Garuda - Garba Rujukan Digital

PENERAPAN METODE SELEKSI FITUR UNTUK MENINGKATKAN HASIL DIAGNOSIS KANKER PAYUDARA Wahyuni, Elvira Sukma
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 7, No 1 (2016): JURNAL SIMETRIS VOLUME 7 NO 1 TAHUN 2016
Publisher : Universitas Muria Kudus

Tujuan utama penelitian ini adalah untuk meningkatkan peforma klasifikasi pada diagnosis kanker payudara dengan menerapkan seleksi fitur pada beberapa algoritme klasifikasi. Penelitian ini menggunakan database kanker payudara Wisconsin Breast Cancer Database (WBCD). Metode seleksi fitur F-score dan Rough Set akan dipasangkan dengan beberapa algoritme klasifikasi yaitu SMO (Sequential Minimal Optimization), Naive Bayes, Multi layer Perceptron, dan C4.5. Penelitian ini menggunakan 10 fold cross validation sebagai metode evaluasi. Hasil penelitian menunjukkan algoritme klasifikasi MLP dan C4.5 mengalami peningkatan peforma klasifikasi secara signifikan setelah dipasangkan dengan seleksi fitur rough set dan F-score, Naive Bayes menunjukan peforma terbaik ketika dipasangkan dengan metode seleksi fitur F-score saja, sedangkan SMO tidak menunjukkan peningkatan peforma klasifikas ketika dipasangkan pada kedua seleksi fitur. Kata kunci: kanker payudara, seleksi fitur, klasifikasi.

Comparison of Some Methods for the Elderly Patient Telemonitoring System Setiawan, Hendra; Wahyuni, Elvira Sukma
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 3, August 2018
Publisher : Universitas Muhammadiyah Malang

This paper analyzes some research results related to patient telemonitoring system. The main objective is to collect many useful information for telemonitoring implementation and its development in the future. Telemonitoring system is focused on fall detection that generally occur prior to critical condition. There are 14 research results that discussed in this paper which have been published from 2013 to 2017. Those researches are grouped into three types i.e. intrusive, non-intrusive and mixed. Analysis is done on aspects of the comfort, complexity, cost, accuracy, and coverage. Furthermore, based on those information, a study of application feasibility is done for elderly patients in Indonesia. The result shows that the non-intrusive method using the camera or access point are the most appropriate system for the elderly fall detection.

Smoke and Fire Detection Base on Convolutional Neural Network WAHYUNI, ELVIRA SUKMA; HENDRI, MUHAMMAD
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 7, No 3 (2019): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v7i3.455

ABSTRAKDeteksi api dan asap adalah langkah pertama sebagai deteksi dini kebakaran. Deteksi dini kebakaran berdasarkan pemrosesan gambar dianggap mampu memberikan hasil yang efektif. Pilihan metode deteksi adalah kunci penting. Metode ekstraksi fitur berdasarkan analisis statistik dan analisis dinamis kadang-kadang memberikan akurasi kurang akurat dalam mendeteksi asap dan api, terutama pada deteksi asap, hal ini disebabkan oleh karakteristik objek asap yang transparan dan bergerak. Dalam penelitian ini, metode Convolutional Neural Network (CNN) diterapkan untuk deteksi asap dan api. Dari penelitian ini, diketahui bahwa CNN memberikan kinerja yang baik dalam deteksi kebakaran dan asap. Akurasi deteksi tertinggi diperoleh dengan menggunakan 144 data pelatihan, 20.000 iterasi dengan dropout.Kata kunci: Deteksi asap, deteksi kebakaran, Jaringan Syaraf Konvolusional ABSTRACTFire and smoke detection is the first step as early detection of fires. Early detection of fire based on image processing is considered capable of providing effective results. The choice of detection method is an important key. Feature extraction methods based on statistical analysis and dynamic analysis sometimes provide less accurate accuracy in detecting smoke and fire, especially on smoke detection, this is due to the characteristics of transparent and moving smoke objects. In this study, the Convolutional Neural Network (CNN) method was applied for smoke and fire detection. From this study, it is known that CNN provides good performance in fire and smoke detection. The highest detection accuracy is obtained by using 144 training data, 20,000 iterations and dropout is true.Keywords: Smoke detection, Fire detection, Convolutional Neural Network

Detection of Human Movement Direction Using Optical Flow Analisys on Multiple Camera Angles Wahyuni, Elvira Sukma; Iqbal, Zulfika; Farahiya, Dzata
JURNAL NASIONAL TEKNIK ELEKTRO Vol 10, No 2: July 2021
Publisher : Jurusan Teknik Elektro Universitas Andalas

The active movement of children poses a safety risk in the absence of adult supervision. To reduce the risk of accidents in children, an automatic detection system for the direction of children's movements is crucially needed. In this study, detection of the direction of human movement based on image processing was carried out with the input of videos produce from 4 CCTV installed in each corner of the room. The system will detect the direction of object movement with classification of orientation, namely front, back, right and left. The detection method used in this research is Optical Flow. Optical Flow will calculate the value of the direction or orientation of the movement of an object. The orientation obtained is then accumulated with HOOF (Histogram Orientation of Optical Flow), where HOOF will collect the orientation of objects on the whole frame according to a 8-part Cartesian angle. The results of the orientation with Optical Flow will be compared with the direction of detection measured manually to determine whether the detection of movement direction using Optical Flow is running well. According to the results, it is known that the Optical Flow method has succeeded in detecting the direction of movement accurately based on different camera angles.Keywords :Â Image Processing, CCTV, Optical Flow, HOOF

Comparison of Motion History Image and Approximated Ellipse Method in Human Fall Detection System Mohammad Brado Frasetyo; Elvira Sukma Wahyuni; Hendra Setiawan
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 2 (2019): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.43632

This paper compares two different method in human fall detection system namely motion history image and approximated ellipse. Research has been done in small studio with 4 CCTV camera as video data recorder, whereas video data are processed using MATLAB software. The experiment was carried out using three object’s fall direction and two type of falling movement. The fall direction is consist of front, side, and back fall. Whereas the falling movement is consist of direct and indirect fall movement. Meanwhile, the object’s initial position is standing and size of captured object is constant. The result is motion history image has accuracy 74.26% for direct falling movement, and 75.69% for indirect falling movement. Whereas approximated ellipse has accuracy 56.85% for direct falling movement, and 61.81% for indirect falling movement. Therefore, motion history image is better than approximated ellipse in human fall detection system.

PENERAPAN METODE SELEKSI FITUR UNTUK MENINGKATKAN HASIL DIAGNOSIS KANKER PAYUDARA Elvira Sukma Wahyuni
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 7, No 1 (2016): JURNAL SIMETRIS VOLUME 7 NO 1 TAHUN 2016
Publisher : Universitas Muria Kudus

Tujuan utama penelitian ini adalah untuk meningkatkan peforma klasifikasi pada diagnosis kanker payudara dengan menerapkan seleksi fitur pada beberapa algoritme klasifikasi. Penelitian ini menggunakan database kanker payudara Wisconsin Breast Cancer Database (WBCD). Metode seleksi fitur F-score dan Rough Set akan dipasangkan dengan beberapa algoritme klasifikasi yaitu SMO (Sequential Minimal Optimization), Naive Bayes, Multi layer Perceptron, dan C4.5. Penelitian ini menggunakan 10 fold cross validation sebagai metode evaluasi. Hasil penelitian menunjukkan algoritme klasifikasi MLP dan C4.5 mengalami peningkatan peforma klasifikasi secara signifikan setelah dipasangkan dengan seleksi fitur rough set dan F-score, Naive Bayes menunjukan peforma terbaik ketika dipasangkan dengan metode seleksi fitur F-score saja, sedangkan SMO tidak menunjukkan peningkatan peforma klasifikas ketika dipasangkan pada kedua seleksi fitur. Kata kunci: kanker payudara, seleksi fitur, klasifikasi.

Detection of Human Movement Direction Using Optical Flow Analisys on Multiple Camera Angles Elvira Sukma Wahyuni; Zulfika Iqbal; Dzata Farahiya
JURNAL NASIONAL TEKNIK ELEKTRO Vol 10, No 2: July 2021
Publisher : Jurusan Teknik Elektro Universitas Andalas

The active movement of children poses a safety risk in the absence of adult supervision. To reduce the risk of accidents in children, an automatic detection system for the direction of children's movements is crucially needed. In this study, detection of the direction of human movement based on image processing was carried out with the input of videos produce from 4 CCTV installed in each corner of the room. The system will detect the direction of object movement with classification of orientation, namely front, back, right and left. The detection method used in this research is Optical Flow. Optical Flow will calculate the value of the direction or orientation of the movement of an object. The orientation obtained is then accumulated with HOOF (Histogram Orientation of Optical Flow), where HOOF will collect the orientation of objects on the whole frame according to a 8-part Cartesian angle. The results of the orientation with Optical Flow will be compared with the direction of detection measured manually to determine whether the detection of movement direction using Optical Flow is running well. According to the results, it is known that the Optical Flow method has succeeded in detecting the direction of movement accurately based on different camera angles.Keywords : Image Processing, CCTV, Optical Flow, HOOF

Comparison of Some Methods for the Elderly Patient Telemonitoring System Hendra Setiawan; Elvira Sukma Wahyuni
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 3, August 2018
Publisher : Universitas Muhammadiyah Malang

This paper analyzes some research results related to patient telemonitoring system. The main objective is to collect many useful information for telemonitoring implementation and its development in the future. Telemonitoring system is focused on fall detection that generally occur prior to critical condition. There are 14 research results that discussed in this paper which have been published from 2013 to 2017. Those researches are grouped into three types i.e. intrusive, non-intrusive and mixed. Analysis is done on aspects of the comfort, complexity, cost, accuracy, and coverage. Furthermore, based on those information, a study of application feasibility is done for elderly patients in Indonesia. The result shows that the non-intrusive method using the camera or access point are the most appropriate system for the elderly fall detection.

Eye Detection System Based on Image Processing for Vehicle Safety Almira Budiyanto; Abdul Manan; Elvira Sukma Wahyuni
Techné : Jurnal Ilmiah Elektroteknika Vol. 19 No. 1 (2020)
Publisher : Fakultas Teknik Elektronika dan Komputer Universitas Kristen Satya Wacana

The more advanced the technology and the greater the community's need to carry out activities every day, the number of vehicles on the highway is getting crowded. From year to year, the greater the level of traffic accidents caused by many factors, among the usual reasons is the loss of awareness of the driver when driving a vehicle especially drowsiness. One of the drowsiness parameters is the frequency eye blinks. Therefore, to get the drowsiness symptoms, the purpose of this research is to detect the eye blinks, which in turn reduce the level of accidents by detecting sleepy eyes based on digital image processing. The method used to detect both eyes is the Viola-Jones method. The detection of both eyes can also acquire the duration of closed eyes and the number of eye blinks. A person can be said to be sleepy by means of sleepiness parameters determined by a study. The research shows that detection of eye blinks using the Viola-Jones method has a fairly high accuracy of up to 84.72% if the face condition is upright and tilted no more than 45 degrees. Another conclusion is that eye detection and driver detection are more effective at certain light intensity values which are around 2-33 lux.

The Performance Comparison of Machine Learning Models for COVID-19 Classification Based on Chest X-ray Elvira Sukma Wahyuni
Journal of Biomedical Science and Bioengineering Vol 2, No 1 (2022)
Publisher : Center for Biomechanics, Biomaterials, Biomechantronics and Biosignal Processing (CBOIM3S)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jbiomes.2022.v2i1.1-6

COVID-19 has become a pandemic spread to nearly all countries in the world. This virus has caused many deaths. Screening using a chest X-ray is an alternative to find out positive COVID-19 patients. Chest X-ray is advantageous because every hospital must have an X-ray device so that hospitals do not need additional equipment to detect COVID-19-positive patients. This study aims to compare the machine learning models of Naive Bayes, Decision Tree, K-Nearest Neighbor, and Logistic Regression to predict COVID-19 positive patients. The stages of the research carried out by this study are the Pre-process stage, feature extraction, and classification. The results showed that the Naïve Bayes classification method got the highest performance with an accuracy of 95.24%.

Title

Found 13 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 13 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 13 Documents
Search