Claim Missing Document
Check
Articles

Found 39 Documents
Search

HUMAN WEIGHT MEASUREMENT PREDICTION WITH VISUAL IMAGES WITH ARTIFICIAL NEURAL NETWORK ALGORITHM Abdul Basit; Imam Much Ibnu Subroto; Sri Arttini Dwi Prasetyowati
Journal of Telematics and Informatics Vol 8, No 1 (2020)
Publisher : Universitas Islam Sultan Agung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jti.v8i1.

Abstract

Measuring instrument becomes very important to be able to know how much human weight is. Weight information is generally obtained from measurements by body scale. One of other methods to find out a person's weight is by image processing. This study aims to calculate body weight by image processing with the Artificial Neural Network algorithm using back propagation method to detect body weight. The results of testing, analysis, and system accuracy of 97% indicate that the method of calculating body weight is very possible through image processing with various provisions and restrictions.   Key words: Weight, Computer Vision, Artificial Neural Network
PEMODELAN DAN SIMULASI FILTER AKTIF SHUNT UNTUK PERBAIKAN HARMONISA SEBAGAI UPAYA PENGHEMATAN ENERGI LISTRIK Luqman Assaffat; Sri Arttini D. P.; M. Haddin -
MEDIA ELEKTRIKA Vol 6, No 1 (2013): MEDIA ELEKTRIKA
Publisher : PSTE UNIMUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (552.672 KB) | DOI: 10.26714/me.6.1.2013.%p

Abstract

Salah satu metode dalam melakukan penghematan energy adalah dengan memperbaiki kualitas daya listrik. Permasalahan utama dalam kualitas daya listrik adalah permasalahan harmonisa. Harmonisa mempunyai dampak buruk pada sistem tenaga listrik, antara lain terjadinya pemanasan pada trafo, malfungsi peralatan listrik, kesalahan pembacaan pada alat ukur dan kerugian secara finansial. Pengendalian harmonisa pada sistem tenaga dapat dilakukan dengan pemasangan filter harmonisa. Terdapat beberapa jenis filter harmonisa, antara lain filter pasif dan filter aktif. Filter aktif mempunyai kemampuan yang lebih baik dari pada filter pasif karena dapat memperbaiki arus harmonisa sesuai dengan keadaan beban. Pemodelan filter aktif shunt dengan bantuan Matlab/Simulink dan Power System Blocket bertujuan untuk menganalisa berapa besar distorsi harmonisa yang dapat diperbaiki dan besarnya energy listrik yang dapat dihemat. Data simulasi menggunakan data harmonisa pada sistem tenaga listrik Rumah Sakit Panti Wilasa “Citarum” Semarang. Hasil simulasi pemodelan filter aktif shunt menunjukkan bahwa THD Harmonisa arus pada sistem dapat diturunkan sebesar rata-rata 6%. Sedangkan perkiraan energy listrik yang dapat dihemat sebesar 13.692,12 kWH selama satu tahun.
PERBANDINGAN ALGORITMA FLOODFILL DAN DJIKSTRA’S PADA MAZE MAPPING UNTUK ROBOT LINE FOLLOWER Ary Sulistyo Utomo; Sri Arttini Dwi Prasetyowati; Bustanul Arifin
Prosiding SNST Fakultas Teknik Vol 1, No 1 (2015): PROSIDING SEMINAR NASIONAL SAINS DAN TEKNOLOGI 6 2015
Publisher : Prosiding SNST Fakultas Teknik

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Robot line follower (RLF) adalah robot yang dapat berjalan mengikuti suatu maze yang berupa garis secara otomatis.RLF dapat digunakan untuk aplikasi mengantarkan barang dari suatu tempat awal ketempat tujuan dengan tepat dan akurat. Untuk menyelesaikan permasalahan tersebut dibutuhkan suatu algoritma yang digunakan untuk mencari jalur terpendek. Pada penelitian ini digunakan dua algoritma yaitu algoritma djikstra’s dan floodfill. Pengujian dilakukan dengan cara menjalankan RLF dari titik start menuju ketitik finish dan sebaliknya dengan jalur terpendek. Input RLF untuk menyusuri garis berupa photodiode berjumlah 8 buah diproses dalam mikrokontroler Atmega16 untuk mengendalikan 2 buah motor. Area yang digunakan berukuran 200 x 200 cm mempunyai tebal garis lintasan  2cm dengan jarak terdekat pada setiap simpangnya adalah 40 cm.. Warna garis adalah putih dan background berwarna hitam.Hasil penelitian menunjukkan bahwa kestabilan RLF menyusuri garis lintasan dicapai pada nilai pengaturan PIDKp=45, Ki=10 dan KD=100. Dengan pengaturan nilai tersebut masing-masing algoritma menghasilkan jarak terdekat yang sama karena maze yang digunakan sama. Tetapi proses pencarian titik finish dengan algoritma floodfill lebih cepat dibandingkan menggunakan algoritma djikstra’s. Dengan algoritma floodfill,waktu pencarian titik finish lebih cepat dan jarak tempuh lebihdekat.Persentase rata-rata efisiensi waktu floodfill terhadap djikstra’s senilai  52,65 %. Kata kunci: robot line follower, kendali PID, djikstra’s, floodfill, maze mapping
Aplikasi Mikroprosesor Tipe TMS320C6713 Untuk Penghapusan BisingSuara Kendaraan Secara Adaptif Sri Arttini Dwi Prasetyowati; Bustanul Arifin; Eka Nuryanto Budi Susila
PROSIDING CSGTEIS 2013 CSGTEIS 2013
Publisher : PROSIDING CSGTEIS 2013

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstrak- Bising kendaraan, adalah permasalahan yang sangat mngganggu bagi lingkungan yang dekat dengan lalulintas ramai. Solusi yang dikehendaki bukan berupa ruang kedap suara, namun ruang yang bebas dari bising kendaraan namun tetap mendengar suara yang dikehendaki. Penelitian ini meneruskan penelitian yang melakukan eksplorasi penghapusan bising kendaraan dengan menggunakan algoritma LMS (Least Mean Square) Adaptif, dimana dalam penelitian tersebut telah ditemukan nilai-nilai optimal dengan menggunakan dua tingkat proses. Penelitian ini membuat suatu model dalam bentuk hardware untuk menghapus bising kendaraan, tanpa harus kehilangan informasi yang diinginkan.Hardware yang digunakan adalah DSP (Digital Signal Processor) tipe TMS320C6713.Kata kunci: LMS adaptif, DSP tipe TMS320C6713, bising kendaraan
ANALISIS KORELASI DAN SPEKTRUM DATA SUARA GENSET UNTUK PEREDAMAN BISING Sri Arttini Dwi Prasetyowati; Bustanul Arifin; Agus Adhi Nugroho
JURNAL ILMIAH MOMENTUM Vol 15, No 1 (2019)
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jim.v15i1.2652

Abstract

Bising merupakan permasalahan yang seringkali terjadi dan sangat mengganggu apabila tidak diatasi. Penghapusan bising harus didasarkan pada sifat khas sumber bisingnya, yang harus ditemukan sebelum diupayakan peredaman atau penghapusannya. Dalam penelitian ini suara bising dihapus adalah suara genset yang bersifat monoton di laboratorium. Untuk dapat menghapus bising genset terlebih dahulu harus diteliti karakteristik dari sinyal bising tersebut. Adapun yang diteliti adalah korelasi, kroskorelasi, spektrum bising genset yang direkam. Perekaman dilakukan dari jarak berbeda yaitu satu dari tempat sumber dan lainnya dari ruangan yang terganggu kebisingan genset, namun dalam waktu yang sama. Spektrum dicermati dengan menggunakan Fast Fourier Transform. Kata Kunci: korelasi, spektrum, bising genset, fast fourier transform
Classification Of Alcohol Type Using Gas Sensor And K-Nearest Neighbor Munaf Ismail; Sri Arttini Dwi Prasetyowati
JURNAL NASIONAL TEKNIK ELEKTRO Vol 11, No 1: March 2022
Publisher : Jurusan Teknik Elektro Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (348.421 KB) | DOI: 10.25077/jnte.v11n1.989.2022

Abstract

Ethanol, isopropyl and methanol belong to the same alcohol group. The latter is commonly used as an industrial solvent, not for personal consumption. Many traditional alcoholic drink sellers often mix alcoholic beverages, which are commonly called as “oplosan”, this mixed drink is very dangerous for human if it contains methanol. Based on this problem, it is necessary to make a measuring device for the alcohol content in the liquid to classify the alcohol type. The design of this gas sensor-based alcohol classification system and method consists of a series of hardware and software applications. The block diagram of the alcohol classification system measures the ethanol and methanol substances in each alcoholic drink using the MQ3 gas sensor and WeMos as a data acquisition device and microcontroller. The computer was used to process the acquisition data from the gas sensor being used then calculates the K-Nearest Neighbor (K-NN) to obtain the prediction results. The K-NN system testing consists of testing the effect of the K value and testing its accuracy. The result of testing the effect of the K value produces 100% optimum accuracy at the values namely K=1, K=3, K=5, K=10 and 55% on K=20.
Emittance Quality of Terrestrial Digital Multimedia Broadcasting (TDMB) Sri Arttini Dwi Prasetyowati; Gunawan .; Aries Budiyono
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 1: EECSI 2014
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1091.294 KB) | DOI: 10.11591/eecsi.v1.387

Abstract

Television terrestrial broadcasting technology, even fix or mobile have a rapid development along with the development of digital technology. Many countries decided to move from analog TV broadcasting to digital TV broadcasting. Sultan Agung Islamic University (UNISSULA), one of the private university in Central Java had begun to develop the Terrestrial Digital Multimedia Broadcasting (TDMB), as a research to support the migration from analog TV broadcasting to digital TV broadcasting. Because of that goal, must be observed the range of the scope by testing the TDMB Transmitter in UNISSULA. The tool of the test is drive test measurements by Purposive Random Sampling on the three research area, there are, the main road in Semarang, eastern part of the transmitter, Southern part of the transmitter. The Measurement is limited to strength and quality signal.
IAES International Conference on Electrical Engineering, Computer Science and Informatics Munawar A Riyadi; Sri Arttini Dwi Prasetyowati; Tole Sutikno; Deris Stiawan
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 3: EECSI 2016
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (314.65 KB) | DOI: 10.11591/eecsi.v3.1106

Abstract

The 3rd International Conference of Electrical Engineering, Computer Science and Informatics (EECSI) 2016 was held in Semarang, Indonesia from 23th to 25thNovember, 2016. The conference was organized by Universitas Islam Sultan Agung as the host in collaboration with Universitas Diponegoro, Universitas Ahmad Dahlan and Universitas Sriwijaya, and with full technical support from IAES Indonesia Section. Authors and participants from 10 countries made the conference truly international in scope. Participants have delivered their talks of valuable research outputs that vary from many fields of electrical engineering (power electronics, telecommunication, electronics engineering, control system and signal processing) to the field of computer science and informatics. These wide range of topics have colorized this conference.This volume of IOP Conference Series: Materials Science and Engineering contains selected articles from those presented in the conference. After presentation, the revised papers were peer reviewed by fellow reviewers to ensure the quality of published materials. Finally, Editors decided to select and publish as many as 49 papers. It is hoped that the presented papers can offer more insight towards broad audience.On behalf of Editors, we appreciate enormous work of all staffs and reviewers in the preparation of this volume. We would like to express our sincere thanks to all authors and presenters for their valuable contributions. We hope to see you again in the next event of EECSI 2017 which will be held in Yogyakarta, Indonesia, next year.
Utilization of Digital Image Processing in Process of Quality Control of The Primary Packaging of Drug Using Color Normalization Method Danang Erwanto; Sri Arttini Dwi Prasetyowati; Eka Nuryanto Budi Susila
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 3: EECSI 2016
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (805.042 KB) | DOI: 10.11591/eecsi.v3.1118

Abstract

In the process of quality control, accuracy is required so that the improper drug packaging is not included into the next production process. The automatic inspection system using digital image processing can be applied to replace the manual inspection system done by humans. The image captured from the vision sensor is RGB image which is then converted into grayscale. The process of converting RGB image into grayscale image is performed using the color normalization method to spread the data of RGB colors at each pixel. From the software of image processing using the color normalization method that have been created, it shows grayscale images on the drug object which have degrees of gray higher than the grayscale image section of the background when the degree of the R, G or B color of drug is higher than the degree of the R, G, B color on the background of packaging. The determination of threshold value indicates that the binary image of the drug is white and a binary image of the background of drug packaging is black.
Investigation of Diesel’s Residual Noise on Predictive Vehicles Noise Cancelling using LMS Adaptive Algorithm Sri Arttini Dwi Prasetyowati; Adhi Susanto; Ida Widihastuti
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 3: EECSI 2016
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (910.841 KB) | DOI: 10.11591/eecsi.v3.1125

Abstract

Every noise problems require different solution. In this research, the noise that must be cancelled comes from roadway. Least Mean Square (LMS) adaptive is one of the algorithm that can be used to cancel that noise. Residual noise always appears and could not be erased completely. This research aims to know the characteristic of residual noise from vehicle’s noise and analysis so that it is no longer appearing as a problem. LMS algorithm was used to predict the vehicle’s noise and minimize the error. The distribution of the residual noise could be observed to determine the specificity of the residual noise. The statistic of the residual noise close to normal distribution with = 0,0435, = 1,13 and the autocorrelation of the residual noise forming impulse. As a conclusion the residual noise is insignificant.