Jung-Ja Kim

3D motion matching algorithm using signature feature descriptor

This paper introduces a basic frame for rehabilitation motion practice system which detects 3D motion trajectory with the Microsoft Kinect (MSK) sensor system and proposes a cost-effective 3D motion matching algorithm. The rehabilitation motion practice system displays a reference 3D motion in the database system that the player (patient) tries to follow. The player’s motion is traced by the MSK sensor system and then compared with the reference motion to evaluate how well the player follows the reference motion. In this system, 3D motion matching algorithm is a key feature for accurate evaluation for player’s performance. Even though similarity measurement of 3D trajectories is one of the most important tasks in 3D motion analysis, existing methods are still limited. Recent researches focus on the full length 3D trajectory data set. However, it is not true that every point on the trajectory plays the same role and has the same meaning. In this situation, we developed a new cost-effective method that only uses the less number of features called ‘signature’ which is a flexible descriptor computed from the region of ‘elbow points’. Therefore, our proposed method runs faster than other methods which use the full length trajectory information. The similarity of trajectories is measured based on the signature using an alignment method such as dynamic time warping (DTW), continuous dynamic time warping (CDTW) or longest common sub-sequence (LCSS) method. In the experimental studies, we applied the MSK sensor system to detect, trace and match the 3D motion of human body. This application was assumed as a system for guiding a rehabilitation practice which can evaluate how well the motion practice was performed based on comparison of the patient’s practice motion traced by the MSK system with the pre-defined reference motion in a database. In order to evaluate the accuracy of our 3D motion matching algorithm, we compared our method with two other methods using Australian sign word dataset. As a result, our matching algorithm outperforms in matching 3D motion, and it can be exploited for a base framework for various 3D motion-based applications at low cost with high accuracy.

Controlling multi-class error rates for MLP classifier by bias adjustment based on penalty matrix

Multilayer Perceptron (MLP) neural network classifiers have been successfully applied to solve many classification problems. By learning process they reduce the cost function, generally defined by the total sum of errors (TSE) caused by each pattern. The classification result from this type of learning method can be biased to the number of patterns in the classes and does not reflect the importance of the class. However, pattern classification often encounters the problem of different ratio on the pattern numbers and risk ratio between classes. In this paper, a method for effectively controlling the classification rate by adjusting the bias of the output neurons in the neural network based on the penalty matrix is presented. It first trains the multilayer neural network with linear output nodes to find the solution with or without duplication of the patterns in the minor class or important class. Then, the biases of the output nodes are adjusted based on Bayesian decision concept in order to make the classification rate for a certain class to a desired level. Experimental results of this proposed method showed that it is very effective to control the trained network to produce the desired level of classification rate for a certain class with a possible degradation of classification rate for other classes. In the first experiment, the correction rate for Dirtiness fault was changed from 18% to 65.9% as desired of increasing the correction rate for Dirtiness fault. In the second experiment, the error rate of classifying from class Other Faults to class Pastry Fault was decreased from 7.6% to 6.9% when we modified the penalty matrix to archive a lower error rate of classifying from class Other Faults to class Pastry Fault. The proposed method is very useful for the applications that misclassification risk for a specific class is more critical such as medical diagnosis and military decision.

A Cost Effective Method for Matching the 3D Motion Trajectories

3D trajectory data have progressively become common since more devices which are possible to acquire motion data were produced. These technology advancements promote studies of motion analysis based on the 3D trajectory data. Even though similarity measurement of trajectories is one of the most important tasks in 3D motion analysis, existing methods are still limited. Recent researches focus on the full length 3D trajectory data set. However, it is not true that every point on the trajectory plays the same role and has the same meaning. In this situation, we developed a new cost effective method that uses the feature ‘signature’ which is a flexible descriptor computed only from the region of ‘elbow points’. Therefore, our proposed method runs faster than other methods which use the full length trajectory information. The similarity of trajectories is measured based on the signature using an alignment method such as dynamic time warping (DTW), continuous dynamic time warping (CDTW) or longest common subsequence (LCSS) method. In the experimental studies, we compared our method with two other methods using Australian sign word dataset to demonstrate the effectiveness of our algorithm.

Evaluation for Biomechanical Effects of Metatarsal Pad and Insole on Gait

The purpose of this study was to evaluate the effects of metatarsal pad (MP) compared with barefoot and MP with using different insoles on gait. 15 healthy females who had no history of injury in the lower extremity with an average age of 22.7 year(SD=1.35), height of 160 cm(SD=3.4), weight of 48.8 kg(SD=5.52) and average foot size of 232.5 mm(SD=6.8) participated in this study as the subjects. The subjects walked on a treadmill under four different experimental conditions: 1) walking with barefoot, 2) walking wearing MP 3) walking wearing a soft insole with MP(SIMP), 4) walking wearing a rigid insole with MP(HIMP). During walking, foot pressure data such as force, contacting area, peak pressure, and mean pressure was collected using Pedar-X System(Novel Gmbh, Germany) and EMG activity of lower limb muscles such as tibialis anterior(TA), lateral gastrocnemius(LG), rectus femoris(RF), and musculus biceps femoris(MBF) was gathered using Delsys EMG Work System(Delsys, USA). Collected data was then analyzed using paired t-test in order to investigate the effects of each of experimental conditions. As a result of the analysis, when MP and HIMP were equipped, overall contacting area was increased while the force, peak pressure and the mean pressure were decreased. Especially, when the SIMP was equipped, every data were significantly decreased. In case of EMG, wearing MP, SIMP and HIMP made three muscles(TA, LG, RF)s activity decrease. A result of the analysis will be able to apply for manufacturing functional shoes, diabetes shoes, senior shoes and lower extremity orthosis. Significance of the study due to a metatarsal pad and the insole is to analyze the changes in muscle strength.

Effects of custom-made insoles on idiopathic pes cavus foot during walking

From a subject group of pes cavus, the purpose of this study was to evaluate the biomechanical characteristics of lower limbs, based on plantar foot pressure and electromyography (EMG) activities, by the effects on two kind of custom-made insoles. Ten individuals among thirty females with a clinical diagnosis of idiopathic pes cavus (mean age (SD): 22.3 (0.08) years) were selected for the study. The plantar foot pressure data and EMG activities of four lower limb muscles were collected, when subjects walked on a treadmill, under three different experimental conditions. The plantar foot pressure data was analyzed, after the bilateral foot was divided into three areas of masks and into four sections of stance phase, to compare plantar foot pressure. The EMG activities were analyzed for integrated EMG (IEMG) value. The results show that plantar foot pressure concentrated in particular parts is decreased by custom-made insoles. In the case of EMG, all the muscle activities decreased significantly. The custom-made insoles dispersed pressure concentrated by the higher medial longitudinal arch and improved the efficient use of muscles. In particular, the extension structure in the forefoot of custom-made insoles was more efficient for pes cavus. Therefore, it could help patients to walk, by offering support to prevent the disease of pes cavus deformity, and to relieve the burden and fatigue in the lower limbs on gait.

Study on Datamining Techinique for Foot Disease Prediction

Datamining is a method to focus on important and meaningful knowledge in large data. Decision tree, one of typical technique in datamining, is process to predict a couple of subgroup from object group by observing relation. The purpose of the study was to find out significant knowledge between two complex disease and symptoms in clinical data of the Foot clinic by decision tree. The first medical examination clinical data of 400 patients diagnosed with complex disease were used for analysis. A dependent variable was composed of four complex disease groups. Independent variables were selected with 14 variables closely related to disease. After object data were divided into training data and test data, C5.0 algorithm was applied for analysis. In conclusion, 13 diagnosis rules were created and major symptom information was verified. On the basis of this study, other decision tree algorithms will be applied to develop additional model and perform comparison analysis for producing an ideal model from now on.

Real-time Sitting Posture Monitoring System for Functional Scoliosis Patients

In recent years, with the increase in sitting time, real-time posture monitoring system is needed. We developed sitting posture monitoring system with accelerometer to evaluate postural balance. Unstable structure of the system was designed to assess asymmetrical balance caused by habitual sitting position. Postural patterns of normal group and patients with functional scoliosis group were analyzed. Consequently, inclination angle of scoliosis group were tilted to the posterior and left side. From these results, we concluded that real-time sitting posture monitoring system can be utilized to measure asymmetrical balance of patients and provide accurate diagnosis as well as treatment for individuals.

Classification Prediction of the Foot Disease Pattern Using Decision Tree Model

Datamining is used to find out desired important and meaningful knowledge in large scale data. The decision tree in classification algorithms has been applied to categorical attributes and numeric attributes in different domains. The purpose of study was to acquire significant information between singular disease groups and biomechanical parameters related with symptoms by developing prediction model. Sample data of 90 patient’s records diagnosed with a singular disease was selected for analysis, in total 2418 data. A dependent variable was composed of 9 singular disease groups. 18 of 32 independent variables closely related to disease were selected and optimized. After object data was divided into training data and test data, C5.0 algorithm was applied for analysis. In conclusion, 10 diagnosis rules were created and major symptom information was verified. On the basis of the study, additional analysis with utilizing other datamining methods will be performed to improve accuracy from now on.

Correlation Analysis between Idiopathic Scoliosis and Pelvic Asymmetry Using Sitting Posture Measurement System

The effects of pelvic asymmetry and idiopathic scoliosis on postural balance sitting were studied by measuring inclination angle and electromyography. Subjects were classified into a control group, pelvic asymmetry group, scoliosis group, and scoliosis with pelvic asymmetry and then performed anterior, posterior, and left-right pelvic tilting while sitting on the sitting posture measurement system for 5 seconds to assess their postural balance. Inclination and obliquity angles between the groups were measured by an accelerometer located on the system. Surface electrodes were attached to the erector spinae muscles of each participant. Inclination and obliquity angles increased more symmetrically in participants with both pelvic asymmetry and scoliosis than with pelvic asymmetry or scoliosis alone. Muscle contraction patterns of erector spinae muscles may be influenced by spine curve type and region of idiopathic scoliosis. Asymmetrical muscle activities were observed on the convex side of scoliotic patients and these muscle activity patterns were changed by the pelvic asymmetry. From these results, sitting posture measurement system may be utilized to assess the effects of asymmetrical postural balance and muscle activity caused by pelvic asymmetry and scoliosis on the physical activity of adolescent patients in their daily lives.

Evaluation of Custom-Made Insoles on Pes Cavus During Walking

From a subject group of pes cavus, the purpose of this study was to evaluate the biomechanical characteristics of lower limbs, based on plantar foot pressure and electromyography (EMG) activities, by the effects on two kind of custom-made insoles. Ten individuals among thirty females with a clinical diagnosis of idiopathic pes cavus were selected for the study. Method: The plantar foot pressure data and EMG activities of four lower limb muscles were collected, when subjects walked on a treadmill, under three different experimental conditions. The plantar foot pressure data was analyzed, after the bilateral foot was divided into three areas of masks, to compare plantar foot pressure. The EMG activities were analyzed for integrated EMG (IEMG) value. The results show that plantar foot pressure concentrated in particular parts is decreased by custom-made insoles. In the case of EMG, all the muscle activities de-creased significantly. Thus, the result of this study can be applied for designing functional insoles and lower extremity orthoses for individuals with pes cavus.