A New Hybrid Improved Method for Measuring Concept Semantic Similarity in WordNet

Xiaogang Zhang, Shouqian Sun, and Kejun Zhang

College of Computer Science and Technology, Zhejiang University, Hangzhou, China

Abstract: Computing semantic similarity between concepts is an important issue in natural language processing, artificial intelligence, information retrieval and knowledge management. The measure of computing concept similarity is a fundament of semantic computation. In this paper, we analyze typical semantic similarity measures and note Wu and Palmer’s measure which does not distinguish the similarities between nodes from a node to different nodes of the same level. Then, we synthesize the advantages of measure of path-based and IC-based, and propose a new hybrid method for measuring semantic similarity. By testing on a fragment of WordNet hierarchical tree, the results demonstrate the proposed method accurately distinguishes the similarities between nodes from a node to different nodes of the same level and overcome the shortcoming of the Wu and Palmer’s measure.

Keywords: Information content, Semantic similarity, WordNet taxonomy, Hyponym.

Received May 25, 2017; accepted April 25, 2018

Multi Label Ranking Based on

Positive Pairwise Correlations Among Labels

Raed Alazaidah, Farzana Ahmad, and Mohamad Mohsin

School of Computing, Universiti Utara Malaysia, Malaysia

Abstract: Multi-Label Classification (MLC) is a general type of classification that has attracted many researchers in the last few years. Two common approaches are being used to solve the problem of MLC: Problem Transformation Methods (PTMs) and Algorithm Adaptation Methods (AAMs). This Paper is more interested in the first approach; since it is more general and applicable to any domain. In specific, this paper aims to meet two objectives. The first objective is to propose a new multi-label ranking algorithm based on the positive pairwise correlations among labels, while the second objective aims to propose new simple PTMs that are based on labels correlations, and not based on labels frequency as in conventional PTMs. Experiments showed that the proposed algorithm overcomes the existing methods and algorithms on all evaluation metrics that have been used in the experiments. Also, the proposed PTMs show a superior performance when compared with the existing PTMs.

Keywords: Correlations among labels, multi-label classification, multi-label ranking, problem transformation methods.

Received August 23, 2017; accepted August 2, 2018

Privacy-Preserving Data Aggregation

Framework for Mobile Service

Based Multiuser Collaboration

 Hai Liu¹, Zhenqiang Wu¹, Changgen Peng², Feng Tian¹, and Laifeng Lu³

¹School of Computer Science, Shaanxi Normal University, China

²Guizhou Provincial Key Laboratory of Public Big Data, Guizhou University, China

³School of Mathematics and Information Science, Shaanxi Normal University, China

Abstract: Considering the untrusted server, differential privacy and local differential privacy has been used for privacy-preserving in data aggregation. Through our analysis, differential privacy and local differential privacy cannot achieve Nash equilibrium between privacy and utility for mobile service based multiuser collaboration, which is multiuser negotiating a desired privacy budget in a collaborative manner for privacy-preserving. To this end, we proposed a Privacy-Preserving Data Aggregation Framework (PPDAF) that reached Nash equilibrium between privacy and utility. Firstly, we presented an adaptive Gaussian mechanism satisfying Nash equilibrium between privacy and utility by multiplying expected utility factor with conditional filtering noise under expected privacy budget. Secondly, we constructed PPDAF using adaptive Gaussian mechanism based on negotiating privacy budget with heuristic obfuscation. Finally, our theoretical analysis and experimental evaluation showed that the PPDAF could achieve Nash equilibrium between privacy and utility. Furthermore, this framework can be extended to engineering instances in a data aggregation setting.

Keywords: Differential privacy, Nash equilibrium, conditional filtering noise, adaptive Gaussian mechanism, PPDAF.

Received November 22, 2017; accepted October 4, 2018

Design and Implementation of Inter-operable and Secure Agent Migration Protocol

Shakir-Ullah Shah¹, Jamil Ahmad², and Najeeb-ur-Rehman³

¹Department of Computing and Technology,Iqra University Islamabad, Pakistan

²Department of Computer Science, University of Science and Technology (KUST), Pakistan

³Department of Computer Science, University of Gujrat, Pakistan

Abstract: Mobile agent technology is an active research topic and has found its uses in various diverse areas ranging from simple personal assistance to complex distributed big data systems. Its usage permits offline and autonomous execution as compared to classical distributed systems. The free roaming nature of agents makes it prone to several security threats during its transit state, with an added overhead in its interoperability among different types of platforms. To address these problems, both software and hardware based approaches have been proposed to ensure protection at various transit points. However, these approaches do not ensure interoperability and protection to agents during transit over a channel, simultaneously. In this regard, an agent requires a trustworthy, interoperable, and adaptive protocol for secure migration. In this paper, to answer these research issues, we first analyse security flaws in existing agent protection frameworks. Second, we implemented a novel migration architecture which is: 1) fully inter-operable compliance to the Foundation for Intelligent Physical Agents (FIPA) and 2) trustworthy based on Computing Trusted Platform Module (TPM). The proposed approach is validated by testing on software TPM of IBM, JSR321, and jTPMTools as TPM and Trusted Computing Software Stack (TSS) interfaces, JADE-agent framework and 7Mobility Service (JIPMS). Validation is also performed on systems bearing physical TPM-chips. Moreover, some packages of JIPMS are also modified by embedding our proposed approach into their functions. Our performance results show that our approach merely adds an execution overhead during the binding and unbinding phases.

Keywords: Information Security, Multi-Agent Systems, Inter-Platform Agent Mobility, JADE, Trusted Computing.

Received October 9, 2018; accepted February 24, 2019

3D Radon Transform for Shape Retrieval Using Bag-of-Visual-Features

Jinlin Ma and Ziping Ma

College of Computer Science and Engineering, North Minzu University, China

Abstract: In order to improve the accuracy and efficiency of extracting features for 3D models retrieval, a novel approach using 3D radon transform and Bag-of-Visual-Features is proposed in this paper. Firstly the 3D radon transform is employed to obtain a view image using the different features in different angels. Then a set of local descriptor vectors are extracted by the SURF algorithm from the local features of the view. The similarity distance between geometrical transformed models is evaluated by using K-means algorithm to verify the geometric invariance of the proposed method. The numerical experiments are conducted to evaluate the retrieval efficiency compared to other typical methods. The experimental results show that the change of parameters has small effect on the retrieval performance of the proposed method.

Keywords: 3D radon transform, Bag-of-Visual-Features, 3D models retrieval, K-means algorithm.

Received March 6, 2018; accepted January 28, 2020

https://doi.org/10.34028/iajit/17/4/5

Full Text     

Swarm Intelligence Approach to QRS Detection

Mohamed Belkadi and Abdelhamid Daamouche

Signals and Systems Laboratory, Institute of Electrical and Electronics Engineering, Universite M’Hamed Bougara de Boumerdes, Algeria

Abstract: The QRS detection is a crucial step in ECG signal analysis; it has a great impact on the beats segmentation and in the final classification of the ECG signal. The Pan-Tompkins is one of the first and best-performing algorithms for QRS detection. It performs filtering for noise suppression, differentiation for slope dominance, and thresholding for decision making. All of the parameters of the Pan-Tompkins algorithm are selected empirically. However, we think that the Pan-Tompkins method can achieve better performance if the parameters were optimized. Therefore, we propose an adaptive algorithm that looks for the best set of parameters that improves the Pan-Tompkins algorithm performance. For this purpose, we formulate the parameter design as an optimization problem within a particle swarm optimization framework. Experiments conducted on the 24 hours recording of the MIT/BIH arrhythmia benchmark dataset achieved an overall accuracy of 99.83% which outperforms the state-of-the-art time-domain algorithms.

Keywords: ECG, QRS detection, Pan-Tompkins algorithm, Particle Swarm Optimization.

Received October 9, 2018; accepted November 5, 2019

Intelligent Association Classification Technique for Phishing Website Detection

Mustafa Al-Fayoumi¹, Jaber Alwidian², and Mohammad Abusaif²

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

²Big Data Department, Intrasoft Middle East, Jordan

Abstract: Many critical applications need more accuracy and speed in the decision making process. Data mining scholars developed set of artificial automated tools to enhance the entire decisions based on type of application. Phishing is one of the most critical application needs for high accuracy and speed in decision making when a malicious webpage impersonates as legitimate webpage to acquire secret information from the user. In this paper, we proposed a new Association Classification (AC) algorithm as an artificial automated tool to increase the accuracy level of the classification process that aims to discover any malicious webpage. An Intelligent Association Classification (IAC) algorithm developed in this article by employing the Harmonic Mean measure instead of the support and confidence measure to solve the estimation problem in these measures and discovering hidden pattern not generated by the existing AC algorithms. Our algorithm compared with four well-known AC algorithm in terms of accuracy, F1, Precision, Recall and execution time. The experiments and the visualization process show that the IAC algorithm outperformed the others in all cases and emphasize on the importance of the general and specific rules in the classification process.

Keywords: Data mining, Association Classification technique, Apriori algorithm, Phishing.

Received January 28, 2019; accepted March 28, 2019

https://doi.org/10.34028/iajit/17/4/7

Full Text    

   Connectionist Temporal Classification Model for Dynamic Hand Gesture Recognition using RGB and Optical flow Data

Sunil Patel¹ and Ramji Makwana²

¹Computer Engineering Department, Gujarat Technological University, India

²Managing Director, AIIVINE PXL Pvt. Ltd, India

Abstract: Automatic classification of dynamic hand gesture is challenging due to the large diversity in a different class of gesture, Low resolution, and it is performed by finger. Due to a number of challenges many researchers focus on this area. Recently deep neural network can be used for implicit feature extraction and Soft Max layer is used for classification. In this paper, we propose a method based on a two-dimensional convolutional neural network that performs detection and classification of hand gesture simultaneously from multimodal Red, Green, Blue, Depth (RGBD) and Optical flow Data and passes this feature to Long-Short Term Memory (LSTM) recurrent network for frame-to-frame probability generation with Connectionist Temporal Classification (CTC) network for loss calculation. We have calculated an optical flow from Red, Green, Blue (RGB) data for getting proper motion information present in the video. CTC model is used to efficiently evaluate all possible alignment of hand gesture via dynamic programming and check consistency via frame-to-frame for the visual similarity of hand gesture in the unsegmented input stream. CTC network finds the most probable sequence of a frame for a class of gesture. The frame with the highest probability value is selected from the CTC network by max decoding. This entire CTC network is trained end-to-end with calculating CTC loss for recognition of the gesture. We have used challenging Vision for Intelligent Vehicles and Applications (VIVA) dataset for dynamic hand gesture recognition captured with RGB and Depth data. On this VIVA dataset, our proposed hand gesture recognition technique outperforms competing state-of-the-art algorithms and gets an accuracy of 86%.

Keywords: Connectionist temporal classification, Long-short term memory, Hand gesture, Convolutional neural network, VIVA.

Received February 2, 2019; accepted July 28, 2019

https://doi.org/10.34028/iajit/17/4/8

Full Text   

An Effective Framework for Speech and Music Segregation

Sidra Sajid, Ali Javed, and Aun Irtaza

Department of Software Engineering, University of Engineering and Technology Taxila, Pakistan

Abstract: Speech and music segregation from a single channel is a challenging task due to background interference and intermingled signals of voice and music channels. It is of immense importance due to its utility in wide range of applications such as music information retrieval, singer identification, lyrics recognition and alignment. This paper presents an effective method for speech and music segregation. Considering the repeating nature of music, we first detect the local repeating structures in the signal using a locally defined window for each segment. After detecting the repeating structure, we extract them and perform separation using a soft time-frequency mask. We apply an ideal binary mask to enhance the speech and music intelligibility. We evaluated the proposed method on the mixtures set at -5 dB, 0 dB, 5 dB from Multimedia Information Retrieval-1000 clips (MIR-1K) dataset. Experimental results demonstrate that the proposed method for speech and music segregation outperforms the existing state-of-the-art methods in terms of Global-Normalized-Signal-to-Distortion Ratio (GNSDR) values.

Keywords: Ideal binary mask, source segregation, repeating pattern, spectrogram, speech intelligibility.

Received December 7, 2017; accepted October 28, 2018 

https://doi.org/10.34028/iajit/17/4/9

Full Text    

Enhanced Bagging (eBagging): A Novel Approach for Ensemble Learning

Goksu Tuysuzoglu¹ and Derya Birant²

¹Graduate School of Natural and Applied Sciences, Dokuz Eylul University, Turkey

²Department of Computer Engineering, Dokuz Eylul University, Turkey

Abstract: Bagging is one of the well-known ensemble learning methods, which combines several classifiers trained on different subsamples of the dataset. However, a drawback of bagging is its random selection, where the classification performance depends on chance to choose a suitable subset of training objects. This paper proposes a novel modified version of bagging, named enhanced Bagging (eBagging), which uses a new mechanism (error-based bootstrapping) when constructing training sets in order to cope with this problem. In the experimental setting, the proposed eBagging technique was tested on 33 well-known benchmark datasets and compared with both bagging, random forest and boosting techniques using well-known classification algorithms: Support Vector Machines (SVM), decision trees (C4.5), k-Nearest Neighbour (kNN) and Naive Bayes (NB). The results show that eBagging outperforms its counterparts by classifying the data points more accurately while reducing the training error.

Keywords: Bagging, boosting, classification algorithms, machine learning, random forest, supervised learning.

Received July 31, 2018; accepted December12, 2019

Conceptual Persian Text Summarizer: A New Model in Continuous Vector Space

Mohammad Ebrahim Khademi, Mohammad Fakhredanesh, and Seyed Mojtaba Hoseini

Faculty of Electrical and Computer Engineering, Malek Ashtar University of Technology, Iran

Abstract: Traditional methods of summarization are not cost-effective and possible today. Extractive summarization is a process that helps to extract the most important sentences from a text automatically, and generates a short informative summary. In this work, we propose a novel unsupervised method to summarize Persian texts. The proposed method adopt a hybrid approach that clusters the concepts of the text using deep learning and traditional statistical methods. First we produce a word embedding based on Hamshahri2 corpus and a dictionary of word frequencies. Then the proposed algorithm extracts the keywords of the document, clusters its concepts, and finally ranks the sentences to produce the summary. We evaluated the proposed method on Pasokh single-document corpus using the ROUGE evaluation measure. Without using any hand-crafted features, our proposed method achieves better results than the state-of-the-art related work results. We compared our unsupervised method with the best supervised Persian methods and we achieved an overall improvement of ROUGE-2 recall score of 7.5%.

Keywords: Extractive Text Summarization, Unsupervised Learning, Language Independent Summarization, Continuous Vector Space, Word Embedding, Natural Language Processing.

Received September 17, 2018; accepted Febreuary 5 , 2020

Query Authentication of Outsourced

Spatial Database

Jun Hong^1,2, Tao Wen², and Quan Guo³

¹School of Software, North University of China, China

²School of Computer Science and Engineering, Northeastern University, China

 ³Computer Science and Technology, Dalian Neusoft University of Information, China

Abstract: Outsourcing spatial database to a third party is becoming a common practice for more and more individuals and companies to save the cost of managing and maintaining database, where a data owner delegates its spatial data management tasks to a third party and grants it to provide query services. However, the third party is not full trusted. Thus, authentication information should be provided to the client for query authentication. In this paper, we introduce an efficient space authenticated data structure, called Verifiable Similarity Indexing tree (VSS-tree), to support authenticated spatial query. We build VSS-tree based on SS-tree which employs bounding sphere rather than bounding rectangle for region shape and extend it with authentication information. Based on VSS-tree, the third party finds query results and builds their corresponding verification object. The client performs query authentication using the verification object and the public key published. Finally, we evaluate the performance and validity of our algorithms, the experiment results show that VSS-tree can efficiently support spatial query and have better performance than Merkle R tree (MR-tree).

Keywords: Data Outsourcing, KNN, spatial database, cloud computing, query authentication.

Received February 7, 2017; accepted December 24, 2018

Generation of Chaotic Signal for

Scrambling Matrix Content

Naziha Khlif, Ahmed Ghorbel, Walid Aydi, and Nouri Masmoudi

Laboratory of Electronics and Information Technologies, Sfax University, Tunisia

Abstract: Very well evolved, information technology made so easy the transfer of all types of data over public channels. For this reason, ensuring data security is certainly a necessary requirement. Scrambling data is one solution to hide information from non authorized users. Presenting matrix content, image scrambling can be made by only adding a mask to the real content. A user, having the appropriate mask, can recognize the image content by only subtracting it. Chaotic function is recently used for image encryption. In this paper, an algorithm of image scrambling based on three logistic chaotic functions is proposed. Defined by its initial condition and parameter, each chaotic function will generate a random signal. The set of initial conditions and parameters is the encryption key. The performance of this technique is ensured for two great reasons. First, using masks on the image makes unintelligible its content. Second, using three successive encryption processes makes so difficult attacks. This point reflects, in one hand, a sufficient key length to resist to brute force attack. In the other hand, it reflects the random aspect of the pixel distribution in the scrambled image. That means, the randomness in one mask minimizes the correlations really existent between neighboring pixels. That makes our proposed approach resistant to known attacks and suitable for applications requiring secure data transfer such as medical image exchanged between doctors.

Keywords: Chaotic signal, scrambling, image encryption.

Received April 16, 2017; accepted October 2, 2018

Finger Knuckle Print Recognition

using MMDA with Fuzzy Vault 

MuthuKumar Arunachalamand and Kavipriya Amuthan

Department of Electronics and Communication Engineering, Kalasalingam Academy of Research Education, India

Abstract: Currently frequent biometric scientific research such as with biometric applications like face, iris, voice, hand-based biometrics traits like palm print and fingerprint technique are utilized for spotting out the persons. These specific biometrics habits have their own improvement and weakness so that no particular biometrics can adequately opt for all terms like the accuracy and cost of all applications. In recent times, in addition, to distinct with the hand-based biometrics technique, Finger Knuckle Print (FKP) has been appealed to boom the attention among biometric researchers. The image template pattern formation of FKP embraces the report that is suitable for spotting the uniqueness of individuality. This FKP trait observes a person based on the knuckle print and the framework in the outer finger surface. This FKP feature determines the line anatomy and finger structures which are well established and persistent throughout the life of an individual. In this paper, a novel method for personal identification will be introduced, along with that data to be stored in a secure way has also been proposed. The authentication process includes the transformation of features using 2D Log Gabor filter and Eigen value representation of Multi-Manifold Discriminant Analysis (MMDA) of FKP. Finally, these features are grouped using k-means clustering for both identification and verification process. This proposed system is initialized based on the FKP framework without a template based on the fuzzy vault. The key idea of fuzzy vault storing is utilized to safeguard the secret key in the existence of random numbers as chaff pints.  

Keywords: Finger Knuckle Print (FKP),2D Gabor filter, Multi-Manifold Discriminant analysis (MMDA),Fuzzy Vault

Received January 5, 2018; accepted December 17, 2019

An Improved Framework for Modelling

Data Warehouse Systems Using UML Profile

Muhammad Babar¹, Akmal Khattak², Fahim Arif³, and Muhammad Tariq⁴

¹Department of Computing and Technology, Iqra University, Pakistan

²Department of Computer Sciences, Quaid-i-Azam University, Pakistan

³Signal College, National University of Sciences and Technology, Pakistan

⁴Abu Dhabi School of Management, Abu Dhabi, UAE

Abstract: Data Warehouse (DW) applications provide past detail for judgment process for the companies. It is acknowledged that these systems depend on Multidimensional (MD) modelling different from traditional database modelling. MD modelling keeps data in the form of facts and dimensions. Some proposals have been presented to achieve the modelling of these systems, but none of them covers the MD modelling completely. There is no any approach which considers all the major components of MD systems. Some proposals provide their proprietary visual notations, which force the architects to gain knowledge of new precise model. This paper describes a framework which is in the form of an extension to Unified Modelling Language (UML). UML is worldwide known to design a variety of perspectives of software systems. Therefore, any method using the UML reduces the endeavour of designers in understanding the novel notations. Another exceptional characteristic of the UML is that it can be extended to bring in novel elements for different domains. In addition, the proposed UML profile focuses on the accurate representations of the properties of the MD systems based on domain specific information. The proposed framework is validated using a specific case study. Moreover, an evaluation and comparative analysis of the proposed framework is also provided to show the efficiency of the proposed work.

Key Words: UML Profile, Data Warehouse, UML, MD Modelling.

Received February 13, 2017; accepted June 18, 2019

Persian Handwritten Digit Recognition Using Combination of Convolutional Neural Network and Support Vector Machine Methods

Mohammad Parseh, Mohammad Rahmanimanesh, and Parviz Keshavarzi

Faculty of Electrical and Computer Engineering, Semnan University, Iran

Abstract: Persian handwritten digit recognition is one of the important topics of image processing which significantly considered by researchers due to its many applications. The most important challenges in Persian handwritten digit recognition is the existence of various patterns in Persian digit writing that makes the feature extraction step to be more complicated.Since the handcraft feature extraction methods are complicated processes and their performance level are not stable, most of the recent studies have concentrated on proposing a suitable method for automatic feature extraction. In this paper, an automatic method based on machine learning is proposed for high-level feature extraction from Persian digit images by using Convolutional Neural Network (CNN). After that, a non-linear multi-class Support Vector Machine (SVM) classifier is used for data classification instead of fully connected layer in final layer of CNN. The proposed method has been applied to HODA dataset and obtained 99.56% of recognition rate. Experimental results are comparable with previous state-of-the-art methods.

Keywords: Handwritten Digit Recognition, Convolutional Neural Network, Support Vector Machine.

Received January 1, 2019; accepted November 11, 2019