2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)最新文献_第8页

Multi-objective spare parts supply network optimization : model formulation and optimal decision-making 多目标备件供应网络优化:模型制定与最优决策

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00031

Yurong Guo, Q. Shi

引用次数: 0

Direct Torque Control of Five-phase Permanent Magnet Synchronous Motor Based on Model Prediction 基于模型预测的五相永磁同步电机直接转矩控制

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00029

Yifei Qin, Aiyuan Wang

引用次数: 0

Research on Image Processing Technology Used for Root Neck Location of Shrubs 灌木根颈定位的图像处理技术研究

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00051

Dingzhong Tan, Chenggong Ji, Chenxi Guan, Yuying Wang, Chao Jiang

{"title":"Research on Image Processing Technology Used for Root Neck Location of Shrubs","authors":"Dingzhong Tan, Chenggong Ji, Chenxi Guan, Yuying Wang, Chao Jiang","doi":"10.1109/MLISE54096.2021.00051","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00051","url":null,"abstract":"By cutting off all the upper branches from the neck of the roots of the shrub, a straight, strong trunk can be created again. In this paper, an active vision system based on line structured light is designed to locate the root neck of shrub. The traditional binarization method has been improved to eliminate the influence of light intensity; the weighted average method is used to gray-scale the image, and the gray-scale image is processed with histogram equalization, and the processed image details are more clear. Using median filter to denoise the gray image, eliminate the noise while retaining the details of the image. The Ostu method is used to segment the image, and the optimal threshold is determined; the small area method is used to process the background noise and “false branches” of the segmented image, and the region of interest is preserved to the greatest extent while denoising. The expansion algorithm and the erosion algorithm are used to obtain the true boundary information of the image target area, and the morphologically processed image is superimposed with the auxiliary positioning image to filter out noise points. The skeleton thinning algorithm is used to refine the spot image, eliminate discrete points and fill in discontinuous points at the same time, and obtain a single-pixel coordinate laser fringe binary image. Based on the triangular distance measurement principle, the coordinates of the root neck of the bush are calculated.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128203054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigation on the influences of comprehensive errors of alignment on the contact characteristic of small-module spiral bevel gear 对中综合误差对小模数螺旋锥齿轮接触特性影响的研究

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00052

M. Xia, Chaosheng Song, Yan Wang, Qiyong Yang

引用次数: 0

Research on Knowledge Consensus Mechanism of Network Learning Space Based on Block Chain 基于区块链的网络学习空间知识共识机制研究

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00072

Yingying Wei, Lu Liu

引用次数: 0

A Defect Detection Network Based on An Improved Receptive Field Block 基于改进接受域块的缺陷检测网络

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00024

Yangsai Wang, Yulong Zhuang, Yongqi Han

引用次数: 0

Using Hidden Markov Model to Predict the Potential Intent of User's Gaze Behavior 利用隐马尔可夫模型预测用户注视行为的潜在意图

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00015

Guogang, Gaozheng, Wushiqian, Yumin

引用次数: 1

Prediction model of tumor marker examination based on fusion of CNN and bilstm 基于CNN与bilstm融合的肿瘤标志物检测预测模型

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00016

Manfu Ma, Wenxia Wang, Hai Jia, Xia Wang, Yong Li, Shaoyao Zhang

{"title":"Prediction model of tumor marker examination based on fusion of CNN and bilstm","authors":"Manfu Ma, Wenxia Wang, Hai Jia, Xia Wang, Yong Li, Shaoyao Zhang","doi":"10.1109/MLISE54096.2021.00016","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00016","url":null,"abstract":"CNN can efficiently learn the local features of electronic medical record (EMR), ignoring the relevance between context semantics; The BiLSTM is the opposite. To solve this problem, this paper introduces attention mechanism and multilayer perceptron, combining CNN algorithm with BiLSTM algorithm. The attention mechanism is used to extract key information of electronic medical records, and the multi-layer perceptron splits local features learned by CNN, contextual semantic features learned by BiLSTM and key EMR features extracted by attention mechanism. This paper proposes a model of CNN-attention-BiLSTM for tumor marker detection prediction. It can be used in tumor marker detection and prediction. The experiment showed that compared with the model without attention mechanism and multilayer perceptron, the accuracy rate, recall rate and F1 value increased by 6.87%, 4.42% and 5.06% respectively. In this paper, this model is compared with traditional machine learning classification algorithms. Experimental results show that the accuracy of this model is 7.77% higher than that of Naive Bayes, which has the best classification effect, and 17.97% higher than that of SVM, which has the worst classification effect. Through experimental comparison, it can be concluded that the model proposed in this paper can better help doctors to assist decision-making to a certain extent.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114809364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prioritized Experience Replay Method Based on Experience Reward 基于经验奖励的优先体验重播方法

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00045

Jiashan Gao, Xiaohui Li, Weihui Liu, Jingchao Zhao

{"title":"Prioritized Experience Replay Method Based on Experience Reward","authors":"Jiashan Gao, Xiaohui Li, Weihui Liu, Jingchao Zhao","doi":"10.1109/MLISE54096.2021.00045","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00045","url":null,"abstract":"In recent years, artificial intelligence has been widely used in modern construction, and reinforcement learning methods have played an important role in it. The experience replay method is an important means to enable the reinforcement learning method to be widely used in real tasks. In order to improve the efficiency of the experience replay method, this article improves the traditional experience replay method and combines the past experience reward value with the timing difference error (TD error) to form a R- T experience prioritized parameter. Based on the data priority, we use R- T experience prioritized parameter as a standard to update and storage the memory pool data method. The improvement is used to form an improved experience replay method based on experience data priority. This paper applies the improved experience replay method to DDPG (Deep Deterministic Policy Gradient) algorithm and conducts simulation experiments. As a result, the improved experience replay method verified by experiments has a good effect on improving the efficiency of algorithm training and the stability of the algorithm training process.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125996638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Research on Device-to-Device Communication Resource Allocation Algorithm in Cellular Network 蜂窝网络中设备间通信资源分配算法研究

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00077

Yujie Chen, Caihong Ma

引用次数: 0