Ground Reaction Forces Predicted by Using Artificial Neural Network during Asymmetric Movements

최안렬,문정환,이재문 한국정밀공학회 2013 International Journal of Precision Engineering and Vol. No.

During the motion analysis, joint moments are calculated by the inverse dynamics method. The ground reaction forces are representative input data for an application of the inverse dynamics technique, and extracted from an installed force platform. However, when the vast majority of human body movement, continuous and wide spaced, is considered, usage of the fixed force platform on analyzing exercises has many limitations. Therefore, the purpose of this study is to suggest a method to predict the ground reaction forces which occur in complex planes during asymmetric movements. Thirteen healthy male subjects performed static posture, gait and asymmetric movements. The experimental equipment included six infrared cameras and two force platforms, and the artificial neural network was used to solve indeterminate problems occurring in a double support phase. The final 13 input variables from a variety of kinematic and kinetic data for the model were carried out by the Self Organizing Map-Genetic Algorithm General Regression Neural Network, and calculated for one side of ground reaction force from the ‘13-26-1’ of a multi-layer neural network and other one from a dynamic equation. As a result, the correlation coefficients between predicted and measured values were 0.88, 0.47, 0.99 and 0.19 N/kg, 0.25 N/kg, 0.61 N/kg of RMSE at the mediolateral, anterior-posterior, vertical axis, respectively. Especially, the highest prediction rate was shown at the vertical direction ground reaction force which has the biggest variations in motion and a small error at the anterior-posterior and lateral-medial axis compared with the measured value. The results of this study show that ground reaction forces can predict general human movements without force platforms, and we expect them to be used as basic information to interpret inverse dynamics.

Determination of Input Variables for the Development of a Gait Asymmetry Expert System in Patients with Idiopathic Scoliosis

최안렬,문정환,윤태선,박현준,서승우,양재혁,이소은,노민상,강태건 한국정밀공학회 2013 International Journal of Precision Engineering and Vol. No.

The purpose of this study was to select the appropriate input variables for the development of an expert system to analyze the gait asymmetry of patients with idiopathic scoliosis. Gait experiments were performed with 12 healthy female adolescents and 16 female adolescents with untreated adolescent idiopathic scoliosis. The experimental equipment included six infrared cameras and two ground reaction force platforms. By using a 3D human model, gait elements, kinematic and kinetic data were extracted. Self-organizing map and genetic algorithm were used for proper selection of input variables, and these methods were validated by using auto regression models, which were described in previous studies. Sixty gait variables based on a literature review were selected, and Self-organizing map was used to maintain the independency between the input variables, and the 39 independent retaining variables were chosen. Also, in order to identify the inputs exhibiting a significant relationship with the output, a genetic algorithm-general regression neural network was applied; and the frequency of the solution set was measured by genetic algorithm iteration. A stepwise method was applied based on the variables with high frequency, and final 11 input variables were selected. Furthermore, a back propagation artificial neural network with high accuracy 96.3(3.2)%, which can discriminate patients from the normal subjects, was developed with selected 11 input variables. Therefore, the results of this study can be used as input variables for the development of a gait asymmetry expert system.

Asymmetric loading of erector spinae muscles during sagittally symmetric lifting

최안렬,윤태선,이경석,민경기,황헌,이기영,오의철,문정환 대한기계학회 2009 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.23 No.1

Functional asymmetry is among the multitude of risk factors for low-back pain (LBP), the most common injury under general industrial and agricultural conditions. However, previous studies showed that normal healthy individuals exhibit some functional asymmetry, indicating that not all asymmetry causes LBP. Therefore, the threshold value that is able to discriminate between normal and pathological situations is used as critical information to predict LBP. As a preliminary study to find threshold, the purpose of this study is to quantify the magnitude of bilateral asymmetries of erector spinae muscle forces of a healthy group during sagittally symmetric lifting. Ten healthy male subjects with no history of back pathology participated in this study, which collected motion capture, force data, and electromyography signals from six infrared cameras (MCam2, Vicon), two force platforms (AMTI), and surface EMG (BME Korea). In order to quantify the magnitude of bilateral asymmetry in the trunk muscle forces, we used 3D linked segment and EMG-assisted modeling approaches, both of which were verified based on their recapitulation of previously-proposed models. The results indicated that each muscle force in the lumbar region exhibited asymmetry during the entire lifting process. In particular, the erector spinae muscle forces exhibited an approximate 24% difference between bilateral sites (p<0.05). The results of this study provided data from normal individuals by which to identify pathological situations and predict LBP incidence within general industrial and agricultural conditions.

비닐 천공 시스템 개발 – 칼날 형상이 천공 성능에 미치는 영향

홍성하,최안렬,이규승 경상대학교 농업생명과학연구원 2016 농업생명과학연구 Vol.50 No.5

본 연구에서 개발된 자동천공기는 콩의 재식밀도를 고려한 비닐 천공능력이 작업주행속도 0.18- 0.28m/s 조건에서 콩의 주간거리 0.20m, 0.25m, 0.30m에 대해 각각 320-500m2/h, 260-400m2/h, 210-330m2/h의 범위로 나타났다. 천공율은 칼날과 지면간 30mm 거리에서 비닐이 100% 천공되었으 며, 50mm 거리에서 원형칼날 16.7-25.2%, 사각칼날 33.0-42.3%, 육각칼날 54.5-100.0% 범위에서 천공되었다. 또한, 육각칼날 60°에서 비닐 절단면이 매끄럽고 부드러워 절단품질이 가장 우수하였다. In this study, performance of a developed automatic punching machine considering the planting density of soybeans was evaluated in the case of the operation speed of 0.18-0.28 m/s. The performance demonstrated a rate of 320-500 m2/h, 260-400 m2/h, and 210-330 m2/h for the 0.20 m, 0.25 m, and 0.30 m soybean planting density, respectively. One hundred percent punching capacity was confirmed in 30 mm distance between the ground and the blade. Additionally, in the 50 mm distance condition, the performance of round, square, and hexagonal blades were observed in the range of 16.7-25.2%, 33.0-42.3%, and 54.5-100.0%, respectively. Above all, the hexagonal blade with a 60° edge angle had the most superior cutting quality demonstrating a smooth and soft cutting plane of the plastic.

Structural design sensitivity analysis of an ultrasonically activated scalpel to improve contact pressure distribution

김태형,최안렬,최문택,문정환,김형건 대한기계학회 2018 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.32 No.11

Ultrasonically activated scalpels (UAS) have excellent hemostatic effects with minimal tissue damage while dissecting tissue. However, inhomogeneous contact pressure (CP) distribution at the sealing site can decrease the quality of sealing strength and cutting. In this study, we evaluated the contact mechanics of UAS using 3D finite element analysis (FEA) simulations, and examined the effects of structural design parameters on the contact mechanics (average CP, standard deviation of CP, maximum CP, and contact area) using experiment-based sensitivity analysis. The largest positive and negative response of the average CP and standard deviation of CP were 0.68-0.85 MPa and 0.81-0.44 MPa, respectively (r = 0.32 and r = -0.73, P < 0.05) when the handle length, jaw cave, and tissue pad height were increased. In conclusion, design parameters (tissue pad height, jaw cave height, jaw cave length, and handle length) of UAS demonstrating high correlation with average CP, standard deviation of CP, maximum CP, and contact area should be considered to attain evenly distributed CP for improved structural optimization of UAS.

Prediction of Cobb-angle for Monitoring System in Adolescent Girls with Idiopathic Scoliosis using Multiple Regression Analysis

서은지,최안렬,박현준,이동준,문정환,오승일 한국농업기계학회 2013 바이오시스템공학 Vol.38 No.1

Purpose: The purpose of this study was to select standing posture parameters that have a significant difference according to the severity of spinal deformity, and to develop a novel Cobb angle prediction model for adolescent girls with idiopathic scoliosis. Methods: Five normal adolescents girls with no history of musculoskeletal disorders, 13 mild scoliosis patients (Cobb angle: 10°-25°), and 14 severe scoliosis patients (Cobb angle: 25°-50°) participated in this study. Six infrared cameras (VICON) were used to acquire data and 35 standing parameters of scoliosis patients were extracted from previous studies. Using the ANOVA and post-hoc test, parameters that had significant differences were extracted. In addition, these standing posture parameters were utilized to develop a Cobb-angle prediction model through multiple regression analysis. Results:Twenty two of the parameters showed differences between at least two of the three groups and these parameters were used to develop the multi-linear regression model. This model showed a good agreement (R2 = 0.92) between the predicted and the measured Cobb angle. Also, a blind study was performed using 5 random datasets that had not been used in the model and the errors were approximately 3.2 ± 1.8. Conclusions: In this study, we demonstrated the possibility of clinically predicting the Cobb angle using a non-invasive technique. Also, monitoring changes in patients with a progressive disease,such as scoliosis, will make possible to have determine the appropriate treatment and rehabilitation strategies without the need for radiation exposure.

The comparison of joint kinematic error using the absolute and relative coordinate systems for human gait

임용훈,최안렬,민경기,금동혁,최창현,문정환,이상식 대한기계학회 2009 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.23 No.1

Minimizing artifacts from skin movement is vital for acquiring more accurate kinematic data in human movement analysis. There are several stages that cause skin movement artifacts and these stages depend on the selection of the reference system, the error reduction method and the coordinate system in clinical gait analysis. Due to residual errors, which are applied to the Euler and Bryant angle methods in each stage, significant cumulative errors are generated in the motion analysis procedure. Thus, there is currently a great deal of research focusing on reducing kinematic errors through error reduction methods and kinematic error estimations in relation to the reference system. However, there have been no studies that have systematically examined the effects of the selected coordinate system on the estimation of kinematic errors, because most of these previous studies have been mainly concerned with the analysis of human movement using only the human models that are provided in the commercial 3D motion capture systems. Therefore, we have estimated the differences between the results of human movement analyses using an absolute coordinate system and a relative coordinate system during a gait, in order to establish which system provides a more accurate kinematic analysis at the ankle joint. Six normal adult subjects with no neurological or orthopedic conditions, lower extremity injuries, or recent history of lower extremity surgery were used in this study. The analysis was conducted at a walking speed of 1.35m/s. For the clinical estimation, we used a cardinal plane based on the segmental reference system and the differences were plotted on the planes. From this analysis, when a relative coordinate system was in the gait analysis, the average kinematic error occurring during the gait was determined to be 13.58mm, which was significantly higher than the error generated with an absolute coordinate system. Therefore, although the relative coordinate system can also be used to calculate the ankle joint center during the clinical gait analysis, the absolute coordinate system should be employed in order to obtain more accurate joint kinematic data. In addition, the results from this study can be used as a basis to select an appropriate coordinate system with regards to the diagnostic accuracy level required for various kinds of gait disorders.

Endurance Time Prediction of Biceps Brachii Muscle Using Dimitrov Spectral Index of Surface Electromyogram During Isotonic Contractions

이기영,이상식,최안렬,최창현,문정환 한국정밀공학회 2011 International Journal of Precision Engineering and Vol. No.

A number of studies have examined the validity of using spectral parameters, such as median frequency (Fmed) and Dimitrov spectral index of muscle fatigue (FInsm5) from the surface EMG signal during dynamic exercise, to assess muscle fatigue. Despite these studies, the ability to accurately predict endurance capacity using these spectral parameters during repetitive dynamic contractions is limited. The main purpose of this study was to examine the potential of using the incremental time,defined as the time when the Dimitrov spectral index increases to a certain value relative to the initial value, to predict the endurance time (Tend), which was determined when the subject became exhausted and could no longer follow the fixed contraction cycle. Ten healthy subjects performed five sets of voluntary isotonic contractions until they could only produce 10% and 20% of their maximal voluntary contraction level (MVC). The Tend for all subjects were within the following ranges: 157±62 s at 10% MVC; 75±31 s at 20% MVC. Spectral parameters such as median frequency and Dimitrov spectral index were extracted from every contraction segment and estimated using linear regressive analysis at every contraction. The initial slope of both spectral parameters and the incremental time of the Dimitrov spectral index were compared as a predictor of endurance time. Significant correlations were found: 1) between Tend and contraction level (p<0.05) and 2) between Tend and the incremental time when the Dimitrov spectral index was above 130% of the increment with respect to the initial value at 20%MVC (p<0.01). In conclusion, the incremental time of the Dimitrov spectral index could be used to describe the changes in the spectral content of the sEMG signal and could be used as a good predictor of endurance time in comparison to the initial slope of the median frequency.

Evaluation of Robust Classifier Algorithm for Tissue Classification under Various Noise Levels

윤수현,신기영,최안렬,문정환 한국전자통신연구원 2017 ETRI Journal Vol.39 No.1

Ultrasonic surgical devices are routinely used for surgical procedures. The incision and coagulation of tissue generate a temperature of 40 °C–150 °C and depend on the controllable output power level of the surgical device. Recently, research on the classification of grasped tissues to automatically control the power level was published. However, this research did not consider the specific characteristics of the surgical device, tissue denaturalization, and so on. Therefore, this research proposes a robust algorithm that simulates noise to resemble real situations and classifies tissue using conventional classifier algorithms. In this research, the bioimpedance spectrum for six tissues (liver, large intestine, kidney, lung, muscle, and fat) is measured, and five classifier algorithms are used. A signal-to-noise ratio of additive white Gaussian noise diversifies the testing sets, and as a result, each classifier’s performance exhibits a difference. The k-nearest neighbors algorithm shows the highest classification rate of 92.09% (p < 0.01) and a standard deviation of 1.92%, which confirms high reproducibility.

A Comparison of the Effects of Worker-Related Variables on Process Efficiency in a Manufacturing System Simulation

이동준,박현준,최안렬,문정환 한국농업기계학회 2013 바이오시스템공학 Vol.38 No.1

Purpose: The goal of this study was to build an accurate digital factory that evaluates the performance of a factory using computer simulation. To achieve this goal, we evaluated the effect of worker-related variables on production in a simulation model using comparative analysis of two cases. Methods: The overall work process and worker-related variables were determined and used to build a simulation model. Siemens PLM Software's Plant Simulation was used to build a simulation model. Also, two simulation models were built, where the only difference was the use of the worker-related variable, and the total daily production analyzed and compared in terms of the individual process. Additionally, worker efficiency was evaluated based on worker analysis. Results: When the daily production of the two models were compared, a 0.16% error rate was observed for the model where the worker-related variables were applied and error rate was approximately 5.35%for the model where the worker-related variables were not applied. In addition, the production in the individual processes showed lower error rate in the model that included the worker-related variables than the model where the worker-related variables were not used. Also, among the total of 22 workers, only three workers satisfied the IFRS (International Financial Reporting Standards) suggested worker capacity rate (90%). Conclusions: In the daily total production and individual process production, the model that included the worker-related variables produced results that were closer to the real production values. This result indicates the importance of worker elements as input variables, in regards to building accurate simulation models. Also, as suggested in this study, the model that included the worker-related variables can be utilized to analyze in more detail actual production. The results from this study are expected to be utilized to improve the work process and worker efficiency.