Abstract:It is known that parameter selection for data sampling frequency and segmentation techniques (including different methods and window sizes) has an impact on the classification accuracy. For Ambient Assisted Living (AAL), no clear information to select these parameters exists, hence a wide variety and inconsistency across today's literature is observed. This paper presents the empirical investigation of different data sampling rates, segmentation techniques and segmentation window sizes and their effect on the accuracy of Activity of Daily Living (ADL) event classification and computational load for two different accelerometer sensor datasets. The study is conducted using an ANalysis Of VAriance (ANOVA) based on 32 different window sizes, three different segmentation algorithm (with and without overlap, totaling in six different parameters) and six sampling frequencies for nine common classification algorithms. The classification accuracy is based on a feature vector consisting of Root Mean Square (RMS), Mean, Signal Magnitude Area (SMA), Signal Vector Magnitude (here SMV), Energy, Entropy, FFTPeak, Standard Deviation (STD). The results are presented alongside recommendations for the parameter selection on the basis of the best performing parameter combinations that are identified by means of the corresponding Pareto curve.

Automated methods of real-time, unobtrusive, human ambulation, activity, and wellness monitoring and data analysis using various algorithmic techniques have been subjects of intense research. The general aim is to devise effective means of addressing the demands of assisted living, rehabilitation, and clinical observation and assessment through sensor-based monitoring. The research studies have resulted in a large amount of literature. This paper presents a holistic articulation of the research studies and offers comprehensive insights along four main axes: distribution of existing studies; monitoring device framework and sensor types; data collection, processing and analysis; and applications, limitations and challenges. The aim is to present a systematic and most complete study of literature in the area in order to identify research gaps and prioritize future research directions.

In MANETs (Mobile Ad Hoc Networks) communication at the mobile nodes can be achieved by using multihop wireless links. The architecture of such network is based not on a centralized base station but on each node which acts as a router and forwards data packets to other nodes in the network. The aim of each protocol, in an ad-hoc network, is to find valid routes between two communicating nodes. These protocols must be able to handle high mobility of the nodes which often cause changes in the network topology. This paper evaluates four ad-hoc network protocols (AODV, DSDV, DSR and TORA) in different network scales taking into consideration the mobility factor. The evaluation of these four protocols was carried out using Network Simulator-2 (ns2), and the poor performance of TORA may be attributed to its implementation in this package. Therefore further investigation of TORA implementation in ns2 needs to be carried out. Wireless NetworksWireless systems, both mobile and fixed, have become an indispensable part of communication infrastructure. Their applications range from simple wireless low data rate transmitting sensors to high data rate real-time systems such as those used for monitoring large retail outlets or real-time broadcasting of sport events. The existing wireless technology is based on point-to-point technology. An example is GSM system with an architecture that is based on mobile nodes communicating directly with central access points. Sometimes there are networks which cannot rely on the centralized connectivity such as Mobile Ad-Hoc Networks (MANET). MANET is a wireless network having mobile nodes with no fixed infrastructure. These kinds of networks are used in areas such as environmental monitoring or in rescue operations. The main limitation of ad-hoc systems is the availability of power. In addition to running the onboard electronics, power consumption is governed by the number of processes and overheads required to maintain connectivity.A number of protocols have been developed for non-centralised networks, e.g. Temporally Order Routing Algorithm (TORA) [1] TORA is a protocol for multi-hop networks. The choice of a route in a multi-hop network influences the performance of the network, measured in terms of power consumption. There are some protocols that strive for energy efficient routing such as DSR (Dynamic Source Routing [2], AODV (Ad-Hoc On Demand Routing) [3] and DSDV (Destination-Sequenced Distance Vector) [4]. These protocols offer varying degrees of efficiency. This research focuses on communication protocols specifically aimed at limiting power consumption and prolonging battery life whilst maintaining the robustness of the system. It also proposes further research into more efficient protocols or variants of existing protocols such as TORA [1] and network topologies. Emphasis is on protocols that could be suitable for the implementation of scalable systems in high node density environments such as in manufacturing or product distribution industries. The main objective of thi...

No abstract

Abstract-Improved solar cell models and control methods using synergies of soft-computing techniques are used to demonstrate increased energy efficiencies of photovoltaic (PV) power plants connected to the electricity grid via space-vector-modulated threephase inverters. The models and control strategies are combined to form two new model-based controllers that are more accurate and resilient than existing solutions resulting in increased power production. A radial-basis-function-network (RBFN) model with a neuro-fuzzy regulator applied to a plant well characterized by the conventional solar cell model provided an estimated 1.5% increase in power production over an existing conventional model proportional integral (PI)-regulator combination. A neuro-fuzzy model with a neuro-fuzzy controller applied to a plant poorly characterized by the conventional solar cell model gave an 8.6% increase in power. An analysis of the net contributions to the increased efficiencies shows that the improved models had the most effect on power gains.Index Terms-Fuzzy neural networks, photovoltaic (PV) power systems, power system modeling, power system simulation.