Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : TELKOMNIKA (Telecommunication Computing Electronics and Control)

Quadrotor Path Planning Based on Modified Fuzzy Cell Decomposition Algorithm Iswanto Iswanto; Oyas Wahyunggoro; Adha Imam Cahyadi
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 2: June 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v14i2.2989

Abstract

The purpose of this paper is to present an algorithm to determine the shortest path for quadrotor to be able to navigate in an unknown area. The problem in robot navigation is that a robot has incapability of finding the shortest path while moving to the goal position and avoiding obstacles. Hence, a modification of several algorithms are proposed to enable the robot to reach the goal position through the shortest path. The algorithms used are fuzzy logic and cell decomposition algorithms, in which the fuzzy algorithm which is an artificial intelligence algorithm is used for robot path planning and cell decomposition algorithm is used to create a map for the robot path, but the merger of these two algorithms is still incapable of finding the shortest distance. Therefore, this paper describes a modification of the both algorithms by adding potential field algorithm that is used to provide weight values on the map in order for the quadrotor to move to its goal position and find the shortest path. The modification of the algorithms have shown that quadrotor is able to avoid various obstacles and find the shortest path so that the time required to get to the goal position is more rapid.
An Optimum Database for Isolated Word in Speech Recognition System Syifaun Nafisah; Oyas Wahyunggoro; Lukito Edi Nugroho
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 2: June 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v14i2.2353

Abstract

Speech recognition system (ASR) is a technology that allows computers receive the input using the spoken words. This technology requires sample words in the pattern matching process that is stored in the database. There is no reference as the fundamental theory to develop database in ASR. So, the research of database development to optimize the performance of the system is required.  Mel-scale frequency cepstral coefficients (MFCCs) is used to extract the characteristics of speech signal and backpropagation neural network in quantized vector is used to evaluate likelihood the maximum log values to the nearest pattern in the database.  The results shows the robustness of ASR is optimum using 140 samples of data reference for each word with an average of accuracy is 99.95% and duration process is 27.4 msec.  The investigation also reported the gender doesn’t have significantly influence to the accuracy.  From these results it concluded that the performance of ASR can be increased by optimizing the database.