cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yuliah Qotimah
Contact Email
yuliah@lppm.itb.ac.id
Phone
+622286010080
Journal Mail Official
jictra@lppm.itb.ac.id
Editorial Address
LPPM - ITB Center for Research and Community Services (CRCS) Building Floor 6th Jl. Ganesha No. 10 Bandung 40132, Indonesia Telp. +62-22-86010080 Fax. +62-22-86010051
Location
Kota bandung,
Jawa barat
INDONESIA
Journal of ICT Research and Applications
Published by Institut Teknologi Bandung
ISSN : 23375787     EISSN : 23385499     DOI : https://doi.org/10.5614/itbj.ict.res.appl.
Core Subject : Science,
Computer Science & IT
Journal of ICT Research and Applications welcomes full research articles in the area of Information and Communication Technology from the following subject areas: Information Theory, Signal Processing, Electronics, Computer Network, Telecommunication, Wireless & Mobile Computing, Internet Technology, Multimedia, Software Engineering, Computer Science, Information System and Knowledge Management.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 302 Documents
 8   9   10   11   12 
New Grapheme Generation Rules for Two-Stage Modelbased Grapheme-to-Phoneme Conversion Seng Kheang; Kouichi Katsurada; Yurie Iribe; Tsuneo Nitta
Journal of ICT Research and Applications Vol. 8 No. 2 (2014)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2014.8.2.6

Abstract

The precise conversion of arbitrary text into its  corresponding phoneme sequence (grapheme-to-phoneme or G2P conversion) is implemented in speech synthesis and recognition, pronunciation learning software, spoken term detection and spoken document retrieval systems. Because the quality of this module plays an important role in the performance of such systems and many problems regarding G2P conversion have been reported, we propose a novel two-stage model-based approach, which is implemented using an existing weighted finite-state transducer-based G2P conversion framework, to improve the performance of the G2P conversion model. The first-stage model is built for automatic conversion of words  to phonemes, while  the second-stage  model utilizes the input graphemes and output phonemes obtained from the first stage to determine the best final output phoneme sequence. Additionally, we designed new grapheme generation rules, which enable extra detail for the vowel and consonant graphemes appearing within a word. When compared with previous approaches, the evaluation results indicate that our approach using rules focusing on the vowel graphemes slightly improved the accuracy of the out-of-vocabulary dataset and consistently increased the accuracy of the in-vocabulary dataset.
Effect of 3 Key Factors on Average End to End Delay and Jitter in MANET Saqib Hakak; Suhaimi Abd Latif; Farhat Anwar; M K Alam; Gulshan Gilkar
Journal of ICT Research and Applications Vol. 8 No. 2 (2014)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2014.8.2.3

Abstract

A mobile ad-hoc network (MANET) is a self-configuring infrastructure-less network of mobile devices connected by wireless links where each node or mobile device is independent to move in any desired direction and thus the links keep moving from one node to another. In such a network, the mobile nodes are equipped with CSMA/CA (carrier sense multiple access with collision avoidance) transceivers and communicate with each other via radio. In MANETs, routing is considered one of the most difficult and challenging tasks. Because of this, most studies on MANETs have focused on comparing protocols under varying network conditions. But to the best of our knowledge no one has studied the effect of other factors on network performance indicators like throughput, jitter and so on, revealing how much influence a particular factor or group of factors has on each network performance indicator. Thus, in this study the effects of three key factors, i.e. routing protocol, packet size and DSSS rate, were evaluated on key network performance metrics, i.e. average delay and average jitter, as these parameters are crucial for network performance and directly affect the buffering requirements for all video devices and downstream networks.
Prediction Method for Rain Rate and Rain Propagation Attenuation for K-Band Satellite Communications Links in Tropical Areas Baso Maruddani; Adit Kurniawan; Sugihartono Sugihartono; Achmad Munir
Journal of ICT Research and Applications Vol. 8 No. 2 (2014)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2014.8.2.1

Abstract

This paper deals with the prediction method using hidden Markov model (HMM) for rain rate and rain propagation attenuation for K-band satellite communication link at tropical area. As is well known, the K-band frequency is susceptible of being affected by atmospheric condition, especially in rainy condition. The wavelength of K-band frequency which approaches to the size of rain droplet causes the signal strength is easily attenuated and absorbed by the rain droplet. In order to keep the quality of system performance for K-band satellite communication link, therefore a special attention has to be paid for rain rate and rain propagation attenuation. Thus, a prediction method for rain rate and rain propagation attenuation based on HMM is developed to process the measurement data. The measured and predicted data are then compared with the ITU-R recommendation. From the result, it is shown that the measured and predicted data show similarity with the model of ITU-R P.837-5 recommendation for rain rate and the model of ITU-R P.618-10 recommendation for rain propagation attenuation. Meanwhile, statistical data for measured and predicted data such as fade duration and interfade duration have insignificant discrepancy with the model of ITU-R P.1623-1 recommendation.
Handwritten Javanese Character Recognition Using Several Artificial Neural Network Methods Gregorius Satia Budhi; Rudy Adipranata
Journal of ICT Research and Applications Vol. 8 No. 3 (2015)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2015.8.3.2

Abstract

Javanese characters are traditional characters that are used to write the Javanese language. The Javanese language is a language used by many people on the island of Java, Indonesia. The use of Javanese characters is diminishing more and more because of the difficulty of studying the Javanese characters themselves. The Javanese character set consists of basic characters, numbers, complementary characters, and so on. In this research we have developed a system to recognize Javanese characters. Input for the system is a digital image containing several handwritten Javanese characters. Preprocessing and segmentation are performed on the input image to get each character. For each character, feature extraction is done using the ICZ-ZCZ method. The output from feature extraction will become input for an artificial neural network. We used several artificial neural networks, namely a bidirectional associative memory network, a counterpropagation network, an evolutionary network, a backpropagation network, and a backpropagation network combined with chi2. From the experimental results it can be seen that the combination of chi2 and backpropagation achieved better recognition accuracy than the other methods.
Exploring the Possibility of Semi-Automated Quality Evaluation of Spatial Datasets in Spatial Data Infrastructure Amin Mobasheri
Journal of ICT Research and Applications Vol. 7 No. 1 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.1.1

Abstract

Over the past decades, World Wide Web technology has developed greatly. One of the most important outcomes of this technology is to share data in a worldwide domain. A considerable amount of available data have spatial components and are hence called spatial data. The level of quality that spatial datasets conform plays an important role in their reliability for use in projects. This research aims to overview spatial data quality elements and select appropriate elements suitable for means of semi-automated quality evaluation. In this paper, the ISO 19100 series of standards for geographic information is used as basis for quality evaluation. The possibilities of use of different spatial data quality elements for semi-automated quality evaluation are explored and discussed. Finally, based on argumentation and reference to other research studies, a list of spatial data quality elements and sub-elements suitable for semi-automated quality evaluation of spatial datasets are presented.
Performance Analysis of a Reconfigurable Shared Memory Multiprocessor System for Embedded Applications Darcy Cook; Ken Ferens
Journal of ICT Research and Applications Vol. 7 No. 1 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.1.2

Abstract

This paper presents a method to predict performance of multiple processor cores in a reconfigurable system for embedded applications. A multiprocessor framework is developed with the capability of reconfigurable processors in a shared memory system optimized for stream-oriented data and signal processing applications. The framework features a discrete time Markov based stochastic tool, which is used to analyze memory contention in the shared memory architecture, and to predict the performance increase (speed of execution) when the number of processors is varied. Performance predictions for variations of other system parameters, such as different task allocations and the number of pipeline stages are possible as well. The results of the prediction tool were verified by experimental results of a green screen application developed and run on a Xilinx Virtex-II Pro FPGA with MicroBlaze soft processors.
Question Classification Using Extreme Learning Machine on Semantic Features H. Hardy; Yu-N Cheah
Journal of ICT Research and Applications Vol. 7 No. 1 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.1.3

Abstract

In statistical machine learning approaches for question classification, efforts based on lexical feature space require high computation power and complex data structures. This is due to the large number of unique words (or high dimensionality). Choosing semantic features instead could significantly reduce the dimensionality of the feature space. This article describes the use of Extreme Learning Machine (ELM) for question classification based on semantic features to improve both the training and testing speeds compared to the benchmark Support Vector Machine (SVM) classifier. Improvements have also been made to the head word extraction and word sense disambiguation processes. These have resulted in a higher accuracy (an increase of 0.2%) for the classification of coarse classes compared to the benchmark. For the fine classes, however, there is a 1.0% decrease in accuracy but is compensated by a significant increase in speed (92.1% on average).
Improved Performance of Mean Greedy Algorithm for Chunk Allocation in SC-FDMA Uplink Systems using Joint-User and Chunk-Based Allocation Arfianto Fahmi; Muhamad Asvial; Dadang Gunawan
Journal of ICT Research and Applications Vol. 7 No. 1 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.1.4

Abstract

In this paper, the problem of subcarrier allocation on chunk-by-chunk basis in SC-FDMA uplink systems is investigated. Improved mean enhanced greedy algorithms are proposed for performing joint-user and chunk-based allocation at each transmission time interval. Selection criteria based on spectral efficiency and fairness are also proposed to choose the final allocation at each transmission time interval. Simulation results show that when the number of users and the velocity of the users were varied, the improved algorithms that use selection criteria based on spectral efficiency and fairness could outperform the existing mean greedy algorithms that employ user-based allocation in terms of spectral efficiency and fairness. Moreover, the improved algorithms not only showed better performance but also had the same time complexity as the existing mean greedy algorithms.
FTR: Performance-Aware and Energy-Efficient Communication Protocol for Integrating Sensor Networks into the Internet Sinung Suakanto; Suhono H. Supangkat; S. Suhardi; Roberd Saragih
Journal of ICT Research and Applications Vol. 7 No. 1 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.1.5

Abstract

Integrating sensor networks into the Internet brings many advantages. For example, users can monitor or control the state of the sensors remotely without visiting the field. Some researchers have proposed methods using a REST-based web service or HTTP to establish communication between sensors and server via the Internet. Unfortunately, as we know, HTTP is a best-effort service. In some cases this means that if the number of sensors increases the end-to-end Quality of Service will decrease. The end-to-end network delay increases, as well as the failure rate of data sending caused by HTTP timeouts. In this paper, we propose Finite Time Response (FTR) HTTP as a communication protocol suitable for integrating sensor networks into the Internet. We have defined a cross-layer approach that coordinates between the application layer and the physical layer to control not only performance but also energy efficiency. The HTTP request-response delay measured at the application layer is used as the decision factor at the physical layer to control the active and sleep periods. We also propose a forced-sleep period as a control mechanism to guarantee average performance for all nodes. The experimental results have shown that FTR has the ability to maintain better performance, indicated by a lower average response time and a lower average timeout experience. Optimization is still needed to gain better performance and better energy efficiency while also considering the average value of the update time.
CSLM: Levenberg Marquardt based Back Propagation Algorithm Optimized with Cuckoo Search Nazri Mohd. Nawi; Abdullah Khan; M. Z. Rehman
Journal of ICT Research and Applications Vol. 7 No. 2 (2013)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2013.7.2.1

Abstract

Training an artificial neural network is an optimization task, since it is desired to find optimal weight sets for a neural network during training process. Traditional training algorithms such as back propagation have some drawbacks such as getting stuck in local minima and slow speed of convergence. This study combines the best features of two algorithms; i.e. Levenberg Marquardt back propagation (LMBP) and Cuckoo Search (CS) for improving the convergence speed of artificial neural networks (ANN) training. The proposed CSLM algorithm is trained on XOR and OR datasets. The experimental results show that the proposed CSLM algorithm has better performance than other similar hybrid variants used in this study.

Page 10 of 31 | Total Record : 302

 8   9   10   11   12 

Filter by Year

2007 2025


Reset
Filter By Issues
All Issue Vol. 19 No. 2 (2025) Vol. 19 No. 1 (2025) Vol. 18 No. 2 (2024): (In Progress) Vol. 18 No. 1 (2024) Vol. 17 No. 3 (2023) Vol. 17 No. 2 (2023) Vol. 17 No. 1 (2023) Vol. 16 No. 3 (2022) Vol. 16 No. 2 (2022) Vol. 16 No. 1 (2022) Vol. 15 No. 3 (2021) Vol. 15 No. 2 (2021) Vol. 15 No. 1 (2021) Vol. 14 No. 3 (2021) Vol. 14 No. 2 (2020) Vol. 14 No. 1 (2020) Vol. 13 No. 3 (2019) Vol. 13 No. 2 (2019) Vol. 13 No. 1 (2019) Vol. 12 No. 3 (2018) Vol. 12 No. 2 (2018) Vol. 12 No. 1 (2018) Vol. 11 No. 3 (2017) Vol. 11 No. 2 (2017) Vol. 11 No. 1 (2017) Vol. 10 No. 3 (2016) Vol. 10 No. 2 (2016) Vol. 10 No. 1 (2016) Vol. 9 No. 3 (2015) Vol. 9 No. 2 (2015) Vol. 9 No. 1 (2015) Vol. 8 No. 3 (2015) Vol. 8 No. 2 (2014) Vol. 8 No. 1 (2014) Vol. 7 No. 3 (2013) Vol. 7 No. 2 (2013) Vol. 7 No. 1 (2013) Vol. 6 No. 3 (2012) Vol. 6 No. 2 (2012) Vol. 6 No. 1 (2012) Vol. 5 No. 3 (2011) Vol. 5 No. 2 (2011) Vol. 5 No. 1 (2011) Vol. 4 No. 2 (2010) Vol. 4 No. 1 (2010) Vol. 3 No. 2 (2009) Vol. 3 No. 1 (2009) Vol. 2 No. 2 (2008) Vol. 2 No. 1 (2008) Vol. 1 No. 2 (2007) Vol. 1 No. 1 (2007) More Issue