2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)最新文献

Time Series Clustering Based on Dynamic Time Warping 基于动态时间翘曲的时间序列聚类

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663857

Weizeng Wang, Gaofan Lyu, Yuliang Shi, Xun Liang

{"title":"Time Series Clustering Based on Dynamic Time Warping","authors":"Weizeng Wang, Gaofan Lyu, Yuliang Shi, Xun Liang","doi":"10.1109/ICSESS.2018.8663857","DOIUrl":"https://doi.org/10.1109/ICSESS.2018.8663857","url":null,"abstract":"In general, solving prediction problems requires a series of operations for the data set such as preprocessing, partitioning, and structuring features, so as to fit a better prediction model. For time series data, it is divided into different data sets according to certain rules to achieve the effect of improving the accuracy of the prediction model. This paper proposes a more novel clustering method which the traditional Euclidean distance and dynamic time planning are separately weighted and combined to do the distance calculation method in clustering. A time series contains both a time dimension and a spatial dimension. Euclidean distance is mainly used for spatial distance calculation. Dynamic time warping can calculate the similarity calculation in time dimension, similar to the distance calculation in the spatial dimension. The measure of similarity of time series is a measure of the degree of similarity between two time series. It is verified by experiments that under the same prediction model, this novel clustering method is better than the Euclidean distance clustering method and the traditional dynamic time warping method.","PeriodicalId":330934,"journal":{"name":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115360096","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: 19

A New Approach on Rule Mining Based on Granularity in Incomplete Information Systems 不完全信息系统中基于粒度的规则挖掘新方法

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663898

Wu Jie, Liang Yan, Ma Yuan

{"title":"A New Approach on Rule Mining Based on Granularity in Incomplete Information Systems","authors":"Wu Jie, Liang Yan, Ma Yuan","doi":"10.1109/ICSESS.2018.8663898","DOIUrl":"https://doi.org/10.1109/ICSESS.2018.8663898","url":null,"abstract":"The analysis of incomplete decision table is an important research topic in the field of intelligent information processing. This paper defines incomplete information system, incomplete decision table, granularity, tolerance granulation, deterministic operator, possible operator. Firstly, it extracts tolerance granulations of the object collections that are divided by decision attributes. Secondly, it gets the new object collections by calculating tolerance granulations via deterministic operators or possible operators. Thirdly, If the intersection of the information granulations from the different attribute values is an empty set or isn't a subset of the elements from the new object sets, then it chooses the information granules of the attribute values according to different conditions. The execution is out of the loop until it doesn't satisfy the cycle conditions. It outputs the deterministic or possible decision rules. And lastly, it continues to find the deterministic or possible decision rules from the rest of the new object collections. The paper presents a new method that the deterministic or possible decision rules are mined based on granularity in incomplete information systems. It gives the mining algorithms and the instance. The approach has the advantages of high efficiency, more rules, concise forms, good comprehensibility and generalization ability.","PeriodicalId":330934,"journal":{"name":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116883825","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

Transfer Learning on Convolutional Neural Networks for Dog Identification 基于卷积神经网络的狗狗识别迁移学习

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663718

Xinyuan Tu, K. Lai, S. Yanushkevich

引用次数: 13

A Multi-Sentiment Classifier Based on GRU and Attention Mechanism 基于GRU和注意机制的多情感分类器

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663799

X. Liang, Zhiming Liu, Chunping Ouyang

引用次数: 8

Class-Probability Based Semi-Supervised Dimensionality Reduction for Hyperspectral Images 基于类概率的高光谱图像半监督降维

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/icsess.2018.8663892

Lu Liang, Yi Xia, Lina Xun, Qing Yan, Dexiang Zhang

{"title":"Class-Probability Based Semi-Supervised Dimensionality Reduction for Hyperspectral Images","authors":"Lu Liang, Yi Xia, Lina Xun, Qing Yan, Dexiang Zhang","doi":"10.1109/icsess.2018.8663892","DOIUrl":"https://doi.org/10.1109/icsess.2018.8663892","url":null,"abstract":"Hyperspectral images (HSI)are very useful due to the rich information they contained. However, for the same reason, it is also inconvenient to be analyzed due to its high dimension and also because it contains a lot of redundant information. Therefore, dimensionality reduction (DR)is often an indispensable step for the analysis of HSI. Due to the expensiveness of labeling samples, semi-supervised learning technique that performs DR with only a small amount of labeled samples, has attract more and more attention during the past several years. In this paper, we propose a novel method called class probability semi-supervised DR (CPSDR). Unlike previously semi-supervised DR methods, which only focus on a small number of labeled samples and depend on their local geometry information, our approach also pay much attention on unlabeled samples. Moreover, in our approach, not only local geometry information but also class structure information was exploited. We then combined these two information together to yield a more discriminative scatter matrix. We formulate our problem as an optimization problem and solve it by eigenvalue decomposition. The experimental results on Salinas and PaviaU hyperspectral data suggested that our algorithm achieved state-of-the-art performance.","PeriodicalId":330934,"journal":{"name":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117136733","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

Research on Optimization of Massive E-Commerce Data Fusion Technology 电子商务海量数据融合技术优化研究

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663755

Fei Gao

引用次数: 0

Parallel Random Forest Algorithm Optimization Based on Maximal Information Coefficient 基于最大信息系数的并行随机森林算法优化

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663954

Song Liu, Tianyu Hu

{"title":"Parallel Random Forest Algorithm Optimization Based on Maximal Information Coefficient","authors":"Song Liu, Tianyu Hu","doi":"10.1109/ICSESS.2018.8663954","DOIUrl":"https://doi.org/10.1109/ICSESS.2018.8663954","url":null,"abstract":"In order to solve the problem that the traditional random forest algorithm runs too long or cannot be executed facing massive data, meanwhile in order to solve the problem that some redundant features are added to the training process and some strong expressive features are not selected when the traditional random forest algorithm randomly chooses features. A random forest algorithm based on maximum information coefficient (MIC)is proposed, and the algorithm is parallelized on the Spark platform. Firstly, MIC is used to rank each feature and the features are divided into three interval: high correlation interval, middle correlation interval and low correlation interval. In the process of constructing a single decision tree, the features of low correlation interval are deleted. Then, all the features of high correlation interval and the randomly selected features of middle correlation interval are selected to form a new feature subset to build the decision tree. Finally, the parallelization of the algorithm is implemented based on Spark. The experimental results show that the proposed algorithm has a certain improvement in accuracy and stability compared with the traditional random forest algorithm.","PeriodicalId":330934,"journal":{"name":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126116946","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

A Study on the Impact of Reusing Redundant Patches on Automatic Program Repair 重复使用冗余补丁对程序自动修复的影响研究

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663876

Hang Gao, Tao Ji, Xiaoguang Mao

引用次数: 0

A Solution for Input Limit in CNN Due to Fully-Connected Layer 一种基于全连通层的CNN输入限制解决方案

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663724

Yili Qu, Yaobin Ke, Wei Yu

{"title":"A Solution for Input Limit in CNN Due to Fully-Connected Layer","authors":"Yili Qu, Yaobin Ke, Wei Yu","doi":"10.1109/ICSESS.2018.8663724","DOIUrl":"https://doi.org/10.1109/ICSESS.2018.8663724","url":null,"abstract":"Many CNNs require a fixed-size input due to the inclusion of fully-connected layer. In actual training and application, the size of input maybe various. The usual solution is cropping or warping. But cropping may lose useful pixels while warping will destroy the structural information thus causing geometric distortion potentially. Since there is still a wide range of application scenarios for fully-connected layer, we hope to solve this problem under the premise of retaining the fully-connected layer. In this paper, a solution based on the SPP improvement operator for CNNs containing fully-connected layer is proposed to help networks accept various size inputs and learn effectively. We build a dataset consisted of various-size geometry images, which is sensitive to geometric distortion. By the comparison of experiments on this dataset using different method, we verify that our method can significantly improve the prediction accuracy by avoiding the geometric distortion. By applying our method on AlexNet and VGGNet, we show the robustness of our method for models. On the public dataset VOC 2007 with unfixed image sizes and ImageNet with fixed image sizes, our solution can maintain the accuracy of the original model, indicating that our method is robust on ordinary datasets that are not sensitive to geometric distortion.","PeriodicalId":330934,"journal":{"name":"2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125363804","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

Acceptance Evaluation of Code Recommendation Systems by Programming Behaviors Detection and Analysis 基于编程行为检测与分析的代码推荐系统验收评估

2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) Pub Date : 2018-11-01 DOI: 10.1109/ICSESS.2018.8663798

Hongming Zhu, Yajun Xu, Hongfei Fan, Qin Liu

引用次数: 0