{"title":"Vision Transformer Approach for Vegetables Recognition","authors":"Li-Hua Li, Radius Tanone","doi":"10.1109/iSemantic55962.2022.9920435","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920435","url":null,"abstract":"The use of Vision Transformer to solve computer vision issues, particularly Image Classification, is a recent trend. Smart agriculture is one of the objectives of Industry 4.0 in Indonesia, which is currently vigorously advancing the agricultural sector. Vegetable classification is one example of a difficulty that can be encountered in the approach of smart agriculture. As a result of this possible issue, one solution is to use Vision Transformer to construct deep learning models. In this study, we use the Vision Transformer to tackle the problem of vegetable classification with an input size of 32x32 and a total patch size of 64. The model is constructed and trained with, and it has a 98% accuracy. Furthermore, the model employs several measures to evaluate the performance of the developed model. These findings indicate a promising performance for image classification problems, particularly with vegetables recognition.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126331792","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}
R. Yusianto, I. Hermadi, K. Kusnadi, Marimin Suprihatin, H. Hardjomidjojo
{"title":"Selection of Optimal Transportation Routes in the Distribution of Temanggung Original Robusta Coffee using Genetic Algorithms","authors":"R. Yusianto, I. Hermadi, K. Kusnadi, Marimin Suprihatin, H. Hardjomidjojo","doi":"10.1109/iSemantic55962.2022.9920408","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920408","url":null,"abstract":"The selection of optimal transportation routes in the distribution of agro-industrial commodities consists of the need to visit locations that are the safest and optimal by considering the risk of commodity damage. In practice, the amount of time available is limited, complex, and uncertain, so metaheuristic algorithms are used. This study aims to help decision-makers choose the optimal transportation route in the original Temanggung robusta coffee distribution using Genetic Algorithms (GA). We used five interrelated research variables: location point, modes of transportation, path traversed, vehicle capacity, and distribution cost. We discussed the construction of the population, chromosome representation, fitness function, natural selection, crossover, and mutation. The results showed that the minimum distance traveled was 264.8 Km, the chromosomes having that distance were Z<inf>1</inf>\" – Z<inf>2</inf>\" – Z<inf>5</inf>\" – Z<inf>3</inf>\" – Z<inf>4</inf>\" – Z<inf>6</inf>\" – Z<inf>8</inf>\" – Z<inf>7</inf>\", and all chromosomes have the same route, namely Node<inf>1</inf> – Node<inf>2</inf> – Node<inf>5</inf> – Node<inf>3</inf> – Node<inf>4</inf> – Node<inf>6</inf> – Node<inf>8</inf> – Node<inf>7</inf>. The results of GA transportation optimization can find the minimum solution. It shows that GA can be used to choose the optimal transportation route in the distribution of the original robusta coffee of Temanggung. For further research, researchers can add resistance variables at each node.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134091602","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}
Wiwiek Hayyin Suristiyanti, Sholihul Ibad, M. N. Alfa Farah, Nova Rijati, Aris Marjuni
{"title":"Integration of Fuzzy Multi-Attribute Decision Making and Clustering Methods for Student Apprenticeship Recommendations","authors":"Wiwiek Hayyin Suristiyanti, Sholihul Ibad, M. N. Alfa Farah, Nova Rijati, Aris Marjuni","doi":"10.1109/iSemantic55962.2022.9920426","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920426","url":null,"abstract":"Harmonious vocational education and training with the company, industry, and occupation are carried out by providing access to apprenticeships and industrial work practices. This study proposes a method of clustering student competencies in vocational education and training institutions as a recommendation for students who can be apprenticed to the company, industry, and occupation. The Fuzzy Multi-Attribute Decision Making (FMADM) approach is proposed with a combination of two methods, namely Fuzzy Simple Additive Weighting and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (FSAW-TOPSIS). FSAW-TOPSIS provides a more optimal solution and better performance. The FSAW-TOPSIS method which is integrated with clustering produces an accuracy of 100% for the Decision Tree method, with a Neural Network with the best accuracy marked by the smallest RMSE value of 0.246. FSAW-TOPSIS integration and clustering provide optimal student apprenticeship recommendations as material for decision-making for leaders of vocational education and training institutions to apprentice their students in the company, industry, and occupation.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132439062","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}
F. Alzami, Z. Hasibuan, Sari Ayu Wulandari, Filmada Ocky Saputra, J. Jumanto, P. Andono
{"title":"Component of Traffic Management System for Developing Countries: A Review","authors":"F. Alzami, Z. Hasibuan, Sari Ayu Wulandari, Filmada Ocky Saputra, J. Jumanto, P. Andono","doi":"10.1109/iSemantic55962.2022.9920460","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920460","url":null,"abstract":"Traffic Management System is part in field of transportation which help in building integrated system of people, vehicles, and roads. The main challenge in traffic management systems is predict the next possible condition of traffic with high precision to help avoid the traffic congestion which reduce the pollution, reduce the fuel consumption, reduce the stress level of road users, and reduce travel time. Traffic Management System in developed Countries is bit different with developing countries in matter of vehicular behavior. Thus, this paper presents a review about component of traffic management system for developing countries in point of view: 1) data source and data model; 2) prediction models. The paper also presents advantages, drawback and how to improve those components.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131136463","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}
R. Yusianto, M. Sugarindra, Valentina Widya Suryaningtyas, Marimin Marimin
{"title":"Optimization of Horticultural Food Commodity Distribution Routes using Genetic Algorithm with Crossover Partially Match","authors":"R. Yusianto, M. Sugarindra, Valentina Widya Suryaningtyas, Marimin Marimin","doi":"10.1109/iSemantic55962.2022.9920422","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920422","url":null,"abstract":"Horticultural food commodities have unique characteristics: perishable and not durable. In addition, the distribution of these commodities is also uncertain along highly complex routes. We experimented to determine the route of potato distribution in Central Java, Indonesia. We use metaheuristic methods to find solutions to these problems. This method solves the problem using algorithms for optimization. This study aimed to determine the most optimal route using a genetic algorithm (GA) with partially matched crossover (PMX). The GA stages in this study include (1) Population Initialization; we use the Random Generator Algorithm, (2) Selection; we use the Roulette Wheel Selection method, (3) Crossover; we use the PMX method and (4) Mutation. We used ten chromosomes with seven genes each. We used ten chromosomes with seven genes each. The results of this study indicate that the best route is obtained in the second generation, namely through node1 - node7 - node2 - node6 - node5 - node3 - node4 - node1 with an optimal distance of 159 km. For further research, consider the spatial conditions for a better solution.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127625114","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}
Neza Aemal Fadilla, Mohamad Lathif Puja Sakti, Nita Setyaningsih, Naufal Zhafran, Taufik Aulia Pramudyawardhana, Viki Arri Shelomita, Nukat Alvian Ideastari, C. A. Sari, E. H. Rachmawanto, A. Fahmi
{"title":"Cholesterol Detection Through Iris Using Daugman’s and GLCM Based on K-Means Clustering","authors":"Neza Aemal Fadilla, Mohamad Lathif Puja Sakti, Nita Setyaningsih, Naufal Zhafran, Taufik Aulia Pramudyawardhana, Viki Arri Shelomita, Nukat Alvian Ideastari, C. A. Sari, E. H. Rachmawanto, A. Fahmi","doi":"10.1109/iSemantic55962.2022.9920428","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920428","url":null,"abstract":"Cholesterol is a disease that is influenced by fat deposits originating from the liver. Detection of cholesterol disease can be known through blood tests, urine checks and visually the iris of the human eye. Cholesterol detection through the iris can be implemented using image processing techniques, especially in image segmentation. Input-based image segmentation on feature extraction and pattern classification has been applied in this article. GLCM is a feature extraction technique that is commonly used to sharpen image textures to make the classification process easier. In this article, K-Means have been selected to carry out the classification process. To improve accuracy, the original image has been preprocessed using grayscalling, noise removal, image contrast enhancement and cropping. The experimental results have obtained 100% accuracy.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"297 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133466224","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}
Robet Robet, Z. Hasibuan, M. Arief Soeleman, Purwanto Purwanto, P. Andono, Pujiono Pujiono
{"title":"Deep Learning Model In Road Surface Condition Monitoring","authors":"Robet Robet, Z. Hasibuan, M. Arief Soeleman, Purwanto Purwanto, P. Andono, Pujiono Pujiono","doi":"10.1109/iSemantic55962.2022.9920464","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920464","url":null,"abstract":"Road is a crucial asset for public services. Therefore, it must be repaired as soon as possible to bring safety for the driver on the road. In recent years research in monitoring and identifying road surface conditions using images captured by the low-cost camera or smartphone cameras and deep learning can identify road surface conditions efficiently and quickly. The study aims to explore the performance of the deep learning model. We proposed a U-Net architecture for road extraction from Road Traversing Knowledge (RTK) dataset. The result has been compared with different automatic segmentation models, and the development of segmentation using U-Net showed a more precise Accuracy of 97.08%, Mean-IoU 0.364, and faster computing time than the other models.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123281174","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}
{"title":"Early Detection for Determinants of Risky Behavior in Cervical Cancer Cases through the C4.5 Algorithm in Indonesia","authors":"Adinda Cipta Dewi, Guruh Fajar Shidik","doi":"10.1109/iSemantic55962.2022.9920459","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920459","url":null,"abstract":"In 2020, the discovery of cervical cancer is the second most common cancer in Indonesia after breast cancer, which is 9.2%. Community efforts to carry out prevention and early diagnosis are still low, due to lack of knowledge, awareness, and ignorance of screening. The purpose of this study is to apply the C4.5 algorithm for early detection of determinants of cervical cancer risk behavior. This study uses a quantitative approach with experimental methods on the RapidMiner application to find knowledge. The study analyzes 10 attributes that contain information about demographic and behavior. The samples studied were divided into 2, namely primary data as testing data from 23 respondents and secondary data as training data from 668 respondents. The pattern generated from the C4.5 Algorithm technique can be used to predict patient categories, are positive cervical cancer and negative cervical cancer through demographic and behavioral factors. This result indicate that demographic factor, age is the most influential determinant of a person's risk of cervical cancer. Age is one of the determinants of a person's behavior. Measurements using RapidMiner software prove that the C4.5 algorithm has an accuracy of 91.30%. While the AUC curve has a value of 0.866 which according to Gorunescu is included in the Good Classification. Researcher suggest an increase in cervical cancer prevention programs in health services such as health promotion activities, screening, and consultation on contraceptive use. This activity is very influential in reducing the incidence of cervical cancer.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125075522","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}
Sukma Ayu Septianingrum, M. Alfian Dzikri, M. Soeleman, Pujiono Pujiono, M. Muslih
{"title":"Performance Analysis of Multiple Linear Regression and Random Forest for an Estimate of the Price of a House","authors":"Sukma Ayu Septianingrum, M. Alfian Dzikri, M. Soeleman, Pujiono Pujiono, M. Muslih","doi":"10.1109/iSemantic55962.2022.9920454","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920454","url":null,"abstract":"The house is a human need for boards. House prices that continue to rise every year make it difficult for some people to buy a house according to their respective financial capabilities. Many property developers in big cities continue to build housing, including the South Jakarta area with many new arrivals. In this study, we will predict house prices using a comparison of 2 methods, multiple linear regression and random forest which produces a better RMSE value at an 8:2 comparison between training data and testing data, and the multiple linear regression method produces fewer errors. The 8:2 experiment produces an RMSE 3673441811.575 of Linear Regression and 3693111743.726 of Random Forest.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"239 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129164911","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}
Raihan Yusuf, Muhammad Hilmi, Safira Hasna Setiyani, Vira Wahyuni Idhayanti, Ali Muksin, C. A. Sari, E. H. Rachmawanto, Heru Lestiawan
{"title":"Super Encryption Video Cryptography : Combination of Vigenere Cipher and Myszkowski Transposition","authors":"Raihan Yusuf, Muhammad Hilmi, Safira Hasna Setiyani, Vira Wahyuni Idhayanti, Ali Muksin, C. A. Sari, E. H. Rachmawanto, Heru Lestiawan","doi":"10.1109/iSemantic55962.2022.9920432","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920432","url":null,"abstract":"Cryptography is a method used to protect the confidentiality of data. In super encryption, two or more encryption algorithms are combined to make it more secure. In this work Vigenere Cipher and Myszkowsi Transposition are combined to form a super encryption. Vigenere cipher is a technique of encoding messages with Caesar cipher using the characters in the key used. The key used in this algorithm is a symmetric key and the characters in the key will be used repeatedly if all the characters in the message have not been processed while the Myszkowski Transposition is a type of cipher transposition algorithm that has its own uniqueness The specialty of this algorithm is that it has the need for keywords with identically numbered repeated letters. The key used in this algorithm is in the form of words or letters that are converted into a sequence of numbers. The alphabetical arrangement of the letters in the keyword determines the numbers. The first letter in the alphabetical order will be the number 1, the second letter in the alphabetical order will be 2, and so on. The super encryption is expected to be both easy-to-implement and more secure. The data integrity is still guaranteed because the two algorithms work together to secure the data and enable its return to plaintext.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127724359","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}