Class of physical activities

Physical activities can be classified into dynamic, static and postural transition. Activities that are characterized by large movements such as walking and running are classified as dynamic activity, while static activity is defined by activities that involve small movement such as sitting, lying down and standing. Postural transitions is the movements that change from one…

KCAR: A knowledge-driven approach for concurrent activity recognition

Ye et al. proposed a concurrent activity recognition technique by analyzing real-time input sensor events to determine their semantic dissimilarity to segment a continuous sensor sequence into fragments, which a fragment corresponds to one ongoing activity [1]. Sensor events is defined as a function with three parameters, each of which refers to reported time of…

Feature Selection and Activity Recognition System Using a Single Tri-Axial Accelerometer

Gupta and Dallas have proposed feature selection and activity recognition system using a single tri-axial accelerometer in 2014 [1]. The physical activities recognized in this study are walking, running, jumping, sit-to-stand/stand-to-sit, stand-to-kneel-tostand and being stationary (sitting and standing at one place). The data are sampled at 126Hz during the experiments. The acceleration data are segmented…

Context-aware activity recognition through a combination of ontological and statistical reasoning

Riboni and Bettini have proposed a techinique for human activity recognition using ontologies and ontological reasoning combined with statistical inferencing [1]. The technique does not relies on large amount of training data which is difficult to obtain in applications such as rehabilitation systems, chronic disease management or monitoring of the elderly. [1] Riboni, Daniele, and…

A Distributed Reasoning Engine Ecosystem for Semantic Context-Management in Smart Environments

Context information inference consumes a lot of time when dealing with large amount of data. This situation is common in modern ubiquitous computing when there are a lot of sensors and devices available. Therefore, Almeida and López-de-Ipiña have proposed an agent-based system architecture to distribute the context reasoning problem into smaller parts in order to…

Intelligent context-aware energy management using the incremental simultaneous method in future wireless sensor networks and computing systems

Nam et al. minimize energy wasting in wireless sensor network using simultaneous human activity pattern and Hierarchical Hidden Markov Model (HHMM) [1]. Activity context model is constructed by analyzing the simultaneous activity patterns using Incrementally Simultaneous Method (ISM) and representing the simultaneous activity patterns using Allen’s temporal relation logic. The result shows that weekly saving…

Power Management for Context Aware System

Energy efficiency is important issue in wireless sensor network application. Sensor nodes run on batteries which needs to replaced frequently. Thus, operational states of the sensor nodes should be adapted according to the surrounding to achieve best power consumption but without compromising accurate and good sensing service. Additionally, users could provide some inputs by setting…