Hanbyul Kim

Unconstrained detection of freezing of Gait in Parkinson's disease patients using smartphone

Freezing of gait (FOG) is a common motor impairment to suffer an inability to walk, experienced by Parkinsons disease (PD) patients. FOG interferes with daily activities and increases fall risk, which can cause severe health problems. We propose a novel smartphone-based system to detect FOG symptoms in an unconstrained way. The feasibility of single device to sense gait characteristic was tested on the various body positions such as ankle, trouser pocket, waist and chest pocket. Using measured data from accelerometer and gyroscope in the smartphone, machine learning algorithm was applied to classify freezing episodes from normal walking. The performance of AdaBoost.M1 classifier showed the best sensitivity of 86% at the waist, 84% and 81% in the trouser pocket and at the ankle respectively, which is comparable to the results of previous studies.

Correction: Automatic Classification of Tremor Severity in Parkinson’s Disease Using a Wearable Device. Sensors 2017, 17, 2067

Hyoseon Jeon 1, Woongwoo Lee 2 ID , Hyeyoung Park 2, Hong Ji Lee 1, Sang Kyong Kim 1, Han Byul Kim 1, Beomseok Jeon 2 and Kwang Suk Park 3,* 1 The Interdisciplinary Program for Bioengineering, Seoul National University, Seoul 03080, Korea; nulpurunhs@bmsil.snu.ac.kr (H.J.); hongjidan@bmsil.snu.ac.kr (H.J.L.); skkim@bmsil.snu.ac.kr (S.K.K.); hahanbyul@bmsil.snu.ac.kr (H.B.K.) 2 Department of Neurology and Movement Disorder Center, Seoul National University Hospital, Seoul 03080, Korea; w2pooh@daum.net (W.L.); 0907bluelove@naver.com (H.P.); brain@snu.ac.kr (B.J.) 3 Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul 03080, Korea * Correspondence: pks@bmsil.snu.ac.kr; Tel.: +82-2-2072-3135; Fax: +82-2-3676-2821

Automatic Classification of Tremor Severity in Parkinson’s Disease Using a Wearable Device

Although there is clinical demand for new technology that can accurately measure Parkinsonian tremors, automatic scoring of Parkinsonian tremors using machine-learning approaches has not yet been employed. This study aims to fill this gap by proposing machine-learning algorithms as a way to predict the Unified Parkinson’s Disease Rating Scale (UPDRS), which are similar to how neurologists rate scores in actual clinical practice. In this study, the tremor signals of 85 patients with Parkinson’s disease (PD) were measured using a wrist-watch-type wearable device consisting of an accelerometer and a gyroscope. The displacement and angle signals were calculated from the measured acceleration and angular velocity, and the acceleration, angular velocity, displacement, and angle signals were used for analysis. Nineteen features were extracted from each signal, and the pairwise correlation strategy was used to reduce the number of feature dimensions. With the selected features, a decision tree (DT), support vector machine (SVM), discriminant analysis (DA), random forest (RF), and k-nearest-neighbor (kNN) algorithm were explored for automatic scoring of the Parkinsonian tremor severity. The performance of the employed classifiers was analyzed using accuracy, recall, and precision, and compared to other findings in similar studies. Finally, the limitations and plans for further study are discussed.

Evaluation of Electrohysterogram Feature Extraction to Classify the Preterm and Term Delivery Groups

The prediction of preterm delivery is very important for investigating risk factors for preterm birth and initiating risk specific treatment but still remains a challenge for obstetricians. Based on the fact that the characteristics of unterine muscle activities change as pregnancy progresses, many researchers have tried to use noninavise Electrohysterogram (EHG) for separating the preterm and term delivery. To investigate novel and useful features to classify the preterm and term delivery groups, we randomly selected 40 records from Physionet EHG database. The records were classified into four groups depending on the time of recording (before or after the 26th week of gestation) and the length of gestation (term delivery: ≥ 37 weeks of pregnancy duration or preterm delivery: < 37 weeks of pregnancy duration). 40 records were composed of 10 records from each group. 26 features including 18 time domain features and 8 frequency domain features were applied to each record to find out the difference in characteristics of the uterine muscle activities between term and preterm delivery. As a result, Frequency Ratio (FR) and Mean Absolute Value Slope1 (MAVSLP1) indicated a significant difference between term and preterm delivery records recorded before 26th week. And Willison amplitude (WAMP), Slope Sign Change (SSC), and 3rd Spectral Moments (SM3) had significant difference between preterm and term delivery data recorded during the later period of gestation. Also, Slope Sign Change (SSC) and Frequency Ratio (FR) showed a significant difference between all term and all preterm delivery records.

Preliminary Study for Developed Foot Plantar Surface Temperature Monitoring System by Reducing Pressure Effect

The diabetic foot is one of the major complications in diabetic patients. Many studies revealed that monitoring temperature differences of the corresponding points on the foot plantar surface is important to prevent the foot ulceration. However, even though there are many wearable devices developed for monitoring plantar surface temperature, no studies have investigated how the person’s pressure can effect on the temperature sensors while monitoring the plantar temperature when the people stand on the insole. This pressure effect can change the monitoring result which will produce the wrong diagnosis. In this study, we propose two methods; each is corresponding to estimate the standing habit of the person, and to correct the monitoring result which is affected by the pressure. Although it cannot correct the error in certain situation and it is limited to steady state, these two methods were able to correct the error caused by the pressure on the sensor.