Claim Missing Document
Check
Articles

Found 4 Documents
Search

Analysis of the Impact of Interview-Based Feature Selection on the Performance of Machine Learning Algorithms in Mental Health Disorder Classification Hendrick
Jurnal Komputer, Informasi dan Teknologi Vol. 4 No. 2 (2024): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v4i2.2039

Abstract

Mental health issues in the workplace have become an increasingly important concern, particularly in the high-pressure environment of the information technology industry. This study aims to evaluate the impact of feature selection based on interviews on the performance of machine learning models in classifying mental health disorders. The dataset used is sourced from Open Sourcing Mental Illness (OSMI), which consists of various features related to employees' mental health conditions, previously used without feature selection in prior research. Through an interview with an experienced Human Capital professional with a psychological background, relevant features were selected based on domain expertise. Subsequently, machine learning models, namely Random Forest and XGBoost, were trained using two scenarios: without feature selection and with feature selection. The results of the study indicate that feature selection based on interviews can improve model accuracy by 1.67% for Random Forest and 0.67% for XGBoost. These findings emphasize the importance of integrating psychological insights into the data processing to produce more relevant and efficient models. This research provides practical contributions to assist companies in implementing early detection of mental health disorders effectively.
A Study on Dengue Cases Detection based on Lazy Classifier Roslan, Nur Amiratun Nazihah; Mahdin, Hairulnizam; Hidayat, Rahmat; Hendrick
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 1 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (219.454 KB) | DOI: 10.62527/ijasce.1.1.10

Abstract

With the rise of social networking approach, there has been a surge of users generated content all over the world and with that in an era where technology advancement are up to the level where it could put us in a step ahead of pathogens and germination of diseases, we couldn’t help but to take advantage of that advancement and provide an early precaution measures to overcome it. Twitter on the other hand are one of the social media platform that provides access to a huge data availability. To manipulate those data and transform it into an important information that could be used in many different scopes that could help improve people’s lives for the better. In this paper, we gather a total of six algorithms from Lazy Classifier to compare between them on which algorithm suited the most with the diabetes dataset. This research are using WEKA as the data mining tool for data analyzation 
Analysis of Eye Disease Classification by Comparison of the Random Forest Method and K-Nearest Neighbor Method Meidelfi, Dwiny; Hendrick; Sukma, Fanni; Kharisma, Srintika Yunni
International Journal of Advanced Science Computing and Engineering Vol. 5 No. 2 (2023)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.5.2.151

Abstract

Eye disease is a serious issue all over the world, and image-based classification systems play an important role in the early detection and management of eye disease. This research compares the performance between Random Forest (RF) and K-Nearest Neighbor (KNN) classification models in identifying eye disorders using image datasets divided into four classes: "normal," "glaucoma," "cataract," and "diabetic retinopathy."   The dataset is converted into a feature vector and then divided into training data and test data subsets. The analysis results show that the RF model achieved an accuracy level of 80%, whereas the KNN model achieved 70%. Based on these findings, it is possible to conclude that the RF model outperforms the other models in categorizing the types of eye illnesses in the dataset. A Python-based website was also built utilizing the Flask framework to build an interactive and real-time eye illness diagnosis system. Users can upload photos of their retinas to this website and quickly receive eye disease detection results. The adoption of this technology has a tremendous impact, making eye disease detection solutions more accessible. Furthermore, this solution plays an important role in the early detection and effective management of eye health cases.
Implementation of Convolutional Neural Network and Vincenty Formula on Face Attendance System Web-Based for Managing the Attendance Meidelfi, Dwiny; Hendrick; Yulherniwati; Novi; Zulfitri, Alvin Faiz
International Journal of Advanced Science Computing and Engineering Vol. 5 No. 3 (2023)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.5.3.181

Abstract

The level of student attendance at tertiary institutions has a crucial role in determining the quality of education. The Information Technology Department at Padang State Polytechnic realizes the urgent need to increase the efficiency of managing student attendance, which currently still relies on a manual attendance system. As an innovative solution, this research proposes designing a face-based attendance system that utilizes facial recognition technology to verify student attendance automatically. One of the challenges in developing a face-based attendance system is the accuracy of calculating the distance between the student's location and the institutional location. To overcome this problem, the research used the Vincenty Formula method which was proven to have a high level of accuracy in calculating the distance between two points on the earth. The integration of this method is expected to increase the accuracy of calculating the distance between the student's location and the institution. Apart from that, this attendance system adopts the Convolutional Neural Network (CNN) algorithm, an algorithm specifically designed to process two-dimensional data. CNN is used to learn and detect features in images so that facial recognition can be done with a high level of accuracy. This approach is expected to improve system performance in recognizing and verifying student attendance.