International Journal of Advances in Data and Information System
Not a member yet
161 research outputs found
Sort by
Enhancing Soil-Transmitted Helminth Detection in Microscopic Images Using the Chain Code for Object Feature Extraction
Full text linkSoil-Transmitted Helminth (STH) infections are a grave global health issue, which involves particularly in countries that are developing with insufficient sanitation and limited access to healthcare. With better intestinal helminth egg detection technology, health facilities in areas with limited resources can identify and treat these infections more promptly. It is necessary to create a strong framework and an effective method to solve this challenge. The outcomes of this study could assist in parasite infection discovery and public health. Chain code-based feature extraction strategy can also be the foundation for the development of comparable approaches for diagnosing various parasitic diseases. Overall, the neural network design used in this study makes the model that is produced a good model that assigns well to never-before-seen data. The significance of image processing technologies in the medical field is shown by this study
Hoax Detection News Using Naïve Bayes and Support Vector Machine Algorithm
Full text linkWebsites and blogs are well-known as media for broadcasting news in various fields such as broadcasting news. The validity of news articles can be valid or fake. Fake news is also known as hoax news. The purpose of making hoax news is to persuade, manipulate, and influence news readers to do things that contradict or prevent correct action. This study proposes to experiment with the Support Vector Machine and Naïve Bayes classifications to detect hoax news in Indonesian. This study uses a dataset from public data, namely news between valid news and hoaxes. The system can classify online news in Indonesian with the term frequency feature the machine vector Support algorithm and naïve Bayes classification. While the evaluation model used is the Confusion Matrix. The results of the comparison of the two models as a Support Vector Machine have an accuracy rate of 75,5%, and Naive Bayes has an accuracy rate of 88%. Therefore, for the classification of hoax news, we recommend the Naive Bayes model because it has a better level of accuracy than the Support Vector Machine
Website Evaluation of DISPERDAG Section of the Average Price of Standard Needs Using the WEBQUAL 4.0 Method
Full text linkDISPERDAG of Madiun City is one of the organizations that has utilized technology. The community can easily access and get price updates for basic necessities at Pasar Besar City of Madiun. The Internet helps support strong governance management, which benefits its effectiveness. Its functions include making it easier to get information, access public services, communicate with the public, and others. DISPERDAG aims to continue to provide quality services. The quality of services provided to the public must complement the implementation of website-based services so that the public continues to use SISKAPERBAPO services. To provide the best service to users, government institutions should prioritize service quality. Therefore, the success of the service quality of the SISKAPERBAPO website has not been known as long as the website is implemented. This is because there has never been an evaluation of website quality based on user satisfaction. It goes without saying that a website that is useful for assisting users in obtaining information must maintain quality in terms of information delivery and user interaction. Good service quality is offered from the user\u27s point of view as well as the service provider\u27s point of view
Web-Based Counseling Skills Evaluation Information System Using Design Science Research Methodology (DSRM) Approach
Full text linkThis research presents the development of a web-based counseling skills evaluation information system using the Design Science Research Methodology (DSRM) approach. The DSRM approach was utilized to design and develop an effective and efficient information system that meets the requirements of the counseling profession. The research discusses the six stages of DSRM, which include problem identification, solution design, construction, evaluation, communication, and reflection, and how they were used to develop the system. The evaluation stage involved conducting empirical studies to assess the system\u27s effectiveness in supporting counseling skills evaluation. The article concludes that the DSRM approach was effective in developing a web-based counseling skills evaluation information system that meets the needs of the counseling profession. This web using PHP, MySQL and Youtube API. The testing software using blackbox and beta testing. the final results of the study show the level of success of the system in facilitating the process of assessing and evaluating basic counseling skills
Prediction of Apartment Price Considering Socio Economic and Crime Rates Factors in DKI Jakarta
Full text linkInvesting in real estate properties in Indonesia is highly lucrative due to their consistent appreciation in value. Amongst the various property types, apartments are particularly favored for investment in limited land space. However, determining the value of apartments is often subjective and lacks quantitative measures. To address this issue, this study develops prediction models to predict rental prices and asset value based on apartment specifications, socio-economic factors, and crime rates. Machine learning models employed include Random Forest, Decision Tree, and Gradient Boosting Machine. The findings show Gradient Boosting Machine exhibits the highest accuracy in predicting apartment rental and sale prices, achieving R² values of 0.9230 and 0.8460, respectively. The study also highlights the significant influence of socio-economic factors and crime rates on the performance of the models, contributing between 0.09 and 0.22 with an average of 0.14, as indicated by the improved R² values. This study demonstrate that these models can be valuable tools for real estate investors and professionals seeking quantitative measures to determine the value of apartments. By incorporating apartment specifications, socio-economic factors, and crime rates, the models can provide objective insights into the potential rental income and asset value of apartments
Hybrid Model Transfer Learning ResNet50 and Support Vector Machine for Face Mask Detection
Full text linkThe Covid-19 virus caused a health crisis in Indonesia. This virus is so deadly that it has caused many fatalities which have caused the whole world including the government to pay major attention to the Covid-19 pandemic. The Indonesian government has issued several policies to prevent the spread of this epidemic, one of which is wearing a mask in public places. One approach that is widely used in the field of computer vision is the Convolutional Neural Network (CNN) transfer learning. In this study, Hybrid Model Transfer Learning ResNet50 and SVM with RGB to HSV preprocessing is presented to detect masks in facial images. This model consists of three process components. The first is preprocessing RGB images to HSV, the second component is for Feature Extraction with ResNet50 and the third is mask classification on face images with Support Vector Machine (SVM). From dataset of 7328 training and testing data were carried out. The first model, without preprocessing the image data with ResNet50, produces an accuracy of 86.52%. The second model, the model with preprocessing converts image data from RGB to HSV with ResNet50 resulting in an accuracy of 99.18%. In the third model, without preprocessing with ResNet50 and SVM which has an accuracy of 90.55%. The fourth model, the model with preprocessing converts image data from RGB to HSV with ResNet50 and SVM resulting in an accuracy of 98.36%
Prediction of Service Level Agreement Time of Delivery of Goods and Documents at PT Pos Indonesia Using the Random Forest Method
Full text linkThis study aimed to predict the service level agreement travel time for goods and document shipments at PT Pos Indonesia (Persero) from the island of Java to the islands of Kalimantan, Sulawesi, Maluku and Papua. This is very important because of the high competition between the logistics industry which is getting faster and faster. The random forest method was chosen because this method is easy to use and flexible for various kinds of data. The prediction results with Random Forest in this study have a good level of accuracy, namely 83.86% of the average 4 trials. This shows that the Random Forest method is the right choice for managing the existing data model at PT Pos Indonesia
Pay Later Risk Management: A Review of FMECA and Potential Customer Prediction Frameworks Through the Application of Machine Learning
Full text linkThe development of technology continues to develop and gradually change the way people buy such as on online shopping sites. The increase in internet use, especially in the use of E Commerce, has given birth to great potential in the market, especially in Indonesia. These changes prompted the birth of various payment methods. One of them is Pay Later. 27% of the 3560 samples decided to use Pay Later with all the conveniences offered. However, the development of Pay Later is not synchronized with good risk management. The use of Pay Later, which is not targeted at the right consumers, causes PT. XYZ suffered losses due to 22.37% of users defaulting on Pay Later installments. The purpose of this study is to reduce Pay Later default users by answering what factors cause consumers to default. To support this study, the authors used FMECA, Cause Effect Diagrams and conducted tests using Machine Learning to improve company efficiency. Through critical matrix analysis, the author gets 3 priority failure modes, Users default, users disappear, and users experience payment delays. In solving the problems in this study, the authors provide recommendations in the form of a new framework in the form of analyzing the best Pay Later offers by analyzing consumer behavior patterns in an E Commerce by utilizing Machine Learning. However, future research will need to be conducted correlation analysis and static testing in testing attribute correlation before testing algorithms when building machine learning models. The authors also suggested comparing using other methods to improve risk management in this study
Comparative Analysis of Software Development Lifecycle Methods in Software Development: A Systematic Literature Review
Full text linkIn the last decades, various Software Development Lifecycle (SDLC) models have been developed to meet the different needs and challenges in the software industry. The purpose of this research is to analyze and compare some of the most common SDLC methods. After the selection and evaluation process is complete, a literature review is carried out by collecting articles, books, and other sources related to the SDLC method. Several main SDLC methods were selected for thorough analysis. Waterfall, Agile and Scrum are some of the methods. Important factors such as flexibility, speed of development, ability to adapt to changing requirements, and project risk are evaluated. The results of the analysis show that each SDLC method has strengths and weaknesses, and that they are appropriate for a variety of situations. While Agile and Scrum methods emphasize flexibility and teamwork, the Waterfall method provides greater structure and clarity to plans. This study aims to determine the best process method for software development. This literature review provides an in-depth understanding of the features, strengths, and weaknesses of various existing SDLC methods. With a better understanding of these methods, organizations can choose the SDLC method that best suits their project needs, thereby increasing the efficiency and effectiveness of software development. This research resulted in a process method that is widely used in software development, namely the Agile method
The Evaluation of Computer Science Curriculum for High School Education Based on Similarity Analysis
Full text linkThe government is currently developing regulations to regulate education curriculum For High School Students. In this regulation, curriculum standards have been created that can be developed by educators in schools. Computer science teachers at the school level develop a curriculum that has been set as a standard curriculum. However, measurable evaluation to optimize the development of the new curriculum has not been available yet. This research proposes a form of evaluation that can be used as a benchmark by analyzing the similarity of curriculum content developed by teachers using a text mining approach. This is conducted by comparing computer science documents with applicable documents, namely knowledge field documents. It is expected that the results of optimizing competency development in the computer science curriculum can be achieved better. The average similarity checking performances using Cosine Similarity and Word2Vec are 40.9850 and 97.3558 respectively. Meanwhile, in the process of fulfilling the knowledge sector, with Cosine Similarity an average percentage of 40.98% was obtained, and with Word2Vec an average percentage of 97.36% was obtained. The results of this trial will be used as a basis for measurable evaluation of teacher contributions to be able to develop the curriculum better according to the applicable curriculum. The results of this evaluation are also used by the government to make future curriculum evaluations more measurable and the standards used are clear and help facilitate curriculum development in schools