2022 International Seminar on Application for Technology of Information and Communication (iSemantic)最新文献

{"title":"Artifact-EOG Denoising Using FIR-Filtering In EEG Channel Selection For Monitoring and Rehabilitation of Stroke Patients","authors":"M. T. Sulistyono, Dyah Ernawati, Wellia Shinta Sari, Siti Hadiati Nugraini","doi":"10.1109/iSemantic55962.2022.9920409","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920409","url":null,"abstract":"Electroencephalography (EEG) will produce a non-invasive recording of brain signals used to analyze brain performance activity for medical or clinical personnel in diagnosing brain-related diseases such as stroke. The recorded EEG signal is the original brain wave signal which still contains noise artefacts. Artefact noise, among others, occurs due to eye movement or Artifact Electrooculography EOG. The main problem of this paper is that there is still noise in interpreting the EEG signal, so it is necessary to denoise the artefacts of the EOG signal using the FIR filter method. In a previous study to determine the performance of the EEG signal FIR filter in the human brain in reducing EOG artefacts through a movement stimulus, it can reach less than 100 Hz and work very well on Delta signals with the Signal to Noise Ratio (SNR) value obtained after filtering is equal to 3.2198 dB. Theoretically, the Delta signal is a wave that appears when a person is deep asleep and without dreams so that no outside information can enter the brain. Usually, in a deep sleeping position, the brain waves generated by recording will experience very little noise because there is no motor activity. Because this research focuses on stroke patients who have to carry out motor activities in medical rehabilitation, motor activity is needed to find the proper signal to reduce EOG-artefacts so that the cleaning process can be carried out correctly. Therefore, this study will improve the determination of the most appropriate signal for motor activity, namely working on Gamma signals and the performance of the EEG signal FIR filter in the human brain in reducing EOG artefacts through movement stimuli that can reach less than 100 Hz and determining the obtained SNR value. After filtering 3.2284 dB, the higher the SNR value is expected to be less noise cleaned and faster in segmentation, data decomposition, and feature extraction.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"15 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":"115441143","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":"Accreditation Documents Profiling Based On The Used of English Terms Using Text mining Algorithm : A case study on 24 accreditation document","authors":"Syahrul Iman, A. Wibawa, S. Sumpeno, Arbintoro Mas","doi":"10.1109/iSemantic55962.2022.9920369","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920369","url":null,"abstract":"Until recently, study program accreditation is still the standard for evaluating the feasibility and quality of the education process worldwide. Normally, in the process of accreditation, one specific study program needs to prepare a report document that represents the whole process of education, especially from the standpoint of quality, and then submit it to the National Board of Accreditation. Self-assessment and evaluation are the keys to creating a proper accreditation document. In the case of Indonesia, the accreditation process is run by the National Board of Higher Education Accreditation (called BAN-PT). The study program must prepare and submit a document that represents the overall process of education by following the national standard and format determined by BAN-PT. In this study, we hypothesized that the text mining technique can be used to evaluate the accreditation document by analyzing the English terms that are used in the document. The analysis is done by scoring the number of English terms in one accreditation document and selecting the proper terms that are used. We hypothesize that the higher the score is obtained by the document the higher the national rank of accreditation was obtained by the document. In this study, 24 accreditation documents with approximately every document consisting of 200 pages within similar study programs were analyzed. A text processing technique was implemented to filter and clean the documents from unimportant words. English phrases were detected from each sentence in the document and then continued by extracting English terms further filtering to get the English terms is then performed. The selected English terms are then scored from each accreditation document. The validation process is done by mapping the scoring result with the Accreditation Rank obtained by the document. The result showed that the higher the score based on the English terms obtained by one document. The higher the Nasional Accreditation ranks too. However, two out of 24 documents did not show a similar pattern.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"62 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":"128719341","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":"Knn Algorithm For Foodstuff Classification Using Hsv Color Space And Feature Extraction","authors":"Anggun Pambudi, M. A. Rofiq, M. Anwar Sadat, M. Arief Soeleman, Ricardus Anggi P","doi":"10.1109/iSemantic55962.2022.9920421","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920421","url":null,"abstract":"Indonesian nourishment is one of the wealthiest culinary conventions in the world, characterized by its solid taste. This sort of nourishment requires extra fixings in certain sorts of cooking. In any case, most of the foodstuff photographs were disseminated on social media as they contained few nourishment fixings that are unpredictable and troublesome to distinguish. In truth, several clients who need to discover approximately the fixing of nourishment in look engines still utilize inquiries within the shape of content. This thinks, proposes the KNN algorithm combined with HSV color space and includes extraction, such as histogram-based surface features, lacunarity, and GLCM to bunch the nourishment within the form of pictures. In testing utilizing the (k) esteem on KNN, the most excellent highlight comes about are gotten that deliver a tall level of precision, review, and exactness of 100% at values K=1 and K=3 comes about from the combination of Lacunarity highlights, histogram-based surface highlights with color space HSV, and from the esteem of K=1 and K=3 F1-Score execution esteem.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"2009 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":"127326010","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":"Digital Certificate Authentication with Three-Level Cryptography (SHA-256, DSA, 3DES)","authors":"Bagas Dwi Yulianto, L. Budi Handoko, E. H. Rachmawanto, Pujiono, M. Soeleman","doi":"10.1109/iSemantic55962.2022.9920404","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920404","url":null,"abstract":"The rapid development of technology, makes it easier for everyone to exchange information and knowledge. Exchange information via the internet is threatened with security. Security issues, especially the issue of the confidentiality of information content and its authenticity, are vital things that must protect. Peculiarly for agencies that often hold activities that provide certificates in digital form to participants. Digital certificates are digital files conventionally used as proof of participation or a sign of appreciation owned by someone. We need a security technology for certificates as a source of information known as cryptography. This study aims to validate and authenticate digital certificates with digital signatures using SHA-256, DSA, and 3DES. The use of the SHA-256 hash function is in line with the DSA method and the implementation of 3DES which uses 2 private keys so that the security of digital certificate files can be increased. The pixel changes that appear in the MSE calculation have the lowest value of 7.4510 and the highest value of 165.0561 when the file is manipulated, it answers the security of the proposed method is maintained because the only valid file is the original file.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"1 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":"129971448","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":"Evaluation of Real Options Valuation of Petroleum using Deep Learning Algorithms based on Crude Oil Futures Information with Dual Information","authors":"Heru Setyabudi, I. H. Kartowisastro, A. Trisetyarso, E. Abdurachman","doi":"10.1109/iSemantic55962.2022.9920405","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920405","url":null,"abstract":"The valuation of petroleum reserves tends to be undervalued in an uncertain market. The most common method used in the valuation of natural resources is Discounted Cash Flow (DCF), also known as Net Present Value (NPV). However, this method does not consider several important aspects such as flexibility management and uncertainty value. The purpose of this study is to conduct a valuation of petroleum reserves using methods in which the aspects of flexibility management and uncertainty value are considered. The Real Option Valuation (ROV) method is calculated by analogizing it to a Financial Option. There are three types of data used in the valuation, namely: the oil price obtained from futures contracts listed by New York Mercantile Exchange (NYMEX) and Intercontinental Exchange (ICE Futures Exchange), the long-term risk-free interest rate, and the number of oil production and reserves. Artificial Intelligence Algorithm was then used to evaluate the characteristics of oil price movements based on the information retrieved from NYMEX. The ROV method was found to be suitable for the valuation of petroleum reserves. The method could accommodate flexibility management and uncertainty value present in the petroleum reserve market. A deep learning machine was also shown to be an effective tool for predicting futures contracts.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"54 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":"128872947","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":"DESITA: E-Service Optimization of Student Final Project Management Based on Website Technology","authors":"F. I. F. S. Putra, Amron, M. F. Wardhani, R. A. Budiantoro","doi":"10.1109/iSemantic55962.2022.9920446","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920446","url":null,"abstract":"This research aims to implement a new model of e-business technology to optimize the three higher education principles. A strategic step that can be taken is to apply digitalization to increase the selling value of universities in the education industry and increase the usefulness of the satisfaction of lecturers and students. The research approach is exploratory qualitative with data collection techniques through interviews, observations, and literature studies. The sampling method in this study used non-probability sampling (purposive sampling). It can conclude that several supporting factors that influence optimization of the three principles of higher education are flexibility of workplace and time, as well as the use of information technology which is easier to use and has high accessibility. The urgency of this research is to support university programs in implementing smart university so that the three higher education principles become more comprehensive. The stuff that needs to be prepared is integration in implementing the program, ideally to be replicated more easily by the dean in each faculty.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"100 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":"114227191","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":"The Effect of Image Dimension and Exposure Fusion Framework Enhancement in Pneumonia Detection Using Residual Neural Network","authors":"A. W. Setiawan","doi":"10.1109/iSemantic55962.2022.9920377","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920377","url":null,"abstract":"This study tries to find the performance of ResNet 50, 101 and 152 version 1 architecture to classify normal and pneumonia using chest X-ray. For the second goal, the effect of image dimension is investigated. Furthermore, the different distribution of training, validation and testing images in the dataset is explored, i.e. dataset A and B. 5,838 chest X-ray images are used in dataset A. For dataset B, 5,856 images are used. These images are distributed randomly as training, validation and testing images with compositions of 80%, 10% and 10%. For each dataset, 12 image dimensions are used, i.e., 96 × 96; 128 × 128; 160 × 160; 192 × 192; 224 × 224; 256 × 256; 288 × 288; 320 × 320; 352 × 352; 384 × 384; 416 × 416 and 448 × 448 pixels. Moreover, this study used exposure fusion framework as image enhancement in the preprocessing stage. In general, ResNet 152 architecture has better performance than ResNet 50 and 152. However, the best performance is achieved by dataset A using ResNet 50 and an image dimension of 384 × 384 pixels. This model has an accuracy, sensitivity, specificity, precision, F1-score and ROC of 97.6%, 99.3%, 93.1%, 97.5%, 98.4% and 96.2%. The pneumonia detection using ResNet is affected by the distribution of training, validation and testing images. Furthermore, there is no correlation between the image dimension and the detection performance.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"84 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114034267","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":"Hybrid Method of Selection Features to Improve Performance of Covid-19 Classification","authors":"Sabir Rosidin, Muljono, Catur Supriyanto","doi":"10.1109/iSemantic55962.2022.9920453","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920453","url":null,"abstract":"In this study, to improve the performance of the classification algorithm using the Hybrid feature selection method on covid-19 data, this study utilizes the SBS Filtering and Wrapper Technique, aiming to reduce the initial feature sub-space dimensions N (total features) to K (features). best). From the whole process of testing the Hybrid method by combining filtering and wrapper techniques, it can be concluded that from a total of 8974 features, after entering the filtering process, 184, then after applying the wrapper technique to 170 selected features, performance evaluation was carried out and obtained SVM performance results with data The big one is with an accuracy of 83.8% and testing on KNN by testing the parameter value K = 5, getting an accuracy result of 79.5%, the classification of the K value is determined by the researcher. The overall precision comparison is KNN with a precision value of 32.6% and SVM with a precision value of 87.6%, recall with a KNN result of 14.2%, and SVM of 20.1%, a comparison of F1-Score KNN of 17.3% and SVM of 27.5%.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"9 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":"131116091","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":"Comparative Study on Image Filtering For Herbal Plant Identification Using Xception Based Convolutional Neural Network","authors":"Amiel Joseph M. Lozada, Nigel L. Monsanto, Glenn B. Pepito","doi":"10.1109/iSemantic55962.2022.9920424","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920424","url":null,"abstract":"Plant identification, through the use of Convolutional Neural Networks (CNNs), has been utilized in several studies over recent years. With CNNs being almost the default approach when dealing with image processing, the researchers shifted their focus on image filtering techniques. This study determined to investigate the most effective image filter for herbal plant identification. An image dataset of eleven medicinal plants was used by the researchers, made into four copies for image processing. Three image filters were then applied to three different copies of the dataset, namely: Canny Edge Detection filter, Color Saturation filter, and Contrast Enhancement and Thresholding filter; none were applied to the fourth copy since it served as the control group of the study. The Xception model was trained using each of the processed datasets. Afterwards, the researchers discerned which CNN and image filter yielded the most accurate results during testing through the confusion matrix. It was calculated and concluded that the Color Saturation filter was the best image filtering technique to use for identifying herbal plants, achieving 100% in the metrics used during the study. The results of this study can be applied in works and systems that focus on plant identification and image processing in general.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"271 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":"134251295","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":"User Experience Model using Concise User- Centered Design in Small and Medium Enterprise E-Commerce","authors":"Herman Try Maulana, Umi Rosyidah","doi":"10.1109/iSemantic55962.2022.9920381","DOIUrl":"https://doi.org/10.1109/iSemantic55962.2022.9920381","url":null,"abstract":"There are difficulties for small and medium enterprises (SMEs) to use the online platform, specifically e- commerce. Most of the problems are related to user experience because SME owners are very diverse in terms of digital literacy. For example, snack SMEs managed by elderly households are having difficulties operating e-commerce due to a lack of understanding of the user interface. There are many research used User-Centered Design (UCD) as a framework to develop the user experience for e-commerce. It is generally divided into several sections such as defining the scope, analyzing the problem including personas, and usability problems to find user problems and needs. This study uses concise UCD to model the user experience in SME e-commerce. The way to collect the SME’s information is combined in one process, namely the interview, starting with personal questions, habits, and about the business. This approach helps in determining difficult and complex decisions based on the user's point of view. The result shows the low-fidelity wireframe stage that could be the framework to develop the e-commerce user experience for SMEs.","PeriodicalId":360042,"journal":{"name":"2022 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"80 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":"115049786","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}