2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)最新文献_第5页

Research on Low Illumination Image Processing Algorithm Based on Adaptive Parameter Homomorphic Filtering 基于自适应参数同态滤波的低照度图像处理算法研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00118

Siyu Di, Wensheng Sun

引用次数: 2

Construction of online course evaluation model from the perspective of learning willingness 学习意愿视角下的网络课程评价模型构建

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00051

Yang Yang, Jingjing Wang, Yanying Yang, Yixuan Li, Ying Liu

{"title":"Construction of online course evaluation model from the perspective of learning willingness","authors":"Yang Yang, Jingjing Wang, Yanying Yang, Yixuan Li, Ying Liu","doi":"10.1109/CACML55074.2022.00051","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00051","url":null,"abstract":"With the gradual “desensitization” processing of the online learning platform, it is difficult for researchers to construct student portraits through incomplete learning data. This paper uses the public evaluation and message data of the relevant online courses, uses the Latent Dirichlet Allocation (LDA) to extract the subject words, introduces the topic correlation parameters and course characteristic parameters, and finally constructs the LDA online course evaluation model by visualizing the results. Firstly, taking the “innovation and entrepreneurship” course as an example, it studies how to allocate online course resources more reasonably and effectively through new technologies and new carriers, which are suitable for online course developers, managers and researchers to study the characteristics of a certain type of course. Secondly, through the setting of course characteristic parameters, the model can also be applied to the specific course analysis, this paper takes the “Modern Etiquette” of Hunan University and the “Advanced Mathematics (I)” course of Tongji University as examples for visual analysis, and provides a reference for the course team to carry out teaching intervention and teaching decision-making.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"49 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134412768","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

Design and Analysis of Job Assignment in Server Farms of Data Centers 数据中心服务器群作业分配的设计与分析

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00057

Qiong Xiao, Yangyang Chen

引用次数: 0

Detection of anomalies in key performance indicator data by a convolutional long short-term memory prediction model 基于卷积长短期记忆预测模型的关键绩效指标数据异常检测

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00062

Jie Xie, Qing Cheng, Guangquan Cheng, Jincai Huang

{"title":"Detection of anomalies in key performance indicator data by a convolutional long short-term memory prediction model","authors":"Jie Xie, Qing Cheng, Guangquan Cheng, Jincai Huang","doi":"10.1109/CACML55074.2022.00062","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00062","url":null,"abstract":"The rapid development of Internet technology has led to increasingly complex web service systems. The resulting large number of component interactions pose a challenge to anomaly detection, which is realized primarily by operation and maintenance (OM) personnel through the deployment, management, and monitoring of various key performance indicators (KPIs). Anomalous behaviors during daily OM often cause problems in KPI data; these problems include high noise, high dimensionality, and large-scale data streams. In addition, anomalies in KPI data occur infrequently and are of various types. These factors are the cause of the very low accuracy currently observed in conventional machine learning methods for detecting anomalies in large OM systems. Hence, a convolutional long short-term memory (C-LSTM) neural network is presented in this study to detect anomalies in small datasets that contain a variety of anomalies. First, a sliding window is used to preprocess the KPI data. Then, a C-LSTM neural network, which combines the features of the convolutional neural network (CNN) and LSTM algorithms, is employed to effectively model the time and numerical information contained in the preprocessed KPI data. Finally, the C-LSTM algorithm is tested on the datasets used in the competition of the Artificial Intelligence for Information Technology Operations (AIOPs) Active Network Management (ANM) 2018 Fall Project. The results show that the C-LSTM prediction algorithm outperforms the conventional LSTM and CNN algorithms in terms of its capacity to detect anomalies in small datasets that contain various anomalies, with a 12.90% higher accuracy, 5.68% higher recall, and 9.58% higher F1-score.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"29 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":"114717179","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: 1

Predicting Beijing Air Quality Using Bayesian Optimized CNN-RNN Hybrid Model 基于贝叶斯优化CNN-RNN混合模型的北京空气质量预测

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00104

Zihan Tu, Zhe Wu

引用次数: 2

Progressive Face Super-Resolution Reconstruction Network Based on Relational Modeling 基于关系建模的渐进式人脸超分辨率重建网络

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00105

Rong Tan, Jun Yu Li, Zhiping Shi

{"title":"Progressive Face Super-Resolution Reconstruction Network Based on Relational Modeling","authors":"Rong Tan, Jun Yu Li, Zhiping Shi","doi":"10.1109/CACML55074.2022.00105","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00105","url":null,"abstract":"Aiming at the imprecise details of the reconstructed face image caused by the large scale and ignoring the relationship modeling between different pixels in the upsampling process of most existing face super-resolution reconstruction algorithm models, a new progressive face super-resolution reconstruction network based on relationship modeling is proposed. The network mainly includes a detail information generation module based on progressive upsampling and a detail information enhancement module based on relational modeling. The step-by-step upsampling detail information generation module realizes the step-by-step generation of the face image detail information through the step-by-step upsampling operation. The detail information enhancement module based on relational modeling which adopts a linear and nonlinear relational modeling method optimizes the channel-level and spatial feature-level modeling of the detail information of the face image, and combines with the progressive upsampling detail information to achieve accurate reconstruction. Finally, through the experimental verification, the effectiveness of the algorithm proposed in this paper is proved.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"31 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":"132586612","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

Nearest Neighbor outperforms Kernel-Kernel Methods for Distribution Regression 最近邻优于核-核分布回归方法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00009

Ilqar Ramazanli

引用次数: 0

Research on the demand characteristics of logistics talents based on Web text mining 基于Web文本挖掘的物流人才需求特征研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00122

Sitong Xue, Beilin Liu

引用次数: 0

Research on Deflection Deformation in Transfer Alignment 传递对准中的挠曲变形研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00116

Bo Jia, Hongwei Mu, Jiayuan Cao, Dan Jia, Junnan Cui

引用次数: 0

PaFPN-SOLO: A SOLO-based Image Instance Segmentation Algorithm PaFPN-SOLO:基于solo的图像实例分割算法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00100

Bo Li, Ji-kai Zhang, Yong Liang

引用次数: 0