cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI)
Published by Universitas Ahmad Dahlan
ISSN : 23383070     EISSN : 23383062     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
JITEKI (Jurnal Ilmiah Teknik Elektro Komputer dan Informatika) is a peer-reviewed, scientific journal published by Universitas Ahmad Dahlan (UAD) in collaboration with Institute of Advanced Engineering and Science (IAES). The aim of this journal scope is 1) Control and Automation, 2) Electrical (power), 3) Signal Processing, 4) Computing and Informatics, generally or on specific issues, etc.
Arjuna Subject : -
Articles 601 Documents
 57   58   59   60   61 
Sentence-Level Granularity Oriented Sentiment Analysis of Social Media Using Long Short-Term Memory (LSTM) and IndoBERTweet Method Nisa Maulia Azahra; Erwin Budi Setiawan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 1 (2023): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i1.25765

Abstract

The dissemination of information through social media has been rampant, especially on the Twitter platform. This information eventually invites various opinions from users as their points of view on a topic being discussed. These opinions can be collected and processed using sentiment analysis to assess public tendencies to obtain a fundamental source of decision-making. However, the procedure is not optimal enough due to its inability to recognize the word meaning of the opinion sentences. By using sentence-level granularity-oriented sentiment analysis, the system can explore the "sense of the word" in each sentence by giving it a granularity weight as the system's consideration in recognizing word meaning. To construct the procedure, this research utilizes LSTM as the classification model combined with TF-IDF and IndoBERTweet as feature extraction. Not only that, but this research also conducts the Word2Vec feature expansion method which was built using Twitter and IndoNews corpus to produce word similarity corpus and find effective word semantics. To be fully compliant with the granularity requirements, manual labeling, and system labeling were performed by considering weight granularity as a model performance comparison. This research succeeded in getting 88.97% accuracy for manual labeling data and 97.80% for system labeling data after combining these methods. The experimental results show that the granularity-oriented sentiment analysis model can outperform the conventional sentiment analysis system which can be seen based on the high performance of the resulting system.
Measuring and Mitigating Bias in Bank Customers Data with XGBoost, LightGBM, and Random Forest Algorithm Berliana Shafa Wardani; Siti Sa'adah; Dade Nurjanah
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 1 (2023): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i1.25768

Abstract

To retain its clients, the Portuguese banking institution conducts direct marketing in the form of phone calls to conduct marketing so that clients subscribe to the bank's term deposit. The data used is named bank customers data. Important client features are considered in the acquisition process. This research was conducted with bank customers data from Portuguese banking institution which implements agent acquisition. With a large number of data on bank customers, it can lead to a diversity of data which allows the results of agent acquisition to be unfair. With this, a bias detection and mitigation algorithm are needed to achieve fairness. AI fairness 360 (AIF 360) is a toolkit that provided a bias detection and mitigation algorithm. The bias mitigation algorithm in AIF 360 is divided into three processes, namely reweighing and learning fair representation at the pre-processing stage, prejudice remover and adversarial debasing at the in-processing stage, and equalized odds and reject option classification at the post-processing stage. The output of this study is a comparison of the calculation of bias detection with disparate impact (DI) and statistical parity differences (SPD) before and after mitigation. The adversarial debiasing algorithm performed best than others with 0.943 of DI, -0.004 of SPD, and also increased the 0.015% of the AUC score. Conducting this research can help the prediction of client’s term deposits in Portuguese banking institution more fairly.
Palm Print Recognition Using Intelligent Techniques: A review Sara A. Mohammed Al-Taie; Baydaa I. Khaleel
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 1 (2023): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i1.25777

Abstract

Hand or Palm print recognition systems are one of the efficient people recognition and authentication systems that provide high-security levels by approving the entering and exiting of people such as employees in the work field or companies. The basis for using palmprints lies in the fact that no two individuals have exactly the same palmprint pattern, moreover palmprints remain more or less stablethroughout the lifetime and are easily obtainable using standard imaging techniques. Palm print recognition systems process picture data from a photograph of a person's palm and compare it to a record for that person using a scanning device or camera-based application. There are numerous ways to obtain a palmprint image, including digital scanners. Researchers have taken palmprint photographs using video cameras, CCD-based scanners, and tripods. A CCD-based scanner may be used to take a high resolution image of a palmprint. A palm image can also be perfectly aligned with the user's hand thanks to the pegs on the CCD-based scanner The palmprint has a variety of natural ompositions that are rich in identifying characteristics like wrinkles, ridges, major lines, single, and minute points. Because of these, a palmprint is a distinctive biometric that is trustworthy for identifying humans As Artificial Intelligence (AI) methods and applications improved, the improvement of computer techniques and the usage of  techniques increased in all fields including people recognition field. Many intelligent techniques are used to recognize people such as neural networks, the Genetic Algorithm, Particle Swarm Algorithm, and Deep Learning all these techniques are used and have almost the same recognition accuracy
Social Media Sentiment Analysis Using Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) Ahmad Zahri Ruhban Adam; Erwin Budi Setiawan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 1 (2023): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i1.25813

Abstract

The advancing technologies are aimed to maximize human performance. One of the great developments in technology is social media. The social media used in this study is Twitter because most people in Indonesia give their opinions to the public through tweets. The opinions given are very diverse, where they write positive, negative, and neutral opinions. The purpose of this study is to analyze the sentiments of the opinions given by the public in Bahasa Indonesia. To conduct sentiment analysis, tweets are collected by crawling the data. Tweets are then labeled positive, negative, and neutral and then represented as 1, -1, and 0. The method used to classify tweet sentiment is the Convolutional Neural Network (CNN) and Gated Recurrent Unit method (GRU). Research stages including feature selection, feature expansion, preprocessing and balancing with SMOTE. The highest accuracy value obtained on the CNN-GRU model with an accuracy value of 97.58% value. Based on these tests, it can be concluded that sentiment analysis research on Twitter social media using the Convolutional Neural Network and Gated Recurrent Unit methods can produce fairly high accuracy, and feature expansion testing of the deep learning model can provide a significant increase in accuracy values.
Water Quality Monitoring with Regression Based PPM Sensor for Controlling Hydroponic Dissolved Nutrient Dimas Adiputra; Titus Kristanto; Abduh Sayid Albana; Gilbert Wednestwo Samuel; Syakira Andriyani; Christian Jose Anto Kurniawan; Nursyahjaya Ramadaniputra; Era Anzha Naelil Munna
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.25915

Abstract

Hydroponic cultivation requires rigorous monitoring and control of several parameters, such as turbidity, electric conductivity, acidity (pH), dissolved oxygen and nutrient, which usually be measured once a day manually. Therefore, automation in hydroponic cultivation requires those water quality information as the controlled variable. The dissolved nutrient is especially important because it significantly affects the hydroponic plant growth. Acquiring the dissolved nutrient can be done by using a PPM (parts per million) sensor, but most of the time the sensor needs further processing to obtain the desired measurement. This study presents a reading correction of a PPM sensor based on a regression method so the desired measurement can be done. Sample water with different PPM, such 309 PPM, 290 PPM, 762 PPM, 1910 PPM and 2420 PPM are measured first using a standard PPM meter. Then, the sample PPM is measured by using the PPM sensor. The study also investigates the best regression method to map the PPM sensor measurement to the standard PPM meter measurement by comparing several line equations, such as linear, exponential, polynomial and logarithmic. The function coefficient and bias is chosen by using least square methods. After comparing, the result shows that the polynomial function provides the best reading correction with average error of 76 PPM. The error is especially few when measuring the higher PPM (more than 500 PPM), which is suitable with hydroponic cultivation. Therefore, the PPM sensor with the polynomial function shown in this study can be used to measure the dissolve nutrient accurately in the automation of hydroponic activity compare to other line equations. This study is limited to small sample sizes to prove the concept. The generalization can also be considered in the future study.
Evaluating Sampling Techniques for Healthcare Insurance Fraud Detection in Imbalanced Dataset Joanito Agili Lopo; Kristoko Dwi Hartomo
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.25929

Abstract

Detecting fraud in the healthcare insurance dataset is challenging due to severe class imbalance, where fraud cases are rare compared to non-fraud cases. Various techniques have been applied to address this problem, such as oversampling and undersampling methods. However, there is a lack of comparison and evaluation of these sampling methods. Therefore, the research contribution of this study is to conduct a comprehensive evaluation of the different sampling methods in different class distributions, utilizing multiple evaluation metrics, including , , , Precision, and Recall. In addition, a model evaluation approach be proposed to address the issue of inconsistent scores in different metrics. This study employs a real-world dataset with the XGBoost algorithm utilized alongside widely used data sampling techniques such as Random Oversampling and Undersampling, SMOTE, and Instance Hardness Threshold. Results indicate that Random Oversampling and Undersampling perform well in the 50% distribution, while SMOTE and Instance Hardness Threshold methods are more effective in the 70% distribution. Instance Hardness Threshold performs best in the 90% distribution. The 70% distribution is more robust with the SMOTE and Instance Hardness Threshold, particularly in the consistent score in different metrics, although they have longer computation times. These models consistently performed well across all evaluation metrics, indicating their ability to generalize to new unseen data in both the minority and majority classes. The study also identifies key features such as costs, diagnosis codes, type of healthcare service, gender, and severity level of diseases, which are important for accurate healthcare insurance fraud detection. These findings could be valuable for healthcare providers to make informed decisions with lower risks. A well-performing fraud detection model ensures the accurate classification of fraud and non-fraud cases. The findings also can be used by healthcare insurance providers to develop more effective fraud detection and prevention strategies.
Interactive Solar System Learning Media Using the Raspberry Pi 3B Mochamad Fajar Wicaksono; Myrna Dwi Rahmatya; Syahrul Syahrul; Sri Nurhayati
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.25948

Abstract

The current learning solar system process uses solar system props. This research aimed to create an interactive solar system learning tool for elementary school students. With this tool, students can learn about the planets in the solar system in learning mode. In addition, there is a question mode to test students' knowledge abilities. This research's contribution was to provide an engaging way for sixth-grade elementary school students to learn about and recognize the planets in the solar system. The method used in this research is the experimental method. The primary part of this system is the Raspberry Pi. In this tool, there are two modes: learning mode and question mode. The learning mode involves the input button for eclipse mode and the LDR sensor as a trigger for activating the DC motor and reading solar system material using gTTS. The question mode involves a question bank on the web application, gTTS for reading questions, and speech recognition for processing answers given by students.   The teacher can add, change, or delete questions and learning materials through the web application. The test on the learning tool is 100% successful. In learning mode, the device can read input from the LDR sensor and provide sound output, and in question mode, the device will ask questions, receive answers in voice form and then process the response based on program scenarios. On the other side, Based on UAT results from 20 sixth-grade elementary school student,  95.14% of student agreed that solar system learning media and quiz features make the learning process more engaging, easy to use, help students understand solar system material, and can be used as a learning tool.
Classification and Clustering of Internet Quota Sales Data Using C4.5 Algorithm and K-Means Eriska Vivian Astuti; Asep Afandi; Dwi Marissa Effendi
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.25970

Abstract

The number of restrictions or limits on internet use is known as internet quota. When you use internet data for a short time, you usually run out of bandwidth. In the Candimas South Abung area, many quotas have been sold in various variants. Visitors to quota outlets have access to various kinds of quota references that they can buy. Apart from guaranteeing the quality of the quotas sold, sales always increase every year, especially in the various quota variants. Based on quota data for 2019 to 2022. This study aims to analyze internet quota sales statistics in the Candimas area between 2019 and 2022. In 2021-2022 the classification produces an accuracy of up to 100% where the best-selling data dominates while clustering remains at the same figure, namely 19 data are very salable, 43 data are lacking sold, and 178 data did not sell. We use the C4.5 classification algorithm and K-Means clustering to identify patterns in the data and provide insight into which brand quotas are the most popular. Our findings can help Xena Cell counter owners make informed decisions about which quota to add or remove to optimize sales and minimize losses.
Pilates Pose Classification Using MediaPipe and Convolutional Neural Networks with Transfer Learning Kenneth Angelo Tanjaya; Mohammad Farid Naufal; Heru Arwoko
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.25975

Abstract

A sedentary lifestyle can lead to heart disease, cancer, and type 2 diabetes. An anaerobic exercise called pilates can address these problems. Although pilates training can provide health benefits, the heavy load of pilates poses may cause severe muscle injury if not done properly. Surveys have found that many teenagers are unaware of the movements in pilates poses. Therefore, a system is needed to help users classify pilates poses accurately. MediaPipe is a system that accurately extracts the real time human body skeleton. Convolutional Neural Network (CNN) with transfer learning is an accurate method for image classification. There have been several studies investigated pilates poses classification. However, there is still no research applies the MediaPipe as a skeleton feature extractor and CNN with a transfer learning to classify pilates poses. In addition, previous research still does not implement the pilates poses classification in real-time. Based on this problem, this study creates a system using MediaPipe as a feature extractor and CNN with transfer learning as a real-time pilates poses classifier. This system runs on a mobile device and gets information from a camera sensor. The results from MediaPipe then be classified by pre-trained CNN architectures with transfer learning: MobileNetV2, Xception, and ResNet50. The best model was obtained by MobileNetV2, which had an f1 score of 98%. Ten people who didn't know much about Pilates also tested the system. They all agreed that the app could accurately identify Pilates poses, make people more interested in Pilates, and help them learn more about Pilates.
On IPv6 Slow Adoption; Why We Might Approach it Wrongly? Mukhammad Andri Setiawan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 2 (2023): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i2.26058

Abstract

The slow adoption of IPv6, despite its numerous advantages over IPv4, is a pressing issue in many regions, including Indonesia. This challenge is particularly significant given the increasing demand for Internet of Things (IoT) devices and the need for a sustainable, scalable, and flexible network infrastructure. In response to this issue, our research introduces the Design Thinking-Inspired Technology Adoption (DTITA) model. This innovative approach leverages design thinking principles to facilitate the adoption of new and challenging technologies. DTITA incorporates the five stages of design thinking alongside traditional technology adoption factors, such as perceived usefulness, ease of use, and social influence. The DTITA model aims to create user-centric solutions that address new technologies' unique challenges and barriers. By placing the user at the center of the design process, we were able to develop solutions that are not only technologically advanced but also highly accessible and relevant to users. Through a survey involving individuals from the education industry, Internet Service Providers (ISPs), content providers, government institutions, and the Information and Communication Technology (ICT) industry, we identified key barriers impeding the widespread implementation of IPv6. This study provides valuable insights into the application of design thinking in the context of technology adoption, particularly in the case of IPv6. It contributes to the broader discourse on technology adoption and offers practical recommendations for stakeholders and decision-makers in Indonesia.

Page 59 of 61 | Total Record : 601

 57   58   59   60   61 

Filter by Year

2015 2026


Reset
Filter By Issues
All Issue Vol. 12 No. 1 (2026): March Vol. 11 No. 4 (2025): December Vol. 11 No. 3 (2025): September Vol. 11 No. 2 (2025): June Vol. 11 No. 1 (2025): March Vol. 10 No. 4 (2024): December Vol. 10 No. 3 (2024): September Vol. 10 No. 2 (2024): June Vol. 10 No. 1 (2024): March Vol. 9 No. 4 (2023): December Vol 9, No 4 (2023): December Vol. 9 No. 3 (2023): September Vol 9, No 3 (2023): September Vol 9, No 2 (2023): June Vol. 9 No. 2 (2023): June Vol. 9 No. 1 (2023): March Vol 9, No 1 (2023): March Vol 8, No 4 (2022): Desember Vol. 8 No. 4 (2022): Desember Vol 8, No 3 (2022): September Vol. 8 No. 3 (2022): September Vol. 8 No. 2 (2022): June Vol 8, No 2 (2022): June Vol 8, No 1 (2022): March Vol. 8 No. 1 (2022): March Vol 7, No 3 (2021): December Vol 7, No 2 (2021): August Vol 7, No 1 (2021): April Vol. 7 No. 1 (2021): April Vol 6, No 2 (2020): December Vol 6, No 1 (2020): June Vol. 6 No. 1 (2020): June Vol 5, No 2 (2019): December Vol 5, No 1 (2019): June Vol 4, No 2 (2018) Vol 4, No 2 (2018) Vol 4, No 1 (2018) Vol 4, No 1 (2018) Vol 3, No 2 (2017) Vol 3, No 2 (2017) Vol 3, No 1 (2017) Vol 3, No 1 (2017) Vol 2, No 2 (2016) Vol 2, No 2 (2016) Vol 2, No 1 (2016) Vol 2, No 1 (2016) Vol 1, No 1 (2015) Vol 1, No 1 (2015) More Issue