检索结果-内蒙古大学图书馆

8th International Conference on information technology, InCIT 2024

作者： Hnoohom, Narit Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Faculty of Engineering Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand University of Phayao Department of Computer Engineering School of Information and Communication Technology Phayao Thailand King Mongkut's University of Technology Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics North Bangkok Thailand

ISBN: (纸本)9798350366303

Motorcyclist behavior recognition (MBR) is a significant factor in improving road safety and preventing accidents. Inertial sensors, such as accelerometers, gyroscopes, and magnetometers, have shown promising potential for capturing the dynamic behavior of motorcyclists. However, existing approaches often require complex models and significant computational resources, limiting their deployment in real-world scenarios. This study presents a MotoNeXt architecture, which is a light deep residual network for correctly identifying the behavior of motorcyclists using data from inertial sensors. Our approach leverages the power of deep learning while maintaining a compact model size, making it suitable for resource-constrained environments. The proposed network incorporates multi-kernel residual blocks to facilitate the learning of hierarchical features and improve gradient flow during training. We evaluate our method on a publicly available benchmark dataset, MB-IMU, collected from multiple riders under various riding conditions. Experimentation has shown that our lightweight model achieves cutting-edge performance, outperforming a variety of existing techniques. In Scenario I, using accelerometer, gyroscope, and magnetometer data, MotoNeXt achieved an accuracy result of 78.90088% along with an F1-score of 81.56738%. According to Scenario II, which included additional sensor data such as VelInc, OriInc, and Euler angles, MotoNeXt further improved its performance, achieving an accuracy result of 83.29735% along with an F1-score of 84.95352%. The proposed approach offers a practical solution for real-time MBR, enabling the development of intelligent transportation systems and rider assistance technologies. Our experiments highlight the effectiveness of lightweight deep learning models in extracting meaningful patterns from inertial sensor data. This opens up opportunities for further investigation in this field. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

TU-IR Apple Image Dataset: Benchmarking, Challenges, and Asymmetric Characterization for Bruise Detection in Application of Automatic Harvesting

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第1期2卷 105-124页

作者： Das, Dipak Hrishi Roy, Sourav Dey Saha, Priya Bhowmik, Mrinal Kanti Government Degree College Department of Information Technology Santirbazar 799144 India Department of Computer Science and Engineering Suryamaninagar 799022 India Department of Cyber Security and Digital Forensics Agartala799001 India

With the blooming interest in computer vision-based technologies for future automation of food producers, there is a need for incorporating an automatic bruise detection module in robotic apple harvesting because of decreasing accessibility and growing labor costs. Although numerous studies have been published for automatic quality inspection of fruit and other agricultural products, there is a lack of publicly available image-based datasets for quality inspection/automatic detection of bruises. Toward the aim of developing a bruise detection system for apple harvesting, especially at night time, this article describes the designing issues (i.e., protocol) and creation of a new infrared imaging-based dataset titled 'TU-IR Apple Image Dataset,' which contains 1375 infrared images of apples defining four major categories of bruises (i.e., fresh, slight, moderate, and severe). Along with the infrared images, ground truths (in the form of binary masks) and measurements of suspicious bruised regions are defined. This study also investigates the efficiency of infrared imaging technology for automatic bruise detection in apples by performing an analysis of temperature-based, intensity-based, texture-based, shape-based, and deep convolutional neural network-based features. The classification performance was evaluated using eight different feature sets. Based on the experimental results, considering the most outer-performed classifier, deep convolutional neural networks as a fixed feature extraction method were found to provide the highest prediction performance for discriminating between fresh and three categories of bruises in apples with an average accuracy, specificity, and sensitivity of 93.87%, 80.57%, and 92.02%, respectively. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare through the Internet of Things: Current State and Future Implications 15

Revolutionizing Healthcare through the Internet of Things: C...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Shantinath, Barwade Rohit Sabnis, Vikrant Jain, Jay Kumar Department of Computer Science Mansarovar Global University Bhopal India Department of Computer Science Faculty of Engineering and Technology Mansarovar Global University Bhopal India Indian Institute of Information Technology Madhya Pradesh Bhopal India

ISBN: (纸本)9798331300579

The Internet of Things (IoT) has the potential to completely transform healthcare by allowing medical professionals to remotely monitor patients, gather data on their activity and health in real-time, and create more efficient treatment regimens. IoT technologies have the potential to save healthcare expenditures while also enhancing patient involvement and improving patient outcomes. However, the adoption of IoMT has been slow, and To ensure that the advantages of IoT are realised while reducing the hazards connected with its use, a number of hurdles must be overcome. The purpose of this research paper is to examine the current state of IoT implementation in healthcare, identify the benefits and challenges of IoMT, and explore the future implications of IoMT. The study starts off with a survey of the literature that has already been written on the use of IoT technology in healthcare, highlighting both the potential advantages and difficulties of doing so. The paper then presents the results of a survey of healthcare providers on the use of IoT technologies in healthcare, providing insights into the current state of IoT implementation in healthcare and the challenges that must be addressed to facilitate its adoption. © Grenze Scientific Society, 2024.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach for medical images classification and segmentation to reduce complexity

引用

Innovations in Systems and Software engineering 2023年第1期19卷 33-46页

作者： Kumar, Ankit Bhatia, Surbhi Bhardwaj, Rajat Singh, Kamred Udham varshney, Neeraj Raja, Linesh Department of Computer Engineering and Applications GLA University Chaumuhan Uttar Pradesh Mathura281406 India Department of Information Systems College of Computer Science and Information Technology King Faisal University Dammam31451 Saudi Arabia Chitkara University Institute of Engineering and Technology Chitkara University Chandigarh-Patiala National Highway Punjab Rajpura140401 India Department of Computer Science and Information Engineering National Cheng Kung University Dasyue Street Tainan Tainan701 Taiwan School of Computing Graphic Era Hill University Bell Road Uttarakhand Dehradun248002 India Department of Computer Apllications Manipal University Jaipur Rajasthan Jaipur303007 India

The computational domain facilitates the performance of novel and innovative medical research and development tasks by providing support and computational power. This analysis method forecasts the future by analyzing the data we now have. The method may be divided into three primary phases: preprocessing, feature extraction, and classification. The research presented here aimed to improve the precision with which heart disease could be predicted across three distinct phases. The first step is thoroughly examining the databases kept at the UCI computer repository. In this study, we use the dataset’s five different algorithms, decision tree, Naive Bayes, random forest, KNN, and support vector machine, to compare their respective performances. In addition to age, the suggested revolutionary technique considers other characteristics such as pulse rate, cholesterol, and so on, which was not the case in earlier studies. In the past, age was the primary consideration in analysis and illness prediction. Compared to more traditional methods, improved prediction accuracy is achieved by modifying the study’s primitive properties. Third, this research introduced a novel hybrid classification model by fusing support vector machines and k-nearest neighbor classification techniques. A k-nearest neighbor classifier will do the heavy lifting to classify the data, while support vector machines will extract the dataset’s features. The accuracy rates for the various prediction methods decision tree, KNN, Naive Bayes, random forest, support vector machine, and proposed method range from 72.53% to 87.32% to 87.39% to 81.34%, respectively. The new technique decreases execution value by 5 % and increases accuracy by up to 8 %. The suggested model outperforms state-of-the-art approaches in terms of accuracy and implementation speed. © 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

5G the Missing Piece in Digital Transformation of the Construction Sector 28

5G the Missing Piece in Digital Transformation of the Constr...

引用

28th International computer Science and engineering Conference, ICSEC 2024

作者： Chnaidini, Shaik Khan, M. Jebran Ullah, Fasee Khan, Arafat Ahmad Prashar, Deepak Gulf American University Dept. of Civil Engineering Fujairah United Arab Emirates Sarhad University of Science and Information Technology Dept of Computing and Information Technology Peshawar Pakistan Uinversiti Teknology Petronas Dept. of Computer and Information Sciences Seri Iskandar Malaysia Khonkaen University Dept. of Computer Science Khon Kaen Thailand Lovely Professional University Dept. of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350366860

The 5th generation of wireless technology with a continuum leap rushing towards the future in the world of communication has a puzzle that enables the autonomous machine to work in site making a louder voice that shows the era where even if we cannot be fully robotic, we can make the machines do the work by sitting on a faraway control room. Making ways clear to see the work done miles away on construction sites the 5th generation has not only brought the people close through communication but also made them work collegiately with a clearer view front. The paper discusses 5G and the other related technologies that are emerging all over the world and how it is needed specifically in the construction industry. In the present paper, we tried to shed light on the acceptance and implementation of 5G technology in the construction sector. It is seen that the construction sector in India is lagging behind when it comes to implementation and availability of required support and resources for the 5G implementation. © 2024 IEEE.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

Efficient MMSE Equalization for Direct-Sequence Spread-Spectrum Underwater Communications

引用

IEEE Internet of Things Journal 2025年第11期12卷 16325-16335页

作者： Liu, Mengzhuo Liu, Jun Peng, Zheng Cui, Jun-Hong Beihang University School of Electronic and Information Engineering Beijing100191 China Jilin University College of Computer Science and Technology Changchun130012 China UESTC Shenzhen Institute for Advanced Study Shenzhen518110 China Smart Ocean Technology Co. Ltd Shenzhen518057 China

To facilitate the exploration and exploitation of underwater resources, autonomous systems and Underwater Acoustic Networks (UANs) are deployed for tasks unsuitable for direct human intervention and exchange information between devices. To keep the reliability of information exchanged, Direct Sequence Spread Spectrum (DSSS) communication is commonly adopted for this scenario. To simplify the channel equalization process in DSSS communication, a Minimum Mean Square Error (MMSE) equalizer is often utilized. However, the characteristics of underwater acoustic channels and acoustic modem, including long delay spreads and limited computational resources, lead to high computational complexity for MMSE equalization, thereby reducing decoding efficiency. To address this challenge, we propose a refined MMSE equalizer, termed the Efficient MMSE Equalizer (EME). Unlike conventional MMSE methods, the EME approach involves initially despreading the received chip sequence, followed by equalizing on the noisy symbols. By reducing the size of the correlation matrix in the core computational step of MMSE equalization, our method significantly improves computational efficiency. We assess the computational complexity of the proposed EME approach in comparison to conventional MMSE equalization and validate its performance through simulations and experimental studies. The results demonstrate that the EME achieves a bit error rate (BER) performance comparable to that of conventional MMSE equalization under high signal-to-noise ratio (SNR) conditions, while significantly enhancing computational efficiency. © 2014 IEEE.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Student Trend Analysis for Foreign Education Employing Machine Learning: A Case Study from ‘Disha Consultants’, Gujarat, India

引用

Annals of Data Science 2024年第2期11卷 571-588页

作者： Shah, Manan Kshirsagar, Ameya Sushra, Tulasi Department of Chemical Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India Department of Computer Science and Information Technology Symbiosis Institute of Technology Maharashtra Pune India Department of Business Administration School of Liberal Administration Pandit Deendayal Energy University Gujarat Gandhinagar382426 India

For many years, there has been literature on study abroad, student mobility, and international student exchange;however, the scope & depth of this work has expanded dramatically in the recent two decades. Most of this research in comparative education studies is rarely published in its primary publications. This study report aims to give a complete overview of the trends and difficulties surrounding international student recruiting and assist institutional leaders & administrators in making informed choices and effectively setting priorities. We have performed EDA testing, a thorough analysis that helps discover data distribution. It is essential for all domains because it exposes trends, patterns, and relationships that are not immediately apparent. EDA is the most effective approach to finding outliers, but it might lead us wrong if not done correctly. We demonstrated that our research gives a suitable pragmatic answer for future International study patterns among students by conducting thorough trend analysis of varying detailed data obtained from various sources. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Parasitic Egg Detection and Classification in Low-Cost Microscopic Images Using Transfer Learning

引用

SN computer Science 2024年第1期5卷 82页

作者： Suwannaphong, Thanaphon Chavana, Sawaphob Tongsom, Sahapol Palasuwan, Duangdao Chalidabhongse, Thanarat H. Anantrasirichai, Nantheera Department of Engineering Mathematics University of Bristol Bristol United Kingdom Department of Computer Engineering Chulalongkorn University Bangkok Thailand Research Group on Applied Computer Engineering Technology for Medicine and Healthcare Chulalongkorn University Bangkok Thailand Visual Information Laboratory University of Bristol Bristol United Kingdom

Intestinal parasitic infection leads to several morbidities in humans worldwide, especially in tropical countries. The traditional diagnosis usually relies on manual analysis from microscopic images which is prone to human error due to morphological similarity of different parasitic eggs and abundance of impurities in a sample. Many studies have developed automatic systems for parasite egg detection to reduce human workload. However, they work with high-quality microscopes, which unfortunately remain unaffordable in some rural areas. Our work thus exploits a benefit of a low-cost USB microscope. This instrument however provides poor quality images due to the limitation of magnification (10 ×), causing difficulty in parasite detection and species classification. In this paper, we propose a CNN-based technique using transfer learning strategy to enhance the efficiency of automatic parasite classification in poor-quality microscopic images. The patch-based technique with a sliding window is employed to search for the location of the eggs. Two networks, AlexNet and ResNet50, are examined with a trade-off between architecture size and classification performance. The results show that our proposed framework outperforms the state-of-the-art object recognition methods. Our system combined with the final decision from an expert may improve the real faecal examination with low-cost microscopes. © 2023, The Author(s).

关键词： Automatic detection Convolutional neural networks Deep learning Human intestinal parasites Transfer learning USB microscope

来源：评论

学校读者我要写书评

暂无评论

Elite-guided equilibrium optimiser based on information enhancement:Algorithm and mobile edge computing applications

引用

CAAI Transactions on Intelligence technology 2024年第5期9卷 1126-1171页

作者： Zong-Shan Wang Shi-Jin Li Hong-Wei Ding Gaurav Dhiman Peng Hou Ai-Shan Li Peng Hu Zhi-Jun Yang Jie Wang School of Information Science and Engineering Yunnan UniversityKunmingChina Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhenChina Academic Affairs Office Yunnan University of Finance and EconomicsKunmingChina Faculty of Management and Economics Kunming University of TechnologyKunmingChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirutLebanon Department of Computer Science and Engineering University Centre for Research and DevelopmentChandigarh UniversityChennaiIndia Department of Computer Science and Engineering Graphic Era Deemed to Be UniversityDehradunIndia School of Computer Science Fudan UniversityShanghaiChina Rackham Graduate School University of MichiganAnn ArborMIUSA Research and Development Department Youbei Technology Co.LTDKunmingChina School of Mechanical and Power Engineering Zhengzhou UniversityZhengzhouChina

The Equilibrium Optimiser(EO)has been demonstrated to be one of the metaheuristic algorithms that can effectively solve global optimisation *** the paradox between exploration and exploitation operations while enhancing the ability to jump out of the local optimum are two key points to be addressed in EO *** alleviate these limitations,an EO variant named adaptive elite-guided Equilibrium Optimiser(AEEO)is ***,the adaptive elite-guided search mechanism enhances the balance between exploration and *** modified mutualism phase reinforces the information interaction among particles and local optima *** cooperation of these two mechanisms boosts the overall performance of the basic *** AEEO is subjected to competitive experiments with state-of-the-art algorithms and modified algorithms on 23 classical benchmark functions and IEE CEC 2017 function test *** results demonstrate that AEEO outperforms several well-performing EO variants,DE variants,PSO variants,SSA variants,and GWO variants in terms of convergence speed and *** addition,the AEEO algorithm is used for the edge server(ES)placement problem in mobile edge computing(MEC)*** experimental results show that the author’s approach outperforms the representative approaches compared in terms of access latency and deployment cost.

关键词： ANT COLONY optimization CLOUD COMPUTING GENETIC ALGORITHMS SWARM intelligence

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Detecting and Preventing Security Attacks in MANETs

A Hybrid Approach for Detecting and Preventing Security Atta...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Rajalakshmi, D. Immaculate, P.S. Madhumitha, D. Saravanan, D. Rajeswari, S. Pandi, S. Senthil Sri Sai Ram Institute of Technology Computer Science and Engineering Chennai India Sri Sai Ram Institute of Technology Master of Business Administration Chennai India Pavendar Bharathidasan College of Engineering & Technology Computer Science and Engineering Trichy India K.Ramakrishnan College of Engineering Information Technology Trichy India Rajalakshmi Engineering College Computer Science and Engineering Chennai India

ISBN: (纸本)9798350300857

MANETs are new sort of organizational network that works in a profoundly powerful and unusual atmosphere. Though the flexible nature of MANET is attractive, the dynamic topology of MANETs brings in numerous threats. The existing Intrusion Detection Systems (IDS) doesn't strictly detect the generation of attacks namely Black Hole, Gray Hole, Worm Hole and additional routing attacks. Added to it, the traditional methods of protection techniques won't be sufficed as MANETs are capable of providing network even in the absence of fixed infrastructure. In this proposed system introduces a new technique to detect these attacks and also prevent the generation of attacks by using Black Hole, Gray Hole, Neuro-Fuzzy based (BGNF) based Intrusion Detection System. This BGNF based Particle Swarm Optimization (PSO) helps to optimize and minimize the false alarms and data loss. © 2023 IEEE.

关键词： Intrusion 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：