Mobile agent networks, such as multi-UAV systems, are constrained by limited resources. In particular, limited energy affects system performance directly, such as system lifetime. It has been demonstrated in the wireless sensor network literature that the communication energy consumption dominates the computational and the sensing energy consumption. Hence, the lifetime of the multi-UAV systems can be extended significantly by optimizing the amount of communication data, at the expense of increasing computational cost. In this work, we aim at attaining an optimal trade-off between the communication and the computational energy. Specifically, we propose a mixed-integer optimization formulation for a multi-hop hierarchical clustering-based self-organizing UAV network incorporating data aggregation, to obtain an energy-efficient information routing scheme. The proposed framework is tested on two applications, namely target tracking and area mapping. Based on simulation results, our method can significantly save energy compared to a baseline strategy, where there is no data aggregation and clustering scheme. I. INTRODUCTIONInexpensive mobile agents, such as unmanned aerial vehicles (UAVs), are useful for several remote monitoring applications such as agriculture [1], geology [2], ecology [3] and forestry [4]. The viability of UAVs for scientific and non-military applications are due to reduced cost of the UAVs, low sensor cost and ease in handling. Typically, these applications are of large scale and the mission time can be shortened by introducing multiple UAVs.Central to these applications is the necessity to have a human-in-the-loop (HITL) capability that increases situational awareness and operator autonomy to modify missions dynamically. For HITL, UAVs have to gather and disseminate information periodically to the operator who may be located at a distant (base station) from the operational arena. Typical information required at the base station is aerial footage [5], which is a communication intensive operation consuming considerable energy. Unfortunately, low cost UAVs have limited flight time due to battery/fuel capacity. Hence, there is a need to find different mechanisms by which flight time endurance can be increased. One way is to use gliders that take advantage of the updrafts to soar for long endurance [6]. However, during soaring it is very difficult to maintain a good resolution of the terrain due to varying UAV height for mapping or surveillance applications. Instead, we propose to optimize the energy consumed by various units in a given aircraft to increase the flight time and hence the UAV team mission time.For many applications [1], [4], it is necessary that a UAV must fly at a constant speed and maintain a prescribed height. Under these conditions, the major energy consumption units are propulsion, sensing, computation and communication. On average, the power consumed during flight is approximately constant. The sensing and the computational units also consume constant power. However, the energy e...

A pattern matching method (signature-based) is widely used in basic network intrusion detection systems (IDS). A more robust method is to use a machine learning classifier to detect anomalies and unseen attacks. However, a single machine learning classifier is unlikely to be able to accurately detect all types of attacks, especially uncommon attacks e.g., Remote2Local (R2L) and User2Root (U2R) due to a large difference in the patterns of attacks. Thus, a hybrid approach offers more promising performance. In this paper, we proposed a Double-Layered Hybrid Approach (DLHA) designed specifically to address the aforementioned problem. We studied common characteristics of different attack categories by creating Principal Component Analysis (PCA) variables that maximize variance from each attack type, and found that R2L and U2R attacks have similar behaviour to normal users. DLHA deploys Naive Bayes classifier as Layer 1 to detect DOS and Probe, and adopts SVM as Layer 2 to distinguish R2L and U2R from normal instances. We compared our work with other published research articles using the NSL-KDD data set. The experimental results suggest that DLHA outperforms several existing state-of-the-art IDS techniques, and is significantly better than any single machine learning classifier by large margins. DLHA also displays an outstanding performance in detecting rare attacks by obtaining a detection rate of 96.67% and 100% from R2L and U2R respectively.

We propose three novel mathematical optimization formulations that solve the same two-type heterogeneous multiprocessor scheduling problem for a real-time taskset with hard constraints. Our formulations are based on a global scheduling scheme and a fluid model. The first formulation is a mixed-integer nonlinear program, since the scheduling problem is intuitively considered as an assignment problem. However, by changing the scheduling problem to first determine a task workload partition and then to find the execution order of all tasks, the computation time can be significantly reduced. Specifically, the workload partitioning problem can be formulated as a continuous nonlinear program for a system with continuous operating frequency, and as a continuous linear program for a practical system with a discrete speed level set. The latter problem can therefore be solved by an interior point method to any accuracy in polynomial time. The task ordering problem can be solved by an algorithm with a complexity that is linear in the total number of tasks. The work is evaluated against existing global energy/feasibility optimal workload allocation formulations. The results illustrate that our algorithms are both feasibility optimal and energy optimal for both implicit and constrained deadline tasksets. Specifically, our algorithm can achieve up to 40% energy saving for some simulated tasksets with constrained deadlines. The benefit of our formulation compared with existing work is that our algorithms can solve a more general class of scheduling problems due to incorporat-

No abstract