Pub Date : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590110
M. T. Anwar, Al Kautsar Permana, Laksmi Ambarwati, Desy Agustin
This research aimed to do sentiment analysis by conducting text classification targeting six basic human emotions (fear, anger, joy, sadness, disgust, and surprise) using state-of-the-art Natural Language Processing (NLP) technique called ‘Transformers'. More than 1000 tweet data are obtained from Twitter on the issue of the mudik prohibition policy issued by the government of Indonesia in May 2021. The result showed that most people are feeling sad (47%) and surprised (24%) about the mudik prohibition policy. The sad feeling is related to the publics' inability to come back to their hometown and missing their families there. Whereas the ‘surprised’ feelings are due to the contradiction of the mudik prohibition policy with other policies such as the opening of tourist attractions and malls. Our result also showed that the model can accurately predict and have high confidence in predicting the emotions even when the texts do not contain obvious words that are strongly associated with certain emotions. The average confidence score on the prediction is pretty high at 0.82 with most of the predictions having a confidence score higher than 0.95.
{"title":"Analyzing Public Opinion Based on Emotion Labeling Using Transformers","authors":"M. T. Anwar, Al Kautsar Permana, Laksmi Ambarwati, Desy Agustin","doi":"10.1109/ICITech50181.2021.9590110","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590110","url":null,"abstract":"This research aimed to do sentiment analysis by conducting text classification targeting six basic human emotions (fear, anger, joy, sadness, disgust, and surprise) using state-of-the-art Natural Language Processing (NLP) technique called ‘Transformers'. More than 1000 tweet data are obtained from Twitter on the issue of the mudik prohibition policy issued by the government of Indonesia in May 2021. The result showed that most people are feeling sad (47%) and surprised (24%) about the mudik prohibition policy. The sad feeling is related to the publics' inability to come back to their hometown and missing their families there. Whereas the ‘surprised’ feelings are due to the contradiction of the mudik prohibition policy with other policies such as the opening of tourist attractions and malls. Our result also showed that the model can accurately predict and have high confidence in predicting the emotions even when the texts do not contain obvious words that are strongly associated with certain emotions. The average confidence score on the prediction is pretty high at 0.82 with most of the predictions having a confidence score higher than 0.95.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127667062","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590178
Zhihan Xue, T. Gonsalves
In this paper, a method based on deep reinforcement learning (DRL) is proposed, which allows unmanned aerial vehicles (UAVs) to complete obstacle avoidance tasks only through vision in an environment full of common indoor obstacles. This technology is very important for indoor UAVs, due to the limited GPS signal and overcrowding of obstacles compared to the outdoor environment. We use Variational Autoencoder (VAE) to compress image information combined with the policy-based DRL model to implement the visual obstacle avoidance of VAVs. Simulation experiments have demonstrated that this method can make the UAV master obstacle avoidance in a continuous action space with a fixed direction. Compared with the traditional policy-based DRL visual obstacle avoidance algorithms, it can converge faster.
{"title":"Monocular Vision Obstacle Avoidance UAV: A Deep Reinforcement Learning Method","authors":"Zhihan Xue, T. Gonsalves","doi":"10.1109/ICITech50181.2021.9590178","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590178","url":null,"abstract":"In this paper, a method based on deep reinforcement learning (DRL) is proposed, which allows unmanned aerial vehicles (UAVs) to complete obstacle avoidance tasks only through vision in an environment full of common indoor obstacles. This technology is very important for indoor UAVs, due to the limited GPS signal and overcrowding of obstacles compared to the outdoor environment. We use Variational Autoencoder (VAE) to compress image information combined with the policy-based DRL model to implement the visual obstacle avoidance of VAVs. Simulation experiments have demonstrated that this method can make the UAV master obstacle avoidance in a continuous action space with a fixed direction. Compared with the traditional policy-based DRL visual obstacle avoidance algorithms, it can converge faster.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132821083","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}
Students are a country's backbone. The appropriate surroundings for studying must be provided for them. Of all these criteria, a place where you may locate the appropriate setting for your requirements is the most important. The purpose of the study is to identify the best environment to study among students living with parents and hostels. This research also explores issues such as the life and academic chances of students. Adapted questionnaires were utilized to evaluate the responses of 400 students from different colleges, institutes, and students freshly graduated. According to the findings of the survey, students choose to live and study at home because it is healthy and convenient. A variety of algorithm techniques are used, but the Logistics Regression algorithm was the key preference for this study because it had the highest accuracy score. This leads to the conclusion that students opt to stay at home.
{"title":"Machine Learning Approach to Find Students' Best Place to Study: Home vs Hostel","authors":"Jarin Nooder, Ashrarfi Mahbuba, Shayla Sharmin, Nazmun Nessa Moon, Lamisha Haque Poushy, Salauddin Ahmed Bhuiyan, Samia Nawshin","doi":"10.1109/ICITech50181.2021.9590130","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590130","url":null,"abstract":"Students are a country's backbone. The appropriate surroundings for studying must be provided for them. Of all these criteria, a place where you may locate the appropriate setting for your requirements is the most important. The purpose of the study is to identify the best environment to study among students living with parents and hostels. This research also explores issues such as the life and academic chances of students. Adapted questionnaires were utilized to evaluate the responses of 400 students from different colleges, institutes, and students freshly graduated. According to the findings of the survey, students choose to live and study at home because it is healthy and convenient. A variety of algorithm techniques are used, but the Logistics Regression algorithm was the key preference for this study because it had the highest accuracy score. This leads to the conclusion that students opt to stay at home.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130968504","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590147
Christ Zefanya Omega, Hendry
The recommendation system is a tool to assist in decision- making by providing items following user preferences. Recommendation systems are used in a wide variety of fields. Like in e-commerce, social media, ads, and others. The algorithm that is popular in making recommendation systems is collaborative filtering; however, the algorithm is less accurate if the amount of data is too small. Therefore, the use of the weighted average method can help to improve accuracy in providing recommendations. This study indicates that the user weighted average and the movie weighted average influence in providing film recommendations to the user. Furthermore, it shows that the level of accuracy of the recommendation system that uses the weighted average has higher accuracy than the recommendation system that uses collaborative filtering
{"title":"Movie Recommendation System using Weighted Average Approach","authors":"Christ Zefanya Omega, Hendry","doi":"10.1109/ICITech50181.2021.9590147","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590147","url":null,"abstract":"The recommendation system is a tool to assist in decision- making by providing items following user preferences. Recommendation systems are used in a wide variety of fields. Like in e-commerce, social media, ads, and others. The algorithm that is popular in making recommendation systems is collaborative filtering; however, the algorithm is less accurate if the amount of data is too small. Therefore, the use of the weighted average method can help to improve accuracy in providing recommendations. This study indicates that the user weighted average and the movie weighted average influence in providing film recommendations to the user. Furthermore, it shows that the level of accuracy of the recommendation system that uses the weighted average has higher accuracy than the recommendation system that uses collaborative filtering","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121486972","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590189
D. K. Larasati, Iwan Setvawan
The number of road users, in particular those using motor vehicles, is constantly increasing. It is imperative that these users obey road markings, in order to ensure traffic safety. However, the number of traffic violations is still very high. One example is violation of stop line before a pedestrian crossing. This paper proposes an automatic detection of this type of traffic violation. The approach is based on the Hough transform. This experiment show that the approach can achieve accuracy rate for the morning and afternoon dataset are 89% and for the evening dataset is approximately 69% (or 71% using an alternative set of parameters). So, the overall average of accuracy rate of the system is 82.33 % (or 83 %, with an alternative set of parameters). The main factors affecting the system performance is the availability of adequate lighting and the quality of the stop line marking.
{"title":"Detection of Stop Line Violations Using the Hough Transform","authors":"D. K. Larasati, Iwan Setvawan","doi":"10.1109/ICITech50181.2021.9590189","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590189","url":null,"abstract":"The number of road users, in particular those using motor vehicles, is constantly increasing. It is imperative that these users obey road markings, in order to ensure traffic safety. However, the number of traffic violations is still very high. One example is violation of stop line before a pedestrian crossing. This paper proposes an automatic detection of this type of traffic violation. The approach is based on the Hough transform. This experiment show that the approach can achieve accuracy rate for the morning and afternoon dataset are 89% and for the evening dataset is approximately 69% (or 71% using an alternative set of parameters). So, the overall average of accuracy rate of the system is 82.33 % (or 83 %, with an alternative set of parameters). The main factors affecting the system performance is the availability of adequate lighting and the quality of the stop line marking.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131164763","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590113
J. Mohith, Divij Kulshrestha, K. Jothi
Air pollution is a threat that all urban municipalities across the globe are trying to tackle. In India, air pollution is the fifth major cause of death, leading to around 2 million deaths per year, according to the World Health Organization. The ability to accurately predict air pollution levels in a region would give authorities the chance to take proactive measures, preventing the exposure of citizens to toxic pollutants and avoiding accidents and damage to property caused by smog. In this paper, we forecast the level of Particulate Matter 2.5 (PM2.5) for multiple urban cities in India using various machine learning algorithms built upon historical data. This data includes meteorological parameters such as temperature, wind speed, humidity, and the pollutant levels leading up to that given date/time. Based on the performance of the forecasting models, we perform a comparative analysis of each model and derive key insights.
空气污染是全球所有城市都在努力解决的威胁。世界卫生组织(World Health Organization)的数据显示，在印度，空气污染是第五大死因，每年导致约200万人死亡。准确预测一个地区空气污染水平的能力将使当局有机会采取积极措施，防止市民接触有毒污染物，避免雾霾造成的事故和财产损失。在本文中，我们使用基于历史数据的各种机器学习算法预测了印度多个城市的PM2.5水平。这些数据包括气象参数，如温度、风速、湿度和在给定日期/时间之前的污染物水平。基于预测模型的表现，我们对每个模型进行比较分析，并得出关键的见解。
{"title":"A Comprehensive Analysis of Machine Learning Methods for Air Pollution Forecasting","authors":"J. Mohith, Divij Kulshrestha, K. Jothi","doi":"10.1109/ICITech50181.2021.9590113","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590113","url":null,"abstract":"Air pollution is a threat that all urban municipalities across the globe are trying to tackle. In India, air pollution is the fifth major cause of death, leading to around 2 million deaths per year, according to the World Health Organization. The ability to accurately predict air pollution levels in a region would give authorities the chance to take proactive measures, preventing the exposure of citizens to toxic pollutants and avoiding accidents and damage to property caused by smog. In this paper, we forecast the level of Particulate Matter 2.5 (PM2.5) for multiple urban cities in India using various machine learning algorithms built upon historical data. This data includes meteorological parameters such as temperature, wind speed, humidity, and the pollutant levels leading up to that given date/time. Based on the performance of the forecasting models, we perform a comparative analysis of each model and derive key insights.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134435468","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590188
M. F. X. Cham, Radius Tanone, Hendra Alexander T Riadi
Rice is a rice-producing plant that is susceptible to disease so it can make it difficult for farmers to identify the types of diseases that exist in rice leaves. On the other hand, farmers need convenience in identifying diseases that exist in rice leaves more effectively and efficiently. Seeing the development trend of deep learning and mobile android, we need an application that can help farmers to analyze diseases in leaves effectively and efficiently. This research was conducted in several stages including literature study, application design and manufacture, application testing and analysis as well as conclusion drawing and report writing. With deep learning technology, a Convolutional Neural Network (CNN) model was developed on Tensorflow lite and stored in the ML Kit service. Furthermore, the model can be embedded in a detection application built on the android mobile platform. This is to assist farmers in identifying healthy and unhealthy rice leaves. The results of the development of the algorithm and its application to an Android-based mobile application can run well where the level of accuracy generated from the model formed in classifying disease images on rice leaves in this study is 80%.
{"title":"Identification of Rice Leaf Disease Using Convolutional Neural Network Based on Android Mobile Platform","authors":"M. F. X. Cham, Radius Tanone, Hendra Alexander T Riadi","doi":"10.1109/ICITech50181.2021.9590188","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590188","url":null,"abstract":"Rice is a rice-producing plant that is susceptible to disease so it can make it difficult for farmers to identify the types of diseases that exist in rice leaves. On the other hand, farmers need convenience in identifying diseases that exist in rice leaves more effectively and efficiently. Seeing the development trend of deep learning and mobile android, we need an application that can help farmers to analyze diseases in leaves effectively and efficiently. This research was conducted in several stages including literature study, application design and manufacture, application testing and analysis as well as conclusion drawing and report writing. With deep learning technology, a Convolutional Neural Network (CNN) model was developed on Tensorflow lite and stored in the ML Kit service. Furthermore, the model can be embedded in a detection application built on the android mobile platform. This is to assist farmers in identifying healthy and unhealthy rice leaves. The results of the development of the algorithm and its application to an Android-based mobile application can run well where the level of accuracy generated from the model formed in classifying disease images on rice leaves in this study is 80%.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114791806","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590161
Ramos Somya, E. Winarko, Sigit Privanta
Online shopping activities are currently experiencing a significant increase due to the development of the reach of the internet services and the changed activities from offline to online. The data analysis generated from online shopping activities is necessary to determine the right sales strategy. One of the types of data that needs to be analyzed is market consumer behavior data in online shops, generated in the form of clickstream data. Currently, there was not any research that examines the determination of clickstream data components, clickstream data recording mechanism, and how to analyze clickstream data components in online shops properly. This paper describes the architecture of the proposed online shop application, the module to record the clickstream data, and the method to analyze the clickstream data. Based on our evaluation, eight clickstream data components were successfully recorded in the database using Asynchronous JavaScript and XML (AJAX) technology. The clickstream data component that contains market customer behavior data is Multi-Criteria Decision Making (MCDM) data and has been analyzed using the Simple Additive Weighting (SAW) ranking method.
{"title":"A Novel Approach to Collect and Analyze Market Customer Behavior Data on Online Shop","authors":"Ramos Somya, E. Winarko, Sigit Privanta","doi":"10.1109/ICITech50181.2021.9590161","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590161","url":null,"abstract":"Online shopping activities are currently experiencing a significant increase due to the development of the reach of the internet services and the changed activities from offline to online. The data analysis generated from online shopping activities is necessary to determine the right sales strategy. One of the types of data that needs to be analyzed is market consumer behavior data in online shops, generated in the form of clickstream data. Currently, there was not any research that examines the determination of clickstream data components, clickstream data recording mechanism, and how to analyze clickstream data components in online shops properly. This paper describes the architecture of the proposed online shop application, the module to record the clickstream data, and the method to analyze the clickstream data. Based on our evaluation, eight clickstream data components were successfully recorded in the database using Asynchronous JavaScript and XML (AJAX) technology. The clickstream data component that contains market customer behavior data is Multi-Criteria Decision Making (MCDM) data and has been analyzed using the Simple Additive Weighting (SAW) ranking method.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116971086","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590134
Edy Winarno, W. Hadikurniawati, Setyawan Wibisono, Anindita Septiarini
The fingerprint identification system is a recognition process by measuring the characteristics on human fingers and then comparing them with those in the database. The purpose of this study is to create a system for fingerprints recognition using the edge detection method and Grey Level Co-occurrence Matrix (GLCM). The method used in this fingerprint recognition research is texture analysis. Preprocessing was performed with edge detection and feature extraction with GLCM method. First, the fingerprint is captured using the fingerprint scanner. Then the fingerprint image was extracted using the Grey Level Co-occurrence Matrix (GLCM) feature. The features obtained are energy, contrast, homogeneity and correlation. The final result of the fingerprint identification system is the success of displaying the image with the identity data of the fingerprint owner. Using two methods, fingerprint identification accuracy of 83% was achieved.
{"title":"Edge Detection and Grey Level Co-Occurrence Matrix (GLCM) Algorithms for Fingerprint Identification","authors":"Edy Winarno, W. Hadikurniawati, Setyawan Wibisono, Anindita Septiarini","doi":"10.1109/ICITech50181.2021.9590134","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590134","url":null,"abstract":"The fingerprint identification system is a recognition process by measuring the characteristics on human fingers and then comparing them with those in the database. The purpose of this study is to create a system for fingerprints recognition using the edge detection method and Grey Level Co-occurrence Matrix (GLCM). The method used in this fingerprint recognition research is texture analysis. Preprocessing was performed with edge detection and feature extraction with GLCM method. First, the fingerprint is captured using the fingerprint scanner. Then the fingerprint image was extracted using the Grey Level Co-occurrence Matrix (GLCM) feature. The features obtained are energy, contrast, homogeneity and correlation. The final result of the fingerprint identification system is the success of displaying the image with the identity data of the fingerprint owner. Using two methods, fingerprint identification accuracy of 83% was achieved.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132301582","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 : 2021-09-23DOI: 10.1109/ICITech50181.2021.9590186
Arif Ridho Lubis, S. Prayudani, Y. Fatmi, Al-Khowarizmi, Julham, Y. Y. Lase
Image processing is one of the sciences in image processing which can involve several other techniques such as data mining techniques, in this case the detection of an image. Images are generally carried out classification which results in accurate detection wherein the detection of an image is carried out by extracting the features so that the image can be recognized by computation. One of the extract features that are superior and easy to apply in computational techniques is HOG (Histogram OF Oriented Gradients). The HOG feature can be useful in helping detect images in the form of Tuberculosis xray. After extracting the features, then the classification is carried out using 2 methods that are good for learning levels such as KNN (K-Nearest Neighbor) and SVM (Support Vector Machine). The results of this paper in the detection of HOG Tuberculosis X-ray with KNN for positive images got an accuracy of 77.95% while the negative ones got an accuracy of 78.65%. The results of HOG detection on Tuberculosis X-ray results with SVM on images that were positive got an accuracy of 65.75% while those who were negative were 79.39%.
图像处理是图像处理中的一门科学，它可以涉及到其他一些技术，如数据挖掘技术，在这种情况下是图像的检测。通常对图像进行分类，从而进行准确的检测，其中通过提取特征来进行图像的检测，从而通过计算来识别图像。HOG (Histogram of Oriented Gradients)是一种优越且易于应用于计算技术的提取特征。HOG特征可用于帮助检测结核x线图像。提取特征后，使用KNN (K-Nearest Neighbor)和SVM (Support Vector Machine)两种有利于学习水平的方法进行分类。本文结果表明，利用KNN检测HOG结核x线阳性图像的准确率为77.95%，阴性图像的准确率为78.65%。SVM对结核x线阳性图像HOG检测的准确率为65.75%，阴性图像HOG检测的准确率为79.39%。
{"title":"Detection of HOG Features on Tuberculosis X-Ray Results Using SVM and KNN","authors":"Arif Ridho Lubis, S. Prayudani, Y. Fatmi, Al-Khowarizmi, Julham, Y. Y. Lase","doi":"10.1109/ICITech50181.2021.9590186","DOIUrl":"https://doi.org/10.1109/ICITech50181.2021.9590186","url":null,"abstract":"Image processing is one of the sciences in image processing which can involve several other techniques such as data mining techniques, in this case the detection of an image. Images are generally carried out classification which results in accurate detection wherein the detection of an image is carried out by extracting the features so that the image can be recognized by computation. One of the extract features that are superior and easy to apply in computational techniques is HOG (Histogram OF Oriented Gradients). The HOG feature can be useful in helping detect images in the form of Tuberculosis xray. After extracting the features, then the classification is carried out using 2 methods that are good for learning levels such as KNN (K-Nearest Neighbor) and SVM (Support Vector Machine). The results of this paper in the detection of HOG Tuberculosis X-ray with KNN for positive images got an accuracy of 77.95% while the negative ones got an accuracy of 78.65%. The results of HOG detection on Tuberculosis X-ray results with SVM on images that were positive got an accuracy of 65.75% while those who were negative were 79.39%.","PeriodicalId":429669,"journal":{"name":"2021 2nd International Conference on Innovative and Creative Information Technology (ICITech)","volume":"67 24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127396712","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：