Garuda - Garba Rujukan Digital

A Klasifikasi Penyakit Tumor Ginjal Menggunakan SVM dengan Ekstraksi Ciri HOG dan GLCM Affandy, Muhammad Eric; Mohamad Sofie; Muhammad Rofi’i
The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i3.4882

Early detection of kidney tumors is essential to increase the chances of a patient's recovery. This study aims to develop a classification system for kidney CT scan images to distinguish between normal kidneys and kidneys containing tumors. The classification method used is Support Vector Machine (SVM) with three types of kernels, namely linear, polynomial, and radial basis function (RBF). Previously, feature extraction was performed using two approaches, namely Histogram of Oriented Gradients (HOG) to obtain shape values, and Gray Level Co-occurrence Matrix (GLCM) to obtain texture characteristics of the image. The test results show that SVM with a linear kernel gives the highest accuracy of 90%, followed by polynomial at 85%, while the RBF kernel only reaches 50%. Based on these results, it can be concluded that the combination of HOG and GLCM feature extraction followed by classification using linear kernel SVM is effective for distinguishing normal kidney images and kidney tumors. This research makes a positive contribution to the development of a medical image-based kidney disease diagnosis support system.

Analisis Statistika Multivariat untuk Menilai Keterkaitan Gaya Hidup Digital dengan Tingkat Stres Mahasiswa Rusliadi Rusliadi; Mohamad Sofie
Jurnal Pengabdian Dian Mandala Vol. 3 No. 1 (2025): June : Jurnal Pengabdian Dian Mandala
Publisher : STP Dian Mandala Gunungsitoli Nias Keuskupan Sibolga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62200/jpdm.v3i1.226

Digital lifestyle has become an integral part of university students' daily lives, involving the use of social media, digital devices, and digital content consumption. The development of digital technology has positive impacts, facilitating easy access to information and social interactions. However, excessive use can lead to digital stress, which negatively affects students' mental health. This study aims to identify the key factors influencing students' digital lifestyles and analyze their relationship with stress levels. A quantitative approach with a survey method was employed, using a questionnaire to measure digital lifestyle, including social media usage frequency and digital device interaction duration, along with the Perceived Stress Scale (PSS) to measure students' stress levels. The factor analysis results show that social media usage and prolonged interaction with digital devices are significant factors contributing to students' stress. Furthermore, sleep disturbances and social anxiety were identified as other significant factors associated with increased stress. The multivariate regression analysis confirmed that students who spent more time on social media reported higher stress levels, associated with social anxiety and sleep disturbances caused by digital addiction. This study suggests the importance of managing digital device usage and raising students' awareness of the negative impacts of excessive social media use. The findings imply the need for support from universities and mental health organizations to provide interventions that help students manage their digital lifestyles, reduce stress, and improve their mental well-being.

Analisis Statistika Multivariat untuk Menilai Keterkaitan Gaya Hidup Digital dengan Tingkat Stres Mahasiswa Rusliadi Rusliadi; Mohamad Sofie
Journal of New Trends in Sciences Vol. 3 No. 1 (2025): Journal of New Trends in Sciences
Publisher : CV. Aksara Global Akademia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59031/jnts.v3i1.750

Digital lifestyle has become an integral part of university students' daily lives, involving the use of social media, digital devices, and digital content consumption. The development of digital technology has positive impacts, facilitating easy access to information and social interactions. However, excessive use can lead to digital stress, which negatively affects students' mental health. This study aims to identify the key factors influencing students' digital lifestyles and analyze their relationship with stress levels. A quantitative approach with a survey method was employed, using a questionnaire to measure digital lifestyle, including social media usage frequency and digital device interaction duration, along with the Perceived Stress Scale (PSS) to measure students' stress levels. The factor analysis results show that social media usage and prolonged interaction with digital devices are significant factors contributing to students' stress. Furthermore, sleep disturbances and social anxiety were identified as other significant factors associated with increased stress. The multivariate regression analysis confirmed that students who spent more time on social media reported higher stress levels, associated with social anxiety and sleep disturbances caused by digital addiction. This study suggests the importance of managing digital device usage and raising students' awareness of the negative impacts of excessive social media use. The findings imply the need for support from universities and mental health organizations to provide interventions that help students manage their digital lifestyles, reduce stress, and improve their mental well-being.

Classification of Skin Cancer Diseases Using KNN, CNN and SVM Methods Mohamad Sofie; Mohammad Rofi’i; Bayu Wahyudi
Journal of Engineering, Electrical and Informatics Vol. 5 No. 2 (2025): June: Journal of Engineering, Electrical and Informatics
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jeei.v5i2.3844

According to the WHO, about 2 to 3 million non-melanoma.non-melanoma skin cancers and 132,000 melanoma skin cancers occur globally every year, making up one out of every three cancers.globally each year, and account for one in every three cancers diagnosed.diagnosed. In Indonesia, skin cancer is listed as the cancer with the third highestincidence after uterine cervical and ovarian cancer, and breast cancer.Skin cancer can be detected with dermoscopy. Dermoscopy is a non-invasive diagnostic technique using optical magnification that allows visualization of morphologicHowever, this cannot be done optimally because it still relies on manual analysis so it cannot classify skin cancer types on larger datasets with potential errors and low accuracy. To accurately determine the type of skin cancer,a better classification method is needed. The purpose of this research is to determine the accuracy of skin cancer calcification using Convolutional Neural Network (CNN), support vector machine (SVM), K-nearest neighbor (KNN) models. The datasheet used amounted to 2,239 containing skin cancer images with class division 114 actinic keratosis, 376 basal cell carcinoma, 95 dermatofibroma, 438 melanoma, 357 nevus, 462 pigmented benign, 77 seborrheic keratosis, 181 squamos cell, 139 vascular lesion. The results showed that the convolutional neural network (CNN) algorithm model obtained a sensitivity of 92.59%, specificity of 99%, precision of 93%, F1-Score of 93.01%, and accuracy of 98.35%. For the KNN algorithm model, 57.77% sensitivity, 94.53% specificity, 64.25% precision, 55.99% F1-Score, and 90.45% accuracy were obtained. And for the SVM algorithm model, 61% sensitivity, 94.81% specificity, 70.23% precision, 61.26% F1-Score, and 91.17% accuracy were obtained.

Arduino Uno Based Audiometer Design Mohamad Sofie; Muhammad Rizky Aditya Firdaus; Bayu Wahyudi
Journal of Engineering, Electrical and Informatics Vol. 5 No. 2 (2025): June: Journal of Engineering, Electrical and Informatics
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jeei.v5i2.4828

The ability to detect hearing impairment early is an important aspect of preventive efforts in the field of ear and hearing health. An audiometer is a device used to measure a person's hearing threshold by presenting sound stimuli at various frequencies and intensities. This research aims to design and build a simple digital audiometer that can be used as a means of early hearing screening at primary healthcare facilities. The developed audiometer system uses a microcontroller as the control center, equipped with a user interface based on an LCD screen and buttons for adjusting frequency and sound intensity. Sound output is channeled through headphones and calibrated within the frequency range of 125 Hz to 10,000 Hz with intensity levels from 0 dB to 10 - 100 dB. The value obtained from the measurements after making improvements on TP 1 (Input adapter) showed an error of 0.03% TP 2 (Nextion LCD input) at 5.12 V which is still within tolerance. TP 3 (Arduino Input) at 11.64 V which is still within tolerance. TP 4 (Input IC LM2956) at 11.66 V which is still within tolerance. The function of this audiometer tool was tested using a digital multimeter. The highest error value is at a frequency of 500 Hz, which is 0.152%. This is partly due to the tolerance values of the components used. Based on the data collection using a sound level meter, the furthest difference in sound intensity values at the point of 40 dB was found to be 3.46 dB. This is due to the influence of noise in the surrounding measurement area.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search