检索结果-内蒙古大学图书馆

2nd IEEE international conference on advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Antony Rosewelt, L. Nivetha, E. Sakthi Priya, M. Blessy Carolin, S. Sri Sai Ram Institute of Technology Computer Science and Engineering Chennai India

ISBN: (纸本)9798350315905

Diabetic Retinopathy (DR) is a disease that is caused by long term diabetes mellitus, which causes lesions on the retina that impact vision. If it is not detected early, it could lead to blindness Deep learning algorithms have yielded encouraging results for detecting DR in retinal pictures. The goal of this research is to investigate the feasibility of employing deep convolutional neural networks (CNNs) to detect DR. The work will concentrate on training CNNs to classify different phases of DR utilising large-scale datasets of retinal pictures. The performance of different deep learning models, including ResNet and Inception, will be evaluated, and the robustness of these models to variations in image quality and disease severity will be assessed. The proposed research has the potential to contribute to the development of an accurate and efficient diagnostic tool for the early detection of DR, which can aid in preventing vision loss in diabetic patients. The findings of this research can potentially improve the clinical management of DR and provide better outcomes for patients. © 2023 IEEE.

关键词： Eye protection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetes Prediction and Management through Machine Learning: A Comparative Study 4

Enhancing Diabetes Prediction and Management through Machine...

引用

4th international conference on advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Sudha, K. Lakshmipriya, C. Pajila, P. J. Beslin Venitha, E. Anita, M. Siva Subramanian, R. R.M.D Engineering College Dept of Csbs India S.A Engineering College Dept of Cse India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept of Cse India Rajalakshmi Institute of Technology Dept of Cse Poonamalle Chennai600124 India Easwari Engineering College Dept of It India R.M.K College of Engg and Tech Dept of Cse India

ISBN: (纸本)9798350343670

Diabetes, defined as high blood sugar levels, which represents an important risk to a person's health and which may have many negative consequences if left uncontrolled. Among these risks are heart-related diseases kidney problems, hypertension, visual impairment, & potential harm to various vital organs. Rapid action and an accurate prediction are necessary for successful diabetes care. This study aims to make early diabetes prediction and increase accuracy by using machine learning techniques. Machine learning (ML) approaches provide an efficient approach for diabetes prediction by using patient information to develop models. This work predicts the onset of diabetes using ML classification techniques on a diabetes dataset. Among the techniques used in this study include KNN, RF, NB, and LR. Selecting the model with the greatest accuracy and measure of how effectively it predicts diabetes is the purpose of the study. Our experimental results show Naive Bayes works better compare to other machine learning techniques and achieves very high accuracy. The findings of this study will significantly change the diagnosis and management of diabetes. Naive Bayes have shown that selecting the best correct model makes to more effective early treatments and customized healthcare strategies. This research suggests ongoing efforts to handle diabetes by highlighting the importance of early detection as an important in reducing the long-term impact of this prominent chronic condition. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Design and Test of Tunnel-Type Naan Baking Stove 5

Design and Test of Tunnel-Type Naan Baking Stove

引用

5th international conference on Electronic engineering and Informatics, ICEEI 2023

作者： Wu, Yebei Rusuli, Aili Zhao, Dandan Li, Xuezhi Experimental Training Management Center Xinjiang Institute of Technology Xinjiang Akesu China School of Mechanical and Electrical Engineering Xinjiang Institute of Technology Xinjiang Akesu China School of Economics and Trade Xinjiang Institute of Technology Xinjiang Akesu China

ISBN: (纸本)9781643685021

In view of the problems such as high labor intensity, low processing efficiency and great potential danger during the baking process of Xinjiang Naan, an electric tunnel-type Naan baking stove was designed. By the COMSOL software, the thermal simulation of tunnel-type Naan baking stove drawn by SolidWorks was made, so as to find out the heat distribution, heat source loss position and the Naan sizes suitable for processing in Naan baking stoves. In the workshop, a baking experiment was made on the prototype in order to realize the baking of Naan. The simulation results show that the heat dissipation at the inlet and outlet of the baking oven is serious, and the large distance between the heating rods is not suitable for heating Naan. The test results show that the baking stove has good baking effect and stable baking performance under the test conditions of determining the transmission speed of 6m/s and the heating tube temperature of 260 °C by adjusting various horizontal factors and parameters, which can achieve the expected design objectives and has certain value for popularization and application. © 2024 The Authors.

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

Cyber-Attacks on Power System Frequency Control

Cyber-Attacks on Power System Frequency Control

引用

robotics, engineering, science, and technology (RESTCON), international conference on

作者： Thongchart Kerdphol Noppada Teera-Achariyakul Tossaporn Surinkaew Watcharakorn Pinthurat Department of Electrical Engineering Faculty of Engineering Kasetsart University Bangkok Thailand Department of Electrical Engineering Faculty of Engineering King Mongkut’s Institute of Technology Ladkrabang Bangkok Thailand Department of Electrical Engineering Faculty of Engineering Rajamangala University of Technology Tawan-Ok Chanthaburi Thailand

Due to the increasing number of cyber hacking activities, cyber-attacks become urgent concerns to power system security worldwide. A power system is vulnerable to cyber-attacks due to the exchanged information in its area. In this study, cyber-attacks on power system frequency control are studied by corrupting the exchange of information. Considering the frequency measurement of the system, essential attack strategies from hackers’ perspectives, which are usually concerned with cyber-attacks on critical infrastructure, have been modeled concerning the false data injection. Simulation results analyze the strengths and weaknesses of different attacks against frequency control of the system. The exogenous cyber-attacks on frequency power measurements can cause severe frequency excursions, which lead to system instability and power blackouts. Such attack methods require effective detection from defenders to guarantee system security before hackers further deteriorate the system’s stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topology Control Algorithm for Underwater Wireless Sensor Networks Facing Data Theft Problem 2

Topology Control Algorithm for Underwater Wireless Sensor Ne...

引用

2nd Asia conference on Advanced robotics, Automation, and Control engineering, ARACE 2023

作者： Yan, Tianan Zhang, Yifan You, Zhaosen Hua, Ruikai Institute of Scientific and Technical Information of China Engineering Center Beijing China Xi'an University of Finance and Economics Institute of Statistics Xi'an China University of Science and Technology of China Schools of Software Engineering Suzhou China Commercial Bank Jiangnan Rural Changzhou China

ISBN: (纸本)9798350328363

With the rapid development and increasing maturity of wireless sensor technology, a type of micro detection equipment that can work underwater has emerged, and this type of equipment has strong computing and communication capabilities, known as underwater sensor nodes. Numerous underwater sensor nodes collaborate to form an underwater sensor network through self-organization, which is mainly deployed in environments with water as the medium for monitoring, transmitting, and receiving messages. Different from traditional wireless sensor networks, underwater sensor networks are deployed in more special and complex environments. In order to improve the security of data transmission, this article proposes and verifies a topology control algorithm in underwater sensor networks aimed at reducing data theft rates, which makes node penetration follow a power-law distribution. By adjusting the node communication radius, the network achieves optimal performance. Finally, the performance of the algorithm was further verified through simulation experiments. The simulation results show that the network topology constructed by the proposed algorithm can maintain network connectivity and minimize the possibility of data being stolen by malicious nodes during transmission. © 2023 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Design of a Seven-Bar Gait Training Robot with Simulated Ankle Trajectory 2

Design of a Seven-Bar Gait Training Robot with Simulated Ank...

引用

2nd international conference on Intelligent Equipment and Special Robots, ICIESR 2023

作者： Shi, Kan Yuan, Huanzhi Wang, Ju Yao, Yanan College of Mechanical and Electronic Engineering Shandong University of Science and Technology Qingdao266590 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781643685144

In this paper, a seven-bar mechanism gait training robot was introduced. The core mechanism of the robot is designed as two sets of seven bar mechanisms with two degrees of freedom. An appropriate reference system is established and the model of the equipment is designed. The kinematics of the mechanism is analyzed, the conditions for determining the motion of the mechanism are analyzed. Subsequently, standard algorithm was used to optimize the end trajectory of the linkage mechanism. According to the results obtained and the principles of human factors engineering, the motion characteristics of the robot were analyzed using Adams software. The simulation results show that the proposed seven bar mechanism gait training robot has a terminal trajectory close to the walking trajectory of the human ankle joint, and can complete gait assistance training tasks. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Studies Conducting Concurrent Diagnosis of Bearings via Swin Transformer and VGG SENet 5

Studies Conducting Concurrent Diagnosis of Bearings via Swin...

引用

5th international conference on advances in Electrical engineering and Computer Applications, AEECA 2024

作者： Gong, Yi Gong, Ruyue Qingdao University of Science and Technology School of Information Science and Technology Qingdao China Neusoft Institute Guangdong School of Computing Foshan China

ISBN: (纸本)9798350355253

As the manufacturing sector undergoes profound changes, more and more large-scale mechanical equipment has been introduced into production and life, and unpredictable motor failures may lead to shutdowns, accidents, and economic losses. Bearings are an important component of motors, and conducting research to diagnose faults in them is of immense importance. Traditional motor diagnosis methods mainly rely on manually extracting features, which require a large amount of professional knowledge and expert experience, consume a lot of human and material resources, and have extremely low efficiency. Aiming at the above problems, a method for diagnosing motor bearing faults, which concurrently utilizes Swin-Transformer and VGG-SENet as a base, is suggested by integrating the Swin Transformer framework. First, fault signals' multi-scale characteristics are derived through the application of fast Fourier transformation and variational mode decomposition techniques. Subsequently, an enhanced convolutional pooling network is employed to learn the global features of the signals, and the local features of the fault signals are extracted based on the Swin Transformer model using the window attention mechanism. Ultimately, the integration of local attributes post-adaptive average pooling with global spatial attributes enhances the model's efficiency and its capacity to generalize. The experimental findings, in contrast to current models, reveal clear enhancements in classification accuracy, precision, recall, and F-value for the model introduced in this study. © 2024 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-branch Distribution Network Fault Localization Method Based on the Combination of Single and Double-ended Traveling Wave 5

Multi-branch Distribution Network Fault Localization Method ...

引用

5th international conference on advances in Electrical engineering and Computer Applications, AEECA 2024

作者： Tan, Weibin Xu, Guang Tian, Weiwei Zhang, Xiangxing Qi, Ang Huang, Xinyue Zhuhai XJ Electric Co. Ltd. Zhuhai China Shandong University of Science and Technology College of Electrical Engineering and Automation Qingdao China

ISBN: (纸本)9798350355253

To address the issue of low wavefront calibration accuracy in traveling wave fault location methods for multi-branch distribution networks, a technique for finding faults based on the combination of single and double-ended traveling wave methods is proposed. First, an analysis is conducted on the feeder lines of the distribution network's traveling wave transmitting properties. Based on the arrival time and polarity of the wavefront, traveling wave filtering conditions are constructed to obtain effective information on subsequent fault wavefronts. The location of the fault spot on the branch line is inferred from the effective information of multiple subsequent wavefronts in single-ended measurement data. The fault spot on the primary line is inferred based on the time difference of the first traveling wavefront between double-ended measurements. Thus, under the premise of configuring measurement terminals for branch lines, fault location in a distribution network with several branches is achieved. To address the difficulty in identifying subsequent wavefront, a fault location method according to the blend of single and double-ended traveling wave methods is proposed. Analysis is done on the traveling wave transmission properties in the distribution network's branch lines. Based on the arrival time and polarity of the wavefront, traveling wave filtering conditions are constructed to identify segments of traveling waves containing effective information, thus inferring the location of the fault spot on the branch line. Finally, the suggested approach is tested and a distribution network simulation system with several branches is constructed using MATLAB/SIMULINK simulation software. The suggested approach has high fault location accuracy and can calibrate the wavefront with effectiveness, according to simulation results. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Weapon Detection System for the Prevention of any Potential Crime Using Artificial Intelligence 5

Weapon Detection System for the Prevention of any Potential ...

引用

5th IEEE international conference on advances in Computing, Communication Control and Networking, ICAC3N 2023

作者： Tabassum, Husna Najmusher, H. Anjum, Ayesha Jenita, J. Humera, D. Viji, C. Hkbk College Of Engineering Computer Science & Engineering Bangalore India Jain University Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350330861

To ensure the protection and security of the general public, infrastructure elements like security cameras and video monitoring systems are essential. Due to the rising demand for safety and security, video surveillance systems that can recognize and understand the scene and transmit the appropriate response are required. This idea was proposed because it is time-consuming to physically locate dangerous objects. This enables us to locate any potentially harmful weapons and alert the relevant authorities so they can take the appropriate action. This research aims to develop a low-cost, efficient, AI-based method for recognizing weapons in surveillance videos in real-time and in different environments. The system is verified and makes use of Tensor Flow technology. Two different dataset types are used in this application. In one dataset, the pictures are already labeled, while in the other, the labels were added by hand. This is applicable everywhere in the globe. © 2023 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

BEVUDA++: Geometric-Aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 5109-5122页

作者： Zhang, Rongyu Liu, Jiaming Li, Xiaoqi Chi, Xiaowei Wang, Dan Du, Li Du, Yuan Zhang, Shanghang Nanjing University School of Electronic Science and Engineering Nanjing210093 China The Hong Kong Polytechnic University Department of Computing Hung Hom Hong Kong Peking University National Key Laboratory for Multimedia Information Processing School of Computer Science Beijing100871 China The Hong Kong University of Science and Technology Academy of Interdisciplinary Studies Hung Hom Hong Kong

Vision-centric Bird’s Eye View (BEV) perception holds considerable promise for autonomous driving. Recent studies have prioritized efficiency or accuracy enhancements, yet the issue of domain shift has been overlooked, leading to substantial performance degradation upon transfer. We identify major domain gaps in real-world cross-domain scenarios and initiate the first effort to address the Domain Adaptation (DA) challenge in multi-view 3D object detection for BEV perception. Given the complexity of BEV perception approaches with their multiple components, domain shift accumulation across multi-geometric spaces (e.g., 2D, 3D Voxel, BEV) poses a significant challenge for BEV domain adaptation. In this paper, we introduce an innovative geometric-aware teacher-student framework, BEVUDA++, to diminish this issue, comprising a Reliable Depth Teacher (RDT) and a Geometric Consistent Student (GCS) model. Specifically, RDT effectively blends target LiDAR with dependable depth predictions to generate depth-aware information based on uncertainty estimation, enhancing the extraction of Voxel and BEV features that are essential for understanding the target domain. To collaboratively reduce the domain shift, GCS maps features from multiple spaces into a unified geometric embedding space, thereby narrowing the gap in data distribution between the two domains. Additionally, we introduce a novel Uncertainty-guided Exponential Moving Average (UEMA) to further reduce error accumulation due to domain shifts informed by previously obtained uncertainty guidance. To demonstrate the superiority of our proposed method, we execute comprehensive experiments in four cross-domain scenarios, securing state-of-the-art performance in BEV 3D object detection tasks, e.g., 12.9% NDS and 9.5% mAP enhancement on Day-Night adaptation. © 1991-2012 IEEE.

关键词： Teaching

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：