International Journal of Soft Computing and Networking
These articles have been peer-reviewed and accepted for publication 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 Articles will not be published until the final proofs are validated by their authors.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.
International Journal of Soft Computing and Networking (4 papers in press)
Enhanced Cloud Server Management Software Development by Adapting Systematic Innovations by Song-Kyoo Kim Abstract: The paper is dealing with algorithmic system software implementation of the cloud service reliability by using the systematic innovation method that is the structured process to generate the new idea. By using the unique innovation methods, it provides the implementation algorithm to manage the computing resources that are delivered as a service over the Internet. Cloud server management is focused on reliability and the external cloud servers are hooked up by the long-haul network and replace broken main cloud severs immediately. When the recovery system is not available because of the given conditions, external servers are being used for backups. The results are demonstrated in the framework of optimized server allocation problems with unreliable backup servers and algorithm (operational workflow) that could be implemented on the management system. Keywords: Network management; systematic innovation; stochastic modelling; cloud architecture;.
Improvisation in the processes of Intrusion Detection System through CAII by Saad Masood Butt Abstract: Usability evaluation methods have gained a substantial attention in networks particularly in Intrusion Detection System (IDS) as these evaluation methods are envisioned to achieve usability and define usability defects for a large number of practical softwares. Despite a good number of available survey and methods on usability evaluation, we feel that there is a gap in existing literature in terms of usability evaluation methods, IDS interfaces and following usability guidelines in IDS development. This paper reviews the state of the art for improving usability of networks that illustrates the issues and challenges in the context of design matters. Further, we propose the taxonomy of key issues in evaluation methods and usability problems. We also define design heuristics for IDS users and interfaces that improves detection of usability defects and interface usability compared to conventional evaluation heuristics. The similarities and differences of usability evaluation methods and usability problems are summarized on the basis of usability factors, current evaluation methods and interfaces loopholes. Keywords: Intrusion Detection System; Heuristics Evaluation; IDS Interface; Usability Evaluation methods.
AN OPTIMIZED QoS-BASED CLUSTERING WITH MULTIPATH SECURE ROUTING PROTOCOL FOR WIRELESS SENSOR NETWORKS by Onthachi Deepa, J. Suguna Abstract: Recent advances in wireless technology with networking capabilities have generated a lot of interest to design routing protocol for Wireless Sensor Networks (WSNs). WSNs are a promising approach used in various applications but finding an optimal route discovery is more problematic due to dynamicity, heterogeneity, resource scarcity and so on. Generally, residual energy of sensors in sink coverage area is drained very quickly compared to other area nodes in WSNs. The proposed Optimized QoS-based Clustering with Multipath Secure Routing Protocol (OQoS-CMSRP) for WSNs reduces the energy consumption in sink coverage area and solving hot spot problem. The proposed protocol is used to find near optimal multi-hop communication path from sink to sensors for selecting the next hop neighbor nodes. An enhanced (k,n)-threshold secret sharing scheme is required to make n shares and recover the secret by using k shares based on Hermites interpolating polynomial. The proposed protocol is to provide end-to-end security from different network layer attacks and to provide an efficient service for transmitting data in secure and reliable manner. According to QoS metrics, the performance of this communication protocol is evaluated and compared with other existing protocols namely MRBCH and EE-LEACH. The simulation result shows that OQoS-CMSRP for WSN achieves prominent data communication with reasonable energy conservation. It also reduces transmission delay and communication overhead on the basis of ensuring the outcome of the entire network. Keywords: An enhanced (k,n)-threshold secret sharing scheme; Hermite’s interpolating polynomial; Hot spot problem; OQoS-CMSRP; Quality of Service; Wireless Sensor Networks.
Deep Reinforcement Learning Based Participant Selection Method for Mobile Crowdsensing by Otniel Yosi Viktorisa, Ito Wasito, Bob Hardian Syahbuddin Abstract: Mobile crowdsensing (MCS) is one of the new paradigms in the field of sensing. The emergence of MCS is influenced by the rapid development of mobile phones and smart devices that are equipped with various sensors and has computing capabilities. In addition, previous research has proven that MCS can be applied to be a solution to real world problems. To be able to run, MCS requires user participation. Therefore, the selection process of participants becomes quite important in the field of MCS. Previous research proposing participantrnselection methods generally uses the greedy approach. The method fails to evaluate individuals as part of a large population. This research proposes participant selection method based on deep reinforcement learning by applying the pursuit learning game algorithm to solve the problem. The proposed model wasrnevaluated by running simulations using data taken from Geolife Trajectory Dataset 1.3. Evaluation results show the proposed model has been quite effective in conducting the participant selection process. Keywords: mobile crowdsensing; participant selection; reinforcement learning; deep learning.