检索结果-内蒙古大学图书馆

Asilomar Conference on Signals, Systems & computers

作者： Tianqi Zheng Pengcheng You Enrique Mallada Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Dept. of Industrial Engineering and Management Peking University Beijing China

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several algorithms rooted in sampled-based primal-dual methods have been recently proposed to solve this problem in policy space. However, such methods are based on stochastic gradient descent-ascent algorithms whose trajectories are connected to the optimal policy only after a mixing output stage that depends on the algorithm's history. As a result, there is a mismatch between the behavioral policy and the optimal one. In this work, we propose a novel algorithm for constrained RL that does not suffer from these limitations. Leveraging recent results on regularized saddle-flow dynamics, we develop a novel stochastic gradient descent-ascent algorithm whose trajectories converge to the optimal policy almost surely.

关键词： computers Heuristic algorithms Reinforcement learning Approximation algorithms Extraterrestrial measurements Trajectory Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Using Pyramid Vision Transformer for Assisting Glaucoma Diagnosis with Small Datasets

Using Pyramid Vision Transformer for Assisting Glaucoma Diag...

引用

IEEE International Conference on Networking, Sensing and control

作者： Qinhao Wu Shuaiyu Yao Wendi Ouyang Jingzhe Huang Qi Kang Dept. of Mathematics and Computer Science Eindhoven University of Technology Eindhoven The Netherlands Coll. of Electronic and Information Engineering Tongji University Shanghai China Coll. of Economics and Management Nanjing University of Aeronautics and Astronautics Nanjing China Dept. of Mathematics King's College London London United Kingdom

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

Glaucoma is one of the leading causes of blindness worldwide. Patients with open-angle glaucoma have difficulty realizing the graduate vision loss. However, the optic nerve head's morphological change can manifest in the retinal image. Therefore, many studies offer computer-aided glaucoma diagnosis based on retinal image analysis. With the trend of deep learning, there have been several attempts to utilise deep-learning-based glaucoma classification in practice. However, the limited size of the dataset is a problem when adapting deep-learning models to glaucoma classification. Therefore, we test three vision transformer models to handle this problem and demonstrate their performance in glaucoma classification. Also, based on their performance, we give suggestions for their usage in clinical practice. In this paper, we fine-tuned three transformer models for glaucoma classification using two datasets, RIM-ONE_DL and Drishti-GS. Based on our experiments, the pyramid vision transformer (PVT) model achieves the best performance, with good scores in terms of accuracy and sensitivity. This suggests that the PVT can catch the missing detail and can be used to support the glaucoma diagnosis.

关键词： Glaucoma Training Adaptation models computer vision Sensitivity Computational modeling Transformers Retina Reliability Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Recent Scientific Achievements and Developments in Software Defined Networking: A Survey 1

Recent Scientific Achievements and Developments in Software ...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Bale, Ajay Sudhir Hamsalekha, R. Prakash, Bishwajeet Babu, Pidikiti Surendra Gupta, Rashmi Malik, Suraj New Hoizon College of Engineering Dept. of Ece Bengaluru India Sharda School of Law Sharda University Uttar Pradesh Greater Noida India R&d Engineer Tlc Industrial Equipments Pvt. Ltd Hyderabad India Dr. Ambedkar Institute of Management Studies and Research Maharashtra Nagpur India Iimt University Department of Computer Science and Engineering U.P Meerut India

ISBN: (纸本)9798350315769

Application devices or application programming interfaces (APIs) that are connected with the channel's core embedded system and regulate congestion is known as software-defined networking (SDN). Architecture is the primary distinction among SDN and conventional connectivity. Traditional networking is hardware-based, whereas SDN is software-based. Compared to conventional networks, SDN is far more versatile since the routing protocol is software-based. Without adding extra equipment, it enables managers to handle the connection, alter customization options, supply resources, and boost internet bandwidth from a single user interface. There are a lot of developments in SDN which have enabled networking managers to get more freedom in selecting networking hardware, Adaptable network architecture and robust protection of the network. These new trends are reviewed in this article. We are hopeful that this chapter provides future insights in the research of SDN. © 2023 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Neuro Fuzzy to Predict Cryptocurrency Based on the Crisp Method: Case of COVID-19

An Adaptive Neuro Fuzzy to Predict Cryptocurrency Based on t...

引用

Advances in Data-Driven Analytics And Intelligent Systems (ADACIS), IEEE International Conference on

作者： Hajer Chlif Dalel Kanzari Yosra Ben Said Dept. Prince Higher Institute of Computer Science and Communication Techniques of Hammam Sousse (ISITCom or Infcom) Sousse Tunisia Research Decision and Process Control Laboratory (LARODEC) Higher Institute of Management Tunisia Tunisia Tunisia Faculty of Economic Sciences and Management SFAX Tunisia

Over the past few years, there has been a notable surge in interest towards cryptocurrency, especially in the context of the crisis, where researchers have been diligently examining the influence of the coronavirus on cryptocurrency *** studies have utilized econometric and machine learning techniques to forecast cryptocurrency prices, but most of them have focused solely on the financial domain. This paper introduces a novel approach called ANFPC (Adaptive Neuro Fuzzy Prediction Cryptocurrency), which combines insights from both the financial and health domains to predict the price fluctuations of various cryptocurrencies such as bitcoin, ethereum, cardano, xpr, and dogecoin. The approach relies on the ANFIS Model, a fusion of fuzzy logic and artificial neural network (ANN).The experimental findings demonstrate that ANFPC provides accurate predictions, as measured by metrics like Mae and Mse, outperforming traditional ANN and LSTM methods. This approach proves to be a valuable decision support tool for data analysts in the realm of cryptocurrency prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pushing the Limits of Machine Translation with GPT-4 and Marian NMT in Multilingual Communication

Pushing the Limits of Machine Translation with GPT-4 and Mar...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Sourabh Jain Mohd. Sadim Hemant Amhia N. Krishna Kumar Shibanjali Choudhury P.V. Rajlakshmi Dept of Computer Science & Engineering GGITS Jabalpur M.P. India Department of Computer Science & Engineering IES Institute of Technology and Management IES University Bhopal M.P. India Electrical Engineering department Jabalpur Engineering College Jabalpur mp India Dept.of CSE Guru Nanak Institutions Technical Campus Ibrahimpatam Hyderabad Telangana India Dept. of CSE Techno College of Engineering Agartala Tripura India Department of English Kongu Engineering College Erode TN India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Machine translation (MT) plays a crucial role in enabling linguistic diversity in online interactions. In this research, we provide a unique method for expanding the capabilities of MT inside a multilingual communication framework by combining GPT-4 with Marian Neural Machine Translation (NMT). We present a complete technique comprising translation quality evaluation, contextual coherence augmentation, and translation delay optimization. The results show that our method is successful in enhancing translation quality, preserving contextual coherence, and decreasing delay. Three algorithms are used in the suggested technique. 1) Contextual Coherence Enhancement, 2) Translation Latency Optimization, and 3) Translation Quality Assessment using BLEU and METEOR ratings. The first method uses BLEU and METEOR scores to quantitatively measure translation quality, guaranteeing linguistic precision. The second method improves conversational fluency by increasing contextual coherence. The third method minimizes the time it takes to translate a sentence, facilitating simultaneous translation and conversation. We evaluated our approach by comparing it to six established MT techniques. According to the outcomes, our strategy is superior to the status quo in many respects. In particular, our approach enhanced translation quality as measured by BLEU and METEOR ratings. It also had a far greater Contextual Coherence Enhancement Factor (CEF) and Coherence Improvement Percentage, indicating that it successfully preserved the rational progressions of conversations. Furthermore, significant improvements in translation latency were also highlighted by the Latency Optimization Ratio (LOR).

关键词： Translation Neural machine translation Coherence Oral communication Particle measurements Multilingual Delays Quality assessment Meteors Optimization

来源：评论

学校读者我要写书评

暂无评论

Correlation between wearable inertial sensor data and standardised Parkinson’s disease axial impairment measures using machine learning

Correlation between wearable inertial sensor data and standa...

引用

Mediterranean Electrotechnical Conference (MELECON)

作者： Luigi Borzi’ Alessandro Manoni Alessandro Zampogna Fernanda Irrera Antonio Suppa Gabriella Olmo Dept. Control and Computer Engineering Politecnico di Torino Turin Italy Dept. Information Engineering Electronics and Telecommunication Sapienza University Rome Italy Dept. Human Neurosciences Sapienza University Rome Italy IRCCS NEUROMED Institute Pozzilli Italy

ISBN: (数字)9781665442800

ISBN: (纸本)9781665442817

Wearable sensors represent a valuable means for monitoring motion signs and symptoms of Parkinson’s disease (PD). In this paper, we explore the potential of a single inertial sensor to yield information correlated to the patient’s subjective perception of axial motion impairment during daily activities. This latter is expressed using as a relevant metric the sum of MDS-UPDRS items 2.11-2.13. Methods: thirty-one patients with PD were enrolled in this study, and asked to perform a timed-up-and-go test while wearing an inertial sensor on their thigh. Several time- and frequency-domain features were extracted from the inertial signals. They were fed to a random forest regression model for the prediction of the axial impairment metric. The model was optimized using 10-fold cross-validation and performance were assessed using leave-one-subject-out test. Results: Pearson correlation coefficient with the addressed metric of 0.76 (0.86) and mean absolute error of 1.70 (1.52) were obtained in patients under (not under) dopaminergic therapy. Moreover, moderate to strong correlations were found between the predicted score and some important disease progression, axial impairment, and motor performance metrics. Conclusion: a single wearable inertial sensor may be used for assessing motor disabilities of patients with PD.

关键词： Measurement Correlation Inertial sensors Thigh Predictive models Feature extraction Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Delivery Through IoT Applications in Remote Patient Monitoring and Telemedicine

Enhancing Healthcare Delivery Through IoT Applications in Re...

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Kottala Sri Yogi Dankan Gowda V Manoj Kumar S B R.Nithya A.Yasmine Begum Suganthi.N Department of Operations Symbiosis Institute of Business Management Hyderabad Symbiosis International University Pune India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Dept. of ECE Faculty of Engineering Management & Technology BGSIT Adichunchanagiri University Karnataka India Department of Computer Science and Engineering Vivekanandha College of Engineering for Women Namakkal Tamilnadu India Department of Electronics and Communication Engineering School of Engineering Mohan Babu University Tirupati India Department of Electrical and Electronics Engineering Dayananda Sagar College of Engineering Bangalore Karnataka India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

This paper presents how IoT plays a vital role in improving delivery of healthcare services especially through remote patient monitoring and telemedicine. The proposed system also employs IoT devices aimed at passing various health indicators like; pulse rate, blood glucose levels, blood pressure, and physical activity to continually and objectively provide real-time data in the body. This particular study, the participants with chronic diseases, normal population and elderly people also participated in the test of the system. Some of the findings include; it is possible to measure the daily steps corresponding to the a calorie expenditure, the sleep score ranging between 60-80 and oxygen saturation percentages ranging from 96%-99% in various postures. The system also proved the correlation between the percentage of variation in ambient temperature and the percentage of variation in the pulse rate which was quite sensitive to the changes in temperatures. Based on these observations, it is possible to conclude that IoT-based monitoring can improve patient’s conditions as long as underlying issues will be detected at an early stage and necessary actions will be taken in time. The study also also demonstrates the application of telemedicine in making healthcare more accessible especially for the people from rural settings or in developing countries. The results show a good direction regarding the future of the system; however, security issues, privacy relating to data as well as integration are key hurdles in this connection.

关键词： Temperature sensors Temperature measurement Patient monitoring Telemedicine Medical services Real-time systems Internet of Things Security Biomedical monitoring Older adults

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Climate Change Imaging in Geoscience Using Spatio Extreme Fuzzy Gradient Model

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 465-472页

作者： Krushnasamy, V.S. Al-Omari, Omaia Sundaram, Ajith Varghese, Issac K. Muniyandy, Elangovan Rao, M. V. A. L. Narasimha Dept. of EIE Dayananda Sagar College of Engineering Bangalore India Information Systems Department College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Amrita School of Business Amrita Vishwa Vidyapeetham Kochi India T A Pai Management Institute Manipal Academy of Higher Education Manipal India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of MBA Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur 522302 India

In order to estimate high-resolution air temperatures, computationally demanding procedures are required because climate models do not provide the resolution required for urban climate studies. Data-driven methods, on the other hand, provide air temperature downscaling that is quicker and more precise. Lidar technology has become a vital tool for researching these atmospheric components because of its capacity to measure backscattered signals and investigate the atmosphere at extremely high spatial and temporal resolution. However, machine learning has become a potent technique for sophisticated data processing and analysis because of the complexity and diversity of lidar technology. This research proposes a novel technique in urban–rural interface analysis in remote sensing by machine learning (ML) model. Here the input is collected as urban–rural landscape data and processed for noise removal as well as normalisation. Then these data features have been extracted and classified using a spatio extreme fuzzy gradient model with reinforcement Markov vector perceptron neural networks. Experimental analysis has been carried out for various geographical regions in terms of training accuracy, average precision, recall, RMSE, and F-1 score. The proposed model attained an F-1 score of 92%, training accuracy of 98%, average precision of 95%, recall of 93%, and RMSE of 55%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Lidar technology Machine learning model Reinforcement Markov vector Remote sensing Spatio extreme fuzzy gradient

来源：评论

学校读者我要写书评

暂无评论

Challenges and Opportunities in Implementing Smart City Initiatives: A Global Perspective

Challenges and Opportunities in Implementing Smart City Init...

引用

Renewable Energy Technologies and Modern Communications Systems: Future and Challenges, Conference on

作者： Nusrat Hamid Shah Saiful Adli Ismail Azizul Azizan Lubna Hamid Shah Durdana Taranum Khan Faculty of Artificial Intelligence Universiti Teknologi Malaysia Kuala Lampur Malaysia Dept. of Management and Marketting College of Business Jazan University Jazan Saudi Arabia College of Engineering and Computer Science Jazan University Jazan Saudi Arabia

ISBN: (数字)9798331519445

ISBN: (纸本)9798331519452

The concept of smart cities has gained significant traction globally as urban populations continue to grow, necessitating innovative solutions to enhance urban living. This research article explores the multifaceted challenges and opportunities associated with implementing smart city initiatives across various global contexts. Through a comprehensive review of existing studies from various regions, this research seeks to uncover common barriers- such as resource limitations, policy constraints, and public acceptance issues-that cities face when striving to integrate smart technologies. In addition, it highlights effective practices and lessons learned from cities that have pioneered smart city models, offering actionable insights that can aid urban planners, policymakers, and technologists in overcoming these obstacles. Ultimately, the findings aim to guide future research and policy directions, supporting cities in their journey to harness technology for improved urban living and sustainable development.

关键词： Renewable energy sources Smart cities Reviews Communication systems Sustainable development Faces

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Network Effects and Tokenization for Next-Gen Communication Networks in Energy Systems

AI-Driven Network Effects and Tokenization for Next-Gen Comm...

引用

Cognitive Computing in engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Mukul Singh Devesh Singh Pal Priyanka Yadav M.A. Ansari Vishwamitra Singh Vikas Beniwal School of Engineering Gautam Buddha University Gautam Budh Nagar India Dept. of Information Technology HIMT Group of Institutions Gautam Budh Nagar India Dept. of Computer Applications HIMT Group of Institutions Gautam Budh Nagar India Indian Institute of Management Kozhikode Kozhikode Kerela India UNSW Engineering University of New South Wales New South Wales Australia

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

The decentralization of energy systems, driven by rapid adoption of renewable energy sources, has posed new challenges in communication, data sharing, and energy trading. Traditional grid structures rarely cope with the fast-changing dynamics of distributed generation resources (DERs), thus demanding smarter and scalable communication networks and mechanisms of synchronizing and optimizing operations. The set of technologies on AI-driven and tokenization-like approaches practically allows for the change. AI-driven networks support this by enabling real-time decision-making and predictive analytics through smart energy distribution and demand forecasting and massively automated grid optimization. Tokenization, reinforced by blockchain technologies, allows the decentralization of energy trading through transparent peer-to-peer (P2P) transactions that ease the encumbrances of the traditional utility. The paper focuses on how AI-driven networks and tokenization integrate to form the future communication networks in energy systems. It highlights their contribution to improving grid efficiency, securing grid infrastructure, diminishing operational costs, and democratizing energy markets. Additionally, it discusses technical challenges, regulatory barriers, and long-term implications while looking ahead and thinking about how these innovations can be used to reorganize energy infrastructures all over the globe and rapidly quicken the shift to decentralized sustainable energy ecosystems.

关键词： Technological innovation Renewable energy sources Tokenization Real-time systems Communications technology Peer-to-peer computing Distributed power generation Blockchains Communication networks Predictive analytics

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：