Efficient detection of network attacks necessitates the identification of important features, capable of characterizing the attacks. Most of the feature selection techniques are based either on a particular measure or on a particular learning algorithm. As the features selected by each such feature selection technique are different, use of a particular feature selection technique is not enough to assess the importance of a feature. This motivated us to propose a multi-measure multi-weight feature identification approach which combines the filter and wrapper feature selection methods and clustering methods to assign multiple weights to each feature. Two novel weight assignment algorithms for wrapper and clustering method have been proposed to assign weights to each feature. Experiments performed with top weighted features of 10% KDD Cup 99 intrusion detection dataset shows the identified features are indeed important in detecting DoS and probe attacks. Also, the comparison of the proposed approach with the existing algorithms shows that the features identified by the proposed approach detects the attacks with higher accuracy.

Abstract The feature selection phase in network attack detection is mostly classifier based, while clustering techniques are used for labeling and creating compact training datasets. Because clustering finds natural groupings in the data, in this paper, a clustering‐based layered wrapper feature selection approach, LAWRA, has been proposed for selecting appropriate features for attack detection. The existing layered feature selection approaches in attack detection are unable to give results with high precision and recall because of the dependence on classifier accuracy, fitness value, and so on. Hence, in this paper, LAWRA uses external cluster validity indices, F‐measure, and Fowlkes–Mallows index, for feature selection. The two indices are the harmonic and geometric mean of precision and recall, respectively. Each index identifies features that give high precision and high recall of the attack detection algorithm. The first layer of LAWRA identifies the feature subset that best distinguishes between normal and attack instances and the second layer identifies the best cooperating features using cooperative game theory. Experiments have been conducted on NSL‐KDD dataset, and LAWRA has been compared with the existing approaches using different classifiers. The results show that LAWRA gives better overall accuracy and F‐measure value than the other approaches. Copyright © 2015 John Wiley & Sons, Ltd.

Recent years have witnessed the emergence of shared sensor networks as integrated infrastructure for multiple applications. It is important to allocate multiple applications in a shared sensor network, in order to maximize the overall Quality of Monitoring (QoM) subject to resource constraints (e.g., in terms of memory and network bandwidth). The resulting constrained optimization problem is a difficult and open problem since it is discrete, nonlinear, and not in closed-form. This paper makes several important contributions towards optimal multi-application allocation in shared sensor networks. (1) We formulate the optimal application allocation problem for a common class of distributed sensing applications whose QoM can be modeled as variance reduction functions. (2) We prove key theoretical properties of the optimization problem, including the monotonicity and submodularity of the variance reduction functions and the multiple knapsack structure of constraints; (3) By exploiting these properties, we propose a local search algorithm, which is efficient and has a good approximation bound, for application allocation in shared sensor networks. Simulations based on both real-world datasets and randomly generated networks demonstrate that our algorithm is competitive against simulated annealing in term of QoM, with up to three orders of magnitude reduction in execution times, making it a practical solution towards multi-application allocation in shared sensor networks.

Wireless sensor networks are evolving from dedicated application-specific platforms to integrated infrastructure shared by multiple applications. Shared sensor networks offer inherent advantages in terms of flexibility and cost since they allow dynamic resource sharing and allocation among multiple applications. Such shared systems face the critical need for allocation of nodes to contending applications to enhance the overall Quality of Monitoring (QoM) under resource constraints. To address this need, this paper presents Utility-based Multi-application Allocation and Deployment Environment (UMADE), an integrated application deployment system for shared sensor networks. In sharp contrast to traditional approaches that allocate applications based on cyber metrics (e.g., computing resource utilization), UMADE adopts a cyber-physical system approach that dynamically allocates nodes to applications based on their QoM of the physical phenomena. The key novelty of UMADE is that it is designed to deal with the inter-node QoM dependencies typical in cyber-physical applications. Furthermore, UMADE provides an integrated system solution that supports the end-to-end process of (1) QoM specification for applications, (2) QoM-aware application allocation, (3) application deployment over multi-hop wireless networks, and (4) adaptive reallocation of applications in response to network dynamics. UMADE has been implemented on TinyOS and Agilla virtual machine for Telos motes. The feasibility and efficacy of UMADE have been demonstrated on a 28-node wireless sensor network testbed in the context of building automation applications.

No abstract available.

This paper presents MobiQuery, a spatiotemporal query service that allows mobile users to periodically gather information from their surrounding areas through a wireless sensor network. A key advantage of MobiQuery lies in its capability to meet stringent spatiotemporal performance constraints crucial to many applications. These constraints include query latency, data freshness and fidelity, and changing query areas due to user mobility. A novel just-in-time prefetching algorithm enables MobiQuery to maintain robust spatiotemporal guarantees even when nodes operate under extremely low duty cycles. Furthermore, it significantly reduces the storage cost and network contention caused by continuous queries from mobile users. We validate our approach through both theoretical analysis and simulation results under a range of realistic settings.

Many mission-critical applications require spatiotemporal data services for mobile users or objects. Examples include distributed object tracking and fire monitoring by firefighters. To support such applications, wireless sensor networks must satisfy a set of stringent spatiotemporal constraints despite having low network duty cycles and scarce resources. We have developed two new wake-up and topology maintenance protocols, directional tree maintenance (DTM) and omnidirectional tree creation (OTC), to support spatiotemporal services in mobile environments. A key feature of our protocols is that they provide robust spatiotemporal performance while maintaining low overhead and energy consumption. Our simulations showed that both DTM and OTC can successfully deliver over 85% of query results to a mobile user within desired spatiotemporal constraints, even when the sleep schedule is as long as 15 s, the user changes direction every minute, and the location error is as high as 10 m. The benefits of our protocols have been validated through theoretical analysis and empirical results on a testbed of Mica2 motes.

This article presents FAR, a Face-Aware Routing protocol for mobicast---a spatiotemporal variant of multicast tailored for sensor networks with environmental mobility. FAR features face-routing and timed-forwarding for delivering a message to a mobile delivery zone. Both analytical and statistical results show that FAR achieves reliable spatial and just-in-time message delivery with only moderate communication and memory overhead. This article also presents a novel distributed algorithm for spatial neighborhood discovery for FAR bootstrapping. The spatiotemporal performance and reliability of FAR are demonstrated via network simulations.

No abstract available.

Mobile Ad-Hoc Networks (MANETS) are networks of mobile nodes that do not have a fixed infrastructure. Recent research in this field addresses ways of solving existing problems in MANETS by the use of node location information. However, since the location of the nodes change frequently, maintaining location information is in itself a challenge in these networks. In this paper we address the problem of maintaining a location service and present two algorithms in which all nodes maintain location information about all other nodes in the network, keeping this information as up-to-date as practical. Such a location service generates a few outdated values but can be used by an upper level application that can tolerate such values, to provide various location dependent services. Our aim is to achieve algorithms that are simpler and more efficient than existing ones, through the application of probabilistic quorums at the expense of intermittently outdated information.