Unified Inter-Letter Steganographic Algorithm, A Text-based Data Hiding Method

Ahmad Esmaeilkhah¹, Changiz Ghobadi¹, Javad Nourinia¹, and Maryam Majidzadeh²

¹Electrical Engineering Department, Urmia University, Iran

²Department of Electrical and Computer Engineering, Technical and Vocational University, Iran

Abstract: This paper funds a novel text-based steganographic algorithm with enhanced functionality with respect to the previously proposed methods, by careful selection of one of standard space characters, the introduced Inter-Letter Steganographic Method, or Visual and Reverse Extraction attacks, two additional modes of operation have been added to the original InLetSteg algorithm and have been merged into a single one, called as Unified Inter-Letter Steganographic Method, or UILS. The Unified Inter-Letter Steganographic Method (UILS) embeds the data using variable step-size into the host text and the developed mathematical model can calculate the approximate length of the host text required to embed certain data, statistically. In addition, the general mathematical model of UILS makes it customizable to adapt the real-world applications. The statistical parameters that are used through this work are calculated for English host text, but are easily calculable for other languages with similar alphabets and structure of notations. Finally, the programmatically deployed UILS outputs are experimentally examined using 60 attendant and the results are discussed.

Keywords: Steganography, UILS, InLetSteg, Reverse extraction attack, Unicode space character, Inter-letter spacing.

Received June 6, 2018; accepted July 21, 2019

A Self-Healing Model for QoS-aware Web Service Composition

Doaa Elsayed¹, Eman Nasr³, Alaa El Ghazali⁴, and Mervat Gheith²

¹Department of Information Systems and Technology, Cairo University, Egypt

²Department of Computer Science, Cairo University, Egypt

³Independent Researcher, Egypt

⁴Department of Computer and Information Systems, Sadat Academy for Management Sciences, Egypt

Abstract: In the Web Service Composition (WSC) domain, Web Services (WSs) execute in a highly dynamic environment, as a result, the Quality of Service (QoS) of a WS is constantly evolving, and this requires tracking of the global optimization overtime to satisfy the users’ requirements. In order to make a WSC adapt to such QoS changes of WSs, we propose a self-healing model for WSC. Self-healing is the automatic discovery, and healing of the failure of a composite WS by itself due to QoS changes without interruption in the WSC and any human intervention. To the best of our knowledge, almost all the existing self-healing models in this domain substitute the faulty WS with an equivalent one without paying attention to the WS selection processes to achieve global optimization. They focus only on the WS substitution strategy. In this paper, we propose a self-healing model where we use our hybrid approach to find the optimal WSC by using Parallel Genetic Algorithm based on Q-learning, which we integrate with K-means clustering (PGAQK). The components of this model are organized according to IBM’s Monitor, Analyse, Plan, Execute, and Knowledge (MAPE-K) reference model. The PGAQK approach considers as a module in the Execute component. WS substitution strategy has also been applied in this model that substitutes the faulty WS with another equivalent one from a list of candidate WSs by using the K-means clustering technique. K-means clustering is used to prune the WSs in the search space to find the best WSs for the environment changes. We implemented this model over the NET Framework using C# programming language. A series of comparable experiments showed that the proposed model outperforms improved GA to achieve global optimization. Our proposed model also can dynamically substitute the faulty WSs with other equivalent ones in a time-efficient manner.

Keywords: Web service composition, self-healing, quality of service, user requirements; K-means clustering.

Received June 29, 2018; accepted January 28, 2020

Synthesizing Conjunctive and Disjunctive Linear Invariants by K-means++ and SVM

Shengbing Ren and Xiang Zhang

School of Computer Science and Engineering, Central South University, China

Abstract: The problem of synthesizing adequate inductive invariants lies at the heart of automated software verification. The state-of-the-art machine learning algorithms for synthesizing invariants have gradually shown its excellent performance. However, synthesizing disjunctive invariants is a difficult task. In this paper, we propose a method k++ Support Vector Machine (SVM) integrating k-means++ and SVM to synthesize conjunctive and disjunctive invariants. At first, given a program, we start with executing the program to collect program states. Next, k++SVM adopts k-means++ to cluster the positive samples and then applies SVM to distinguish each positive sample cluster from all negative samples to synthesize the candidate invariants. Finally, a set of theories founded on Hoare logic are adopted to check whether the candidate invariants are true invariants. If the candidate invariants fail the check, we should sample more states and repeat our algorithm. The experimental results show that k++SVM is compatible with the algorithms for Intersection Of Half-space (IOH) and more efficient than the tool of Interproc. Furthermore, it is shown that our method can synthesize conjunctive and disjunctive invariants automatically.

Keywords: Software verification, conjunctive invariant, disjunctive invariant, k-means++, SVM.

Received September 5, 2018; accepted January 28, 2020

Recurrence Quantification Analysis of Glottal Signal as non Linear Tool for Pathological Voice Assessment and Classification

Mohamed Dahmani and Mhania Guerti

Laboratoire Signal et Communications, Ecole Nationale Polytechnique, Algiers, Algeria

Abstract: Automatic detection and assessment of Vocal Folds pathologies using signal processing techniques knows an extensively challenge use in the voice or speech research community. This paper contributes the application of the Recurrence Quantification Analysis (RQA) to a glottal signal waveform in order to evaluate the dynamic process of Vocal Folds (VFs) for diagnosis and classify the voice disorders. The proposed solution starts by extracting the glottal signal waveform from the voice signal through an inverse filtering algorithm. In the next step, the parameters of RQA are determined via the Recurrent Plot (RP) structure of the glottal signal where the normal voice is considered as a reference. Finally, these parameters are used as input features set of a hybrid Particle Swarm Optimization-Support Vector Machines (PSO-SVM) algorithms to segregate between normal and pathological voices. For the test validation, we have adopted the collection of Saarbrucken Voice Database (SVD) where we have selected the long vowel /a:/ of 133 normal samples and 260 pathological samples uttered by four groups of subjects : persons having suffered from vocal folds paralysis, persons having vocal folds polyps, persons having spasmodic dysphonia and normal voices. The obtained results show the effectiveness of RQA applied to the glottal signal as a features extraction technique. Indeed, the PSO-SVM as a classification method presented an effective tool for assessment and diagnosis of pathological voices with an accuracy of 97.41%.

Keywords: Glottal Signal, Recurrence Quantification Analysis, Saarbrucken Voice Database, PSO-SVM, Pathological Voice Detection.

Received December 2, 2018; accepted March 23, 2020

Specification of Synchronous Network

Flooding in Temporal Logic

Ra’ed Bani Abdelrahman¹, Rafat Alshorman², Walter Hussak³, and Amitabh Trehan³

¹SoftwareEngineering Department, Ajloun National University, Jordan

²Department of Computer Science, Yarmouk University, Jordan

³Computer Science Department, Loughborough University, United Kindom

Abstract: In distributed network algorithms, network flooding is considered one of the simplest and most fundamental algorithms. This research specifies the basic synchronous memory-less network flooding algorithm where nodes on the network don’t have memory, for any fixed size of network, in Linear Temporal Logic. The specification can be customized to any single network topology or class of topologies. A specification of the termination problem is formulated and used to compare different topologies for earlier termination. This paper gives a worked example of one topology resulting in earlier termination than another, for which we perform a formal verification using the model checker NuSMV.

Keywords: Network flooding, linear temporal logic, model checking.

Received December 17, 2018; accepted June 11, 2019

An Investigative Analysis on Finding Patterns in Co-Author and Co-Institution Networks for LIDAR Research

Imran Ashraf, Soojung Hur, and Yongwan Park

Department of Information and Communication Engineering, Yeungnam University, South Korea

Abstract: Social Network Analysis (SNA) has proven itself to embody the complex relationships between actors of groups inside out. Not only that, but it has also emerged as a new paradigm to investigate the structure of ties and its role on relationships between the actors. This research aims to investigate the patterns of relationships between authors and institutions working in LIght Detection And Ranging (LIDAR) research area. LIDAR has been in the limelight during recent years, especially autonomous vehicles for map-making and objection detection tasks. Researchers need insight into the current contributors and research areas to devise policies and set future targets for this important technology. Current study performs SNA to identify potential institutions and researchers that can help to achieve those goals. National and international co-authorship is analysed separately. A total of 4274 papers from Web of Science (WOS) database are collected from 1998 to September 2017. SNA measures of degree, closeness, betweenness, and eigenvector centrality along with descriptive analysis are employed to study the patterns. Analysis reveals that the United States of America (USA) is the most central and significant country in terms of international co-authorship. China, Germany, the United Kingdom (UK) and Canada are ranked 2^nd, 3^rd, 4^th and 5^th in this list respectively. For co-institution network, National Aeronautics and Space Administration (NASA), University of Idaho and California Institute of Technology USA occupy 1^st, 2^nd, and 5^th position respectively when top 5 institutions are considered. Consiglio NazionaleDelle Ricerche of Italy occupies 3^rd position while Chinese Academy of Science, China, secures 4^th place concerning betweenness centrality. Descriptive analysis reveals that during the last decade, co-author collaboration in scientific research has been elevated. Results show that research articles with 6 or more authors have higher citations than those with two to five authors. In addition, journals producing a higher number of papers and their corresponding citations are also discussed.

Keywords: Social network analysis, co-institution, co-authorship, LIDAR, degree, closeness, Eigenvector.

Received January 1, 2019; accepted April 8, 2020

Wrapper based Feature Selection using Integrative

Teaching Learning Based Optimization Algorithm

Mohan Allam and Nandhini Malaiyappan

Department of Computer Science, Pondicherry University, India

Abstract: The performance of the machine learning models mainly relies on the key features available in the training dataset. Feature selection is a significant job for pattern recognition for finding an important group of features to build classification models with a minimum number of features. Feature selection with optimization algorithms will improve the prediction rate of the classification models. But, tuning the controlling parameters of the optimization algorithms is a challenging task. In this paper, we present a wrapper-based model called Feature Selection with Integrative Teaching Learning Based Optimization (FS-ITLBO), which uses multiple teachers to select the optimal set of features from feature space. The goal of the proposed algorithm is to search the entire solution space without struck in the local optima of features. Moreover, the proposed method only utilizes teacher count parameter along with the size of the population and a number of iterations. Various classification models have been used for finding the fitness of instances in the population and to estimate the effectiveness of the proposed model. The robustness of the proposed algorithm has been assessed on Wisconsin Diagnostic Breast Cancer (WDBC) as well as Parkinson’s Disease datasets and compared with different wrapper-based feature selection techniques, including genetic algorithm and Binary Teaching Learning Based Optimization (BTLBO). The outcomes have confirmed that FS-ITLBO model produced the best accuracy with the optimal subset of features.

Keywords: Feature Selection, Integrative Teaching Learning based Optimization, Genetic Algorithm, Breast Cancer.

Received May 15, 2019; accepted April 10, 2020

Design and Implementation of Crypt Analysis

of Cloud Data Intrusion Management System

Dinesh Elangovan and Ramesh Muthiya

Department of Electronics and Communication Engineering, Anna University, India

Abstract: Cloud computing is the method of employing a set-up of isolated servers to be hosted on the web to accumulate and supervise information instead of an area server or a private laptop. Storage of data in cloud sometimes creates security issues in the data stored so, security in provided for the stored cloud data. In order to provide secured cloud data transaction, our proposed method initially verifies the authentication of the user followed by splitting the information of the user using pattern-matching technique. The blowfish computation is used to encrypt the alienated data. After encryption, resorting to the selection of the optimal position of a data center by means of the cross grey wolf optimization and firefly technique is done. Finally, the encrypted data are stored at an optimal location in the cloud. Then the data split column wise and separated at an optimal location in the cloud, this method is highly secured since the user cannot retrieve the file without authentication verification.

Keywords: Cloud computing, Pattern Matching Technique, Blowfish Algorithm, Hybrid Grey Wolf Optimization and Firefly Technique.

Received July 11, 2019; accepted May 10, 2020

F₀ Modeling for Isarn Speech Synthesis using Deep Neural Networks and Syllable-level Feature Representation

Pongsathon Janyoi and Pusadee Seresangtakul

Department of Computer Science, Khon Kaen University, Thailand

Abstract: The generation of the fundamental frequency (F₀) plays an important role in speech synthesis, which directly influences the naturalness of synthetic speech. In conventional parametric speech synthesis, F₀ is predicted frame-by-frame. This method is insufficient to represent F₀ contours in larger units, especially tone contours of syllables in tonal languages that deviate as a result of long-term context dependency. This work proposes a syllable-level F₀ model that represents F₀ contours within syllables, using syllable-level F₀ parameters that comprise the sampling F₀ points and dynamic features. A Deep Neural Network (DNN) was used to represent the relationships between syllable-level contextual features and syllable-level F₀ parameters. The proposed model was examined using an Isarn speech synthesis system with both large and small training sets. For all training sets, the results of objective and subjective tests indicate that the proposed approach outperforms the baseline systems based on hidden Markov models and DNNS that predict F₀ values at the frame level.

Keywords: Fundamental frequency, speech synthesis, deep neural networks.

Enriching Domain Concepts with Qualitative

Attributes: A Text Mining based Approach

Niyati Kumari Behera and Guruvayur Suryanarayanan Mahalakshmi

Department of Computer Science and Engineering, Anna University, India

Abstract: Attributes, whether qualitative or non-qualitative are the formal description of any real-world entity and are crucial in modern knowledge representation models like ontology. Though ample evidence for the amount of research done for mining non-qualitative attributes (like part-of relation) extraction from text as well as the Web is available in the wealth of literature, on the other side limited research can be found relating to qualitative attribute (i.e., size, color, taste etc.,) mining. Herein this research article an analytical framework has been proposed to retrieve qualitative attribute values from unstructured domain text. The research objective covers two aspects of information retrieval (1) acquiring quality values from unstructured text and (2) then assigning attribute to them by comparing the Google derived meaning or context of attributes as well as quality value (adjectives). The goal has been accomplished by using a framework which integrates Vector Space Modelling (VSM) with a probabilistic Multinomial Naive Bayes (MNB) classifier. Performance Evaluation has been carried out on two data sets (1) HeiPLAS Development Data set (106 adjective-noun exemplary phrases) and (2) a text data set in Medicinal Plant Domain (MPD). System is found to perform better with probabilistic approach compared to the existing pattern-based framework in the state of art.

Keywords: Information retrieval, text mining, qualitative attribute, adjectives, natural language processing.

Received July 24, 2019; accepted May 4, 2020

Polynomial Based Fuzzy Vault Technique for

Template Security in Fingerprint Biometrics

Reza Mehmood and Arvind Selwal

Department of Computer Science and Information Technology, Central University of Jammu, India

Abstract: In recent years the security breaches and fraud transactions are increasing day by day. So there is a necessity for highly secure authentication technologies. The security of an authentication system can be strengthened by using Biometric system rather than the traditional method of authentication like Identity Cards (ID) and password which can be stolen easily. A biometric system works on biometric traits and fingerprint has the maximum share in market for providing biometric authentication as it is reliable, consistent and easy to capture. Although the biometric system is used to provide security to many applications but it is susceptible to different types of assaults too. Among all the modules of the biometric system which needs security, biometric template protection has received great consideration in the past years from the research community due to sensitivity of the biometric data stored in the form of template. A number of methods have been devised for providing template protection. Fuzzy vault is one of the cryptosystem based method of template security. The aim of fuzzy vault technique is to protect the precarious data with the biometric template in a way that only certified user can access the secret by providing valid biometric. In this paper, a modified version of fuzzy vault is presented to increase the level of security to the template and the secret key. The polynomial whose coefficients represent the key is transformed using an integral operator to hide the key where the key can no longer be derived if the polynomial is known to the attacker. The proposed fuzzy vault scheme also prevents the system from stolen key inversion attack. The results are achieved in terms of False Accept Rate (FAR), False Reject Rate (FRR), Genuine Acceptance Rate (GAR) by varying the degree of polynomial and number of biometric samples. It was calculated that for 40 users GAR was found to be 92%, 90%, 85% for degree of polynomial to be 3, 4 and 5 respectively. It was observed that increasing the degree of polynomial decreased the FAR rate, thus increasing the security.

Keywords: Biometrics, Fingerprint, Template Security, Crypto-System, Fuzzy vault.

A Deep Learning Approach for the Romanized

Tunisian Dialect Identification

                Jihene Younes¹, Hadhemi Achour¹, Emna Souissi², and Ahmed Ferchichi¹ 

¹Université de Tunis, ISGT, Tunisia

²Université de Tunis, ENSIT, Tunisia

Abstract: Language identification is an important task in natural language processing that consists in determining the language of a given text. It has increasingly picked the interest of researchers for the past few years, especially for code-switching informal textual content. In this paper, we focus on the identification of the Romanized user-generated Tunisian dialect on the social web. We segment and annotate a corpus extracted from social media and propose a deep learning approach for the identification task. We use a Bidirectional Long Short-Term Memory neural network with Conditional Random Fields decoding (BLSTM-CRF). For word embeddings, we combine word-character BLSTM vector representation and Fast Text embeddings that takes into consideration character n-gram features. The overall accuracy obtained is 98.65%.

Keywords: Tunisian dialect, language identification, deep learning, BLSTM, CRF and natural language processing.

Received August 25, 2019; accepted April 28, 2020

Computer Vision-based Early Fire Detection Using Enhanced Chromatic Segmentation and Optical Flow Analysis Technique

Arnisha Khondaker¹, Arman Khandaker¹, and Jia Uddin^2
1Department of Computer Science and Engineering, BRAC University, Bangladesh
²Department of Technology Studies, Woosong University, South Korea

Abstract: Recent advances in video processing technologies have led to a wave of research on computer vision-based fire detection systems. This paper presents a multi-level framework for fire detection that analyses patterns in chromatic information, shape transmutation, and optical flow estimation of fire. First, the decision function of fire pixels based on chromatic information uses majority voting among state-of-the-art fire color detection rules to extract the regions of interest. The extracted pixels are then verified for authenticity by examining the dynamics of shape. Finally, a measure of turbulence is assessed by an enhanced optical flow analysis algorithm to confirm the presence of fire. To evaluate the performance of the proposed model, we utilize videos from the Mivia and Zenodo datasets, which have a diverse set of scenarios including indoor, outdoor, and forest fires, along with videos containing no fire. The proposed model exhibits an average accuracy of 97.2% for our tested dataset. In addition, the experimental results demonstrate that the proposed model significantly reduces the rate of false alarms compared to the other existing models.

Keywords: Fire detection, color segmentation, shape analysis, optical flow analysis, Lucas-Kanade tracker, neural network.

Received September 26, 2019; accepted March 17, 2020

A Sentiment Analysis System for the Hindi

Language by Integrating Gated Recurrent

Unit with Genetic Algorithm

Kush Shrivastava and Shishir Kumar

Department of Computer Science Engineering, Jaypee University of Engineering and Technology, India

Abstract: The growing availability and popularity of opinion rich resources such as blogs, shopping websites, review portals, and social media platforms have attracted several researchers to perform the sentiment analysis task. Unlike English, Chinese, Spanish, etc. the availability of Indian languages such as Hindi, Telugu, Tamil, etc., over the web have also been increased at a rapid rate. This research work understands the growing popularity of Hindi language in the web domain and considered it for the task of sentiment analysis. The research work analyses the hidden sentiments from the movie reviews collected from the review section of Hindi language e-newspapers. The reviews are multilingual, which makes sentiment analysis a challenging task. To overcome the challenges, this research work proposes a deep learning based approach where a Gated Recurrent Unit network is combined with the Hindi word embedding model. The strategy enables the network to efficiently capture the semantic and syntactic relation between Hindi words and accurately classify them into the sentiment classes. Gated Recurrent Unit network's performance is profoundly dependent upon the selection of its hyper-parameters; therefore, this research work also utilizes a Genetic Algorithm to automatically build a gated recurrent network architecture enabling it to select the best optimal hyper-parameters. It has been observed that the proposed Genetic Algorithm-Gated Recurrent Unit (GA-GRU) model is effective and achieves breakthrough performance results on the Hindi movie review dataset as compared to other traditional resource-based and machine learning approaches.

Keywords: Sentiment analysis, Hindi language, multilingual, deep learning, gated recurrent unit, genetic algorithm.

Received September 28, 2019; accepted May 9, 2020

Traceable Signatures using Lattices

Thakkalapally Preethi and Bharat Amberker

Department of Computer Science and Engineering, National Institute of Technology Warangal, India

Abstract: Traceable Signatures is an extension of group signatures that allow tracing of all signatures generated by a particular group member without violating the privacy of remaining members. It also allows members to claim the ownership of previously signed messages. Till date, all the existing traceable signatures are based on number-theoretic assumptions which are insecure in the presence of quantum computers. This work presents the first traceable signature scheme in lattices, which is secure even after the existence of quantum computers. Our scheme is proved to be secure in the random oracle model based on the hardness of Short Integer Solution and Learning with Errors.

Keywords: Traceable Signatures, Lattices, Short Integer Solution, Learning with Errors.

Received October 7, 2019; accepted May 5, 2020

A Dynamic Particle Swarm Optimisation and Fuzzy Clustering Means Algorithm for Segmentation of Multimodal Brain Magnetic Resonance Image Data

Kies Karima and Benamrane Nacera

Department of Computer Science, Université des Sciences et de la Technologie d’Oran “Mohamed Boudiaf”, Algeria

Abstract: Fuzzy Clustering Means (FCM) algorithm is a widely used clustering method in image segmentation, but it often falls into local minimum and is quite sensitive to initial values which are random in most cases. In this work, we consider the extension to FCM to multimodal data improved by a Dynamic Particle Swarm Optimization (DPSO) algorithm which by construction incorporates local and global optimization capabilities. Image segmentation of three-variate MRI brain data is achieved using FCM-3 and DPSOFCM-3 where the three modalities T1-weighted, T2-weighted and Proton Density (PD), are treated at once (the suffix -3 is added to distinguish our three-variate method from mono-variate methods usually using T1-weighted modality). FCM-3 and DPSOFCM-3 were evaluated on several Magnetic Resonance (MR) brain images corrupted by different levels of noise and intensity non-uniformity. By means of various performance criteria, our results show that the proposed method substantially improves segmentation results. For noisiest and most no-uniform images, the performance improved as much as 9% with respect to other methods.

Keywords: Fuzzy c-mean, particle swarm optimization, brain Magnetic Resonance Images segmentation.

Received December 24, 2019; accepted March 10, 2020