Forthcoming articles


International Journal of Innovative Computing and Applications


These articles have been peer-reviewed and accepted for publication in IJICA, but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.


Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.


Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.


Articles marked with this Open Access icon are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.


Register for our alerting service, which notifies you by email when new issues of IJICA are published online.


We also offer RSS feeds which provide timely updates of tables of contents, newly published articles and calls for papers.


International Journal of Innovative Computing and Applications (15 papers in press)


Regular Issues


  • An Empirical Study of Statistical Language Models: N-gram Language Models vs. Neural Network Language Models   Order a copy of this article
    by Freha MEZZOUDJ, Abdelkader BENYETTOU 
    Abstract: Statistical language models are an important module in many areas of successful applications such as speech recognition and machine translation. And N-gram models are basically the state-of-the-art. However, due to sparsity of data, the modelled language cannot be completely represented in the n-gram language model. In fact, if new words appear in the recognition or translation steps, we need to provide a smoothing method to distribute the model probabilities over the unknown values. Recently, neural networks were used to model language based on the idea of projecting words onto a continuous space and performing the probability estimation in this space. In this experimental work, we compare the behavior of the most popular smoothing methods with statistical n-gram language models and neural network language models in different situations and with different parameters. The language models are trained on two corpora of French and English texts. Good empirical results are obtained by the recurrent neural network language models.
    Keywords: language models; n-grams; Kneser-Ney smoothing; modified Kneser-Ney smoothing; Good-Turing smoothing; interpolation; back-off ; feed-forward neural networks; continuous space language models; recurrent neural networks; speech recognition; machine translation.

  • POND: Polishing the Execution of Nested Context-Familiar Runtime Dynamic Parsing and Sanitization of XSS Worms on Online Edge Servers of Fog Computing   Order a copy of this article
    by Shashank Gupta, Brij Gupta 
    Abstract: This article presents an enhanced duplex context-wise sanitization generator and dynamic parser on the hierarchical distributed structure of Cloud data centers and edge (Fog) servers for obstructing the execution of XSS worms that was recently found on HTML5 and Twitter-based web applications. Such data centers statically explores the diverse nested context of variables of script code and consequently generates the sanitized version of HTML5 documents corresponding to their contexts. Such sanitized templates of HTML5 documents are injected in the edge servers of Fog nodes. The online HTTP response generated by such edge servers undergoes through the phase of dynamic runtime parsing. This phase finds out the nested context of variables of script code that cannot be statically determined during the determination of nested context of such variables in a static manner. Finally, sanitized version of templates of HTML5 web pages are generated as an HTTP response and redirected to the network of smart devices. Cloud data centers and edge servers of Fog nodes are utilized for integrating the infrastructure settings of our prototype framework that was developed in Java developed framework. Numerous tested open source platforms of OSN were utilized for assessing the performance of runtime nested context determination and sanitization of suspicious JavaScript strings. Performance evaluation outcomes revealed that the proposed work experienced better response time at online phase and tolerable performance overhead caused due to the runtime nested context-wise parsing and sanitization of XSS worms on the edge servers of Fog nodes as compared to our existing work on the Cloud data centers.
    Keywords: Cloud Security; Fog Computing; Edge Servers; XSS Worms; Online Social Network (OSN) Security; Context-Familiar Sanitization; HTML5.

  • An Algorithm Based on Voronoi Diagrams for the Multi-Stream Multi-Source Multicast Routing Problem   Order a copy of this article
    by Romerito Andrade, Marco Goldbarg, Elizabeth Goldbarg 
    Abstract: In this study, we present a new heuristic for the multi-stream multi-source multicast routing problem. The core of the heuristic proposed in this study is based on a generalization of Voronoi Diagrams in graphs. It allows building the trees needed to serve the demands of multiple sessions efficiently. Also, the proposed algorithm supports multiple sources. We performed an extensive experimental analysis of different network and problem configurations such as the number of sessions, nodes, sources and participants per session. We compare the proposed algorithm to heuristics proposed previously. The results of the experiments showed that the heuristic proposed in this study finds high-quality solutions efficiently.
    Keywords: multicast routing; multi-source; multi-session; Voronoi diagram.

  • Modelling and implementation of an energy management simulator based on agents using optimized fuzzy rules: Application to an electric vehicle   Order a copy of this article
    by Rachid El Amrani 
    Abstract: This paper presents an intelligent algorithm based on multi agent systems to manage the energy in a hybrid electrical vehicle using a model of lithium metal polymer (LMP) battery and a model of an electrical double layer capacitor (EDLC). The algorithm uses fuzzy rules optimized by a genetic algorithm to control the flow of energy inside the system. The LMP battery is linked to a boost converter to insure the autonomy of the electrical vehicle, while the EDLC is linked to a back boost converter that provides the highly demanded energy in a short time and guarantees the temporarily energy storage when the vehicle is braking (no energy is demanded). The hybrid electrical vehicle is simulated in different driving cycles to analyze the behaviour of the LMP battery and the EDLC. Results showed that the used hybrid strategy was able to ensure the autonomy of the vehicle in terms of energy since it has performed a minimum energy cost and a maximum profit in autonomy, which means a longer life of the Hybrid Electric Source.
    Keywords: Hybrid vehicle; Battery; Capacitor; Modelling; Genetic optimization; Fuzzy control; Multi-agent system; Energy management.

Special Issue on: Secure Data Storage in Cloud Computing

  • An Access Control Framework for Multi-level Security in Cloud Environments   Order a copy of this article
    by Hongbin Zhang, Junshe Wang, Jiang Chang, Ning Cao 
    Abstract: Access control is important for the security in cloud environments while increasing demands for secure interactions in the cloud bring new challenges to access control technologies. As a cloud always consists of many domains, in this paper we design an access control framework which provides rigorous multilevel security in single domain and a multilevel mapping method between domains. In each domain, a policy processing method is designed to handle the multilevel policies and creates a DAG model that describes the access control relationship between all entities in the domain. The DAG model can be converted to a hierarchical access control structures that ensure rigorous multilevel security in intra domains. And between domains, the mapping method based on quantized subject attributes is proposed to determine the subjects security level in its target domain. Credibility is used in the framework to adjust the mapping value in order to achieve flexible multilevel inter-domain access control. Experimental results from simulations show that proposal in this paper can realize accurate inter-domain mapping and achieve multilevel security access control in inter-domain.
    Keywords: multi-level security; cloud; access control; multi-attributes quantization; inter-domain mapping.

  • Improve the Robustness of Data Mining Algorithm Against Adversarial Evasion Attack   Order a copy of this article
    by Ning Cao, Yingying Wang, Guofu Li, Yuyan Shen, Junshe Wang, Hongbin Zhang 
    Abstract: Conventional data mining theories developed for general-purpose applications commonly focus on the reducing the bias and variance on the ideal i.i.d. datasets, but neglecting its potential failure on maliciously generated data points by observing the systems behaviours. Therefore, dealing with these adversarial samples is an essential part of a security system to handle the data that are intentionally made to deceive the system. Due to this concern, this paper proposes a novel approach that introduces uncertainty to the model behaviour, in order to obfuscate the decision process of the attacking strategy and improve the robustness of security system against attacks that try to evade the detection. Our approach addresses three problems. First, we build a pool of mining models to improve robustness of a variety of mining algorithms, similar to ensemble learning but focusing on the optimization the trade-off between off-line accuracy and robustness. Second, we randomly select a subset of models at run time (when the model is used for detection) to further boost the robustness. Third, we propose a theoretical framework that bounds the minimal number of features an attacker needs to modify given a set of selected models.
    Keywords: Data Mining; Robustness; Security.

  • Formal Analysis of a Private Access Control Protocol to a Cloud Storage.   Order a copy of this article
    by Mouhebeddine Berrima 
    Abstract: Cloud storage provides an attractive solution for many organizations and enterprises due to its features such as scalability, availability and reduced costs. However, storing data in the cloud is challenging if we want to ensure data security and user privacy. To address these security issues cryptographic protocols are usually used. Such protocols rely on cryptographic primitives which have to guarantee some security properties such that data and user privacy or authentication. \emph{Attribute-Based Signature} (ABS) and Attribute-Based Encryption (ABE) are very adapted for storing data on an untrusted remote entity. In this work, we enhance the security of cloud storage systems through a formal analysis of a cloud storage protocol based on ABS and ABE schemes. We clarify several ambiguities in the design of this protocol and model the protocol and its security properties with ProVerif an automatic tool for the verification of cryptographic protocols. We discover an unknown attack against user privacy in the Ruj et al. protocol. We propose a correction, and automatically prove the security of the corrected protocol with ProVerif.
    Keywords: Cloud storage; formal methods; attribute based signature; attribute based encryption; data and user privacy.

  • Scalable video coding algorithm and rate-distortion optimization based on cloud computing   Order a copy of this article
    by Yuejin Zhang, Meng Yu, Yong Hu 
    Abstract: In order to provide end users with better quality video, this paper presents an adaptive multi-path video stream scalable video coding algorithm based on the cloud computing for H264/AVC extension, with the path of diversity provided by based on the cloud computing video distribution network, The method of using scalable video coding is finally adapted to the various end users, Moreover, it adapts to network bandwidth fluctuation by observing the changes of the available bandwidth over the multiple overlay paths. And performing rate-distortion optimization in the basis of the end-to-end distortion estimation has given a method of reducing complexity. Experimental results show that the optimization algorithm based on the cloud computing video distribution network is more effective to reduce video packet loss rate and network latency, rate-distortion optimization performance gain outperform the current redundancy coding scheme and traditional recursive optimal per-pixel estimation, ensure the quality of the video network transmission.
    Keywords: video distribution network; scalable video coding; multi-path; rate-distortion optimization; cloud computing.

  • An Empirical study of Cloud Computing and Big Data Analytics   Order a copy of this article
    by Emad Al-Shawakfa, Hiba Alsghaier 
    Abstract: The rapid growth in using the social media in the last few years has lead to introducing new trends to be in line with social media technologies, two of these trends are known as Big Data"; a technology for holding and analysing data, and "Cloud Computing"; a model that combines different infrastructures and services to allow organizations and users to access these resources. Organizations collect data in order to use it at new levels for the promotion and usage of information technology to share accurate, stable business experimentation that direct decision makers to make brilliant decisions, the new trends help organizations to make decisions in real time. These trends have also guided into a revolutionary transformation in research, invention, and business marketing. This paper highlights some aspects of utilizing Big Data and Cloud Computing with their effects on an organization's business performance in many sectors. Furthermore, some issues of using big data and cloud computing in various environments were also addressed, the usage of cloud computing for Internet of things and issues about it were also discussed in this paper The paper is organized as follows: Section 1 gives the Introduction, Section 2 covers the Background, Section 3 gives the Literature Review with subsections about Hadoop, Cloud Computing, and Big data. Section 4 covers the challenges while Section 5 gives the Conclusion.
    Keywords: Big Data Analytics; Big Data; Cloud Computing; Hadoop.

  • A blue noise pattern sampling method based on cloud computing to prevent aliasing   Order a copy of this article
    by Aiyun Zhan, Yong Hu, Meng Yu, Yuejin Zhang 
    Abstract: The high frequency of the image through pre-filtering and sampling cannot be eliminated, whereby the power spectrum of the oscillation may appear the aliasing phenomenon, the sampling scheme based on cloud computing proposed two standard blue noise pattern: step blue noise and unimodal blue noise. By using an octree and n-bit quantized gray, MIP average complexity can be reduced to O (n2). This improvement makes the interactive visualization and the data storage security of MIP greatly improved in large capacity data application. In order to meet the results of theoretical complexity of O (n2), an object-order algorithm is proposed. Experimental results show that the low sampling rate model based on cloud computing can effectively prevent aliasing structure, in a high sampling rate model based on cloud computing also perform equally well, Simulation results employing H.264's redundant slice mechanism show significant performance gains over conventional error-resilient encoding methods and native redundant encoding methods.
    Keywords: blue noise pattern; aliasing; sampling; cloud computing; MIP; encoding methods.

Special Issue on: Social Media Analysis From Misinformation to Valuable Data Source

  • Multi-level Privacy Preserving Data Publishing   Order a copy of this article
    by Zhiqiang Gao 
    Abstract: Policedata is an important source of social media data and can be regarded as a technical assistance to increase government accountability and transparency. Notably, it contains large amounts of personal private information that should be preserved deliberately. However, sharing and publishing policedata through private or public cloud infrastructure are still faced with tremendously potential threats and challenges recently: (1) with little constant vigilance of data privacy, neither data curators nor insiders of police department pay adequate attention on the process of data publishing, holding the mind that policedata can be published, transferred, data-mined and shared within inner network safely as well as conveniently. (2) multi-sourced policedata from social media, such as tabular data and web pages, result in high complexity of privacy preserving data publishing. (3) privacy preservation in policedata is still problematic and vulnerable in the complex situation of multi-level data publishing. Unfortunately, existing researches regarding privacy preserving data publishing (PPDP) fail to cope with the aforementioned problems. Our work aims to propose a systematic multi-level privacy preserving data publishing (ML-PPDP) architecture. Moreover, a personalized multi-level privacy preserving (pML-PPDP) mechanism that developed from the combination of the state-of-the-art methods including k-anonymity, l-diversity, t-closeness and differential privacy is designed for policedata publishing. Our solution authorized users with different privileges to different privacy-preserving levels. Experimental results of pML-PPDP mechanism on datasets collected from policedata website are implemented under our proposed ML-PPDP architecture with satisfactory trade-off between privacy and utility.
    Keywords: Social media policedata; Privacy preserving data publishing; Attribute-based Encryption; k-anonymity; l-diversity; t-closeness; Differential privacy.

  • Hybrid Genetic-annealing Algorithm for Intelligent power consumption of large building   Order a copy of this article
    by Yanping Li, Boying Shi, Tao Wang, Linyan Wu, Qi Wang 
    Abstract: At present, the electrical equipment in buildings is constantly increasing, and correspondingly, the energy consumption is also greatly improved. Therefore, scientific and intelligent power consumption is particularly important. In this paper, the main factors that affect the room environment are modelled, such as room temperature, light intensity. At the same time, genetic annealing algorithm is introduced to solve the multi-objective optimization of the parameters of the electrical equipment, find the best strategy for intelligent power system. Finally, the simulation is carried out on the MATLAB platform, and the simulation results show that it has good energy saving effect of architectural smart power system.
    Keywords: Architectural Smart Power,Hybrid Genetic-annealing Algorithm,Indoor comfort.

  • Rapid detection and social media supervision of runway incursion based on deep learning   Order a copy of this article
    by Chengtao Cai, Kejun Wu, YongJie Yan 
    Abstract: In order to solve the problem of runway incursion, which is a serious threat to the safety of the aviation industry, we divide the problem into target detection and scheduling optimization by analysing a large number of runway incursion accidents. We analyse social media data and showed people's concern about airport runway incursion. We take the target of aircrafts and vehicles on the runway as the research objects, and then learn from deep learning and image processing experience. Finally we put forward the airport target detection method based on optimized YOLO framework. The simulation experiment is carried out by constructing the airport simulation environment. We study the airport target detection in single target, multi-target and extreme environment target, and focus on the influence of the overlooking angle of the monitoring system on the detection results. We selected Tiny YOLO and Faster R-CNN as the control group to demonstrate the performance of the optimized YOLO detector at speed. The experimental result shows that the airport target detection based on optimized YOLO has excellent fastness and accuracy when the arrangement angle is 35
    Keywords: Runway incursion; social media supervision; target detection; deep learning; YOLO.

  • Rumor Propagation Considering the Active Inquiry Factor on Social Media Networks   Order a copy of this article
    by Jing Wang, Min Li 
    Abstract: In this paper, considering the influence of the active inquiry factor, the dynamical behaviors of rumor spreading on social networks is investigated by means of mean-field theory. The mean-field equations of two cases of link global addition and link local addition are derived to describe the propagation process of susceptible-infected-removed (SIR) rumor model, separately. Theoretical analysis shows that, considering the influence of the active inquiry factor, the higher the proportion that new links are added into the networks, the smaller the propagation critical threshold, the faster the transmission velocity of rumors. It is also found that with the increase of the number of new addition links, the number of nodes that finally accept rumors also increases. In addition, compared with the link global addition case, the number of nodes that are finally infected by rumors in the link local addition case is clearly reduced. Numerical simulations have confirmed the theoretical results.
    Keywords: Rumor propagation; Active inquiry; SIR model; Social network.

  • The spread pattern on Ebola and the control schemes   Order a copy of this article
    by Jiangjie Sun, Wei-Yu Xia, Jiang-Jie Sun, Jia-Bao Liu, Fa-Hong Yu 
    Abstract: This paper aims to study a reasonable system that includes viral transmission and disease cure of Ebola. Firstly, we utilize the logistic model to simulate the change of number of patients. Secondly, we establish the infection dynamics model to evaluate the probability of the outbreak of related region according to some close-related indexes. Finally, we make use of nonlinear programming and 0-1 integer programming to achieve the maximum efficiency for the whole system in spite of the minimum costs.
    Keywords: Reasonable system; logistic model; 0-1 integer programming.