{"title":"Deep Face Recognition for Imperfect Human Face Images on Social Media using the CNN Method","authors":"Shifa Inges Yudita, T. Mantoro, M. A. Ayu","doi":"10.1109/ic2ie53219.2021.9649317","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649317","url":null,"abstract":"Face recognition systems nowadays are applied in any gadget. The usual purpose of this technology is to recognize people's information for security purposes on a smartphone. Unfortunately, this face recognition is only available for perfect facial data. In some cases, there are situations where full faces may not be available on social media and recognizing imperfect human facial structure is not a simple task. The aim of this study is to provide the capability to recognize human faces based on partial or imperfect human facial data. This study explores the idea of face recognition based on partial or imperfect human facial data using the state art convolutional neural network-based architecture, especially for the CNN model with the pre-trained VGG-Face model which promises a good recognizing imperfect image of human face results.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127804636","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":"Identification of Feed in Determining the Quality of Cow's Milk using Forward Chaining","authors":"Ijang Japar Sidik, Yaddarabullah, S. Permana","doi":"10.1109/ic2ie53219.2021.9649077","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649077","url":null,"abstract":"Milk is a popular beverage among most people because it contains numerous nutrients that are beneficial to the body, such as calcium, vitamin D, and protein. Whole cow's milk is a type of milk that contains a lot of nutrients and does not go through a lot of processing. As a result, pure cow's milk is very beneficial to the body, such as assisting child growth, assisting in weight gain, maintaining heart health, increasing muscle mass, and many other benefits. However, the benefits will be diminished if the cow's milk consumed is of less good quality. Feed is one of the many factors that influence the quality of milk produced. However, feed comes in a variety of varieties, as do those in The Hamlet of Sepaku Pamulihan Subdistrict, which has a variety of feed. Cooperative Tandangsari is one of the cooperatives in charge of managing dairy farms in the Sepaku area. Because the various types of feed in this area are so diverse, determining a good feed for dairy cows is difficult. As a result, this study was carried out in order to identify the best type of feed for improving milk quality. The forward chaining method is used in this study to determine the type of feed for cows, and feed type identification testing is performed using the WEKA application. The test result has an accuracy value of 71.5 %, precision of 0.714, and recall of 0.652, where the type of forage feed that can improve milk quality includes elephant grass, king grass, rice straw, and corn, among others.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131792481","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":"Air Pressure Control on Ventilator using Fuzzy Logic Method","authors":"Alya Amaranggana, R. Priramadhi","doi":"10.1109/ic2ie53219.2021.9649324","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649324","url":null,"abstract":"In a virus outbreak that attacks human respiration, there is an increase in the need for ventilators that is not proportional to their availability. A ventilator is a device that serves to assist or replace normal ventilation functions in people who have respiratory problems. The lungs are important organs in the respiratory system. The lungs can inflate if the atmospheric pressure is greater than the lung pressure (Palv). Conversely, the lungs can deflate if the atmospheric pressure is less than Palv. In the process of inspiration, air flows from outside to the alveoli, increasing oxygen levels. The faster oxygen is introduced into the alveoli from the atmosphere, the higher the oxygen concentration in the alveoli. So that the oxygen concentration in the alveoli is controlled by the speed with which new oxygen enters the lungs through the ventilation process. In people who have respiratory problems, the body is less able to supply the oxygen needs of the lungs so that the flow of air pressure that flows into the lungs must be controlled. A ventilator is made with the principle of pressure difference. Atmospheric pressure is set greater than Palv so that air enters the lungs. In contrast, atmospheric pressure is set to be less than Palv to force air out of the lungs. The outside air pressure can be increased by providing positive pressure air from the airflow drive device. With the Fuzzy Logic control method, the speed of the airflow drive device is adjusted to meet the patient's needs. Ventilators that have been designed and manufactured can provide air pressure in the pressure range of 0 to +50 cmH2O or the equivalent of 0 to 0.711167 psi. The basic pressure at the end of the breath is set to be equal to atmospheric pressure.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134447554","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}
Erisvaha Kiki Purwaningsih, Prasetyo Adi Wibowo Putro, D. I. Sensuse, Kautsarina, Ryan Randy Suryono
{"title":"The Architecture for Rice Stock Information System in Indonesia","authors":"Erisvaha Kiki Purwaningsih, Prasetyo Adi Wibowo Putro, D. I. Sensuse, Kautsarina, Ryan Randy Suryono","doi":"10.1109/ic2ie53219.2021.9649153","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649153","url":null,"abstract":"Stock Information System as part of Supply Chain Management application must deliver same information service to all stakeholders. Although rice stock information already exists on many applications, it cannot identify stock in all stakeholders. This research identifies a stock information system that can provide added value for farmers. Soft System Methodology uses to identify the problem in the current system and possible solutions. As a result, we propose a system architecture with three optional input/output channels proposed: collect SMS gateway, API, and webserver. The proposed system has a rice price report feature for each data storing process from stakeholders. This research is only based on usage guidelines regardless of the system architecture that is already running. Therefore it can be continued by applying the architecture offered to the existing system.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130101176","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":"Optimization of the FP-Growth Algorithm in Data Mining Techniques to Get the Electric Power Theft Pattern for the Development of Smart City","authors":"I. P. Sari, Al-Khowarizmi, Ismail Hanif Batubara","doi":"10.1109/ic2ie53219.2021.9649303","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649303","url":null,"abstract":"In general, people's daily lives cannot be separated from energy resources, namely electricity. Where electricity is one of the basic needs of society for survival. The amount of electricity consumption is now increasing, because people almost every day and every home uses electronic devices. Not only the needs of homes that use electricity, even companies, schools, shopping centers also cause an increase in the use of electric current. The increasing use of electric current makes many people commit violations in the use of electricity. This makes the Electric Power Company in managing the distribution of electrical energy to the public to check for violations in the use of electricity. For this reason, data mining techniques are needed to get patterns in energy use violations by optimizing the FP-Growth algorithm in getting a good pattern where the 1300Kwh meter in the optimized pattern is recognized as having more frequent violations such as breaking electric current. So that the optimization pattern can be applied to the electricity meter to develop smart city concepts such as the smart grid. In this paper, we apply data mining with the FP-Growth algorithm in analyzing the pattern of electricity theft. The existing pattern describes the cause and effect of the theft of electric power. In the future smart electricity grid, also known as the \"smart grid\", network stability is expected to be achieved through different energy sources, among others. If the results of renewable energy that depend on weather and time are not adjusted to the latest electricity usage, there can be a network imbalance that ends in a blackout or blackout.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131154912","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":"Classification of COVID-19 Patients Using Deep Learning Architecture of InceptionV3 and ResNet50","authors":"M. Raihan, M. Suryanegara","doi":"10.1109/ic2ie53219.2021.9649255","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649255","url":null,"abstract":"This paper aims to compare the deep learning Convolutional Neural Network (CNN) model for a case study of 3 classes chest x-ray classification of patients with \"COVID-19\", \"pneumonia\", and \"normal people\" using 2 architectures, namely InceptionV3 and ResNet50. This model was created using the GoogleColab platform with the Python programming language. This comparison aims to find the best results using 4 evaluation metrics and several scenarios for dividing the number of datasets used for training and validation. The evaluation metrics used include accuracy, precision, recall, and F1-score. The best accuracy is generated on a model with the ResNet50 architecture with a training accuracy value of 98.62% and accuracy validation of 96.53%. While in the InceptionV3 architecture, the resulting value for training accuracy is 96.13% and accuracy validation is 91.52%.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131174913","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}
Arif Ridho Lubis, S. Prayudani, Y. Fatmi, Al-Khowarizmi, Julham, Y. Y. Lase
{"title":"Extraction in Detecting Tuberculosis X-Ray Results using Histogram of Oriented Gradients","authors":"Arif Ridho Lubis, S. Prayudani, Y. Fatmi, Al-Khowarizmi, Julham, Y. Y. Lase","doi":"10.1109/ic2ie53219.2021.9649335","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649335","url":null,"abstract":"Image processing is a very popular study in research. Image processing research developed from starting to improve images that have lost pixels or adding pixels to make the image clearer in providing and conveying information. However, with the support of various image processing computational techniques, it is not only conveying information but also applying machine learning techniques to carry out lessons from the available data. In this study, a training was implemented in an X-ray image of Tuberculosis. Tuberculosis is made due to the presence of bacteria that have gathered so that the results of X-rays of Tuberculosis are processed by extracting features to detect whether the results of the Tuberculosis X-ray image are positive or negative. The very simple feature extract is processed to detect the Histogram of Oriented Gradients (HOG) because it applies the gradient function to be mathematically processed in detecting Tuberculosis. In this paper, the results using HOG feature extraction based on the percentage of positive tuberculosis are 70.90%, the proportion of negative diagnosis results is 29.10%, the proportion of negative diagnosis results is 72.72%, and the positive diagnosis results are 27.28%.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126236184","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":"Digitalization for Business Model Innovation: Create, Change, and Improve for Values","authors":"Mercurius Broto Legowo, Budi Indiarto, Deden Prayitno","doi":"10.1109/ic2ie53219.2021.9649340","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649340","url":null,"abstract":"Recently, business organizations, including SMEs, have faced challenges in utilizing digitalization in the face of global competition. It stated that the discourse related to digitalization has a role in creating, changing, and improving for values business model innovation (BMI) in SMEs. That is the concern of digitalization researchers, SME owners, SMEs regulators, and policymakers. This study's purpose is to reveal that the digitization of Small and Medium Enterprises (SMEs) is to create, transform, and enhance values derived from business model innovations. The research problem is to find out the factors that influence the implementation of digitalization in creating, changing, and improving the values of business model innovation in Indonesian SMEs. Data collection on a survey of 100 Indonesian SMEs. This study using a convergent parallel mixed methods research approach. As the research sample, data collecting from a survey of 100 valid SMEs. The main findings of this study show that digitalization affecting by external business factors and dynamic capability factor has a significant role in creating, changing, and improving values in business model innovation for Indonesian SMEs. The main research contribution is providing input related to business model innovation for SMEs and supporting the SME digitalization program from the Indonesian government.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126798962","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":"Hand Gesture Video Identification using Spatial and Temporal Convolutional","authors":"Denden Raka Setiawan, E. C. Djamal, Fikri Nugraha","doi":"10.1109/ic2ie53219.2021.9649052","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649052","url":null,"abstract":"Hand gestures can be used for indirect interaction. The hand movement in the video causes the hand position of each frame to move. Position shift can be information in the identification of hand movements. However, video identification is not easy; it requires comprehensive feature detection in each part of the frame and identifies connectivity patterns between each frame. The use of architecture in recognizing each characteristic pattern in each frame can affect the identification results due to the number and arrangement of layers in extracting features in each frame. Previous research has identified video hand movements used Convolutional Neural Networks (CNN) with the Single-Stream Spatial CNN method to identifying hand movement patterns but ignoring the relationship between frames. In other research, the Single-Stream Temporal CNN was used to identify hand movements used two frames to connected the relationship between frames at a specific time. This research proposed the Two-Stream CNN method, namely spatial and temporal. Spatial to get the pattern on the frame as a whole. Temporal to obtain information on the relationship between the frame and Optical Flow used the Gunnar Farneback method by looking for light transfer points in pixels in all parts of the frame between two interconnected frames. Two different architectures and optimizers were used, namely VGG16 and Xception, for the architecture, while the optimizer were SGD and AdaDelta. The proposed method used two architectures, namely VGG16 and Xception. Besides, the optimizer model used SGD and AdaDelta. As a result, the Xception architecture with the SGD optimizer model provided a higher accuracy of 98.68%.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115513281","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":"Optimization of Overcurrent Relay Coordination using Artificial Bee Colony","authors":"Y. Siregar, Z. Pane, A. Nasution","doi":"10.1109/ic2ie53219.2021.9649281","DOIUrl":"https://doi.org/10.1109/ic2ie53219.2021.9649281","url":null,"abstract":"A protection relay system is essential to isolate the disturbance as early as possible in the electric power system. In overcoming various disturbances, relay coordination is important to cooperate relay to ensure safe and reliable operation for the continuity of electrical service. The relay coordination is the main relay that works selectively against disturbances that occur in the electrical system. If the relay fails to isolate the disturbance, the backup relay can work as a backup safety. Previously, research on optimization of overcurrent relay coordination has been carried out using the Fuzzy Logic method. This study compares the Artificial Bee Colony method with Fuzzy Logic optimization for time and TMS values for getting optimization. Using the Artificial Bee Colony method, the study results showed the average TMS error value is 21.57%, and the average time error value is 13.46%. On the other hand, the fuzzy logic optimization average TMS error value is 30.48%, and the average time error value is 43.18%.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125906368","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}