Claim Missing Document
Check
Articles

Found 9 Documents
Search

Geometric Model for Human Body Orientation Classification Ardiyanto, Igi
CommIT (Communication and Information Technology) Journal Vol 9, No 1 (2015): CommIT Vol. 9 No. 1 Tahun 2015
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v9i1.1659

Abstract

This  paper proposes  an approach  for cal- culating  and estimating  human body orientation  using geometric model. A novel framework integrating gradient shape and texture model of the human body orientation is proposed.  The gradient  is a natural way for describing the human  shapes, while the texture  explains the body characteristic. The framework  is then combined with the random  forest classifier to obtain a robust  class  differ- ence  of the human body orientation. Experiments and comparison results are provided to show the advantages of our system over state-of-the-art. For both modeled and un-modeled gradient-texture  features with random forest classifier, they achieve the highest accuracy on separating each human orientation   class, respectively  56.9% and 67.3% for TUD-Stadtmitte  dataset.
GEOMETRIC MODEL FOR HUMAN BODY ORIENTATION CLASSIFICATION Ardiyanto, Igi
CommIT (Communication and Information Technology) Journal Vol 9, No 1 (2015): CommIT Vol. 9 No. 1 Tahun 2015
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v9i1.882

Abstract

This paper proposes an approach for calculating and estimating human body orientation using geometric model. A novel framework integrating gradient shape and texture model of the human body orientation is proposed. The gradient is a natural way for describing the human shapes, while the texture explains the body characteristic. The framework is then combined with the random forest classifier to obtain a robust class difference of the human body orientation. Experiments and comparison results are provided to show the advantages of our system over state-of-the-art. For both modeled and un-modeled gradient-texture features with random forest classifier, they achieve the highest accuracy on separating each human orientation class, respectively 56.9% and 67.3% for TUD-Stadtmitte dataset.Keywords: Human Body Orientation; Histogram of Oriented Gradient; Local Binary Pattern; Geometric Model
Segmentation of retinal blood vessels for detection of diabetic retinopathy: A review Aras, Rezty Amalia; Lestari, Tri; Nugroho, Hanung Adi; Ardiyanto, Igi
Communications in Science and Technology Vol 1 No 1 (2016)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.1.1.2016.13

Abstract

Diabetic detinopathy (DR) is effect of diabetes mellitus to the human vision that is the major cause of blindness. Early diagnosis of DR is an important requirement in diabetes treatment. Retinal fundus image is commonly used to observe the diabetic retinopathy symptoms. It can present retinal features such as blood vessel and also capture the pathologies which may lead to DR. Blood vessel is one of retinal features which can show the retina pathologies. It can be extracted from retinal image by image processing with following stages: pre-processing, segmentation, and post-processing. This paper contains a review of public retinal image dataset and several methods from various conducted researches. All discussed methods are applicable to each researcher cases. There is no further analysis to conclude the best method which can be used for general cases. However, we suggest morphological and multiscale method that gives the best accuracy in segmentation.
Analisis Pengaruh Kompresi Citra Fundus terhadap Kinerja Sistem Automated Microanerysm Detections Persada, Anugerah Galang; Nasikun, Ahmad; Ardiyanto, Igi; Nugroho, Hanung Adi
Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI) Vol 7, No 1 (2018)
Publisher : Jurusan Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1011.955 KB) | DOI: 10.22146/jnteti.v7i1.403

Abstract

Diabetes is one of the most serious diseases that commonly suffered by people around the world, including Indonesia. Early symptoms of diabetes could be observed from various indicators, one of which is through the retina. Retina conditions is affected by diabetics and when remain unproperly threated could lead to blindness. This retinal disorders due to diabetes is normally called Diabetic Retinopathy (DR). One method that able to distinguish and detect DR is microaneurysm detection. This method requires good quality of retinal images. However, in certain areas such as rural areas, this requirement may difficult to meet due to lack of adequate infrastructure. One solution that may overcome this problem is to compress the images. In this paper, image compression algorithms were applied to the retinal image, and then used to detect microaneuryms through Deep Learning-based systems. The result shows that the most stable and appropriate algorithm is PNG, which is able to correctly classify around 83% in accuracy with 5,5% variance.
Dark lesion elimination based on area, eccentricity and extent features for supporting haemorrhages detection Yulyanti, Vesi; Adi Nugroho, Hanung; Ardiyanto, Igi; Oktoeberza, Widhia KZ
Communications in Science and Technology Vol 4 No 1 (2019)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (410.365 KB) | DOI: 10.21924/cst.4.1.2019.110

Abstract

One of the complications due to the long-term of diabetes is retinal vessels damaging called diabetic retinopathy. It is characterised by appearing the bleeding spots in the large size (haemorrhages) on the surface of retina. Early detection of haemorrhages is needed for preventing the worst effect which leads to vision loss. This study aims to detect haemorrhages by eliminating other dark lesion objects that have similar characteristics with haemorrhages based on three features, i.e. area, eccentricity and extent features. This study uses 43 retinal fundus images taken from DIARETDB1 database. Based on the validation process, the average level of sensitivity gained is 80.5%. These results indicate that the proposed method is quite capable of detecting haemorrhages which appear in the retinal surface.
Remote Sensing Technology for Land Farm Mapping Based on NDMI, NDVI, and LST Feature Mabrur, Ahmad Fauzi; Setiawan, Noor Akhmad; Ardiyanto, Igi
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 3, No 3 (2019): September 2019
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1513.335 KB) | DOI: 10.22146/ijitee.47430

Abstract

Remote Sensing is a reliable and efficient data acquisition techniques. This technique is widely used for land image processing. This technique has many advantages, especially in terms of cost and time. In this study, the classification between dry and irrigated land from irrigation canals is presented. Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), and Land Surface Temperature (LST) values obtained from satellite imagery data are used in this process. It is expected that through this method, the distribution and control of irrigation water can optimize existing agricultural potential. Ground Check (GC) is used for validation process. The results showed that the error rate based on the moon was not so large, i.e., 18%. The highest errors occur in February and March. This happens because those months are the rainy season, so the measured temperature is mostly the temperature above the cloud layer. On the other hand, the lowest error occurs in November. Also, it can be seen that this method can function optimally when detecting residential areas or highways.
Deep Learning Methods for EEG Signals Classification of Motor Imagery in BCI Saputra, Muhammad Fawaz; Setiawan, Noor Akhmad; Ardiyanto, Igi
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 3, No 3 (2019): September 2019
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1033.036 KB) | DOI: 10.22146/ijitee.48110

Abstract

EEG signals are obtained from an EEG device after recording the user's brain signals. EEG signals can be generated by the user after performing motor movements or imagery tasks. Motor Imagery (MI) is the task of imagining motor movements that resemble the original motor movements. Brain Computer Interface (BCI) bridges interactions between users and applications in performing tasks. Brain Computer Interface (BCI) Competition IV 2a was used in this study. A fully automated correction method of EOG artifacts in EEG recordings was applied in order to remove artifacts and Common Spatial Pattern (CSP) to get features that can distinguish motor imagery tasks. In this study, a comparative studies between two deep learning methods was explored, namely Deep Belief Network (DBN) and Long Short Term Memory (LSTM). Usability of both deep learning methods was evaluated using the BCI Competition IV-2a dataset. The experimental results of these two deep learning methods show average accuracy of 50.35% for DBN and 49.65% for LSTM.
Perbandingan Performa Relational, Document-Oriented dan Graph Database Pada Struktur Data Directed Acyclic Graph Setialana, Pradana; Adji, Teguh Bharata; Ardiyanto, Igi
Jurnal Buana Informatika Vol 8, No 2 (2017): Jurnal Buana Informatika Volume 8 Nomor 2 April 2017
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v8i2.1079

Abstract

Abstract.Directed Acyclic Graph (DAG) is a directed graph which is not cyclic and is usually employed in social network and data genealogy. Based on the characteristic of DAG data, a suitable database type should be evaluated and then chosen as a platform. A performance comparison among relational database (PostgreSQL), document-oriented database (MongoDB), and graph database (Neo4j) on a DAG dataset are then conducted to get the appropriate database type. The performance test is done on Node.js running on Windows 10 and uses the dataset that has 3910 nodes in single write synchronous (SWS) and single read (SR). The access performance of PostgreSQL is 0.64ms on SWS and 0.32ms on SR, MongoDB is 0.64ms on SWS and 4.59ms on SR, and Neo4j is 9.92ms on SWS and 8.92ms on SR. Hence, relational database (PostgreSQL) has better performance in the operation of SWS and SR than document-oriented database (MongoDB) and graph database (Neo4j).Keywords: database performance, directed acyclic graph, relational database, document-oriented database, graph database Abstrak.Directed Acyclic Graph (DAG) adalah graf berarah tanpa putaran yang dapat ditemui pada data jejaring sosial dan silsilah keluarga. Setiap jenis database memiliki performa yang berbeda sesuai dengan struktur data yang ditangani. Oleh karena itu perlu diketahui database yang tepat khususnya untuk data DAG. Tujuan penelitian ini adalah membandingkan performa dari relational database (PostgreSQL), document-oriented database (MongoDB) dan graph database (Neo4j) pada data DAG. Metode yang dilakukan adalah mengimplentasi dataset yang memiliki 3910 node dalam operasi single write synchronous (SWS) dan single read (SR) pada setiap database menggunakan Node.js dalam Windows 10. Hasil pengujian performa PostgreSQL dalam operasi SWS sebesar 0.64ms dan SR sebesar 0.32ms, performa MongoDB pada SWS sebesar 0.64ms dan SR sebesar 4.59ms sedangkan performa Neo4j pada operasi SWS sebesar 9.92ms dan SR sebesar 8.92ms. Hasil penelitian menunjukan bahwa relational database (PostgreSQL) memiliki performa terbaik dalam operasi SWS dan SR dibandingkan document-oriented database (MongoDB) dan graph database (Neo4j).Kata Kunci: performa database, directed acyclic graph, relational database, document-oriented database, graph database
COMPARISON OF TEXT-IMAGE FUSION MODELS FOR HIGH SCHOOL DIPLOMA CERTIFICATE CLASSIFICATION Atmaja Perdana, Chandra Ramadhan; Adi Nugroho, Hanung; Ardiyanto, Igi
Communications in Science and Technology Vol 5 No 1 (2020)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (901.175 KB) | DOI: 10.21924/cst.5.1.2020.172

Abstract

File scanned documents are commonly used in this digital era. Text and image extraction of scanned documents play an important role in acquiring information. A document may contain both texts and images. A combination of text-image classification has been previously investigated. The dataset used for those research works the text were digitally provided. In this research, we used a dataset of high school diploma certificate, which the text must be acquired using optical character recognition (OCR) method. There were two categories for this high school diploma certificate, each category has three classes. We used convolutional neural network for both text and image classifications. We then combined those two models by using adaptive fusion model and weight fusion model to find the best fusion model. We come into conclusion that the performance of weight fusion model which is 0.927 is better than that of adaptive fusion model with 0.892.