cover
Contact Name
Dewa Made Sri Arsa
Contact Email
dewamsa@unud.ac.id
Phone
-
Journal Mail Official
lontarkomputer@unud.ac.id
Editorial Address
Research institutions and Community Service, University of Udayana, Kampus Bukit Jimbaran Bali
Location
Kota denpasar,
Bali
INDONESIA
Lontar Komputer: Jurnal Ilmiah Teknologi Informasi
Published by Universitas Udayana
ISSN : 20881541     EISSN : 25415832     DOI : 10.24843/LKJITI
Lontar Komputer: Jurnal Ilmiah Teknologi Informasi focuses on the theory, practice, and methodology of all aspects of technology in the field of computer science and engineering. It provides an international publication platform to boost the scientific and academic publication of research in the field. Submissions are invited concerning any theoretical or practical implementation of algorithm design, methods, and development. The subject of articles contributed may cover, but is not limited to: Data Analysis Natural Language Processing Artificial Intelligence Neural Networks Pattern Recognition Internet of Things (IoT) Remote Sensing Image Processing Fuzzy Logic Genetic Algorithm Bioinformatics/Biomedical Applications Biometrical Application Computer Network and Architecture Network Security Content-Based Multimedia Retrievals Information System
Articles 36 Documents
Evaluation of the performance of the Smote, Smote Enn, and Borderline Smote resampling methods based on the number of outlier data with Z Score arisgunadi gunadi; Dewi Oktofa Rahmawati; Nurfa Risha
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p05

Abstract

Handling class imbalances in datasets is a significant challenge in the classification process. Disruption occurs if the minority class has a crucial role in decision-making. Oversampling is one of the solutions that is widely used to overcome this problem. This study compares the performance of three popular oversampling methods, namely SMOTE (Synthetic Minority Oversampling Technique), SMOTE-ENN (SMOTE with Edited Nearest Neighbor), and Borderline-SMOTE, based on the number of outlier data produced. Outlier data is measured using a Z-score-based statistical approach. The research was conducted by applying the three oversampling methods on several datasets. Evaluation is carried out by counting the number of outlier data after the resample process, as well as by evaluating their impact on the performance of the classification model using metrics such as accuracy, precision, recall, and F1-score. The research results show that there is no significant difference in the number of outlier data in SMOTE, ENN SMOTE, or borderline SMOTE. In the diabetes.csv dataset, it was found that the percentage of outlier data in the initial condition and the condition after resampling with SMOTE, resampling with SMOTE ENN, and borderline SMOTE were 7.4%, 6.8%, 6.7%, and 63%, respectively. For the predict_ honor.csv dataset, the data are 7.1%, 7.3%, 7.6%, and 7%. For the winequality.csv dataset, the data are 8%, 7.8%, 6.8%, and 5.8%. Meanwhile, smoking.csv data found 7.1%, 7.3%, 7.6%, and 7.0%. However, if we look at each feature in each dataset, more varied conditions are found regarding the performance of the three algorithms, which is related to the number of outlier data produced. In terms of differences, no significant differences were found in the number of outlier data produced. The second finding is related to the performance of the decision tree classification model. It can be stated that the influence of feature correlation is more important than perfect data balance in the dataset.
Extensive Deep Learning Models Evaluation For Indonesian Sign Language Recognition Audrey Tilanov Pramasa; Ni Putu Sutramiani; I Putu Agung Bayupati; I Wayan Agus Surya Darma
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p04

Abstract

Sign language is a vital communication method for individuals with hearing loss or deafness, with variations reflecting unique cultural contexts. Real-time recognition of sign language can bridge communication gaps, yet­­ developing tools for Indonesian Sign Language (BISINDO) is challenging due to limited datasets. This research addresses these challenges by enhancing BISINDO detection and real-time rec­­ognition, focusing on flexible dataset collection and adaptation to varying lighting conditions. Three convolutional neural networks—InceptionV3, MobileNetV2, and ResNet50—are evaluated with optimizers SGD, Adagrad, and Adam to determine the best architecture-optimizer combination. Models were trained on a common dataset and analyzed for optimal performance. Real-time recognition uses MobileNetV2 SSD, integrating data augmentation to improve performance under diverse lighting. The system was deployed on a mobile device for practical use. Results showed the real-time model attained a mean Average Precision (mAP) of 90.34%. This study demonstrates significant advancements in BISINDO recognition and real-time application
Classification of Acne Severity Using K-Nearest Neighbor (KNN) and Random Forest Method Gloria Flourin Maitimu; Putu Harry Gunawan; Muhammad Ilyas
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p06

Abstract

The development of machine learning technology, especially in dermatology, offers excellent opportunities for classifying and diagnosing skin conditions such as acne. This study aims to apply and compare two machine learning methods, K-Nearest Neighbors (KNN) and Random Forest methods, to classify acne severity into three levels: mild, moderate, and severe. The acne density and average confidence features were extracted from facial images using the YOLOv8 model based on acne bounding boxes. While the KNN model achieves 95% accuracy, the Random Forest model reaches 97%, indicating superior performance with excellent precision, recall, and F1-score values. With its level of accuracy, the integration of the Random Forest model and the features extracted using the YOLOv8 model appear to be a promising tool in dermatology for classifying acne severity in a more accurate and effective way.
Breaking Class Imbalance: Machine Learning Solutions for Stunting Detection Hasna Aqila Raihana; Putu Harry Gunawan; Narita Aquarini
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p03

Abstract

Stunting is a critical public health issue primarily caused by malnutrition, which hampers the growth of children. This study evaluates the performance of two machine learning models, K-Nearest Neighbors (KNN) and Decision Tree, in classifying stunting status in toddlers. Three strategies for handling class imbalance—no sampling, Synthetic Minority Over-sampling Technique (SMOTE), and random undersampling-are compared to enhance the detection of the minority class (stunting). The results show that KNN with SMOTE achieved the best performance, with an accuracy of 99.17% and an F1-Score of 99.17%, highlighting the model’s effectiveness in balancing sensitivity to the minority class. In contrast, although Decision Tree achieved an accuracy of 99.11% without sampling technique, it faced challenges in detecting stunting, which were addressed with the use of SMOTE, improving its accuracy to 97.41%. The application of random undersampling caused a significant decline in performance for both models. These findings underscore the effectiveness of SMOTE in handling class imbalance for stunting detection and provide valuable insights into the application of machine learning techniques in addressing public health issues.
Determining Tuna Grade Quality Based on Color Using Convolutional Neural Network and k-Nearest Neighbors I Gede Sujana Eka Putra; Ahmad Catur Widyatmoko; I Ketut Gede Darma Putra; Made Sudarma; A. A. K. Oka Sudana
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p02

Abstract

One of the main commodities that Indonesia exports is tuna. Indonesia's inadequate handling of food safety is demonstrated by a number of instances when the United States has rejected Indonesian fishery goods and food poisoning incidences. Fish quality grade is currently determined by manual inspection which has risk human mistake. According to Robert DiGregorio, four tuna grade classifications exist: grade 1, 2+, 2, and 3. The purpose of this study is to assess the tuna meat's quality according to its color. The procedure involves pre-processing images, training datasets, and classifying them using the Convolutional Neural Network (CNN) and k-Nearest Neighbors algorithms. CNN pre-processing involves converting the image into HSV color space and training the CNN model using 240 training datasets and 74 testing datasets. CNN’s accuracy was 84% higher than k-Nearest Neighbors' which was 54%. Additionally, a comparison of the classification accuracy of CNN, VGG (Visual Geometry Group) 16, and AlexNet revealed that CNN outperformed the others with an accuracy of 84%, followed by VGG16 with 70% and AlexNet with 66%.
Strategizing Economic Revival in Mandalika through A One-Stop Digital Collaborative Marketing Platform Upholding Local Wisdom Ario Yudo; Nadiyasari Agitha; Fitri Bimantoro; Nuraqilla Waidha Bintang Grendis
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p01

Abstract

In the era of digital transformation, information technology plays a pivotal role in shaping economic landscapes and cultural preservation strategies. This research introduces an innovative approach to economic revitalization in Mandalika, Indonesia, through a One-Stop Digital Collaborative Marketing Platform, fully integrated with the NTBmall app, a key digital initiative by Dinas Perdagangan NTB for promoting local products. This symbiotic blend of cutting-edge digital solutions and Mandalika's rich local wisdom forms the core of our strategy, aiming to rejuvenate the region's economic vitality while safeguarding its cultural heritage. Utilizing the System Usability Scale (SUS) for evaluation, the study involved 23 street vendors and 7 Tourism Awareness Group (Pokdarwis: Kelompok Sadar Wisata). The results were compelling: street vendors recorded a usability score of 72.8, indicating good system functionality, while Pokdarwis achieved an outstanding score of 85, reflecting excellent usability. These outcomes highlight the platform's versatility in meeting diverse user needs and its significant potential in boosting Mandalika's economy. By merging innovative IT solutions with traditional values, this research not only propels economic growth in Mandalika but also sets a scalable and replicable model for similar developments globally, showcasing the transformative power of information technology in regional development.
Multi Classification of Strawberry Leaves Using Support Vector Machine (SVM) Method on Smart Greenhouse Plants Based on Internet Of Things (IoT) osphanie mentari; Agung Surya Wibowo; Muhammad Zimamul Adli; Agung Muhamad Toha
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 02 (2025): Vol.16, No. 02 August 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i02.p07

Abstract

Strawberry plants, or Fragaria x ananassa, are shrubs in the Rosaceae (rose) family that produce sweet and scented red fruit. Strawberries are high in vitamin C and other minerals. The benefits of growing strawberries in smart greenhouses are one of the hydroponic farming sectors advances. The construction of a smart greenhouse system that can be monitored and controlled automatically simplifies agricultural research, which formerly relied on traditional farming and wet labs with long study timeframes and high expenses. This innovation makes it easier for researchers to study the impact of the Internet of Things (IoT) on strawberry plant growth by using several sensors in the greenhouse and Artificial Intelligence (AI) to save time and money in optimizing strawberry plant growth. Meanwhile, the Support Vector Machine (SVM) algorithm with a multi-classification category on leaves 3, 4, and 5 achieved Precision: 0.96, Recall: 0.95, F1-Score: 0.95, and Accuracy: 0.95. The accuracy level reaches 95%, implying that machine learning can be used in strawberry cultivation to assist hydroponic farmers.
The Influence Of Applying Stopword Removal And Smote On Indonesian Sentiment Classification Arif Bijaksana Putra Negara
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 14 No. 03 (2023): Vol. 14, No. 03 December 2023
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2023.v14.i03.p05

Abstract

Information, like public opinions or responses, can be obtained through Twitter tweets. These opinions can expressed as a sentiment. Sentiments can be positive, neutral, or negative. Sentiment analysis (opinion mining) on a text can performed through text classification. This research aims to determine the influence of implementing Stopword Removal and SMOTE on the sentiment classification model for Indonesian tweets. The algorithms used in this research are Logistic Regression and Random Forest. Based on the evaluation, the best classification model in this research was achieved by implementing the Random Forest algorithm along with SMOTE, with an f1-score value of 75.03%. Meanwhile, implementing the Random Forest algorithm and Stopword Removal achieved the worst classification model, with an f1-score value of 68.09%. Implementing Stopword Removal in both algorithms has a negative impact in the form of a decrease in the resulting f1-score. Meanwhile, the performance of SMOTE provides a positive impact in the form of an increase in the resulting f1-score. This happened since Stopword Removal could reduce information and alter the meaning of processed tweets, causing the tweet to lose its sentiment.
Implementation of Random Forest Method with Information Gain Selection and Hyperparameter Tuning for Alzheimer’s Disease Classification Riska Nuril Fadhila; Nurissaidah Ulinnuha; Dian Yuliati
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 01 (2025): Vol.16, No. 01 April 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i01.p01

Abstract

Alzheimer's disease is one of the leading causes of decreased quality of life in the elderly aged 65 years and above. One of the problems facing Alzheimer's cases is the difficulty of making an early diagnosis to prevent disease progression, as early symptoms are often mistaken for senile dementia. Using the Random Forest method with information gain feature selection and hyperparameter tuning optimization, this study aims to determine the results of optimization with feature selection and hyperparameter tuning using Random Search and Grid Search to classify Alzheimer's medical record data consisting of 32 variables, including lifestyle factors, clinical measurements, cognitive and functional assessments, as well as symptoms that indicate Alzheimer's. The results showed that applying Information Gain and parameter optimization with the Grid Search method achieved the highest accuracy among all tested experiments. Random Forest with Information Gain and Grid Search gave an accuracy of 95.57%, sensitivity of 92.93%, and specificity of 96.99%, which showed better performance than the Random Search method. This indicates that parameter optimization has a vital role in improving model performance. This research contributes to assisting paramedics in determining whether a patient has Alzheimer's disease based on the characteristics derived from the data.
Modification of the LSTM Model in Time Series Data Prediction Daniel Robi Sanjaya; Bayu Surarso; Tarno
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 16 No. 01 (2025): Vol.16, No. 01 April 2025
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2025.v16.i01.p02

Abstract

Accurate stock price forecasting is crucial in supporting investment decision-making, especially during stock price fluctuations. This research aims to improve the accuracy of stock price prediction on time series data through modification of the Long Short-Term Memory (LSTM) model. The modification is done by simplifying the hyperparameters, adding dense layers, and applying the Adam optimizer. In addition, this research also aims to compare the prediction error rate of the LSTM model with several other methods using the Mean Absolute Percentage Error (MAPE) metric. The results show that the modified LSTM model produces lower MAPE on different stock data, namely 3.51% (train) and 1.65% (test) for ANTM.JK, 2.24% (train) and 1.69% (test) for BBRI.JK, 2.17% (train) and 1.52% (test) for BBCA.JK, and 3.06% (train) and 1.43% (test) for BBNI.JK. This model outperforms the LSTM method before modification and other methods such as RNN, CNN, SES, WMA, and Facebook Prophet. This finding shows that LSTM modification significantly improves the accuracy of stock price prediction.

Page 1 of 4 | Total Record : 36