Results 1 -
4 of
4
An Energy Effective Adaptive Spatial Sampling Algorithm for WSNs
"... Abstract: The objective of environmental observation with WSNs (wireless sensor networks) is to extract the synoptic structures (spatio-temporal sequence) of the phenomena of ROI (region of interest) in order to make effective predictive and analytical characterizations. Energy limitation is one of ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: The objective of environmental observation with WSNs (wireless sensor networks) is to extract the synoptic structures (spatio-temporal sequence) of the phenomena of ROI (region of interest) in order to make effective predictive and analytical characterizations. Energy limitation is one of the main obstacles to the universal application of WSNs and therefore there are a large mass of researches on energy conservation for WSNs. Among them, adaptive sampling strategy is regarded as a promising method to improve energy efficiency in recent years, therefore, many researches are concerning to different kinds of energy efficient sampling scheme for WSNs. In this paper, we dedicate to investigating how to schedule sensor nodes in the spatial region domain by our adaptive sampling scheme so as to reduce energy consumption of sensor nodes. The key idea of this paper is to schedule sensor nodes to achieve the desired level of accuracy by activating sensor system only when necessary to acquire a new set of samples and then prepare to power it off immediately afterwards. By adaptively sampling the region of interest, fewer sensors are activated at the same time. Moreover, only the necessary communications are remaining with this algorithm, so as to achieve significant energy conservation than before. The algorithm proposed in this literature is named as Adaptive Spatial Sampling (ASS) algorithm in short. The simulation results verified that ASS algorithm can outperform traditional fixed sampling strategy.
1 A Review on Radio Based Activity Recognition
"... Recognizing human activities in their daily living enables the development and widely usage of human-centric applications, such as health monitoring, assisted living, etc. Traditional activity recognition methods often rely on physical sensors (camera, accelerometer, gyroscope, etc.) to continuously ..."
Abstract
- Add to MetaCart
(Show Context)
Recognizing human activities in their daily living enables the development and widely usage of human-centric applications, such as health monitoring, assisted living, etc. Traditional activity recognition methods often rely on physical sensors (camera, accelerometer, gyroscope, etc.) to continuously collect sensor readings, and utilize pattern recognition algorithms to identify user's activities at an aggregator. Though traditional activity recognition methods have been demonstrated to be effective in previous work, they raise some concerns such as privacy, energy consumption and deployment cost. In recent years, a new activity recognition approach, which takes advantage of body attenuation and/or channel fading of wireless radio, has been proposed. Compared with traditional activity recognition methods, radio based methods utilize wireless transceivers in environments as infrastructure, exploit radio communication characters to achieve high recognition accuracy, reduce energy cost and preserve user's privacy. In this paper, we divide radio based methods into four categories: ZigBee radio based activity recognition, WiFi radio based activity recognition, RFID radio based activity recognition, and other radio based activity recognition. Some existing work in each category is introduced and reviewed in detail. Then, we compare some representative methods to show their advantages and disadvantages. At last, we point out some future research directions of this new research topic. 2 1.
1Exploiting the Data Sensitivity of Neurometric Fidelity for Optimizing EEG Sensing
"... Abstract—With newly developed wireless neuroheadsets, elec-troencephalography (EEG) neurometrics can be incorporated into in-situ and ubiquitous physiological monitoring for hu-man mental health. As a resource constraint system providing critical health services, the EEG headset design must consider ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—With newly developed wireless neuroheadsets, elec-troencephalography (EEG) neurometrics can be incorporated into in-situ and ubiquitous physiological monitoring for hu-man mental health. As a resource constraint system providing critical health services, the EEG headset design must consider both high application fidelity and energy efficiency. However, through empirical studies with an off-the-shelf Emotiv EPOC Neuroheadset, we uncover a mismatch between lossy EEG sensor communication and high neurometric application fidelity requirements. To tackle this problem, we study how to learn the sensitivity of neurometric application fidelity to EEG data. The learned sensitivity is used to develop two algorithms: an energy minimization algorithm minimizing the energy usage in EEG sampling and networking while meeting applications ’ fidelity requirements; a fidelity maximization algorithm maximizing the sum of all applications ’ fidelities through the incorporation and optimal utilization of a limited data buffer. The effectiveness of our proposed solutions is validated through trace-driven experiments. Index Terms—EEG sensors, neurometric fidelity, energy effi-ciency, data sensitivity analysis.
Limitations with Activity Recognition Methodology & Data Sets
"... Human activity recognition (AR) has begun to mature as a field, but for AR research to thrive, large, diverse, high quality, AR data sets must be publically available and AR methodology must be clearly documented and standardized. In the process of comparing our AR research to other efforts, however ..."
Abstract
- Add to MetaCart
(Show Context)
Human activity recognition (AR) has begun to mature as a field, but for AR research to thrive, large, diverse, high quality, AR data sets must be publically available and AR methodology must be clearly documented and standardized. In the process of comparing our AR research to other efforts, however, we found that most AR data sets are sufficiently limited as to impact the reliability of existing research results, and that many AR research papers do not clearly document their experimental methodology and often make unrealistic assumptions. In this paper we outline problems and limitations with AR data sets and describe the methodology problems we noticed, in the hope that this will lead to the creation of improved and better
