检索结果-内蒙古大学图书馆

3D Model classification based on regnet design space and voting algorithm

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第14期83卷 42391页

作者： Gao, Xueyao Yan, Shaokang Zhang, Chunxiang Harbin Univ Sci & Technol Sch Comp Sci & Technol 52 Xuefu Rd Harbin 150080 Heilongjiang Peoples R China

3D models are widely used in industrial manufacturing, virtual reality, medical diagnosis and so on. At present, view-based 3D model classification has become an important research topic. However, single view feature can not describe the overall shape of 3D model. When multiple views are fused to describe 3D model, useful information is confused. It causes certain interference to determine 3D model's category. To solve these problems, a novel method of 3D model classification based on RegNet design space and voting algorithm is proposed. Firstly, 2D views of 3D model are input into RegNet design space with attention mechanism to extract high-level semantic feature(HSF). Secondly, HSF and the corresponding low-level shape features (LSF) of view are fused, including D1, D2, D3, Fourier descriptor, and Zernike moment. Thirdly, LSTM is combined with softmax function to extract more representative features from the fused feature. Finally, based on discriminative features, improved voting algorithm based on shannon entropy is constructed to determine 3D model's category. Experimental results show that average accuracy of the proposed method on ModelNet10 reaches 94.93%, and the classification performance is outstanding.

关键词： 3D model classification Semantic feature RegNet design space voting algorithm Shape features

来源：评论

学校读者我要写书评

暂无评论

Adaptive Tracking of Nonlinear Switched Systems with Sensor Uncertainties Based on a Weighted Average voting algorithm 19th

Adaptive Tracking of Nonlinear Switched Systems with Sensor ...

引用

19th Chinese Intelligent Systems Conference

作者： Cheng, Zhiyi Lin, Yan Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao 266510 Peoples R China

ISBN: (纸本)9789819968497;9789819968473;9789819968466

In this paper, we proposed an adaptive tracking control by output feedback based on a weighted average voting algorithm for a class of switched systems with external disturbances and sensor uncertainties. A modified weighted average voting algorithm is employed to regulate the proportion of information transmitted by sensors in different cases. By incorporating high gain scaling technique, the dynamic gain state observer and linear-like controller compose the closed-loop system are constructed, which ensures all signals are bounded and tracking errors can converge to a residual set that can be made arbitrarily small within sensor failures. Finally, a numerical simulation was given to illustrate the availability of our scheme.

关键词： Nonlinear switched systems voting algorithm Dynamic gain observer Sensor uncertainties

来源：评论

学校读者我要写书评

暂无评论

Prediction of Thermophilic Proteins Using voting algorithm 7th

Prediction of Thermophilic Proteins Using Voting Algorithm

引用

7th International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO)

作者： Li, Jing Zhu, Pengfei Zou, Quan Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Univ Elect Sci & Technol China Inst Fundamental & Frontier Sci Chengdu Peoples R China

ISBN: (纸本)9783030179380;9783030179373

Thermophilic proteins have widely used in food, medicine, tanning, and oil drilling. By analyzing the protein sequence, the superior structure and properties of the protein sequence are obtained, which is used to efficiently predict the protein species. In this paper, a voting algorithm was designed independently. Protein features and dimensions were extracted and reduced, respectively. Data was predicted by WEKA. Next, the voting algorithm was applied to the data obtained by the above processing. In this experiment, the highest accuracy rate of 93.03% was achieved. This experiment has at least two advantages: First, the voting algorithm was developed independently. Second, any optimization method was not used for this experiment, which prevents over-fitting. Therefore, voting is a very effective strategy for the thermal stability of proteins. The prediction data set used in this paper can be freely downloaded from http://***/similar to lijing/thermo ***.

关键词： Thermophilic proteins voting algorithm Feature selection Machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification by Gait using Convolutional Restricted Boltzmann Machine and voting algorithm 11

Identification by Gait using Convolutional Restricted Boltzm...

引用

IEEE International Congress on Cybermatics / IEEE Conferences on Internet of Things, Green Computing and Communications, Cyber, Physical and Social Computing, Smart Data, Blockchain, Computer and Information Technology

作者： Yu, Tao Liu, Xingang Mei, Yongyong Dai, Cheng Yan, Jingren Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Sichuan Peoples R China

ISBN: (纸本)9781538679753

Human identification by biological features has been popular in our daily life. Compared with other identification methods, human gait has specific advantages for distinguishing who is the subject. The existing gait recognition methods mainly adopt the features that designed by the hands, which is a complex feature engineering. In this paper, we propose a new gait recognition architecture based on deep learning and mathematical voting algorithm. Different with the conventional methods, the convolutional restricted Boltzmann machine (CRBM) is adopted to extract features by the unsupervised method, and the fully connected layers are employed to learn the gait feature. Meanwhile, the voting algorithm is added to the architecture by using statistical analysis algorithm to identify subjects. The experimental results show that the proposed architecture could outperform state-of-the-arts on the CASIA-B gait dataset.

关键词： Gait recognition CRBM voting algorithm human identification

来源：评论

学校读者我要写书评

暂无评论

TAMING voting algorithmS ON GPUS FOR AN EFFICIENT CONNECTED COMPONENT ANALYSIS algorithm

TAMING VOTING ALGORITHMS ON GPUS FOR AN EFFICIENT CONNECTED ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Lemaitre, Florian Hennequin, Arthur Lacassagne, Lionel Sorbonne Univ CNRS LIP6 Paris France CERN LHCb Expt Geneva Switzerland

ISBN: (纸本)9781728176055

Connected Component Analysis is vastly used as a building block for many Computer Vision algorithms from many fields like medical image processing, surveillance, or autonomous driving. It extends Connected Component Labeling by computing some features of the connected components like their bounding box or their surface. As such, Connected Component Analysis is a voting algorithm just like histogram computation or Hough transform. voting algorithms are difficult on many-core architectures like GPUs because of the serialization of atomic memory accesses. The trend to increase the number of cores makes this issue even more critical. This paper explores multiple ways to reduce those conflicts for voting algorithms and especially for Connected Component Analysis. We show that our new algorithm is from 4 up to 10 times faster than State-of-the-Art on average on an Nvidia A100.

关键词： voting algorithm Connected Component Analysis GPU Cuda Histogram

来源：评论

学校读者我要写书评

暂无评论

Soft Inference as a voting Mechanism in k-Nearest Neighbors Clustering algorithm 29th

Soft Inference as a Voting Mechanism in k-Nearest Neighbors ...

引用

29th International Conference on Information and Software Technologies (ICIST)

作者： Bury, Tomasz Kacprzak, Aleksandra Zerdzinski, Piotr Silesian Tech Univ Fac Appl Math Kaszubska 23 Gliwice Poland

ISBN: (纸本)9783031489808;9783031489815

The rapid growth of IT systems that use artificial intelligence algorithms necessitates increasingly accurate methods. To handle data uncertainty, computer scientists can employ soft sets. One popular classification method in machine learning that utilizes the idea of proximity between data points is the k-NN algorithm. In this paper, we describe a modification to the k-NN algorithm that makes use of soft sets to take into account uncertainty in the classification process. This is achieved by introducing soft inference as a voting mechanism. The authors present a mathematical model with pseudocode for re-implementation purposes and demonstrate and discuss experimental results from conducted tests to show the effectiveness of the proposed approach.

关键词： k-Nearest Neighbor (k-NN) soft sets voting algorithm

来源：评论

学校读者我要写书评

暂无评论

Expiremental validation of a fault tolerant control of induction motor using a voting algorithm 3

Expiremental validation of a fault tolerant control of induc...

引用

INTERNATIONAL CONFERENCE ON CONTROL ENGINEERING & INFORMATION TECHNOLOGY (CEIT)

作者： Gouichiche, Abdelmadjid Zabar, Mohamed Chedjara, Zakaria Safa, Ahmed Tadjine, Mohamed Univ Ibn Khaldoun Lab Genie Elect & Plasmas Tiaret Algeria Ecole Natl Polytech Lab Commandes Proc Algiers Algeria

ISBN: (纸本)9781479982134

In this paper, we describe a method for designing an active fault tolerant control system for speed sensor fault of an induction motor. The aim of this work is to develop an algorithm receiving multiple outputs from different version (sensor or observers) to choose between the most probably adequate for such situation (nominal or faulty). This algorithm is called maximum-likelihood voting (MLV) algorithm. Two adaptive observers are used (Luenberger and sliding mode observers). The proposed approach is verified by experiment results.

关键词： fault tolerant control (FTC) induction motor speed sensor failure voting algorithm observers

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis in reciprocating air compressors using ensemble voting classifier

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2025年

作者： Reddy, Suhash Sridharan, Naveen Venkatesh Sivakumar, Aravinth Vaithiyanathan, Sugumaran Vellore Inst Technol Sch Mech Engn SMEC Vandalur Kelambakkam Rd Chennai 600127 India Lulea Univ Technol Div Operat & Maintenance Engn Lulea Sweden Sri Ranganathar Inst Engn & Technol Deparment Mech Engn Coimbatore India

Reciprocating air compressors play a pivotal role in various industrial applications, demanding a steadfast focus on their dependable operation. This research addresses the challenge of fault diagnosis in reciprocating air compressors by leveraging the potential of ensemble voting classifiers. Vibration signals were captured under five compressor conditions, covering both normal operation and multiple fault scenarios, such as inlet valve fluttering, outlet valve fluttering, check valve faults, and combined inlet and outlet valve issues. A range of features, including statistical and autoregressive moving average features were extracted from the acquired vibration signals to effectively differentiate among these conditions. Feature selection was executed using the J48 algorithm to identify the most pertinent indicators. During the classification phase, an exhaustive evaluation of individual classifiers, such as K-Nearest Neighbors, J48, support vector machine, multilayer perceptron (MLP), Na & iuml;ve Bayes, logistic regression, random forest (RF), and logistic model tree, was conducted. The top-performing classifiers were subsequently selected for incorporation into ensemble voting systems. Within the ensemble voting framework, various configurations were explored, ranging from two to five classifiers, employing multiple voting strategies to optimize fault diagnosis performance. The findings of this study showcase that the combination of MLP and RF classifiers for statistical features produced the maximum classification accuracy of 98.67%.

关键词： Air compressors fault diagnosis voting algorithm J48 algorithm valve fault

来源：评论

学校读者我要写书评

暂无评论

Multi-Vehicle Tracking and Counting Framework in Average Daily Traffic Survey Using RT-DETR and ByteTrack

引用

IEEE ACCESS 2024年 12卷 121723-121737页

作者： Gladiensyah Bihanda, Yusuf Fatichah, Chastine Yuniarti, Anny Inst Teknol Sepuluh Nopember Dept Informat Surabaya 60117 Indonesia

The average daily traffic survey is essential for repairing and maintaining road sections. This method is generally conducted using a semi-manual approach that counts vehicles using CCTV. This approach is not effective or efficient because of the potential for human error. This paper have three contributions as follows. First, this paper proposes a framework by applying the RT-DETR architecture for vehicle detection and ByteTrack for vehicle tracking and counting in an average daily traffic survey. Second, this paper proposes a multi-vehicle voting algorithm to filter false identification of the same vehicle during the tracking process prior to vehicle counting. Third, to demonstrate the robustness of the proposed frameworks, we evaluated its performance using seven CCTV camera videos taken from diverse scenes during the day and night. RT-DETR Resnet 101, which is trained in an average daily traffic survey dataset, outperforms all object detection architectures with mAP@50 value of 0.992 and mAP@50-95 value of 0.891. RT-DETR Resnet101 also achieve best F1-score among all object detectors with value of 0.91. This framework using a combination of RT-DETR and ByteTrack also succeeded in counting vehicles with various video backgrounds, with an average counting accuracy value above 83% for all conditions. We compare the effect of using a multi-vehicle voting algorithm with and without showed that counting accuracy increased for each combination with an average increase value of 0.78. RT-DETR also has best performance compared to another object detection methods in detecting vehicles experiencing motion blur, especially in nighttime video scenes. In addition, ByteTrack roles in tracking vehicle objects show its robustness to handle occlusion and vehicle ID switch.

关键词： Surveys Road traffic Videos Cameras Tracking Prediction algorithms Traffic control Multi-vehicle tracking counting framework average daily traffic survey RT-DETR ByteTrack voting algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on deep learning garbage classification system based on fusion of image classification and object detection classification

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第3期20卷 4741-4759页

作者： Yang, Zhongxue Bao, Yiqin Liu, Yuan Zhao, Qiang Zheng, Hao Bao, YuLu Nanjing XiaoZhuang Univ Sch Informat Engn Nanjing 211171 Peoples R China Jinling Univ Sci & Technol Business Sch Nanjing 211199 Peoples R China Schulich Sch Business Dept Informat Syst Toronto ON Canada Nanjing RuiHuaTeng Intellectual Property Co Ltd Nanjing 211175 Peoples R China

With the development of national economy, the output of waste is also increasing. People's living standards are constantly improving, and the problem of garbage pollution is increasingly serious, which has a great impact on the environment. Garbage classification and processing has become the focus of today. This topic studies the garbage classification system based on deep learning convolutional neural network, which integrates the garbage classification and recognition methods of image classification and object detection. First, the data sets and data labels used are made, and then the garbage classification data are trained and tested through ResNet and MobileNetV2 algorithms, Three algorithms of YOLOv5 family are used to train and test garbage object data. Finally, five research results of garbage classification are merged. Through consensus voting algorithm, the recognition rate of image classification is improved to 2%. Practice has proved that the recognition rate of garbage image classification has been increased to about 98%, and it has been transplanted to the raspberry pie microcomputer to achieve ideal results.

关键词： remote upgrade load balancing genetic algorithm power monitoring terminal voting algorithm

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：