检索结果-内蒙古大学图书馆

Analysis of Deep Learning Methods for Fracture Segmentation of Road surface under on Encoder and Decoder

Analysis of Deep Learning Methods for Fracture Segmentation ...

2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022

作者： Subha, T.D. Sasirekha, N. Shamitha, C. Radhika, S. Tamilselvi, M. R.M.K. Engineering College Department of Electronics and Communication Engineering Chennai601 206 India Sona College of Technology Department of Electronics and Communication Engineering Salem636005 India MIT MAHE Department of Electronics and Communication Engineering Bengaluru560064 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Chennai602105 India T.S.Srinivasan Centre for Polytechnic College and Advanced Training Department of Mechatronics Engineering Chennai600 095 India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

Road imperfections have a significant impact on driving in terms of both safety and convenience. It's for this reason that road degradation identification and restoration assessments are carried out on a regular basis. Road accidents, especially in developing countries like India, are often caused by poorly designed roads and highways that have been damaged by cracks or potholes. Road accident and fatality rates may be reduced if interested parties get timely and accurate information about dangerous road conditions. A new topology for neural networks, as well as training and prediction approaches is discussed in this research. Road surface deterioration conditions may be detected using a unique deep neural network approach proposed here. 1300 training photos and 400 testing photographs with various sorts of road distress are used to train the neural network. Nine deep learning models from diverse disciplines are compared with the suggested approach. The suggested method exceeds all others with a pixel accuracy of 97.61%, according to the comparison findings. The findings of this research might play a significant role in the future in assuring safe driving by quickly identifying dangerous highway conditions. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Patient health monitoring system using smart IoT devices for medical emergency services

Patient health monitoring system using smart IoT devices for...

引用

2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022

作者： Sreelakshmy, R. Sruthy, R. Rajeshwari, R. Thyla, B. Suresh Kumar, M. Veltech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai Avadi600062 India NSS Polytechnic College Department of Electronics & Communication Engineering PandalamPandalamPandalam689501 India S.A. Engineering College Department of Master of Computer Applications Thiruverkadu Chennai600077 India KCG College of Technology Department of Electronics and Communication Engineering KCG College Rd Tamil Nadu Karapakkam Chennai600097 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai Thandalam602105 India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

When devices, applications, monitors, and network services are connected together, the Internet of Things (IoT) is created, which allows these organizations to collect and share data more efficiently. The aware of the status of a person via the testing of numerous metrics, as well as the inference of a positive outcome from the past of this kind of continuous supervision, distinguishes the Internet of Things inside the medical system. A difficult endeavor, the prognosis of cardiovascular disease survival is important in assisting medical practitioners in making the best judgments possible for their individuals. Patients with heart failure need the knowledge and skill of health doctors to be properly cared for. The use of machine learning techniques may aid in the comprehension of the signs of cardiovascular disease. Hand - crafted feature development, on the other hand, is difficult and necessitates the use of specialized knowledge to determine the most suited approach. This research presents a smart health monitoring structure that makes use of the Internet of Things and cloud mechanism to enhance the mortality forecast of patients with chronic heart failure with no need for human classifier, as previously done. In addition, the smart IoT-based infrastructure analyzes individuals just on based entirely information and offers cardiac rehabilitation with fast, efficient, and high-quality medical care. Additionally, the suggested model analyses whether deep learning models are effective in distinguishing between heart failure patients who are alive and those who are died. The framework makes use of Internet of Things-based sensors to collect signals and transmit them to a cloud web application for analysis. Learning algorithms are used to further analyse these data in order to identify the condition of the patients. Health information and process monitoring are communicated with a medical expert who will respond to the patient in the event that emergency assistance is

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Self-temperature compensation approach for fiber specklegram magnetic field sensor based on polarization specklegram analysis 27

Self-temperature compensation approach for fiber specklegram...

引用

27th International Conference on Optical Fiber Sensors, OFS 2022

作者： Hu, Shicheng Liu, Haifeng Liu, Bo Lin, Wei Zhang, Hao Song, Binbin Wu, Jixuan Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology Institute of Modern Optics Nankai University Tianjin300350 China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Institute of Modern Optics Nankai University Tianjin300350 China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai519000 China Key Laboratory of Computer Vision and Systems School of Computer Science and Engineering Tianjin University of Technology Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems College of Electronic and Information Engineering Tianjin Polytechnic University Tianjin300387 China

We proposed a self-temperature-compensation approach for fiber specklegram sensor (FSS) based on polarization specklegram analysis, and designed a fiber specklegram magnetic field sensor with high stability and good r... 详细信息

ISBN: (纸本)9781957171142

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Self-temperature compensation approach for fiber specklegram magnetic field sensor based on polarization specklegram analysis 8

Self-temperature compensation approach for fiber specklegram...

引用

8th Symposium on Novel Photoelectronic Detection technology and Applications

作者： Hu, Shicheng Liu, Haifeng Liu, Bo Lin, Wei Zhang, Hao Song, Binbin Wu, Jixuan Tianjin Key Laboratory of Micro-Scale Optical Information Science and Technology Institute of Modern Optics Nankai University Tianjin300350 China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Institute of Modern Optics Nankai University Tianjin300350 China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai519000 China Key Laboratory of Computer Vision and Systems Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems College of Electronic and Information Engineering Tianjin Polytechnic University Tianjin300387 China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

In this letter, we proposed a self-temperature-compensation approach for fiber specklegram sensor (FSS) based on polarization specklegram analysis. The temperature compensation is achieved by comparing the variation difference of the two specklegrams with vertical linear polarization state. We designed a fiber specklegram magnetic field sensor employing this method and the magneto-birefringence effect of magnetic fluid. The measurement of magnetic field with high stability and good repeatability has been successfully achieved, which demonstrated the effectiveness of the proposed method. Due to the merits of low cost, ease of implement and system simplicity, the proposed method can promote the practical use of the FSS in long term monitoring. © 2022 SPIE

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

2-D GCANet Applied to Denoise 1-D EEG Signals in Online Remote Teaching Scenarios

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1289-1302页

作者： Huang, Ting-Qing Wang, Chuan-Sheng Chen, Zhao-Qi Zhang, Fu-Quan Meng, Xiang-Long Grau, Antoni Chen, Yang Huang, Jing-Wei College of Computer and Control Engineering Minjiang University Fuzhou University Town No. 200 Xiyuangong Road Fuzhou China Department of Automatic Control Technical Polytechnic University of Catalonia Autonomous Region of Catalonia Barcelona Spain College of Computer and Big Data Fuzhou University Fuzhou University Town No. 2 Wulong Jiangbei Avenue Fuzhou China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music No. 2 Wannianchang Street Chenghua District Sichuan Province Chengdu City China Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou University Town NO. 200 Xiyuangong Road Fuzhou China Fujian Province University No. 599 Quanxiu Road Juyuanzhou Ecological Civilization District Fujian Province Fuzhou City China College of Electronic Engineering Shandong University of Science and Technology No. 579 Qianwangang Road Huangdao District Qingdao China School of Mechanical and Automotive Engineering Fujian University of Technology No. 33 Xuefu South Road University New District Fujian Province Fuzhou City China

When EEG signals are used to assess the level of student engagement in online teaching tasks, they are often interfered by noise. It is a challenge to effectively remove these noises. Currently, deep learning methods have been applied to the field of EEG denoising. However, existing methods still have some problems. The denoised signals still have obvious noise residue, or the original EEG signals are damaged, and the model fitting speed is too slow. Image dehazing, as a typical denoising task in the field of image enhancement, has achieved great success in recent years. Therefore, inspired by advanced models in this field, we introduce CNN into EEG denoising tasks. In this paper, we take GCANet, an excellent image enhancement model, as an example. The dilated convolutions and gate fusion subnetworks included in GCANet enable more efficient EEG signal denoising. The results demonstrate that the proposed model effectively reduces noise while preserving essential features. Furthermore, in comparison to other state-of-the-art models, our proposed model exhibits enhanced robustness and faster convergence, as evidenced by achieving lower loss values after five epochs. Its good performance provides a new development idea for the field of EEG denoising. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Investigation and Development of Energy Efficient EV Chargers 5

Investigation and Development of Energy Efficient EV Charger...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Raghavendra, G. Neeraja Kumar, P. Ravi Rawat, Ramesh Singh Deepak, A. Arora, Deepika Sapthagiri College of Engineering Department of Electrical and Electronics Engineering Bangalore India Government Polytechnic Department of Electrical and Electronics Engineering Telangana Hyderabad India KPR Institute of Engineering and Technology Department of EEE Avinashi Road Arasur Coimbatore India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering SIMATS Tamilnadu Chennai India Lloyd Institute of Engineering and Technology Department of CSE Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350398267

technology advancements and concerns about greenhouse gas emissions will make electric vehicles the preferred mode of transportation in the future. The goal of this research is to resolve the current power grid issues of harmonics and low power factor. Rectifiers are primarily used in electric vehicles to convert AC power to DC power. A popular feature of SPWM rectifiers is that they produce high output voltage, unity power factor, and excellent dynamic response with low input current distortions. Closed-loop DC-DC converters and single-phase SPWM rectifiers convert direct current from one voltage to another. This method can balance the DC link to maintain a unity power factor and account for reactive power. With the proposed technology, individual rectifiers will be reliable and effective, and electric vehicle grids will be stable. The EU's energy paradigm has undergone considerable changes. To achieve the gradual shift toward electric vehicles and renewable energy, the EU climate commitment 2050 sets a reduction target of 80 to 95 percent. The requirements for Flexibility may vary from source to load due to the advancement of demand-side resource and storage technologies. A future grid with intermittent and uncontrollable wind and solar power generation presents problems. To maximize the integration of renewable resources and electric vehicles and to enhance renewable energy penetration, a novel grid technique is proposed and analyzed in this study. The charging and discharging strategy is managed by a distribution control system employing V2G technology to provide a mismatch between charging and renewable generation. To fulfill demand, avoid peak hours, and provide auxiliary services, it is necessary to maintain consistent frequency, smooth load configuration, and stable power quality. © 2022 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

The role of implementing Machine Learning approaches in enhancing the effectiveness of HealthCare service 2

The role of implementing Machine Learning approaches in enha...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Umamaheswaran, S.K. Munagala, Nvlm Krishna Mishra, Deepti Othman, Bestoon Sinthu, S. Tripathi, Vikas Sri Sai Ram Engineering College Department of Mathematics TN Chennai India Gitam Deemed to Be University Department of Electrical Electronics and Communication Engineering Andhra Pradesh Visakhapatnam India G.L. Bajaj Institute of Technology and Management Department of Computer Science and Engineering UP Greater Noida India Erbil Polytechnic University Koya Technical Institute Erbil Iraq Nawroz University College of Administration and Economics Department of Business Administration Duhok Iraq Tamilnadu Karur India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665437899

'Machine Learning' (ML) is a useful technology for extracting information from 'Internet of Things' (IoT) data. These hybrid systems intelligently improve decision-making in a variety of fields, including education, business, healthcare as well as security. IoT can use machine learning to decipher hidden patterns in large amounts of data, allowing for better forecasting and recommendation engines. In healthcare, ML is utilised for disease assessment and treatment predictions, as well as target discovery and verification, pharmaceutical product development, biomarker recognition, and pathogenesis. Government expenditure on healthcare has achieved an all-time peak, despite the obvious need for improved patient-physician communication. In the areas of smartphone applications, computer appliances, online websites, cybersecurity, and other areas, such techniques have already been used. A 'health prediction system' deals with the problem of unexpected changes among hospital patient flows. Emergency occurrences such as 'ambulance arrivals during natural catastrophes' and 'motor vehicle accidents', as well as normal outpatient demand, generate demand for healthcare services in many hospitals. These healthcare related issues can be managed by using ML algorithms. In order to collect important information, this research paper has considered primary quantitative or survey method by considering 78 healthcare professionals to get proper information. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Superabsorbent Hydrogel Evaporator with Sandwich Sa/Cnts/Sa Cellular Wall for Solar-Driven Water Purification

SSRN

引用

SSRN 2024年

作者： Yu, Xi Fang, Jianhui Yu, Zikang Zheng, Senyi Kong, Xuan Liang, Huafeng Yang, Qifeng Wang, Lihuan Yu, Hui Liu, Zijin Fan, Longfei Zuo, Qi Wu, Xiaohui Gan, Feng Li, Zhengrong Kan, Chi-Wai Yan, Jianhua Wang, Xianfeng Guangdong-Hong Kong Joint Laboratory for New Textile Materials School of Textile Materials and Engineering Wuyi University Jiangmen529020 China Guangdong Laboratory of Chemistry Fine Chemical Industry Jieyang Center Jieyang515200 China School of Textile and Garment Anhui Polytechnic University Anhui Wuhu241000 China School of Computer Science Guangdong Vocational and Technical University of Business and Technology Zhaoqing526000 China Institute of Textiles & Clothing The Hong Kong Polytechnic University 100872 Hong Kong Innovation Center for Textile Science and Technology Donghua University Shanghai200051 China Key Laboratory of Science & Technology of Eco-Textile China

The global shortage of fresh water resources is imminent, and solar desalination has been recognized as a low-cost, simplest and feasible strategy for freshwater resource acquisition. However, the evaporation rate of the current solar evaporator will be affected by the absorption capacity of sunlight and surface salt condensation, and the evaporator is vulnerable to collapse under external pressure, which seriously limits the water evaporation performance in the long-term use. Therefore, we developed a simple and effective idea to prepare hydrogel evaporators. By using the combination of homogeneous dispersion and freeze drying, carbon nanotubes(CNTs) were embedded in the hydrophilic polymer sodium alginate(SA) to prepare highly water-absorbing hydrogel evaporator. By optimizing the proportion of raw materials and process parameters, the CNTs were coated with SA to form a stable sandwich cellular wall structure, and the sandwich cellular walls were interconnected to form an aerogel with vertical penetration channels, which could quickly and efficiently absorb water (absorption ratio of 29 times) and transport seawater in the direction of the cellular. The evaporator has continuous and stable water transport function and high photothermal conversion efficiency, light absorption efficiency reaches more than 96%, and has an evaporation rate of 2.25kg·m-2·h-1 under one sun. In addition, the solar energy absorber has extremely stable compressibility and salt resistance, thereby improving the working life and continuous working ability of the evaporator. © 2024, The Authors. All rights reserved.

关键词： Sodium alginate

来源：评论

学校读者我要写书评

暂无评论

Performance Monitoring and Controlling of Multicore Shared-Memory Parallel Processing Systems

Performance Monitoring and Controlling of Multicore Shared-M...

引用

Information technology To Enhance e-learning and Other Application (IT-ELA)

作者： Lailan M Haji Subhi R. M. Zeebaree Zainab Salih Ageed Omar M. Ahmed Mohammed A. M. Sadeeq Hanan M. Shukur Computer Science Dep. Faculty of Science University of Zakho Duhok Iraq Energy Eng. Dept. Technical College of Engineering Duhok Polytechnic University Duhok Iraq Computer Science Dept. College of Science Nawroz University Duhok Iraq Information Technology Dept. Zakho Technical Institute Duhok Polytechnic University Duhok Iraq ITM Dept. Technical College of Administration Duhok Polytechnic University Duhok Iraq Computer Engineering Dept. Al-Kitab University Kirkuk Iraq

The field of research known as “parallel processing” examines architectural and algorithmic methods for increasing the efficiency and other desirable qualities (such as cost-effectiveness and reliability) of computers by exploiting many forms of concurrency. The development of multi-core CPUs has opened the door to novel strategies for boosting system performance via parallelism. Increasing the number of concurrent threads greatly affects the time cost. While increased parallelism might reduce calculation time, the associated synchronization costs would likely be prohibitive for most applications. In this article, we'll go through the first half of the process, which involves gathering requirements and designing a prototype; the second half, which involves monitoring and managing a program that can run on a wide range of multicore system architectures, including those with (2, 4, and 8 CPUs). A shared-memory parallel processing method was proposed and built to show off the system's full potential. The implications of multi-core systems on overall program execution time and parallel processing in shared-memory systems provide the backbone of this investigation.

关键词： Costs Multicore processing System performance Systems architecture Prototypes Parallel processing Central Processing Unit

来源：评论

学校读者我要写书评

暂无评论

Frontend Amplifier with Unipolar Oxide TFTs for Heart Rate Measurement

Frontend Amplifier with Unipolar Oxide TFTs for Heart Rate M...

引用

International Conference on Display technology, ICDT 2022

作者： Xu, Yuming Li, Bin Deng, Sunbin Zhong, Wei Yin, Xuemei Wu, Zhaohui Kowk, Hoi-Sing Chen, Rongsheng School of Microelectronics South China University of Technology Guangzhou510640 China State Key Laboratory on Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Purdue University West LafayetteIN United States School of integrated circuits Guangdong University of Technology Guangzhou China School of artificial intelligence Zhuhai City Polytechnic College Zhuhai China

This paper presents a frontend amplifier based on the n-type only indium-tin-oxide (ITO)-stabilized ZnO thin film transistors (TFTs) on glass substrate. The amplifier has an external-bias AC-coupled, open-loop capacitor bootstrap structure. The area and power consumption are 41 mm2 and 0.1 mW (8V), respectively. Measurement results show a gain of 20 dB, a bandwidth of 3 Hz–6 kHz, a common mode rejection ratio (CMRR) up to 42 dB, an input impedance of 100 MΩ, and an input-referred noise of 106 μVrms (integrated from 1 Hz–200 Hz). The noise efficiency factor (NEF) and power efficiency factor (PEF) of the amplifier are respectively 248 and 4.9×105. The amplifier is successfully used to measure the heart-rate signal. © 2022, John Wiley and Sons Inc. All rights reserved.

关键词： Tin oxides

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：