2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)最新文献

Model Study of Segment Market on Internet of Vehicles Big Data 基于车联网大数据的细分市场模型研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00096

Huajun Wang, Liang Yang, Wenbin Wang, Xiaolin Zhang

引用次数: 0

TsRss: A Practical Stream data Cleaning Method based on Local Shape Feature 一种实用的基于局部形状特征的流数据清洗方法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00137

Changyong Yu, Peng Liu, Yudi Liu, Haitao Ma, Yuhai Zhao

{"title":"TsRss: A Practical Stream data Cleaning Method based on Local Shape Feature","authors":"Changyong Yu, Peng Liu, Yudi Liu, Haitao Ma, Yuhai Zhao","doi":"10.1109/CACML55074.2022.00137","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00137","url":null,"abstract":"Stream data which is common usually suffers from dirty data points due to noise interference, unreliable sensor reading, erroneous extraction of stock prices or other various reasons. Existing smoothing filter based data cleaning methods seriously alter the data without preserving the original information. And the others such as SCREEN need to be guided by some semantic constraints in specific application scenarios. To improve the usability, we propose a method called TsRss, which is a practical stream data cleaning method based on local shape feature (Shape-Sheet). TsRss is based on the basic idea that data points failing to match its local shape features are more likely to be dirty. To this end, we first study the methods of generating and representing unequal-length Shape-Sheets based on the local shape features. Then the method for finding dirty data via anomaly detection is proposed based on Shape-Sheet. Finally, experiments were conducted on several real datasets. The result showed that TsRss was more practical in use on various types of data, more accurate or more time-saving compared with state-of-the-art methods.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129322626","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

An interpretable Neural Network and Its Application in Inferring Inter-well Connectivity 可解释神经网络及其在井间连通性推断中的应用

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00089

Huaqing Zhang, Yunqi Jiang, Jian Wang, Kaixiang Zhang, N. Pal

{"title":"An interpretable Neural Network and Its Application in Inferring Inter-well Connectivity","authors":"Huaqing Zhang, Yunqi Jiang, Jian Wang, Kaixiang Zhang, N. Pal","doi":"10.1109/CACML55074.2022.00089","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00089","url":null,"abstract":"The demand for understandable and accountable machine learning models is becoming more and more important with time. In this paper, we propose a sparsity-based inter-pretable neural network model and a constrained interpretable neural network model. Both of them are simple and easier to interpret, providing more accurate and comprehensive overview of the relationships between the inputs and the outputs of the network model. We use some effective evaluation measures to assess the contribution from each input to each output. Clear interpretations of the learned models are revealed, along with intuitive heat-maps for visualization of the connection weights. Furthermore, the proposed methods are applied to infer the inter-well connectivity between the injectors and the producers in reservoir engineering. After training the networks by water injection rate and liquid production rate data, the reservoir connectivity is efficiently characterized with dynamic parameters. To our knowledge, this is the first time to emphasize on special interpretable neural networks to handle this problem. The empirical results demonstrate the effectiveness of the proposed methods and validate their interpretations.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124632060","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

Attacking Random Forest Classifiers based on Shortest Path Algorithm 基于最短路径算法的随机森林分类器攻击

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00039

Tianjian Wang, Fuyong Zhang

引用次数: 0

Color image enhancement algorithm based on improved Retinex algorithm 基于改进Retinex算法的彩色图像增强算法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00046

Yuhang Gao, Chuhao Su, Zhaoheng Xu

{"title":"Color image enhancement algorithm based on improved Retinex algorithm","authors":"Yuhang Gao, Chuhao Su, Zhaoheng Xu","doi":"10.1109/CACML55074.2022.00046","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00046","url":null,"abstract":"In order to solve the problem of low expressiveness caused by color distortion and poor saturation when performing image enhancement with classic Retinex algorithm, this paper proposes a color image enhancement algorithm base on the improved Retinex algorithm. In this algorithm, the input image is decomposed into illumination component and reflection component base on Retinex theory first, then logarithmic transfor-mation and Gaussian filtering are performed on the illumination component of HSV color space to approximate the visual system's perception intensity to physical reflectance. Next, the estimated illumination value of scene is used to adjust the multi-scale reflection components of the input image, and to obtain a preliminarily enhanced image. Finally, a color correction factor is introduced into the initial enhanced image to obtain the final enhanced image base on gray world hypothesis. Experimental results show that compared with several classical Retinex algorithms, the proposed algorithm can effectively improve the brightness, contrast and visual information fidelity of the input image without color distortion.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123649962","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

Uncertainty Estimation for Efficient Monocular Depth Perception 高效单目深度感知的不确定性估计

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00138

Hao Du, Guoan Cheng, Ai Matsune, Qiang Zhu, Shu Zhan

引用次数: 0

Real-time Occupancy Detection Of On-street Parking Spaces Based On An Edge Device 基于边缘设备的路边停车位实时占用检测

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00109

Fengshun Liao, Yu Sun, Yiliang Wu, Ju Wang

引用次数: 0

Design of an Agricultural Picking Robot based on Arduino 基于Arduino的农业采摘机器人设计

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00058

Yanhui Xu, Zhifu Huang

引用次数: 0

Parameter estimation of mixed two distributions based on EM algorithm and Nelder-Mead algorithm 基于EM算法和Nelder-Mead算法的混合两种分布参数估计

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00101

Yuting Zhou, Xuemei Yang, Shiqi Liu, Junping Yin

{"title":"Parameter estimation of mixed two distributions based on EM algorithm and Nelder-Mead algorithm","authors":"Yuting Zhou, Xuemei Yang, Shiqi Liu, Junping Yin","doi":"10.1109/CACML55074.2022.00101","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00101","url":null,"abstract":"As the amount of data increases, the data can obey either a single distribution, two distributions or even multiple distributions. If the distribution parameters and mixing ratio can be estimated for mixed data, it will be beneficial to further analysis and research in practical applications. In this paper, the EM algorithm and the Nelder-Mead(NM) algorithm are applied to the mixed parameter estimation of the two distributions, including mixing two identical distributions, mixing two different distributions, and comparing the EM algorithm and the Nelder-Mead algorithm to estimate the accuracy of the mixed distribution parameter estimation and its initial comparison. The stability of the value and other advantages and disadvantages. A large amount of data simulation results found that the EM algorithm has a good effect on the estimation of mixed distribution parameters, with high accuracy and fast convergence. The initial value selection has little effect on the results, and the preliminary derivation process is more complicated; the Nelder-Mead algorithm has a good effect on the estimation of mixed distribution parameters. High precision, fast convergence speed, the initial value selection has a greater impact on the result, the preliminary derivation process is relatively simple, and the application range is wide. When the initial value is close to the peak value of the real data, the parameter estimation effect is better; the two algorithms have poorer effect on the unimodal distribution parameter estimation for the data, and the bimodal distribution parameter estimation effect is better.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123693515","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

Proceedings 2022 Asia Conference on Algorithms, Computing and Machine Learning 2022年亚洲算法、计算和机器学习会议论文集

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/cacml55074.2022.00002

引用次数: 0