Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068577
Arie Yulfa, T. Aditya, H. Sutanta
Spatial data are indispensable in supporting disaster responders. Accurate locations of disaster areas will help responders to create an appropriate response in reducing the impact of the disaster. Indonesian Geospatial Information Agency (BIG-Badan Informasi Geospasial) has made spatial data available for emergency response activities across the country. In 2011, BIG launched a geoportal, which is a part of National Spatial Data Infrastructure Network (NSDIN). For data related to the disaster, Indonesian National Board for Disaster Management (BNPB) handles them that is a part of the network. At the national level, the data are in medium and small scale and not suitable for operational purposes such as in disaster response. Indonesian law on geospatial information has ordered the local government to develop local SDI to solve it. In disaster response phase, the data should reflect the latest situation, complete and reliable. They should be available in a short time period. SDI has impediments to meet these criteria because it is built based on the authoritative perspective that is not agile. On the other side, crowds enrich and update data rapidly by utilizing web 2.0 technology (e.g. social media and map applications). This paper discusses existing SDI frameworks and crowdsourcing concepts in Indonesia and global levels to come up with a new framework that can comply with disaster response activities.
空间数据在支持救灾人员方面是不可或缺的。准确的灾区位置将有助于救援人员制定适当的应对措施，以减少灾害的影响。印度尼西亚地理空间信息局(BIG-Badan Informasi Geospasial)为全国各地的应急活动提供了空间数据。2011年，BIG启动了一个地理门户，它是国家空间数据基础设施网络(NSDIN)的一部分。对于与灾难有关的数据，印度尼西亚国家灾害管理委员会(BNPB)处理它们，这是网络的一部分。在国家一级，这些数据是中型和小型的，不适合用于救灾等业务目的。印尼地理空间信息法律要求当地政府开发本地SDI来解决这个问题。在灾害响应阶段，数据应反映最新情况，完整可靠。它们应该在短时间内可用。SDI在满足这些标准方面存在障碍，因为它是基于非敏捷的权威视角构建的。另一方面，人群利用web2.0技术(如社交媒体和地图应用)快速丰富和更新数据。本文讨论了印度尼西亚和全球现有的SDI框架和众包概念，以提出一个符合灾害响应活动的新框架。
{"title":"Towards SDI services for crowdsourcing spatial data in disaster response","authors":"Arie Yulfa, T. Aditya, H. Sutanta","doi":"10.1109/INAES.2017.8068577","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068577","url":null,"abstract":"Spatial data are indispensable in supporting disaster responders. Accurate locations of disaster areas will help responders to create an appropriate response in reducing the impact of the disaster. Indonesian Geospatial Information Agency (BIG-Badan Informasi Geospasial) has made spatial data available for emergency response activities across the country. In 2011, BIG launched a geoportal, which is a part of National Spatial Data Infrastructure Network (NSDIN). For data related to the disaster, Indonesian National Board for Disaster Management (BNPB) handles them that is a part of the network. At the national level, the data are in medium and small scale and not suitable for operational purposes such as in disaster response. Indonesian law on geospatial information has ordered the local government to develop local SDI to solve it. In disaster response phase, the data should reflect the latest situation, complete and reliable. They should be available in a short time period. SDI has impediments to meet these criteria because it is built based on the authoritative perspective that is not agile. On the other side, crowds enrich and update data rapidly by utilizing web 2.0 technology (e.g. social media and map applications). This paper discusses existing SDI frameworks and crowdsourcing concepts in Indonesia and global levels to come up with a new framework that can comply with disaster response activities.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131854296","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068555
Kusuma Adi Achmad, L. Nugroho, Widyawan, A. Djunaedi
Tourism recommender system relies on several items in supporting its effectiveness in the context. The items' searching and selecting needed tools, such recommender system. The item concerns with the contextual information, such as location, time, or social. Recommendations that use contextual information in processing recommendations are Context-Aware Recommender System. However, to identify and acquire contextual information that may affect user preferences in the decision-making process is considered challenging. Therefore, in providing recommendations, the system requires the identification of relevant contextual information. The contextual information proposes a list of proper relevant tourism items information to tourists, when tourists are in a specific location at a certain time, activity on social networks, and with particular weather situations. This study aims to identify relevant contextual information based on study associated research Context-Aware Recommender System for tourism.
{"title":"Tourism contextual information for recommender system","authors":"Kusuma Adi Achmad, L. Nugroho, Widyawan, A. Djunaedi","doi":"10.1109/INAES.2017.8068555","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068555","url":null,"abstract":"Tourism recommender system relies on several items in supporting its effectiveness in the context. The items' searching and selecting needed tools, such recommender system. The item concerns with the contextual information, such as location, time, or social. Recommendations that use contextual information in processing recommendations are Context-Aware Recommender System. However, to identify and acquire contextual information that may affect user preferences in the decision-making process is considered challenging. Therefore, in providing recommendations, the system requires the identification of relevant contextual information. The contextual information proposes a list of proper relevant tourism items information to tourists, when tourists are in a specific location at a certain time, activity on social networks, and with particular weather situations. This study aims to identify relevant contextual information based on study associated research Context-Aware Recommender System for tourism.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122498334","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068537
Novita Anindita, H. A. Nugroho, T. B. Adji
Hepatitis is one of the major health problems which can progress to chronic hepatitis and cancer. Currently, computer based diagnosis is commonly use among medical examination. The diagnosis has been examined by using the disease dataset as a reference to make the decisions. However, the dataset was incomplete because it contained many instances containing missing values. This situation can lead the results of the analysis to be biased. One method of handling missing values is Multiple Imputation. Hepatitis dataset has an arbitrary pattern of missing values. This pattern can be handled by using Markov Chain Monte Carlo (MCMC) and Fully Conditional Specification (FCS) as Multiple Imputation algorithms. The research conducted an experiment to compare combinations of Multiple Imputations algorithm and Principal Component Analysis (PCA) as instance selection. Instance selection applied to reduce data by selecting variables that contribute greatly to the dataset. The goal was to improve the accuracy of the analysis on data which had missing values with the arbitrary pattern. The results showed that FCS-PCA is the best performance with the higher accuracy (98.80%) and the lowest error rate (0.0116).
{"title":"A Combination of multiple imputation and principal component analysis to handle missing value with arbitrary pattern","authors":"Novita Anindita, H. A. Nugroho, T. B. Adji","doi":"10.1109/INAES.2017.8068537","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068537","url":null,"abstract":"Hepatitis is one of the major health problems which can progress to chronic hepatitis and cancer. Currently, computer based diagnosis is commonly use among medical examination. The diagnosis has been examined by using the disease dataset as a reference to make the decisions. However, the dataset was incomplete because it contained many instances containing missing values. This situation can lead the results of the analysis to be biased. One method of handling missing values is Multiple Imputation. Hepatitis dataset has an arbitrary pattern of missing values. This pattern can be handled by using Markov Chain Monte Carlo (MCMC) and Fully Conditional Specification (FCS) as Multiple Imputation algorithms. The research conducted an experiment to compare combinations of Multiple Imputations algorithm and Principal Component Analysis (PCA) as instance selection. Instance selection applied to reduce data by selecting variables that contribute greatly to the dataset. The goal was to improve the accuracy of the analysis on data which had missing values with the arbitrary pattern. The results showed that FCS-PCA is the best performance with the higher accuracy (98.80%) and the lowest error rate (0.0116).","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"159 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128942861","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068549
Fakhriy Hario, S. Pramono, I. Mustika, A. Susanto
Laser is one of the light sources that transmits wavelength with frequency, phase, and polarization parameters. The response of each dielectric material to light created nonlinear in strong electromagnetic field. Nonlinearity occurs within the optical fiber with high intensity of light at the core with long span. The focus of this paper was to reduce the behavior of nonlinearity SPM (Self Phase Modulation) and GVD (Group Velocity Dispersion) characteristic on optical fiber transmission using frequency dithering technique. This paper showed signal characteristic after passing dithering system. By investigating this, we expected to mitigate and reduce nonlinearity on optical medium transmission for minimum OLP (Optical Launch Power) with varied linewidth. The peak of maximum power after the technique was applied was −30 dBm with respective SNR (Signal to Noise Ratio) and EVM (Error-Vector-Magnitude) value were 65 dB and 0.125 % on linewidth of 0.15 MHz.
{"title":"Mitigation of nonlinear impact on optical fiber","authors":"Fakhriy Hario, S. Pramono, I. Mustika, A. Susanto","doi":"10.1109/INAES.2017.8068549","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068549","url":null,"abstract":"Laser is one of the light sources that transmits wavelength with frequency, phase, and polarization parameters. The response of each dielectric material to light created nonlinear in strong electromagnetic field. Nonlinearity occurs within the optical fiber with high intensity of light at the core with long span. The focus of this paper was to reduce the behavior of nonlinearity SPM (Self Phase Modulation) and GVD (Group Velocity Dispersion) characteristic on optical fiber transmission using frequency dithering technique. This paper showed signal characteristic after passing dithering system. By investigating this, we expected to mitigate and reduce nonlinearity on optical medium transmission for minimum OLP (Optical Launch Power) with varied linewidth. The peak of maximum power after the technique was applied was −30 dBm with respective SNR (Signal to Noise Ratio) and EVM (Error-Vector-Magnitude) value were 65 dB and 0.125 % on linewidth of 0.15 MHz.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"51 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120996172","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068574
Auliantya Ayurin Putri, T. Aditya
Since 2014, Universitas Gadjah Mada (UGM) has established Drinking Water Supply System (DWSS). DWSS established in UGM is in line with Indonesian Government's target to fulfil needs for 100% drinking water access in 2019. In order to improve the system's sustainability, planning and monitoring through mapping and 3D modeling of DWSS network distribution are needed. DWSS is expected to not only be well distributed but also to be easily monitored and accessed by student and staff in UGM. The purpose of this paper is to present the utilization of 3D GIS to map water dispenser location and to model the distribution of pipeline network. It also focuses to assess the appropriateness of the planned water supply for fulfilling the need of drinking water in each faculty. In addition to that, the map of water dispenser finder is also developed to support campus community in finding the nearest drinking water facility. Data acquisition of water location has been done by using Handheld GPS, while data processing and presentation of DWSS in 3D format are done by using AutoCad 2009, ArcGIS for Desktop 10.3.1 (ArcScene and ArcMap), while Sketch Up, ArcGIS Online, and CityEngine Web Viewer are used to model and visualize the 3D map. This project produces Geographic Information System of DWSS in UGM. The 3D GIS of DWSS encompasses the map of distribution of water dispensers, the 3D model of network distribution of drinking water supply, and analysis of planned water supply in order to assess the drinking water needs in each faculty. The map of distribution of water dispensers is a map depicting distributed water dispenser in UGM. 3D map of network distribution of DWSS is built by combining multiple datasets including UGM's Digital Terrain Model (DTM), 3D model of campus building, 3D model of pipeline network, 3D model of water dispensers and reservoirs. 3D network distribution modeling of DWSS is presented offline by using ArcScene 10.3.1 •software and presented online by using CityEngine Web Viewer. From GIS analysis, it is found that the planned water supply has not answered the need of drinking water in each faculty. It can be seen that need of drinking water has reached 218.870 litres per day, whereas the planned supply is only 3.889,30 liters per day.
自2014年以来，Gadjah Mada大学(UGM)建立了饮用水供应系统(DWSS)。在UGM建立的DWSS符合印度尼西亚政府在2019年满足100%饮用水获取需求的目标。为了提高系统的可持续性，需要通过对DWSS网络分布的制图和三维建模进行规划和监测。DWSS不仅要分布良好，而且要便于UGM的学生和工作人员监控和访问。本文的目的是介绍利用三维地理信息系统来绘制饮水机位置和建立管网分布模型。它还侧重于评估计划供水的适当性，以满足每个学院的饮用水需求。除此之外，还开发了饮水机发现者地图，以支持校园社区寻找最近的饮用水设施。利用手持GPS对水体位置进行数据采集，利用AutoCad 2009、ArcGIS for Desktop 10.3.1 (ArcScene和ArcMap)对DWSS进行三维格式的数据处理和呈现，并利用Sketch Up、ArcGIS Online和CityEngine Web Viewer对三维地图进行建模和可视化。本项目在UGM中制作DWSS地理信息系统。DWSS的三维地理信息系统包括饮水机分布图，饮用水供应网络分布的三维模型，以及计划供水的分析，以评估每个学院的饮用水需求。饮水机分布图是一幅描绘UGM分布的饮水机的地图。结合UGM的数字地形模型(DTM)、校园建筑三维模型、管网三维模型、饮水机和水库三维模型等多个数据集，构建DWSS网络分布的三维地图。采用ArcScene 10.3.1•软件离线呈现DWSS三维网络分布模型，使用CityEngine Web Viewer在线呈现DWSS三维网络分布模型。从GIS分析中发现，规划供水不能满足各院系的饮水需求。可以看出，饮用水的需求量已达到每天218.870升，而计划供应量仅为每天3.889万升。
{"title":"3D modelling and visualization of drinking water supply system using 3D GIS","authors":"Auliantya Ayurin Putri, T. Aditya","doi":"10.1109/INAES.2017.8068574","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068574","url":null,"abstract":"Since 2014, Universitas Gadjah Mada (UGM) has established Drinking Water Supply System (DWSS). DWSS established in UGM is in line with Indonesian Government's target to fulfil needs for 100% drinking water access in 2019. In order to improve the system's sustainability, planning and monitoring through mapping and 3D modeling of DWSS network distribution are needed. DWSS is expected to not only be well distributed but also to be easily monitored and accessed by student and staff in UGM. The purpose of this paper is to present the utilization of 3D GIS to map water dispenser location and to model the distribution of pipeline network. It also focuses to assess the appropriateness of the planned water supply for fulfilling the need of drinking water in each faculty. In addition to that, the map of water dispenser finder is also developed to support campus community in finding the nearest drinking water facility. Data acquisition of water location has been done by using Handheld GPS, while data processing and presentation of DWSS in 3D format are done by using AutoCad 2009, ArcGIS for Desktop 10.3.1 (ArcScene and ArcMap), while Sketch Up, ArcGIS Online, and CityEngine Web Viewer are used to model and visualize the 3D map. This project produces Geographic Information System of DWSS in UGM. The 3D GIS of DWSS encompasses the map of distribution of water dispensers, the 3D model of network distribution of drinking water supply, and analysis of planned water supply in order to assess the drinking water needs in each faculty. The map of distribution of water dispensers is a map depicting distributed water dispenser in UGM. 3D map of network distribution of DWSS is built by combining multiple datasets including UGM's Digital Terrain Model (DTM), 3D model of campus building, 3D model of pipeline network, 3D model of water dispensers and reservoirs. 3D network distribution modeling of DWSS is presented offline by using ArcScene 10.3.1 •software and presented online by using CityEngine Web Viewer. From GIS analysis, it is found that the planned water supply has not answered the need of drinking water in each faculty. It can be seen that need of drinking water has reached 218.870 litres per day, whereas the planned supply is only 3.889,30 liters per day.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123585037","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068552
Wasilah, L. Nugroho, P. Santosa, R. Ferdiana
A number of benefits originate from the implementation of cloud computing. Cloud computing has been extensively implemented in organizations like companies and universities. However, in Indonesia cloud computing is not widely approved by universities yet. This condition can be caused by lack of trust of the universities in the risk of cloud computing implementation. This paper is intended to analyze the risk of current data management of academic data in university, as a baseline to create recommendation of cloud computing use in university. The result of the analysis is risk leveling of academic data of cloud computing implementation in Higher Education. The process used is COBIT 5 Framework. The result of this study is expected to help the IT staffs to manage academic data in universities more effectively. Eventually, it is able to give effects on the increase of service quality.
{"title":"Recommendation of cloud computing use for the academic data storage in University in Lampung Province, Indonesia","authors":"Wasilah, L. Nugroho, P. Santosa, R. Ferdiana","doi":"10.1109/INAES.2017.8068552","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068552","url":null,"abstract":"A number of benefits originate from the implementation of cloud computing. Cloud computing has been extensively implemented in organizations like companies and universities. However, in Indonesia cloud computing is not widely approved by universities yet. This condition can be caused by lack of trust of the universities in the risk of cloud computing implementation. This paper is intended to analyze the risk of current data management of academic data in university, as a baseline to create recommendation of cloud computing use in university. The result of the analysis is risk leveling of academic data of cloud computing implementation in Higher Education. The process used is COBIT 5 Framework. The result of this study is expected to help the IT staffs to manage academic data in universities more effectively. Eventually, it is able to give effects on the increase of service quality.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"35 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120821903","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068547
Reza Ferizal, S. Wibirama, N. A. Setiawan
This paper explains the gender recognition system through a human facial image by using the basic method of Principal Component Analysis (PCA) combined with Linear Discriminant Analysis (LDA). PCA+LDA method performance can be improved by improvising the preprocessing techniques such as resizing the image, equalizing the histogram, and removing the variation of the image background by adding oval masking face. Furthermore, in classification process, using 9 nearest neighbors gives the better recognition accuracy rather than using only 1 nearest neighbor. The highest accuracy results obtained with the proposed method is superior to get 89.70% when compared to the PCA + LDA method without adding masking face, which only reached 84.16%.
{"title":"Gender recognition using PCA and LDA with improve preprocessing and classification technique","authors":"Reza Ferizal, S. Wibirama, N. A. Setiawan","doi":"10.1109/INAES.2017.8068547","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068547","url":null,"abstract":"This paper explains the gender recognition system through a human facial image by using the basic method of Principal Component Analysis (PCA) combined with Linear Discriminant Analysis (LDA). PCA+LDA method performance can be improved by improvising the preprocessing techniques such as resizing the image, equalizing the histogram, and removing the variation of the image background by adding oval masking face. Furthermore, in classification process, using 9 nearest neighbors gives the better recognition accuracy rather than using only 1 nearest neighbor. The highest accuracy results obtained with the proposed method is superior to get 89.70% when compared to the PCA + LDA method without adding masking face, which only reached 84.16%.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133528999","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068556
Adyan Marendra Ramadhani, H. Goo
The social media has Immense and popularity among all the services today. Data from SNS (Social Network Service) can be used for a lot of objectives such as prediction or sentiment analysis. Twitter is a SNS that has a huge data with user posting, with this significant amount of data, it has the potential of research related to text mining and could be subjected to sentiment analysis. But handling such a huge amount of unstructured data is a difficult task, machine learning is needed for handling such huge of data. Deep learning is of the machine learning method that use the deep feed forward neural network with many hidden layers in the term of neural network with the result of the experiment about 75%.
{"title":"Twitter sentiment analysis using deep learning methods","authors":"Adyan Marendra Ramadhani, H. Goo","doi":"10.1109/INAES.2017.8068556","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068556","url":null,"abstract":"The social media has Immense and popularity among all the services today. Data from SNS (Social Network Service) can be used for a lot of objectives such as prediction or sentiment analysis. Twitter is a SNS that has a huge data with user posting, with this significant amount of data, it has the potential of research related to text mining and could be subjected to sentiment analysis. But handling such a huge amount of unstructured data is a difficult task, machine learning is needed for handling such huge of data. Deep learning is of the machine learning method that use the deep feed forward neural network with many hidden layers in the term of neural network with the result of the experiment about 75%.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130121059","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068548
A. Hidayat, S. Munawar, S. Syarif, A. Achmad
One of the quality requirements of a satellite low Earth orbit receiver antenna that maintain is pointing accuracy. The research is trying to using FFT to analyze the quality of the LEO satellite receiver antenna. Currently, the antenna tracking error analysis using graphs fault elevation and azimuth error compare to the time. This study is conducted find the effectiveness of the frequency and amplitude of the tracking error using (FFT). FFT is able to count the amplitude and frequency error. Calculation and plotting error by FFT in this study shows amplitude and frequency error. The goal system malfunction at data reception, recording satellite reception can be detected earlier. Solution and problem solving more efficient, availability of systems also data continuity can be maintained and protected.
{"title":"LEO antenna ground station analysis using fast fourier transform","authors":"A. Hidayat, S. Munawar, S. Syarif, A. Achmad","doi":"10.1109/INAES.2017.8068548","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068548","url":null,"abstract":"One of the quality requirements of a satellite low Earth orbit receiver antenna that maintain is pointing accuracy. The research is trying to using FFT to analyze the quality of the LEO satellite receiver antenna. Currently, the antenna tracking error analysis using graphs fault elevation and azimuth error compare to the time. This study is conducted find the effectiveness of the frequency and amplitude of the tracking error using (FFT). FFT is able to count the amplitude and frequency error. Calculation and plotting error by FFT in this study shows amplitude and frequency error. The goal system malfunction at data reception, recording satellite reception can be detected earlier. Solution and problem solving more efficient, availability of systems also data continuity can be maintained and protected.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878271","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}
Pub Date : 2017-08-01DOI: 10.1109/INAES.2017.8068538
Ahmad Zuli Amrullah, Rudy Hartanto, I. Mustika
Part of speech tagging has some different methods or techniques to the problem in assigning each word of a text with a part-of-speech tag. In this paper, we conducted some part-of-speech tagging techniques for Bahasa Indonesia experiments using statistical approach (Unigram, Hidden Markov Models) and Brill's tagger. In this study, we used Supervised POS Tagging approach requiring a large number of annotated training corpuses to tag properly. We used some resource annotation corpus of Bahasa. Those corpuses were implemented with POS Tagging techniques. We subsequently compared and analyzed the results. We also compared the accuracy and highlighted some advantages and disadvantages for every technique we used. Unigram showed a higher accuracy compared to HMM and Brill tagger with 88,37% on a tagged corpus.
{"title":"A comparison of different part-of-speech tagging technique for text in Bahasa Indonesia","authors":"Ahmad Zuli Amrullah, Rudy Hartanto, I. Mustika","doi":"10.1109/INAES.2017.8068538","DOIUrl":"https://doi.org/10.1109/INAES.2017.8068538","url":null,"abstract":"Part of speech tagging has some different methods or techniques to the problem in assigning each word of a text with a part-of-speech tag. In this paper, we conducted some part-of-speech tagging techniques for Bahasa Indonesia experiments using statistical approach (Unigram, Hidden Markov Models) and Brill's tagger. In this study, we used Supervised POS Tagging approach requiring a large number of annotated training corpuses to tag properly. We used some resource annotation corpus of Bahasa. Those corpuses were implemented with POS Tagging techniques. We subsequently compared and analyzed the results. We also compared the accuracy and highlighted some advantages and disadvantages for every technique we used. Unigram showed a higher accuracy compared to HMM and Brill tagger with 88,37% on a tagged corpus.","PeriodicalId":382919,"journal":{"name":"2017 7th International Annual Engineering Seminar (InAES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129734792","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：