Articles
<![CDATA[Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms ]]>
<![CDATA[Dewantara, Bima Sena Bayu]]>;
<![CDATA[Miura, Jun]]>
<![CDATA[ EMITTER International Journal of Engineering Technology Vol 2, No 2 (2014) ]]>
Publisher : <![CDATA[Politeknik Elektronika Negeri Surabaya (PENS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Fuzzy rule optimization is a challenging step in the development of a fuzzy model. A simple two inputs fuzzy model may have thousands of combination of fuzzy rules when it deals with large number of input variations. Intuitively and trialâerror determination of fuzzy rule is very difficult. This paper addresses the problem of optimizing Fuzzy rule using Genetic Algorithm to compensate illumination effect in face recognition. Since uneven illumination contributes negative effects to the performance of face recognition, those effects must be compensated. We have developed a novel algorithmbased on a reflectance model to compensate the effect of illumination for human face recognition. We build a pair of model from a single image and reason those modelsusing Fuzzy.Fuzzy rule, then, is optimized using Genetic Algorithm. This approachspendsless computation cost by still keepinga high performance. Based on the experimental result, we can show that our algorithm is feasiblefor recognizing desired person under variable lighting conditions with faster computation time.Keywords: Face recognition, harsh illumination, reflectance model, fuzzy, genetic algorithm]]>
<![CDATA[The Enhancement of 3 MHz Ultrasonic Echo Signal for Conversion Curve Development for Acoustic Impedance Estimation by Using Wavelet Transform ]]>
<![CDATA[Prastika, Edo Bagus]]>;
<![CDATA[Gunawan, Agus Indra]]>;
<![CDATA[Bayu Dewantara, Bima Sena]]>;
<![CDATA[Hozumi, Naohiro]]>;
<![CDATA[Prianto, Chandra Edy]]>
<![CDATA[ EMITTER International Journal of Engineering Technology Vol 6, No 1 (2018) ]]>
Publisher : <![CDATA[Politeknik Elektronika Negeri Surabaya (PENS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24003/emitter.v6i1.245
<![CDATA[Ultrasonic technology has already been used for many applications. Most of them are mainly used for object measurement. Some techniques have been widely applied to particular measurement by utilizing a very specific component. In this research, the previous technique to develop a conversion curve to obtain the acoustic impedance of the target is adopted. Then, we propose a 3 MHz concave shaped ultrasonic transducer for measuring liquids and a confirmation is needed to confirm if the system used is correct. Therefore, several saline solutions which property has been known are used. A low voltage of 10 Volt pulse is used to trigger the transducer. The ultrasonic wave is then transmitted through the multilayered mediums, which is pure water, clear acrylic, and the target. The echo from the interface between the acrylic and the target is then received by the same transducer. Some parameters such as peak and RMS are used to develop the conversion curve. A peak detection and comparison between the original echo and the processed one by using Wavelet transform (UWT and DWT) is then performed. Some analysis of the echo signal by using multiresolution and time-frequency analysis is also proposed. The result obtained from the measurement is then compared to that from the theoretical calculation. Based on the result, in terms of developing the calibration graph, only the RMS value (UWT) which has the closest trend to the result of the calculation, with the mean percentage error of 0.65512%, which is the smallest value among all parameters.]]>
<![CDATA[Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms ]]>
<![CDATA[Dewantara, Bima Sena Bayu]]>;
<![CDATA[Miura, Jun]]>
<![CDATA[ EMITTER International Journal of Engineering Technology Vol 2, No 2 (2014) ]]>
Publisher : <![CDATA[Politeknik Elektronika Negeri Surabaya (PENS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24003/emitter.v2i2.27
<![CDATA[Fuzzy rule optimization is a challenging step in the development of a fuzzy model. A simple two inputs fuzzy model may have thousands of combination of fuzzy rules when it deals with large number of input variations. Intuitively and trialâerror determination of fuzzy rule is very difficult. This paper addresses the problem of optimizing Fuzzy rule using Genetic Algorithm to compensate illumination effect in face recognition. Since uneven illumination contributes negative effects to the performance of face recognition, those effects must be compensated. We have developed a novel algorithmbased on a reflectance model to compensate the effect of illumination for human face recognition. We build a pair of model from a single image and reason those modelsusing Fuzzy.Fuzzy rule, then, is optimized using Genetic Algorithm. This approachspendsless computation cost by still keepinga high performance. Based on the experimental result, we can show that our algorithm is feasiblefor recognizing desired person under variable lighting conditions with faster computation time.Keywords: Face recognition, harsh illumination, reflectance model, fuzzy, genetic algorithm]]>
<![CDATA[Design and Implementation of Embedded Water Quality Control and Monitoring System for Indoor Shrimp Cultivation ]]>
<![CDATA[Natan, Oskar]]>;
<![CDATA[Gunawan, Agus Indra]]>;
<![CDATA[Dewantara, Bima Sena Bayu]]>
<![CDATA[ EMITTER International Journal of Engineering Technology Vol 7, No 1 (2019) ]]>
Publisher : <![CDATA[Politeknik Elektronika Negeri Surabaya (PENS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (724.62 KB)
|
DOI: 10.24003/emitter.v7i1.344
<![CDATA[Maintaining the water quality of a pond is one of the main issues on aquaculture management. Water quality represents the condition of a pond based on several water parameters such as dissolved oxygen (DO), temperature, pH, and salinity. All of these parameters need to be strictly supervised since it affects the life-sustainability of cultivated organisms. However, DO is said to be the main parameter since it affects the growth and survival rate of the shrimp. Therefore, a water quality control and monitoring system is needed to maintain water parameters at acceptable value. The system is developed on a mini-PC and microcontroller which are integrated with several sensors and actuator forming an embedded system. Then, this system is used to collect water quality data that is consisting of several water parameters and control the DO as the main parameter. In accordance with the stability needs against the sensitive environment, a fuzzy logic-based controller is developed to maintain the DO rate in the water. This system is also equipped with SIM800 module to notice the farmer by SMS, built-in wifi module for web-based data logging, and improved with Android-based graphical user interface (GUI) to perform user-friendly monitoring. From the experiment results, a fuzzy controller that is attached to the system can control the DO at the acceptable value of 6 ppm. The controller is said to have high robustness since its deviation for long-time use is only 0.12 ppm. Another test shows that the controller is able to overcome the given disturbance and easily adapt when the DO’s set point is changed. Finally, the system is able to collect and store the data into cloud storage periodically and show the data on a website.]]>
<![CDATA[Implementation of Yin Algorithm to Detect Human Voice Emotions According to Gender: Implementation of Yin Algorithm to Detect Human Voice Emotions According to Gender ]]>
<![CDATA[Aulia, Fikri]]>;
<![CDATA[Basuki, Achmad]]>;
<![CDATA[Dewantara, Bima Sena Bayu]]>
<![CDATA[ Jurnal Mantik Vol. 4 No. 1 (2020): May: Manajemen, Teknologi Informatika dan Komunikasi (Mantik) ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Computer technology and artificial intelligence experience rapid development every year, one of which is in media speech recognition. Speech recognition is a virtual digital data assistant that exists in software applications, and is used as a tool to help human needs such as communication, but is often misused by users. This study conducted a voice recording to get the difference in the sound of each human gender data. The study uses the Yin algorithm to extract data, then the sound pitching process is performed using the histogram pitch feature of the standard deviation and the mean. From this study, it was found that the pitch of men is different from women. The shape of the pitch histogram contours is similar between men and women but the female pitch histogram shifts to a higher frequency than men. This pitch shift in women occurs in all expressions.]]>
<![CDATA[Studi Analisi Konsentrasi Warna Pada Cairan Pewarna Makanan Dengan Metode Pengukuran Optical Density ]]>
<![CDATA[Onie Meiyanto]]>;
<![CDATA[Agus Indra Gunawan]]>;
<![CDATA[Bima Sena Bayu Dewantara]]>
<![CDATA[ BRILIANT: Jurnal Riset dan Konseptual Vol 6 No 4 (2021): Volume 6 Nomor 4, November 2021 ]]>
Publisher : <![CDATA[Universitas Nahdlatul Ulama Blitar ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1307.714 KB)
|
DOI: 10.28926/briliant.v6i4.718
<![CDATA[Metode Image Processing banyak diimplementasikan untuk mengidetifikasi suatu bentuk atau perubahan pada gambar untuk mendapatkan hasil identifikasi suatu percobaan. Dalam penelitian ini perpaduan Image Processing, optical density(OD) dan sensor rgb untuk menentukan kualitas campuran air yang didapatkan nilai komposisi cairan warna. Karakteristik warna dari sampel air diperoleh dari histogram pada gambar yang tertangkap oleh mikroskop digital, dari histogram warna dapat diperoleh nilai max dan mean dan hasil gambar dari difraksi oleh kamera digital serta nilai output sensor rgb. Dengan metode tersebut diperoleh hasil setiap sampel yang telah di encerkan memiliki karakteristik warna yang berbeda-beda, hal ini dapat dilihat dari setiap kanal warna dari output sensor. Pengolahan data dengan metode histogram untuk dilakukan proses pengambilan nilai rata-rata(mean) dan nilai maksimum(Max) diperoleh model untuk memprediksi jenis dan konsentrasi dari sampel, pengujian yang telah dilakukan, didapatkan hasil grafik yang sigifikan sesuai dengan komposisi kualitas air dengan pewarna makanan]]>
<![CDATA[Responsive Motion Control for Robot Soccer Navigation Using Adaptive Social Force Framework ]]>
<![CDATA[Bima Sena Bayu Dewantara]]>;
<![CDATA[Bagus Nugraha Deby Ariyadi]]>;
<![CDATA[Hary Oktavianto]]>
<![CDATA[ Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 9, No 3: September 2021 ]]>
Publisher : <![CDATA[IAES Indonesian Section ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52549/.v9i3.2859
<![CDATA[This paper presents a modified Social Force Model (SFM) for navigation control of a soccer robot application. We modified the way of determining the parameter value of the gain factor, , of the SFM using the Fuzzy Inference System (FIS), so that the value of the gain factor, , is adaptive. The purpose of the gain factor adaptation is that the robot can move responsively but not over-reactive when it encounters an obstacle at high speed, which is a weakness of SFM with fixed parameters. Modification of SFM parameters using FIS is hereinafter referred to as the Fuzzy-based Social Force Model (F-SFM). We used this technique on a soccer robot with an omnidirectional drive platform with three motors. As an experiment, several modifications to the FIS rules were made and compared to the SFM with fixed parameters. The simulation-based experimental results show that the proposed method outperforms the SFM method with fixed-parameters, and the computation time does not differ significantly so that it can be applied for real implementation.]]>
<![CDATA[Segmentasi Pertumbuhan Padi berbasis Aerial Image menggunakan Fitur Warna dan Tekstur untuk Estimasi Produksi Hasil Panen ]]>
<![CDATA[Muhammad Jainal Arifin]]>;
<![CDATA[Achmad Basuki]]>;
<![CDATA[Bima Sena Bayu Dewantara]]>
<![CDATA[ Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8 No 1: Februari 2021 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.25126/jtiik.0813438
<![CDATA[Pertumbuhan padi di daerah yang luas seringkali tidak ideal. Ini dapat disebabkan oleh faktor alam, jenis varietas padi, dan model perawatan yang digunakan. Ini juga akan mempengaruhi hasil panen. Luasnya lahan membuat petani sulit untuk memantau bagian yang tidak terjangkau. Seringkali pemantauan perkembangan padi dilakukan di tepi sawah tetapi tidak mencapai area tengah. Studi ini mengusulkan sistem pemantauan untuk pengembangan padi yang dapat menjangkau secara lebih luas dan memperkirakan hasil padi di setiap area lahan pertanian. Sistem ini menggunakan gambar udara untuk menjangkau area yang lebih luas dan kemudian memperkirakan produksi pertanian. Estimasi produksi dilakukan dengan mengelompokkan gambar kawasan pertanian menggunakan metode K-Means. Pengelompokan ini menggunakan parameter warna HSV dan tekstur Gabor sebagai fitur dari setiap bagian gambar. Hasilnya adalah segmen area padi berdasarkan pertumbuhannya. Jumlah segmen yang sesuai dengan usia Padi nyata akan menentukan nilai estimasi hasil. Penelitian menunjukkan bahwa tiga segmen pengembangan padi, dan memperkirakan produksi adalah 1.787 ton dengan perkiraan panen maksimum 1.924 ton dari data nyata 1,80 ton. Dan dengan skala kesalahan persentase rata-rata absolut 0,72% dan perbedaan 0,013 ton. AbstractPaddy growth in large areas is often not ideal. This can be caused by natural factors, types of rice varieties, and the treatment model used. This will also affect crop yields. The extent of land makes it difficult for farmers to monitor the unreachable part. Often monitoring of rice developments is done on the edge of the field but does not reach the middle area. This study proposes a monitoring system for rice development that can reach more broadly and estimate the yield of rice in every area of agriculture land. This system uses aerial images to reach a wider area and then estimates of agricultural production. Estimation of production is done by clustering images of agricultural areas using the K-Means method. This clustering uses HSV color parameters and Gabor textures as features of each part of the image. The result is a segment of the paddy area based on its growth. The number of segments corresponding to the age of the real Paddy will determine the estimated value of the yield. The research shows that three segments of rice development, and estimates the production is 1,787 tons with a maximum estimated harvest of 1,924 tons from the real data of 1, 80 tons. And with a mean absolute percentage error scale of 0.72% and a difference of 0.013 tons.]]>
<![CDATA[PERENCANAAN JALUR MOBILE ROBOT PADA LINGKUNGAN DINAMIS BERBASIS COMPACT GENETIC ALGORITHM ]]>
<![CDATA[Bima Sena Bayu Dewantara]]>;
<![CDATA[Djoko Purwanto]]>
<![CDATA[ Seminar Nasional Informatika (SEMNASIF) Vol 1, No 2 (2009): Instrumentational And Robotic ]]>
Publisher : <![CDATA[Jurusan Teknik Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Permasalahan yang timbul pada sebuah pencarian dan pembentukan jalur optimal pada sebuah mobile robot adalah kemampuan untuk menghindarkan diri dari halangan, kecepatan algoritma dan jarak jalur yang dibentuk. Beberapa metode sebelumnya : novel (seperti Adaptif Path Planner, Potential Field Method, Road Map dan Djikstra) kebanyakan hanya mampu menyelesaikan dua diantara ketiga parameter yang dipersyaratkan tersebut, yaitu kecepatan algoritma dan kemampuan menghindari tumbukan. Sedangkan Algoritma Genetika juga hanya mampu menyelesaikan dua parameter yaitu kemampuan menghindari tumbukan dan jarak terpendek, namun gagal di kecepatan algoritma sehingga sulit untuk dijadikan sebuah sistem online. Untuk itu perlu digunakan sebuah sistem baru yang lebih cepat namun tetap mampu menghindari halangan dan jarak terpendek tercapai, yaitu dengan Algoritma Genetika Kompak (cGA). Penelitian ini diawali dengan mengidentifikasi area kosong dan halangan (obstacle) yang bersifat dinamis dimana posisinya dalam area dapat berpindah. Setelah area dan halangan diketahui, maka Algoritma Genetika Kompak (cGA) akan mulai membangun jalur terpendek dan paling aman (tidak menumbuk halangan) dengan memanfaatkan beberapa via point yang diberikan secara acak diluar area halangan (obstacle). Setelah jalur dengan jarak terpendek dan teraman ditemukan, maka sebuah simulator robot akan berjalan sebagai visualisasi gerakan yang menggambarkan gerakan pada robot sesungguhnya. Dengan menggunakan metode cGA yang telah diaplikasikan pada sistem, diperoleh hasil yang sama dengan Algoritma Genetika konvensional dalam hal penghindaran halangan dan jarak yang diperoleh adalah yang terpendek, serta satu lagi parameter waktu pencarian solusi yang lebih cepat.]]>
<![CDATA[Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms ]]>
<![CDATA[Bima Sena Bayu Dewantara]]>;
<![CDATA[Jun Miura]]>
<![CDATA[ EMITTER International Journal of Engineering Technology Vol 2 No 2 (2014) ]]>
Publisher : <![CDATA[Politeknik Elektronika Negeri Surabaya (PENS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24003/emitter.v2i2.27
<![CDATA[Fuzzy rule optimization is a challenging step in the development of a fuzzy model. A simple two inputs fuzzy model may have thousands of combination of fuzzy rules when it deals with large number of input variations. Intuitively and trialâ€error determination of fuzzy rule is very difficult. This paper addresses the problem of optimizing Fuzzy rule using Genetic Algorithm to compensate illumination effect in face recognition. Since uneven illumination contributes negative effects to the performance of face recognition, those effects must be compensated. We have developed a novel algorithmbased on a reflectance model to compensate the effect of illumination for human face recognition. We build a pair of model from a single image and reason those modelsusing Fuzzy.Fuzzy rule, then, is optimized using Genetic Algorithm. This approachspendsless computation cost by still keepinga high performance. Based on the experimental result, we can show that our algorithm is feasiblefor recognizing desired person under variable lighting conditions with faster computation time.Keywords: Face recognition, harsh illumination, reflectance model, fuzzy, genetic algorithm]]>
