检索结果-内蒙古大学图书馆

4th International Conference on Signal Processing and Machine Learning, CONF-SPML 2024

作者： Chandana, D. Tushara, M. Sri, A. Ramya Sakhamuri, Sridevi Abualigah, Laith Department of Electronics and Computer Engineering Koneru Lakshmaiah Education Foundation AP Vaddeswaram522502 India Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al al-Bayt University Mafraq25113 Jordan MEU Research Unit Middle East University Amman Jordan

ISBN: (纸本)9781510674721

Every human has their own kind of disabilities, we all try to live and overcome them in our life. We educate ourselves to overcome them, we invent technology to achieve our goals. Sign Language is a communication path for deaf-mute people through hand gestures and actions. Sign Language helps people who can’t speak sign language to interact with the people who can speak sign language, this deep learning paper aims to help build a communication bridge for this reason. We used Amazon Rekognition service which uses Deep CNN algorithm for the detection of static images of the signs. As most of the signs are for words they are in the form of videos. We used the I3D algorithm for the classification of videos of the signs of words. The PyTorch framework provides support for CuDNN (NVIDIA CUDA Deep Neural Network) which provides fast GPU implementations for the deep neural networks. The Experimental results has shown that the models used has displayed good results in detecting the words. © 2024 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Machine Learning for Enhanced Distributed Computing in Wireless Network Systems

Harnessing Machine Learning for Enhanced Distributed Computi...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Rashmi, K. Anandhi, R.J. Singh, Navdeep Kumar, V. Surya Pavan Gupta, Krashnkant Albawi, Ali Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Information Science Engineering Bangalore India Lovely Professional University Phagwara India Mlr Institute Of Technology Department Of CSE-AI&ML Telangana Hyderabad India Amity University Greater Noida Department Of Electronics & Communication Engineering India College Of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350366846

A complete wireless network system for flexible resource sharing, spectrum management, security, and cross-layer optimization is described in this paper. Five algorithms comprise the system. These are ADS, QoS-ML, CLO, and DSM. Wireless networks adapt and grow, and these applications solve issues. Real-time resource allocation using predictive models enhances network performance, latency, and efficiency with the PRA algorithm. DSM uses adaptive spectrum utilization to reduce interference. ADS uses machine learning to detect unusual activity and implement flexible safety measures to make networks safer. QoS-ML improves routing options using real-time QoS data to ensure network-wide QoS. CLO alters layer connections, utilizes metrics across layers, and is continually searching for network improvements. A detailed analysis of the research examined each program's distinct qualities and how they function together. The discussion focused on how well the framework performed in various settings and was adaptable. In the conclusion, the algorithms' strengths and potential in distributed computing environments were highlighted. The recommended technique outperformed others in speed, latency, security, energy efficiency, scalability, and customer satisfaction. Performance trends, parameter distributions, and trade-offs were shown, making the structure more dependable. By offering a full, adaptive, and successful method, this study advances wireless network management. Optimizations, scalability, and real-world applications might be studied to ensure the system works in various conditions. In challenging and changing situations, the proposed architecture supports wireless network expansion. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-Guided Autoencoders for Unsupervised Change Detection in Heterogeneous Remote Sensing Images

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2458-2471页

作者： Shi, Jiao Wu, Tiancheng Kai Qin, Alex Lei, Yu Jeon, Gwanggil Northwestern Polytechnical University School of Electronics and Information Xi'an710129 China Northwestern Polytechnical University in Shenzhen Research and Development Institute Shenzhen518057 China Chongqing Innovation Center of Northwestern Polytechnical University Chongqing401135 China Swinburne University of Technology Department of Computer Science and Software Engineering HawthornVIC3122 Australia Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

To address the problem of enormous differences in two heterogeneous images, the traditional unsupervised frameworks are most normally realized by converting two images into a common domain with various auxiliary strategies, such as transformation and alignment, which requires extensive calculation and has difficulty balancing the training tasks. To achieve a concise framework, this article proposes self-guided autoencoders (SGAE) for unsupervised change detection (CD) in heterogeneous remote sensing images (RSIs). Unlike traditional methods that aim to narrow the differences of heterogeneous images to highlight the changed information, SGAE forces the flow of identification in formation generated in unlabeled data through self-guided iterations. First, initial unsupervised networks output an elementary change map that will be screened to obtain reliable pseudolabels. The selected pseudolabeled samples will be used as the input of a supervised network to obtain another change map. Then, multiple change maps will be fused to refine the confidence of pseudolabels again, obtaining new fused pseudolabeled samples for the self-guided network, which will be trained with pseudolabeled samples and unlabeled samples. Finally, the above operations will be repeated to continuously optimize the net, which helps itself to extract the discriminative features for classification in self-guided iterations. Experiments compared with several algorithms on four datasets demonstrate the effectiveness and robustness of our method, which can help unsupervised models improve discriminative feature extraction and classification performance with a more flexible learning method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Polarization-induced photocurrent switching effect in heterojunction photodiodes

引用

Nano Research 2023年第4期16卷 5503-5510页

作者： Dingbo Chen Yu-Chang Chen Guang Zeng Yu-Chun Li Xiao-Xi Li Dong Li Chao Shen Nan Chi Boon S.Ooi David Wei Zhang Hong-Liang Lu State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics&SystemsSchool of MicroelectronicsFudan UniversityShanghai 200433China Key Laboratory for Information Science of Electromagnetic Waves Department of Communication Science and EngineeringFudan UniversityShanghai 200433China Photonics Laboratory Division of ComputerElectricaland Mathematical Sciences and EngineeringKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia

The unipolar photocurrent in conventional photodiodes(PDs)based on photovoltaic effect limits the output modes and potential versatility of these devices in *** photodiodes with photocurrent switching are emerging as a promising solution for obtaining photoelectric devices with unique and attractive functions,such as optical logic ***,we design an all-solid-state chip-scale ultraviolet(UV)PD based on a hybrid GaN heterojunction with engineered bipolar polarized electric *** introducing the polarization-induced photocurrent switching effect,the photocurrent direction can be switched in response to the wavelength of incident light at 0 V *** particular,the photocurrent direction exhibits negative when the irradiation wavelength is less than 315 nm,but positive when the wavelength is longer than 315 *** device shows a responsivity of up to−6.7 mA/W at 300 nm and 5.3 mA/W at 340 nm,*** particular,three special logic gates in response to different dual UV light inputs are demonstrated via a single bipolar PD,which may be beneficial for future multifunctional UV photonic integrated devices and systems.

关键词： GaN heterostructure ultraviolet(UV)photodiodes bipolar photocurrent optical logic device

来源：评论

学校读者我要写书评

暂无评论

The role of WES and BESS in the provision of operating electricity reserves-a review

The role of WES and BESS in the provision of operating elect...

引用

Power engineering Conference (SAUPEC), Southern African Universities

作者： Siphelele Joseph Mndiya Mukovhe Ratshitanga Senthil Krishnamurthy Department of Electrical Electronics and Computer Engineering Cape Peninsula University of Technology Cape Town South Africa

Active power reserves are required for an electrical system to work effectively. These reserves are modified regularly to meet system generation and demand to maintain a constant electrical frequency. Regulation reserves, spinning reserves, and non-spinning reserves are the three main forms of operating reserves. Reserves can be used in both normal and extraordinary conditions to maintain supply and demand balance. There have been various attempts to do research into how renewable generation might contribute to the provision of reserves now that large-scale wind energy has been integrated into the grid, but these efforts have been hampered by the stochastic and intermittent character of renewable generation. When proper control techniques are put in place, wind turbines can participate in the provision of operating reserves. This paper discusses the role of wind energy systems and battery energy storage systems in the provision of operating reserves. This research also looks at South Africa’s operating reserve margin and storage capacity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Use Of Machine Learning On SAR Data To Classify Submerged And Flooded Regions

Use Of Machine Learning On SAR Data To Classify Submerged An...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Ajay Kumar Maurya Prashansha Vasistha Bambam Kumar Dharmendra Singh Department of Electronics and Communication Engineering National Institute of Technology Patna Patna INDIA Computer Science & Engineering Banasthali Vidyapith Rajasthan INDIA Department of Electronics and Communication Engineering Indian Institute of Technology Roorkee Roorkee INDIA

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

In the past few years very much, attention has been given to flood monitoring. Along with flood detection, it is also essential to classify the fully merged, submerged, and without merged regions, which are helpful in various decision-making and environmental studies, but it is onerous to classify due to the mixed scattering response from these classes. However, there is some difference in the scattering response, which is hard to classify using only ordinary techniques. Machine learning (ML) is apt to deal with such mixed-class problems and classify them with acceptable accuracy. Therefore, in this paper, ML (Xgboost and Radom Forest) models are applied to the extracted optimum features from the Sentinel-1 synthetic aperture radar (SAR) data to classify the submerged and flooded regions. By combining ML algorithms with time series SAR data, flood monitoring systems can provide accurate and timely information about flooded and submerged areas, enhancing flood management strategies and reducing the impact on vulnerable communities.

关键词： Machine learning algorithms Accuracy Time series analysis Scattering Machine learning Feature extraction Classification algorithms Floods Synthetic aperture radar Monitoring

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Bus Tracking and Arrival Prediction in Real Time for Both Public and Private Sectors, Powered by Firebase

Revolutionizing Bus Tracking and Arrival Prediction in Real ...

引用

Distributed Computing and Electrical Circuits and electronics (ICDCECE), IEEE International Conference on

作者： Mohammed Shafiulla Abdul Lateef Haroon P S Shaik Mohammed Naveed Suhail Ahmed Mahika Dhar M Utkarsh Kumar Department of Computer Science and Engineering Ballari Institute of Technology & Management Ballari India Department of Electronics and Communication Engineering Ballari Institute of Technology and Management Ballari India Department of Computer Science and Engineering Ballari Institute of Technology and Management Ballari India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Public transport systems often face challenges related to reliability and efficiency, leading to inconvenience and uncertainty for passengers. Existing solutions for real-time bus monitoring typically rely on expensive Internet of Things (IoT) components. This paper presents Track N Go, a cost-effective alternative for real-time monitoring of public buses and taxis using mobile phone location data. The system utilizes a robust backend system built with Java and *** for the user interface. Integration of GPS via the Map Box API and Firebase database ensures accurate location tracking. Track N Go provides accurate real-time monitoring, addressing challenges associated with public transport and improving overall urban mobility. The system enhances convenience and peace of mind for passengers by delivering reliable and user-centric solutions. The evaluation of Track N Go demonstrates its effectiveness in improving urban mobility and transit services. By offering a reliable and cost-effective solution for real-time bus monitoring, Track N Go aims to streamline daily commutes and make public transport more efficient and predictable.

关键词： Uncertainty Smart cities Scalability User interfaces Real-time systems Mobile handsets Reliability

来源：评论

学校读者我要写书评

暂无评论

Futuristic IoT based Smart Precision Agriculture: Brief Analysis

引用

Journal of Mobile Multimedia 2022年第3期18卷 935-956页

作者： Swamidason, Iwin Thanakumar Joseph Pandiyarajan, Shanthini Velswamy, Karunakaran Leela Jancy, P. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhrapradesh Vijayawada India Department of Electronics and Communication Engineering Karunya Institute of Technology and Sciences Tamilnadu Coimbatore India Department of Computer Science and Engineering (AI & ML) and (Cybersecurity) Jain University Karnataka Bengaluru India Department of Information Technology Sri Sai Ram Institute of Technology Tamilnadu Chennai India

Agriculture is considered as the backbone of any nation across the globe. With the advent of modern technologies, smart tools and techniques are used in the agriculture/farming to build on the quantity as well as quality of the agriculture production to feed the basic necessity of the humans. Smart technology such as Internet of Things play a vital role in monitoring and analyzing various environmental parameters such as water level, humidity, soil moisture, air quality, UV level, rain etc. which are highly essential to ensure the fruitful yield of any nutritious crops. In this research article, precision agriculture concepts are investigated widely with the focus of improving the productivity level and also the effective utilization of resources with the minimal cost while compared with the conventional methodologies. © 2022 River Publishers.

关键词： Drones Internet of things (IoT) Irrigation Precision agriculture Sensors

来源：评论

学校读者我要写书评

暂无评论

Active power reserve provision with large-scale WES and BESS

Active power reserve provision with large-scale WES and BESS

引用

IEEE Power engineering Society Conference and Exposition in Africa, PowerAfrica

作者： Siphelele Joseph Mndiya Mukovhe Ratshitanga Senthil Krishnamurthy Department of Electrical Electronics and Computer Engineering Cape peninsula University of Technology Cape Town South africa

ISBN: (数字)9798350389388

ISBN: (纸本)9798350389395

For an electrical system to function properly, active power reserves are needed to stabilize the frequency. Recent studies show that power utilities can convert variable wind power generation into dispatchable technology by integrating wind farms with battery energy storage systems. For this study, an IEEE 9 bus system was modified and modelled using Real-time Simulator computer-Aided Design (RSCAD) simulation package by Real-Time Digital Simulator (RTDS) technologies. Using RSCAD, active power compensation control systems for both the wind energy system and the battery energy storage system were developed. The simulation results indicate that the developed control schemes are effective, and the combination of a wind energy system and the battery energy storage system can successfully provide the active power reserves and help balance the generation and demand.

关键词： Time-frequency analysis Battery energy storage system Wind energy Simulation Wind power generation Wind farms Power system stability Real-time systems IEC Standards Standards

来源：评论

学校读者我要写书评

暂无评论

A novel healthcare decision support system using IoT and ANFIS

引用

International Journal of Information technology (Singapore) 2024年第8期16卷 5421-5427页

作者： Dewangan, Naveen Kumar Pandey, Neeti Gautam, Ritu Goswami, Avinash Krishna Mitkari, Santosh Rameshwar Singh, Amanveer Kopare, Anand Gobi, N. Electronics & amp Telecommunication Engineering Bhilai Institute of Technology Chhattisgarh Durg India Madhav Vidhi Mahavidyala Jiwaji University Gwalior India School of Law Sharda University Noida India Sharda School of Law Sharda University Noida India Engineering Sciences & amp Allied Engineering Bharati Vidyapeeth’s College of Engineering for Women Maharashtra Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of ISME ATLAS SkillTech University Maharashta Kurla India Department of Computer Science and Information Technology JAIN (Deemed-to-be University) Karnataka Bangaluru India

Modern healthcare facilities are equipped with major difficulties, particularly in poor nations where there are insufficient high-quality hospitals and medical professionals in remote places. Healthcare has profited from artificial intelligence’s revolution in many other areas of life. A few issues with the current architecture of the store-and-forward method of conventional telemedicine are that it requires a local health center with a dedicated staff, medical equipment to prepare patient reports, and long turnaround time for receiving a diagnosis and medication details from a medical expert in a main hospital, the cost of local health centers, and the requirement for a Wi-Fi connection. In this work, we present a new intelligent healthcare system built on cutting-edge technology such as deep learning and the Internet of Things (IoT). This system has the intelligence to use a medical decision support system to sense and process patient data by making use of adaptive neuro fuzzy inference system (ANFIS). For those who live in rural places, this system offers an affordable solution. By contacting local hospitals, users can determine whether they have a serious health concern and seek appropriate treatment. Additionally, the experiment findings demonstrate that the suggested system is capable of providing health services due to its efficiency and intelligence. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： ANFIS Fuzzy logic (FL) IoT Neural networks Smart healthcare

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：