Anomaly detection is a key factor in the processing of large amounts of sensor data from Wireless Sensor Networks (WSN). Efficient anomaly detection algorithms can be devised performing online node-local computations and reducing communication overhead, thus improving the use of the limited hardware resources. This work introduces a fixed-point embedded implementation of Online Sequential Extreme Learning Machine (OS-ELM), an online learning algorithm for Single Layer Feed forward Neural Networks (SLFN). To overcome the stability issues introduced by the fixed precision, we apply correction mechanisms previously proposed for Recursive Least Squares (RLS). The proposed implementation is tested extensively with generated and real-world datasets, and compared with RLS, Linear Least Squares Estimation, and a rule-based method as benchmarks. The methods are evaluated on the prediction accuracy and on the detection of anomalies. The experimental results demonstrate that fixed-point OS-ELM can be successfully implemented on resource-limited embedded systems, with guarantees of numerical stability. Furthermore, the detection accuracy of fixed-point OS-ELM shows better generalization properties in comparison with, for instance, fixed-point RLS. © 2013 IEEE.
DOCUMENT
Energy conservation is crucial in wireless ad hoc sensor network design to increase network lifetime. Since communication consumes a major part of the energy used by a sensor node, efficient communication is important. Topology control aims at achieving more efficient communication by dropping links and reducing interference among simultaneous transmissions by adjusting the nodes’ transmission power. Since dropping links make a network more susceptible to node failure, a fundamental problem in wireless sensor networks is to find a communication graph with minimum interference and minimum power assignment aiming at an induced topology that can satisfy fault-tolerant properties. In this paper, we examine and propose linear integer programming formulations and a hybrid meta-heuristic GRASP/VNS (Greedy Randomized Adaptive Search Procedure/Variable Neighborhood Search) to determine the transmission power of each node while maintaining a fault-tolerant network and simultaneously minimize the interference and the total power consumption. Optimal biconnected topologies for moderately sized networks with minimum interference and minimum power are obtained using a commercial solver. We report computational simulations comparing the integer programming formulations and the GRASP/VNS, and evaluate the effectiveness of three meta-heuristics in terms of the tradeoffs between computation time and solution quality. We show that the proposed meta-heuristics are able to find good solutions for sensor networks with up to 400 nodes and that the GRASP/VNS was able to systematically find the best lower bounds and optimal solutions.
DOCUMENT
An energy harvesting device for obtaining energy from drops without needing of moving the drops along the device, in a reduced scale and combinable with othertypes of harvesting devices, the energy harvesting device comprising one or more triboelectric generators comprising a bottom electrode, a friction or triboelectric element placed over the bottom electrode, and at least two top electrodes placed over the triboelectric element and defining at least one gap between them, exposing the triboelectric element to the external environment so that on contacting a drop of liquid makes an electrical connection between the top electrodes varying the capacitance of the triboelectric generators and alternatively for functioning as a power unit for a sensor or as a self-powered sensor producing an electrical signal generated by the contact of the liquid with the electrodes.
DOCUMENT
The maturing field of Wireless Sensor Networks (WSN) results in long-lived deployments that produce large amounts of sensor data. Lightweight online on-mote processing may improve the usage of their limited resources, such as energy, by transmitting only unexpected sensor data (anomalies). We detect anomalies by analyzing sensor reading predictions from a linear model. We use Recursive Least Squares (RLS) to estimate the model parameters, because for large datasets the standard Linear Least Squares Estimation (LLSE) is not resource friendly. We evaluate the use of fixed-point RLS with adaptive thresholding, and its application to anomaly detection in embedded systems. We present an extensive experimental campaign on generated and real-world datasets, with floating-point RLS, LLSE, and a rule-based method as benchmarks. The methods are evaluated on prediction accuracy of the models, and on detection of anomalies, which are injected in the generated dataset. The experimental results show that the proposed algorithm is comparable, in terms of prediction accuracy and detection performance, to the other LS methods. However, fixed-point RLS is efficiently implementable in embedded devices. The presented method enables online on-mote anomaly detection with results comparable to offline LS methods. © 2013 IEEE.
DOCUMENT
Sensor systems can be deployed in the homes of older adults living alone for functional health assessments. Their information is very useful for health care specialists. The problem lies in developing person independent models while facing a large variability in behavior. We address this problem by, first, proposing a new feature extraction method for data from ambient motion sensors. The method uses functional similarities between houses and daily structure to extract meaningful features. Second, we propose a change-based approach for analyzing data, taking difference scores of both the sensor features and health metrics. To evaluate our approach, experiments on longitudinal data were conducted, where the relationship between sensor data and health measurements was modeled with linear regression and (nonlinear) regression forests. These experiments show that the change-based approach yields better results and that the resulting models can be used as a reliable metric for (functional) health. In addition, feature analysis can help health care specialists understand relevant aspects of behavior. Prediction of health metrics is possible even with simple sensors. With such sensors, it is possible to detect problems and health decline in an early stage. This will have great impact on clinical practice.
DOCUMENT
Existing research on the recognition of Activities of Daily Living (ADL) from simple sensor networks assumes that only a single person is present in the home. In real life there will be situations where the inhabitant receives visits from family members or professional health care givers. In such cases activity recognition is unreliable. In this paper, we investigate the problem of detecting multiple persons in an environment equipped with a sensor network consisting of binary sensors. We conduct a real-life experiment for detection of visits in the oce of the supervisor where the oce is equipped with a video camera to record the ground truth. We collected data during two months and used two models, a Naive Bayes Classier and a Hidden Markov Model for a visitor detection. An evaluation of these two models shows that we achieve an accuracy of 83% with the NBC and an accuracy of 92% with a HMM, respectively.
MULTIFILE
Reliability is a constraint of low-power wireless connectivity, commonly addressed by the deployment of mesh topology. Accordingly, power consumption becomes a major concern during the design and implementation of such networks. Thus, a mono-objective optimization was implemented in this work to decrease the total amount of power consumed by a low-power wireless mesh network based on Thread protocol. Using a genetic algorithm, the optimization procedure takes into account a pre-defined connectivity matrix, in which the possible distances between all network devices are considered. The experimental proof-of-concept shows that a mean gain of 26.45 dB is achievable in a specific scenario. Through our experimental results, we conclude that the Thread mesh protocol has much leeway to meet the low-power consumption requirement of wireless sensor networks.
LINK
A low-cost sensornode is introduced to monitor the 5G EMF exposure in the Netherlands for the four FR1 frequency bands. The sensornode is validated with in-lab measurements both with CW signals as for QAM signals and perform for both cases and for all frequency bands an error less than 1 dB for a dynamic range of 40 dB. This sensor is a follow up of the earlier version of our previously developed sensor and have substantial improvements in terms of linearity, error, and stability.
DOCUMENT
Ambient monitoring systems offer great possibilities for health trend analysis in addition to anomaly detection. Health trend analysis helps care professionals to evaluate someones functional health and direct or evaluate the choice of interventions. This paper presents one case study of a person that was followed with an ambient monitoring system for almost three years and another of a person that was followed for over a year. A simple algorithm is applied to make a location based data representation. This data is visualized for care professionals, and used for inspecting the regularity of the pattern with means of principal component analysis (PCA). This paper provides a set of tools for analyzing longitudinal behavioral data for health assessments. We advocate a standardized data collection procedure, particularly the health metrics that could be used to validate health focused sensor data analyses.
DOCUMENT
Wireless sensor networks are becoming popular in the field of ambient assisted living. In this paper we report our study on the relationship between a functional health metric and features derived from the sensor data. Sensor systems are installed in the houses of nine people who are also quarterly visited by an occupational therapist for functional health assessments. Different features are extracted and these are correlated with a metric of functional health (the AMPS). Though the sample is small, the results indicate that some features are better in describing the functional health in the population, but individual differences should also be taken into account when developing a sensor system for functional health assessment.
DOCUMENT
