cover
Contact Name
Hindriyanto Dwi Purnomo
Contact Email
garuda@apji.org
Phone
+6285885852706
Journal Mail Official
ijiteb@uksw.edu
Editorial Address
Fakultas Teknologi Informasi Universitas Kristen Satya Wacana Jl. Notohamidjojo 1, Blotongan, Salatiga, Jawa Tengah, 50711
Location
Kota salatiga,
Jawa tengah
INDONESIA
International Journal of Information Technology and Business
ISSN : 26559293     EISSN : 2655495X     DOI : 10.24246
Core Subject : Science,
Information Technology Management Information System E-commerce Computational Intelligence Information Infrastructure Cyberspace Enterprise Resource Model Business Intelligence Diffusion and Future IT Network Management IoT Infrastructure
Articles 40 Documents
Optimization of J&T Express Manado Courier Distribution Route Using Coordinate-Based Travelling Salesman Problem Method Anggraini Deborah Manisea; Winsy Christo Deilan Wekua; Deiby Tineke Salakia
International Journal of Information Technology and Business Vol. 6 No. 1 (2023): November : International Journal of Information Technology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.612023.01-09

Abstract

In the package delivery industry, exemplified by J&T Express Manado, optimizing courier distribution routes is essential for customer satisfaction, cost reduction, and on-time deliveries. The Traveling Salesman Problem (TSP) is a valuable tool for finding efficient routes to visit all delivery points once. This study employed the Genetic Algorithm and Nearest Neighbor Algorithm to tackle the TSP, aiming to identify the shortest routes and minimize distribution distances for J&T Express Manado's couriers using geographical coordinates. The Genetic Algorithm resulted in a distribution route of 41.20678 km, while the Nearest Neighbor Algorithm achieved a shorter route of 38.10361 km. For J&T Express Manado, our findings indicate that the Nearest Neighbor Algorithm excels in identifying the shortest courier distribution route and requires significantly less computational time. This study offers insights for J&T Express Manado and similar courier services, enabling them to enhance distribution operations, potentially reducing costs and improving efficiency. It also underscores the practical advantages of the Nearest Neighbor Algorithm in addressing TSP challenges within the industry
The Power Transformer Failure Prediction with Dissolved Gas Analysis Method Using TDCG based Random Forest Sugiman, Marcelino Maxwell; Purnowo, Hindriyanto Dwi
International Journal of Information Technology and Business Vol. 7 No. 2 (2025): April : International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.722025.15-20

Abstract

The transformer is an important component, and early detection of potential failures plays an important role in the reliable operation of the electric power system. This article describes a new approach to power transformer failure prediction based on dissolved gas analysis (DGA) by applying the TDCG method with  the Random Forest algorithm. DGA data from operational transformers is used to train and test predictive models. The random forest  method based on TDCG allows comprehensive analysis of changes in dissolved gases in transformer oil, thus enabling early detection of failure conditions. The experimental results show that  the prediction model uses a model created by applying hyperparameter tuning for optimal  parameter tuning to have high accuracy, accuracy is obtained up to 96% in detecting potential failures, the standard used for accuracy presentation uses confusion matrix as the accuracy of the prediction model. In addition, it can optimize time efficiency in analyzing failures and prevent human error when calculating gas fault  identification or potential failures.
Design of Batik Motif Detection System Using Deep Learning Method Janinda Puspita Anidya; Hindriyanto Dwi Purnomo
International Journal of Information Technology and Business Vol. 7 No. 2 (2025): April : International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.722025.09-14

Abstract

Batik in Indonesia is growing very rapidly, almost every region or city in Indonesia has a variety of batik motifs. The batik motifs owned by each region are their own wealth and heritage in each region that must be preserved and maintained properly. So the Indonesian people need to collaborate with each other to place batik preservation as a top priority in the field of preserving the nation's culture. Because knowledge of batik motifs in Indonesia is important in order to maintain the culture of the Indonesian nation, including knowledge of batik motifs in each of their respective regions, so there is a need to make it easier for humans to recognize batik motifs in regions in Indonesia quickly and easily. This study aims to build a system model that can assist humans in recognizing batik motifs in Indonesia through this batik motif detection system. This research produces a model that can detect batik motifs from every area in Central Java. The conclusion of this study is a batik detection model that can help and introduce to the public about various batik motifs from each region.Batik in Indonesia is growing very rapidly, almost every region or city in Indonesia has a variety of batik motifs. The batik motifs owned by each region are their own wealth and heritage in each region that must be preserved and maintained properly. So the Indonesian people need to collaborate with each other to place batik preservation as a top priority in the field of preserving the nation's culture. Because knowledge of batik motifs in Indonesia is important in order to maintain the culture of the Indonesian nation, including knowledge of batik motifs in each of their respective regions, so there is a need to make it easier for humans to recognize batik motifs in regions in Indonesia quickly and easily. This study aims to build a system model that can assist humans in recognizing batik motifs in Indonesia through this batik motif detection system. This research produces a model that can detect batik motifs from every area in Central Java. The conclusion of this study is a batik detection model that can help and introduce to the public about various batik motifs from each region.
Twitter Sentiment Analysis Using Natural Language Processing (NLP) Method and Long Short Term Memory (LSTM) Algorithm in the 2024 Indonesian Presidential Election Basworo Ardi Pramono; April Firman Daru; Muhammad Bahrul Ulum
International Journal of Information Technology and Business Vol. 6 No. 2 (2024): April: International Journal of Information Technology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.622024.24-30

Abstract

Twitter is one of the media used by the Indonesian people to express their opinions regarding the 2024 Presidential Election. However, there is no scientific calculation that can determine the tone of public opinion regarding the 2024 presidential election. In this study, sentiment analysis was carried out on the tweets of the Indonesian people related to the 2024 Presidential Election (Pilpres 2024). The purpose of this study is to find out the opinions of Indonesian Twitter users regarding the 2024 Presidential Election using Natural Language Processing (NLP) Technology and Long Short Term Memory (LSTM) algorithms. NLP techniques are used to understand natural language and extract meaning from tweet copy, and LSTM is used to analyze the accuracy and accuracy of classification. The data used in this study was 1,004 tweets with the topic "Presidential Election", this data researchers obtained through the process of crawling using the tweet harvest library. In this study, 53.2% had positive emotions, 3.5% had neutral emotions, and 43.3% had negative emotions. 78% accuracy, 67% precision, and 67% recall.
GoPay App Review Sentiment Classification Optimization Using a Combination of Text Representation and Machine Learning Rifki Dwi Kurniawan
International Journal of Information Technology and Business Vol. 6 No. 2 (2024): April: International Journal of Information Technology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.622024.31-36

Abstract

GoPay as one of the digital payment applications in Indonesia faces challenges in understanding user perceptions in the midst of fierce competition. This study aims to develop a user review sentiment analysis model by comparing two approaches to text representation, namely TF-IDF and BERT, as well as two machine learning algorithms, namely Random Forest and Logistic Regression. Review data is obtained from the Google Play Store and processed through pre-processing, feature extraction, and sentiment modeling. The results showed that the combination of BERT + Logistic Regression provided the best performance with an F1 Score of 0.86, showing the superiority of BERT in understanding the semantic context compared to TF-IDF. An important feature analysis identifies financial-related words such as "duitnyaapakah" and "kompensasi" as key issues. This research makes a practical contribution by helping app developers improve the user experience through prioritizing relevant features and solutions to key problems complained of.
Optimizing Natural Resources: Dye Plant Conservation For the Harungguan Muara Ulos Weaving Industry Dahlia Nopelina Siallagan; Rina Handayani; Sariayu Sibarani
International Journal of Information Technology and Business Vol. 7 No. 1 (2024): November: International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.712024.09-16

Abstract

Plant dyes are used in the Harungguan Muara ulos weaving industry to optimize local natural resources. Synthetic dyes have become a fast option along with the increasing demand for ulos. However, synthetic dyes adversely affect the quality and sustainability of the environment. This research used observational methods, in-depth interviews, also gaining an understanding of current and applicable conservation practices. The research showed some local plant species are well suited to be used as a source of natural dyes, but their populations are threatened by overexploitation, lack of conservation efforts and emphasized the importance of traditional knowledge with contemporary conservation methods. The proposed recommendations educate ulos weavers on the importance of using natural dyes, and conduct follow-up research to find more efficient cultivation methods.This research make efforts to preserve Batak cultural heritage and support sustainability to strengthen the ulos weaving industry as an environmentally friendly and economically valuable cultural product.
Analysis of Twitter Sentiment in Cases Of Domestic Violence Comparison of Lexion-Based and Niave-Bayes Ardi Wijaya; Rozali Toyib; Jestika Safitri; Anisya Sonita; Yulia Darnita
International Journal of Information Technology and Business Vol. 7 No. 1 (2024): November: International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.712024.01-08

Abstract

Twitter, a social media platform with millions of users, serves as a valuable source for unique insights. The case of Lestibillar domestic violence has garnered attention, fueling various circulating rumors that encompass positive, negative, and neutral opinions. This, in turn, gives rise to the potential spread of fake news. To counter this, sentiment analysis is employed using machine learning techniques. In this research, two machine learning algorithms within the realm of supervised learning are compared: lexicon-based and Naive Bayes. Sentiment objects are created for each algorithm to facilitate the comparison, aiming to determine which algorithm performs better in terms of accuracy. The results of the calculations indicate that Naive Bayes outperforms, achieving a superior accuracy of 99.96%, while the lexicon-based method lags significantly behind at 10.29%. The dominance of positive tweets is evident, comprising 2709 out of the total tweets on Twitter.
Analysis of Learning Patterns of Job Training Class Users on the Masadepan.ku Platform Indah Amelia; Herti Yani; Beny Beny
International Journal of Information Technology and Business Vol. 7 No. 2 (2025): April : International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.722025.27-32

Abstract

Masadepan.ku platform provides digital-based job training classes; however, the utilization of user data to enhance learning effectiveness remains suboptimal. This study aims to analyze user learning patterns based on completion rates, final scores, and participation across various fields of study. The methods used include pearson correlation analysis and data visualization through dashboards. The findings indicate no significant correlation between final scores and class completion time, with a correlation value of -0.0896. Fields of study with high participation and completion rates include social sciences, which have a participation rate of 99% and a completion rate of 97%, as well as entrepreneurship, with a participation rate of 93% and a completion rate of 95%, followed by religion, law, and administration. Fields of study with low participation and low completion rates include education and others. Additionally, fields of study that also exhibit low participation and low completion rates include technology and accounting. In terms of user satisfaction, the health category recorded the highest average rating of 4.96, indicating a very high level of satisfaction among participants. Meanwhile, the engineering and automotive category registered the lowest average rating of 4.76. Fields of study that require improvement based on low completion rates and low ratings include automation, with a completion rate of 85% and an average rating of 4.79, and tourism, with a completion rate of 83% and an average rating of 4.85, as well as the others, design, technology, and accounting categories.
Sales Data Analysis and Visualization for Distribution Optimization: Case Study: US Candy Distribution Riska Indarwati; Herti Yani; Beny, Beny
International Journal of Information Technology and Business Vol. 7 No. 2 (2025): April : International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.722025.21-26

Abstract

Optimization of US Candy's product distribution was conducted through sales data analysis and visualization. The main challenges identified include less strategic factory locations and high logistics costs. This research used a quantitative approach. The purpose of this analysis is to analyze the distribution pattern. Data visualization was conducted using Power BI to show the results of the analysis that New York is the highest selling city with total sales of $10,945.89, with the leading product being Wonka Bar - Scrumdiddlyumptious ($2,718). The consistent increase in sales trend in the fourth quarter of each year, triggered by celebrations such as Halloween, special promotions, and holidays can be utilized to develop future marketing and product inventory strategies. A distribution optimization strategy is recommended to minimize logistics costs and delivery time, by moving distribution to the Wicked Choccy's factory with a distance of 8237.2 km. Marketing strategies such as discounting best-selling products and bundling system for low-selling products are proposed to improve market competitiveness. The resulting interactive dashboard implementation is expected to assist the company in making more accurate and efficient data-based decisions.
Classification of Investment Opportunities in Semarang City Using the K-Nearest Neighbor Data Mining Method Bernadus Very Christioko; Daru, April Firman; Dyan Sinung Prabowo; Alaudin Maulana Hirzan
International Journal of Information Technology and Business Vol. 7 No. 2 (2025): April : International Journal of Information Techonology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.722025.01-08

Abstract

Investment is an activity undertaken to allocate funds with the expectation of generating future returns. In a dynamic economic environment, identifying profitable investment opportunities can be a complex task. This study aims to determine potential investment opportunities in Semarang City using a classification method that facilitates business actors or investors in selecting appropriate business sectors. The study utilizes valid data to help investors make informed decisions when establishing a business in the region. Data collection was conducted through research at the Investment and One-Stop Integrated Services Agency (DPMPTSP) of Semarang City, employing a quantitative approach with the K-Nearest Neighbor (K-NN) method. The dataset was divided into training and testing sets with an 80:20 ratio. The experimental results show that the implementation of the K-NN algorithm, conducted using Google Colab, achieved an accuracy of 86% based on 60 testing data points. This demonstrates that the K-NN classification algorithm is effective and produces accurate predictions. Therefore, applying data mining classification techniques to identify investment opportunities can serve as a viable solution to support strategic decision-making for investors.their business development strategies with sector-specific prospects in Semarang City.

Page 4 of 4 | Total Record : 40