2018 5th International Conference on Data and Software Engineering (ICoDSE)最新文献_第3页

Boosting-Based Relevance Feedback for CBIR 基于增强的CBIR相关反馈

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705854

Jasman Pardede, B. Sitohang, Saiful Akbar, M. L. Khodra

{"title":"Boosting-Based Relevance Feedback for CBIR","authors":"Jasman Pardede, B. Sitohang, Saiful Akbar, M. L. Khodra","doi":"10.1109/ICODSE.2018.8705854","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705854","url":null,"abstract":"In this research, we implemented Boosting-based Relevance Feedback (BRF) technique for Content-Based Image Retrieval (CBIR) system. The BRF technique follows two stages. In the first stage, the system returns the results of image retrieval based on the dissimilarity measure using Jeffrey Divergence with threshold 0.15. In the second stage, the system returns the results of the image retrieval based on the prediction of the BRF model which is generated based on the user's feedback image. With the same procedure, every feedback generates a BRF model that corresponds to the user's feedback images. In this study, we compare existing three Boosting algorithms, i.e.: AdaBoost, Gradient Boosting, and XGBoost. We consider the performance of application from precision, recall, F-measure, and accuracy value. The best BRF technique is XGBoost on fourth feedback, based on the results of experiments that conducted on the Wang Dataset. The BRF technique using XGBoost enhances the average precision value by 18.82%, the average recall value amount 173.32%, the average F-measure value amount 94.97%, and the average accuracy value amount 4.15% compared with the baseline. The BRF technique using XGBoost achieves the best performance on both the average recall and F-measure value compared to the most recent methods.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"1 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":"122541654","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

The Influence of Negation Handling on Sentiment Analysis in Bahasa Indonesia 否定处理对印尼语情感分析的影响

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705802

Annisa Maulida Ningtyas, Guntur Budi Herwanto

{"title":"The Influence of Negation Handling on Sentiment Analysis in Bahasa Indonesia","authors":"Annisa Maulida Ningtyas, Guntur Budi Herwanto","doi":"10.1109/ICODSE.2018.8705802","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705802","url":null,"abstract":"The negation handling has not been the main focus in Bahasa Indonesia sentiment analysis so that sentence's polarity that has the word negation cannot be determined automatically. This study aimed to analyze the effect of negation handling in Bahasa Indonesia using First Sentiment Word (FSW), Rest of Sentence (ROS) and Fixed Window Length (FWL) with $mathbf{n}= 1-5$. FSW will change the sentiment polarity of the first word after negation word, RoS will change the sentiment polarity of the entire word after the negation word, and FWL will change the polarity of sentiment words that exist in the scope of its window size. Results from this study indicate that the negation handling determined the sentence polarity optimally, compared to the absence of negation handling. FSW and FWL have an average accuracy increase by 2.43%, precision by 2.38%, and recall by 2.93%. FWL with $mathbf{n}=3$ results the best with a precision, recall and accuracy value of 71.58%, 69.62%, 73.79% respectively. The negation handling on the automatic labeling process proved to be beneficial in increasing the performance of the classification.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"24 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":"131545167","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

Access to Relational Databases Using Interrogative Sentences in Indonesian Language 用印尼语疑问句访问关系数据库

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705900

Hishshah Ghassani, T. E. Widagdo

引用次数: 5

SDRank: An Adaptable Service Selection for IoT Based on Ranking 基于排名的物联网自适应服务选择

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705811

Deddy Christoper Kakunsi, Muhammad Z. C. Candra

{"title":"SDRank: An Adaptable Service Selection for IoT Based on Ranking","authors":"Deddy Christoper Kakunsi, Muhammad Z. C. Candra","doi":"10.1109/ICODSE.2018.8705811","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705811","url":null,"abstract":"The Internet of Things (IoT) is a computing paradigm merging the physical object to the internet and enabling an interaction through the existing network protocols. The development of networking technology and the device's computing capacity drives the number of connected objects that increase rapidly. While this gives many benefits, it also brings challenges. One of them is the service selection capability. Issues arises in this context are related to the availability of service information and the dynamic nature of the devices. There are many of them sharing the same functionality but in fact, it's attributes changes over time. Thus, a service selection based on similarity and provide a handling of device changes is required. This research proposed the IoT service model and IOT-WSDL as a description model to support IoT-specific characteristic. Also, we introduced the SDRank, an implementation of adaptable service selection for IoT. It utilizes ranking to provide a selection method and to enable the adaptation of service changes. The models are useful in describing and sorting services to generate ranking. We compared two ranking methods, namely Service Rating and Analytical Hierarchy Process (AHP). The result shows that AHP provide a more relevant and consistent ranking than Service Rating without significant performance degradation.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"59 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":"130710333","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

A Simple Thermal-Front Detection for Cloudy Sea Surface Temperature Data 多云海面温度资料的简单热锋探测

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705795

Yus Sholva, Novi Safriadi, Hengky Anra, Tjahjanto

{"title":"A Simple Thermal-Front Detection for Cloudy Sea Surface Temperature Data","authors":"Yus Sholva, Novi Safriadi, Hengky Anra, Tjahjanto","doi":"10.1109/ICODSE.2018.8705795","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705795","url":null,"abstract":"The detection of thermal-fronts using data derived from satellites imagery data tends to be unsuccessful when the data being analyzed are largely covered by cloud. Segmentation or clustering-based detection method requires clear data and large size of dimension to achieve success on segmentation or clustering process. Otherwise, it needs a complex pre-process stage to process the cloudy data before the detection process. We proposed a simple thermal-fronts detection to process the Aqua MODIS Level 3 data that have a lot of clouds cover. By using the mathematical approach, we developed a model based on the pixels detection by analyze the values of the pixels and its relationships to neighbor pixels. We applied the segmentation approach using two window masks, i.e., searching window and neighboring window. Each pixel in the searching window will be evaluated based on the difference value (DV) between the center pixel and its' neighbor pixel, meanwhile each neighbor pixels will be created a neighboring window and evaluated using the edge thresholding value (ETV). The results from DV and ETV are used to determine whether or not the pixels in the searching window can be set as the thermal-fronts pixels. The experimental results show that the proposed method has a good performance to detect thermal-fronts using cloudy data.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"61 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":"131205549","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

Vertex-Cut Partitioning Performance Analysis for FASTCD Algorithm in Large-Scale Graph 大规模图中FASTCD算法的点切分割性能分析

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705840

Rizki Rusdiwijaya, G. Saptawati

{"title":"Vertex-Cut Partitioning Performance Analysis for FASTCD Algorithm in Large-Scale Graph","authors":"Rizki Rusdiwijaya, G. Saptawati","doi":"10.1109/ICODSE.2018.8705840","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705840","url":null,"abstract":"Large-scale graph processing has become a popular research topic in domain graph partitioning and community detection. FastCD is a community-based detection algorithm based on modularity optimization capable of detecting communities on large-scale graphs. Community detection on large graphs requires graph partitioning techniques that partition large-scale graphs into several subgraphs for processing carried out in parallel, so that computational loads can be distributed across machines in the cluster. The research was conducted on graph-parallel distributed framework, GraphX, which is a graph processing component in Spark. The strategies of vertex-cut partitioning method such as RandomVertexCut, CanonicalRandomVertexCut, EdgePartition1D, and EdgePartition2D applied to the FastCD to perform community detection on large scale graphs in parallel. Furthermore, EdgePartition1D has the best performance for FastCD performing parallel community detection on large-scale graphs with the number of edges 7,600,595 and vertices 685,230. The results of this research can be seen that the FastCD algorithm with EdgePartition1D and EdgePartition2D is able to maintain valuable information contained in graphs by considering vertices and neighboring edges quickly.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"1 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":"131035625","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

Realtime Porn Image Censor Method for Preventing Smartphone Users to Take a Pornographic Photo 防止智能手机用户拍摄色情照片的实时色情图像审查方法

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705807

Ario Yudo Husodo, I. S. Wijaya, I Wayan Agus Arimbawa

{"title":"Realtime Porn Image Censor Method for Preventing Smartphone Users to Take a Pornographic Photo","authors":"Ario Yudo Husodo, I. S. Wijaya, I Wayan Agus Arimbawa","doi":"10.1109/ICODSE.2018.8705807","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705807","url":null,"abstract":"Nowadays, many pornographic photos are taken by using smartphones. These photos unfortunately can be shared instantly around the world by only using social media. In order to minimize the spread of these kind of photos, this paper proposes a method to prevent smartphones users to take pornographic photo. This paper proposes a built-in camera application that can detect the existence of pornographic aspect in a photo then it can automatically censor the pornographic part in real time. The main approach used in this paper is it recognizes the pornographic part of a photo by using pattern matching method, then it censors those parts automatically. If a smartphone user tries to take a pornographic photo, with this proposed system, then he/she will save a photo including the censors. The key feature of proposed method is its ability to censor only pornographic part of a photo automatically in real time. This proposed method is also implemented in common smartphone. It has been tested to practically run in low resource machine like a smartphone. This paper is designed to overcome the ambiguity of pornographic photo. For example, in some countries the existence of bra can be categorized as a pornographic part of a photo. Meanwhile in other countries, a pornographic part of a photo must contain nipples. The proposed method uses external files as pattern matching templates to find pornographic part in a photo. By using the external files, the proposed method can flexibly adjust its measurement of pornographic part in a photo according to the circumstance that it faces. For example, the proposed method uses different external file to identify pornographic part in a photo taken in West Countries and in East Countries. By using the proposed method, the spread of pornographic photo taken by smartphone can be decreased automatically and flexibly.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"2 4-5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120909513","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

Efficient Mining of Maximal Frequent Itemsets Based on M-Step Lookahead 基于m步前瞻的最大频繁项集高效挖掘

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705805

Elijah L. Meyer, S. M. Chung

引用次数: 1

Internet Browsing History Data Analysis for Automatic Negative Content Website Identification (Case Study: TRUST+™ Positif) 用于负面内容网站自动识别的互联网浏览历史数据分析(案例研究:TRUST+™Positif)

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705919

Army Aristofany, G. A. Putri Saptawati, Y. Asnar

{"title":"Internet Browsing History Data Analysis for Automatic Negative Content Website Identification (Case Study: TRUST+™ Positif)","authors":"Army Aristofany, G. A. Putri Saptawati, Y. Asnar","doi":"10.1109/ICODSE.2018.8705919","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705919","url":null,"abstract":"Negative content website is a website that contains one or more of these following elements: pornography, violence and coercion in children, incitement to anarchy, and gambling. Negative content website grows along with the development of the internet. The number of internet users who's potentially exposed to negative content is increasing because of the cheaper cost of access to the internet and the increasing number of devices that support the use of the internet. Several programs have been taken by the authorities. Among them is the creation of TRUST + ™ Positive system that holds the huge list of negative website address. The ISP (Internet Service Provider) will blocks any negative content website referring to this system. The number of negative content website listed in the TRUST + ™ Positive list increases when there's reports about new negative content website or after doing the back-crawling process. The problem we faced is that the addition of the number of negative content website listed on the TRUST + ™ Positive list depends heavily on external reports and the ability of the TRUST + ™ Positive back-crawling engine. Therefore, by using ISP's Internet browsing history data we will performing data mining process to identify new negative content website. Data mining is done by using an association algorithm. Some internet user browsing history data setup techniques are used to find the best results according to internet browsing patterns that may arise. To reduce the number of identification errors we will filter any websites that are believed to be a website that has no negative content. The result obtained is that although the results of the association algorithm can be used for the identification of negative content website, but more than 75% of those results are not a negative content website or still need validation about its content.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"1 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":"127489176","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

Optimizations of Dual Polarization FMCW Weather Radar Signal Processing on CUDA Platform 基于CUDA平台的双极化FMCW天气雷达信号处理优化

2018 5th International Conference on Data and Software Engineering (ICoDSE) Pub Date : 2018-11-01 DOI: 10.1109/ICODSE.2018.8705821

Satrio Adi Rukmono, A. I. Kistijantoro, Riza Satria Perdana

{"title":"Optimizations of Dual Polarization FMCW Weather Radar Signal Processing on CUDA Platform","authors":"Satrio Adi Rukmono, A. I. Kistijantoro, Riza Satria Perdana","doi":"10.1109/ICODSE.2018.8705821","DOIUrl":"https://doi.org/10.1109/ICODSE.2018.8705821","url":null,"abstract":"Weather radar is a system that utilizes advanced radio wave engineering to detect precipitation in the atmosphere. One of the wave generation technique used in weather radar is frequency-modulated continuous wave (FMCW), with dual polarization for differentiating detected precipitation types by its shape and size. Weather radar signal processing is usually performed using digital signal processing and field-programmable gate array (FPGA), that performs well but with difficulty in system development and deployment. Software implementation of weather radar signal processing enables easier and faster development and deployment with the cost of performance when done serially. Parallel implementation using general purpose graphics processing units (GP-GPU) may provide best of both worlds with easier development and deployment compared to hardware-based solutions but with better performance than serial CPU implementations. In this paper, implementation of various optimization strategies weather signal radar processing in GP-GPU environment on the Nvidia CUDA platform is shown. Performance measurements show that among optimization strategies implemented, only the utilization of multiple CUDA streams give significant performance gain. This paper contributes in attempts to build full weather radar signal processing stack on GPU.","PeriodicalId":362422,"journal":{"name":"2018 5th International Conference on Data and Software Engineering (ICoDSE)","volume":"39 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":"123348881","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