Articles

Found 28 Documents
Search

Penerapan Algoritma Levenberg-Marquadt dan Backpropagation Neural Network Untuk Klasifikasi Suara Manusia

Jurnal Buana Informatika Vol 4, No 1 (2013): Jurnal Buana Informatika Volume 4 Nomor 1 Januari 2013
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Original Source | Check in Google Scholar

Abstract

Abstract. Voice recognition technology is currently experiencing growth, especially in the case of speech processing. Speech processing is a way to extract the desired information from a voice signal. This study discusses the classification of human voice system male and female. Extract the characteristics of the voice signal in each frame time domain and frequency domain is to help simplify and speed calculations. The features for voice or other audio between Short Time Energy, Zero Crossing Rate, Spectral Centroid, and others. Test results show that the classification system the human voice using the backpropagation neural network and Levenberg-Marquadt algorithm to change matrix weight is very good because of the complexity and rapid calculation which is not too high. Database voice sample of 40 voices with the test data as much as 5 votes. The output of the system is the result of the classification that has been identified with a similarity value>=0.5 for male and <0.5 as a female. Testing using artificial neural network produced an average success rate in voice classification amounted to 91%.Keywords: Feature Extraction, Classification, Backpropagation, Levenberg-Marquadt Algorithm, Human Voice Abstrak. Teknologi pengenalan suara saat ini telah mengalami perkembangan terutama dalam hal speech processing. Speech processing merupakan suatu cara untuk mengekstrak informasi yang diinginkan dari sebuah sinyal suara. Penelitian ini membahas sistem klasifikasi suara manusia male dan female. Mengekstrak ciri dari sinyal suara setiap frame pada kawasan waktu dan kawasan frekuensi sangat membantu untuk  menyederhanakan dan mempercepat perhitungan. Adapun fitur-fitur untuk suara atau audio antara lain Short Time Energy, Zero Crossing Rate, Spectral Centroid dan lain-lain. Hasil pengujian sistem menunjukkan bahwa klasifikasi suara manusia dengan menggunakan jaringan saraf tiruan backpropagation dan algoritma Levenberg-Marquadt untuk perubahan matriks bobot, sangat baik dan cepat karena kompleksitas perhitungan yang tidak terlalu tinggi. Database sample suara sebanyak 40 buah dengan data test sebanyak 5 suara. Output dari sistem adalah hasil klasifikasi yang telah dikenali dengan nilai kemiripan >= 0,5 sebagai pria dan < 0,5 sebagai wanita. Pengujian dengan menggunakan jaringan saraf tiruan dihasilkan rata-rata tingkat keberhasilan dalam klasifikasi suara adalah sebesar 91 %.Kata Kunci: Feature Extraction, Klasifikasi, Backpropagation, Algoritma Levenberg-Marquadt, Suara Manusia

PENERAPAN ALGORITMA JARINGAN SARAF TIRUAN BACKPROPAGATION UNTUK PENGENALAN POLA TANDA TANGAN

Jurnal Teknologi Vol 6, No 2 (2013): Edisi Desember 2013
Publisher : Jurnal Teknologi

Show Abstract | Original Source | Check in Google Scholar

Abstract

This paper discusses the process of signature identification using computer by implementing the artificial neural network of backpropagation and the function of activation using sigmoid biner by initializing small random numbers for weights and biases, and value range generated between 0 and 1. The method of analysis and its design use Object-Oriented Analysis and Design (OOAD) through the approach of Prototype and its test uses black box. This application receives the input of signature pattern using digital image in the format of bmp, jpg, png, gif and tif sized in 300 x 300 pixels or the signature pattern directly drawn by using mouse in a specified area. The architecture of artificial neural network of backpropagation is 400 nodes of input layer, 50 nodes of hidden layer and 4 nodes of output layer.Keywords:         Signature pattern, artificial neural network of backpropagation, sigmoid biner, object-oriented analysis and design, prototype, black box 

Perubahan warna lempeng resin akrilik yang direndam dalam larutan desinfektan sodium hipoklorit dan klorhexidin (The color changes of acrylic resins denture base material which are immersed in Sodium hypochlorite and chlorhexidine)

Dental Journal (Majalah Kedokteran Gigi) Vol 38, No 1 (2005): (March 2005)
Publisher : Faculty of Dental Medicine, Universitas Airlangga

Show Abstract | Original Source | Check in Google Scholar

Abstract

One of the acrylic resins properties is the water absorption including color fluids and chemically fluids that affect on the color changes of the acrylic resins. This laboratory experiments studied sodium hypochlorite and chlorhexidine effect on the color changes of acrylic denture base resins material. The study was conducted by immersing heat cured acrylic plate samples of 26 mm of diameter and 0.4 mm of thickness in sodium hypochlorite for 10; 70 and 140 minutes and chlorhexidine for 15; 105 and 210 minutes. Seven samples were used for each experiment. An optical spectrometer BPX-47 type photo cell and a digital microvoltage were used for the color changes observation. The statistical test used were t-test, One-way ANOVA and LSD with 0.05 significance degree level. The results of the studied showed that the color of acrylic resins denture base plate changed after immersion in sodium hypochlorite for 70 and 140 minutes and chlorhexidine for 105 and 210 minute of immersion.

Sistem Pakar Diagnosa Penyakit Ikan Lele Dumbo

Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) 2015
Publisher : Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (626.261 KB)

Abstract

Sistem pakar dapat dijadikan sebagai sarana untuk konsultasi dan membantu para pakar dan peternak ikan lele dumbo yang sedang mengalami permasalahan dalam mengidentifikasi penyakit pada ikan lele dumbo beserta solusi. Agar sistem pakar ini dapat diakses dengan mudah oleh siapapun dan dimanapun yang terhubung dengan jaringan internet, sistem pakar ini dibuat berbasis web (web-based). Database MySQL yang digunakan dalam sistem ini akan menyimpan fakta-fakta yang di bangun dengan menggunakan bahasa pemograman PHP. Begitu juga dengan pengembangan sistem hanya terbatas pada mendiagnosa penyakit ikan lele dumbo. Output dari sistem ini berupa informasi penyakit pada ikan lele dumbo serta cara penanganannya. Bentuk penelitian yang digunakan penulis adalah studi literature dan diaplikasikan dengan riset eksperimental. Metode pengembangan perangkat lunak yang digunakan penulis adalah menggunakan metode Prototype. Knowledge base yang digunakan terdiri dari rules dengan menggunakan inference engine forward chaining. penelusuran rule menggunakan working memory dan production rule. Hasil penelitian yang telah dibuat, didapatkan bahwa website beserta sitem pakar ini memudahkan bagi orang awam atau pemula untuk membudidayakan ikan lele dumbo agar bisa menghasilkan ikan lele yang sehat dan unggul.

Hubungan Keterlambatan Kedatangan Dokter terhadap Kepuasan Pasien di Instalasi Rawat Jalan

Jurnal Kedokteran Brawijaya Vol 28, No 1 (2014)
Publisher : Fakultas Kedokteran Universitas Brawijaya

Show Abstract | Original Source | Check in Google Scholar

Abstract

Kepuasan pasien merupakan tujuan utama pelayanan kesehatan. Salah satu indikator mutu pelayanan di instalasi rawat jalan rumah sakit adalah ketepatan kedatangan dokter sesuai dengan waktu yang telah ditentukan oleh rumah sakit. Tujuan penelitian ini adalah untuk menilai pengaruh kepuasan pasien di instalasi rawat jalan terhadap keterlambatan jam kedatangan dokter sesuai dengan jadwal yang tertera. Penelitian ini menggunakan metode kuantitatif korelasional dengan pendekatan cross sectional. Instrumen penelitian menggunakan kuesioner daftar tilik yang telah dilakukan uji validitas dan reliabilitas dengan tambahan pertanyaan terbuka untuk saran. Secara keseluruhan pasien yang puas hanya 14% dan cukup puas 60%. Ketidakpuasan tertinggi (>50%) didapatkan pada aspek keterlambatan dokter dan permintaan maaf dari dokter ketika terlambat. Hasil menunjukkan hubungan yang kuat antara kepuasan pasien dengan ketepatan jam kedatangan dokter di instalasi rawat jalan rumah sakit (p<0,001). Beberapa solusi untuk meningkatkan kepuasan pasien adalah dengan meningkatkan kenyamanan ruang tunggu dan melakukan penjadwalan ulang jam praktek dokter.Kata Kunci: Kepuasan pasien, keterlambatan dokter

SIMULASI ELECTRONIC ROAD PRICING BERBASIS GLOBAL POSITIONING SYSTEM

JETri Jurnal Ilmiah Teknik Elektro JETri Volume 12, Nomor 1, Agustus 2014
Publisher : Jurusan Teknik Elektro Fakultas Teknologi Industri Universitas Trisakti

Show Abstract | Original Source | Check in Google Scholar

Abstract

Electronic Road Pricing system is a system that uses GIS technology (Geographic Information System) which serves to locate the vehicle. This project is an ERP (Electronic Road Pricing) system concept simulation based on GPS (Global Positioning System). Rapsberry Pi attached with the GPS sensor has been used to replace the OBU (On Board Unit) so it can receive the GPS signal which will be proceed into coordinates. Those coordinates will be sent to the server and stored into a database. The database served as a storage for user which accessible so that it becomes closer to user (user friendly). An email notification as a feedback system has been used to notify the user that he has entered a paying zone and the money transaction has been made. The simulation test shown that the data obtained was not accurate due to the accuracy of GPS sensor about 10 m. An improvement process has been made to the coordinate data using Polynomial Interpolation approach, so it can be improved by 0.6 m from the maximum missed distances 4.2 m to 3.6 m. Keywords: ERP, GPS, OBU, Rapsberry Pi, Data BaseSistem pembiayaan jalan elektronik adalah sebuah sistem yang menggunakan teknologi GIS (Geographic Information System) untuk mengetahui lokasi kendaraan. Simulasi penelitian dengan konsep ERP (Electronic Road Pricing) berbasis GPS (Global Positioning System). Raspberry Pi yang disambungkan pada sensor GPS berfungsi untuk menggantikan OBU (On Board Unit) sehingga dapat menerima sinyal GPS dan mengubahnya ke dalam bentuk koordinat. Koordinat-koordinat tersebut akan dikirim ke sebuah server dan disimpan pada basis data. Basis data digunakan sebagai tempat penyimpan data sehingga dengan mudah dapat digunakan oleh pengguna. Untuk memberitahu pengguna bahwa ia telah memasuki daerah berbayar dan telah terjadi transaksi keuangan digunakan notifikasi email. Dari pengujian simulasi diketahui bahwa data yang didapat tidak tepat karena ketelitian sensor GPS sekitar 10 m. Perbaikan data koordinat dibuat dengan cara pendekatan interpolasi polinomial sehingga koordinat dapat diperbaiki dengan ketelitian sampai 0,6 m dari selisih jarak 3,6 m sampai 4,2 m. Kata kunci: ERP, GPS, OBU, Rapsberry Pi, Basis Data

RESPON KELANGSUNGAN HIDUP DAN PERTUMBUHAN LARVA TERHADAP PADAT TEBAR IKAN TAMBAKAN (Hellostoma temmincki. C.V)

Jurnal Ilmiah Universitas Batanghari Jambi Vol 14, No 4 (2014): Desember
Publisher : Jurnal Ilmiah Universitas Batanghari Jambi

Show Abstract | Original Source | Check in Google Scholar | Full PDF (170.632 KB)

Abstract

Fish Tambakan (H. temmincki. CV) is one of the freshwater fish species from the tropics, precisely Southeast Asia. Currently the presence of fish gouramis (H. temmincki. CV) already scarce, and threatened that should be preserved. One effort that can be done to preserve this fish is through cultivation, Density is closely related to the production and the expected growth rate of fish. Activities carried out for 5 months, in hectery Fish Seed Center (BBI) Tempino, District Mestong, Kabupten Muaro. Test fish are fish larvae Tambakan (H. temmincki. CV) of 71 400 individuals. The container used is aquarium measuring 42.5 x 40 x 40 cm, with a height of 10 cm of water as much as 12 aquariums. This research is a design environment completely randomized design (CRD) with 4 treatments and 3 Deuteronomy. The results of this study to the best stocking density is treatment A (200 individuals / liter) which resulted in the percentage of survival of the highest of 86.21%., Average length and weight growth - average yield growth of average length - average 1.50 cm / tail and average weight - average 0159 g / tail and average daily growth - average 0.00396 grams / tail.Keywords: Kissing gourami (Hellostoma temmincki. CV), Solid stocking

Evaluation of the oral toxicity of formaldehyde in rats

Universa Medicina Vol 27, No 3 (2008)
Publisher : Faculty of Medicine, Trisakti University

Show Abstract | Original Source | Check in Google Scholar

Abstract

Formaldehyde is used in the production of plywood, particleboard, a wide variety of molded or extruded plastic items, and for preserving cadavers. Experimental posttest only control group design was used to determine the histopathological changes of rat stomach tissue exposed to formaldehyde for 12 weeks in thirty adult female Sprague-Dawley rats weighing 150–200 g. The animals were randomized into three groups, namely the control group, the treatment group given 4 mg/L of formaldehyde, and the group treated with 6 mg/L of formaldehyde. The results showed that there was a significant difference in the thickness of the mucous layer of the gastric fundus between the control group and the group treated with 6 mg/L (p = 0.011), and also a significant difference in the thickness of the mucous layer of the gastric fundus between both treatment groups (4 mg/L vs. 6 mg/L) (p = 0.003), indicating that there was necrosis of the superficial layers of the gastric mucosa due to high concentrations of formaldehyde. In histopathology sections from all groups, similar changes were observed in both treatment groups, in the form of vacuolar (hydropic) degeneration of gastric fundus glands. In conclusion, administration of formaldehyde in drinking-water for 12 weeks caused histopathologic effects on the gastric mucosa in rats.

PERBANDINGAN ALGORITMA MINIMAX DAN NEGASCOUT PADA PERMAINAN CATUR SEDERHANA

Informatika Mulawarman Vol 8, No 2 (2013): 2013: Vol 8 No 2
Publisher : Mulawarman University

Show Abstract | Original Source | Check in Google Scholar | Full PDF (328.89 KB)

Abstract

Simple Chess is a board game played by two players using boards sized in 3 rows and 3 columns and each player has pawns with different colors (normally black and white). The player wins if he/she can arrange the pawns in one line (diagonal, vertical or horizontal). The writer makes the comparisons of negascout algorithm and minimax algorithm in the application of Simple Chess to maximize the more suitable algorithm and implement them on the pawn placements in the shortest time. This research applies experimental method in form of literature study. The aspects of this research cover required features such as interface, input validation and output design. The result of this design is the application of Simple Chess embedded in negasc out algorithm and minimax algorithm. The tests used by White Box are Input, Output, program functions, and the speed of negascout algorithm and minimax algorithm in the pawn placements in Simple Chess. After being tested, the result shows that each algorithm has its own advantages and disadvantages, in which tests are done through pawn placements with the fastest time. After the comparison tests are finished, the writer concludes that in this research, minimax algorithm has a better pawn movement time in placements, whereas negascout algorithm has a better step decision.

Robot Scanner Gambar Menggunakan Intensitas Cahaya

Creative Information Technology Journal Vol 1, No 3 (2014): Mei - Juli
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Original Source | Check in Google Scholar | Full PDF (700.432 KB)

Abstract

Banyak teknologi robot yang dapat digunakan untuk meniru mesin-mesin dengan kemampuan digitalisasi. Salah satu teknologi robot yang terkenal sekarang adalah Lego Mindstorms NXT 2.0 dengan platform Mindstorm NXT-G. Pada Penelitian ini, dirakit dan dikodekan program sebuah robot scanner menggunakan intensitas cahaya. Metode yang digunakan adalah metode Mindstorms dengan robot Lego Minstorms NXT 2.0. Metode ini adalah metode sederhana yang terdiri dari empat tahapan yaitu mencari ide untuk robot, membangun robot, memprogram robot dan dokumentasi. Pemrograman robot dengan menggunakan bahasa pemrograman NXT-G digunakan untuk mendapatkan program yang bekerja terbaik. Pengujian V-model akan digunakan untuk menguji program utama. Robot yang dibuat dengan menggunakan Lego Mindstorms NXT 2.0 dapat melakukan scanning pada gambar dengan output pada Layar NXT Brick. Robot dapat membedakan warna berdasarkan intensitas cahaya yang dipantulkan. Sensor warna mendeteksi pantulan infra merah pada permukaan kertas yang berwarna dengan intensitas tertentu. Hasil pendeteksian disimpan dalam memory dan sebagai pusat kendali dari robot ini menggunakan NXT Brick yang sudah termasuk dalam paket LEGO MINDSTORMS NXT 2.0.A lot of Robot technology that can be used to act like machines with digital ability. Nowadays, one of the famous robot technology is Lego Mindstorms NXT 2.0 with Mindstorm NXT-G platform. In this research, created and coded by program, a scanner robot uses light intensity. Method that being used is Mindstorms method with Lego Mindstorms NXT 2.0. robot. This method is a simple method with four steps. They are find the idea for the robot, construct the robot, program the robot and documentation. Robot programming with NXT-G programming language is use to get the best working program. V-Model test will be use to test the main program. Robot that being created with Lego Mindstorms NXT 2.0 can do scanning to an image with output from the NXT brick screen. Robot can differentiate colors base on light intensity that has been reflected. Color censor detect infrared reflection at the colored paper surface with certain intensity. Result of the detection is being saved into memory and as the control center from this robot, it uses NXT brick that has been included in the LEGO MINDSTORMS NXT 2.0. package.