检索结果-内蒙古大学图书馆

2023 3rd international conference on Mechanical Automation and Electronic Information engineering, MAEIE 2023

作者： Huang, Zihao Huang, Kaiqi Lan, Haoqiang School of Mechanical and Electrical Engineering Jiangxi University of Science and Technology Ganzhou341000 China

To improve the vehicle's handling stability and enhance the steering assist effect of distributed drive electric vehicles, a differential assist steering control strategy is proposed based on the Particle Swarm Optimization (PSO) algorithm to optimize PID control parameters. A dynamic model of steering torque considering the influence of tire force is established, based on the reference steering torque to calculate the required torque. The PSO algorithm with the Integral of Time-weighted Absolute Error (ITAE) is used to optimize the parameters in the PID steering control, and wheel torque allocation is performed by using the objective function constraint. Simulation results show that the differential assistance can meet the driving requirements of drivers at both high and low speeds, and the proposed control strategy is effective. © Published under licence by IOP Publishing Ltd.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Metal 3D Printing using Artificial Neural Network based Seagull Optimization Algorithm 3

Optimizing Metal 3D Printing using Artificial Neural Network...

引用

3rd IEEE international conference on Distributed Computing and electrical Circuits and Electronics, ICDCECE 2024

作者： Li, Cheng Liuzhou Vocational And Technical College College Of Mechanical And Electrical Engineering Liuzhou China

ISBN: (纸本)9798350318609

The infill parameters are important according to overall saving and cost material when printing metal 3D model. The Fused Deposition Modeling (FDM) is applied in different industries to formed functional regions through polymers and metal reinforced polymer mixtures to obtain chosen properties. The Laser Powder Bed Fusion (LPBF) is complex to complete as surface roughness which is based on orientation. Hence, this research explored the finishing effects SS 316L LPBF components in different parts. The Artificial Neural Network (ANN) based Seagull Optimization Algorithm (SOA) is proposed for optimizing metal 3D printing. Moreover, the impact of critical speed at milling procedure on surface roughness SS 316L LPBF is analyzed with layer thickness and orientations of LPBF components. The printing temperature, layer height, compressive, flexural and tensile strength are considered as input and output parameters. The result exposed that machined surface suffers important orientation and layer thickness variations. The ANN-SOA achieved 0.21µ m, 0.47µm, 0.19µm, 0.38µm, 0.15µm and 0.56µm for 1-6 experiments respectively. © 2024 IEEE.

关键词： Surface roughness

来源：评论

学校读者我要写书评

暂无评论

A review of the different power system architecture at the district level and its analysis

引用

ENERGY REPORTS 2023年 9卷 1456-1462页

作者： Lang, Ren Quan, Kuang Jun, Zhang Tao, Wang Gang, Liu Bibo, Tang Hu, Luo State Grid Hunan Elect Power Co Ltd 388 Shaoshan North Rd Changsha 410000 Peoples R China State Grid Zhangjiajie Power Supply Co 53 Nanzhuang Rd Zhangjiajie 427000 Peoples R China State Grid Xiangtan Power Supply Co 399 Yunlong Middle Rd Xiangtan 411200 Xiangtan County Peoples R China State Grid Yiyang Power Supply Co 99 North Longzhou Rd Yiyang 413000 Peoples R China HNAC Technol Co Ltd 609 Lusong RdLugu Ind Pk Changsha 410000 Peoples R China

The new power system at the station level is the phased product of the large-scale and high-proportion penetration development of wind and solar new energy. The source network load storage system with the station area as the smallest adjustable unit is constructed by using energy storage +. Different from the traditional substation area system, the architecture of the new power system at the substation area level becomes extremely complex due to the change of access terminal attributes, interaction relationship and various business types. In order to systematically describe the new power system architecture at the station district level, this paper first combs and summarizes the relevant literature at home and abroad, and summarizes the literature related to the current substation District, wind and new energy access and energy storage system regulation. Secondly, from the perspectives of demand differences, common functional requirements and non functional requirements, the requirements of station area level new power system under different application scenarios are classified and analyzed in detail. Then, a new power system for different scenarios is designed, which is divided into local equipment layer, edge control layer, station management layer and centralized control layer from bottom to top, and the functions of each layer are described in detail. Taking Zhangjiajie scenery storage and charging comprehensive energy demonstration project as an example, this paper expounds the ways of terminal data access, transmission and visualization under the framework of Taiwan district level new power system, so as to provide reference for the networking of other similar projects. Finally, the research contents of this paper are summarized, and the contents that need further research in the future are prospected. (c) 2023 Published by Elsevier Ltd. This is an open access article under theCCBY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Distribution station area System architecture New power system Energy storage system Scenery new energy

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Cardiac Disease Detection and Family History Association 3

Machine Learning for Cardiac Disease Detection and Family Hi...

引用

3rd international conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Srinivas, Inumarthi V. Saritha, G. Yadav, Renu Subburam, S. Divya, K. Kj Somaiya Institute of Management Data Science and Technology Depatment Mumbai India Sri Sairam Institute of Technology Computer Science India Ies College of Technology Department of Electronics & Communication Engineering Bhopal India New Prince Shri Bhavani College of Engineering and Technology India Prince Shri Venkateshwara Padmavathy Engineering College Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350342338

As cardiac diseases continue to rise, early detection is crucial for effective treatment. Machine learning (ML) offers promising avenues for accurate diagnosis. This study explores the integration of family history, a vital risk factor, into ML-based cardiac disease detection models. By leveraging diverse patient datasets, ML algorithms are trained and validated. Incorporating family history enhances predictive accuracy. The literature review highlights the significance of genetics in disease predisposition. Model performance metrics demonstrate improved precision, recall, and overall accuracy. Interpretation of results reveals the interplay between genetics and ML. While data limitations and biases are acknowledged, the study presents implications for both clinical practice and research. This research contributes to the growing field of ML-driven medical diagnostics and underscores the importance of family history in cardiac disease prediction. © 2023 IEEE.

关键词： Clinical decision support disease prediction and machine learning genetic predisposition healthcare analytics healthcare applications patient datasets

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Intrusion Detection Mechanism for WSN Using ML 3

Comparative Analysis of Intrusion Detection Mechanism for WS...

引用

3rd international conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Vikas Sagar, B.B. Manjul, Manisha Birla Institute of Technology Computer Science & Engineering Mesra India Kanpur India Delhi Skill and Entrepreneurship University Delhi India

ISBN: (纸本)9798350342338

To protect the network system from attacks across the network, effective intrusion detection is required. Since intruders have tried to break into or abuse the system over the past 20 years, intrusion detection has become quite popular. IDS employs a variety of ways to defend computers and networks from host-based and network-based assaults. As the Internet of Things (IoT) expands, sensor nodes are utilised more frequently and are more likely to be connected to other sensor nodes that have security vulnerabilities. Hence, it is essential to utilize intrusion detection methods to prevent attacks that take advantage of vulnerabilities in sensor systems. However, conventional intrusion detection systems were ineffective in WSN situations because of the specific protocols used and the constrained capabilities of Sensor nodes. © 2023 IEEE.

关键词： Internet of Things (IoT) Intrusion Detection Systems (IDS) Wireless Sensor Networks (WSN)

来源：评论

学校读者我要写书评

暂无评论

Thrombus Segmentation in Ultrasound Deep Vein Thrombosis (DVT) Images using VGG16 and UNet based on Denoising Filters 3

Thrombus Segmentation in Ultrasound Deep Vein Thrombosis (DV...

引用

3rd IEEE international Biomedical Instrumentation and technology conference, IBITeC 2023

作者： Ramadhani, Ahmad Purnama, I Ketut Eddy Yuniarno, Eko Mulyanto Nugroho, Johanes Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Department of Electrical Engineering Department of Computer Engineering Surabaya Indonesia Airlangga University Department of Cardiology Surabaya Indonesia

ISBN: (纸本)9798350302424

Deep Vein Thrombosis (DVT) is a disease that occurs when a thrombus forms within the deep veins. This thrombus can disrupt normal blood flow and lead to severe issues if left untreated. The dataset used in this research consists of 2D ultrasound images of thrombus from 5 patients with DVT. Medical specialists used ultrasound equipment to gather and document the dataset. A medical practitioner performed the manual labeling of ultrasound thrombus images. Manual thrombus diagnosis requires a considerable amount of time, and the accuracy of thrombus image analysis relies on specialized doctors. Hence, an automatic thrombus diagnosis is needed for DVT patients to shorten the time and enhance the accuracy of thrombus image analysis. This research proposes thrombus segmentation in ultrasound images using pre-trained VGG16 and UNet model based on denoising filters. The encoder for the UNet model in this segmentation model is a pre-trained VGG16 model. In this study, five denoising filters are utilized. Based on the conducted experiments, the Gaussian filter yielded the most optimal results for thrombus segmentation with an accuracy of 99.166% and a loss value of 0.0269 for the UNet model. Furthermore, the pre-trained VGG16 and UNet model's accuracy was 99.222%, and the loss value was 0.284. Thrombus prediction tests using the UNet model resulted in a mean IoU of 77.087%, a mean Dice coefficient of 0.8608, and a mean Hausdorff distance of 3.44. Meanwhile, thrombus prediction tests using the pre-trained VGG16 and UNet model produced a mean IoU of 88.298%, a mean Dice coefficient of 0.8784, and a mean Hausdorff distance of 3.07. As a result, utilizing VGG16 as the encoder in the UNet architecture may enhance accuracy when segmenting. © 2023 IEEE.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Health Detection of High-speed Train Pantograph Based on Deep Belief Network 3

Health Detection of High-speed Train Pantograph Based on Dee...

引用

3rd international conference on Testing technology and Automation engineering, TTAE 2023

作者： Wu, Zhihe Feng, Qingsheng School of Automation and Electrical Engineering Dalian Jiaotong University Dalian116028 China

ISBN: (纸本)9781510674769

Pantograph is an important subsystem in the Pantograph-OCS system, and its health condition is related to the smooth running of high-speed train. This article, the structure of high-speed railway pantograph model is first optimized based on finite element analysis. After optimization, the average low-order vibration frequency was reduced by 7.75%, and it was concluded that the optimal pantograph sliding plate consists of four equally symmetrical structures. Then, the weak links in the pantograph structure were obtained by comprehensive static strength analysis, and acceleration sensors were arranged to collect the working status data of the pantograph. Finally, a deep belief network (DBN) is used to detect the health status of key pantograph components. The vibration signals collected by multiple sensors were segmented and extracted, and feature extracted for unsupervised DBN training. By comparing and analyzing the prediction results, an appropriate number of samples was selected to improve the diagnostic accuracy of the model to 97.87%. The experimental results show that the fully trained pantograph DBN network model can achieve high accuracy in identifying and classifying fatigue conditions. © 2024 SPIE.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Mask Detection in Security Cameras Using Deep Learning 3

Mask Detection in Security Cameras Using Deep Learning

引用

3rd international conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Kumar, Amodh Hooda, Susheela Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350342338

Mask detection in security camera surveillance is an important operation for icing public safety and security. The face masks worn by culprits for concealment during criminal acts pose major challenges for traditional surveillance systems. This paper presents a mask detection system that uses deep learning and computer vision ways to analyse live videotape feeds from security cameras for recognizing persons engaged in theft or criminal activity. The proposed system uses a pre-trained convolutional neural network to detect faces in the videotape feed and applies a binary classification model to determine whether the person is wearing a mask or not. The system can detect multiple faces in the videotape feed simultaneously and give real- time cautions when a person is wearing a mask. The proposed system provides a practical and effective result for security personnel to cover the mask-wearing people in the confined areas, thereby helping to reduce the theft rate and enhance public safety. © 2023 IEEE.

关键词： camera deep learning Detection machine learning mask security

来源：评论

学校读者我要写书评

暂无评论

Gait recognition based on GaitPart and multimodal feature fusion 3

Gait recognition based on GaitPart and multimodal feature fu...

引用

3rd international conference on Control and Intelligent Robotics, ICCIR 2023

作者： Chen, Pengpeng Hu, Chuanping School of Electrical Information Zhengzhou University Zhengzhou 450001 China School of Cyber Science and Engineering Zhengzhou University Zhengzhou 450002 China

ISBN: (纸本)9781510671867

A new multimodal feature fusion representation method is proposed to address the problem of low accuracy in gait recognition under single-modal conditions. The contour features and skeletal features are obtained using background subtraction and human pose estimator, respectively. The two types of features are fused in an embedded manner to generate contour-skeleton feature images. The resulting skeleton-contour sequences are horizontally segmented and processed individually. Finally, the extracted feature vectors are mapped to a metric space using fully connected layers. Furthermore, in the existing GaitPart algorithm, the triplet loss function is employed for distance metric learning during network training. However, it suffers from slow convergence and unstable performance. To enhance the discriminative ability of the network, we propose a joint loss function that combines the triplet loss and softmax loss during the training process. Finally, extensive experiments are conducted on the CASIA-B dataset to evaluate the effectiveness of our proposed approach. © 2023 SPIE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of Interdigitated Electrode Based Biosensor for the Detection of Leukemia 3

Design and Fabrication of Interdigitated Electrode Based Bio...

引用

3rd international conference on Emerging Techniques in Computational Intelligence, ICETCI 2023

作者： Iyer, Saachi Pawnikar, Shrirang Kalambe, Jayu Rotake, Dinesh Shri Ramdeobaba College of Engineering and Management Nagpur India Indian Institute of Technology Department of Electrical Engineering Hyderabad India

ISBN: (纸本)9798350300604

Leukemia is a cancer of the blood-forming tissues as well as the bone marrow. It occurs when there is an absurd increase in the production of white blood cells (WBCs) or the ones produced are unhealthy. Research shows that Leukemia was the 15th most frequent cause of cancer incidence and 11th most cancer-related mortality, with 311,594 deaths reported worldwide. Most deaths reported by Leukemia are due to being detected at the later stage with a very severely progressed tumor. Hence, various approaches are being used by researchers in the healthcare industry to focus on treatments that support early detection. The experimentation to detect Leukemia at an early stage was demonstrated in this paper using an Interdigitated Electrode (IDE) sensor with an attempt to not only sensitize the output to understand the severity of the situation but also to miniaturize the testing device. For this testing purpose, an (IDE) based sensor was created to input blood and measure the change in resistance on the readout circuit. The nanolayer used for the experimentation over gold IDE was Cnt-ZnO. It was observed that the difference in the resistance of an infected leukemic sample was almost three times that of healthy samples. © 2023 IEEE.

关键词： Blood

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：