Articles
Sistem Pakar Diagnosis Tanaman Cabai dengan Metode Forward Chaining dan Dempster Shafer
Mega Laely;
I Gede Pasek Suta Wijaya;
Arik Aranta
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 2 No 2 (2020): September 2020
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29303/jtika.v2i2.118
Tanaman cabai (Capsicum Annum) merupakan salah satu komoditi hortikultura yang buahnya mempunyai nilai gizi cukup tinggi terutama kandungan vitamin A dan C. Secara nasional produktivitas dan luas panen cabai menjadi yang tertinggi dibandingkan komoditi hortikultura lainnya. Salah satu masalah pada tanaman cabai adalah serangan penyakit cabai yang dapat menurunkan kualitas dan kuantitas hasil produksi cabai. Penelitian ini bertujuan untuk mengembangkan sistem pakar yang dapat mendiagnosis penyakit tanaman cabai berdasarkan pengetahuan 3 pakar dengan menggunakan 7 data penyakit cabai dan 32 data gejala. Metode yang digunakan untuk memperoleh hasil diagnois yaitu, Forward Chaining dan Dempster Shafer. Penelitian ini menggunakan 4 teknik pengujian yaitu pengujian black box dengan hasil yang secara fungsionalitas sudah berjalan sesuai perancangan, pengujian dengan perhitungan teoritis pada 1 contoh kasus menghasilkan hasil perhitungan yang tepat dengan hasil perhitungan sistem, pengujian Akurasii sistem pada 30 contoh kasus menghasilkan Akurasii sistem berdasarkan rata-rata nilai belief 3 pakar sebesar 90% dan Akurasii sistem berdasarkan nilai belief masing-masing pakar sebesar 95,56%, pengujian Mean Opinion Score (MOS) menghasilkan nilai MOS sebesar 4,35 untuk mahasiswa Teknik Informatika, nilai MOS sebesar 4 untuk Pertanian, nilai MOS sebesar 4,68 untuk Penyuluh Pertanian, nilai MOS sebesar 4.54 untuk Petani.
Deteksi Api pada Video dengan Gaussian Mixture Model Untuk Deteksi Gerakan Dan Segmentasi Warna Api Dalam Ruang Warna YCbCr
Ristirianto Adi;
I Gede Pasek Suta Wijaya
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 3 No 1 (2021): March 2021
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29303/jtika.v3i1.125
Fire is a disaster that can endanger lives and cause property loss. The solution to detect fire that is commonly used today is to use a sensor. Fire sensors can be used together with surveillance cameras (CCTV) which are now being installed in many office buildings. This study tries to build a model for detecting fire in video with a digital image processing approach using the Gaussian Mixture Model for motion detection and fire color segmentation in the YCbCr color space. The model is then tested with metrics for accuracy, precision, recall, and processing speed. The dataset used is in the form of videos with small, medium, large fire sizes, and videos that only have fire-like objects. The test results show that the algorithm is able to detect fire when the size of the fire is not too small or the position of the fire is close enough to the camera. For videos with a resolution of 800x600 and a framerate of 30 fps, it can achieve 66.89% accuracy, 73.77% precision, and 66.66% recall. The performance during the day is relatively better than at night. Algorithm processing speed is too slow to be implemented in real-time
Pengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Ekstraksi Fitur Discrete Cosine Transform Dan Klasifikasi Backpropagation Artificial Neural Network
Farhan Yakub Bawazir;
I Gede Pasek Suta Wijaya
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 3 No 1 (2021): March 2021
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29303/jtika.v3i1.127
Arabic is a language that is spoken as the first or native language of more than 280 million people, most of whom live in the Middle East and North Africa. Apart from the Middle East and North Africa, Arabic is also familiar and often used in Indonesia because of the majority of Indonesia's population is Muslim and Arabic is the language of worship in Islam. The recognition of Arabic handwritten letters is one of the studies that has been done before, where the accuracy results obtained vary according to the research and methods used. This study aims to determine the accuracy resulting from the recognition of Arabic script handwriting patterns using a combination of the DCT(Discrete Cosine Transform) feature extraction method and the ANN Backpropagation classification method. The data used for this study were data from handwritten sources on A4 HVS paper using markers with categories of age from 7-13 years old and 18-23 years old with 15 respondents in each group and a total dataset image of 8400. Testing the best model model obtained on all images produces an accuracy of 80.79%, using the images of age range 17-23 years produces 87.27% accuracy, and the images of age range 7-13 produces an accuracy of 72.84%. Keywords: pengenalan pola, tulisan tangan, aksara, DCT, backpropagation
Sistem Pakar Diagnosis Penyakit pada Kambing dengan Metode Forward Chaining dan Certainty Factor
Novita Nurul Fakhriyah;
Fitri Bimantoro;
I Gede Pasek Suta Wijaya
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 3 No 1 (2021): March 2021
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29303/jtika.v3i1.138
Penyakit pada hewan kambing terdiri dari dua jenis yaitu penyakit menular dan tidak menular. Penyakit padahewan perlu dilakukan penanganan yang tepat terutama penyakit menular agar tidak dapat menular pada ternak lain.Penelitian ini bertujuan untuk membangun sistem pakar yang berbasis Android untuk mendiagnosis 14 jenis penyakitpada kambing berdasarkan pengetahuan 3 orang pakar hewan dengan menggunakan metode Forward Chaining sebagaimetode inferensi dan Certainty Factor sebagai metode perhitungan untuk mendapatkan nilai densitas atau tingkatkepercayaan dari hasil diagnosis penyakit pada kambing. Penelitian ini menggunakan empat jenis pengujian yaituberupa pengujian blackbox, pengujian kuisioner (MOS), pengujian teoritis dan pengujian akurasi sistem. Dari pengujianakurasi sistem yang dilakukan, didapatkan nilai akurasi berdasarkan bobot rata-rata 3 orang pakar sebesar 85.55%,sedangkan pengujian akurasi menggunakan bobot masing-masing pakar diperoleh hasil 86.66% untuk pakar 1, 83.33%untuk pakar 2, dan 86.66% untuk pakar 3. Untuk pengujian MOS (Mean Opinion Score) didapatkan hasil sebesar 4.35dari skala 5, serta pengujian perhitungan teoritis yang mendapatkan hasil perhitungan sama antara hasil perhitungandiagnosis sistem dan diagnosis pakar. Berdasarkan hasil perngujian maka sistem pakar diagnosis penyakit pada kambingini layak digunakan dan dikategorikan ke dalam sistem yang baik.
Rancang Bangun Sistem Pendukung Keputusan Inventory Pakaian Adat berbasis Web menggunakan Fuzzy Inference Tsukamoto (Studi Kasus : Toko Bali Antic)
I Made Subiantara Putra;
I Gde Putu Wirarama Wedaswhara W.;
I Gede Pasek Suta Wijaya
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 3 No 2 (2021): September 2021
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29303/jtika.v3i2.150
Traditional clothing is a symbol of clothing in an area that has an identity and is characterized as a relevant cultural symbol. Inventory control is very important to take into account because shortage or excess inventory is a factor that triggers an increase in costs. In daily operations, the data collection process that is still done manually is mostly done in clothing sales stores, so there are many mistakes from the responsible departments such as sales, the absence of forecasting the need for goods is also a problem for the efficiency of store operational costs. This research was developed in line with the problems that are often faced at the Bali Antic Shop. Seeing this, a website-based custom clothing inventory decision support system was developed using the Tsukamoto fuzzy method. This system is applied in determining the percentage of sales with input variables of price margin, demand and existing inventory. In this research, it is proven by comparison between manual calculation and system calculation, and the result is the percentage of sales.
MARINE WASTE CLASSIFICATION USING MOMENT INVARIANTS AND NAÏVE BAYES CLASSIFIER
Imam Arief Putrajaya;
I Gede Pasek Suta Wijaya;
I Made Budii i Suksmadana
DIELEKTRIKA Vol 5 No 2 (2018): DIELEKTRIKA
Publisher : Jurusan Teknik Elektro Fakultas Teknik Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (496.086 KB)
|
DOI: 10.29303/dielektrika.v5i2 Agustus.164
People have transformed marine areas into huge garbage container where other creatures are feeding on it. Plastics as one of major waste produced by human have contaminated food chain. To date, there are no cheap or simple method for managing the waste. In this work, Naïve Bayes Classifier combined with Moment Invariants system is developed to help classifying floating waste on marine areas. This system is implemented in Java by using 2000 sample data from marine and several experimental environments. Several image processings are also used such as resizing, Otsu Thresholding and Histogram Equalization. The results obtained from the proposed system are acceptable in accuracy (69.35%) and False Positive Rate (20.52%) but unreliable False Negative Rate (61.06%). This results are due to overlapping features distribution produced from 10 ranges of Moment Invariants. Although the results are still far from good, the proposed method opens limitless improvements for the next implementations.
Fast pornographic image recognition using compact holistic features and multi-layer neural network
I Gede Pasek Suta Wijaya;
Ida Bagus Ketut Widiartha;
Keiichi Uchimura;
Muhamad Syamsu Iqbal;
Ario Yudo Husodo
International Journal of Advances in Intelligent Informatics Vol 5, No 2 (2019): July 2019
Publisher : Universitas Ahmad Dahlan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/ijain.v5i2.268
The paper presents an alternative fast pornographic image recognition using compact holistic features and multi-layer neural network (MNN). The compact holistic features of pornographic images, which are invariant features against pose and scale, is extracted by shape and frequency analysis on pornographic images under skin region of interests (ROIs). The main objective of this work is to design pornographic recognition scheme which not only can improve performances of existing methods (i.e., methods based on skin probability, scale invariant feature transform, eigenporn, and Multilayer-Perceptron and Neuro-Fuzzy (MP-NF)) but also can works fast for recognition. The experimental outcome display that our proposed system can improve 0.3% of accuracy and reduce 6.60% the false negative rate (FNR) of the best existing method (skin probability and eigenporn on YCbCr, SEP), respectively. Additionally, our proposed method also provides almost similar robust performances to the MP-NF on large size dataset. However, our proposed method needs short recognition time by about 0.021 seconds per image for both tested datasets.
Buildings Cracks Classification Using Zoning and Invariant Moment Features and Quadratic Discriminant Analysis Classifier
I Gede Pasek Suta Wijaya;
Ida Bagus Ketut Widiartha;
Fitri Bimantoro;
Aldian Wahyu Septiadi
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 10, No. 3 December 2019
Publisher : Institute for Research and Community Services, Udayana University
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (8739.257 KB)
|
DOI: 10.24843/LKJITI.2019.v10.i03.p04
Natural disasters such as earthquake often cause cracks in buildings and even demolish them. The cracked building must be assessed by an expert to determine whether the building is still suitable for use or not. The feasibility of a building is assessed based on the width, depth, and length of cracks in walls, beams, columns, and even the floor of the building. Only experienced experts can do such kind of task so that building assessment requires many structural engineering experts when an earthquake has happened. However, structural engineering experts are limited which able to do buildings assessment in the area affected. Therefore, the research based on a pattern recognition approach is conducted to classify cracks in buildings to be mild, moderate, or severe. It will be part of automatic building assessment based on the crack analysis. An alternative pattern recognition approach for classifying buildings cracks is a scheme based on zoning and shape features and Quadratic discriminant analysis (QDA) classifier. Based on the experimental results the proposed scheme gives reasonable achievement more than 80% of accuracy.
RANCANG BANGUN APLIKASI PEMBUATAN KARTU TANDA PENDUDUK NON-PERMANEN KELURAHAN PAGESANGAN BARAT BERBASIS DESKTOP: Desktop-Based Application to Make an ID Card for Non-Permanent Resident in Pagesangan Barat Sub District
Chandra Adiguna;
I Gede Pasek Suta Wijaya;
Lalu Sweta Arif
Jurnal Begawe Teknologi Informasi (JBegaTI) Vol. 1 No. 1 (2020): JBegaTI
Publisher : Program Studi Teknik Informatika, Fakultas Teknik Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (710.236 KB)
|
DOI: 10.29303/jbegati.v1i1.1
As a number of increasing a non-permanent resident in Mataram especially in Pagesangan Barat, this will also increase the number of problem like theft and robbery because of their ID are not recorded on the local government and also when a non-permanent resident got an accident when they live in Pagesangan Barat the local government can contact their parents to tell them of that accident that happened to their family in Pagesangan Barat. Therefore, based on that problem, we develop a desktop-based application to minimize that problem occur in Pagesangan Barat. This application was designed to provide some information about non-permanent resident, boarding house and this application also can make an ID card for non-permanent resident that already registered on the system. Meanwhile, for non-permanent resident that has not non-permanent resident ID card, they will not to serve by local government. The system testing technique which was used in this researd were blackbox testing. The result of blackbox testing on the application showed that all features can be run as planned.
MEMPOSTING INFORMASI PADA WEB SMKN 5 KOTA MATARAM: Posting Information on SMKN 5 Mataram Website
Belmiro Razak Setiawan;
I Gede Pasek Suta Wijaya;
Dedi Ermansyah
Jurnal Begawe Teknologi Informasi (JBegaTI) Vol. 1 No. 1 (2020): JBegaTI
Publisher : Program Studi Teknik Informatika, Fakultas Teknik Universitas Mataram
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (840.204 KB)
|
DOI: 10.29303/jbegati.v1i1.83
SMKN 5 Kota Mataram merupakan sekolah menengah kejuruan negeri dengan jurusan bidang kesenian di kota mataram. SMKN 5 kota mataram memiliki web sekolah yang berisi informasi mengenai sekolah SMKN 5. Web tersebut menggunakan wordpress, namun web tersebut belum ada informasi yang diposting sehingga masih kosong. Maka dari itu, pada PKL ini dilakukan posting terhadap web SMKN 5 kota Mataram menggunakan wordpress. Hal yang dilakukan dalam memposting di wordpress adalah memposting tulisan, file, gambar, dan menambah halaman. Kegiatan PKL tersebut berhasil dikerjakan sesuai dengan apa yang diinginkan oleh SMKN 5 kota Mataram.