmentation Using Deep Learning

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Mohammad Tabbakha Hassan Al Masri Abdullatif Hammad Mohammed Alsulatie Hiam Alquran Wan Azani Mustafa Muntather Almusawi Abbas Hameed Abdul Hussein Department of Biomedical Systems and Informatics Engineering Yarmouk University Irbid Jordan King Hussein Medical Center Royal Jordanian Medical Service The Institute of Biomedical Technology Amman Jordan Faculty of Electrical Engineering & Technology Campus Pauh Putra Advanced Computing (AdvComp) Centre of Excellence Universiti Malaysia Perlis Arau Perlis Malaysia Faculty of Engineering The Islamic University Najaf Iraq College of MLT Ahl Al Bayt University Karbala Iraqs

As an indicator regarding cardiovascular health, vascular dynamics, and more, Photoplethysmography (PPG) consists of a baseline with two pulsatile peaks that reflect the blood flow variations. In the absence of critical studies and a precise understanding of PPG signal this study proposes a deep learning approach to predict and define each phase of PPG waveform utilizing Gated recurrent unit (GRU) due to its optimal performance in the short-term dependencies in sequences, the model is composed mainly of GRU layer with 20 hidden units applying tanh and sigmoid activation function, followed by dropout layer and a fully connected layer, afterward a softmax layer was added, we conducted our study on a dataset combined of an accessible Bed-Based Ballistocardiography Dataset (BBB), after that, the data was manually labeled. Following up, hyperparameters such as learning rate, batch size, and other parameters were adjusted after numerous trials, which resulted in test accuracy, precision, and recall of 0.875, 0.892, and 0.854, respectively in the used dataset. These promising results might be the first step of more future investigations concerning PPG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning-Based Method for Automated Detection and Characterization of Cracks in Drainage Pipes

SSRN

引用

SSRN 2024年

作者： Yang, Chenhao Zheng, Feifei Kapelan, Zoran Savic, Dragan Pan, Gang Feng, Yu Ma, Yiyi College of Civil Engineering and Architecture Zhejiang University China Department of Water Management Delft University of Technology Netherlands Centre for Water Systems University of Exeter North Park Road ExeterEX4 4QF United Kingdom KWR Water Research Institute Netherlands Faculty of Civil Engineering University of Belgrade Serbia College of Intelligence and Computing Tianjin University China Cartography and Visual Analytics Technical University of Munich Germany

Currently, the interpretation of closed-circuit television images for structural defect analysis of drainage pipes is mostly conducted manually, which is labor-intensive. In this study, an integrated deep-learning-based algorithm is proposed, namely the Crack Detection and Characterization (CDC) method, which can detect and quantify (e.g., length) pipe cracks. The CDC algorithm is verified by images of pipe cracks both artificially created in the laboratory and from real filed inspection. From the results, the CDC algorithm with the DeepLab V3+ crack detection model performs best for both the laboratory and field cases. The results also show the significant effect of the deblurring process in improving the accuracy of the CDC algorithm. The process increases the mean intersection over union (mIoU) of the calculated results by 1.2%. This study offers an innovative way of detection and characterization of drainage pipe cracks, capable of more accurate pipe defect assessment compared with traditional work. © 2024, The Authors. All rights reserved.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：