Editorial

International Journal of Pervasive Computing and Communications

ISSN: 1742-7371

Article publication date: 28 October 2014

108

Citation

Khalil, I. and Chen, L. (2014), "Editorial", International Journal of Pervasive Computing and Communications, Vol. 10 No. 4. https://doi.org/10.1108/IJPCC-09-2014-0045

Publisher

:

Emerald Group Publishing Limited


Editorial

Article Type: Editorial From: International Journal of Pervasive Computing and Communications, Volume 10, Issue 4

This issue of the International Journal of Pervasive Computing and Communication contains six papers covering a number of hot research topics, including energy saving in wireless sensor networks, security issues in IoT systems, activity recognition, transfer learning and participatory sensing systems for pervasive healthcare and efficient message routing in opportunistic networks. These papers represent and reflect the latest state-of-the-art of research and development in these related areas which help to identify opportunities and challenges for interested researchers and technology and system developers, and inspire and provoke follow-up research in the time to come. The following is a short brief for each paper.

The paper “Lightweight Security Scheme for IoT Applications Using CoAP” introduces a lightweight security scheme in CoAP using AES-128 symmetric key algorithm. It describes an object security (payload embedded)-based robust authentication mechanism with integrated key management and further presents a couple of unique modifications to CoAP header to optimize security operation and minimize communication cost. The scheme is generic in nature able to be applicable for gamut of IoT applications. It has been tested for vehicle tracking applications in emulated laboratory setup. Initial comparison with DTLS-enabled CoAP has proved the efficacy of the proposed solution.

The paper “Heterogeneous Transfer Learning for Activity Recognition using Heuristic Search Techniques” introduces three novel heterogeneous transfer learning techniques that reverse the typical transfer model and map the target feature space to the source feature space and apply them to activity recognition in a smart apartment. The techniques represent a considerable step forward in heterogeneous transfer learning by removing the need to rely on instance–instance or feature–feature co-occurrence data. The techniques have been evaluated on data from 18 different smart apartments located in an assisted-care facility. By comparing the results against several baselines, it has shown that the three transfer learning techniques are all able to outperform the baseline performance in several situations. Furthermore, the techniques are also successfully used in an ensemble approach to achieve even higher levels of accuracy.

The paper “Participatory Sensing and Education: Helping the Community Mitigate Sleep Disturbance from Traffic Noise” introduces an approach to using smartphones to measure the level of traffic noise in residential homes. The approach is realized in a mobile app call 2Loud? That turns the smartphones of users into noise sensors with accuracies comparable to professional sound meters. The collected data are analyzed by environment and acoustic experts, and personalized feedback is then provided in the form of mitigation strategies. The strategies are also delivered through the app to allow users to share within the community. Initial assessment has shown that users appreciate the technology and do feel a sense of empowerment for managing their own life, thus proving the effectiveness of innovative use of participatory sensing systems.

The paper “A duration-based online reminder system” describes a system that processes data from a network of sensors with the capability of sensing user interactions and on-going iADLs in the living environment. The system contains a probabilistic learning model to compute joint probability distributions over different activities representing users’ behavioral patterns in performing activities. This probability model underpins an intervention framework that prompts the user with the next step in the iADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability taken into consideration the iADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the iADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent toward the completion of the activity, thus updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct. Experiment results show by including duration information the prediction accuracy of the model is increased and the confidence level for the next step in the iADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single sensor activation in comparison to an alternative approach which did not consider activity durations.

The paper “Energy Efficient Clustering for Wireless Sensor Networks” addresses the energy-saving problem in WSN by designing a hierarchical routing protocol. It started by designing a protocol called Efficient Energy Aware Distributed Clustering (EEADC). Simulation result showed EEADC might generate clusters with very small or very large size. To solve this problem, the paper developed a new algorithm called Fixed Efficient Energy Aware Distributed Clustering (FEEADC). As CHs far away from the base station die faster than the ones closer to it, the study further proposes an enhanced algorithm called Multi-hop Fixed Efficient Energy Aware Distributed Clustering (M-FEEADC). M-FEEADC is based on a new fixed clustering mechanism, thus creating a balanced distribution of Cluster-Heads based on data aggregation and Sleep/Wakeup techniques. The simulation results show a significant improvement in terms of energy consumption and network lifetime over the well-known protocols LEACH and TEEN.

The paper “LOC algorithm: Location-aware opportunistic forwarding by using node’s approximate location” proposes an algorithm, dubbed as Location-aware opportunistic content forwarding (LOC), to improve the message directivity using direction vectors in opportunistic networks. The LOC is based on the assumption that if approximate location of the destination node is known then overall message delivery and cost can be improved. The LOC algorithm has been tested in two sets of mobility models, synthetic movement model, as well as in real mobility datasets. In the first set, Working Day Movement (WDM) is used as synthetic movement model, where proposed algorithm is compared against Lobby Influence (LI) and Epidemic (EPI) algorithms. In the second set of experiments, the new algorithm is tested in three mobility data sets, namely, Cambridge, Reality & Sassy, and compared results against LI algorithm. The reason of using various movement models is to establish strength and weaknesses of proposed algorithm in different scenarios. The experimental results show that the new algorithm performed extremely well in different scenarios, not only in terms of overall message delivery but also successfully manages to reduce the communication cost.

We would like to take this opportunity to thank all authors for their valuable contributions, and also the publishers for their continuous support, advice and hard work.

Ismail Khalil and Liming Luke Chen - IJPCC Editors

Related articles