Ika Candradewi, Ika
Unknown Affiliation

Published : 12 Documents
Articles

Found 12 Documents
Search

SISTEM KLASIFIKASI KENDARAAN BERBASIS PENGOLAHAN CITRA DIGITAL DENGAN METODE MULTILAYER PERCEPTRON Irfan, Muhammad; Ardi Sumbodo, Bakhtiar Alldino; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 7, No 2 (2017): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.677 KB) | DOI: 10.22146/ijeis.18260

Abstract

The evolution of video sensors and hardware can be used for developing traffic monitoring system vision based.  It can provide information about vehicle passing by utilizing the camera, so that monitoring can be done automatically. It is needed for the processing systems to provide some information regarding traffic conditions. One such approach is to utilize digital image processing.This research consisted of two phases image processing, namely the process of detection and classification. The process of detection using Haar Cascade Classifier with the training data image form the vehicle and data test form the image state of toll road drawn at random. While, Multilayer Perceptron classification process uses by utilizing the result of the detection process. Vehicle classification is divided into three types, namely car, bus and truck. Then the classification parameters were evaluated by accuracy. The test results vehicle detection indicate the value of accuracy is 92.67. Meanwhile, the classification process is done with phase trial and error to evaluate the parameters that have been determined.  Results of the study show the classification system has an average value of the accuracy is  87.60%.
KLASIFIKASI SEL DARAH PUTIH MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM) BERBASIS PENGOLAHAN CITRA DIGITAL Caraka, Bhima; Sumbodo, Bakhtiar Alldino Ardi; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 7, No 1 (2017): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (658.547 KB) | DOI: 10.22146/ijeis.15420

Abstract

White blood cells are classified into five types (basophils, eosinophils, neutrophils, lymphocytes and monocytes) with additional classes lymphoblast cells from microscope images are processed. By applying image processing, image its white blood cells extracted using the Histogram Oriented Gradient. Feature extraction results obtained then classified using Support Vector Machine method by comparing the results of two different kernel parameters: kernel Linear and kernel Radial Basis Function (RBF). Classification evaluated with these parameters: Accuracy, specificity, and sensitivity.Obtained an accuracy of 72.26% from the detection of white blood cells in the microscope image. The average value of microscope images of patients and different kernel every white blood cells (monocytes, basophils, neutrophils, eosinophils, lymphocytes and lymphoblast) were evaluated with these parameters. Results of the study show the classification system has an average value of 82.20% accuracy (RBF Patient 1), 81.63% (RBF Patient 2) and 78.73% (Linear Patient 1), 79.55% (Linear Patient 2 ), then the value of specificity of 89.91% (RBF patient 1), 92.18% (RBF patient 2) and 88.06% (Linear patient 1), 91.34% (Linear patient 2), and sensitivity values 15 , 45% (RBF patient 1), 12.97% (RBF patient 2) and 13.33% (Linear patient 1), 12.50% (Linear patient 2).
SEGMENTATION OF WHITE BLOOD CELLS AND LYMPHOBLAST CELLS USING MOVING K-MEANS Candradewi, Ika; Bagasjvara, Reno Ghaffur
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 8, No 2 (2018): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (472.545 KB) | DOI: 10.22146/ijeis.39734

Abstract

One of the diagnosis procedures for acute lymphoblastic leukemia is screening for blood cells by expert operator using microscope. This process is relatively long and will slow healing process of this disease which need fast treatment. Another way to screen this disease is by using digital image processing technique in microscopic image of blood smears to detect lymphoblast cells and types of white blood cells. One of essential step in digital image processing is segmentation because this process influences the subsequent process of detecting and classifying Acute Lymphoblastic Leukemia disease. This research performed segmentation of white blood cells using moving k-means algorithm. Some process are done to remove noise such as red blood cells and reduce detection errors such as white blood cells and/or lymphoblastic cell  that?s appear overlap. Postprocessing are performed to improve segmentation quality and to separate connected white blood cell. The dataset in this study has been validated with expert clinical pathologists from Sardjito Regional General Hospital, Yogyakarta, Indonesia. This research produces systems performance with results in sensitivity of 85.6%, precision 82.3%, Fscore of 83,9% and accuracy of 72.3%. Based on the results of the testing process with a much larger number of datasets on the side of the variations level of cell segmentation difficulties both in terms of illumination and overlapping cell, the method proposed in this study was able to detect or segment overlapping white blood cells better.
DETEKSI KETERSEDIAAN SLOT PARKIR BERBASIS PENGOLAHAN CITRA DIGITAL MENGGUNAKAN METODE HISTOGRAM OF ORIENTED GRADIENTS DAN SUPPORT VECTOR MACHINE Putra, Aditya Riska; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 7, No 1 (2017): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (818.035 KB) | DOI: 10.22146/ijeis.15411

Abstract

This research aims to implement method based on digital image processing to inform the status of parking slots at the car parking area by using a feature extraction HOG (Histogram of Oriented Gradients) method in every region of the parking area. Feature extraction results are classified using SVM (Support Vector Machine) by comparing the Linear, RBF (Radial Basis Function), Poly, and Sigmoid kernels. SVM classification results were analyzed using the confusion matrix with accuracy, specificity, sensitivity, and precision parameters. In terms of accuracy, system obtained with Linear kernel in sunny conditions shows 98.0% accuracy; rainy 98.8% accuracy; cloudy 99.2% accuracy. Obtained accuracy using Poly kernel test in sunny conditions shows 99.2%; rainy 98.9%; cloudy 99.4%. Obtained accuracy using RBF kernel in sunny conditions shows 97.9%; rainy 98.7%; cloudy 99.6%. In terms of accuracy using additional data testing obtained with Linear kernel shows accuracy of 97.7%; RBF kernel 97.9% accuracy;  Poly kernel 97.4% accuracy. Sigmoid kernel testing can?t be used because the optimal model did not obtained by using default grid.
SISTEM PENDETEKSI DAN PELACAKAN BOLA DENGAN METODE HOUGH CIRCLE TRANSFORM, BLOB DETECTION, DAN CAMSHIFT MENGGUNAKAN AR.DRONE Pamungkas, Elki Muhamad; Sumbodo, Bakhtiar Alldino Ardi; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 7, No 1 (2017): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (563.473 KB) | DOI: 10.22146/ijeis.15405

Abstract

 Parrot AR.Drone is one type of quadrotor UAV. Quadrotor is operated manually with remote control and automatically using GPS (Global Positioning System), but using GPS in tracking mission an object has disadvantage that can?t  afford quadrotor position relative to object. Quadrotor require other control methods to perform object tracking. One approach is utilize digital image processing. In this research is designed detection and tracking ball system with digital image processing using OpenCV library and implemented on platform Robot Operating System. The methods which used is hough transform circle, blob detection and camshif.            The results of this research is system on AR.Drone capable of detecting and tracking ball. Based on the test results it was concluded that the maximum distance of system is capable to detecting ball with diameter of 20 cm using hough transform circle method is 500 cm and using blob detection method is 900 cm. Average time detection process to detect the ball using hough transform circle that is 0.0054 second and  for blob detection method is 0.0116 second. The success rate of tracking the ball using camshift method from the results of detection hough circle transfom is 100% while from result of detection blob detection is 96.67%
SISTEM PENGUKUR KECEPATAN KENDARAAN BERBASIS PENGOLAHAN VIDEO Sadewo, Satrio Sani; Sumiharto, Raden; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 5, No 2 (2015): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (566.293 KB) | DOI: 10.22146/ijeis.7641

Abstract

This system is implemented by digital image processing to detect the objects and measure the speed. This system using background subtraction method with Gaussian Mixture Model (GMM) algorithm. Background subtraction will separate background and detected objects. Coordinates of the objects midpoint used as the the object moving value in pixel. The actual distance also measured in meters where the distance is limited by region of interest (ROI). The ROI is 160 pixel. Having obtained the moving objects time from previous frame to current frame so the value of pixel/s can converted to km/h.System testing the measurement validation, calculate the speed after being validated, and the influence of light intensity. The speed validation process uses average speed of early three frames speed as the reference for the speed measurement in the next frame. The average speed accuracy of 3 frames early gives a percentage error about 1,92% - 15,75%. When validation is performed on the entire reading frame of video, it produces an error range 1,21% - 21,37%. The system works well in the morning, afternoon, and evening conditions with light intensity about 600-1900 lux. While at night with 0-5 lux light intensity range, the system can?t work properly.
SISTEM PENGENAL ISYARAT TANGAN UNTUK MENGENDALIKAN GERAKAN ROBOT BERODA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK Adi, Habib Astari; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 9, No 2 (2019): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (851.523 KB) | DOI: 10.22146/ijeis.50208

Abstract

Currently, Human and computer interaction is generally done using a remote control. This approach tends to be impractical for wheeled robot operation because it must always carry an intermediary tool during the operation. The application of hand gesture recognition using digital image processing techniques and machine learning in the control process of wheeled robots will facilitate the control of wheeled robots because control no longer requires an intermediary tool.In this study, hand image taken using a camera then will be processed using a single board computer to be recognized. The results of recognized are passed on to arduino leonardo and DC motor to control twelve wheeled robot movement. The method used in this study is contrast stretching for preprocessing and Convolutional Neural Network (CNN) for hand recognition. This method is tested with a variation of  bright 26-140 lux, the distance from the face to the camera is 120-200cm. Hand recognition systems using this method resulting accuracy 97,5%, precision 97,57%, sensitivity 97.5%, spesificity 99,77 and f1 score 97.45%.
HAND-RAISE DETECTION PADA KELAS CENDEKIA MENGGUNAKAN KAMERA RGB DAN DEPTH Auni, Muhammad Fajar Khairul; Timur, Muhammad Idham Ananta; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 8, No 1 (2018): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (383.353 KB) | DOI: 10.22146/ijeis.34162

Abstract

The requisite of intelligent classroom?s to perform the quickest speaker lift determination of speakers in the classroom using the concept of ubiquitous computing where the technology exists but does not feel around. The classroom concept requires several capabilities such as knowing the ideal distance from the camera, performing real-time hand-lifted movements from the speaker using the AdaBoost method, and determining the fastest hand lift from the speaker in real-time. The camera's ideal distance to speakers is about 250 cm. the system has a detection accuracy of 97.485497% and accuracy using coordinates joint point of 98%. The system is also capable of determining the fastest time using AdaBoost with 93.5% accuracy and the accuracy of the fastest hands lifting using coordinates joint point of 95%.
KLASIFIKASI SEL DARAH PUTIH BERDASARKAN CIRI WARNA DAN BENTUK DENGAN METODE K-NEAREST NEIGHBOR (K-NN) Khasanah, Mizan Nur; Harjoko, Agus; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 6, No 2 (2016): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (462.769 KB) | DOI: 10.22146/ijeis.15254

Abstract

The traditional procedure of classification of blood cells using a microscope in the laboratory of hematology to obtain information types of blood cells. It has become a cornerstone in the laboratory of hematology to diagnose and monitor hematologic disorders. However, the manual procedure through a series of labory test can take a while. Thresfore, this research can be helpful in the early stages of the classification of white blood cells automatically in the medical field.Efforts to overcome the length of time and for the purposes of early diagnose can use the image processing technique based on morphology of blood cells. This research aims to classify the white blood cells based on cell morphology with the k-nearest neighbor (knn). Image processing algorithms used hough circle, thresholding, feature extraction, then to the process of classification was used the method of k-nearest neighbor (knn).In the process of testing used 100 images to be aware of its kind. The test results showed segmentation accuracy of 78% and testing the classification of 64%.
SISTEM KLASIFIKASI TINGKAT KEPARAHAN RETINOPATI DIABETIK MENGGUNAKAN SUPPORT VECTOR MACHINE Adi Putranto, Taufiq Galang; Candradewi, Ika
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 8, No 1 (2018): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (844.602 KB) | DOI: 10.22146/ijeis.31206

Abstract

Diabetic retinopathy is a vision disorder disease that can cause damage to the retina of the eye that will have a direct impact on the disruption of vision of the patient. The diabetic retinopathy phase is classified into four types (normal, mild NPDR, moderate NPDR (Non-Proliferative Diabetic Retinopathy), and severe NPDR). Retinal of eye data of diabetic retinopathy patients treated from the MESSIDOR database. By applying image processing, the retinal image of the eye in extraction using the area features extraction from the detection of exudate, blood vessels, microaneurysms, and texture feature extraction Gray Level Co-occurrence Matrix. The extracted results classified using the Support Vector Machine method with the Radial Basis Function (RBF) kernel. Classification evaluated with these parameters: Accuracy, specificity, and sensitivity.The results of classification show the best value using 6 statistical features ie, contrast, homogeneity, correlation, energy, entropy and inverse difference moment in the direction of 45 degrees with the RBF kernel. The result of classification research system on 240 data training and 60 data testing yields an average accuracy is 95.93%, the value of specificity is 97.29%, and a sensitivity rating is  91.07%. From the research result, using RBF kernel get the best accuracy result than using kernel polynomial or kernel linear.