Design and Implementation of a Novel System for Correcting Posture Through the Use of a Wearable Necklace Sensor.

BACKGROUND: To our knowledge, few studies have examined the use of wearable sensing devices to effectively integrate information communication technologies and apply them to health care issues (particularly those pertaining to posture correction). OBJECTIVE: A novel system for posture correction involving the application of wearable sensing technology was developed in this study. The system was created with the aim of preventing the unconscious development of bad postures (as well as potential spinal diseases over the long term). METHODS: The newly developed system consists of a combination of 3 subsystems, namely, a smart necklace, notebook computer, and smartphone. The notebook computer is enabled to use a depth camera to read the relevant data, to identify the skeletal structure and joint reference points of a user, and to compute calculations relating to those reference points, after which the computer then sends signals to the smart necklace to enable calibration of the smart necklace's standard values (base values for posture assessment). The gravitational acceleration data of the user are collected and analyzed by a microprocessor unit-6050 sensor housed in the smart necklace when the smart necklace is worn, with those data being used by the smart necklace to determine the user's body posture. When poor posture is detected by the smart necklace, the smart necklace sends the user's smartphone a reminder to correct his or her posture; a mobile app that was also developed as part of the study allows the smart necklace to transmit such messages to the smartphone. RESULTS: The system effectively enables a user to monitor and correct his or her own posture, which in turn will assist the user in preventing spine-related diseases and, consequently, in living a healthier life. CONCLUSIONS: The proposed system makes it possible for (1) the user to self-correct his or her posture without resorting to the use of heavy, thick, or uncomfortable corrective clothing; (2) the smart necklace's standard values to be quickly calibrated via the use of posture imaging; and (3) the need for complex wiring to be eliminated through the effective application of the Internet of Things as well as by implementing wireless communication between the smart necklace, notebook computer, and smartphone.

T-S region-based fuzzy control with multiple performance constraints.

Takagi-Sugeno fuzzy control problems with minimizing H2/Hinfinity norm are investigated in this paper. A redesigned T-S fuzzy model and controller are called a T-S Region-based Fuzzy Model (TSRFM) and a T-S Region-based Fuzzy Controller (TSRFC), respectively, which are derived from the fuzzy region concept and the robust control technique. The fuzzy region concept is used to divide the general plant rules into several fuzzy regions and the robust control technique is used to stabilize all plant rules of each fuzzy region. In this case, the stability conditions with H2/Hinfinity performance are derived from Lyapunov criterion, which are expressed in terms of LMIs. For the fuzzy model involving large plant rules, the proposed idea greatly reduces the total number of LMIs and controller rules so that TSRFC is easy to implement with simple hardware. Although the controller rules are reduced, TSRFC is able to provide performance as good as former designs.

Application of facial electromyography in computer mouse access for people with disabilities.

PURPOSE: This study develops a newly facial EMG human-computer interface for people with disabilities for controllng the movement of the cursor on a computer screen. METHOD: We access the computer cursor according to different facial muscle activity patterns. In order to exactly detect the muscle activity threshold, this study adopts continuous wavelet transformation to estimate the single motor unit action potentials dynamically. RESULT: The experiment indicates that the accuracy of using the facial mouse is greater than 80%, and this result indicates the feasibility of the proposed system. Moreover, the subject can improve performance of manipulation by repeated training. CONCLUSION: Compared with previous works, the proposed system achieves complete cursor function and provides an inexpensive solution. Although there are still some drawbacks in the facial EMG-based human-computer interface, the facial mouse can provide an alternative among other expensive and complicated assistive technologies.

Neuro-sliding mode control with its applications to seesaw systems.

This paper proposes an approach of cooperative control that is based on the concept of combining neural networks and the methodology of sliding mode control (SMC). The main purpose is to eliminate the chattering phenomenon. Next, the system performance can be improved by using the method of SMC. In the present approach, two parallel Neural Networks are utilized to realize a neuro-sliding mode control (NSMC), where the equivalent control and the corrective control are the outputs of neural network 1 and neural network 2, respectively. Based on expressions of the SMC, the weight adaptations of neural network can be determined. Furthermore, the gradient descent method is used to minimize the control force so that the chattering phenomenon can be eliminated. Finally, experimental results are given to show the effectiveness and feasibility of the approach.