		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
June 2018 | Vol. 96 No.11

Title:	INTERACTING THROUGH DISCLOSING: PEER INTERACTION PATTERNS BASED ON SELF-DISCLOSURE LEVELS VIA FACEBOOK
Author:	SYAZWANI SIDEK, ZAIDATUN TASIR, NURUL FARHANA JUMAAT
Abstract:	Peer interaction in an online environment has close connections with self-disclosure. Hence, this study was conducted to explore peer interaction patterns and self-disclosure levels via a social networking tool, specifically, Facebook. Twenty-two postgraduate students who enrolled for the Authoring System course participated in the study. Data were gathered from the online discussion transcripts in Facebook. The online discussion transcripts were coded and analysed based on (a) coding scheme for identifying patterns of peer interaction, and (b) a self-disclosure rating scale for categorizing the levels of self-disclosure. Findings showed that the students had mostly used response and position types of peer interaction. Meanwhile, most of the students were self-disclosing through Information-Level 1 followed by Feeling-Level 1, and Thought-Level 1. Furthermore, peer interaction patterns were found to have a strong significant and positive correlation with self-disclosure levels. In conclusion, this study revealed that high self-disclosure by students affects positively peer interaction in Facebook discussions. The implications of these results are considered, and possible future studies are suggested.
Keywords:	Peer Interaction, Self-disclosure, Online Discussion, Online Learning Environment, Facebook
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	ASSESSING INFORMATION SECURITY RISK WITH THE FUZZY SET THEORY
Author:	MURATKHAN RAIKHAN, KHABDOLDA BOLAT, ZHUMABEKOV MEIRAM, OMAROVA ALTYNAY
Abstract:	There are two important issues when it comes to information system development – business processes modeling and business project risk assessment. However, in practice, risk is assessed at the later stages of project development (design and implementation). This enhances the importance of the question whether performed business processes are safe. Traditionally, information system risk is defined as the combination of probable negative events and possible consequences. However, information security risk of a modern organization is a multidimensional complex concept that includes a set of interrelated variables. Values of risk factors often cannot be accurately calculated. Therefore, information security risk assessment can be considered as an unclear problem. This article describes methods of information security risk assessment with the fuzzy set theory. An example of organization's information security risk assessment is considered according to the requirements of international standards and preferences of the owner of information resources.
Keywords:	Risk, fuzzy set theory, risk assessment method
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A FRAMEWORK FOR MONITORING BLOOD PRESSURE OF PATIENTS IN THE RURAL AREA USING INTERNET OF THINGS TECHNOLOGY
Author:	DR. MODESTA .E. EZMA, MR. CELESTINE .I.UGWU
Abstract:	The convergence of multiple technologies, ranging from wireless communication to the internet and embedded systems, such as wireless sensor network, control system and automation gave rise to the internet of things (IoT). The application of IoT in healthcare system, typically use sensors enabled devices to assist in remote health monitoring. This health monitoring devices can range from blood pressure and heart bit monitors to advanced devices capable of monitoring specialized implants. In this paper we have proposed a framework for monitoring blood pressure of patients in the rural area using Internet of Things technology. We also discussed the background of IoT technology, application areas of Internet of Things technology, Internet of Things communications model, an overview of enabling communication and cooperation technologies for the IoT and issues in IoT.
Keywords:	Internet of Things, Sensor, Heart, Health Network
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	COLOR IMAGE COMPRESSION BASED on DCT, DIFFERENTIAL PULSE CODING MODULATION, and ADAPTIVE SHIFT CODING
Author:	ENAS KH. HASSAN , LOAY E. GEORGE , FAISAL G. MOHAMMED
Abstract:	In this study a color image compression scheme was introduced, the proposed scheme was applied to images in RGB and YCbCr color models for the issues of comparison in performance; each plane was partitioned into 16x16 blocks and 1-D DCT was used to transform the image planes to frequency domain instead of 2-D DCT (typically applied to images) for the purpose of compression/ decompression time reduction; the implementation time was reduced by 47:1 for the DCT step only. An adaptive scalar quantization step is applied on all image planes in RGB color model, but for YCbCr color model the quantization parameters where reduced by half for the chrominance plane while it is the same for the luminance planes to preserve the image quality, the zigzag scan was used to rearrange the data from non-zero low frequency coefficients to high frequency coefficients, where the adaptive shift coding was applied that performs Differential Pulse Coding Modulation on the DC coefficients for the entire image and Run Length Encoding for the AC coefficients for the entire image; the shift optimizer was applied to these coefficients to produce the exact number of bits needed to represent each one of them . The attained compression results indicated good efficiency in terms of compression gain while keeping the fidelity level above the acceptable level.
Keywords:	Color Conversion, DPCM, Lossy Image Compression, Zigzag Scan, Run Length Encoding, DCT Compression
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	SHAPE SYMMETRY-BASED SEMANTIC IMAGE RETRIEVAL USING HIDDEN MARKOV MODEL
Author:	MAHMOUD ELMEZAIN
Abstract:	In this paper, we propose a novel framework to retrieve semantic images based on shape skeletonizing, ontology base and Hidden Markov Model. First, the region of interest is localized using an adaptive Gaussian model to model the background subtraction. Second, symmetry features for an object is extracted and then quantized using k-means procedure for learning or retrieving processes by Hidden Markov Model. Query Engine, Matching Module and Ontology Manger are to retrieve the semantic image using SPARQL language on input text or image query. The left-right Hidden Markov Model topology using Viterbi algorithm for retrieving and Baum-welch for learning is investigated. The outcome of our proposed framework is empirically tested against the mammals Benchmark. The experiments on the semantic image retrieval yields an efficient result to intricate event by input text or image query than previously notified.
Keywords:	Image retrieval, Query Engine, SPARQL, Hidden Markov Model
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A REVIEW ON REQUIREMENTS VALIDATION FOR SOFTWARE DEVELOPMENT
Author:	NOR AIZA MOKETAR, MASSILA KAMALRUDIN, MOKHTAR MOHD. YUSOF, SAFIAH SIDEK
Abstract:	Requirement validation is an important phase in software development project in order to certify that the captured requirements are the exact representations of the users’ needs and expectations. This phase helps to identify and avoid requirements errors from propagating to the later stage. In this paper, we performed a literature review that investigated the trend in software requirements validation approach studied in a decade from the year of 2007 until 2016. Here, we investigated the types of contributions, modes of approaches, requirements types and the techniques that were commonly used and proposed for requirements validation. In this study, we found that many studies contributed new methodology/approach for validating the functional requirements using semi-formalise method. The Unified Modelling Language (UML) models were the most favourite models for this purpose. Furthermore, we found that requirements prototyping was the most used technique for requirements validation. This study also reported the most important requirements quality criteria that need to be validated and fulfil in order to develop high quality software. From the results we found that quality of consistency, correctness and completeness were most frequently validated in requirements validation.
Keywords:	Software Engineering, Requirements Engineering, Requirements Validation, Quality of Requirements
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	THE MULTI-DIMENSIONAL VECTORS AND AN YULE-II MEASURE USED FOR A SELF-ORGANIZING MAP ALGORITHM OF ENGLISH SENTIMENT CLASSIFICATION IN A DISTRIBUTED ENVIRONMENT
Author:	DR.VO NGOC PHU, DR.VO THI NGOC TRAN
Abstract:	We have proposed a new model for big data sentiment classification using a Self-Organizing Map Algorithm (SOM) – an unsupervised learning of a machine learning to classify the sentiments (positive, negative, or neutral) for all the documents of our testing data set according to all the documents of our training data set in English. We only run the SOM only once, the results of the sentiment classification of all the documents of the testing data are identified. The SOM is proposed according to many multi-dimensional vectors of both the testing data set and the training data set. The multi-dimensional vectors are based on many sentiment lexicons of our basis English sentiment dictionary (bESD). One document is corresponding to one multi-dimensional vector according to the sentiment lexicons. After running the SOM only once, a Map is used in presenting the results of the SOM. The results of clustering all documents of the testing data set into either the positive polarity or the negative polarity are shown on the Map, we can find all the results of the sentiment classification of all the documents of the testing data set fully. We only use many multi-dimensional vectors based on the sentiment lexicons of the bESD. In a sequential system, the new model has been tested firstly, and then, this model has been performed in a parallel network environment secondly. The accuracy of the testing data set has been achieved 88.72% certainly. Many different fields can widely use the results of this new model.
Keywords:	English sentiment classification; parallel system; Cloudera; Hadoop Map and Hadoop Reduce; Yule-II Measure; Self-Organizing Map
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	APPLICATION OF FUZZY LOGIC IN ESTIMATION OF CARBON MONOXIDE OF URBAN TRANSPORT IN THE CITY OF KENITRA, MOROCCO
Author:	SOUAD LAAROUSSI, TAOUFIK CHERRADI, SOULHI AZIZ, RABIAE SAIDI
Abstract:	Decreasing carbon monoxide (CO) emissions has become an overarching concern for transportation policy and planning throughout the world. This article presents a fuzzy logic based approach for urban transport sustainability. We address the issue of reducing CO emissions by varying other factors related to urban transport. Fuzzy logic modeling is developed using three input variables including speed, fuel consumption, and number of bus stops for the case of the city of Kenitra. The fuzzy controllers Mamdani and Sugeno were used to develop this model. The results of this study provide a decision-support model for help local authorities to reduce CO emissions by varying the other factors related to urban transport.
Keywords:	Fuzzy Logic, CO Emission, Urban Transport, Speed, Fuel Consumption, Number Of Bus Stops, Kenitra
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A SELF-TRAINING - BASED MODEL USING A K-NN ALGORITHM AND THE SENTIMENT LEXICONS - BASED MULTI-DIMENSIONAL VECTORS OF A S6 COEFFICIENT FOR SENTIMENT CLASSIFICATION
Author:	DR.VO NGOC PHU, DR.VO THI NGOC TRAN
Abstract:	Many surveys and commercial applications of sentiment classification have already applied to many different fields in everyday life, such as in political activities, commodity production, and commercial activities significantly. A semi-supervised learning of a machine learning used for a new model for big data sentiment classification has already been built in this survey. We have proposed a novel model using mainly a self-training (ST) approach to classify 12,500,000 documents of our testing data set comprising the 6,250,000 positive and the 6,250,000 negative into 2,000 documents of our training data set including the 1,000 positive and the 1,000 negative in English. In this self-training model (STM), a K-Nearest Neighbors algorithm (K-NN) has been used in training a classifier according to many multi-dimensional vectors of sentiment lexicons of a S6 coefficient (S6C). After training this classifier of the STM of each loop, the 100 documents of the testing data set have certainly been chosen, and then, they have been added to this classifier. The sentiment classification of all the documents of the testing data set has been identified after many loops of training the classifier of the STM certainly. In this survey, we do not use any vector space modeling (VSM). We do not use any one-dimensional vectors according to both the VSM and the sentiment classification. The S6C is used in creating the sentiment classification of our basis English sentiment dictionary (bESD) through a Google search engine with AND operator and OR operator. The novel model has firstly been performed in a sequential system and then, we have secondly implemented the proposed model in a parallel network environment. The results of the sequential environment are less than that in the distributed system. We have achieved 89.13% accuracy of the testing data set. The results of the proposed model can widely be used in many commercial applications and surveys of the sentiment classification.
Keywords:	English sentiment classification; parallel system; Cloudera; Hadoop Map and Hadoop Reduce; Balanced Iterative Reducing and Clustering using Hierarchies; K-NN; S6 coefficient.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	SWITCHING BOND GRAPH APPROACH FOR STRUCTURAL CONTROLLABILITY OF SWITCHED LINEAR SINGULAR SYSTEMS
Author:	MOHAMED BENDAOUD, HICHAM HIHI, KHALID FAITAH
Abstract:	This paper investigates the structural controllability of switched linear singular systems (SLSS). Graphical methods are proposed in order to determine different conditions for the structural controllability of SLSS systems. These methods are based on simple causal paths and causal manipulations on the switching bond graph model. Our approach can be implemented in software such as Symbol2000 or 20sim, in order to control the systems in real time.
Keywords:	Singular System, Switched Systems, Bond Graph, Structural R-Controllability, Structural I-Controllability, Structural C-Controllability.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A FUZZY C-MEANS ALGORITHM AND SENTIMENT-LEXICONS-BASED MULTI-DIMENSIONAL VECTORS OF A SOKAL & SNEATH-IV COEFFICIENT USED FOR ENGLISH SENTIMENT CLASSIFICATION
Author:	DR.VO NGOC PHU, DR.VO THI NGOC TRAN
Abstract:	Sentiment classification has long been the subject of research and there are many applications and many studies to service communities, commerce, politics, etc. In this research, we have proposed a new model for Big Data sentiment classification in the parallel network environment – a Cloudera system with Hadoop Map (M) and Hadoop Reduce (R). Our new model has used a Fuzzy C-Means Algorithm (FCM) with sentiment-lexicons-based multi-dimensional vectors and 3,000,000 documents of our training data set for document-level sentiment classification in English. First, we calculate the sentiment scores of English terms (verbs, nouns, adjectives, adverbs, etc.) by using a SOKAL & SNEATH-IV coefficient (SSIVC) through a Google search engine with AND operator and OR operator. Then, we transfer all the documents of both the testing data set and the training data set into many multi-dimensional vectors which are identified by using the sentiment lexicons. Finally, we implement the proposed model in both a sequential environment and a distributed system. Our new model can classify sentiment of millions of English documents based on many English documents in the parallel network environment. However, we tested our new model on our testing data set (including 5,500,000 English reviews, 2,750,000 positive and 2,750,000 negative) and achieved 87.82% accuracy. The results of this work can be widely used in applications and research of the English sentiment classification.
Keywords:	English sentiment dictionary; sentiment lexicons; English sentiment classification; Fuzzy C-Means; FCM; Cloudera; Hadoop Map; Hadoop Reduce; SOKAL & SNEATH-IV coefficient.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	USING SOFT SYSTEMS METHODOLOGY AS AN APPROACH TO EVALUATE CHEATING IN THE NATIONAL EXAMINATION
Author:	ADE IRIANI , DANNY MANONGGA
Abstract:	One of the most important issues the National Examination (UN) is the quality aspect of the level of honestly or integrity of parties involved in national examination. From various evaluation of the National Examination, the acts of cheating is always a problem from year to year, starting from the incident of cheating until the leakage of exam questions has always been a polemic. One of the factors considered to be the largest contributor to the cheating behavior is the national exam as a determinant of students’ graduation. For that matter, the government has implemented various policies including removing the national exam as determinant of graduation, but the policy was not followed by a decrease in the rate of cheating. This research is using soft-system methodology as well as to propose a conceptual model and plan for change in facing in situation of the problems.
Keywords:	National Examination, Cheating, Soft-System Methodology
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	ENGLISH SENTIMENT CLASSIFICATION USING AN YULEQ SIMILARITY MEASURE AND THE ONE-DIMENSIONAL VECTORS IN A PARALLEL NETWORK ENVIRONMENT
Author:	DR.VO NGOC PHU, DR.VO THI NGOC TRAN
Abstract:	Sentiment classification is significant in everyday life, such as in political activities, commodity production, and commercial activities. In this study, we have proposed a new model for Big Data sentiment classification. We use a YULEQ coefficient (YC) of the clustering technologies of a data mining field to cluster one document of our English testing data set, which is 7,000,000 documents comprising the 3,500,000 positive and the 3,500,000 negative, into either the positive polarity or the negative polarity based on our English training data set which is 5,000,000 documents including the 2,500,000 positive and the 2,500,000 negative. We do not use any sentiment lexicons in English. We do not use any multi-dimensional vector based on both a vector space modeling (VSM) and the sentiment lexicons. We only use many one-dimensional vectors based on VSM. One one-dimensional vector is clustered into either the positive or the negative if this vector is very close to either the positive or the negative by using many similarity coefficients of the YC. It means that this vector is very similar to either the positive or the negative. One document of the testing data set is clustered into the sentiments (positive, negative, or neutral) based on many one-dimensional vectors. We tested the proposed model in both a sequential environment and a distributed network system. We achieved 87.85% accuracy of the testing data set. The execution time of the model in the parallel network environment is faster than the execution time of the model in the sequential system. This survey used many similarity coefficients of the data mining field. The results of this work can be widely used in applications and research of the English sentiment classification.
Keywords:	English Sentiment Classification; Distributed System; Parallel System; YULEQ Similarity Measure; Cloudera; Hadoop Map And Hadoop Reduce; Clustering Technology.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	SERVICE COMPOSITION ALGORITHMS IN CYBER PHYSICAL SYSTEMS
Author:	SWATI NIKAM , RAJESH INGLE
Abstract:	Service composition in Cyber Physical Systems (CPS) means integrating individual services used for different purposes which individually cannot accomplish the goal, but if integrated then it can achieve a specific goal. So there is need of combining various services into one composite service to satisfy complete requirement. CPS is an emerging field in which cyber and physical world interact closely. By nature CPS is application oriented so the need of composing the existing services arises frequently. Hence understanding and resolving the service composition issues in the context of CPS becomes very important. Service composition is very well studied in Web service, Cloud Computing, Grid Computing and Wireless Sensor Network domain. Service composition work has initiated in CPS domain also, but still it lacks in maturity as compared to other domains. Service composition in CPS becomes critical firstly because of the dynamic and unpredictable nature of CPS which comes from the involvement of cyber and physical domain. Secondly lot of heterogeneity is observed in CPS components which range from simple sensors, actuators to high end computing devices. Thirdly resources also needs to be considered in the process of service composition and last but not the least, while looking at the practical applications of CPS, it needs to be considered in networked CPS context. Selecting best individual services for service composition is the main problem which is addressed in this paper. A middleware is designed for performing service composition and also phase wise algorithms for service composition are presented. Two significant methods of Multi Attribute Decision Making (MADM) methods are used to solve the service selection problem. Algorithms are tested in simulated environment with different scenarios to check suitability of MADM methods for service selection problem. The observation is few significant methods of MADM like PSI can be used to select best service for service composition.
Keywords:	Cyber Physical System, Service Composition, Quality of Service ( QoS)
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A NOVEL APPROACH FOR CROWD BEHAVIOR REPRESENTATION: NORMAL AND ABNORMAL EVENT DETECTION
Author:	SHERIF EL-ETRIBY, MAHMOUD ELMEZAIN, MOEIZ MIRAOUI
Abstract:	The concept of crowd refers to the gathering many people in one place, such as train stations, airports and subways, as well as gatherings sports, religious special crowds Hajj and Umrah became highly congested. In this paper, a novel approach is investigated to the crowd behaviors of individual using discriminative models. The novelty of the proposed approach can be described in three aspects. First, we sectioned video segments into spatio-temporal flow-blocks which allow the marginalization of arbitrarily dense flow field. Second, the observed flow field in each flow-block is treated as 2D distribution of samples and mixtures of Gaussian is used to parameterize it by keeping the generality of flow field intact. Moreover, we implemented, K-means algorithm to initialize the mixture model while Expectation Maximization algorithm is employed for optimization. These mixtures of Gaussian result in the distinct flow patterns (i.e. precisely a sequence of dynamic patterns) for each flow-block. Third, discriminative models such as Conditional Random Field, Hidden Conditional Random Field and Latent-dynamic Conditional Random Field were employed one for each flow-block and were learned from the sequence of dynamic patterns which was then classified for each flow-block as normal and abnormal. Our experiment on our own realistic Data set (Hajj-Umrah DataSet) from crowd in the pilgrimage shows promising results with no scarifying real-time performance for a wide range of practical crowd applications.
Keywords:	Crowd Behavior, Gaussian mixture, K-means technique, conditional Random Field.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A STUDY ON DYNAMIC HAND GESTURE RECOGNITION FOR FINGER DISABILITY USING MULTI-LAYER NEURAL NETWORK
Author:	ROMI FADILLAH RAHMAT, SARAH PURNAMAWATI, EKA PRATIWI GOENFI, OPIM SALIM SITOMPUL, MUHAMMAD FERMI PASHA, RAHMAT BUDIARTO
Abstract:	Interaction between human and computer is generally performed with a keyboard and mouse. However, these interactions have certain drawbacks which cannot be done by users with physical disabilities or user who have disability from the wrist to the fingertip. To overcome this problem, an approach to recognize human hand gesture as a means of human-computer interaction is needed. The method proposed by the author is the use of algorithms: nearest neighbor, grayscaling, frame-differencing, Principal Component Analysis (PCA) and Multi-Layer Perceptron (MLP). This research was conducted in two experiments, which were experiment with six different types of hand gestures and experiments with four different types of hand gestures. Each experiment was performed five times with different value of number of hidden layers parameter and hidden neurons parameter. The best testing result obtained from the experiment with six types of hand gestures is from the second experiment with two hidden layers using 300 and 50 hidden neurons for each layer, resulting in an accuracy rate of 77.02%. The best testing result obtained from the experiment with four different types of hand gestures is from the first experiment with two hidden layers using 300 and 50 hidden neurons for each layer, resulting in an accuracy rate of 89.72%. The best overall result is then implemented into the front-end system for controlling application such as: file explorer, music player, video player, slideshows and PDF reader.
Keywords:	Dynamic Hand Gesture, Multilayer Perceptron, Finger Disability, Image Processing
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	AN ENHANCE CNN-RNN MODEL FOR PREDICTING FUNCTIONAL NON-CODING VARIANTS
Author:	JALILAH ARIJAH MOHD KAMARUDIN, NUR AFIFAH AHMAD AHYAD, AFNIZANFAIZAL ABDULLAH, ROSELINA SALLEHUDDIN
Abstract:	In the era of big data, deep learning has advanced rapidly particularly in the field of computational biology and bioinformatics. In comparison to conventional analysis strategies, deep learning method performs accurate structure prediction because it can handle high coverage biological data such as DNA sequence and RNA measurement using high-level features. However, predicting functions of non-coding DNA sequence using deep learning method have not been widely used and require further study. The purpose of this study is to develop a new algorithm to predict the function of non-coding DNA sequence using deep learning approach. We propose an enhanced CNN-RNN model to predict the function of non-coding DNA sequence. In this model, we train an algorithm to automatically find the optimal initial weight and hyper-parameter to increase prediction accuracy which outperforms other prediction models.
Keywords:	Functional Non-coding Variant, Machine Learning, Deep Learning, Convolutional Neural Network, Recurrent Neural Network
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	TIME-FREQUENCY ANALYSIS IN ICTAL AND INTERICTAL SEIZURE EPILEPSY PATIENTS USING ELECTROENCEPHALOGRAM
Author:	MOHD SYAKIR FATHILLAH, KALAIVANI CHELLAPPAN, ROSMINA JAAFAR, RABANI REMLI, WAN ASYRAF WAN ZAIDI
Abstract:	Conventional method to distinguish normal and seizure EEG by an epileptologist’s visual screening is tedious and operator dependent. Normal DWT-based seizure detection technique established before suffers from deteriorating of performance due to increasing number of non-relevant features by wavelet decomposition. PCA approach has been utilized in this paper to overcome this problem. Energy, amplitude dispersion and approximate entropy (ApEn) of each sub-band were used as feature of interest and fed to Support Vector Machine (SVM) classifier. Differences between ictal, interictal and normal EEG based on these features were explored. There are significant differences in delta, theta and alpha band in sub-band energy, whereas ApEn changes are found in beta and alpha for ictal EEG. Amplitude dispersion illustrates changes in all sub-bands. PCA approach has been proven to have better accuracy (98%) compared to non-PCA approach (97%) in detecting ictal seizure. The proposed method produced the highest accuracy (98%) compared to other existing methods. The algorithm shows potential to be used clinically.
Keywords:	Time Frequency Analysis, Discrete Wavelet Transform (DWT), Approximate Entropy (ApEn), Principal Component Analysis (PCA), Support Vector Machine (SVM), Epilepsy, Seizure Detection
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	AN EFFICIENT APPROACH FOR IMAGE HIDING USING HYBRID TECHNIQUE
Author:	ABDULLAH MOHAMMED AWAD , MUZHIR SHABAN AL-ANI
Abstract:	Recently, many works are published concerned with image encryption and information hiding. Some of these works are concentrated on hiding of image and others are concentrated on hiding of text. These works have various applications such as; communication systems, multi-media systems, image and data compression and cryptography. The research aims to introduce an efficient approach for image hiding using hybrid technique. The proposed approach based on hiding the information via the cover image and then encrypting the image to generate a new image carry the information. This paper deals with the efficient method for image hiding taking into consideration the features which are built applying discrete wavelet transform (DWT). The achieved contribution from this research is concentrated on applying DWT leading to powerful hiding technique. A good performance and result for image hiding are obtained using this approach.
Keywords:	Image Hiding; Image Compression; DWT; Image Encryption.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	INTELLIGENT ROUTING TOPOLOGY FOR BEACON DATA TRANSFER
Author:	BYONG-KWON LEE, SEOK-HUN KIM
Abstract:	Indoors the positioning technique retrieves the position of users by the intensity of the signal and the identifier information generated in the beacon node. However, user location measurement is designed without considering the movement path of the data, the energy amount of the beacon node, the distance and the number of hops. Also, beacon nodes often lose data due to the disappearance of the data path depending on the installed state in a building. In this paper, we have studied routing topology configuration method that delivers the energy amount, the distance between nodes and the number of hops efficiently in a real environment. In conclusion, we have solved the problems of loss for local energy and data in fixed path models.
Keywords:	Beacon Routing, Effective Routing Topology, Intelligent Routing
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	LOSSLESS CODING SCHEME FOR DATA AUDIO 2 CHANNEL USING HUFFMAN AND SHANNON-FANO
Author:	TONNY HIDAYAT, MOHD HAFIZ ZAKARIA, AHMAD NAIM CHE PEE
Abstract:	This paper shows the comparison of various lossless compression techniques. This research only concerns on audio the WAV 2 channel audio format. If an audio is said to be stereo, it means it has 2 channels (left channel and right channel). The code prefix to be generated becomes more and may appear more diverse. In this paper gives little change in the rule model for the allocation of bits to the prefix code generated. It gives different conclusions on the size and time ratios, toward existing research. The result of compression can accelerate transmission of information from one individual to another. Compression requires a technique which can be strategy against the pack of data. Information that can be compressed not only text but it can be Audio, pictures and video information. Furthermore, lossless compression is the most approach which is frequently used in data compression. Lossless compressions consist of some algorithm, such as Huffman, Shannon-Fano, Lempel Ziv Welch and run-length encoding. Each algorithm can play out another pressure. Finally, this paper generates the conclusion about the comparison of performance in Huffman and Shannon-Fano based on discussion of the result. The conclusions are difference result of compression-decompression speed and compression factor and ratio both of this algorithm.
Keywords:	Audio, Lossless, WAV, Compression, Huffman, Shannon-fano
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	AN EFFICIENT AND FAST IMAGE INDEXING AND SEARCH SYSTEM BASED ON COLOR AND TEXTURE FEATURES
Author:	EL AROUSSI EL MEHDI, EL HOUSSIF NOURDDINE, SILKAN HASSAN
Abstract:	Content-Based Image Retrieval (CBIR) allows to automatically extracting target images according to objective visual contents of the image itself. Representation of visual features and similarity match are important issues in CBIR. Color, texture and shape information have been the primitive image descriptors in content-based image retrieval systems. This paper presents a fast and efficient image indexing and search system based on color and texture features. The color features are represented by combines 2-D histogram and statistical moments and texture features are represented by 2-D Localized SDFT that uses the Gaussian kernel to offer the spatial localization ability. 2-D SDFT is expected to provide more useful information. It is observed that color features in combination with the texture features derived from the brightness component provide approximately similar results when color features are combined with the texture features using all three components of color, but with much less processing time. The detailed experimental analysis is carried out using precision and recall on two datasets: Corel-DB, Coil-100. The time analysis is also performed to compare processing speeds of the proposed method with the existing similar best.
Keywords:	CBIR, Color histogram, Texture feature, statistical moments, 2-D Localized SDFT.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	CURRENT STATE OF BENCHMARKING SPECTRUM SENSING AND ROUTING STRATEGIES IN COGNITIVE RADIO AD HOC NETWORKS
Author:	DASARI.RAMESH , Dr.N.VENKATRAM
Abstract:	Cognitive radio technology is one of the prominent solutions developed to address under-utilization of spectrums. The CR technology provides different solutions by exploring different segments in the spectrum based on the opportunities created due to the temporary vacation of licensed users. Ease of networking the devices equipped with cognitive abilities for creating CRAHNs networks poses several challenges at different layers of the network. These challenges arise primarily due to the inherent flexibility in accessing spectrum by multiple devices. This paper offers a survey of the contemporary spectrum sensing and routing solutions in . The report commences through listing the spectrum sensing and routing challenges which are linked to the . In the next sections, the research work discusses multiple routing protocols and sensing protocols mostly designed for the cognitive radio network. These protocols can be broadly classified into six groups on the basis of routing metrics. The routing metrics considered for this analysis include- hop/delay, throughput performance, reasonable stability, energy consumption awareness along with multi-metric protocols. These multi-metric protocols either unite multiple metrics or engage different metrics as per specific rules. The paper also offers a discussion of the directions which ought to be taken by the future research.
Keywords:	Cognitive Radio Ad Hoc Networks, Spectrum Sensing, Routing, Channel Scheduling, Quality Of Service
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	DETERMINING THE SIMILARITY OF UML-MODELS BY COMBINING DIFFERENT SOFTWARE PROPERTIES
Author:	ALHASSAN ADAMU, WAN MOHD NAZMEE WAN ZAINON
Abstract:	One of the most important elements of every software system is its design architecture. Software design is a demanding task that requires lot of experience, expertise and knowledge of many different types of design alternatives. Each software engineers acquires more specific knowledge as he/she participate in a new project. Experienced engineers are very vital asset to Software Company, especially in a high competitive market environment; as such reusing knowledge of experienced engineers can save a lot of cost and time to the software company. UML models are de facto modelling language used by many software engineers during the software design stage, its receiving a widespread attention in the field of software reuse. It’s not surprising, because of the benefits that can be reaped out during the reuse of early software design is numerous, and it can lead to reuse of all related work-products. There is considerable amount of works that takes place within the scope of UML models reuse, this paper presents an experimental results of different features of UML models that are used during the matching and retrieval of UML diagrams from repository.
Keywords:	UML Models, Similarity, Software Properties, Reuse.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	HYBRID OF MULTI-CAR ELEVATOR SYSTEM AND DOUBLE-DECK ELEVATOR SYSTEM
Author:	YEONG CHERNG LIEW, CHENG SIONG LIM, MICHAEL LOONG PENG TAN, CHEE WEI TAN
Abstract:	Multi-car elevator system is a new breakthrough in an elevator system in 2001. It has broken the traditional concept of developing only one elevator car in an elevator shaft. Multi-car elevator system can have more than one elevator car moving in an elevator shaft and it has improved a lot in minimizing the waiting time of passengers if compared with only one elevator car in an elevator shaft. The main advantage of multi-car elevator system is to reduce the construction cost where 30% of the core-tube area of the elevator system is made up of shaft. By developing multi-car elevator system, many of elevator shafts need not to be developed and it still can perform about the same efficiency in serving passengers. However, it is still not able to transport a large number of passengers efficiently if the passengers are calling from the same floor, especially during the up-peak traffic. For that reason, the feature of double-deck elevator system is integrated into multi-car elevator system to develop a new hybridized elevator system called “Hybrid of multi-car elevator system and double-deck elevator system” to solve the limited car capacity problem. The performance of both systems, the hybridized elevator system and the multi-car elevator system is simulated. The result shows that the average journey time of the hybridized elevator system is shorter than the multi-car elevator system in all the three traffic modes, i.e. up-peak, down-peak and inter-floor traffics. For the up-peak traffic mode of the hybridized elevator system, it manages to achieve the best result of 33.5% shorter of the average journey time compared to the multi-car elevator system.
Keywords:	Elevator System, Transport Capacity, Multi-Car Elevator System, Double-Deck Elevator System, Hybridizing
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A WEB APPLICATION FOR TRAFFIC STATUS UPDATE USING CROWD-SOURCED DATA ACQUISITION AND REAL-TIME MODIFICATION
Author:	SHUVASHISH PAUL, PINKU DEB NATH, NASEEF M. ABDUS SATTAR, HASAN U. ZAMAN
Abstract:	Traffic jams are one of the most frustrating inconveniences experienced in all the major cities of the world. In the case of Dhaka, the capital of Bangladesh, factors such as high population density and increasing usage of private transport result in horrendous traffic jams on a daily basis and loss of valuable working hours. This paper introduces rTraffic -- a smartphone based web application that aims at making this issue a little more bearable by combining a crowd-sourced data acquisition model and real-time notifications system to provide a visual representation of the current traffic conditions in Dhaka and send notifications pertaining to the major intersections in the city. The paper also talks about the basic methodology, low-level implementation details and scaling factor considerations for real world deployment and performance benchmarks.
Keywords:	Real-time Traffic Notifications, Crowd-sourced Data Model, RESTful Application, Android, Traffic Congestion
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	A C2C E-COMMERCE TRUST MODEL BASED ON REPUTATION
Author:	ZHANG YILONG, JIANG HUIFANG, ZHANG SHUOSHUO,WANG XIAORUI, REN YUAN
Abstract:	The reputation of the nodes come from the evaluation information in C2C e-commerce. The trust model in actual application is generally cumulative or mean model, this model is too simple to effectively resist malicious attacks because of the false evaluation, it is difficult to guarantee the accuracy of reputation calculation. A new trust model is proposed in the paper, in which the seller’s reputation and buyer’s credit are designed respectively. The model also considers the new factors, such as the default reputation of the system, the number of failed transactions, the credibility of the transaction and so on. In order to calculate the buyer’s confidence in the seller, it increased the buyer’s confidence in the goods. The experimental results show that the model is effective and anti attack, and it is more accurate than the existing trust model. It can be effectively applied to C2C e-commerce system.
Keywords:	Reputation, Trust Model, False Evaluation, E-commerce, Node
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	NON-PARAMETRIC TARGET DETECTION IN A PASSIVE SEISMIC LOCATOR BASED ON SPECTRAL DATA
Author:	YURY MOROZOV, MIKHAIL RAJFELD, ALEKSANDR SPECTOR
Abstract:	The present paper proposes the approach to the universal non-parametric detector of seismic signals based on the amplitude spectrum analysis. The decision statistics of spectral components exceeding over reference ones is proposed. The maximal amplitude spectrum mean value over several adjacent reference cycles is subtracted from each working cycle spectrum to stabilize false alarm probability. The range of frequency components has been selected. The threshold estimation procedure is stated with respect to spectrum averages fluctuation. It has been shown that the detection probability achieves 0.9 for signal-to-noise ratio about 3 dB when the number of working cycles is 5.
Keywords:	Non-Parametric Method, Seismic Location, Detection, Amplitude Spectrum
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	PRIVACY-PRESERVING QUERIES FOR LBS: INDEPENDENT SECURED HASH FUNCTION
Author:	ABDULLAH ALBELAIHY, JONATHAN CAZALAS, VIJEY THAYANANTHAN
Abstract:	While location-based services have become ubiquitous, seemingly permeating our personal and professional lives, their inherent nature poses security risks to users, who are forced to reveal their highly-sensitive location data in order to make effective use of the service. Towards this end, a litany of techniques have been proposed to provide efficient answers for privacy-preserving queries in LBS. Spatial bloom filters were initially proposed as an efficient data structure used to manage special and geographic information in an space-efficient manner. Unfortunately, bloom filters suffer from two deficiencies: they leak at most one bit of information per query, and the hash functions require careful design and security analysis in order to be orthogonal and independent. In fact, developing quality hash function is paramount. We propose a method to automatically generate good, independent hash functions, with the goal of reducing information leakage. This means that even if one of the hash function is broken, for any reason, nothing can be learned about any other hash function. The results show that our proposed Hash functions are less dependent and leaked than the compared approach, while still seeing a notable improvement in performance.
Keywords:	Privacy, Bloom filter, LBS, Mobile user, Hash function.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text

Title:	AMAZIGH NAMED ENTITY RECOGNITION: A NOVEL APPROACH
Author:	AMRI SAMIR, ZENKOUAR LAHBIB
Abstract:	Information Extraction (IE) is a sub discipline of Artificial Intelligence. IE identifies information in unstructured information source that adheres to predefined semantics i.e. people, location etc. Recognition of named entities (NEs) from computer readable natural language text is significant task of IE and natural language processing (NLP). Named entity (NE) extraction is important step for processing unstructured content. Unstructured data is computationally opaque. Computers require computationally transparent data for processing. IE adds meaning to raw data so that it can be easily processed by computers. There are various different approaches that are applied for extraction of entities from text. This paper elaborates need of NE recognition for Amazigh language and discusses issues and challenges involved in NE recognition tasks for Amazigh language. It also explores various methods and techniques that are useful for creation of learning resources and lexicons that are important for extraction of NEs from natural language unstructured text.
Keywords:	Amazigh, Corpus, Named Entity Recognition, Information Extraction, Challenges, NLP
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2018 -- Vol. 96. No. 11 -- 2018
Full Text