Pub Date : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878547
Budi Utami Fahnun, A. Mutiara, E. P. Wibowo, J. Harlan, Apriyadi Abdullah, Muhammad Abdul Latief
Ultrasound is an important diagnostic tool in diagnosing various abnormalities in the liver. Ultrasound is safe strategy for patient examination, being easy to apply, a non-invasive, and economical one. Ultrasound examination has the probability of repeatability producing images in real-time mode for diagnosing abdominal disorder such as liver cancer. Unprocessed ultrasound image has poor quality due to loss of texture or shape that can affect expert interpretation. The filtering methods are the initial process to reduce noise in the images. Enhanced image quality is needed for processing at the next stage after this initial processing. The research used salt and pepper, gaussian, and speckle noise. Filter that used to improved image quality to reduce noise are; mean, 2D medians, 3D medians, gaussian, and wiener. Image quality is measured by the quantitative value of MSE, RMSE and PSNR. Filter testing is done with noise level 1 and each filter has sigma value with average of 5. From the trial results, the best method for handling salt and pepper noise is the 3D median filter with MSE and RMSE values approaching 0 then having PSNR greater than 30 dB of all filter. The wiener filter is the best method to overcome Gaussian and speckle noise.
{"title":"Filtering Techniques for Noise Reduction in Liver Ultrasound Images","authors":"Budi Utami Fahnun, A. Mutiara, E. P. Wibowo, J. Harlan, Apriyadi Abdullah, Muhammad Abdul Latief","doi":"10.1109/EIConCIT.2018.8878547","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878547","url":null,"abstract":"Ultrasound is an important diagnostic tool in diagnosing various abnormalities in the liver. Ultrasound is safe strategy for patient examination, being easy to apply, a non-invasive, and economical one. Ultrasound examination has the probability of repeatability producing images in real-time mode for diagnosing abdominal disorder such as liver cancer. Unprocessed ultrasound image has poor quality due to loss of texture or shape that can affect expert interpretation. The filtering methods are the initial process to reduce noise in the images. Enhanced image quality is needed for processing at the next stage after this initial processing. The research used salt and pepper, gaussian, and speckle noise. Filter that used to improved image quality to reduce noise are; mean, 2D medians, 3D medians, gaussian, and wiener. Image quality is measured by the quantitative value of MSE, RMSE and PSNR. Filter testing is done with noise level 1 and each filter has sigma value with average of 5. From the trial results, the best method for handling salt and pepper noise is the 3D median filter with MSE and RMSE values approaching 0 then having PSNR greater than 30 dB of all filter. The wiener filter is the best method to overcome Gaussian and speckle noise.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"28 2 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":"123274437","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878526
Eko Suripto Pasinggi, S. Sulistyo, B. Hantono
This study focuses on designing and implementing a Positioning System (PS) that is addressed as a component of the Location-aware Museum Guide System (GMS). The level of accuracy of the Positioning System (PS) is an important aspect in determining the suitability of the information received by the visitors. The design flow of the system begins by identifying the location of implementation. After that, choose the components to build the system. The principle used in this study is the use of existing infrastructure to reduce the cost of system development. A recent study was completed in the museum gathered information about the museum environment to assist with the design process. The system design is proposed by using WLAN technology with RSSI-based fingerprinting techniques. The algorithm used for this fingerprint technique is KNN. The addition of Access Point (AP) and AP filtering methods were also applied to improve the system performance. The test results showed that there were significant differences on accuracy level of PS among three times trial tested to the expectation of accuracy level at 1.2 meter. First trial was without additional support the existing infrastructure in the Museum is unable to provide an accurate estimating position. It was only 3.75 m. The second was by adding five APs from 6 to 11 APs, the accuracy level was 2.55 m. The last was to implement the AP filtering. It can provide improvement to 1.83 m.
{"title":"KNN-Based Visitor Positioning For Museum Guide System","authors":"Eko Suripto Pasinggi, S. Sulistyo, B. Hantono","doi":"10.1109/EIConCIT.2018.8878526","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878526","url":null,"abstract":"This study focuses on designing and implementing a Positioning System (PS) that is addressed as a component of the Location-aware Museum Guide System (GMS). The level of accuracy of the Positioning System (PS) is an important aspect in determining the suitability of the information received by the visitors. The design flow of the system begins by identifying the location of implementation. After that, choose the components to build the system. The principle used in this study is the use of existing infrastructure to reduce the cost of system development. A recent study was completed in the museum gathered information about the museum environment to assist with the design process. The system design is proposed by using WLAN technology with RSSI-based fingerprinting techniques. The algorithm used for this fingerprint technique is KNN. The addition of Access Point (AP) and AP filtering methods were also applied to improve the system performance. The test results showed that there were significant differences on accuracy level of PS among three times trial tested to the expectation of accuracy level at 1.2 meter. First trial was without additional support the existing infrastructure in the Museum is unable to provide an accurate estimating position. It was only 3.75 m. The second was by adding five APs from 6 to 11 APs, the accuracy level was 2.55 m. The last was to implement the AP filtering. It can provide improvement to 1.83 m.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"38 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":"124989652","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878568
B. A. Ashad, I. Gunadin, A. Siswanto, Yusran
The electrical systems, the addition of loads can result in fewer stability limits, if there is interference, it can cause black out. In this study analyzing early warning, by observing the limits of stability in the event of a disturbance before black out in the South Sulawesi electricity system. This study observed an early warning system consisting of 44 buses and 15 generators using a Voltage stability margin (VSM) in the event of a disruption. From the training data about each disruption from various buses that occur then learning to use Extreme Learning (ELM) engines is used to detect early warnings during transient conditions. From the ELM simulation results can work quickly 0.0001 and 0.0024 and the error value is low so that it can be known before a blackout occurs.
{"title":"Early Warning Condition Transient Stability on South Sulawesi System using Extreme Learning Machine","authors":"B. A. Ashad, I. Gunadin, A. Siswanto, Yusran","doi":"10.1109/EIConCIT.2018.8878568","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878568","url":null,"abstract":"The electrical systems, the addition of loads can result in fewer stability limits, if there is interference, it can cause black out. In this study analyzing early warning, by observing the limits of stability in the event of a disturbance before black out in the South Sulawesi electricity system. This study observed an early warning system consisting of 44 buses and 15 generators using a Voltage stability margin (VSM) in the event of a disruption. From the training data about each disruption from various buses that occur then learning to use Extreme Learning (ELM) engines is used to detect early warnings during transient conditions. From the ELM simulation results can work quickly 0.0001 and 0.0024 and the error value is low so that it can be known before a blackout occurs.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"48 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":"124674200","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878672
Wistiani Astuti, Lilis Nur Hayati, Abdul Rachman Manga’, Herdianti Darwis, Yulita Salim, Harlinda, Poetri Lestari Lokapitasari Belluano
Paraphilia is still not widely known by the public. Lack of information about paraphilia is a serious concern of the Makassar City Government. This is because there are 12 types of paraphilia and some of them are contagious diseases such as fetishism, transvestism, sadomasochism, pedophilia, transsexualism, voyeurism, exhibitionism. There are several paraphilia diseases that are difficult to distinguish. The nature of paraphilia can be seen by society through its given (nature) and caused by environmental influences. In this study, the K-Nearest Neighbor (KNN) method has been applied to categorize the disease. The dataset used is derived from observations of 250 datasets. The dataset is divided into two, training data (165) and testing data (70). Based on the experiment, the k-NN method has an accuracy of Confusion Matrix of 8l%. On the other hand, the k-NN method is able to classify 12 venereal diseases quite accurately. Thus, this method was good as an alternative method for the classification task. For future research, optimization of the application will be performed to increase the accuracy of kNN.
{"title":"A Performance of K-Nearest Neighbor Classification in Paraphilia Disease","authors":"Wistiani Astuti, Lilis Nur Hayati, Abdul Rachman Manga’, Herdianti Darwis, Yulita Salim, Harlinda, Poetri Lestari Lokapitasari Belluano","doi":"10.1109/EIConCIT.2018.8878672","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878672","url":null,"abstract":"Paraphilia is still not widely known by the public. Lack of information about paraphilia is a serious concern of the Makassar City Government. This is because there are 12 types of paraphilia and some of them are contagious diseases such as fetishism, transvestism, sadomasochism, pedophilia, transsexualism, voyeurism, exhibitionism. There are several paraphilia diseases that are difficult to distinguish. The nature of paraphilia can be seen by society through its given (nature) and caused by environmental influences. In this study, the K-Nearest Neighbor (KNN) method has been applied to categorize the disease. The dataset used is derived from observations of 250 datasets. The dataset is divided into two, training data (165) and testing data (70). Based on the experiment, the k-NN method has an accuracy of Confusion Matrix of 8l%. On the other hand, the k-NN method is able to classify 12 venereal diseases quite accurately. Thus, this method was good as an alternative method for the classification task. For future research, optimization of the application will be performed to increase the accuracy of kNN.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"77 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":"121915446","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 : 2018-11-01DOI: 10.1109/eiconcit.2018.8878548
M. Tsuru
In response to the explosive growth of network traffic as well as the continuous increase of network applications diversity and complexity, fair and effective network resource sharing among multiple users/applications are essential. In this talk, after briefly viewing recent trends in communication networks, we survey and discuss the concept of fairness in terms of achieved performance of each user through a few simple examples in wireless and wired networks. Then we go into more detail about one example and see how a network control scheme works to realize fair and effective resource sharing
{"title":"Keynote Speech 1 Fair and Effective Resource Sharing in Network Control","authors":"M. Tsuru","doi":"10.1109/eiconcit.2018.8878548","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878548","url":null,"abstract":"In response to the explosive growth of network traffic as well as the continuous increase of network applications diversity and complexity, fair and effective network resource sharing among multiple users/applications are essential. In this talk, after briefly viewing recent trends in communication networks, we survey and discuss the concept of fairness in terms of achieved performance of each user through a few simple examples in wireless and wired networks. Then we go into more detail about one example and see how a network control scheme works to realize fair and effective resource sharing","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"26 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":"128894583","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878572
I. Nuritha, A. A. Arifiyanti, Vandha Widartha
Productivity of organic coffee plants in Indonesia is still lower if compared by productivity of coffee which use ordinary cultivation. One of the problems, which is faced by farmers to develop organic coffee is no certainty market. This could be because not all people of Indonesia are able to buy organic coffee products which quite expensive. Based on these, it is necessary to analyze public perception sentiment of organic coffee products, to identify potential and opportunities the development of organic coffee farming in Indonesia. This research uses a text mining approach to classify the public perception sentiment on organic coffee products based on tweet which posted in social media, i.e., twitter. Sentiment classification is performed by Naïve Bayes Classifier algorithm. The most of sentiment value formed in this research is positive sentiment. These results show that the public perception on organic coffee is in positive manner. So that the prospect of organic coffee plants development in Indonesia and the market opportunity of organic coffee products are predicted to rise as well.
{"title":"Analysis of Public Perception on Organic Coffee through Text Mining Approach using Naïve Bayes Classifier","authors":"I. Nuritha, A. A. Arifiyanti, Vandha Widartha","doi":"10.1109/EIConCIT.2018.8878572","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878572","url":null,"abstract":"Productivity of organic coffee plants in Indonesia is still lower if compared by productivity of coffee which use ordinary cultivation. One of the problems, which is faced by farmers to develop organic coffee is no certainty market. This could be because not all people of Indonesia are able to buy organic coffee products which quite expensive. Based on these, it is necessary to analyze public perception sentiment of organic coffee products, to identify potential and opportunities the development of organic coffee farming in Indonesia. This research uses a text mining approach to classify the public perception sentiment on organic coffee products based on tweet which posted in social media, i.e., twitter. Sentiment classification is performed by Naïve Bayes Classifier algorithm. The most of sentiment value formed in this research is positive sentiment. These results show that the public perception on organic coffee is in positive manner. So that the prospect of organic coffee plants development in Indonesia and the market opportunity of organic coffee products are predicted to rise as well.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"28 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":"129441976","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 : 2018-11-01DOI: 10.1109/eiconcit.2018.8878580
{"title":"Call for Paper 3rd 2019 EIConCIT","authors":"","doi":"10.1109/eiconcit.2018.8878580","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878580","url":null,"abstract":"","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","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":"130178323","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}
Tumor and cyst are two dangerous gum diseases commonly found in the mouth. However, unnoticed signs and symptoms in the early stages of them frequently lead to the late treatment of recovery. Earlier detection to them as a preventive care before becoming a chronic cancer is considered important leading to earlier diagnosis and treatment. Feature selection before detection and classification plays a vital role in order to maximize the classification accuracy. In this research, an implementation of principal component analysis (PCA) is proposed to overcome the high dimensionality of the dental panoramic images. This research is intended to offer a solution in selecting the most dominant and principal features to prevent the features weaken the accuracy. It has figured out that by using PCA, there are only four features that dominant among 33 features extracted. This means that only 12% of overall features significantly play a dominant role. Variance of these features affects the proportion contributed. Components that have a proportion of contribution greater than 1% are PC1, PC2, PC3, PC4, each of 86.44%, 9.74%, 2.59%, and 1,125%. The four dominant features which have been found are Feature 21, 22, 24, and 27 extracted by using GLRLM with SRE, LRE, RP, and HGRE respectively in other words, the 4 selected features represent 99.7% of the overall data variance representing 99.7% of the overall data variance.
{"title":"Feature Selection of Oral Cyst and Tumor Images Using Principal Component Analysis","authors":"Syahrul Mubarak, Herdianti Darwis, Fitriyani Umar, Lutfi Budi Ilmawan, Siska Anraeni, Muh. Aliyazid Mude","doi":"10.1109/EIConCIT.2018.8878641","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878641","url":null,"abstract":"Tumor and cyst are two dangerous gum diseases commonly found in the mouth. However, unnoticed signs and symptoms in the early stages of them frequently lead to the late treatment of recovery. Earlier detection to them as a preventive care before becoming a chronic cancer is considered important leading to earlier diagnosis and treatment. Feature selection before detection and classification plays a vital role in order to maximize the classification accuracy. In this research, an implementation of principal component analysis (PCA) is proposed to overcome the high dimensionality of the dental panoramic images. This research is intended to offer a solution in selecting the most dominant and principal features to prevent the features weaken the accuracy. It has figured out that by using PCA, there are only four features that dominant among 33 features extracted. This means that only 12% of overall features significantly play a dominant role. Variance of these features affects the proportion contributed. Components that have a proportion of contribution greater than 1% are PC1, PC2, PC3, PC4, each of 86.44%, 9.74%, 2.59%, and 1,125%. The four dominant features which have been found are Feature 21, 22, 24, and 27 extracted by using GLRLM with SRE, LRE, RP, and HGRE respectively in other words, the 4 selected features represent 99.7% of the overall data variance representing 99.7% of the overall data variance.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","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":"130024935","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 : 2018-11-01DOI: 10.1109/eiconcit.2018.8878588
Rayner Alfred
Over the last few years, the concept of e-government has enabled governments to serve the public using the Internet. It also allowed governments to capture data, process and report on data efficiently and improve on their decision making. However, the advances in smart technologies (e.g., Artificial Intelligence and Machine Learning), better informed and connected citizens, and global connected economies have created opportunities, forcing governments to rethink their role in today’s society. With the rise of people awareness about the fourth industrial revolution (IR4.0), driven by four disruptions: the astonishing rise in data volumes, computational power, and connectivity, especially new low-power wide-area networks; the emergence of analytics and business-intelligence capabilities; government should look into a few opportunities to transform from e-government into a modern and smart government. Local governments can now gather real time data, combined with the capabilities of artificial intelligence, and are realizing interesting new ways to run more efficiently and effectively. Artificial Intelligence is a collection of advanced technologies that allows machines to sense, comprehend, act and learn. Some of the key applications include intelligent automation, robotic process automation, cognitive robotics, virtual agents, machine learning and deep learning, natural language processing and video analytics. It was unrealistic to apply artificial intelligence or machine learning to many areas of government administration before. But now even more exciting, machines can now analyze things that humans might not have been able to do so before. In this talk, we will share some of the machine learning algorithms that can now be applied in transforming Sabah e- Government to smart government. Particularly, we will look several applications that can be used to enhance the effectiveness of Sabah administration that include detecting fake news, measuring public opinion using sentiment analysis, learning how people use cities/buildings in order to optimize infrastructures in cities/buildings, improving public safety in cities/buildings and improving services and productivity.
{"title":"Keynote Speech 2 How Machine Intelligence Transforms Sabah E-Government to Smart Government","authors":"Rayner Alfred","doi":"10.1109/eiconcit.2018.8878588","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878588","url":null,"abstract":"Over the last few years, the concept of e-government has enabled governments to serve the public using the Internet. It also allowed governments to capture data, process and report on data efficiently and improve on their decision making. However, the advances in smart technologies (e.g., Artificial Intelligence and Machine Learning), better informed and connected citizens, and global connected economies have created opportunities, forcing governments to rethink their role in today’s society. With the rise of people awareness about the fourth industrial revolution (IR4.0), driven by four disruptions: the astonishing rise in data volumes, computational power, and connectivity, especially new low-power wide-area networks; the emergence of analytics and business-intelligence capabilities; government should look into a few opportunities to transform from e-government into a modern and smart government. Local governments can now gather real time data, combined with the capabilities of artificial intelligence, and are realizing interesting new ways to run more efficiently and effectively. Artificial Intelligence is a collection of advanced technologies that allows machines to sense, comprehend, act and learn. Some of the key applications include intelligent automation, robotic process automation, cognitive robotics, virtual agents, machine learning and deep learning, natural language processing and video analytics. It was unrealistic to apply artificial intelligence or machine learning to many areas of government administration before. But now even more exciting, machines can now analyze things that humans might not have been able to do so before. In this talk, we will share some of the machine learning algorithms that can now be applied in transforming Sabah e- Government to smart government. Particularly, we will look several applications that can be used to enhance the effectiveness of Sabah administration that include detecting fake news, measuring public opinion using sentiment analysis, learning how people use cities/buildings in order to optimize infrastructures in cities/buildings, improving public safety in cities/buildings and improving services and productivity.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"42 41","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133787430","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878627
Nurul Hardiyanti, A. Lawi, Diaraya, F. Aziz
Rapid technological development at this time is not only recognized by humans, now sensors embedded in smartphones can also recognize human activity using an accelerometer sensor and gyroscope sensor that has been embedded in it by producing hundreds or even thousands of records. accelerometer sensor and gyroscope sensor is one feature that serves to read the rate of change of acceleration from a smartphone but has a different function and requires data mining methods to group based on that output. Data mining methods that have better performance than other methods are Support Vector Machine (SVM) but are sensitive to parameter settings and sample training that cause undefined performance to overcome the shortcomings of the Support Vector Machine method by performing SVM ensembles, which are ensemble used is bagging. This research proposes the application of svm ensemble technique to perform human activity classification based on accelerometer sensor and gyroscope sensor. The results show that the best performance of SVM ensemble technique when comparing datasets with 70% training data and 30% test data with 99.1% accuracy, sensitivity 99.6% and specificity 98.7%.
{"title":"Classification of Human Activity based on Sensor Accelerometer and Gyroscope Using Ensemble SVM method","authors":"Nurul Hardiyanti, A. Lawi, Diaraya, F. Aziz","doi":"10.1109/EIConCIT.2018.8878627","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878627","url":null,"abstract":"Rapid technological development at this time is not only recognized by humans, now sensors embedded in smartphones can also recognize human activity using an accelerometer sensor and gyroscope sensor that has been embedded in it by producing hundreds or even thousands of records. accelerometer sensor and gyroscope sensor is one feature that serves to read the rate of change of acceleration from a smartphone but has a different function and requires data mining methods to group based on that output. Data mining methods that have better performance than other methods are Support Vector Machine (SVM) but are sensitive to parameter settings and sample training that cause undefined performance to overcome the shortcomings of the Support Vector Machine method by performing SVM ensembles, which are ensemble used is bagging. This research proposes the application of svm ensemble technique to perform human activity classification based on accelerometer sensor and gyroscope sensor. The results show that the best performance of SVM ensemble technique when comparing datasets with 70% training data and 30% test data with 99.1% accuracy, sensitivity 99.6% and specificity 98.7%.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"58 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":"127972006","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：