Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems最新文献_第6页

Identifying text reuse using word net-based extended named entity recognition 使用基于词网络的扩展命名实体识别识别识别文本重用

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264811

Eunji Lee, Pankoo Kim

引用次数: 0

Optimization of vehicle routing problem with fatigue driving based on genetic algorithm 基于遗传算法的疲劳驾驶车辆路径优化

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264782

Jiacheng Li, Jiaoman Du, Lei Li

引用次数: 2

A survey on ocean observatory networks 海洋观测网概况

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264800

Jingyi Chen, Xin Su, Xuewu Zhang, Chang Choi, Dongmin Choi

引用次数: 3

An efficient load balancing multicast scheduling for solving congestion problem in social data center networks 一种解决社交数据中心网络拥塞问题的高效负载均衡组播调度方法

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264763

Hsueh-Wen Tseng, Ya-Ju Yu, Kai-Hsu Hsieh

引用次数: 0

Energy-aware task scheduling strategies with QoS constraint for green computing in cloud data centers 基于QoS约束的云数据中心绿色计算能耗感知任务调度策略

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264792

Xing Liu, Panwen Liu, Hongjing Li, Zheng Li, Chengming Zou, Haiying Zhou, Xin Yan, Ruoshi Xia

{"title":"Energy-aware task scheduling strategies with QoS constraint for green computing in cloud data centers","authors":"Xing Liu, Panwen Liu, Hongjing Li, Zheng Li, Chengming Zou, Haiying Zhou, Xin Yan, Ruoshi Xia","doi":"10.1145/3264746.3264792","DOIUrl":"https://doi.org/10.1145/3264746.3264792","url":null,"abstract":"Energy optimization with Quality-of-Service (QoS) constraint has become a timely and significant challenge for the cloud datacenters. In this paper, a hardware and software collaborative optimization strategy is implemented to minimize the energy cost while satisfying the time constraint of the cloud-computing datacenters. In the hardware aspect, a DVFS-capable CPU/GPU/FPGA heterogeneous cloud infrastructure is built. This infrastructure has high flexibility, and can adjust its hardware characteristics dynamically in terms of the software run-time contexts, so that a hardware platform which matches the software can be built. Based on this hardware platform, the cloud applications can be executed more efficiently with less energy cost. In the software aspect, the deadline-aware energy-efficient task scheduling algorithms are investigated. Different from the traditional approaches which search for the optimal scheduling solution by the heuristic approaches, a new scheduling approach based on the improved Mathematical Morphology (MM) algorithm is investigated in this paper. To evaluate the performance of our work, we calculated the energy cost of the Fourier transform (FT) and Gaussian elimination (GE) applications on the homogeneous and heterogeneous cloud computing platforms by applying the GA and MM algorithms, respectively. The results proved the MM algorithms running on the DVFS-capable heterogeneous cloud infrastructure could decrease the energy cost of the FT application and GE application respectively by 24.7% and 37.8%, if compared with the GA algorithm running on the DVFS-incapable homogeneous cloud infrastructure.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"44 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120922904","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: 5

Abstractive summarization by neural attention model with document content memory 基于文献内容记忆的神经注意模型抽象摘要

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264773

YunSeok Choi, Dahae Kim, Jee-Hyong Lee

引用次数: 3

Dimensionality reduction by bayesian eigenvalue-analysis for state prediction in large sensor systems: with application in wind turbines 基于贝叶斯特征值分析的大型传感器系统状态预测降维方法及其在风力发电中的应用

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264753

J. Herp, E. Nadimi

引用次数: 1

Clustering algorithms on imbalanced data using the SMOTE technique for image segmentation 基于SMOTE技术的非平衡数据聚类算法

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264774

W. Abeysinghe, C. Hung, Slim Bechikh, Xiaosong Wang, Altaf Rattani

{"title":"Clustering algorithms on imbalanced data using the SMOTE technique for image segmentation","authors":"W. Abeysinghe, C. Hung, Slim Bechikh, Xiaosong Wang, Altaf Rattani","doi":"10.1145/3264746.3264774","DOIUrl":"https://doi.org/10.1145/3264746.3264774","url":null,"abstract":"Imbalanced data is a critical problem in machine learning. Most imbalanced dataset consists of one or more classes, called the minority class, which do not have enough number of samples for the recognition. Many traditional classification algorithms are unable to recognize the minority class effectively. Clustering algorithms used for image segmentation may have a high accuracy; however, none of samples in the minority class is classified correctly. In this study, we use three approaches, traditional oversampling technique, traditional undersampling technique, and the Synthetic Minority Over-sampling Technique (SMOTE), to reduce the significant difference of imbalance of the number of samples between the majority classes and the minority classes in the dataset. Fuzzy C-means algorithm (FCM) and Possibilistic Clustering Algorithm (PCA) are used to segment the images in which the samples are generated using above sampling methods. Experimental results are evaluated using the Kappa Coefficient and Confusion matrix. Our evaluation shows that the oversampling, undersampling, and SMOTE techniques can improve the imbalanced image segmentation problem with a higher accuracy[1].","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126828055","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: 4

Data hiding using compressed archives 使用压缩档案隐藏数据

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264752

B. Carpentieri, Arcangelo Castiglione, A. D. Santis, F. Palmieri, Raffaele Pizzolante

{"title":"Data hiding using compressed archives","authors":"B. Carpentieri, Arcangelo Castiglione, A. D. Santis, F. Palmieri, Raffaele Pizzolante","doi":"10.1145/3264746.3264752","DOIUrl":"https://doi.org/10.1145/3264746.3264752","url":null,"abstract":"The need to avoid suspicion in a potential observer/investigator, though it can be seen as a weak requirement for the protection of transmitted data, it can be extremely useful. For example, once discovered that the data has been protected by means of certain security tools, a malicious user that is strongly interested in such data could make a great effort in trying to remove the protection, for example, by cracking the password or by exploiting the vulnerabilities of the algorithm that was used to protect the data. Hence, to transfer information in a secure way, it is sometimes better to hide it inside other data, rather than protecting it in a conventional manner. One of the most important techniques in data hiding is steganography. In this work we propose a novel steganographic method which enables to hide information by using a compressed archive as information carrier. The method we propose uses these compressed archives, together with their relative hierarchical structure, to hide bits of information. We remark that by means of our method the hidden information does not have any semantic relation with respect to the content of the compressed archive, whereas such relation will concern how the archive (and the relative sub-archives) was compressed, i.e., what compression algorithms and relative parameters were used, as well as how this operation was performed. Since it is a common practice to send compressed data by means of a communication channel, we believe that our proposal can be a valid tool for steganographic purposes, since the suspect generated in a potential observer could be considered almost negligible.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114237727","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

Development of vegetation mapping with deep convolutional neural network 基于深度卷积神经网络的植被制图研究进展

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264791

Sae-Han Suh, Ji-Eun Jhang, Kwanghee Won, Sung Y. Shin, C. Sung

引用次数: 0