Journal of Informatics And Telecommunication Engineering
Not a member yet
373 research outputs found
Sort by
Input Parameters Comparison on NARX Neural Network to Increase the Accuracy of Stock Prediction
Get PDFThe trading of stocks is one of the activities carried out all over the world. To make the most profit, analysis is required, so the trader could determine whether to buy or sell stocks at the right moment and at the right price. Traditionally, technical analysis which is mathematically processed based on historical price data can be used. Parallel to technological development, the analysis of stock price and its forecasting can also be accomplished by using computer algorithms e.g. machine learning. In this study, Nonlinear Auto Regressive network with eXogenous inputs (NARX) neural network simulations were performed to predict the stock index prices. Experiments were implemented using various configurations of input parameters consisting of Open, High, Low, Closed prices in conjunction with several technical indicators for maximum accuracy. The simulations were carried out by using stock index data sets namely JKSE (Indonesia Jakarta index) and N225 (Japan Nikkei index). This work showed that the best input configurations can predict the future 13 days Close prices with 0.016 and 0.064 mean absolute error (MAE) for JKSE and N225 respectively.Â
Classification of Public Figures Sentiment on Twitter using Big Data Technology
Get PDFPublic figures often receive widespread public attention because they can exert a meaningful influence. On Twitter, the users can freely express their opinion through tweets. There are about 456,000 tweets sent in a minute which with this large and diverse number will make Big Data. Big Data has valuable potential for better decision-making. This large amount of tweet data can yield valuable information through sentiment analysis. This study aims to conduct a sentiment classification of Indonesian public figures using Twitter's data. This study used 1,034,329 tweets collected from Twitter in the period November 2021 until March 2022. Tweet classification is done by building a classification model using the Bidirectional Long Short-Term Memory algorithm. Sentiment toward public figures in Indonesia is 45.98% negative sentiment, 28.04% positive sentiment, and 25.98% neutral sentiment resulting from this study. The highest positive sentiment is obtained by public figures when there is content or news that is relevant to the public figure, while the highest negative sentiment is obtained when there is content or news that contradicts the image of the public figure
Implementation of Logistic Regression Classification Algorithm and Support Vector Machine for Credit Eligibility Prediction
Get PDFCredit is a provision of money or bills that can be equated with it, the provision of loans or credit. A good credit analysis is very necessary, because it is one of the most important processes in the form of an investigation regarding the smooth or substandard credit repayments. The stages of identifying and predicting customers properly and correctly can be done before the loan process. This is done by examining the historical data of the customer's loan. At this time this activity is an effort made by the banking industry in dealing with credit risk problems. In this research, researchers will apply several data mining classification methods, including Logistic Regression algorithms and Support Vector Machines to predict creditworthiness. The dataset used 481 record motorized vehicle loan data, both problematic and non-problematic. The input variables in this study consisted of thirteen variables, including marital status, number of dependents, age, residence status, home ownership, occupation, employment status, company status, income, down payment, education, length of stay, and housing conditions. From the results of research and testing, the performance of the Logistic Regression model for predicting creditworthiness provided an accuracy rate of 94.81% with an area under the curve (AUC) value of 0.987. While the performance of the Support Vector Machine model provides an accuracy of 94.19% with an area under the curve (AUC) value of 0.978. Based on the T-Test test, the Logistic Regression method has the same performance compared to the Support Vector Machine
Analysis Of Deep Learning Architecture In Classifying SNI Masks
Get PDFIn preparing for the new normal for COVID-19, every government agency, school and university will be required to comply with new regulations by the government, in which the government will oblige everyone who does activities outside the home to wear masks and practice physical distancing. This is one of the new habits that the government will familiarize with starting in 2020. Due to the ease with which the Covid-19 virus spreads. So the selection of a good mask is recommended good mask, namely a mask that follows the recommendations of the WHO at least 3 layers. The purpose of this study was to classify the types of SNI and non-SNI masks so that the presence of this SNI mask cluster monitoring system could improve security at locations that apply the use of masks and the masks used can function effectively to prevent the spread and spread of Covid-19, classification of research models it uses the InceptionV3, Resnet50, InceptionV2, AlexNet and DenseNet architectures. The results of trials that have been carried out by the InceptionV3 architecture have the most optimal accuracy with loss values of 3.4889 and 0.9894 (98.94%)
Aceh's Historic Tourist Attractions: An Augmented Reality-Based Prototype of a Virtual Tour Application
Get PDFIndonesia has attractive tourist destinations for tourism such as beautiful interior areas and historical places. The purpose of this research is to design and build a virtual tour application for Aceh tourism objects using augmented reality. One of the problems that occur in tourist objects is that foreign tourists do not have an idea about the tourist objects they want to visit. The technology used in this study and previous research is Augmented Reality, but previous research only displays 3D tourist objects, while in this study, augmented reality technology is incorporated into the design of the 4 Aceh tourist attractions by showing a 3-dimensional illustration of the object as a whole. for the outside of the building and displays a virtual tour image in the form of a video to illustrate the inside of the tourist attraction building on the Android mobile platform. Based on the results of distance and angle testing, the best (ideal) distance that produces clear and bright marker detection is found at a distance between 25 to 45 cm, while the best angle is between an angle with a slope of 0° to 60°. Measurements of distances and angles are carried out using threads, bows and measuring tapes. The 3D object is successfully displayed by pointing the camera at the marker to be detected.Â
Deterministic Finite State Automatic Smartphone Sales at Handphone Store Using Vending Machine
Get PDFMobile phones are getting more sophisticated from year to year, and there are many features that have the latest in these cellphones. Mobile phones have the fastest network today with fourth generation technology so it's not slow to watch videos, play games, study online, and so on. Mobile phones sold have variations of Android and Iphone Operating System. The sale of the cellphones is through mall counters, roadside counters, and street vendor counters. Cellphone sales counters still use tables, cell phone holders, brochures to promote cellphones, and others seem boring, there must be something unique to attract customers' attention. This study aims to develop innovation in selling cellphones that are unique and different from other cellphone stores. The research method uses Deterministic Finite State Automata on the Vending Machine. State Diagram design to define features, main view design, and purchase flow. The results of the study using Deterministic Finite State Automata in the Vending Machine design make it easier for buyers to make purchases of cellphones independently and have their own uniqueness to attract customers' attentio
E-COMMERCE BASED SALES APPLICATION TO INCREASE PROFIT DURING COVID19 IN FURNITURE STORES
Get PDFSince December 2019 there has been an outbreak that can kill thousands of people in a matter of days, while the outbreak has become a threat to a new pandemic known as Covid-19. The impact of the Covid-19 outbreak has greatly affected various sectors, one of which is the trade sector. Since the outbreak of the Covid-19 outbreak and the Government's recommendations regarding Social Distancing and the establishment of very strict health protocols, some people are reluctant to do activities outside the home so that people are more restricting themselves by staying at home. This certainly makes trade experience a slump so that it has an impact on an unstable economy and finances. the development of technology and the internet in Indonesia, has had a major impact on changes in business and sales systems. E-commerce is an internet service that is used for buying and selling online. The purpose of this research is to build an E-Commerce-based system that can help some furniture businesses in increasing sales profit, by providing convenience in the payment process. The stages of the research method that the researcher planned were to conduct survey techniques and followed by interview activitie
Determining The Location Of RMU, Using K-Means Clustering, Evaluate The Location Of Existing RMU, Using R-Programming
Get PDFRice milling into rice, (Rice Milling Unit, RMU) is needed to process the harvested grain into rice. In determining the location, the consideration of road access to consumers is still used and it is often far from the rice fields, the source of the grain material to be milled. This paper aims to analyze the ideal location with the consideration of being in a rice field cluster and the area of the rice field, so that it can accommodate crop yields around the cluster, namely the location of the spatial coordinates and the area (hectare). Primary data was obtained by the author from the Department of Agriculture of Malang Regency and the data was processed as input for analysis. Analysis of determining the location of the center of the rice field cluster using the Weighted K-Means Clustering method by comparing several alternative cluster points (K) and the area of rice fields, testing the variation of K is, K = 5, 6, 7 and 8. Optimal test results at K = 7. Calculations using the R language. The test results obtained that the cluster center suggested 7 clusters to accommodate the rice harvest in 7 regions, namely in the west, north (1), middle (2), south (3), east (1) and west (1 ) . Evaluation of the location of the existing RMU, there are 5 locations, so that for the next planning, you can add 2 more clusters to build the RMU and accommodate a more even rice harvest
Application of the Waterfall Method in Software Design on Android-Based Programming Language Course Applications
Get PDFIn this era of technology and information proliferating, programming skills are needed. Technology affects every area of life from industry, business, communication, transportation, health, and others. Everyone has the same opportunity to learn and master technology thus programming language courses are needed to provide education, innovation, and improvement of skills and abilities in the field of programming and data science to the public. Until now, programming language courses still use the conventional system, where everything is done manually, from class registration, class scheduling, teaching and learning process, and payment processing which results in many archives that must be stored for administrative purposes and require a relatively large amount of time for customers to come to the course location. Therefore, an information technology-based system is needed to fix the weaknesses of the old system. In this study, an Android-based programming language course application is designed to facilitate customers and course owners in teaching and learning activities and transactions. The design in this study uses the waterfall method, which consists of five stages, needs analysis, design, code, testing, and maintenance. The results obtained from testing applications using questionnaires on programming language course applications are 80% stated by course customers, where the application is easy to use, faster, and more practical in registering. In conclusion, this designed application can make it easier for customers to carry out teaching and learning activities and transact quickly and practically
Recommendation System of Component Selection for Aquascape With SMART Method
Get PDFAbstractThe increasing enthusiasm of aquascape hobbyists is one of the factors in the development of the beauty industry of artificial underwater ecosystems in the aquarium. The aesthetic value offered by aquascape is one of the allures for its connoisseurs. The art of organizing ecosystems in water is a simple definition of an aquascape. The complexity of the arrangement can then be described through the presence of various themes. The selection of tools, flora and fauna, and other ornaments to form a unified ecosystem are things that are of concern so that an ecosystem in artificial water has good aesthetic value and can be categorized in a certain theme. By using a decision support system (DSS) or decision-making system, the results can provide better decisions and minimize the possibility of errors. One method of decision making in the scope of decision support system (DSS) or decision making system is Simple Multi Attribute Rating Technique (SMART), where this method can determine product recommendations based on several product variants offered as a form of marketing analysis. This method is able to provide recommendations for more than one decision and provide results with the best accuracy. System testing was conducted to 50 users and it was found that the recommendation system based on the questionnaire application was able to provide a good percentage of conformity between the user's wishes and the recommendations given. That is, 51% of correspondents rated it very appropriate, 27.5% of correspondents rated accordingly, 19.5% of correspondents rated neutral, and only 2% of correspondents rated it inappropriateKeywords: Aquascape, Decision Support System, SMART, Recommendatio