检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 148-160页

作者： Pan, Zhaoqing Yuan, Feng Wang, Xu Xu, Long Shao, Xiao Kwong, Sam the School of Electrical and Information Engineering Tianjin University Tianjin300072 China the College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China the Key Laboratory of Solar Activity National Astronomical Observatories Chinese Academy of Sciences Beijing100012 China the School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China the Department of Computer Science City University of Hong Kong Hong Kong

No-reference image quality assessment (NR-IQA) aims to evaluate image quality without using the original reference images. Since the early NR-IQA methods based on distortion types were only applicable to specific distortion scenarios, and lack of practicality, it is challenging to designing a universal NR-IQA method. In this article, a multibranch convolutional neural network (MB-CNN) based NR-IQA method is proposed, which includes a spatial-domain feature extractor, a gradient-domain feature extractor, and a weight mechanism. The spatial-domain feature extractor aims to extract the distortion features from the spatial domain. The gradient-domain feature extractor is used to guide the spatial-domain feature extractor to pay more attention to the distortions of the structure information. Particularly, the spatial-domain feature extractor uses the hierarchical feature merge module to realize multiscale feature representation, and the gradient-domain feature extractor uses pyramidal convolution to extract the multiscale structure information of the distorted image. In addition, a position vector is proposed to build the weight mechanism by considering the position relationships between patches and its entire image for improving the final prediction performance. We conduct the experiments on five representative databases: LIVE, TID2013, CSIQ, LIVE MD and Waterloo Exploration Database, and the experimental results show that the proposed NR-IQA method achieves the state-of-the-art performance, which demonstrate the effectiveness of our proposed NR-IQA method. The code ofthe proposed MB-CNN will be released at https://***/NUIST-Videocoding/MB-CNN. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Gradient Boosted Energy Optimization Model(GBEOM)for MANET

引用

computer Systems science & engineering 2023年第7期46卷 637-657页

作者： Neenavath Veeraiah Youseef Alotaibi Saleh Alghamdi Satish Thatavarti Department of Electronics and Communications DVR&DHS MIC Engineering CollegeKanchikacharlaA.P521180India Department of Computer Science College of Computers and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramA.P522502India

Mobile Ad Hoc Network(MANET)is an infrastructure-less network that is comprised of a set of nodes that move *** MANET,the overall performance is improved through multipath multicast routing to achieve the quality of service(quality of service).In this,different nodes are involved in the information data collection and transmission to the destination nodes in the *** different nodes are combined and presented to achieve energy-efficient data transmission and classification of the *** route identification and routing are established based on the data broadcast by the network *** transmitting the data packet,evaluating the data delivery ratio is necessary to achieve optimal data transmission in the ***,energy consumption and overhead are considered essential factors for the effective data transmission rate and better data delivery *** this paper,a Gradient-Based Energy Optimization model(GBEOM)for the route in MANET is proposed to achieve an improved data delivery ***,the Weighted Multi-objective Cluster-based Spider Monkey Load Balancing(WMC-SMLB)technique is utilized for obtaining energy efficiency and load balancing *** WMC algorithm is applied to perform an efficient node clustering process from the considered mobile nodes in *** balancing efficiency is improved with a higher data delivery ratio and minimum routing overhead based on the residual energy and bandwidth ***,the Gradient Boosted Multinomial ID3 Classification algorithm is applied to improve the performance of multipath multicast routing in MANET with minimal energy consumption and higher load balancing *** proposed GBEOM exhibits∼4%improved performance in MANET routing.

关键词： Manet routing load balancing clustering gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Progress in Artificial Intelligence Applications Based on the Combination of Self-Driven Sensors and Deep Learning 4

Progress in Artificial Intelligence Applications Based on th...

引用

4th International Conference on Consumer Electronics and computer engineering, ICCECE 2024

作者： Wan, Weixiang Sun, Wenjian Zeng, Qiang Pan, Linying Xu, Jingyu University of Electronic Science and Technology of China Electronics & Communication Engineering Chengdu China Yantai University Electronic and Information Engineering Shandong Yantai China Zhejiang University Computer Technology Zhejiang Hangzhou China Trine University Information Studies PhoenixAZ United States Northem Arizona University Computer Information Technology FlagstaffAZ United States

ISBN: (纸本)9798350384062

In the era of the Internet of Things, developing a smart sensor system with sustainable power supply, easy deployment, and flexible use has become a challenging problem. Traditional power supplies, prone to frequent replacements or requiring charging during usage, hinder the advancement of wearable devices. The contact-to-separate friction nanogenerator (TEN G), composed of polychotomy ethylene (PTFE) and aluminum (AI) foils, addresses this issue by harvesting human motion energy through body movement arrangement. This energy is then utilized to monitor human motion posture by detecting changes in output electrical signals. In 2012, Academician Wang Zhonglin and his team invented the triboelectric nanogenerator (TENG), which operates as a self-driven sensor primarily powered by Maxwell displacement current. This enables direct conversion of mechanical stimulation into electrical signals during action, making it suitable for self-powered sensor applications. TENG-based sensors boast a simple structure and high instantaneous power density, providing a crucial tool for constructing intelligent sensor systems. Additionally, when combined with machine learning characteristics such as low cost, short development cycles, robust data processing, and predictive capabilities, the processing of the numerous electrical signals generated by TENG has a significant impact. The integration of TENG sensors is poised to drive the rapid evolution of intelligent sensor networks in various fields such as transportation, security, water conservancy, and construction, where urban sound management is essential. The method of seamlessly integrating sensors with Internet access is implemented using the NetBox network development platform, following these steps: 1) Initially, read the default parameter settings from pre-existing storage media, including parameters like IP address, subnet code, gateway address, sensor input and output types, and sensor range. These settings can be modified onl

关键词： Ethylene

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive rolling motion for snake robots in unstructured environments based on torque control

引用

Biomimetic Intelligence & Robotics 2023年第3期3卷 59-66页

作者： Shihao Ma Fatao Qin Shufan Chen Longchuan Li Jianming Wang Zengzeng Wang Shuai Li Xuan Xiao School of Electronic and Information Engineering Tiangong UniversityTianjin 300382China College of Mechanical and Electrical Engineering Beijing University of Chemical TechnologyBeijing 100029China College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin 300382China School of Computer Science and Technology Tiangong UniversityTianjin 300382China

Snake robots have great potential for exploring and operating in challenging unstructured environments,such as rubble,caves,and narrow ***,due to the complexity and unpredictability of unstructured environments,designing a controller that can achieve adaptive motion is *** paper proposes a self-adaptive torque-based rolling controller for snake robots,enabling compliant motion in unstructured ***,a controller is designed to modify the torque of each motor by focusing on the different motion states of the rolling ***,an experimental platform is established for snake robots to verify the effectiveness of the ***,a series of rolling experiments are conducted using the torque-based rolling *** conclusion,the self-adaptive torque-based rolling controller enhances snake robot adaptability and mobility.

关键词： Snake robot Torque-based control Self-adaptive rolling gait Unstructured environments

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning to Develop an Improved Real-Time Data Analysis System 3

Utilizing Machine Learning to Develop an Improved Real-Time ...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Khandari, Harsimrat Sahoo, Girija Shankar Raja Praveen, K.N. Shree, Ritu Umamaheswari, B. Yashwant, V. Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350319125

With the constantly growing volume of facts being produced, conventional data evaluation structures are regularly insufficient in terms of presenting an correct overview of the most modern-day data. The utilization of system mastering provides the potential to create an improved real-time records evaluation device this is more able to making experience of and knowledge the records. The development of an progressed actual-time statistics evaluation device utilizing system studying can hugely enhance statistics analysis techniques by means of integrating relevant data and structured analyses of the identical. this will include strategies inclusive of natural language processing and clustering algorithms to perceive trends, sentiment evaluation to understand customer feedback, and predictive analytics to better perceive areas for improvement. Moreover, the realtime statistics analysis system can be further enhanced by means of incorporating AI to make extra correct predictions, as well as reinforcement studying to evolve present models as new statistics is integrated. this would allow the system to learn more efficaciously and modify its algorithms to continually enhance its overall performance. Universal, by using machine studying to develop an advanced actual-time statistics evaluation system, extra correct and comprehensive insights can be generated from information, and groups can use this facts to better tell their choice making. moreover, temporal records evaluation can be advanced with faster response times as a result of the device being able to process records © 2023 IEEE.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Temperature Management Using Smart Thermostat in Cyber Physical Systems

Temperature Management Using Smart Thermostat in Cyber Physi...

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Thakur, Payal Sehgal, Vivek Kumar Computer Science and Engineering Jaypee University of Information Technology India

ISBN: (纸本)9781665458832

With technological advancement, the role of technology to make homes smart has increased. The prime aim is to achieve the occupant's comfort. Thus, the demand for temperature control has significantly increased. By using a heater and taking into account the external factors affecting the temperature, the temperature in a room can be controlled while considering energy efficiency. In this paper, the cyber-physical system approach is used to propose a thermal controller for the room. By considering the heater, curtain, and window, the suggested controller can achieve the required temperature along with attaining energy efficiency. The proposed temperature control system for the room is modeled and evaluated using Simulink. © 2022 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Deep Learning - Based Prediction Models for Colon and Rectum Cancer Disease: Enhancing the Precision Diagnosis

Deep Learning - Based Prediction Models for Colon and Rectum...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Suman, Sunil Kumar Kumaraswamy, D. Sahu, Sunil Kumar Akella, Prasanna Lakshmi Santhoshkumar, S.P. Karthika, R. Supaul College of Engineering Department of Computer Science and Engineering Supaul India Ellenki College of Engineering and Technology Telangana Sangareddy India Hyderabad India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India School of Computing Department of Information Technology Rathinam Technical Campus Coimbatore India

ISBN: (纸本)9798331538538

Colon and rectal cancer are among the leading causes of cancer-related illness and death worldwide. The detection and treatment of colon cancer are viewed as social and economic issues due to the high fatality rates. Every year, around half a million people worldwide develop cancer, including colon cancer. Although improving patient outcomes requires an accurate and timely diagnosis, traditional diagnostic methods usually suffer from subjectivity and variability problems. An extensive summary of colon cancer diagnosis is given here. Deep learning, a branch of artificial intelligence, has become a powerful tool for increasing cancer detection accuracy by utilizing large datasets and complex algorithms. This study combines genomic data, medical imaging, histopathological analysis, and clinical decision-making tools to better comprehend the creation and application of deep learning-based prediction models in the diagnosis of colon and rectal cancer. Through the use of Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and hybrid models, deep learning can improve the accuracy of cancer detection, anticipate the course of a disease, and assist with customized treatment planning. By automating and enhancing diagnostic precision, these models have the potential to revolutionize healthcare workflows, reduce diagnostic errors, and ultimately increase patient survival rates. This research also discusses the challenges and possible advantages of using deep learning to clinical practice for colon and rectal cancer. Last but not least, the problems that exist today and possible directions for future research are examined. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

AIoTtalk: A SIP-Based Service Platform for Heterogeneous Artificial Intelligence of Things Applications

引用

IEEE Internet of Things Journal 2023年第16期10卷 14167-14181页

作者： Yang, Shun-Ren Lin, Yi-Chun Lin, Phone Fang, Yuguang National Tsing Hua University Department of Computer Science The Institute of Communications Engineering Hsinchu30013 Taiwan Taiwan Semiconductor Manufacturing Corporation Design & Technology Platform Hsinchu300096 Taiwan National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

Recently, several Internet of Things (IoT) service platforms have been proposed to facilitate IoT application deployment. These platforms typically utilize the lightweight MQTT or CoAP application protocol, optimized for massive IoT applications. Unfortunately, these protocols are not suitable for the emerging, more sophisticated Artificial Intelligence of Things (AIoT). Session initiation protocol (SIP), in contrast, is a signaling and controlling protocol for real-time multimedia sessions, and has been viewed as a better candidate to provide a full range support of different broadband, critical, and industrial AIoT applications. However, there exists no generic SIP-based AIoT service platform that supports creations and operations of heterogeneous AIoT applications with various quality of service. This article presents the first SIP-based AIoT service platform, AIoTtalk, that enables rapid development of scalar and multimedia AIoT applications. Moreover, we deploy an experimental testbed and two real SIP-based AIoT applications to demonstrate the applicability and the performance of our AIoTtalk under both the cloud and edge scenarios. The experimental results show that, together with accurate model predictions and edge-virtualization auto scaling, AIoTtalk guarantees low latency and high quality of experience for messaging and streaming-based AIoT applications. © 2014 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Analytical Method for Optical Waveguide Design in Communication Systems

Analytical Method for Optical Waveguide Design in Communicat...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Kavitha, R. Bhambu, Pawan Mishra, Awakash Computer Science Engineering Department Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineeing & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350357769

The goal of this study is to provide an analytical framework, reinforced by numerical insights, to facilitate the design of optical slab waveguides for use in optical networks of communication. This paper presents the detailed design of an optically slab waveguide structure made of silicon-on-silicon dioxide and the detailed analysis that followed. The main feature being studied is the mode's effective index, together with a careful analysis of its response to changes in the waveguide's size. Through an investigation of the interactions among effective index, waveguide measurements, and wavelength, this work offers a sophisticated comprehension of the nuances controlling the behavior of optical slab waveguides. A crucial aspect of the research is examining waveguide bending loss, paying close attention to changes in waveguide length and thickness. Three distinct waveguide transmission windows are used for this inquiry, with the wavelengths of 850 nm, 1300 nm, and 1550 nm being the main targets. The analysis's conclusions provide insightful information on how waveguide shape affects bending losses inside these gearbox windows, which is essential knowledge for maximizing the effectiveness of optical slab the waveguides in real-world applications. © 2023 IEEE.

关键词： Analytical Method Communication Systems Effective Index Numerical Insights Optical Slab Waveguides Optical Waveguide Design Silicon-On-Silicon Dioxide Waveguide Measurements Wavelength and Bending Loss

来源：评论

学校读者我要写书评

暂无评论

Identification of cyber attacks using machine learning in smart IoT networks

引用

Materials Today: Proceedings 2023年 80卷 2518-2523页

作者： Malathi, C. Padmaja, I. Naga Department of Computer Science Sri Padmavathi Mahila Visvavidyalayam AP Tirupati India Department of Information Technology RVR&JC College of Engineering Chowdavaram AP Guntur India

The Internet of Things (IoT) combines billions of physical objects that can communicate with each device without minimal human interaction. IoT has grown to be one of the most popular technologies and an attractive field of interest in the business world. The demand and usage of IoT are expanding rapidly. Several organizations are funding in this domain for their business use and giving it as a service for other organizations. The result of IoT development is the rise of different security difficulties to both organizations and buyers. Cyber Security gives excellent services to preserve internet privacy and business interventions such as disguising communication intrusions, denial of service interventions, blocked, and unauthorized real-time communication. Performing safety measures, such as authentication, encryption, network protection, access power, and application protection to IoT devices and their natural vulnerabilities are less effective. Therefore, security should improve to protect the IoT ecosystem efficiently. Machine Learning algorithms are proposed to secure the data from cyber security risks. Machine-learning algorithms that can apply in different ways to limit and identify the outbreaks and security gaps in networks. The main goal of this article ability to understand the efficiency of machine learning (ML) algorithms in opposing Network-related cyber security Assault, with a focus on Denial of Service (DoS) attacks. We also address the difficulties that require to be discussed to implement these Machine Learning (ML) security schemes in practical physical object (IoT) systems. In this research, our main aim is to provide security by multiple machine-learning (ML) algorithms that are mostly used to recognise the interrelated (IoT) network Assault immediately. Unique metadata, Bot-IoT, is accustomed to estimate different recognition algorithms. In this execution stage, several kinds of Machine-Learning (ML) algorithms were handled and mostly reached e

关键词： Metadata

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：