Using the MQTT Protocol in Real Time for

Synchronizing IoT Device State

Adnan Shaout and Brennan Crispin

Electrical and Computer Engineering Department, University of Michigan, Dearborn

Abstract: This paper will present a design and implementation for an embedded system to connect to a Machine to Machine (M2M) broker. The proposed system will use the cloud server to communicate with other embedded systems. The system will be configurable from a cloud-based web service. The paper also will explore previous research on M2M protocols such as Message Queueing Telemetry Transport (MQTT) and Advanced Messaging Queuing Protocol (AMQP). The paper will present and demonstrate an MQTT based system for synchronizing IoT device state across multiple client nodes. The objective of the system is for state changes to be registered and distributed throughout the system in under 1 second; and initial registration of a new node should occur in under 30 seconds.

Keywords: MQTT, synchronizing, machine to machine, real time systems, IoT, cloud computing.

Abstract: In the last decade, several works proposed their own approaches about the context management for the Internet of Things (IoT). An important issue in such systems is faced by context data distribution with a sufficient level of quality i.e., Quality of Context (QoC). In this paper, a fuzzy logic-based framework is proposed which handles QoC evaluating within distributed context manager and context-aware applications. In addition, IoT contains massive context sources and data. From this issue, we use MapReduce skyline to speed up the computation and introduce parallelism in the processing. This article presents also a solutions provided by the Model Driven Approach (MDA) for modelling the captured context information from different context source.

Keywords: IoT, context manager, MDA, fuzzy logic, QoC, context source, map reduce skyline, application.

Received February 14, 2018, accepted April 17, 2018

RNN-LSTM Based Beta-Elliptic Model for Online Handwriting Script Identification

Ramzi Zouari¹, Houcine Boubaker¹, and Monji Kherallah²

¹National School of Engineers of Sfax, University of Sfax, Tunisia

²Faculty of Sciences of Sfax, University of Sfax, Tunisia

Abstract: Recurrent Neural Network (RNN) has achieved the state-of-the-art performance in a wide range of applications dealing with sequential input data. In this context, the proposed system aims to classify the online handwriting scripts based on their labelled pseudo-words. To avoid the vanishing gradient problem, we have used a variant of recurrent network with Long Short-Term Memory. The representation of the sequential aspect of the data is done through the beta-elliptic model. It allows extracting the dynamics and kinematics profiles of different strokes constituting a script over the time. This system was assessed with a large vocabulary containing scripts from ADAB, UNIPEN and PENDIGIT databases. The experiments results show the effectiveness of the proposed system which reached a high recognition rate with only one recurrent layer and using the dropout technique.

Keywords: Online, pseudo, stroke, velocity, beta-elliptic, recurrent, dropout.

Received February 15, 2018; accepted April 20, 2018

Building a Syntactic-Semantic Interface for aSemi-Automatically Generated TAG for Arabic

Abstract: Syntactic and semantic resources play an important role for various Natural Language Processing (NLP) tasks by providing information about the correct structural representations of the sentences and their meaning. To date, there is not a wide-coverage electronic grammar for the Arabic language. In this context, we present a new approach for building a Tree Adjoining Grammar (TAG) to represent the syntax and the semantic of modern standard Arabic. This grammar is produced semi-automatically with the eXtensible MetaGrammar (XMG) description language. First the syntax of Arabic is described using the defined Arab-XMG meta-grammar. Then semantic information is added by introducing semantic frame-based dimension into the meta-grammar. This is achieved by exploiting lexical resources such as ArabicVerbNet. Finally, the link between semantic and syntax is established using a syntax-semantic interface that allows the construction of sentence meaning through semantic role labeling. Experiments were performed to check grammar coverage as well as the syntactic-semantic analysis. The results showed that the generated grammar can cover the basic syntactic structures of Arabic sentences and the different phrasal structures with a precision rate of about 92%. Moreover, it confirms the effectiveness of the proposed approach as we were able to parse semantically a set of sentences and build their semantic representations with a precision rate of about 72%.

Keywords: TAG, meta-grammar, syntax-semantic interface, semantic frame, semantic role, Arabic language.

Received February 19, 2018; accepted April 18, 2018

Firas Albalas¹, Majd Al-Soud¹, Omar Almomani², and Ammar Almomani³

¹Department of Computer Science, Jordan University of Science and Technology, Jordan

²Network Computer and Information Systems Department, the World Islamic Sciences and Education University, Jordan

³Department of Information Technology, Al-Balqa Applied University, Jordan

Abstract: Currently, the concept of the Internet of Things (IoT) has become more noticeable where it is being used in all aspects of life, such as home automation, smart cities, military surveillance, security, agriculture, healthcare, etc., However, the heterogeneity of the constrained devices and the complexity of the internet bring up the need for a security system to secure all the communications, data and participating things. In this paper, This paper proposed a lightweight secure Constrained Application Protocol (CoAP) using Elliptic Curve Cryptography (ECC) to transport security between IoT objects and the Resource Directory (RD). The advantage of using ECC is its compact key size enabling it to utilize a smaller key size compared to the other identification methods such as Rivest-Shamir-Adleman (RSA). This work mainly has two parts; the first part implements the CoAP using ECC and using RSA algorithms where the results have proven that using ECC much better than RSA in terms of energy saving. The second part of this paper shows the proposed evaluation function and focuses on the security services that were applied in the proposed protocol. The results show that authentication achieved a 75.3% energy savings, data integrity had a 55.7% energy saving and confidentiality achieved a 47% energy saving.

Keywords: IoT, CoAP, ECC,energy saving, security, IoT.

Received February 12, 2018; accepted April 18, 2018

Conditional Arabic Light Stemmer: CondLight

Yaser Al-Lahham, Khawlah Matarneh, and Mohammad Hassan

Computer Science Department, Zarqa University, Jordan

Abstract: Arabic language has a complex morphological structure, which makes it hard to select index terms for an IR system. The complexity of the Arabic morphology caused by multimode terms, using diacritics, letters have different forms according to its location in the word and affixes can be added at all locations in a word. Several methods were proposed to overcome these problems; such as root extraction and light stemming. Light stemming show better retrieval efficiency, Light10 is the best stemmer among a series of light stemmers, it simply removes suffixes and prefixes if it is listed in a predefined table. Light10 has no restrictions on the affixes, so it is possible to have two different terms having the same token while they have different meanings. This paper proposes CondLight stemmer which adds new prefixes and suffixes to the table of Light10, and imposes a set of conditions on removing these affixes. The implementation and testing of the proposed method show that CondLight gains 38% precision, while Light10 stemmer gains average precision of 36.7%. Moreover CondLight show better average precision either when imposing all conditions or part of them.

Keywords: Arabic IR,light stemming,morphological analysis, affixes’ removal, term selection, Arabic document indexing.

Received February 14, 2018; accepted April 18, 2018

Dynamic Random Forest for the Recognition of Arabic Handwritten Mathematical Symbols with A Novel Set of Features

Ibtissem Ali and Mohamed Mahjoub

Laboratory of Advanced Technology and Intelligent Systems, University of Sousse, Tunisia

Abstract: Mathematics has a number of characteristics which distinguish it from conventional text and make it a challenging area for recognition. This include principally its two dimensional structure and the diversity of used symbols, especially in Arabic context. Recognition of mathematical formulas requires solving three sub problems: segmentation, the symbol recognition and finally the symbol arrangement analysis. In this paper we will focus on the Arabic mathematical symbol recognition step. This is a challenging task due to the large symbol set with many similar looking symbols used in Arabic mathematics and also the great variability found in human writing. The strength of the selected features and the effectiveness of the classifier are the two key factors determining the performance of a handwritten symbols recognition System .In this paper we proposed a novel Shape Context (SH) descriptor and explored its combination with a modified Chain Code Histogram (CCH) and a Histogram of Oriented Gradient (HOG) at the level of descriptors extraction. For the classification we used a Dynamic Random Forest (DRF) model which has the advantage of efficiently modelling the interaction among trees to determine the right prediction. The results carried out Handwritten Arabic Mathematical Dataset (HAMF) show that the DRF proves a significant improvement in terms of accuracy compared to the standard static RF and Support Vector Machines (SVM).

Keywords: Arabic handwritten mathematical symbols recognition, SH, HOG, CCH, dynamic RF.

A Machine Learning System for Distinguishing

Nominal and Verbal Arabic Sentences

Duaa Abdelrazaq¹, Saleh Abu-Soud², and Arafat Awajan¹

¹Department of Computer Science, Princess Sumaya University for Technology, Jordan

²Department of Software Engineering, Princess Sumaya University for Technology, Jordan

Abstract: The complexity of Arabic language takes origin from the richness in morphology, differences and difficulties of its structures than other languages. Thus, it is important to learn about the specialty and the structure of this language to deal with its complexity. This paper presents a new inductive learning system that distinguishes the nominal and verbal sentences in Modern Standard Arabic (MSA). The use of inductive learning in association with natural language processing is a new and an interdisciplinary collaboration field, specifically in Arabic Language. A series of experiments on 376 well annotated (i.e., Gold Standards) Arabic sentences that range from 2 to 11 words, which present simple to complex MSA sentences, have been conducted. The results obtained showed that the proposed system has distinguished nominal and verbal sentences with an accuracy around 90% for 15% unseen sentences, and around 80% for 75% of unseen sentences.

Keywords: Arabic language processing; natural language processing; inductive learning, ILA.

Received February 14, 2018; accepted April 20, 2018

A new Model of Multi-Key Generation for RFID

Access Control System

Mustafa Al-Fayoumi¹, Malek Al-Zewairi^{1, 2}, and Salam Hamdan¹

¹Computer Science Department, Princess Sumaya University for Technology, Jordan

²Jordan Information Security and Digital Forensics Research Group

Abstract: When studying traditional access control models, one could conclude that they have been proven inefficient in handling modern security threats, with access decisions influenced by several factors, including situational, environmental and risk factors. Accordingly, several studies have proposed risk-aware access control models to overcome the limitations of the traditional models. In this paper, the authors continue to improve on a previously proposed risk adaptive hybrid access control system, in which risk assessment is performed using a multilevel fuzzy inference system, by introducing an enhanced multi-key model for generating the symmetric encryption key dynamically for each user on demand. Consequently, the proposed model helps in solving the issue of having a single point of failure caused by employing a master encryption key, as in the previous models. The experimental results show that the proposed multi-key model does, indeed, improve the overall security of the system while preserving the previous model architecture and with negligible processing overhead.

Keywords: Encryption key generation model, Risk-based access control, Radio frequency identification.

Keyword: Aware-Routing Best First Search (AR-BFS), heuristic function, Wireless Sensor Networks (WSNs), load balancing.

Hybrid Support Vector Machine based Feature Selection Method for Text Classification

Thabit Sabbah¹, Mosab Ayyash¹, and Mahmood Ashraf²

¹Faculty of Technology and Applied Sciences, Al-Quds Open University, Palestine

²Department of Computer Science, Federal Urdu University, Pakistan

Abstract: Automatic text classification is an effective solution used to sort out the increasing amount of online textual content. However, high dimensionality is a considerable impediment observed in the text classification field in spite of the fact that there have been many statistical methods available to address this issue. Still, none of these has proved to be effective enough in solving this problem. This paper proposes a machine learning based feature ranking and selection method named Support Vector Machine based Feature Ranking Method (SVM-FRM). The proposed method utilizes Support Vector Machine (SVM) learning algorithm for weighting and selecting the significant features in order to obtain better classification performance. Later on, hybridization techniques are applied to enhance the performance of SVM-FRM method in some experimental situations. The proposed SVM-FRM method and its enhancement are tested using three text classification public datasets. The achieved results are compared with other statistical feature selection methods currently used for the said purpose. Results evaluation shows higher and superior F-measure and accuracy performances of the proposed SVM-FRM on balanced datasets. Moreover, a noticeable performance enhancement is recorded due to the application of the proposed hybridization techniques on an unbalanced dataset.

Keywords: Feature ranking, text classification, feature selection, SVM-based weighting, hybridization, dimensionality reduction.

Received February 12, 2018; accepted April 22, 2018

Toward a New Arabic Question Answering System

Imane Lahbari, Said El Alaoui, and Khalid Zidani

Computer Science and Modeling Laboratory, Sidi Mohammed Ben Abdellah University, Morocco

Abstract: Question Answering Systems (QAS) aim at returning precise answers to user’s questions that are written in natural language. In this paper, we describe our question processing and document retrieval as two components of Arabic QAS. First, we present Arabic question classification method based on SVM classifier and Li and Roth’s [24] taxonomy. Then, we describe our proposed technique to transform an Arabic question, to a query which is available to get information from the Arabic Wikipedia. In this paper, we use a hybrid Arabic Part-of-Speech (POS) tagging and Arabic WordNet (AWN) for query expansion. We have conducted several experiments using Text Retrieval Conference (TREC) and Cross Lingual Evaluation Forum (CLEF) datasets. The obtained results have shown that the proposed method is more effective as compared with the existing methods.

Keywords: Natural language processing, Arabic question answering system, question classification, taxonomy, machine learning approach, SVM, decision-tree, naive bayes, POS tagging, query expansion, AWN.

Using Deep Learning for Automatically Determining Correct Application of Basic Quranic Recitation Rules

Mahmoud Al-Ayyoub, Nour Alhuda Damer, and Ismail Hmeidi

Jordan University of Science and Technology, Jordan

Abstract: Quranic Recitation Rules (Ahkam Al-Tajweed) are the articulation rules that should be applied properly when reciting the Holy Quran. Most of the current automatic Quran recitation systems focus on the basic aspects of recitation, which are concerned with the correct pronunciation of words and neglect the other Ahkam Al-Tajweed that are related to the rhythmic and melodious way of recitation such as where to stop and how to “stretch” or “merge” certain letters. The only existing works on the latter parts are limited in terms of the rules they consider or the parts of Quran they cover. This paper comes to fill these gaps. It addresses the problem of identifying the correct usage of Ahkam Al-Tajweed in the entire Quran. Specifically, we focus on eight Ahkam Al-Tajweed faced by early learners of recitation. In the first part of our work, we used traditional audio processing techniques for feature extraction (such as Linear predictive Code (LPC), Mel-Frequency Cepstral Coefficient (MFCC), Wavelet Packet Decomposition (WPD) and Markov Model based Spectral Peak Location (HMM-SPL)) and classification (such as k-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Random Forest (RF)) on an in-house dataset of thousands of audio recordings covering all occurrences of the rules under consideration in the entire Holy Quran by different reciters of both genders. In this part, we show how to improve the classification accuracy to surpass 97.7% by incorporating deep learning techniques. Specifically, this result is obtained by incorporating most traditional features with ones extracted using Convolutional Deep Belief Network (CDBN) while the classification is performed using SVM.

Keywords: Articulation rules (Ahkam Al-Tajweed), Mel-Frequency Cepstral Coefficient (MFCC), Linear predictive Code (LPC), Wavelet Packet Decomposition (WPD), Hidden Markov Model based Spectral Peak Location (HMM-SPL), Convolutional Deep Belief Network (CDBN); k-Nearest Neighbors (KNN); Support Vector Machines (SVM); Artificial Neural Network (NN), Random Forest (RF), multiclass classifier, bagging; t-Test.

Critical Proficiencies for Requirements Analysts: Reflect a Real-world Needs

Issam Jebreen and Ahmad Al-Qerem

Faculty of Information Technology, Zarqa University, Jordan

Abstract: Requirements Determination (RD) is regarded as a critical phase of software development, In particular, the involvement of human interaction with RD diversity increase of communication issues such as miscommunication, misunderstandings between stakeholders that impact on software projects time and cost. Therefore, the software analysts’ communication skills are a key factor in project success. Originally analysts’ responsibility is RD tasks, however, due to the variety and the number of tasks that need to be covered, as well as different skills for each task, the sphere of their job is usually extended. This study is explored analysts’ proficiencies in requirement determination. An Ethnography method has been used with software Development Company in order to investigate the analysts’ proficiencies. Our research design conducted through an interpretive philosophy using thematic analysis data-driven approach. We have found that 18 critical proficiencies are impacting situations in which requirement determination occurs. We propose that the analysts’ proficiencies are a set of activities between analysts and users in which requirement determination situations consists of gathering users’ initial requirements follow by deeply understanding of the users’ requirements. Surprisingly, knowledge of requirements analysis and design solution methodologies including the traditional approach did not seem to be critical proficiencies for requirements analysts. In another hand, knowledge of commercial software and business process for various types of commercial business seem to be one of the most important critical proficiencies for requirements analysts.

Keywords: Requirements determination, analysts’ proficiencies.