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
sji@mail.unnes.ac.id
Editorial Address
-
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
Published by Universitas Negeri Semarang
ISSN : 24077658     EISSN : 24600040     DOI : -
Core Subject : Science,
Computer Science & IT
Scientific Journal of Informatics published by the Department of Computer Science, Semarang State University, a scientific journal of Information Systems and Information Technology which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences.
Arjuna Subject : -
Articles 564 Documents
 53   54   55   56   57 
A Comparative Study of Random Forest and Double Random Forest Models from View Points of Their Interpretability Khairunnisa, Adlina; Notodiputro, Khairil Anwar; Sartono, Bagus
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.48721

Abstract

Purpose: This study aims to compare the performance of ensemble trees such as Random Forest (RF) and Double Random Forest (DRF) from view points of interpretability of the models. Both models have strong predictive performance but the inner working of the models is not human understandable. Model interpretability is required to explain the relationship between the predictors and the response. We apply association rules to simplify the essence of the models.Methods: This study compares interpretability of RF and DRF using association rules. Each decision tree formed from each model is converted into if-then rules by following the path from root node to leaf nodes. The data was selected in such a way that they were underfit data. This is due to the fact that DRF has been shown by other researchers to overcome the underfitting problem faced by RF. A Simulation study has been conducted to evaluate the extracted rules from RF and DRF. The rules extracted from both models are compared in terms of model interpretability based on support and confidence values. Association rules may also be applied to identify the characteristics of poor people who are working in Yogyakarta.Result: The simulation results revealed that the interpretability of DRF outperformed RF especially in the case of modelling underfit data.  On the other hand, using empirical data we have been able to characterize the profile of poor people who are working in Yogyakarta based on the most frequent rules.Novelty: Research on interpretable DRF is still rare, especially the interpretation model using association rules. Previous studies focused only on interpreting the random forest model using association rules. In this study, the rules extracted from the random forest and double random forest models are compared based on the quality of the rules extracted.
Community Satisfaction with Online Services in East Lombok Regency: (Case Study: BAKSO Application) Ahdarrijal, Yujitia; Pribadi, Ulung
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.48083

Abstract

Purpose: This study analyzes the use of the BAKSO (Create Online Population Administration) application for users, namely employees of the East Lombok Regency Population and Civil Registration Office and the Admin of each village. The measurement uses variables consisting of infrastructure, ICT, bureaucracy, leadership, and implementation of digital government.Methods: The method used is a quantitative type, primary data in the form of a survey of 115 respondents from East Lombok Regency Population and Civil Registration Office office employees and village admins who used the BAKSO application (Create Online Population Administration). Using the Likert Scale (1: strongly disagree, 2: disagree, 3: neutral, 4: agree, and 5: strongly agree). The analysis technique for this study uses SmartPLS 3.Results: The results of this study show that infrastructure and ICT variables have a positive and significant influence on the implementation of digital government in the implementation of the BAKSO application. Meanwhile, bureaucratic and leadership variables have little impact and are substantial in implementing the BAKSO application in East Lombok Regency.Novelty: This study is unique because it examines users who are also employees who use the BAKSO application (Make Online Population Administration) with a measuring indicator, namely the online service index (OSI); most of the previous research on this theory was only oriented to assessing public satisfaction with online services. This research provides a new perspective on using the Online Service Index (OSI) on the scope of application-based online services from an employee perspective. In addition, the empirical contribution lies in the professionalism of employees in using the BAKSO application. So that later, it can provide space for the government to pay attention to human resources in running Online Service Index (OSI)-based application services.
Forensic Analysis of Drones Attacker Detection Using Deep Learning Editya, Arda Surya; Kurniati, Neny; Alamin, Mochammad Machlul; Pramana, Anggay Luri; Lisdiyanto, Angga
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.48183

Abstract

Purpose: This research proposes deep learning techniques to assist forensic analysis in drone accident cases. This process is focused on detecting attacking drones. In this research, we also compare several deep learning and make some comparisons of the best methods for detecting drone attackers.Methods: The methods applied in this research are YOLO, SSD, and Fast R-CNN. Additionally, to validate the effectiveness of the results, extensive experiments were conducted on the dataset. The dataset we use contains videos taken from drones, especially drone collisions. Evaluation metrics such as Precision, Recall, F1-Score, and mAP are used to assess the system's performance in detecting and classifying drone attackers.Results: This research show performance results in detecting and attributing drone-based threats accurately. In this experiment, it was found that YOLOV5 had superior results compared to YOLOV3 YOLOV4, SSD300, and Fast R-CNN. In this experiment we also detected ten types of objects with an average accuracy value of more than 0.5.Novelty: The proposed system contributes to improving security measures against drone-related incidents, serving as a valuable tool for law enforcement agencies, critical infrastructure protection and public safety. Furthermore, this underscores the growing importance of deep learning in addressing security challenges arising from the widespread use of drones in both civil and commercial contexts. 
Knowledge Discovery from Confusion Matrix of Pruned CART in Imbalanced Microarray Data Ovarian Cancer Classification Sapitri, Ni Kadek Emik; Sa’adah, Umu; Shofianah, Nur
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.50077

Abstract

Purpose: The results of microarray data analysis is important in cancer diagnosis, especially in early stages asymptomatic cancers like ovarian cancer. One of the challenges in analyzing microarray data is the problem of imbalanced data. Unfortunately, research that carries out cancer classification from microarray data often ignores this challenge, so that it doesn’t use appropriate evaluation metrics. It makes the results biased towards the majority class. This study uses a popular evaluation metric “accuracy” and an evaluation metric that is suitable for imbalanced data “balanced accuracy (BA)” to gain information from the confusion matrix regarding accuracy and BA values in case of ovarian cancer classification.Methods: This study use Classification and Regression Tree (CART) as the classifier. CART optimized by pruning. CART optimal is determined from the results of CART complexity analysis and confusion matrix.Results: The confusion matrix and CART interpretations in this research show that CART with low complexity is still able to predict majority class respondents well. However, when none of the data in the minority class was classified correctly, the accuracy value was still quite high, namely 86.97% and 88.03% respectively at the training and testing stages, while the BA value at both stages was only 50%.Novelty: It is very important to ensure that the evaluation metrics used match the characteristics of the data being processed. This research illustrate the difference between accuracy and BA. It concluded that that classification of an imbalanced dataset without doing resampling can use BA as evaluation metric, because based on the results, BA is more fairly to both classes.
The Comparison of K-Nearest Neighbors and Random Forest Algorithm to Recognize Indonesian Sign Language in a Real-Time Goenawan, Aaqila Dhiyaanisafa; Hartati, Sri
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.48475

Abstract

Purpose: Comparing 2 models or prototype programs which can recognize Indonesian Sign Language System or Sistem Isyarat Bahasa Indonesia (SIBI) fonts from hand gesture and translate it’s into writing Messages in real-time.Methods: After selecting datasets and reprocessed by the researcher into 1 dataset, which are a combination of several sign image datasets of the SIBI letters images available on the Kaggle website, the dataset is converted into landmarks. The landmarks are divided into 26 sign classes and preprocessed to a total of 19,826 rows of data, and then divided into 67% training data and 33% test data. Next, both K-NN and Random Forest algorithm are implemented into different program and get tested into 2 different tests, model evaluation and real-time. At the end, the result is compared to see the increase of accuracy level of both K-Nearest Neighbors (K-NN) and Random Forest algorithm.Result: The constructed and trained model is then evaluated and the results of Precision, Recall, Accuracy, and F1-Score are 99.88% using the Random Forest algorithm. The results of real-time program testing with the K-Nearest Neighbors algorithm get higher results, where the average accuracy value reaches 99%.Novelty: From the result shows that the model built with the Random Forest algorithm is superior, but the K-Nearest Neighbors algorithm is better in real-time testing. Therefore, image data and its diversity should be increased, in order to improve recognition accuracy. The program could be enhanced by adding a function where the program can recognize hand gesture, not only one or two hands but also can recognize a hand gesture with movements so the program can recognize static and dynamic letter (required hands movement).
Design of an Arduino Mega-Based Walking Cane Assistive Device to Improve the Quality of Life for the Elderly in the Riau Islands Province Dimas Akmarul Putera; Aulia Agung Dermawan; Dwi Ely Kurniawan; Alvendo Wahyu Aranski; Rafi Dio
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47793

Abstract

Purpose: The number of people aged 60 or older is expected to increase globally by nearly three times from 737 million in 2009 to 2 million by 2050. Indonesia's population is projected to reach 28 million by 2045, making up nearly one-third of the total population. In 2020, the population aged 60 or older reached 29.52 million, with 29.52 million from the last two houses being occupied by a house due to numerous housing programs that require a close relationship between people. The study suggests that a house with a strong sense of belonging is a risky group required attention. The study uses a smartphone with a 180° panorama camera and GPS to help locating the house and performing its activities.Methods: Anthropometry can be defined as the study of body dimensions, namely body size, shape, strength and work capacity for the purpose of body design and composition and prototyping. Results: This research has resulted in elderly sticks that use sensors to help elderly mobility. This stick can detect the environment nearby the ESP32-Cam with the password "/Capture_photo" and is able to send information about the location of the elderly by sending a message to the GSM Number connected to the Arduino Mega with the password "Hello" and the device will send a message containing the location of the elderly.Novelty: Based on previous research reviewed by researchers, it was found that similar research using Camera and GPS Technology to Improve the Quality of Life of the Elderly has not been carried out in the Riau Islands of Batam.
JSON and MySQL Databases for Spatial Visualization of Polygon and Multipolygon Data in Geographic Information Systems: A Comparative Study M. Zakki Abdillah; Devi Astri Nawangnugraeni; Solikhin Solikhin; Toni Wijanarko Adi Putra
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47393

Abstract

Purpose: Spatial data is used to display digital maps. Geographic information systems' access performance depends on spatial data formats. This study compared JSON and MySQL database data display speeds. Open-source RDBMSs work with various programming languages. JSON displays data in text format. The purpose of this study is to select spatial data for polygon and multipolygon Geographic Information Systems (GIS).Design of study: access speed to the GIS determined the method. This study evaluated how effectively JSON and MySQL displayed digital maps in GIS using two types of geographical data. JSON was in the server directory, and MySQL was on the database server. To measure performance, these two spatial data sets were compared using the same server parameters. Testers employed various tools, operating systems, devices, and browsers.Result: JSON data is stored on a live server and is easier to access while having more data. This test compares file size and speed on three online devices. This test generates JSON as the fastest geographic data, with an average access time of 3.9 seconds and 8.5 MB loaded. MySQL, which averages 9.7 seconds, loads 6.3 MB of files. Despite its larger file size, JSON is faster for spatial data, according to tests.Originality: Its comparison of JSON and MySQL databases based on its application for geographical data display in GIS is unique. This test offers geographic data in JSON faster than MYSQL. JSON can be used to choose location data that GIS can readily access. 
Exploring Long Short-Term Memory and Gated Recurrent Unit Networks for Emotion Classification from Electroencephalography Signals Dian Palupi Rini; Winda Kurnia Sari; Novi Yusliani; Deris Stiawan; Aspirani Utari
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47734

Abstract

This study delves into comparing LSTM and GRU, two recurrent neural network (RNN) models, for classifying emotion data through electroencephalography (EEG) signals. Both models adeptly handle sequential data challenges, showcasing their unique strengths. In EEG emotion dataset experiments, LSTM demonstrated superior performance in emotion classification compared to GRU, despite GRU’s quicker training processes. Evaluation metrics encompassing accuracy, recall, F1-score, and area under the curve (AUC) underscored LSTM’s dominance, which was particularly evident in the ROC curve analysis. This research sheds light on the nuanced capabilities of these RNN models, offering valuable insights into their efficacy in emotion classification tasks based on EEG data. The study explores parameters, such as the number of layers, neurons, and the utilization of dropout, providing a detailed analysis of their impact on emotion recognition accuracy.Purpose: The proposed model in this study is the result of optimizing LSTM and GRU networks through careful parameter tuning to find the best model for classifying EEG emotion data. The experimental results indicate that the LSTM model can achieve an accuracy level of up to 100%.Methods: To improve the accuracy of the LSTM and GRU methods in this research, hyperparameter tuning techniques were applied, such as adding layers, dense layers, flattening layers, selecting the number of neurons, and introducing dropout to mitigate the risk of overfitting. The goal was to find the best model for both methods.Results: The proposed model in this study is capable of classifying EEG emotion data very effectively. The experimental results demonstrate that the LSTM model achieves a maximum accuracy of 100%, while the GRU model achieves a highest accuracy of approximately 98%.Novelty: The novelty of this research lies in the optimization of hyperparameters for both LSTM and GRU methods, leading to the development of novel architectures capable of effectively classifying EEG emotion data.
Optimized Handwriting-based Parkinson's Disease Classification Using Ensemble Modeling and VGG19 Feature Extraction Jumanto Unjung; Maylinna Rahayu Ningsih
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47108

Abstract

Purpose: Parkinson's is a neurological disorder that causes muscles to weaken and arms and legs to tremor over time. The discovery and identification of the stages of Parkinson's disease can substantially benefit the treatment of its symptoms. Many studies have been conducted in classifying hand-drawn -based Parkinson's disease but the resulting performance is still not optimal. The purpose of this research is to improve the performance of handwritten Parkinson's disease classification accuracy using an ensemble soft voting model.Methods: The model adopted the Parkinson's Disease Augmented Data of Handwritten dataset taken from the Kaggle Repository, where the dataset contains Healthy and Parkinson's classes with a total of 3264 images. Then, the dataset was augmented again, resulting in 2612 images in the training data and 652 images in the validation data. After that, the dataset was optimized with VGG19 feature extraction and fine-tuning and then modeled with the Ensemble Learning model. The model was evaluated with a confusion matrix, and the classification report was viewed.Result: The results of the proposed evaluation test discovered the effectiveness of the Ensemble Learning model with Fine Tuning VGG19 feature extraction by producing an accuracy of 98.9%.Novelty: This research has successfully contributed to the proposed ensemble model for Parkinson's handwriting and improved the accuracy performance of the model.
Plasmodium falciparum Identification Using Otsu Thresholding Segmentation Method Based on Microscopic Blood Image Nurul Huda; Alfa Yuliana Dewi; Adiyah Mahiruna
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47924

Abstract

Purpose: Malaria, particularly the Falciparum strain, is a deadly disease caused by Plasmodium falciparum. Malaria diagnosis heavily relies on a microscopist's expertise. To expedite identification, machine learning research has been extensively conducted. However, it has not yet achieved high accuracy, partly due to the use of microscopic images as the dataset. Otsu thresholding, an optimal image segmentation method, maximizes pixel variance to separate the foreground (objects of interest) from the background, which is especially effective in various lighting conditions. Otsu thresholding aims to enhance accuracy and reliability in detecting and classifying Plasmodium falciparum parasites in blood samples.Methods: Dataset of microscopic images of thin blood smears with Plasmodium falciparum, taken from several sources, such as the UC Irvine Machine Learning Repository (UCI), National Institutes of Health (NIH), Kaggle, and Public Health Image Library (PHIL). The methodology combines various image processing techniques, including illumination correction, contrast enhancement, and noise filtering, to prepare the images effectively. The subsequent segmentation using Otsu thresholding method isolates the parasite regions of interest. The classification process involving CNN and SVM evaluates the performance of accuracy to identify different stages of Plasmodium falciparum parasites.Results: The research found the effectiveness of the Otsu thresholding segmentation method in identifying Plasmodium falciparum parasites in microscopic images. By utilizing Convolutional Neural Network (CNN) and Support Vector Machine (SVM) classifiers, the study achieved impressive accuracy rates, with the CNN achieving 96.5% accuracy and the SVM achieving 95.7%.Novelty: This research recorded significant improvement over previous studies that utilized feature extraction and selection methods. At the same time, previous research achieved an accuracy of 82.67. The key innovation here is the adoption of the Otsu thresholding segmentation method, which enhances the identification of Plasmodium falciparum parasites in microscopic images by integrating traditional image processing techniques like Otsu thresholding with modern machine learning methods like CNN and SVM. This significant improvement suggests that the proposed approach offers a more robust and reliable solution for malaria diagnosis.

Page 55 of 57 | Total Record : 564

 53   54   55   56   57 

Filter by Year

2014 2024


Reset
Filter By Issues
All Issue Vol 11, No 1 (2024): February 2024 Vol 10, No 4 (2023): November 2023 Vol 10, No 3 (2023): August 2023 Vol 10, No 2 (2023): May 2023 Vol 10, No 1 (2023): February 2023 Vol 9, No 2 (2022): November 2022 Vol 9, No 1 (2022): May 2022 Vol 8, No 2 (2021): November 2021 Vol 8, No 1 (2021): May 2021 Vol 7, No 2 (2020): November 2020 Vol 7, No 1 (2020): May 2020 Vol 6, No 2 (2019): November 2019 Vol 6, No 1 (2019): Mei 2019 Vol 6, No 1 (2019): May 2019 Vol 5, No 2 (2018): November 2018 Vol 5, No 2 (2018): November 2018 Vol 5, No 1 (2018): May 2018 Vol 5, No 1 (2018): May 2018 Vol 4, No 2 (2017): November 2017 Vol 4, No 2 (2017): November 2017 Vol 4, No 1 (2017): May 2017 Vol 4, No 1 (2017): May 2017 Vol 3, No 2 (2016): November 2016 Vol 3, No 2 (2016): November 2016 Vol 3, No 1 (2016): May 2016 Vol 3, No 1 (2016): May 2016 Vol 2, No 2 (2015): November 2015 Vol 2, No 2 (2015): November 2015 Vol 2, No 1 (2015): May 2015 Vol 2, No 1 (2015): May 2015 Vol 1, No 2 (2014): November 2014 Vol 1, No 2 (2014): November 2014 Vol 1, No 1 (2014): May 2014 Vol 1, No 1 (2014): May 2014 More Issue