Computer Networks and Distributed Systems
Gholamhossein Ekbatanifard; Omid Yousefi
Volume 5, Issue 2 , May 2019, Pages 57-70
Abstract
The Internet of Things (IoT) and social networking integration, create a new concept named Social Internet of Things (SIoT) according to which the things are able to autonomously establish social relationships with regard to the owners. Things in SIoT operate according to a service-oriented architecture. ...
Read More
The Internet of Things (IoT) and social networking integration, create a new concept named Social Internet of Things (SIoT) according to which the things are able to autonomously establish social relationships with regard to the owners. Things in SIoT operate according to a service-oriented architecture. There may be misbehaving owners and consequently misbehaving devices that can perform harmful attacks based on their social relationships with other things for their own gain at the expense of other IoT devices. This motivates us to work on the issue of how to estimate the trust of a service provider to avoid malicious service providers and select the best service provider. In this paper, a novel trust management model is proposed based on four properties. The model deals with attacks (especially on-off attacks) and considers service levels for services provided by each node. A method to provide different levels of services via SIoT devices, and a new trust assessment scheme are the contributions of this paper. We evaluated the proposed scheme with extensive simulations and the results show that the proposed model can effectively select the best service provider and cope with most trust related attacks.
Pattern Analysis and Intelligent Systems
Masoud Barkhan; Fattah Alizadeh; Vafa Maihami
Volume 5, Issue 2 , May 2019, Pages 71-80
Abstract
For many years, speech has been the most natural and efficient means of information exchange for human beings. With the advancement of technology and the prevalence of computer usage, the design and production of speech recognition systems have been considered by researchers. Among this, lip-reading ...
Read More
For many years, speech has been the most natural and efficient means of information exchange for human beings. With the advancement of technology and the prevalence of computer usage, the design and production of speech recognition systems have been considered by researchers. Among this, lip-reading techniques encountered with many challenges for speech recognition, that one of the challenges being the noise in some situations, which is the main cause of errors in the correct diagnosis of speech. One of the ways for solving this problem is image processing, that in this study, the purpose has been designing and implementing a system for automatic recognition of Persian letters through image-processing techniques. For this purpose, after providing a database for Persian verbal phonetics, we first used image processing techniques to eliminate the presence of noises and detect the cantor in lip, in which we used edge detection to identify the edges of the lip. After finding the upper and lower points of the lip for five frames of each film, we used the mean gap between the upper and lower points of the lip as the characteristic of each phoneme and then by providing a database of these features, with the help of the back propagation artificial neural network and The radial basis function have categorized these phonemes, which ultimately achieved the desired results in the categorization of the phonemes. Of course, the precision of classification using the back propagation artificial neural network has been more than radial basis function ANN.
Software Engineering and Information Systems
Saeid Khajehvand; Seyed Mahdi Abtahi
Volume 5, Issue 2 , May 2019, Pages 81-92
Abstract
In this paper, chaotic dynamic and nonlinear control in a glucose-insulin system in types I diabetic patients and a healthy person have been investigated. Chaotic analysis methods of the blood glucose system include Lyapunov exponent and power spectral density based on the time series derived from the ...
Read More
In this paper, chaotic dynamic and nonlinear control in a glucose-insulin system in types I diabetic patients and a healthy person have been investigated. Chaotic analysis methods of the blood glucose system include Lyapunov exponent and power spectral density based on the time series derived from the clinical data. Wolf's algorithm is used to calculate the Lyapunov exponent, which positive values of the Lyapunov exponent mean the dynamical system is chaotic. Also, a wide range in frequency spectrum based on the power spectral density is also used to confirm the chaotic behavior. In order to control the chaotic system and reach the desired level of a healthy person's glucose, a novel fuzzy high-order sliding mode control method has been proposed. Thus, in the control algorithm of the high-order sliding mode controller, all of the control gains computed by the fuzzy inference system accurately. Then the novel control algorithm is applied to the Bergman's mathematical model that is verified using the clinical data set. In this system, the control input is the amount of insulin injected into the body and the control output is the amount of blood glucose level at any moment. The simulation results of the closed-loop system in various conditions, along with the performance of the control system in disturbance presence, indicate the proper functioning of this controller at the settling time, overshoot and the control inputs.
Pattern Analysis and Intelligent Systems
Jensi R
Volume 5, Issue 2 , May 2019, Pages 93-106
Abstract
Data clustering is the process of partitioning a set of data objects into meaning clusters or groups. Due to the vast usage of clustering algorithms in many fields, a lot of research is still going on to find the best and efficient clustering algorithm. K-means is simple and easy to implement, but it ...
Read More
Data clustering is the process of partitioning a set of data objects into meaning clusters or groups. Due to the vast usage of clustering algorithms in many fields, a lot of research is still going on to find the best and efficient clustering algorithm. K-means is simple and easy to implement, but it suffers from initialization of cluster center and hence trapped in local optimum. In this paper, a new hybrid data clustering approach which combines the modified krill herd and K-means algorithms, named as K-MKH, is proposed. K-MKH algorithm utilizes the power of quick convergence behaviour of K-means and efficient global exploration of Krill Herd and random phenomenon of Levy flight method. The Krill-herd algorithm is modified by incorporating Levy flight in to it to improve the global exploration. The proposed algorithm is tested on artificial and real life datasets. The simulation results are compared with other methods such as K-means, Particle Swarm Optimization (PSO), Original Krill Herd (KH), hybrid K-means and KH. Also the proposed algorithm is compared with other evolutionary algorithms such as hybrid modified cohort intelligence and K-means (K-MCI), Simulated Annealing (SA), Ant Colony Optimization (ACO), Genetic Algorithm (GA), Tabu Search (TS), Honey Bee Mating Optimization (HBMO) and K-means++. The comparison shows that the proposed algorithm improves the clustering results and has high convergence speed.
Computer Networks and Distributed Systems
Olayemi Mikail Olaniyi; Ameh Innocent Ameh; Lukman Adewale Ajao; Omolara Ramota Lawal
Volume 5, Issue 2 , May 2019, Pages 107-116
Abstract
Security is a vital issue in the usage of Automated Teller Machine (ATM) for cash, cashless and many off the counter banking transactions. Weaknesses in the use of ATM machine could not only lead to loss of customer’s data confidentiality and integrity but also breach in the verification of user’s ...
Read More
Security is a vital issue in the usage of Automated Teller Machine (ATM) for cash, cashless and many off the counter banking transactions. Weaknesses in the use of ATM machine could not only lead to loss of customer’s data confidentiality and integrity but also breach in the verification of user’s authentication. Several challenges are associated with the use of ATM smart card such as: card cloning, card skimming, cost of issuance and maintenance. In this paper, we present secure bio-cryptographic authentication system for cardless ATM using enhanced fingerprint biometrics trait and encrypted Personal Identification Number (PIN). Fingerprint biometrics is used to provide automatic identification/verification of a legitimate customer based on unique feature possessed by the customer. Log-Gabor filtering algorithm was used for enhancing low image quality and effect of noise on feature extracted from customer’s fingerprint minutiae. Truncated SHA 512/256 hash algorithm was used to secure the integrity and confidentiality of the PIN from sniffers and possible adversary within the channel of remote ATM banking transactions. Performance evaluation was carried out using False Acceptance Rate (FAR), False Rejection Rate (FRR) metrics and Collision Attack was performed on the Truncated SHA-512/256 hashed data (PIN). Results of the system performance shows Genuine Acceptance Rate (1-FRR) of 97.5% to 100%, Equal Error Rate of 0.0015% and Collision Attack carried out on the encrypted PIN message digest gave an unsuccessful attack. Therefore, the results of performance evaluation show the applicability of the developed system for secure cardless ATM transaction
Pattern Analysis and Intelligent Systems
Mohamed T Elhadi
Volume 5, Issue 2 , May 2019, Pages 117-128
Abstract
Besides for its own merits, text classification (TC) has become a cornerstone in many applications. Work presented here is part of and a pre-requisite for a project we have overtaken to create a corpus for the Arabic text process. It is an attempt to create modules automatically that would help speed ...
Read More
Besides for its own merits, text classification (TC) has become a cornerstone in many applications. Work presented here is part of and a pre-requisite for a project we have overtaken to create a corpus for the Arabic text process. It is an attempt to create modules automatically that would help speed up the process of classification for any text categorization task. It also serves as a tool for the creation of Arabic text corpora. In particular, we create a text classification process for Arabic news articles downloaded from web news portals and sites. The suggested procedure is a pilot project that uses some human predefined set of documents that have been assigned to some subjects or categories. A vectorized Term Frequency, Inverse Document Frequency (TF-IDF) based information processing was used for the initial verification of the categories. The resulting validated categories used to predict categories for new documents. The experiment used 1000 initial documents pre-assigned into five categories of each with 200 documents assigned. An initial set of 2195 documents were downloaded from a number of Arabic news sources. They were pre-processed for use in testing the utility of the suggested classification procedure using the cosine similarity as a classifier. Results were very encouraging with very satisfying precision, recall and F1-score. It is the intention of the authors to improve the procedure and to use it for Arabic corpora creation.