Guest Editorial: Special Section: Convergence of Machine learning Paradigms and Multimedia Cloud Network Systems for Global IT systems

Due to rapid growth and advancement of cloud technology, responsive systems are used therewith generating a huge volume of data in a variety of formats, especially multimedia data. Recently, the development of multimedia technology has played a significant role in exchanging, sharing of data and information at a larger extent in the global IT industry field. Consequently, the fast development of Internet technologies has raised the need for in-depth convergence of Machine Learning paradigms in energy-aware management of computing resources and cloud-based multimedia sharing platform for Global IT systems to efficiently control and reduce ecological and societal impacts. Moreover, significance of Machine Learning approaches in multimedia cloud network system for global IT systems would be feasible and sound. The aim of this special issue is to integrate Machine Learning paradigms, advanced data analytics, and optimization opportunities to bring more awareness on applicability and usefulness of distributed multimedia services in Global IT systems. Further, it is imperative to note that Machine Learning paradigms and other intelligence methods have not been adequately investigated from the perspective of multimedia cloud based service management framework, and its related research issues. Furthermore, in this context, there are many intertwined noteworthy issues (QoS-aware service composition, spatial computing, biologically inspired learning and adaption in self-configuration of network services surveillance system, etc) that need to be addressed in the context of multimedia cloud networking system in convergence with machine learning in global IT systems. Obviously, these challenges also create immense opportunities for researchers. Hence, primary aim of this special issue is to disseminate the application of machine learning approaches/models and its related branches such as evolutionary computation, neural networks, artificial immune systems, swarm intelligence, and so on in multimedia cloud systems for global IT systems. The accepted papers and primary authors are introduced below.

The first article “A Novel Framework for Automatic Chinese Question Generation Based on Multi-Feature Neural Network Model” by Hai-Tao Zheng et al., explicitly addresses a novel framework, called Automatic Chinese Question Generation (ACQG), to generate questions from text or paragraph. In ACQG, the authors have adopted Text-Rank to extract key sentences and a template-based method to construct questions from key sentences. Then a multi-feature neural network model has been built for ranking to obtain the top questions. The automatic evaluation result of this paper reveals that the proposed framework outperforms the state-of-the-art systems in terms of perplexity.

The second paper “Research on Automatic Identification Technique of CT Image in Lung” by Zhijie Zhao et al., proposes an auxiliary diagnosis method for automatic recognition of pulmonary nodules on lung computed tomography (CT) images. The experimental results show that the pulmonary parenchymal segmentation in lung CT images is achieved based on the random walk algorithm, which has better effect on the blurred pulmonary boundary, the regional connectivity of the lungs and the overlapping of the lung parenchyma. Finally, the support vector machine algorithm is used to recognize pulmonary nodules.

The third article “Convolutional Neural Networks and Hash Learning for Feature Extraction and of Fast Retrieval of Pulmonary Nodules” by Pinle Qin et al., presents an effective deep learning framework to create the hash-like binary codes for fast image retrieval. In this research, authors have added a latent-attribute layer in the deep Convolutional neural network (CNN) to simultaneously learn domain specific image representations and a set of hash-like functions. Experimental results shown that, proposed deep CNN method achieves 0.73 retrieval precision on the LUNA2016 datasets.

The fourth article “An Optimized Method of HDFS for Massive Small Files Storage” by Weipeng Jing et al., proposes a method of dynamic queueing that uses an analytical hierarchal process to analyse system performance and addresses differing ranges for small files. In this research, classification the text files has been done via period classification algorithm. Further, this study has chooses suitable queues for different sizes of small files and then merge the files in the queue. The experimental results of this reveal development of the Internet-of-Things (IoT) and the Cyber-Physical System (CPS) have greatly facilitated many aspects of technological applications and development.

The fifth article “A Lightweight Batch Anonymous Authentication Scheme for VANET Based on Pairing-free” Cheng Song et al have solves the efficiency problem in anonymity authentication in existing privacy protection schemes for vehicular ad hoc network (VANET). In this paper, the authors have proposed a certificateless batch anonymity authentication scheme without bilinear pairings operation. Analyses show that this scheme is not only guaranteed many security properties like anonymity, traceability, unlinkability, forward and backward security, etc. on the basis of correctness. This study has proved that proposed scheme can resist Type I and Type II attack under random oracle model. Accordingly, the scheme is proved to be significant in theory and valuable in application in the Internet of Things or embedded environment with limited resources.

The sixth article “Wireless sensor network coverage optimization based on whale group algorithm” by Lei Wang et al., investigates the network coverage problem in wireless sensor network. Firstly, the node sensing model is analyzed and the regional area monitoring is transformed into point monitoring by discrete method. Then, authors have studied the network coverage model, add node utilization and energy utilization in network coverage by the inertial weight method. Thus, the optimization problem of wireless sensor network coverage is transformed into multi-objective optimization problem. In the node deployment issues, this paper proposes a new whale swarm optimization algorithm.

The seventh article “Improved Functional Proxy Re-encryption Scheme for Secure Cloud Data Sharing” by Xu An Wang et al., proposes a concrete AMH-IBCPRE scheme and claim their scheme can achieve IND-sCon-sID-CCA secure (indistinguishable secure under selectively conditional selectively identity chosen cipher-text attack). Also they proposed a deterministic finite automata based functional proxy re-encryption scheme DFA-based FPRE for secure public cloud data sharing, they also claim their scheme can achieve IND-CCA secure (in-distinguishable secure under chosen ciphertext attack).

The eighth article “An Intelligent Image Classification Based on Spatial Weighted Histograms of Concentric Circles” Bushra Zafar et al., presents the spatial contents of an image and the rotations are dealt with efficiently, as compared to approaches that incorporate spatial contents. The spatial information is added by constructing the histogram of circles, while rotations are dealt with by using concentric circles. A weighed scheme is applied to represent the image in the form of a histogram of visual words. Extensive evaluation of benchmark datasets and the comparison with recent classification models demonstrate the effectiveness of the proposed approach. The proposed representation outperforms the state-of-the-art methods in terms of classification accuracy.

Final paper “A Fuzzy Rule-Based System to predict energy consumption of Genetic Programming Algorithms" by Josefa Díaz Álvarez et al., proposes a fuzzy rule based system to predict energy consumption of a kind of Evolutionary Algorithm, Genetic Programming, given the device in which it will be executed, its main parameters, and a measurement of the difficulty of the problem addressed. Experimental results performed show that the proposed model can predict energy consumption with very low error values.

We thank Professor Mirjana Ivanović, Editor-in-Chief of the Computer Science and Information Systems journal, for her support to and comments for this special section. We are grateful to the authors of this special section for contributing their excellent work and to the reviewers for their timely evaluations.

Guest Editors

Dr. David Camacho

Dr. Arun Kumar Sangaiah
VIT University, Vellore, India

Dr. Neil Y. (Yuwen) Yen
University of Aizu, Japan

Dr. Joel J.P.C. Rodrigues
National Institute of Telecommunications, Brazil, Instituto de Telecomunicações, Portugal