Asian Network for Scientific Information is a leading service provider to the publishers of Science, Technology and Medicine (STM) in Asia. Currently Asian Network for Scientific Information is serving more than 37 peer-reviewed journals covering a wide range of academic disciplines to foster communication among scientists, researchers, students and professionals - enabling them to work more efficiently and intelligently, thereby advancing knowledge and learning.

Journal of Artificial Intelligence
eISSN: 2077-2173
pISSN: 1994-5450

Editor-in-Chief:  Dr. Santosh Kumar Nanda
Current Issue
Guide for Authors
Editorial Board
Article Processing Charges
Research Article
Dictionary Properties for Sparse Representation: Implementation and Analysis
Himanshu Patel and Hiren Mewada
Background and Objective: Linear inverse problems emerge throughout the engineering and the mathematical sciences. Over the last two decades, sparsity constraints have emerged as a fundamental type of regularizer. This paper implements and assesses the role of dictionary miscellany in sparse representation for image processing prospective. Materials and Methods: A dictionary is formed by a linear basis using a mathematical model from the set of images referred as analytic dictionary or using a set of realizations of the images referred as trained dictionary. This study considers the problem of true sparsity formation and analyzes the two most commonly used algorithms-the Matching Pursuit (MP) and Orthogonal Matching Pursuit (OMP) using analytical dictionaries. These methods were compared using diverse dictionaries formation for image restoration applications. Results: The results were validated using peak signal to noise ratio and mean square error of the sparse approximation for the images. The different dictionaries like-discrete wavelet dictionary, Discrete Cosine Transform and Kronecker Delta dictionary and Haar Wavelet Packets and DCT dictionary had been used for implementation of these two algorithms. Conclusion: This experiment showed that the discrete wavelet based dictionary performs best with orthogonal matching pursuit algorithm in terms of MSE and PSNR performances. The result also shows the out performance of OMP in comparison with MP. From the experiments, it has been observed that high number of iterations and small patch size proves to be advantageous.
Research Article
Fuzzy Hybrid Approach for Ranking and Selecting Services in Cloud-based Marketplaces
Azubuike Ezenwoke
Background and Objective: The popularity cloud computing has led to the proliferation of services that are commoditized and traded on cloud e-marketplaces. Besides, user’s cloud service requirements-QoS preferences and aspiration are often shrouded in vagueness and subjectivity. Therefore, cloud service selection can be overwhelming and lead to service choice overload. Existing cloud service selection approaches rarely provide mechanisms to elicit both the QoS preferences and aspirations, but rather considers either of them. This study aimed to design fuzzy-based model for service selection in e-market places that articulates both QoS preferences and aspirations. Materials and Methods: This model comprised a fuzzy Analytic Hierarchy Process (AHP) method for deriving relative priority weights of QoS attributes, a fuzzy decision-making method for obtaining user’s QoS aspiration values and a fuzzy multi-objective optimization module for evaluating the services with respect to user requirements. A simulated experiment was conduct using publicly QoS dataset and ranking accuracy produced by the proposed approach compared to existing methods was measured using Normalize Discounted Cumulative Gain (NCDG) metric. Results: The descriptive and inferential analyses of the ranking results from both versions of the proposed approach produce better accuracy results based on the NCDG metric and were in all cases closer to the benchmark metric than the other two existing methods used in this simulation. Conclusion: Results from current simulation experiment showed that the ranking accuracy of this model is not compromised by subjective QoS information from users and this approach is applicable use the subjective QoS requirements of user’s in ranking services in the cloud e-marketplaces.
Research Article
Children Care System: Controlling the Use of Smart Devices
Luai Al-Shalabi and Yusra Abu Jaradeh
Background and Objective: Smart devices have negative influences on human being and especially on the children health. These negative influences inspire the researchers and the vendors to focus on how to avoid such negative issues. This study described the analysis, design and implementation of the software that controls smart devices. The proposed system gives the default time based on the children age, increases or decreases the time when needed, extends the time when video is playing based on specific rules, produces easy to use, attractive and interactive interface and blocks the device when the time is out. Materials and methods: The activity diagram showed the flow of data required for the system. The system model determined all the component of the system including the functions, the database, the interfaces and the users. The algorithm generated from the model. The proposed system compared with twenty available similar applications in the play store using seven features. Results: The authors tested the system against different types of users. The feedbacks of parents and children were highly promising. Results showed that 86.4% of the parents are satisfied with the time controller, around 91.1% of the children are satisfied with the proposed interface and 100% of the children are satisfied with the multiple sessions of the time allowed and video algorithm. Conclusion: The authors concluded that the implementation of this system allows parents to create accounts for their children and control these accounts based on the time allowed.
Research Article
Performance of Convolutional Neural Networks for Human Identification by Gait Recognition
Mohamed Sayed
Background and Objective: Natural walk and topological analysis of human being have respective and certainly unique key features that allow identifications when other biometric techniques are not visible. The objective of this paper is to draw attention towards a simple and novel feature extractor for gait recognition that is based on a deep learning approach. Materials and Methods: Different from conventional ways and means, the gait is designated as regular and intermittent motion taken out directly from silhouettes. Before the use of convolutional neural network to learn human gait representations, two important data pre-processing stages are enforced to enhance the characteristics of gait patterns obtained from grayscale images. Results: The proposed gait recognition approach achieves impressive results in terms of training/validation accuracy and mean square errors. Conclusion: The conducted experimental outcomes report competitive performance as compared to many traditional machine learning methods and previous deep gait models specifically for the case of low-image resolutions and large-scale dataset of input images.

Newsroom    |    Frequently Asked Questions    |    Privacy Policy    |    Terms & Conditions    |    Contact Us