A wearable and flexible Bracelet computer for on-body sensing

With the wide applications of smart devices and mobile computing, smart home becomes a hot issue in the household appliance industry. The controlling and interaction approach plays a key role in users' experience and turns into one of the most important selling points for profit growth. Considering the robustness and privacy protection, wearable devices equipped with MEMS, e.g., smartphones, smartwatches, or smart wristbands, are thought of one of the most feasible commercial solutions for interaction. However, the low-cost built-in MEMS sensors do not perform well in capturing finely grained human activity directly. In this paper, we propose a method that leverages the arm constraint and historical information recorded by MEMS sensors to estimate the maximum likelihood action in a two-phases model. First, in the arm posture estimation phase, we leverage the kinematics model to analyze the maximum likelihood position of users' arms. Second, in the trajectory recognition phase, we leverage the gesture estimation model to identify the key actions and output the instructions to devices by SVM. Our substantial experiments show that the proposed solution can recognize eight kinds of postures defined for manmachine interaction in the smart home application scene, and the solution implements efficient and effective interaction using low-cost smartwatches, and the interaction accuracy is >87%. The experiments also show that the algorithm proposed in this paper can be well applied to the perceptual control of smart household appliances, and has high practical value for the application design of the perceptual interaction function of household appliances.

show abstract

“…To solve this problem, we need to define Lagrange function as (11) and the kernel functions are introduced as :…”

Section: Interactive Action Recognitionmentioning

confidence: 99%

“…With the development of science and technology in recent years, smart devices emerge in an endless stream. A series of smart devices begin to enter people's lives, such as smart phones [10], smart wristbands [11], smart watches [12] and smart glasses [13].…”

Section: Introductionmentioning

confidence: 99%

Control Your Home With a Smartwatch

Zhao

Duan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The modular Bracelet system [1] [3] can be tailored to specific applications according to the requirements. It is not within the scope of this paper to present the system in detail, but to provide essential background for understanding different aspects of the system.…”

Section: The Bracelet Systemmentioning

confidence: 99%

“…It is not within the scope of this paper to present the system in detail, but to provide essential background for understanding different aspects of the system. Interested readers are referred to [3] for details on the Bracelet System.…”

Section: The Bracelet Systemmentioning

confidence: 99%

Making sense of sensor data in practical wireless sensor network designs

Shum

Hailes

McPhillips

et al. 2012

2012 International Conference on Computing, Networking and Communications (ICNC)

Self Cite

View full text Add to dashboard Cite

Fine-grained street-level Carbon Monoxide data with stringent accuracy requirements are required in a collaborative project with environmental scientists. In this project, the chosen electrochemical sensors and the sensor modules were calibrated against concentration and temperature, which is the major environmental factor that affects the baseline of the calibration curve. It was found that there are other environmental factors, including humidity, air flow rate and other gases particular to this application that may contribute to the inaccuracy in the measurements and should be addressed in the system design. The sensitivity of the sensors also decreases with time, which means that sensors are required to be re-calibrated during a long deployment. Observations from real experiments are reported in this paper.

show abstract

“…While signal strength measurement is not as accurate as time difference of arrival or time of arrival [10] it requires no extra hardware to implement and instead relies upon the standard RSSI values reported by most packet-based radio transceivers. This means that unlike other wrist mounted schemes [11] this localization method may be implemented using commercial off the shelf hardware.…”

Section: Introductionmentioning

confidence: 99%

Body shadowing mitigation using differentiated LOS / NLOS channel models for RSSI-based Monte Carlo personnel localization

Cully

Cotton

Scanlon

et al. 2012

2012 IEEE Wireless Communications and Networking Conference (WCNC)

View full text Add to dashboard Cite

Research into localization has produced a wealth of algorithms and techniques to estimate the location of wireless network nodes, however the majority of these schemes do not explicitly account for non-line of sight conditions. Disregarding this common situation reduces their accuracy and their potential for exploitation in real world applications. This is a particular problem for personnel tracking where the user's body itself will inherently cause time-varying blocking according to their movements. Using empirical data, this paper demonstrates that, by accounting for non-line of sight conditions and using received signal strength based Monte Carlo localization, meter scale accuracy can be achieved for a wrist-worn personnel tracking tag in a 120 m 2 indoor office environment.

show abstract

A wearable and flexible Bracelet computer for on-body sensing

Cited by 14 publications

References 12 publications

Control Your Home With a Smartwatch

Control Your Home With a Smartwatch

Making sense of sensor data in practical wireless sensor network designs

Body shadowing mitigation using differentiated LOS / NLOS channel models for RSSI-based Monte Carlo personnel localization

Contact Info

Product

Resources

About