cover
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
ISSN : 23375787     EISSN : 23385499     DOI : https://doi.org/10.5614/itbj.ict.res.appl.
Core Subject : Science,
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.
Articles 12 Documents
Convolution and Recurrent Hybrid Neural Network for Hevea Yield Prediction Varghese, Lince Rachel; Kandasamy, Vanitha
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.6

Abstract

Deep learning techniques have been used effectively for rubber crop yield prediction. A hybrid of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) is the best technique for crop yield prediction because it can effectively handle uncertainty of features. Hence, in this paper, a hybrid CNN-RNN method is proposed to forecast Hevea yields based on environmental data in Kerala state, India. The proposed hybrid CNN-RNN method reduces the internal covariate shift of CNN by batch normalization and solves the gradient vanishing or exploding problem of RNN using LSTM with a cell activation mechanism. The proposed method has three essential characteristics: (i) it captures the time dependency of environmental factors and improves the inherent computational time; (ii) it is capable of generalizing the yield prediction under uncertain conditions without loss of prediction accuracy; (iii) combined with the back propagation and feed forward  method it can reveal the extent to which samples of weather conditions and soil data conditions are suitable to provide a clear boundary between rubber yield variations.
Automated Detection and Classification of Breast Cancer Nuclei with Deep Convolutional Neural Network Balasundaram, Shanmugham; Balasundaram, Revathi; Rasuthevar, Ganesan; Joseph, Christeena; Vimala , Annie Grace; Rajendiran, Nanmaran; Kaliyamurthy, Baskaran
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.3

Abstract

Heterogeneous regions present in tissue with respect to cancer cells are of various types. This study aimed to analyze and classify the morphological features of the nucleus and cytoplasm regions of tumor cells. This tissue morphology study was established through invasive ductal breast cancer histopathology images accessed from the Databiox public dataset. Automatic detection and classification was carried out by means of the computer analytical tool of deep learning algorithm. Residual blocks with short skip were employed with hidden layers of preserved spatial information. A ResNet-based convolutional neural network was adapted to perform end-to-end segmentation of breast cancer nuclei. Nuclei regions were identified through color and tubular structure morphological features. Based on the segmented and extracted images, classification of benign and malignant breast cancer cells was done to identify tumors. The results indicated that the proposed method could successfully segment and classify breast tumors with an average Dice score of 90.68%, sensitivity = 98.64, specificity = 98.68, and accuracy = 98.82.
A New Term Frequency with Gaussian Technique for Text Classification and Sentiment Analysis Vichianchai, Vuttichai; Kasemvilas, Sumonta
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.4

Abstract

This paper proposes a new term frequency with a Gaussian technique (TF-G) to classify the risk of suicide from Thai clinical notes and to perform sentiment analysis based on Thai customer reviews and English tweets of travelers that use US airline services. This research compared TF-G with term weighting techniques based on Thai text classification methods from previous researches, including the bag-of-words (BoW), term frequency (TF), term frequency-inverse document frequency (TF-IDF), and term frequency-inverse corpus document frequency (TF-ICF) techniques. Suicide risk classification and sentiment analysis were performed with the decision tree (DT), naïve Bayes (NB), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) techniques. The experimental results showed that TF-G is appropriate for feature extraction to classify the risk of suicide and to analyze the sentiments of customer reviews and tweets of travelers. The TF-G technique was more accurate than BoW, TF, TF-IDF and TF-ICF for term weighting in Thai suicide risk classification, for term weighting in sentiment analysis of Thai customer reviews for Burger King, Pizza Hut, and Sizzler restaurants, and for the sentiment analysis of English tweets of travelers using US airline services.
Reducing Power Consumption in Hexagonal Wireless Sensor Networks Using Efficient Routing Protocols Alhatimi, Razan Khalid; Almousa, Omar Saad; Albalas , Firas Ali
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.5

Abstract

Power consumption and network lifetime are vital issues in wireless sensor network (WSN) design. This motivated us to find innovative mechanisms that help in reducing energy consumption and prolonging the lifetime of such networks. In this paper, we propose a hexagonal model for WSNs to reduce power consumption when sending data from sensor nodes to cluster heads or the sink. Four models are proposed for cluster head positioning and the results were compared with well-known models such as Power Efficient Gathering In Sensor Information Systems (PEGASIS) and Low-Energy Adaptive Clustering Hierarchy (LEACH). The results showed that the proposed models reduced WSN power consumption and network lifetime.
Design and Implementation of Triple Band Half Mode Substrate Integrated Waveguide (HMSIW) Antenna with Compact Size Taha, Zahraa; Jassim, Hafsa; Ahmed, Anas; Farhan, Ikhlas
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.2

Abstract

This study investigated structure strategies and exploratory scenarios for a half mode substrate integrated waveguide (HMSIW) antenna. The proposed antenna consists of three Hilbert cells, which are simulated by using CST programming. The antenna was manufactured with the realities of minor imperfections and high incorporation. The proposed structure offers a suitable substrate integrated waveguide (SIW) with about a decrease in size by half. In addition, Hilbert cells were added to realize the triple-band characteristics with good impedance matching, radiation patterns, and radiation performance. The antenna was fabricated on h = 1 mm thick dielectric substrate with dielectric constant (𝜀𝑟 = 4.3). The Hilbert cells were drilled on the top plane of the antenna substrate and fed using a microstrip transmission line. The proposed antenna is small, with a slot side length of approximately half of the guided wavelength. The three developed Hilbert cell HMSIW antenna resonates at 3.25, 5.94 and 6.5 GHz with a bandwidth of 2.97, 2.25 and 2.29% within a return loss of ‑38.77, ‑35.82 -23.35 dB, respectively. The results showed enhancements in antenna gain of 3.56, 4.97 and 6.43 dBi, with a radiation efficiency of -1.253, -0.493 and -0.586 dB, respectively.
Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net Van Truong, Hoang; Chi Hieu, Nguyen; Ngoc Giao, Pham; Xuan Phong, Nguyen
Journal of ICT Research and Applications Vol. 15 No. 1 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.1.3

Abstract

Anomaly detection in the sound from machines is an important task in machine monitoring. An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain. However, because of the non-stationary nature of some sounds from the target machine, such a conventional approach does not perform well in those circumstances. In this paper, we propose a novel approach regarding the choice of used features and a new auto-encoder architecture. We created the Mixed Feature, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture. With experiments on the same dataset as the baseline system, using the same architecture for all types of machines, the experimental results showed that our methods outperformed the baseline system in terms of the AUC and pAUC evaluation metrics. The optimized model achieved 83.38% AUC and 64.51% pAUC on average overall machine types on the developed dataset and outperformed the published baseline by 13.43% AUC and 8.13% pAUC.
A Scheme Towards Automatic Word Indexation System for Balinese Palm Leaf Manuscripts Kesiman, Made Windu Antara; Pradnyana, Gede Aditra
Journal of ICT Research and Applications Vol. 15 No. 2 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.2.1

Abstract

This paper proposes an initial scheme towards the development of an automatic word indexation system for Balinese lontar (palm leaf manuscript) collections. The word indexation system scheme consists of a sub module for patch image extraction of text areas in lontars and a sub module for word image transliteration. This is the first word indexation system for lontar collections to be proposed. To detect parts of a lontar image that contain text, a Gabor filter is used to provide initial information about the presence of text texture in the image. An adaptive sliding patch algorithm for the extraction of patch images in lontars is also proposed. The word image transliteration sub module was built using the long short-term memory (LSTM) model. The results showed that the image patch extraction of text areas process succeeded in optimally detecting text areas in lontars and extracting the patch image in a suitable position. The proposed scheme successfully extracted between 20% to 40% of the keywords in lontars and thus can at least provide an initial description for prospective lontar readers of the content contained in a lontar collection or to find in which lontar collection certain keywords can be found.
Revealing the Characteristics of Balinese Dance Maestros by Analyzing Silhouette Sequence Patterns Using Bag of Visual Movement with HoG and SIFT Features Kesiman, Made Windu Antara; Maysanjaya, I Made Dendi; Pradnyana, I Made Ardwi; Sunarya, I Made Gede; Suputra, Putu Hendra
Journal of ICT Research and Applications Vol. 15 No. 1 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.1.6

Abstract

The aim of this research was to reveal and explore the characteristics of Balinese dance maestros by analyzing silhouette sequence patterns of Balinese dance movements. A method and complete scheme for the extraction and construction of silhouette features of Balinese dance movements are proposed to enable performing quantitative analysis of Balinese dance movement patterns. Two different feature extraction methods, namely the Histogram of Gradient (HoG) feature and the Scale Invariant Features Transform (SIFT) descriptor, were used to build the final feature, called the Bag of Visual Movement (BoVM) feature. This research also makes a technical contribution with the proposal of quantifying measures to analyze the movement patterns of Balinese dances and to create the profile and characteristics of dance maestros/creators. Eight Balinese dances from three different Balinese dance maestros were analyzed in this work. Based on the experimental results, the proposed method was able to visually detect and extract patterns from silhouette sequences of Balinese dance movements. Quantitatively, the pattern measures for profiling of Balinese dances and maestros revealed a number of significant characteristics of different dances and different maestros.
Adaptive Multi-level Backward Tracking for Sequential Feature Selection Chotchantarakun, Knitchepon; Sornil, Ohm
Journal of ICT Research and Applications Vol. 15 No. 1 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.1.1

Abstract

In the past few decades, the large amount of available data has become a major challenge in data mining and machine learning. Feature selection is a significant preprocessing step for selecting the most informative features by removing irrelevant and redundant features, especially for large datasets. These selected features play an important role in information searching and enhancing the performance of machine learning models. In this research, we propose a new technique called One-level Forward Multi-level Backward Selection (OFMB). The proposed algorithm consists of two phases. The first phase aims to create preliminarily selected subsets. The second phase provides an improvement on the previous result by an adaptive multi-level backward searching technique. Hence, the idea is to apply an improvement step during the feature addition and an adaptive search method on the backtracking step. We have tested our algorithm on twelve standard UCI datasets based on k-nearest neighbor and naive Bayes classifiers. Their accuracy was then compared with some popular methods. OFMB showed better results than the other sequential forward searching techniques for most of the tested datasets.
Extraction of the Major Features of Brain Signals using Intelligent Networks Salarian, Shirin; Shahabi, Amir Shahab
Journal of ICT Research and Applications Vol. 15 No. 1 (2021)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2021.15.1.5

Abstract

The brain-computer interface is considered one of the main tools for implementing and designing smart medical software. The analysis of brain signal data, called EEG, is one of the main tasks of smart medical diagnostic systems. While EEG signals have many components, one of the most important brain activities pursued is the P300 component. Detection of this component can help detect abnormalities and visualize the movement of organs of the body. In this research, a new method for processing EEG signals is proposed with the aim of detecting the P300 component. Major features were extracted from the BCI Competition IV EEG data set in a number of steps, i.e. normalization with the purpose of noise reduction using a median filter, feature extraction using a recurrent neural network, and classification using Twin Support Vector Machine. Then, a series of evaluation criteria were used to validate the proposed approach and compare it with similar methods. The results showed that the proposed approach has high accuracy.

Page 1 of 2 | Total Record : 12