In this study, we propose a novel context-based location aware algorithm for identification of low-level micro-activities that can be used to derive complex Activities of Daily Living (ADL) performed by home-care patients. This is achieved by gathering location information of the target user using a wearable beacon embedded with magnetometer and inertial sensors. The shortcomings of the beacon signal stability and mismatch issues in magnetic field sequences are overcome by adopting a hybrid three-phase approach for deducing the locus of micro-activities and their associated zones in a smart home environment. The suggested approach is assessed in two different test environments where the main intention is to map the location of a person performing an activity with pre-defined house landmarks and zones in the offline labelled database. In addition to recognition of low-level activities, the proposed method also identifies the person's walking trajectory within the same zone or between different zones of the house. Experimental results demonstrate that it is possible to achieve centimeter-level accuracy for recognition of micro-activities and a classification accuracy of 85% for trajectory prediction. These results are encouraging and imply that collection of accurate low-level information for ADL recognition is possible through integration of inertial sensors, magnetic field and Bluetooth Low Energy (BLE) technologies from the wearable without relying on other infrastructural sensors.
Human body motion can be captured by body area sensor networks. Accurate sensor placement with respect to anatomical landmarks is one of the main factors determining the accuracy of motion-capture systems. Changes in position of the sensors cause increased variability in the motion data, so isolating the characteristic features that represent the most important motion patterns is our concern. As accurate sensor placement is time-consuming and hard to achieve, we propose a signal processing technique that can enable salient data to be isolated. By using functional principal component analysis (f-PCA), we compensate for the variation in data due to changes in the on-body positioning of sensors. More precisely, we investigate the use of f-PCA for filtering and interpreting motion data, whilst accounting for variability in the sensor origin. Data are collected through a marker-based motion capture system from two designed experiments based on human body and robot arm movement. Results show differences between similar actions across different sessions of marker wearing with random changes in position of sensors. After applying the f-PCA filter on the data, we show how uncertainties due to sensor position changes can be compensated for.
As a promising use-case of the Internet of Things (IoT), wildlife tracking and monitoring applications greatly benefit the ecology-related research both commercially and scientifically. In literature, a forward-wait-deliver strategy has been researched to facilitate energy-efficient dissemination of delay-tolerant information, which penitentially contributes to long-term tracking and monitoring. However, this strategy is not directly applicable for wildlife tracking and monitoring applications, as the movement trajectory of animals cannot be precisely predicted for relay selection. To this end, further studies are required to utilize partially predictable mobility based on more generalized navigational information such as the movement direction. In this paper, the feasible exploitation of directional movement in path-unconstrained mobility is investigated for strategic forwarding. Our proposal is an advance to the state-of-the-art because the directional correlation of destination movement is considered to dynamically exploit the node mobility for the optimal selection of a stationary relay. Simulation results show that higher delivery utility can be achieved by the proposed fuzzy path model compared with a forwarding scheme without contact prediction or one based on linear trajectory model.
Frequent link breaks (due to node mobility) and quick exhaustion of energy (due to limited battery volume) are two major problems impacting on the flexibility in mobile ad hoc networks (MANETs). Cooperative communication in MANETs has become an appealing topic, as it can improve system capacity and energy efficiency. In spite of such advantages of cooperative communication, some issues still remain, such as the lack of a systematically designed cooperative routing scheme (including route discovery, route reply, route enhancement, and cooperative data forwarding), facilitation of cooperative communication in mobility resistance, and route selection (jointly considering energy consumption, energy-harvesting ability, and link break probability). Driven by the above concerns, we propose a novel Constructive-Relay-based CooPerative Routing (CRCPR) protocol in this paper. Using topological information stored and maintained in a COoPerative Table and Relay Table, CRCPR enhances resilience to mitigate the mobility issue by self-managing to construct adequate relays for data forwarding. Furthermore, assuming nodes are mostly battery operated, CRCPR proposes a new route selection mechanism, which takes into account energy consumption, energy harvesting, and link break probability, to determine an appropriate route across a network. Simulation results show the robustness of CRCPR against node mobility, further with improvement for up to 60% network throughput and 40% prolonged network lifetime.
In this paper, we propose a collision avoidance algorithm for multi-vehicle systems, which is a common problem in many areas, including navigation and robotics. In dynamic environments, vehicles may become involved in potential collisions with each other, particularly when the vehicle density is high and the direction of travel is unrestricted. Cooperatively planning vehicle movement can effectively reduce and fairly distribute the detour inconvenience before subsequently returning vehicles to their intended paths. We present a novel method of cooperative path planning for multi-vehicle systems based on reinforcement learning to address this problem as a decision process. A dynamic system is described as a multi-dimensional space formed by vectors as states to represent all participating vehicles’ position and orientation, whilst considering the kinematic constraints of the vehicles. Actions are defined for the system to transit from one state to another. In order to select appropriate actions whilst satisfying the constraints of path smoothness, constant speed and complying with a minimum distance between vehicles, an approximate value function is iteratively developed to indicate the desirability of every state-action pair from the continuous state space and action space. The proposed scheme comprises two phases. The convergence of the value function takes place in the former learning phase, and it is then used as a path planning guideline in the subsequent action phase. This paper summarizes the concept and methodologies used to implement this online cooperative collision avoidance algorithm and presents results and analysis regarding how this cooperative scheme improves upon two baseline schemes where vehicles make movement decisions independently.
The increasingly complex roles for which Wireless Sensor Networks (WSNs) are being employed have driven the desire for energy-efficient reliable target tracking. In this paper, a biologically inspired, adaptive energy-efficient multi-sensor scheme is proposed for collaborative target tracking in WSNs. Behavioural data gleaned whilst tracking the target is recorded as metadata to maintain the tracking accuracy. The group of tasking sensors that track the target is selected proactively according to the information associated with the predicted target location probability distribution. One of the selected tasking sensors is elected as a main node for management operations to improve the energy efficiency. Simulation results show that the developed adaptive multi-sensor scheme can achieve a significant reduction in energy consumption and seamless tracking compared with uniform sampling interval schemes.