Can Tunca

Ring Routing: An Energy-Efficient Routing Protocol for Wireless Sensor Networks with a Mobile Sink

In a typical wireless sensor network, the batteries of the nodes near the sink deplete quicker than other nodes due to the data traffic concentrating towards the sink, leaving it stranded and disrupting the sensor data reporting. To mitigate this problem, mobile sinks are proposed. They implicitly provide load-balanced data delivery and achieve uniform-energy consumption across the network. On the other hand, advertising the position of the mobile sink to the network introduces an overhead in terms of energy consumption and packet delays. In this paper, we propose Ring Routing, a novel, distributed, energy-efficient mobile sink routing protocol, suitable for time-sensitive applications, which aims to minimize this overhead while preserving the advantages of mobile sinks. Furthermore, we evaluate the performance of Ring Routing via extensive simulations.

Multimodal Wireless Sensor Network-Based Ambient Assisted Living in Real Homes with Multiple Residents

Human activity recognition and behavior monitoring in a home setting using wireless sensor networks (WSNs) provide a great potential for ambient assisted living (AAL) applications, ranging from health and wellbeing monitoring to resource consumption monitoring. However, due to the limitations of the sensor devices, challenges in wireless communication and the challenges in processing large amounts of sensor data in order to recognize complex human activities, WSN-based AAL systems are not effectively integrated in the home environment. Additionally, given the variety of sensor types and activities, selecting the most suitable set of sensors in the deployment is an important task. In order to investigate and propose solutions to such challenges, we introduce a WSN-based multimodal AAL system compatible for homes with multiple residents. Particularly, we focus on the details of the system architecture, including the challenges of sensor selection, deployment, networking and data collection and provide guidelines for the design and deployment of an effective AAL system. We also present the details of the field study we conducted, using the systems deployed in two different real home environments with multiple residents. With these systems, we are able to collect ambient sensor data from multiple homes. This data can be used to assess the wellbeing of the residents and identify deviations from everyday routines, which may be indicators of health problems. Finally, in order to elaborate on the possible applications of the proposed AAL system and to exemplify directions for processing the collected data, we provide the results of several human activity inference experiments, along with examples on how such results could be interpreted. We believe that the experiences shared in this work will contribute towards accelerating the acceptance of WSN-based AAL systems in the home setting.

Daily life behaviour monitoring for health assessment using machine learning: bridging the gap between domains

Analysis of human behaviour for deducing health and well-being information is one of the contemporary challenges given the ageing in place. To this end, existing and newly developed machine learning methods are needed to be evaluated using annotated real-world data sets. However, the metrics used in performance evaluation are directly taken from the machine learning domain, and they do not necessarily consider the specific needs of human behaviour analysis such as recognizing the duration, start time and frequency of the activities. Moreover, the commonly used metrics such as accuracy or F-measure can be misleading in the presence of skewed class distributions as in the case of human behaviour recognition. In this study, we evaluate the performance of two machine learning methods, hidden Markov model and time windowed neural network on five different real-world data sets through human behaviour understanding for health assessment perspective. According to the experimental results, standard metrics fail to reveal the actual performance of the two compared machine learning methods in terms of behaviour recognition. On the other hand, the proposed evaluation mechanism which considers three different activity categories leads to a more realistic evaluation of the overall performance.

Inertial Sensor-Based Robust Gait Analysis in Non-Hospital Settings for Neurological Disorders

The gold standards for gait analysis are instrumented walkways and marker-based motion capture systems, which require costly infrastructure and are only available in hospitals and specialized gait clinics. Even though the completeness and the accuracy of these systems are unquestionable, a mobile and pervasive gait analysis alternative suitable for non-hospital settings is a clinical necessity. Using inertial sensors for gait analysis has been well explored in the literature with promising results. However, the majority of the existing work does not consider realistic conditions where data collection and sensor placement imperfections are imminent. Moreover, some of the underlying assumptions of the existing work are not compatible with pathological gait, decreasing the accuracy. To overcome these challenges, we propose a foot-mounted inertial sensor-based gait analysis system that extends the well-established zero-velocity update and Kalman filtering methodology. Our system copes with various cases of data collection difficulties and relaxes some of the assumptions invalid for pathological gait (e.g., the assumption of observing a heel strike during a gait cycle). The system is able to extract a rich set of standard gait metrics, including stride length, cadence, cycle time, stance time, swing time, stance ratio, speed, maximum/minimum clearance and turning rate. We validated the spatio-temporal accuracy of the proposed system by comparing the stride length and swing time output with an IR depth-camera-based reference system on a dataset comprised of 22 subjects. Furthermore, to highlight the clinical applicability of the system, we present a clinical discussion of the extracted metrics on a disjoint dataset of 17 subjects with various neurological conditions.

Ring routing: An energy-efficient routing protocol for wireless sensor networks with a mobile sink

In a typical wireless sensor network, the batteries of the nodes near the sink deplete quicker than other nodes due to the data traffic concentrating towards the sink, leaving it stranded and disrupting the sensor data reporting. To mitigate this problem, mobile sinks are proposed. They implicitly provide load-balanced data delivery and achieve uniform-energy consumption across the network. On the other hand, advertising the position of the mobile sink to the network introduces an overhead in terms of energy consumption and packet delays. In this paper, we propose Ring Routing, a novel, distributed, energy-efficient mobile sink routing protocol, suitable for time-sensitive applications, which aims to minimize this overhead while preserving the advantages of mobile sinks. Furthermore, we evaluate the performance of Ring Routing via extensive simulations.

Performance evaluation of wireless sensor networks in realistic wildfire simulation scenarios

Forest fires lead to high amount of environmental and economic loss all over the world. Prevention and early detection efforts aim to eliminate or minimize the damage that will be caused by a fire incident. Current surveillance systems for forest fires do not provide dense real-time monitoring and hence they lack prevention or early detection of a fire threat. Wireless sensor networks (WSNs), on the other hand, can collect real-time information such as temperature and humidity from almost all points of a forest and can provide fresh and accurate data for the fire-fighting management center quickly. In this work, we aim to evaluate the reporting performance of a WSN under realistic workload. Since fires are destructive and burning a deployed WSN is not feasible, simulation is the appropriate way to assess the reporting capability of a WSN during a forest fire. We integrate WSN simulator with a realistic fire propagation simulator which is modified to provide time based temperature field information while the fire propagates through the deployment area. Temperature information is used for the generation of realistic workloads and the determination of sensor destruction times that affects the routing decisions in WSN simulations. We present the effects of WSN related factors; such as reporting rate, number of the sinks, and the sink locations together with the effects of environmental factors such as the wind speed and the number of ignition points in terms of temperature reporting performance and freshness of temperature map.

Performance evaluation of heterogeneous wireless sensor networks for forest fire detection

Forest fires are catastrophes which threaten the natural and human life. Economical, natural and cultural devastation caused by forest fires render the early detection and prevention of forest fires necessary. The success of a forest fire detection system can be assessed in terms of its accurate and quick detection capabilities. It is observed that wireless sensor networks (WSN) have a higher performance in especially early fire detection and high resolution fire monitoring compared to the existing fire detection systems. Temperature and humidity information of particular forest locations can be measured in real-time through the dense deployment of numerous sensors to a particular forest area and these information can be transmitted to the fire-fighting management center quickly. In this study, we evaluate the performance of a heterogeneous WSN-based architecture consisting of various types of devices, which is proposed in the scope of the FP7 FIRESENSE project to increase the capabilities of WSNs, with realistic fire propagation and network simulation experiments. Furthermore, we present a glance at the real life demonstrations.