A Novel Secure Video Steganography

Technique using Temporal Lifted

Wavelet Transform and Human Vision

Properties

Ahmed Thahab

Department of Electrical and Electronic Engineering, University of Babylon, Iraq

Abstract: Steganography is a term that refers to the process of concealing secret data inside a cover media which can be audio, image and video. A new video steganography scheme in the wavelet domain is presented in this paper. Since the convolutional discrete wavelet transform produces float numbers, a lifted wavelet transform is used to conceal data. The method embeds secret data in the detail coefficients of each temporal array of the cover video at spatial localization using a unique embedding via YC_bC_r color space and complementing the secret data to minimize error in the stego video before embedding. Three secret keys are used in the scheme. Method’s performance matrices such as peak signal to noise ratio and Normalized Cross Correlation (NCC) expresses good imperceptibility for the stego-video. The value of Peak Signal to Noise Ratio (PSNR) is in range of 34-40dB, and high embedding capacity.

Keywords: Data hiding, integer wavelets transform, color space, peak signal to noise ratio, first complement.

Received January 8, 2017; accepted April 30, 2018
https://doi.org/10.34028/iajit/17/2/1

A Daubechies DWT Based Image Steganography

Using Smoothing Operation

Vijay Sharma, Devesh Srivastava, and Pratistha Mathur

Computer Science and Engineering Department, Manipal University Jaipur, India

Abstract: Steganography is a capability which conceals the top-secret information into cover media (e.g., digital images, sound files etc.,). This Paper presents a secure, higher embedding capacity Discrete Wavelet Transformation (DWT) based technique. Before embedding correlation in between cover and the secret image is increased by multiplying some variable (i.e., 1/k) to the secret image. In embedding process, the Daubechies DWT of both Arnold transformed secret and cover images are taken followed by alpha blending operation. Arnold is a type of scrambling process which increases the confidentiality of secret image and alpha blending is a type of mixing operation of two images, the alpha value indicates the amount of secret image is embedded into the cover image. Daubechies Inverse Discrete Wavelet Transformation (IDWT) of the resulting image is performed to obtain the stego image. Smoothing operation inspired by the Genetic Algorithm (GA) is used to improve the quality of stego-image by minimizing Mean square error and morphological operation is used to extract the image component from the extracted secret image. Simulation results of the proposed steganography technique are also presented. The projected method is calculated on different parameters of image visual quality measurements.

Keywords: Steganography, Daubechies DWT, Arnold transform, smoothing operation, genetic algorithm, morphological operation.

Received March 18, 2017; accepted January 28, 2018
https://doi.org/10.34028/iajit/17/2/2

Full text      

Toward Building Video Multicast Tree with Congestion Avoidance Capability in Software-Defined Networks

Huifen Huang¹, Zhihong Wu², Jin Ge³, and Lu Wang³

¹School of Information Science and Electrical Engineering, ShanDong JiaoTong University, China

²Qilu Hospital, Shandong University, China

³Shandong Provincial Key Laboratory of Computer Networks, SCSC, China

Abstract: Network congestion is an obstacle to a Quality of Service (QoS) guarantee for online video applications, because it leads to a high packet loss rate and long transmission delay. In the Software-Defined Network (SDN), the controller can conveniently obtain the network topology and link bandwidth use situation. Based on the above advantages, an SDN-based video multicast routing solution, called Congestion Avoidance Video Multicast (CAVM), is proposed in this paper. CAVM obtains overall network topology, monitors available bandwidth resource and measures the link delays based on the OpenFlow, a popular SDN southbound interface. We introduce a novel multicast routing problem, named the Delay-Constrained and Minimum Congestion-Cost Multicast Routing (DCMCCMR) problem, which finds the multicast tree with the lowest congestion cost and a source-destination delay constraint in the SDN environment. The DCMCCMR problem is NP-hard. CAVM uses an algorithm to solve it in polynomial time. Our experimental results confirm that the proposed algorithm can build multicast trees with good congestion avoidance capability.

Keywords: Network congestion, multicast, Software-Defined Network, congestion avoidance. 

Received May 21, 2017; accepted May 7, 2018
https://doi.org/10.34028/iajit/17/2/3

Full text      

Gammachirp Filter Banks Applied in Roust Speaker Recognition Based on GMM-UBM Classifier

Lei Deng and Yong Gao

College of Electronics and Information Engineering, Sichuan University, China

Abstract: In this paper, authors propose an auditory feature extraction algorithm in order to improve the performance of the speaker recognition system in noisy environments. In this auditory feature extraction algorithm, the Gammachirp filter bank is adapted to simulate the auditory model of human cochlea. In addition, the following three techniques are applied: cube-root compression method, Relative Spectral Filtering Technique (RASTA), and Cepstral Mean and Variance Normalization algorithm (CMVN).Subsequently, based on the theory of Gaussian Mixes Model-Universal Background Model (GMM-UBM), the simulated experiment was conducted. The experimental results implied that speaker recognition systems with the new auditory feature has better robustness and recognition performance compared to Mel-Frequency Cepstral Coefficients (MFCC), Relative Spectral-Perceptual Linear Predictive (RASTA-PLP),Cochlear Filter Cepstral Coefficients (CFCC) and gammatone Frequency Cepstral Coefficeints (GFCC).

 Keywords: Feature extraction, gammachirp filter bank, RASTA, CMVN, GMM-UBM.

Received May 9, 2017; accepted June 19, 2019
https://doi.org/10.34028/iajit/17/2/4

Full text      

A New Application for Gabor Filters in Face-Based

Gender Classification

Ebrahim Al-Wajih and Moataz Ahmed

Information and Computer Science Department, King Fahd University of Petroleum and Minerals, KSA

Abstract:Human face is one of the most important biometrics as it contains information such as gender, race, and age. Identifying the gender based on human face images is a challenging problem that has been extensively studied due to its various relevant applications. Several approaches were used to address this problem by specifying suitable features. In this study, we present an extension of feature extraction technique based on statistical aggregation and Gabor filters. We extract statistical features from the image of a face after applying Gabor filters; subsequently, we use seven classifiers to investigate the performance of the selected features. Experiments show that the accuracy achieved using the proposed features is comparable to accuracies reported in recent studies. We used seven classifiers to investigate the performance of our proposed features. Experiments reveal that k-Nearest Neighbors algorithm (k-NN), K-Star classifier (K*), and Rotation Forest offer the best accuracies.

Keywords: Gabor filters, gender recognition, statistical features, PCA.

Received September 25, 2017; accepted May 3, 2018
https://doi.org/10.34028/iajit/17/2/5

Full text      

Enhancement of the Heuristic Optimization Based on Extended Space Forests using Classifier Ensembles

Zeynep Kilimci^1,3 and Sevinç Omurca²

¹Department of Computer Engineering, Dogus University, Turkey

²Department of Computer Engineering, Kocaeli University, Turkey

³Department of Information Systems Engineering, Kocaeli University, Turkey

Abstract: Extended space forests are a matter of common knowledge for ensuring improvements on classification problems. They provide richer feature space and present better performance than the original feature space-based forests. Most of the contemporary studies employs original features as well as various combinations of them as input vectors for extended space forest approach. In this study, we seek to boost the performance of classifier ensembles by integrating them with heuristic optimization-based features. The contributions of this paper are fivefold. First, richer feature space is developed by using random combinations of input vectors and features picked out with ant colony optimization method which have high importance and not have been associated before. Second, we propose widely used classification algorithm which is utilized baseline classifier. Third, three ensemble strategies, namely bagging, random subspace, and random forests are proposed to ensure diversity. Fourth, a wide range of comparative experiments are conducted on widely used biomedicine datasets gathered from the University of California Irvine (UCI) machine learning repository to contribute to the advancement of proposed study. Finally, extended space forest approach with the proposed technique turns out remarkable experimental results compared to the original version and various extended versions of recent state-of-art studies.

Keywords: Classifier ensembles, extended space forests, ant colony optimization, decision tree.

Received November 11, 2017; accepted March 11, 2018
https://doi.org/10.34028/iajit/17/2/6

Full text      

MPKC-based Threshold Proxy Signcryption Scheme

Li Huixian¹, Gao Jin¹, Wang Lingyun¹, and Pang Liaojun²

¹School of Computer Science and Engineering, Northwestern Polytechnical University, China

²State Key Laboratory of Integrated Services Networks, Xidian University, China

Abstract: The threshold proxy signcryption can implement signature and encryption simultaneously in one logical step, and can be used to realize the decentralized protection of the group signature key, so it is an efficient technology for network security. Currently, most of the existing threshold proxy signcryption schemes are designed based on the traditional public key cryptosystems, and their security mainly depends on the difficulty of the large integer decomposition and the discrete logarithm. However, the traditional public key cryptosystems cannot resist the quantum computer attack, which makes the existing threshold proxy signcryption schemes based on traditional public key cryptosystems insecure against quantum attacks. Motivated by these concerns, we proposed a threshold proxy signcryption scheme based on Multivariate Public Key Cryptosystem (MPKC) which is one of the quantum attack-resistent public key algorithms. Under the premise of satisfying the threshold signcryption requirements of the threshold proxy, our scheme can not only realize the flexible participation of the proxy signcrypters but also resist the quantum computing attack. Finally, based on the assumption of Multivariate Quadratic (MQ) problem and Isomorphism Polynomial (IP) problem, the proof of the confidentiality and the unforgeability of the proposed scheme under the random oracle model is given.

Keywords: Multivariate public key cryptosystem, signcryption, threshold proxy signcryption, quantum attack.

Received December 5, 2017; accepted May 29, 2019
https://doi.org/10.34028/iajit/17/2/7

Full text      

Referential DNA Data Compression using Hadoop Map Reduce Framework

Raju Bhukya and Sumit Deshmuk

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

Abstract: The indispensable knowledge of Deoxyribonucleic Acid (DNA) sequences and sharply reducing cost of the DNA sequencing techniques has attracted numerous researchers in the field of Genetics. These sequences are getting available at an exponential rate leading to the bulging size of molecular biology databases making large disk arrays and compute clusters inevitable for analysis.In this paper, we proposed referential DNA data compression using hadoop MapReduce Framework to process humongous amount of genetic data in distributed environment on high performance compute clusters. Our method has successfully achieved a better balance between compression ratio and the amount of time required for DNA data compression as compared to other Referential DNA Data Compression methods.

Keywords: Compression, map reduce sequences, dna sequences.

Received August 12, 2017; accepted April 17, 2018
https://doi.org/10.34028/iajit/17/2/8

Full text      

Intrusion Detection Model Using Naive Bayes and Deep Learning Technique

Mohammed Tabash, Mohamed Abd Allah, and Bella Tawfik

Faculty of Computers and Informatics, Suez Canal University, Egypt

Abstract: The increase of security threats and hacking the computer networks are one of the most dangerous issues should treat in these days. Intrusion Detection Systems (IDSs), are the most appropriate methods to prevent and detect the attacks of networks and computer systems. This study presents several techniques to discover network anomalies using data mining tasks, Machine learning technology and dependence of artificial intelligence techniques. In this research, the smart hybrid model was developed to explore any penetrations inside the network. The model divides into two basic stages. The first stage includes the Genetic Algorithm (GA) in selecting the characteristics with depends on a process of extracting, Discretize And dimensionality reduction through Proportional K-Interval Discretization (PKID) and Fisher Linear Discriminant Analysis (FLDA) on respectively. At the end of the first stage combining Naïve Bayes classifier (NB) and Decision Table (DT) using NSL-KDD data set divided into two separate groups for training and testing. The second stage completely depends on the first stage outputs (predicted class) and reclassified with multilayer perceptrons using Deep Learning4J (DL) and the use of algorithm Stochastic Gradient Descent (SGD). In order to improve the performance in terms of the accuracy in classification of penetrations, raising the average of discovering and reducing the false alarms. The comparison of the proposed model and conventional models show the superiority of the proposed model and the previous conventional hybrid models. The result of the proposed model is 99.9325 of classification accuracy, the rate of detection is 99.9738 and 0.00093 of false alarms.

Keywords: Classification, intrusion detection, deep learning, NSL-KDD, genetic algorithm, naïve bayes.

Received December 30, 2017; accepted April 17, 2018

https://doi.org/10.34028/iajit/17/2/9

Full text      

Fault Tolerance Based Load Balancing

Approach for Web Resources in Cloud Environment

Anju Shukla, Shishir Kumar, and Harikesh Singh

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

Abstract: Cloud computing consists group of heterogeneous resources scattered around the world connected through the network. Since high performance computing is strongly interlinked with geographically distributed service to interact with each other in wide area network, Cloud computing makes the architecture consistent, low-cost, and well-suited with concurrent services. This paper presents a fault tolerance load balancing technique based on resource load and fault index value. The proposed technique works in two phases: resource selection and task execution. The resource selection phase selects the suitable resource for task execution. A resource with least resource load and fault index value is selected for task execution. Further task execution phase sets checkpoints at various intervals for saving the task state periodically. The checkpoints are set at various intervals based on resource fault index. When a task is executed on a resource, fault index value of selected resource is updated accordingly. This reduces the checkpoint overhead by avoiding unnecessary placements of checkpoints. The proposed model is validated on CloudSim and provides improved performance in terms of response time, makespan, throughput and checkpoint overhead in comparison to other state-of-the-art methods.

Keywords: Scheduler, checkpoint manager, cloud computing, checkpointing, fault index, high performance computing.

Received June 6, 2018; accepted July 2, 2019
https://doi.org/10.34028/iajit/17/2/10

Full text      

Empirical Evaluation of Leveraging Named Entities

for Arabic Sentiment Analysis

Hala Mulki¹, Hatem Haddad², Mourad Gridach³, and Ismail Babaoğlu¹

¹Computer Engineering Department, Konya Technical University, Turkey

²Computer Science Department, University of Manouba, Tunisia

³Computational Bioscience Departments, University of Colorado Boulder, USA

Abstract: Social media reflects the attitudes of the public towards specific events. Events are often related to persons, locations or organizations, the so-called Named Entities (NEs). This can define NEs as sentiment-bearing components. In this paper, we dive beyond NEs recognition to the exploitation of sentiment-annotated NEs in Arabic sentiment analysis. Therefore, we develop an algorithm to detect the sentiment of NEs based on the majority of attitudes towards them. This enabled tagging NEs with proper tags and, thus, including them in a sentiment analysis framework of two models: supervised and lexicon-based. Both models were applied on datasets of multi-dialectal content. The results revealed that NEs have no considerable impact on the supervised model, while employing NEs in the lexicon-based model improved the classification performance and outperformed most of the baseline systems.

Keywords: Named entity recognition, Arabic sentiment analysis, supervised learning method, lexicon-based method.

Received August 2, 2018; accepted May 21, 2019
https://doi.org/10.34028/iajit/17/2/11

A New Vector Representation of Short Texts for Classification

Yangyang Li and Bo Liu

College of Information Science and Technology, Jinan University, China

Received January 30, 2019; accepted July 2, 2019
https://doi.org/10.34028/iajit/17/2/12

A Hybrid Approach for Providing Improved Link Connectivity in SDN

Muthumanikandan Vanamoorthy¹, Valliyammai Chinnaiah¹, and Harish Sekar²

¹Department of Computer Technology, Madras Institute of Technology, Anna University, India

²Endurance International Group, India

Abstract: Software-Defined Networking (SDN) is a unique approach to design and build networks. The networks services can be better handled by administrators with the abstraction that SDN provides. The problem of re-routing the packets with minimum overhead in case of link failure is handled in this work. Protection and restoration schemes have been used in the past to handle such issues by giving more priority to minimal response time or controller overhead based on the use case. A hybrid scheme has been proposed with per-link Bidirectional forwarding mechanism to handle the failover. The proposed method makes sure that the controller overhead does not impact the flow of packets, thereby decreasing the overall response time, even with guaranteed network resiliency. The computation of the next shortest backup path also guarantees that the subsequent routing of packets always chooses the shortest path available. The proposed method is compared with the traditional approaches and proven by results to perform better with minimal response time.

Keywords: Open flow, SDN, link failure, protection and restoration.

Received October 12, 2018; accepted January 21, 2019
https://doi.org/10.34028/iajit/17/2/13

On 2-Colorability Problem for Hypergraphs with -free Incidence Graphs

Ruzayn Quaddoura

Faculty of Information Technology, Zarqa University, Jordan

Abstract: A 2-coloring of a hypergraph is a mapping from its vertex set to a set of two colors such that no edge is monochromatic. The hypergraph 2- Coloring Problem is the question whether a given hypergraph is 2-colorable. It is known that deciding the 2-colorability of hypergraphs is NP-complete even for hypergraphs whose hyperedges have size at most 3. In this paper, we present a polynomial time algorithm for deciding if a hypergraph, whose incidence graph is -free and has a dominating set isomorphic to , is 2-colorable or not. This algorithm is semi generalization of the 2-colorability algorithm for hypergraph, whose incidence graph is -free presented by Camby and Schaudt.

Keywords: Hypergraph, Dominating set, -free graph, Computational Complexity.

Received December 17, 2018; accepted June 11, 2019
https://doi.org/10.34028/iajit/17/2/14

Full text

Enhanced Median Flow Tracker for Videos with Illumination Variation Based on Photometric Correction

Asha Narayana and Narasimhadhan Venkata

Department of Electronics and Communication Engineering, National Institute of Technology Karnataka, India

Abstract: Object tracking is a fundamental task in video surveillance, human-computer interaction and activity analysis. One of the common challenges in visual object tracking is illumination variation. A large number of methods for tracking have been proposed over the recent years, and median flow tracker is one of them which can handle various challenges. Median flow tracker is designed to track an object using Lucas-Kanade optical flow method which is sensitive to illumination variation, hence fails when sudden illumination changes occur between the frames. In this paper, we propose an enhanced median flow tracker to achieve an illumination invariance to abruptly varying lighting conditions. In this approach, illumination variation is compensated by modifying the Discrete Cosine Transform (DCT) coefficients of an image in the logarithmic domain. The illumination variations are mainly reflected in the low-frequency coefficients of an image. Therefore, a fixed number of DCT coefficients are ignored. Moreover, the Discrete Cosine (DC) coefficient is maintained almost constant all through the video based on entropy difference to minimize the sudden variations of lighting impacts. In addition, each video frame is enhanced by employing pixel transformation technique that improves the contrast of dull images based on probability distribution of pixels. The proposed scheme can effectively handle the gradual and abrupt changes in the illumination of the object. The experiments are conducted on fast-changing illumination videos, and results show that the proposed method improves median flow tracker with outperforming accuracy compared to the state-of-the-art trackers.

Keywords: Illumination variation, median flow tracker, entropy, gamma correction.

Received April 6, 2017; accepted April 25, 2018

https://doi.org/10.34028/iajit/17/2/15

Full text     

FAAD: A Self-Optimizing Algorithm for Anomaly Detection

Adeel Hashmi and Tanvir Ahmad

Department of Computer Engineering, Jamia Millia Islamia, India

Abstract: Anomaly/Outlier detection is the process of finding abnormal data points in a dataset or data stream. Most of the anomaly detection algorithms require setting of some parameters which significantly affect the performance of the algorithm. These parameters are generally set by hit-and-trial; hence performance is compromised with default or random values. In this paper, the authors propose a self-optimizing algorithm for anomaly detection based on firefly meta-heuristic, and named as Firefly Algorithm for Anomaly Detection (FAAD). The proposed solution is a non-clustering unsupervised learning approach for anomaly detection. The algorithm is implemented on Apache Spark for scalability and hence the solution can handle big data as well. Experiments were conducted on various datasets, and the results show that the proposed solution is much accurate than the standard algorithms of anomaly detection. 　

Keywords: Anomaly detection, outliers, firefly algorithm, big data, parallel algorithms and apache spark.

Received November 19, 2017; accepted April 28, 2019 

https://doi.org/10.34028/iajit/17/2/16

Full text