In this paper, we propose two schedulers for channel sensing in cognitive radio networks. We use both of rules‐based learning and statistical‐based learning to develop the proposed solutions. Both of these schedulers take three channel parameters as an input to generate scheduling decision. These parameters are utilization, success rate, and channel quality. First proposed scheduler employs fuzzy inference technique to generate the decision regarding channel sensing order. It makes use of genetic algorithm to find the best set of fuzzy rules based on environment dynamics. The second proposed scheduler uses Bayesian inference concept by applying Baye's rule on the perceived distribution function of channel occupancy to improve its accuracy. To track the advancement of scheduler performance, we devised a measurement concept called convergence indicator. Both of the proposed mechanisms showed remarkable performance and adaptability to the highly dynamic behavior of wireless environment. Fuzzy inference solution achieved on average 138 per cent increases in terms of channel utilization compared to fixed sensing order, while Bayesian inference achieved 85 per cent increase. Copyright © 2014 John Wiley & Sons, Ltd.

With the increasing number of computers being connected to the Internet, security of an information system has never been more urgent. Because no system can be absolutely secure, the timely and accurate detection of intrusions is necessary. This is the reason of an entire area of research, called Intrusion Detection Systems (IDS). Anomaly systems detect intrusions by searching for an abnormal system activity. But the main problem of anomaly detection IDS is that; it is very difficult to build, because of the difficulty in defining what is normal and what is abnormal. Neural network with its ability of learning has become one of the most promising techniques to solve this problem. This paper presents an overview of neural networks and their use in building anomaly intrusion systems.

No abstract

This paper tackles the issue of spectrum sharing and medium access control among heterogeneous secondary users. Two solutions are proposed in this paper. The first solution can be used in centralized fashion where a central entity exists which decides transmission power for all secondary users. This solution tries to minimize the time required by secondary users to clear their queues. The second solution assumes the autonomy of secondary users where the decision to update transmission power is distributed among users. Dynamical system approach is used to model system behavior. The trajectory of interference noise level suffered by secondary users is used to update transmission power at the beginning of each time frame based on the proposed dynamic power assignment rule. This rule couples the responses of all secondary users in a way which simplifies future interference noise forecasting. A forecasting engine based on deep neural network is proposed. This engine gives secondary users the ability to acquire useful knowledge from surrounding wireless environment. As a result, better transmission power allocation is achieved. Evaluation experiments have confirmed that adopting deep neural network can improve the performance by 46% on average. All of the proposed solutions have achieved an outstanding performance.

Strategies to acquire white space information is the single most significant functionality in cognitive radio networks (CRNs) and as such, it has gone some evolution to enhance information accuracy. The evolution trends are spectrum sensing, prediction algorithm and recently, geo-location database technique. Previously, spectrum sensing was the main technique for detecting the presence/absence of a primary user (PU) signal in a given radio frequency (RF) spectrum. However, this expectation could not materialized as a result of numerous technical challenges ranging from hardware imperfections to RF signal impairments. To convey the evolutionary trends in the development of white space information, we present a survey of the contemporary advancements in PU detection with emphasis on the practical deployment of CRNs i.e. Television white space (TVWS) networks. It is found that geo-location database is the most reliable technique to acquire TVWS information although, it is financially driven. Finally, using financially driven database model, this study compared the data-rate and spectral efficiency of FCC and Ofcom TV channelization. It was discovered that Ofcom TV channelization outperforms FCC TV channelization as a result of having higher spectrum bandwidth. We proposed the adoption of an allinclusive TVWS information acquisition model as the future research direction for TVWS information acquisition techniques.