Sunday, October 21, 2018
   
Text Size
Login

Journal of Information and Communication Technology (JICT) Vol. 17, No. 2, April 2018

FUZZY DISCRETIZATION TECHNIQUE FOR BAYESIAN FLOOD DISASTER MODEL
Nor Idayu Ahmad-Azami, Nooraini Yusoff & Ku Ruhana Ku-Mahamud

COLLABORATION AND INNOVATION MODELS IN INFORMATION AND COMMUNICATION CREATIVE INDUSTRIES – THE CASE OF GERMANY
Jan Stejskal, Petr Hajek & Viktor Prokop

MULTI-LABEL CLASSIFICATION FOR PHYSICAL ACTIVITY RECOGNITION FROM VARIOUS ACCELEROMETER SENSOR POSITIONS
Raihani Mohamed, M. N. Shah Zainudin, Md Nasir Sulaiman, Thinagaran Perumal & Norwati Mustapha

NOISY IMAGE CLASSIFICATION USING HYBRID DEEP LEARNING METHODS
Sudipta Singha Roy, Mahtab Ahmed & Muhammad Aminul Haque Akhand

COMMENT ANALYSIS FOR PRODUCT AND SERVICE SATISFACTION FROM THAI CUSTOMERS' REVIEW IN SOCIAL NETWORK
Todsanai Chumwatana

DEVELOPING AGENT BASED HEURISTIC OPTIMISATION SYSTEM FOR COMPLEX FLOW SHOPS WITH CUSTOMER-IMPOSED PRODUCTION DISRUPTIONS
Tunde Victor Adediran & Ammar Al-Bazi

A HIERARCHICAL CLASSIFIER FOR MULTICLASS PROSTATE HISTOPATHOLOGY IMAGE GLEASON GRADING
Dheeb Albashish, Shahnorbanoun Sahran, Azizi Abdullah, Mohammed Alwenshah & AfzanAdam

AN EMPIRICAL STUDY ON PREDICTORS OF GREEN SUSTAINABLE SOFTWARE PRACTICES IN MALAYSIAN ELECTRONIC INDUSTRIES
Bokolo Anthony Jnr., Mazlina Abdul Majid & Awanis Romli



FUZZY DISCRETIZATION TECHNIQUE FOR BAYESIAN FLOOD DISASTER MODEL
1Nor Idayu Ahmad-Azami, 2Nooraini Yusoff & 2Ku Ruhana Ku-Mahamud

1Faculty of Information & Communication Technology
Limkokwing University of Creative Technology, Malaysia
2,School of Computing, Data Science Research Lab
Universiti Utara Malaysia, Kedah, Malaysia
idayu.azami@limkokwing.edu.my; nooraini@uum.edu.my; ruhana@uum.edu.my

ABSTRACT | FULL TEXT
The use of Bayesian Networks in the domain of disaster management has proven its efficiency in developing the disaster model and has been widely used to represent the logical relationships between variables. Prior to modelling the correlation between the flood factors, it was necessary to discretize the continuous data due to the weakness of the Bayesian Network to handle such variables. Therefore, this paper aimed to propose a data discretization technique and compare the existing discretization techniques to produce a spatial correlation model. In particular, the main contribution of this paper was to propose a fuzzy discretization method for the Bayesian-based flood model. The performance of the model is based on precision, recall, F-measure, and the receiver operating characteristic area. The experimental results demonstrated that the fuzzy discretization method provided the best measurements for the correlation model. Consequently, the proposed fuzzy discretization technique facilitated the data input for the flood model and was able to help the researchers in developing effective early warning systems in the future. In addition, the results of correlation were prominent in disaster management to provide reference that may help the government, planners, and decision-makers to perform actions and mitigate flood events.


Keywords: flood disaster, spatial data mining, Bayesian Network, fuzzy discretization.

Received: 3 May 2017 Accepted: 17 December 2017





COLLABORATION AND INNOVATION MODELS IN INFORMATION AND COMMUNICATION CREATIVE INDUSTRIES – THE CASE OF GERMANY
1Jan Stejskal, 2Petr Hajek & 1Viktor Prokop
1Institute of Economics Sciences, Faculty of Economics and Administration
University Pardubice, Czech Republic
2Institute of System Engineering and Informatics
Faculty of Economics and Administration, University Pardubice, Czech Republic
jan.stejskal@upce.cz;petr.hajek@upce.czviktor.prokop@upce.cz

ABSTRACT | FULL TEXT
In rapidly changing environment of global knowledge economy, innovations play an important role in the process of gaining competitive advantage. Specifically, information and communication creative industries are dependent on constant technological breakthroughs, new sources of knowledge and high innovativeness. Moreover, new knowledge and innovation outputs of these industries subsequently affect products and processes of other businesses as well as innovation activities within different industries. Knowledge acquisition, utilization and dissemination therefore represent important processes that significantly influence the firms´ innovation activities. It was proven that cooperation is an important determinant that helps to spread the existing knowledge and to create new knowledge through knowledge spillover effects. The paper deals with the determinants of cooperation and innovation to examine numerous effects on both activities in German information and communication creative industries. We also test the role of the determinants of innovation performance and their influence on the economic effect of innovation activities in terms of the percentage of innovative products in total turnover. For our analyses, we are using data from Community Innovation Survey 2008-2010. We empirically show that firms from German information and communication creative industries can create innovations through the collaboration and confirm that both internal and external communication significantly contribute to the creation of innovation. Moreover, we confirm the influence of internal expenditures on R&D and observe significant influence of external expenditures on R&D. In conclusion, we also provide some practical implications for policy makers.

Keywords: creative industry, knowledge acquisition, collaboration and innovation models.

Received: 12 October 2017 Accepted: 6 February 2018



 

MULTI-LABEL CLASSIFICATION FOR PHYSICAL ACTIVITY RECOGNITION FROM VARIOUS ACCELEROMETER SENSOR POSITIONS
1Raihani Mohamed, 1,2Mohammad Noorazlan Shah Zainudin,

1Md Nasir Sulaiman, 1Thinagaran Perumal & 1Norwati Mustapha
1Faculty of Computer Science and Information Technology Universiti Putra Malaysia, Selangor, Malaysia
2Faculty of Electronics and Computer Engineering Universiti Teknikal Malaysia Melaka, Malaysia
raihanim@gmail.com; noorazlan@utem.edu.my; nasir@upm.edu.my; thinagaran@upm.edu.my;norwati@upm.edu.my

ABSTRACT | FULL TEXT
In recent years, the use of accelerometers embedded in smartphones for Human Activity Recognition (HAR) has been well considered. Nevertheless, the role of the sensor placement is yet to  be  explored  and  needs  to  be  further  investigated. In this study, we investigated the role of sensor placements for recognizing various types of physical activities using the accelerometer sensor embedded in the smartphone. In fact, most of the reported work in HAR utilized traditional multi-class classification approaches to determine the types of activities. Hence, this study was to recognize the activity based on the best sensor placements that are appropriate to the activity performed. The traditional multi-class classification approach required more manual work and was time consuming to run the experiment separately. Thus, this study proposed the multi- label classification technique with the Label Combination (LC) approach in order to tackle this issue. The result was compared with several state-of-the-art traditional multi-class classification approaches. The multi-label classification result significantly outperformed the traditional multi-class classification methods as well as minimized the model build time.


Keywords: HAR, accelerometer, multi-label classification, multi-class classification, smartphones.

Received: 8 August 2017 Accepted: 20 February 2018




NOISY IMAGE CLASSIFICATION USING HYBRID DEEP LEARNING METHODS
1Sudipta Singha Roy, 2Mahtab Ahmed & 2Muhammad Aminul Haque Akhand

1 Institute of Information and Communication Technology Khulna University of Engineering & Technology, Khulna, Bangladesh
2 Dept. of Computer Science and Engineering Khulna University of Engineering & Technology, Khulna, Bangladesh
sudipta.singha.roy@iict.kuet.ac.bd; mahtab@cse.kuet.ac.bd; akhand@cse.kuet
ABSTRACT | FULL TEXT

In real-world scenario, image classification models degrade in performance as the images are corrupted with noise, while these models are trained with preprocessed data. Although deep neural networks (DNNs) are found efficient for image classification due to their deep layer-wise design to emulate latent features from data, they suffer from the same noise issue. Noise in image is common phenomena in real life scenarios and a number of studies have been conducted in the previous couple of decades with the intention to overcome the effect of noise in the image data. The aim of this study was to investigate the DNN-based better noisy image classification system. At first, the autoencoder (AE)-based denoising techniques were considered to reconstruct native image from the input noisy image. Then, convolutional neural network (CNN) is employed to classify the reconstructed image; as CNN was a prominent DNN method with the ability to preserve better representation of the internal structure of the image data. In the denoising step, a variety of existing AEs, named denoising autoencoder (DAE), convolutional denoising autoencoder  (CDAE)  and  denoising  variational  autoencoder (DVAE) as well as two hybrid AEs (DAE-CDAE and DVAE- CDAE) were used. Therefore, this study considered five hybrid models for noisy image classification termed as: DAE-CNN, CDAE-CNN,   DVAE-CNN,   DAE-CDAE-CNN   and   DVAE- CDAE-CNN. The proposed hybrid classifiers were validated by experimenting over two benchmark datasets (i.e. MNIST and CIFAR-10) after corrupting them with noises of various proportions. These methods outperformed some of the existing eminent methods attaining satisfactory recognition accuracy even when the images were corrupted with 50% noise though these models were trained with 20% noise in the image. Among the proposed methods, DVAE-CDAE-CNN was found to be better than the others while classifying massive noisy images, and DVAE-CNN was the most appropriate for regular noise. The main significance of this work is the employment of the hybrid model with the complementary strengths of AEs and CNN in noisy image classification. AEs in the hybrid models enhanced the proficiency of CNN to classify highly noisy data even though trained with low level noise.

Keywords: Image denoising, CNN, denoising autoencoder, convolutional denoising autoencoder, variational denoising autoencoder, hybrid architecture.

Received: 17 October 2017 Accepted: 10 February 2018




COMMENT ANALYSIS FOR PRODUCT AND SERVICE SATISFACTION FROM THAI CUSTOMERS' REVIEW IN SOCIAL NETWORK

Todsanai Chumwatana
College of Information and Communication Technology Rangsit University, Pathumthani, Thailand
todsanai.c@rsu.ac.th

ABSTRACT | FULL TEXT
In the last decade, the amount of social media usage has rapidly increased exponentially in Thailand. A huge amount of Thai online reviews and comments are available on social network every second. Because of this fact, comment analysis, also called sentiment analysis, has then become an essential task to analyze people’s emotions, opinion, attitudes and sentiments from the amount of these online posts. This paper proposed the technique for analyzing Thai customers’ comments or opinions about the products and services by counting the polarity words of the product and service domains. To demonstrate the proposed technique, experimental studies on analyzing Thai customers’ comments in the social media are presented in this paper. The comments are classified into neutral, positive or negative. The proposed technique benefits the business domain in guiding product improvement and quality of service. Hence, this paper also benefits the end-users in making a smart decision.


Keywords:
Comment analysis, sentiment analysis, opinion mining, social network analysis.


Received: 1 September 2017 Accepted: 2 January 2018



DEVELOPING AGENT BASED HEURISTIC OPTIMISATION SYSTEM FOR COMPLEX FLOW SHOPS WITH CUSTOMER-IMPOSED PRODUCTION DISRUPTIONS
Tunde Victor Adediran & Ammar Al-Bazi

Faculty of Engineering, Environment and Computing Coventry University Coventry, United Kingdom
adedirat@uni.coventry.ac.uk; ammar.albazi@coventry.ac.uk

ABSTRACT | FULL TEXT
The study of complex manufacturing flow-shops has seen a number of approaches and frameworks proposed to tackle various production-associated problems. However, unpredictable disruptions, such as change in sequence of order, order cancellation and change in production delivery due time, imposed by customers on flow-shops that impact production processes and inventory control call for a more adaptive approach capable of responding to these changes. In this research work, a new adaptive framework and agent-based heuristic optimization system was developed to investigate the disruption consequences and recovery strategy. A case study using an Original Equipment Manufacturer (OEM) production process of automotive parts and components was adopted to justify the proposed system. The results of the experiment revealed significant improvement in terms of total number of late orders, order delivery time, number of setups and resources utilization, which provide useful information for manufacturer’s decision-making policies.

Keywords: agent-based simulation, customer production disruptions, flow-shops, heuritic optimisation algorithm, manufacturing systems.

Received: 2 August 2017 Accepted: 10 February 2018



A HIERARCHICAL CLASSIFIER FOR MULTICLASS PROSTATE HISTOPATHOLOGY IMAGE GLEASON GRADING
1Dheeb Albashish, 2Shahnorbanun Sahran, 2Azizi Abdullah, 3 Mohammed Alweshah & 2Afzan Adam

1&3 Prince Abdullah Ben Ghazi Faculty of Information Technology Al-Balqa Applied University, 19117 Al-Salt, Jordan
1&2 Faculty of Information Science and Technology Universiti Kebangsaan Malaysia, Selangor, Malaysia
bashish@bau.edu.jo;{shahnorbanun@bau.edu.jo; azizia@bau.edu.jo; afzan@ukm.edu.my; weshah@bau.edu.jo

ABSTRACT | FULL TEXT
Automated classification of prostate histopathology images includes the identification of multiple classes, such as benign and cancerous (grades 3 & 4). To address the multiclass classification problem in prostate histopathology images, breakdown approaches are utilized, such as one-versus-one (OVO) and one- versus-all (Ovall). In these approaches, the multiclass problem is decomposed into numerous binary subtasks, which are separately addressed. However, OVALL introduces an artificial class imbalance, which degrades the classification performance, while in the case of OVO, the correlation between different classes not regarded as a multiclass problem is broken into multiple independent binary problems. This paper proposes a new multiclass approach called multi-level (hierarchical) learning architecture (MLA). It addresses the binary classification tasks within the framework of a hierarchical strategy. It does so by accounting for the interaction between several classes and the domain knowledge. The proposed approach relies on the ‘divide-and-conquer’ principle by allocating each binary task into two separate subtasks; strong and weak, based on the power of the samples in each binary task. Conversely, the strong samples include more information about the considered task, which motivates the production of the final prediction. Experimental results on prostate histopathological images illustrated that the MLA significantly outperforms the Ovall and OVO approaches when applied to the ensemble framework. The results also confirmed the high efficiency of the ensemble framework with the MLA scheme in dealing with the multiclass classification problem.


Keywords:
Multiclasss classification, hierarchical classification, image classification, ensemble classification.


Received: 2 September 2017 Accepted: 4 January 2018



AN EMPIRICAL STUDY ON PREDICTORS OF GREEN SUSTAINABLE SOFTWARE PRACTICES IN MALAYSIAN ELECTRONIC INDUSTRIES
Bokolo Anthony Jnr., Mazlina Abdul Majid & Awanis Romli
Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang, Malaysia
bkanjr@gmail.com; mazlina@ump.edu.my; awanis@ ump.edu.my

ABSTRACT | FULL TEXT
Currently, sustainability is a pertinent issue that should be considered in the software development process; hence it is imperative to recognize how environmental-friendly practices can be applied in the electronic industries that develop and deploy software products. However, sustainability is not fully considered when electronic industries implement modern software systems. Additionally, software developers in electronic industries believe that software is environmental friendly mainly because it is virtual. Conversely, the life cycle process and approaches applied to implement, deploy and maintain software do possess social and environmental impacts that are usually not accounted for by electronic industries. Therefore this study identified the predictors that determine sustainable software practice applications in electronics industries by presenting a model to facilitate sustainable software products development. The identified predictors influence sustainable software practices applications which correlate to environmental, technical, economic, social and individual dimensions of sustainability in electronics industries. Based on the identified predicators, this research developed a set of indicators for survey questions and collected data from 133 respondents from Information Technology (IT), software, environmental and electronic- based industries. The survey data aimed to verify each of the identified predictors that influence sustainable software practice applications. Descriptive and inferential statistical results from the survey data show that each of the predictors is significant and do influence sustainable software development. The finding from this study provides insights to electronic industries in implementing sustainable software practice applications.


Keywords: Green software development, sustainable software development dimensions, software practice application, software process life cycle, predictors.

Received: 27 June 2017Accepted: 21 December 2017

Universiti Utara Malaysia Press
 Universiti Utara Malaysia, 06010 UUM Sintok
Kedah Darul Aman, MALAYSIA
Phone: +604-928 4816, Fax : +604-928 4792

All Right Reserved. Copyright © 2010, Universiti Utara Malaysia Press