Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315338
Hery, Samuel Lukas, P. Yugopuspito, I. M. Murwantara, D. Krisnadi
Indonesia as a state maritime country has the largest ocean in the world and locates between two continents and two oceans (Figure 1). As a state maritime, Indonesia has a source power of nature which is very large both on land and at sea. Utilization of source power in waters particularly about catching fish in an area must comply with the provisions and regulations that apply, as well as follow procedures like fisheries are responsible, for it required a system that is effective and accurate. System monitoring and surveillance vessel fisheries are generally used in several countries around the world are using the instrument Vessel Monitoring System (VMS). The aim of this paper is to make a based web system that aims to determine the location of catching tuna. System has to be accurate and fast that beneficial for the fishermen who are looking for tuna in the waters of Indonesia. Two methods of machine learning are used in this research. There are Naives Bayes and Support Vector Machine. The results of this paper is a website that serves to determine the location of fishing tuna using the method of Naives Bayes and SVM -Based on Data VMS in the waters of Indonesia. The result shows that the accuracy of SVM is 97. 6 better than that of Naïve Bayes (94.2) in determining the tuna but some area Naïve Bayes is better.
{"title":"Website Design for Locating Tuna Fishing Spot Using Naïve Bayes and SVM Based on VMS Data on Indonesian Sea","authors":"Hery, Samuel Lukas, P. Yugopuspito, I. M. Murwantara, D. Krisnadi","doi":"10.1109/ISRITI51436.2020.9315338","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315338","url":null,"abstract":"Indonesia as a state maritime country has the largest ocean in the world and locates between two continents and two oceans (Figure 1). As a state maritime, Indonesia has a source power of nature which is very large both on land and at sea. Utilization of source power in waters particularly about catching fish in an area must comply with the provisions and regulations that apply, as well as follow procedures like fisheries are responsible, for it required a system that is effective and accurate. System monitoring and surveillance vessel fisheries are generally used in several countries around the world are using the instrument Vessel Monitoring System (VMS). The aim of this paper is to make a based web system that aims to determine the location of catching tuna. System has to be accurate and fast that beneficial for the fishermen who are looking for tuna in the waters of Indonesia. Two methods of machine learning are used in this research. There are Naives Bayes and Support Vector Machine. The results of this paper is a website that serves to determine the location of fishing tuna using the method of Naives Bayes and SVM -Based on Data VMS in the waters of Indonesia. The result shows that the accuracy of SVM is 97. 6 better than that of Naïve Bayes (94.2) in determining the tuna but some area Naïve Bayes is better.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115662823","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315469
N. Puspitasari, J. A. Widians, E. Budiman, M. Wati, Arvanda Eka Ramadhan
Dayak onion plants are traditionally used by the Dayak tribe as a medicinal plant to treat dental caries. This plant contains compounds that can inhibit the growth of bacteria that cause dental caries. The public has not yet known about alternative dental caries treatment derived from Dayak onions. This is due to the lack of public knowledge about how to early diagnose dental caries and how to treat using Dayak onions. Expert systems with the Certainty Factor method can be used as a solution in diagnosing early dental caries. The data used in this study consisted of 20 symptoms of dental caries and 6 types of dental caries. This study shows the percentage level of confidence in the results of the initial diagnosis of the type of dental caries suffered by using the certainty factor method and the handling of the diagnosis using the Dayak plant as an initial treatment solution. The results of the accuracy-test showed that the early dental caries diagnosis system was working well.
{"title":"Dayak Onion (Eleutherine palmifolia (L) Merr) as An Alternative Treatment in Early Detection of Dental Caries using Certainty Factor","authors":"N. Puspitasari, J. A. Widians, E. Budiman, M. Wati, Arvanda Eka Ramadhan","doi":"10.1109/ISRITI51436.2020.9315469","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315469","url":null,"abstract":"Dayak onion plants are traditionally used by the Dayak tribe as a medicinal plant to treat dental caries. This plant contains compounds that can inhibit the growth of bacteria that cause dental caries. The public has not yet known about alternative dental caries treatment derived from Dayak onions. This is due to the lack of public knowledge about how to early diagnose dental caries and how to treat using Dayak onions. Expert systems with the Certainty Factor method can be used as a solution in diagnosing early dental caries. The data used in this study consisted of 20 symptoms of dental caries and 6 types of dental caries. This study shows the percentage level of confidence in the results of the initial diagnosis of the type of dental caries suffered by using the certainty factor method and the handling of the diagnosis using the Dayak plant as an initial treatment solution. The results of the accuracy-test showed that the early dental caries diagnosis system was working well.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128446179","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315489
Rakha Asyrofi, D. Siahaan, Y. Priyadi
Changes in requirements are one of the critical problems that occur during requirement specification. A change in a requirement could trigger changes in other requirements. Thus the identification process requirement to respond and correct the truth, realistic, require, specific, measurable aspects. Previous work has focused on building a model of interdependency between the requirements. This study proposes a method to identify dependencies among requirements. The dependency relations refer to evolutionary requirements. The technique uses natural language processing to extract dependency relations. This research analyzes how to obtain feature extractions by including the following: 1) Gathering requirements statement from the SRS document, 2) Identifying dependencies between requirements, 3) Developing interdependency extraction methods and, 4) Modeling of the interdependency requirement. The expectation of this experiment indicates the interdependency graph model. This graph defines the interdependency in the (Software Requirement Specification) SRS document. This method gathers interdependency between SRS document requirements such as PART OF, AND, OR, & XOR. Therefore, getting the feature extraction to identify the interdependency requirement will be useful for solving specified requirements changing.
{"title":"Extraction Dependency Based on Evolutionary Requirement Using Natural Language Processing","authors":"Rakha Asyrofi, D. Siahaan, Y. Priyadi","doi":"10.1109/ISRITI51436.2020.9315489","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315489","url":null,"abstract":"Changes in requirements are one of the critical problems that occur during requirement specification. A change in a requirement could trigger changes in other requirements. Thus the identification process requirement to respond and correct the truth, realistic, require, specific, measurable aspects. Previous work has focused on building a model of interdependency between the requirements. This study proposes a method to identify dependencies among requirements. The dependency relations refer to evolutionary requirements. The technique uses natural language processing to extract dependency relations. This research analyzes how to obtain feature extractions by including the following: 1) Gathering requirements statement from the SRS document, 2) Identifying dependencies between requirements, 3) Developing interdependency extraction methods and, 4) Modeling of the interdependency requirement. The expectation of this experiment indicates the interdependency graph model. This graph defines the interdependency in the (Software Requirement Specification) SRS document. This method gathers interdependency between SRS document requirements such as PART OF, AND, OR, & XOR. Therefore, getting the feature extraction to identify the interdependency requirement will be useful for solving specified requirements changing.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130630618","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315372
F. Zulfira, S. Suyanto
There are several ways to detect glaucoma, one of the most accurate is the presence of peripapillary atrophy (PPA). PPA is located outside the optic disc around the optic nerve head (ONH) and sometimes looks vague which can cause misclassification, so other parameters that can detect glaucoma are needed. The calculation of the optic cup to disc ratio (CDR) is mostly done for glaucoma detection so that CDR can be considered in addition to the presence of PPA to improve classification results. In this paper, a multi-class glaucoma detection is developed using an active contour snake to get the value of the optic cup and optic disc to measure CDR and a support vector machine (SVM) for classification. Glaucoma is categorized into three classes: non-glaucoma, mild-glaucoma, and severe-glaucoma. Hence, the model can detect its severity which determines further treatment. Evaluation using two datasets of 210 retinal fundus images (165 train and 45 test) informs that the model reaches high accuracies of 95%.
{"title":"Detection of Multi-Class Glaucoma Using Active Contour Snakes and Support Vector Machine","authors":"F. Zulfira, S. Suyanto","doi":"10.1109/ISRITI51436.2020.9315372","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315372","url":null,"abstract":"There are several ways to detect glaucoma, one of the most accurate is the presence of peripapillary atrophy (PPA). PPA is located outside the optic disc around the optic nerve head (ONH) and sometimes looks vague which can cause misclassification, so other parameters that can detect glaucoma are needed. The calculation of the optic cup to disc ratio (CDR) is mostly done for glaucoma detection so that CDR can be considered in addition to the presence of PPA to improve classification results. In this paper, a multi-class glaucoma detection is developed using an active contour snake to get the value of the optic cup and optic disc to measure CDR and a support vector machine (SVM) for classification. Glaucoma is categorized into three classes: non-glaucoma, mild-glaucoma, and severe-glaucoma. Hence, the model can detect its severity which determines further treatment. Evaluation using two datasets of 210 retinal fundus images (165 train and 45 test) informs that the model reaches high accuracies of 95%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127483496","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315463
Fatima O Hamed, E. Supriyanto, S. Osman, Tarig Ahmed El Khider Ali
Major Depressive Disorder (MDD) is a serious medical condition that can affect many areas of a person's daily life significantly. MDD, caused by a combination of factors, will be debilitating if not detected and managed early. This is why it is the leading cause of disability around the world. If detected early, several treatment and management programs can be done, for example, change of lifestyle. There are models developed to predict the risk of individual suffering MDD but they have low sensitivity and specificity. In this study, a new MDD risk prediction model is developed using a novel equation and Artificial Neural Network (ANN). The model is created using risk factors of MDD that are categorized into three groups, which are psychological, social and biological. Two predictor methods are applied, first, using a conventional equation, then using an ANN tool. From the results, the conventional equation is able to provide the risk estimation for MDD. After comparing, ANN showed the ability to calculate the risk prediction of MDD with 70% test accuracy and found to have a better sensitivity and specificity than the existing models.
{"title":"Risk Prediction of Major Depressive Disorder using Artificial Neural Network","authors":"Fatima O Hamed, E. Supriyanto, S. Osman, Tarig Ahmed El Khider Ali","doi":"10.1109/ISRITI51436.2020.9315463","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315463","url":null,"abstract":"Major Depressive Disorder (MDD) is a serious medical condition that can affect many areas of a person's daily life significantly. MDD, caused by a combination of factors, will be debilitating if not detected and managed early. This is why it is the leading cause of disability around the world. If detected early, several treatment and management programs can be done, for example, change of lifestyle. There are models developed to predict the risk of individual suffering MDD but they have low sensitivity and specificity. In this study, a new MDD risk prediction model is developed using a novel equation and Artificial Neural Network (ANN). The model is created using risk factors of MDD that are categorized into three groups, which are psychological, social and biological. Two predictor methods are applied, first, using a conventional equation, then using an ANN tool. From the results, the conventional equation is able to provide the risk estimation for MDD. After comparing, ANN showed the ability to calculate the risk prediction of MDD with 70% test accuracy and found to have a better sensitivity and specificity than the existing models.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123931022","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315497
Wahyuni Eka Sari, Y. Kurniawati, P. Santosa
Papaya is one of the tropical fruits that is grown in Indonesia. The weather condition in Indonesia cause it to be attacked by pest and disease. The farmers have difficulty identifying them due to a lack of knowledge and obtaining information from experts. In this study, an expert system was developed to detect papaya disease. Expert knowledge is applied to the system so the farmer can use it to identify the condition without an expert. It is usually represented in the linguistic form, was converted into numbers using fuzzy reasoning, Triangular Fuzzy Number (TFN) membership function. Then the expert knowledge was processed using the Naïve Bayes Classifier to obtain the results of the disease classification. The test was also performed using forward chaining search methods. The accuracy was 88% for FNBC and 90% for forward chaining compared to expert knowledge.
{"title":"Papaya Disease Detection Using Fuzzy Naïve Bayes Classifier","authors":"Wahyuni Eka Sari, Y. Kurniawati, P. Santosa","doi":"10.1109/ISRITI51436.2020.9315497","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315497","url":null,"abstract":"Papaya is one of the tropical fruits that is grown in Indonesia. The weather condition in Indonesia cause it to be attacked by pest and disease. The farmers have difficulty identifying them due to a lack of knowledge and obtaining information from experts. In this study, an expert system was developed to detect papaya disease. Expert knowledge is applied to the system so the farmer can use it to identify the condition without an expert. It is usually represented in the linguistic form, was converted into numbers using fuzzy reasoning, Triangular Fuzzy Number (TFN) membership function. Then the expert knowledge was processed using the Naïve Bayes Classifier to obtain the results of the disease classification. The test was also performed using forward chaining search methods. The accuracy was 88% for FNBC and 90% for forward chaining compared to expert knowledge.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121905365","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315418
Ionut-Cristian Severin
The current paper proposes and presents a new wearable system for head posture recognition, based on three inertial sensors used to prevent inadequate head posture during different office daily activities. During this experiment, 9 daily office activities were evaluated. The proposed model distinguished between bad or good posture with a high accuracy using the inertial time series's raw data. The performance of the proposed wearable system was evaluated offline with the help of machine learning algorithms. The advantage of the proposed approach is the possibility of transmitting data through the Wi-Fi connection, portability, low cost, and high performance. During this experiment, the best classification performances it was obtained with Decision Extra Trees Classifier, that was achieved an accuracy equal to 96.78%.
本文提出并提出了一种新的头部姿势识别可穿戴系统，该系统基于三个惯性传感器，用于防止在不同的办公室日常活动中头部姿势不当。在本次实验中，我们评估了9项日常办公活动。该模型利用惯性时间序列的原始数据对姿态进行了高精度的区分。在机器学习算法的帮助下，离线评估了所提出的可穿戴系统的性能。该方法的优点是可以通过Wi-Fi连接传输数据、便携、低成本和高性能。在本实验中，Decision Extra Trees分类器的分类性能最好，准确率达到96.78%。
{"title":"The Head Posture System Based on 3 Inertial Sensors and Machine Learning Models: Offline Analyze","authors":"Ionut-Cristian Severin","doi":"10.1109/ISRITI51436.2020.9315418","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315418","url":null,"abstract":"The current paper proposes and presents a new wearable system for head posture recognition, based on three inertial sensors used to prevent inadequate head posture during different office daily activities. During this experiment, 9 daily office activities were evaluated. The proposed model distinguished between bad or good posture with a high accuracy using the inertial time series's raw data. The performance of the proposed wearable system was evaluated offline with the help of machine learning algorithms. The advantage of the proposed approach is the possibility of transmitting data through the Wi-Fi connection, portability, low cost, and high performance. During this experiment, the best classification performances it was obtained with Decision Extra Trees Classifier, that was achieved an accuracy equal to 96.78%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123198677","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315366
Huy Nguyen-Quoc, Vinh Truong Hoang
Automatic gender determination received many attentions in the recent years due to its potential applications in e-commerce and demographic data collection. Face and voice are the most common factors of human which are used to determine the gender. A comparative study of gender recognition based hand-crated and deep features via ear images is introduced in this paper. The EarVN1.0 dataset is employed to evaluate this study. The experimental results show that deep learning approach clearly outperforms features-based methods for gender determination based on ear images.
{"title":"Gender recognition based on ear images: a comparative experimental study","authors":"Huy Nguyen-Quoc, Vinh Truong Hoang","doi":"10.1109/ISRITI51436.2020.9315366","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315366","url":null,"abstract":"Automatic gender determination received many attentions in the recent years due to its potential applications in e-commerce and demographic data collection. Face and voice are the most common factors of human which are used to determine the gender. A comparative study of gender recognition based hand-crated and deep features via ear images is introduced in this paper. The EarVN1.0 dataset is employed to evaluate this study. The experimental results show that deep learning approach clearly outperforms features-based methods for gender determination based on ear images.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123473382","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315494
N. N. Qomariyah, D. Kazakov, A. Fajar
Learning user preferences become very important as the personalization systems grow rapidly in this current era. Offering special and personal services can be an added value for the companies to maintain their customer loyalty. Building a personalized recommendation requires a good machine learning model to understand the individual preferences. Every user can be presented with a list of items sorted by its score learned from the individual preferences. So the first couple items shown will be the most liked items by the user. We can borrow the Learning to Rank algorithm from Information Retrieval to solve this problem. In this paper, we present the implementation of user preferences learning by using XGBoost Learning to Rank method in movie domain. We show the evaluation of three different approaches in Learning to Rank according to their Normalized Discounted Cumulative Gain (NDCG) score. We can conclude that in our case study, the pairwise approach appears to be the best solution to produce a personalized list of recommendation.
{"title":"Predicting User Preferences with XGBoost Learning to Rank Method","authors":"N. N. Qomariyah, D. Kazakov, A. Fajar","doi":"10.1109/ISRITI51436.2020.9315494","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315494","url":null,"abstract":"Learning user preferences become very important as the personalization systems grow rapidly in this current era. Offering special and personal services can be an added value for the companies to maintain their customer loyalty. Building a personalized recommendation requires a good machine learning model to understand the individual preferences. Every user can be presented with a list of items sorted by its score learned from the individual preferences. So the first couple items shown will be the most liked items by the user. We can borrow the Learning to Rank algorithm from Information Retrieval to solve this problem. In this paper, we present the implementation of user preferences learning by using XGBoost Learning to Rank method in movie domain. We show the evaluation of three different approaches in Learning to Rank according to their Normalized Discounted Cumulative Gain (NDCG) score. We can conclude that in our case study, the pairwise approach appears to be the best solution to produce a personalized list of recommendation.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129874739","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315438
Nur Nafi’iyah, C. Fatichah, Eha Renwi Astuti, D. Herumurti
Mandibular segmentation is indispensable to support the automation of the gender detection system based on the dental panoramic radiography image. However, the dental panoramic radiography image has low image contrast, the gray intensity value inhomogeneous, and the gray intensity value between the teeth and mandibular bone is almost indistinguishable. So, a good segmentation method is required to separate the mandible and teeth properly. This study aims to analyze the effect of the use of preprocessing and post-processing to enhance mandible segmentation on dental panoramic radiography images properly. In the preprocessing, we use contrast enhancement and Gaussian filters to make the mandibular area more prominent. Meanwhile, in the post-processing, we use erosion and opening morphology to remove the tooth area attached to the mandible. The mandibular segmentation uses the Active Contours method with predefined contour initialization. The dataset used is 86 dental panoramic radiographic images and the segmentation evaluation method uses Jaccard similarity. The experimental results show that the mandibular segmentation with preprocessing and postprocessing obtain Jaccard similarity values are 0.31 and 0.34, on average. Meanwhile, the results of mandibular segmentation with post-processing achieve the Jaccard similarity values are 0.51 and 0.52, on average.
{"title":"The Use of Pre and Post Processing to Enhance Mandible Segmentation using Active Contours on Dental Panoramic Radiography Images","authors":"Nur Nafi’iyah, C. Fatichah, Eha Renwi Astuti, D. Herumurti","doi":"10.1109/ISRITI51436.2020.9315438","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315438","url":null,"abstract":"Mandibular segmentation is indispensable to support the automation of the gender detection system based on the dental panoramic radiography image. However, the dental panoramic radiography image has low image contrast, the gray intensity value inhomogeneous, and the gray intensity value between the teeth and mandibular bone is almost indistinguishable. So, a good segmentation method is required to separate the mandible and teeth properly. This study aims to analyze the effect of the use of preprocessing and post-processing to enhance mandible segmentation on dental panoramic radiography images properly. In the preprocessing, we use contrast enhancement and Gaussian filters to make the mandibular area more prominent. Meanwhile, in the post-processing, we use erosion and opening morphology to remove the tooth area attached to the mandible. The mandibular segmentation uses the Active Contours method with predefined contour initialization. The dataset used is 86 dental panoramic radiographic images and the segmentation evaluation method uses Jaccard similarity. The experimental results show that the mandibular segmentation with preprocessing and postprocessing obtain Jaccard similarity values are 0.31 and 0.34, on average. Meanwhile, the results of mandibular segmentation with post-processing achieve the Jaccard similarity values are 0.51 and 0.52, on average.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117218575","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：