Reliability and validity analyzes of Kinect V2 based measurement system for shoulder motions.

Telerehabilitation systems provide some advantages against the classic rehabilitation methods. The ability of the shoulders depends on active motion range of them to do activities in daily life and to do sports. To evaluate the shoulder motions, range of motion (ROM) measurement is a basic method. Clinical goniometer and digital goniometer are the most commonly used measurement tools. However, these measurement tools have some deficiencies and difficulties. In this paper, we consider a Kinect One Sensor (Kinect V2) based measurement system for shoulder motions as an alternative method. The aim of this study is to examine the reliability and validity analyzes of the proposed shoulder measurement system. Three systems were used to evaluate validity of the Kinect V2 to measure shoulder motions: Kinect V2 based system, clinical goniometer and digital goniometer. One expert physical therapist measured shoulder abduction, flexion, external rotation, internal rotation and extension ROM values using a clinical goniometer and a digital goniometer in 40 healthy volunteers (22 males, 18 females, and 19-33 years old). All poses for each shoulder motion were captured with the Kinect V2 based system again and the ROM values were calculated. These procedures were carried out with all of the volunteer participants in three repetitions. In reliability for Kinect V2 based shoulder motion measurement system, we used the intraclass correlation coefficients (ICC), standard error of the measure (SEM), minimal detectable change (MDC). The validity test includes the 95% limits of agreement (LOA) and mean difference between the Kinect V2 based system and the both of the goniometer systems for measuring shoulder motions. The high ICC values show that the Kinect V2 based shoulder motion measurement system has very good intra-rater reliability for abduction, flexion, external rotation, internal rotation shoulder poses. For extension pose, it has good reliability result according to the ICC value. The validity analysis gives good results for all shoulder poses except internal rotation between Kinect V2 and clinical/digital goniometer. As a result, Kinect V2 based measurement system is a reliable and valid alternative telerehabilitation tool for shoulder motions.

Performance comparison of differential evolution techniques on optimization of feeding profile for an industrial scale baker's yeast fermentation process.

Differential evolution (DE) is one of the novel evolutionary optimization methods used for solving the problems that consist of nondifferentiable, nonlinear and multi-objective functions. In this presented work, the classical DE technique and its various versions, such as opposition based on differential evolution (ODE), adaptive differential evolution (ADE), adaptive opposition based on differential evolution (AODE) which is an advanced version of ODE, are presented to determine the optimal feeding flow profile of an industrial scale fed-batch baker's yeast fermentation process. The main objective in any fed-batch fermentation process optimization is both to maximize the amount of the biomass at the end of the process and to minimize the ethanol formation during the process. Four different cases regarding the initial condition of the fermentation process were considered so as to evaluate the performances of proposed algorithms. Besides, two strategies of mutation and crossover operators, which are the most popular in DE's applications, were utilized for performance comparison tests. The influence of initial seed value, initial condition of the process, and both of the mutation and crossover strategies have been investigated for all the different classic, opposition-based, self-adaptive and adaptive opposition-based mechanisms. To demonstrate the performance comparison of the of DE's techniques, the experimental data collected from the fermentor with volume of 100 m(3) are presented with the optimization results obtained by using all the interested DE techniques for the same initial conditions.

On-line evolutionary optimization of an industrial fed-batch yeast fermentation process.

This paper presents two genetic algorithms based on optimization methods to maximize biomass concentration, and to minimize ethanol formation. The objective function is maximized according to the values of feed flow rate, using genetic search approaches. Five case studies were carried out for different initial conditions, which strongly influence the optimal profiles of feed flow rate for the fermentation process. The ethanol and glucose disturbance effects were examined to stress the effectiveness of proposed approaches. The proposed genetic approaches were implemented for an industrial scale baker's yeast fermentor which produces Saccharomyces cerevisiae known as baker's yeast. The results show that optimal feed flow rate was obtained in a satisfactory and successful way for fed-batch fermentation process.

Nonlinear predictive control of a drying process using genetic algorithms.

A nonlinear predictive control technique is developed to determine the optimal drying profile for a drying process. A complete nonlinear model of the baker's yeast drying process is used for predicting the future control actions. To minimize the difference between the model predictions and the desired trajectory throughout finite horizon, an objective function is described. The optimization problem is solved using a genetic algorithm due to the successful overconventional optimization techniques in the applications of the complex optimization problems. The control scheme comprises a drying process, a nonlinear prediction model, an optimizer, and a genetic search block. The nonlinear predictive control method proposed in this paper is applied to the baker's yeast drying process. The results show significant enhancement of the manufacturing quality, considerable decrease of the energy consumption and drying time, obtained by the proposed nonlinear predictive control.