Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234269
Ilham Cahya Suherman, R. Sarno, Sholiq
One of Project Manager early activity is to estimate time, and cost based on given scope, which can help project manager to plan schedule and used resources. Estimation is very important in project management because a bad result of estimation will result in bad management of project and may cause failure. There are methods that can be used to estimate software development effort; COCOMO II is one method that commonly used. Many researcher before have been used algorithm, such as Bat, Bee Colony, or MOPSO to increase COCOMO II estimation accuracy. However, as the technology advanced, there are a lot more options that can be used to predict software effort estimation based on COCOMO, such as machine learning. In this paper, we compare machine learning algorithm with tuning parameter method to know whether tuning parameter estimation is better than machine learning estimation or vice versa. In this paper, we use Random Forest Regression as machine learning algorithm to estimate the effort. We also compare it with another machine learning algorithm, Support Vector Regression, and Bee Colony Method as parameter tuning method. The results of experiment is evaluated by their error rate. The results show that Random Forest Regression is better than Support Vector Regression and Bee Colony Method.
{"title":"Implementation of Random Forest Regression for COCOMO II Effort Estimation","authors":"Ilham Cahya Suherman, R. Sarno, Sholiq","doi":"10.1109/iSemantic50169.2020.9234269","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234269","url":null,"abstract":"One of Project Manager early activity is to estimate time, and cost based on given scope, which can help project manager to plan schedule and used resources. Estimation is very important in project management because a bad result of estimation will result in bad management of project and may cause failure. There are methods that can be used to estimate software development effort; COCOMO II is one method that commonly used. Many researcher before have been used algorithm, such as Bat, Bee Colony, or MOPSO to increase COCOMO II estimation accuracy. However, as the technology advanced, there are a lot more options that can be used to predict software effort estimation based on COCOMO, such as machine learning. In this paper, we compare machine learning algorithm with tuning parameter method to know whether tuning parameter estimation is better than machine learning estimation or vice versa. In this paper, we use Random Forest Regression as machine learning algorithm to estimate the effort. We also compare it with another machine learning algorithm, Support Vector Regression, and Bee Colony Method as parameter tuning method. The results of experiment is evaluated by their error rate. The results show that Random Forest Regression is better than Support Vector Regression and Bee Colony Method.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115513682","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234196
Petricia Pungki, Christy Atika Sari, De Rosal Ignatius Moses Setiadi, Eko Hari Rachmawanto
Plants have an important role in human life. Several plants can be used for daily life, namely as food, in the health sector, to become a main ingredient for the industry. Plant type classification techniques using data mining methods become one of the efforts to help humans produce more accurate and consistent classifications. The learning process in the classification method requires good dataset quality, where a small number of datasets will affect the results of the classification. The main objective of this research is to test the Artificial Neural Network (ANN) method for classifying plant species in a relatively small dataset. Three stages are proposed, namely preprocessing using image segmentation thresholding methods and morphological operations, and the extraction of metric and eccentricity features. Based on the results of testing the ANN method can also work well with relatively small datasets, which results in accuracy reaching 96% with the number of training data 125 and testing data 25.
{"title":"Classification of Plant Types based on Leaf Image using the Artificial Neural Network Method","authors":"Petricia Pungki, Christy Atika Sari, De Rosal Ignatius Moses Setiadi, Eko Hari Rachmawanto","doi":"10.1109/iSemantic50169.2020.9234196","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234196","url":null,"abstract":"Plants have an important role in human life. Several plants can be used for daily life, namely as food, in the health sector, to become a main ingredient for the industry. Plant type classification techniques using data mining methods become one of the efforts to help humans produce more accurate and consistent classifications. The learning process in the classification method requires good dataset quality, where a small number of datasets will affect the results of the classification. The main objective of this research is to test the Artificial Neural Network (ANN) method for classifying plant species in a relatively small dataset. Three stages are proposed, namely preprocessing using image segmentation thresholding methods and morphological operations, and the extraction of metric and eccentricity features. Based on the results of testing the ANN method can also work well with relatively small datasets, which results in accuracy reaching 96% with the number of training data 125 and testing data 25.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682252","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234262
Rakha Asyrofi, Yoni Azhar Winata, R. Sarno, Aziz Fajar
K-means clustering can be used as an algorithm segmentation that can split an area of interest from the image into several different regions containing each pixel based on color. Nevertheless, the result of the color division of the clustering has not been able to display clean segmentation because there are still pixels that connect each other and produce pixel noise or unwanted pixels. In this work, we propose a technique where it can select four dominant colors from the k-means clustering results then display it as digital image output. In our approach, the proposed method can separate the cerebellum and frontal lobe from the background of the brain after several operations of morphological transformation. In implementing this method, three samples of the brain from different people were tested. From the experimental results, the DSI produces a value of 0.72 from 1 for the frontal lobe and 0.86 from 1 for the cerebellum. It means that the proposed method can segment the desired part of the brain properly.
{"title":"Cerebellum and Frontal Lobe Segmentation Based on K-Means Clustering and Morphological Transformation","authors":"Rakha Asyrofi, Yoni Azhar Winata, R. Sarno, Aziz Fajar","doi":"10.1109/iSemantic50169.2020.9234262","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234262","url":null,"abstract":"K-means clustering can be used as an algorithm segmentation that can split an area of interest from the image into several different regions containing each pixel based on color. Nevertheless, the result of the color division of the clustering has not been able to display clean segmentation because there are still pixels that connect each other and produce pixel noise or unwanted pixels. In this work, we propose a technique where it can select four dominant colors from the k-means clustering results then display it as digital image output. In our approach, the proposed method can separate the cerebellum and frontal lobe from the background of the brain after several operations of morphological transformation. In implementing this method, three samples of the brain from different people were tested. From the experimental results, the DSI produces a value of 0.72 from 1 for the frontal lobe and 0.86 from 1 for the cerebellum. It means that the proposed method can segment the desired part of the brain properly.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125976461","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234256
Agustinus Bimo Gumelar, H. Setyorini, Derry Pramono Adi, Sengguruh Nilowardono, Latipah, Agung Widodo, Achmad Teguh Wibowo, M. T. Sulistyono, Evy Christine
Stock exchange is one of the famous economical strategy that finally find its way to be experimented with ever-growing Machine Learning (ML) algorithm. With ML, many aspects regarding stock is learnable, to the point where one can predict stock prices. Although tempting, stock price prediction is still a challenging task due to its natural dynamic and real-time movement. Thus, predicting stock prices are deemed unseemingly. On the other hand, different patterns of stock prices are capable of represent a whole lot of detailed data, which is in favor for Deep Learning. In this study, we conducted an experiment of predicting the close stock price for 25 companies. To ensure data reliability and regional notion, these selected companies are officially enlisted in the Indonesia Stock Exchange (IDX). The two ML algorithms used for this experiment are the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost), both known for its high accuracy of prediction from various representative data. By setting two thresholds, we were able to present a trading approach: when to buy or when to sell. This prediction result from the ML algorithm using in the ensuing trading approach leads to distinct aspects of benefit. In this experiment, XGBoost shown best performance by 99% prediction accuracy result.
{"title":"Boosting the Accuracy of Stock Market Prediction using XGBoost and Long Short-Term Memory","authors":"Agustinus Bimo Gumelar, H. Setyorini, Derry Pramono Adi, Sengguruh Nilowardono, Latipah, Agung Widodo, Achmad Teguh Wibowo, M. T. Sulistyono, Evy Christine","doi":"10.1109/iSemantic50169.2020.9234256","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234256","url":null,"abstract":"Stock exchange is one of the famous economical strategy that finally find its way to be experimented with ever-growing Machine Learning (ML) algorithm. With ML, many aspects regarding stock is learnable, to the point where one can predict stock prices. Although tempting, stock price prediction is still a challenging task due to its natural dynamic and real-time movement. Thus, predicting stock prices are deemed unseemingly. On the other hand, different patterns of stock prices are capable of represent a whole lot of detailed data, which is in favor for Deep Learning. In this study, we conducted an experiment of predicting the close stock price for 25 companies. To ensure data reliability and regional notion, these selected companies are officially enlisted in the Indonesia Stock Exchange (IDX). The two ML algorithms used for this experiment are the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost), both known for its high accuracy of prediction from various representative data. By setting two thresholds, we were able to present a trading approach: when to buy or when to sell. This prediction result from the ML algorithm using in the ensuing trading approach leads to distinct aspects of benefit. In this experiment, XGBoost shown best performance by 99% prediction accuracy result.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121866959","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234301
Rahmat Awaludin Rizal, R. Sarno, Kelly Rossa Sungkono
The information and communication technology development has increased to fulfil processes of an organization. It needs to be structured to create a clean, competent, evident and liable government and a quality and reliable civil service. With the existence of a system of electronic-based government system (SPBE), one of the regional governments that implemented SPBE is East Java Province by generating SPBE index value of 2.92. The SPBE value shows the SPBE implementation quality is still below the expected value, which is 3. By using COBIT 5 Framework, this research obtains levels of selected process capabilities, i.e. EDM05, APO01, APO04, APO06, are below 3rd level (Established). This research also gives recommendations for improving the level of the process capability.
{"title":"COBIT 5 for Analysing Information Technology Governance Maturity Level on Masterplan E-Government","authors":"Rahmat Awaludin Rizal, R. Sarno, Kelly Rossa Sungkono","doi":"10.1109/iSemantic50169.2020.9234301","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234301","url":null,"abstract":"The information and communication technology development has increased to fulfil processes of an organization. It needs to be structured to create a clean, competent, evident and liable government and a quality and reliable civil service. With the existence of a system of electronic-based government system (SPBE), one of the regional governments that implemented SPBE is East Java Province by generating SPBE index value of 2.92. The SPBE value shows the SPBE implementation quality is still below the expected value, which is 3. By using COBIT 5 Framework, this research obtains levels of selected process capabilities, i.e. EDM05, APO01, APO04, APO06, are below 3rd level (Established). This research also gives recommendations for improving the level of the process capability.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122143148","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234255
Prima R. Maulidina, R. Sarno, K. R. Sungkono, Tantya A. Giranita
This study aims to discover the factors that influence users in using Shopee e-commerce. One of the ways to know the contributing factor that influences users is the Unified Theory of Acceptance and Usage of Technology 2 (UTAUT2). UTAUT2 is a known model that could determine the factors thoroughly. However, this study uses seven constructs from UTAUT2 with two additional constructs. For this, the study has targeted 160 Indonesian respondents who have done transactions on Shopee e-commerce in Indonesia. Furthermore, data analysis in this study used Partial Least Squares-Structural Equation Model (PLS-SEM) on SmartPLS software due to its ability to analyze data with a small sample size, even if the model used is complex. The results show that Habit and Trust in Interest are significantly influencing Behavioral Intention. In contrast, other factors such as Hedonic Motivation, Effort Expectancy, Facilitating Conditions, Performance Expectancy, Social Influence, Price Value, and Perceived Transaction Risk do not significantly influence Behavioral Intention in using Shopee. Moderating variables like age, gender, and experience do not significantly influence the relationship between independent variables and Behavioral Intention of users. The extension of the original constructs from UTAUT2 with two additional constructs from two previous studies is the novelty contribution in this study.
{"title":"Using Extended UTAUT2 Model to Determine Factors Influencing the Use of Shopee E-commerce","authors":"Prima R. Maulidina, R. Sarno, K. R. Sungkono, Tantya A. Giranita","doi":"10.1109/iSemantic50169.2020.9234255","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234255","url":null,"abstract":"This study aims to discover the factors that influence users in using Shopee e-commerce. One of the ways to know the contributing factor that influences users is the Unified Theory of Acceptance and Usage of Technology 2 (UTAUT2). UTAUT2 is a known model that could determine the factors thoroughly. However, this study uses seven constructs from UTAUT2 with two additional constructs. For this, the study has targeted 160 Indonesian respondents who have done transactions on Shopee e-commerce in Indonesia. Furthermore, data analysis in this study used Partial Least Squares-Structural Equation Model (PLS-SEM) on SmartPLS software due to its ability to analyze data with a small sample size, even if the model used is complex. The results show that Habit and Trust in Interest are significantly influencing Behavioral Intention. In contrast, other factors such as Hedonic Motivation, Effort Expectancy, Facilitating Conditions, Performance Expectancy, Social Influence, Price Value, and Perceived Transaction Risk do not significantly influence Behavioral Intention in using Shopee. Moderating variables like age, gender, and experience do not significantly influence the relationship between independent variables and Behavioral Intention of users. The extension of the original constructs from UTAUT2 with two additional constructs from two previous studies is the novelty contribution in this study.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121537384","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234264
Nadia Salsabila, R. A. Palembiya, K. R. Sungkono, R. Sarno
Event log records all events of performed business process on the system. Analysts used the event log to detect occurred anomalies, one of which is wrong pattern, in the process. However, there are conditions, i.e. skip condition, redo condition, and switch condition, which can be misinterpreted as wrong pattern. Uniquely, those conditions cannot be depicted in the reference model without utilizing additional tasks, namely invisible tasks. This research proposes rules which can check the wrong pattern in the process model containing those conditions. This research automatically formed declarative miner rules carrying invisible tasks based on a process model. The form of the used process model in this research is a graph model. Then, the rules are used to checking the wrong pattern. The experiment uses real data, i.e. port-container handling processes, and several simulation data. The analysis explains that declarative miners have 100% accuracy to check the wrong pattern in the process model that contains each invisible task including skip condition, redo condition, and switch condition.
{"title":"Checking Wrong Pattern in Process Model Containing Invisible Task by Using Declarative Miner","authors":"Nadia Salsabila, R. A. Palembiya, K. R. Sungkono, R. Sarno","doi":"10.1109/iSemantic50169.2020.9234264","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234264","url":null,"abstract":"Event log records all events of performed business process on the system. Analysts used the event log to detect occurred anomalies, one of which is wrong pattern, in the process. However, there are conditions, i.e. skip condition, redo condition, and switch condition, which can be misinterpreted as wrong pattern. Uniquely, those conditions cannot be depicted in the reference model without utilizing additional tasks, namely invisible tasks. This research proposes rules which can check the wrong pattern in the process model containing those conditions. This research automatically formed declarative miner rules carrying invisible tasks based on a process model. The form of the used process model in this research is a graph model. Then, the rules are used to checking the wrong pattern. The experiment uses real data, i.e. port-container handling processes, and several simulation data. The analysis explains that declarative miners have 100% accuracy to check the wrong pattern in the process model that contains each invisible task including skip condition, redo condition, and switch condition.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115217750","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234226
Hadapininglaksmi Astri Purwanithami, Christy Atika Sari, E. H. Rachmawanto, De Rosal Ignatius Moses Setiadi
Hemorrhage Diabetic Retinopathy is a type of diabetes that attacks the blood vessels of the retina. This disease can cause blindness, but early treatment can minimize this. This research proposes a method of detecting blood vessels in the retina caused by Hemorrhage Diabetic Retinopathy. Detection is based on the Fundus image based on several stages of preprocessing, segmentation, and detection. At the preprocessing stage, the fundus image with the RGB image format is taken the green channel to do a contrast enhancement operation with CLAHE and segmentation with FCM. Then the detection is done using the Neural Network method. At the experimental stage, 100 testing images are used which are divided into two classes, namely Hemorrhage and Non-Hemorrhage. Detection results showed from 100 images, only one image was detected incorrectly, so it can be concluded that the detection accuracy reached 99%.
{"title":"Hemorrhage Diabetic Retinopathy Detection based on Fundus Image using Neural Network and FCM Segmentation","authors":"Hadapininglaksmi Astri Purwanithami, Christy Atika Sari, E. H. Rachmawanto, De Rosal Ignatius Moses Setiadi","doi":"10.1109/iSemantic50169.2020.9234226","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234226","url":null,"abstract":"Hemorrhage Diabetic Retinopathy is a type of diabetes that attacks the blood vessels of the retina. This disease can cause blindness, but early treatment can minimize this. This research proposes a method of detecting blood vessels in the retina caused by Hemorrhage Diabetic Retinopathy. Detection is based on the Fundus image based on several stages of preprocessing, segmentation, and detection. At the preprocessing stage, the fundus image with the RGB image format is taken the green channel to do a contrast enhancement operation with CLAHE and segmentation with FCM. Then the detection is done using the Neural Network method. At the experimental stage, 100 testing images are used which are divided into two classes, namely Hemorrhage and Non-Hemorrhage. Detection results showed from 100 images, only one image was detected incorrectly, so it can be concluded that the detection accuracy reached 99%.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121557856","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234253
A. S. Shahab, R. Sarno
The Attendance system, especially in companies is needed to help assess the attendance and discipline of employees. Some attendance systems that have been made based on the detection of biometrics, barcodes, and QR Codes have not been able to simplify the attendance process where employees still have to queue in front of the attendance machine. This paper aims to design an attendance system that flexible which can simplify and speed up the process by using a mobile application based on geofencing and face recognition so the company does not need to expend the extra cost to buy dedicated machine. The system is using a mobile application as a device to presence. Each of the employees has their own geofencing area which worked as a location virtual boundary. The employee face images are sent to the server from mobile application for the attendance process which includes a recognition process using k-Nearest Neighbours (k-NN) and Principal Component Analysis (PCA). The results obtained are using face recognition k-NN and PCA obtained a 90% accuracy rate with a processing time of 1.5 seconds. The fastest time to do a complete presence is 3.4s which include a geofencing authentication and face recognition process.
{"title":"Android Application for Presence Recognition based on Face and Geofencing","authors":"A. S. Shahab, R. Sarno","doi":"10.1109/iSemantic50169.2020.9234253","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234253","url":null,"abstract":"The Attendance system, especially in companies is needed to help assess the attendance and discipline of employees. Some attendance systems that have been made based on the detection of biometrics, barcodes, and QR Codes have not been able to simplify the attendance process where employees still have to queue in front of the attendance machine. This paper aims to design an attendance system that flexible which can simplify and speed up the process by using a mobile application based on geofencing and face recognition so the company does not need to expend the extra cost to buy dedicated machine. The system is using a mobile application as a device to presence. Each of the employees has their own geofencing area which worked as a location virtual boundary. The employee face images are sent to the server from mobile application for the attendance process which includes a recognition process using k-Nearest Neighbours (k-NN) and Principal Component Analysis (PCA). The results obtained are using face recognition k-NN and PCA obtained a 90% accuracy rate with a processing time of 1.5 seconds. The fastest time to do a complete presence is 3.4s which include a geofencing authentication and face recognition process.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132670510","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234278
Agustinus Rudatyo Himamunanto, Supriadi Rustad, M. Arief Soeleman, Guruh Fajar Sidhik
Hand gesture dataset is a collection of hand gesture images. Several hand gesture datasets are freely available and can be used for various purposes, such as comparison or method testing. Processing the distribution of hand gesture image quality in the dataset has the opportunity to find potential models of hand gesture image quality for further research. This study tries to provide answers by exploring the quality of hand gesture images based on various datasets of public hand gestures. Then perform feature extraction based on the image histogram profile to get an overview of the range of color intensity values from the hand gesture image. The Herarchical Clustering method is used to build clusters based on histogram characteristics. The feasibility of the relationship between clusters was tested based on the silhouette index clustering method. The total number of hand gesture test images is 16 thousand data taken from 6 dataset sources that have been used in hand gesture recognition research. Based on the results of the processing, it is shown that the three clusters have no relationship feasibility or in other words the image clusters are independent.
{"title":"Silhouette Analysis of Hand Gesture Dataset Using Histogram Profile Feature Extraction","authors":"Agustinus Rudatyo Himamunanto, Supriadi Rustad, M. Arief Soeleman, Guruh Fajar Sidhik","doi":"10.1109/iSemantic50169.2020.9234278","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234278","url":null,"abstract":"Hand gesture dataset is a collection of hand gesture images. Several hand gesture datasets are freely available and can be used for various purposes, such as comparison or method testing. Processing the distribution of hand gesture image quality in the dataset has the opportunity to find potential models of hand gesture image quality for further research. This study tries to provide answers by exploring the quality of hand gesture images based on various datasets of public hand gestures. Then perform feature extraction based on the image histogram profile to get an overview of the range of color intensity values from the hand gesture image. The Herarchical Clustering method is used to build clusters based on histogram characteristics. The feasibility of the relationship between clusters was tested based on the silhouette index clustering method. The total number of hand gesture test images is 16 thousand data taken from 6 dataset sources that have been used in hand gesture recognition research. Based on the results of the processing, it is shown that the three clusters have no relationship feasibility or in other words the image clusters are independent.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131748586","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：