The TDOA-based source localization problem in sensor networks is considered with sensor node location uncertainty. A total least squares (TLSs) algorithm is developed by a linear closed-form solution for this problem, and the uncertainty of the sensor location is formulated as a perturbation. The sensitivity of the TLS solution is also analyzed. Simulation results show its improved performance against the classic least squares approaches.
This paper introduces a two-stage approach to the detection of people eating and/or drinking for the purposes of surveillance of daily life. With the sole use of wearable accelerometer sensor attached to somebody’s (man or a woman) wrists, this two-stage approach consists of feature extraction followed by classification. At the first stage, based on the limb’s three dimensional kinematics movement model and the Extended Kalman Filter (EKF), the realtime arm movement features described by Euler angles are extracted from the raw accelerometer measurement data. In the latter stage, the Hierarchical Temporal Memory (HTM) network is adopted to classify the extracted features of the eating/drinking activities based on the space and time varying property of the features, by making use of the powerful modelling capability of HTM network on dynamic signals which is varying with both space and time. The proposed approach is tested through the real eating and drinking activities using the three dimensional accelerometers. Experimental results show that the EKF and HTM based two-stage approach can perform the activity detection successfully with very high accuracy.
This paper is concerned with the estimation problem for a dynamic stochastic estimation in a sensor network. Firstly, the quantized Kalman filter based on the quantized observations (QKFQO) is presented. Approximate solutions for two optimal bandwidth scheduling problems are given, where the tradeoff between the number of quantization levels or the bandwidth constraint and the energy consumption is considered. However, for a large observed output, quantizing observations will result in large information loss under the limited bandwidth. To reduce the information loss, another quantized Kalman filter based on quantized innovations (QKFQI) is developed, which requires that the fusion center broadcast the one-step prediction of state and innovation variances to the tasking sensor nodes. Compared with QKFQO, QKFQI has better accuracy. Simulations show the effectiveness.
Distributed estimation of Gaussian mixtures has many applications in wireless sensor network (WSN), and its energy-efficient solution is still challenging. This paper presents a novel diffusion-based EM algorithm for this problem. A diffusion strategy is introduced for acquiring the global statistics in EM algorithm in which each sensor node only needs to communicate its local statistics to its neighboring nodes at each iteration. This improves the existing consensus-based distributed EM algorithm which may need much more communication overhead for consensus, especially in large scale networks. The robustness and scalability of the proposed approach can be achieved by distributed processing in the networks. In addition, we show that the proposed approach can be considered as a stochastic approximation method to find the maximum likelihood estimation for Gaussian mixtures. Simulation results show the efficiency of this approach.
Due to uncertainties of target and limited sensing range and possible miss detection of sensor, single sensor based collaborative target tracking, as addressed in existing literature, suffers from the low tracking accuracy and unreliability problem when a scheduled sensor fails to detect the target. In this paper, a multi-sensor scheduling scheme for collaborative target tracking in WSNs is proposed where at each time step, a number of sensors are selected based on a specified detection probability. These tasking sensors form a temporary tracking group with one of them being the leader to carry out fusion estimation of target using measurements from the tasking sensors. The leader is also responsible for tasking sensor selection for the next time step. Due to the difficulties in calculating the joint detection probability of multiple sensors, a Monte Carlo method is adopted for calculating the detection probability. An incremental sensor selection heuristic is proposed to select tasking sensors to meet the specified detection probability requirement. Simulation results show that, compared to a single sensor scheduling approach, the proposed approach can significantly improve the tracking accuracy and the reliability