• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.4
• /
• pp.145-154
• /
• 2008

In this paper, we propose the pet robot control system using hand gesture recognition in image sequences acquired from a camera affixed to the pet robot. The proposed system consists of 4 steps; hand detection, feature extraction, gesture recognition and robot control. The hand region is first detected from the input images using the skin color model in HSI color space and connected component analysis. Next, the hand shape and motion features from the image sequences are extracted. Then we consider the hand shape for classification of meaning gestures. Thereafter the hand gesture is recognized by using HMMs (hidden markov models) which have the input as the quantized symbol sequence by the hand motion. Finally the pet robot is controlled by a order corresponding to the recognized hand gesture. We defined four commands of sit down, stand up, lie flat and shake hands for control of pet robot. And we show that user is able to control of pet robot through proposed system in the experiment.

• Archives of Reconstructive Microsurgery
• /
• v.17 no.2
• /
• pp.108-114
• /
• 2008

Purpose: There are many controversies concerning therapeutic guidelines for the treatment of Kienb$\ddot{o}$ck's disease. The purpose of this study is to evaluate the clinical and radiological result of lunate replacement by vascularized os pisiform transfer in advanced Kienb$\ddot{o}$ck's disease. Materials & Methods: There were two men and three women. The mean age was 55 years, ranging from 41 to 70. According to Lichtman's classification, three cases were stage IIIb and two cases were stage IV. Results: At the period of follow up, pain during motion was markedly diminished in all patients, the arc of motion ranged on average from 49 degrees of flexion to 53 degrees of extension and the grip power of the affected hand reached on average 83% compared with the contralateral side. Clinical results assessed by DASH and modified Mayo score showed 8 and 90. On plain X-rays, carpal height ratio and radioscaphoid angle were not changed postoperatively. Conclusion: Lunate excision and vascularized os pisiform transfer is a reliable alternative method for the treatment of advanced Kienb$\ddot{o}$ck's disease.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.129-136
• /
• 2020

Recognizing finger movements have been used as a intuitive way of human-computer interaction. In this study, we implement an wearable device for finger motion recognition and evaluate the accuracy of several ML (Machine learning) techniques. Not only HMM (Hidden markov model) and DTW (Dynamic time warping) techniques that have been traditionally used as time series data analysis, but also NN (Neural network) technique are applied to compare and analyze the accuracy of each technique. In order to minimize the computational requirement, we also apply the pre-processing to each ML techniques. Our extensive evaluations demonstrate that the NN-based gesture recognition system achieves 99.1% recognition accuracy while the HMM and DTW achieve 96.6% and 95.9% recognition accuracy, respectively.

• Journal of Yeungnam Medical Science
• /
• v.35 no.1
• /
• pp.130-134
• /
• 2018

Heterotopic ossification (HO) around the hip joint is not uncommon following neurological injury. Often, surgical treatment is performed in patients with restricted motion and/or refractory pain due to grade III or IV HO according to Brooker classification. The major complication that occurs as a result of surgical HO removal is perioperative bleeding due to hyper-vascularization of the lesion. Here, we report a case of preoperative embolization in a 51-year-old male patient presenting with restricted bilateral hip range of motion (ROM) due to HO following a spinal cord injury. In the right hip without preoperative arterial embolization, massive bleeding occurred during surgical removal of HO. Thus, the patient received a transfusion postoperatively due to decreased serum hemoglobin levels. For surgery of the left hip, preoperative embolization of the arteries supplying HO was performed. Surgical treatment was completed without bleeding complications, and the patient recovered without a postoperative transfusion. This case highlights that, while completing surgical removal for ROM improvements, orthopedic surgeons should consider preoperative arterial embolization in patients with hip HO.

• Journal of Korean Clinical Nursing Research
• /
• v.25 no.1
• /
• pp.55-66
• /
• 2019

Purpose: This study was done to assess development and postnatal care interventions in postnatal care intervention records for maternity ward nurses in tertiary hospitals and women's hospitals in South Korea. Methods: This mixed-method research was a Time-Motion (TM) study. Data were collected through external observation of 12 nurses in 4 wards over 24 hours. Mann-Whitney U test and independent t-test were employed for the analysis of frequency and provision time of direct/indirect care activity. $x^2$ (Fisher's exact test) was utilized to determine the difference in frequency between two groups. IBM SPSS 22.0 statistical program was employed for calculation. All statistical significance levels were at ${\alpha}=.05$. Results: According to the KPCS-1 (Korean Patient Classification System-1), women's hospitals are group 3 and tertiary hospitals, group 4. With respect to time difference in direct care, tertiary hospitals showed 791 minutes and women's hospitals, 399 a difference of 392 minutes. For time difference in indirect care, women's hospitals had 2,415 minutes while tertiary hospitals, 2,080, a difference of 335 minutes for women's hospitals. No difference was found in the average total care workload between the two institutions. Individual time also showed no difference (p>.05). Conclusion: High-risk maternal care strength in tertiary hospitals and breast-feeding strength in women's hospitals need to be benchmarked with each other.

• Clinics in Shoulder and Elbow
• /
• v.21 no.4
• /
• pp.220-226
• /
• 2018

Background: This study introduces a surgical technique with good clinical outcome useful in the treatment of osteoporotic displaced 3- or 4-part proximal humeral fractures. Methods: From May 2014 to February 2016, 16 patients with displaced 3- or 4-part proximal humeral fractures were treated by application of a locking plate with an endosteal strut allograft via a deltoid splitting approach with a minimum follow-up of 12 months. The allograft was inserted through a fractured gap of the greater tuberosity to support the humeral head and then fixed by a locking plate with meticulous soft tissue dissection to protect the axillary nerve. Surgical outcomes were evaluated by the American Shoulder and Elbow Surgeons (ASES) and visual analogue scale (VAS) scores, radiological imaging, and clinical examination. Fixation failure on radiographs was defined as a >$5^{\circ}$ loss of neck shaft angle (NSA) compared to that on an immediate postoperative radiograph. Avascular necrosis (AVN) of the humeral head was also evaluated. Results: In all cases, complete union was achieved. The ASES and VAS scores were improved to $85.4{\pm}2.1$ and $3.2{\pm}1.3$, respectively. Twelve patients (75.0%) had greater than a $5^{\circ}$ change in NSA; the average NSA change was $3.8^{\circ}$. Five patients (31.3%) had unsatisfactory ranges of motion exhibiting a <$100^{\circ}$ active forward flexion. No axillary nerve injuries or AVN were observed at the last follow-up. One patient was converted to reverse total arthroplasty due to severe pain and functional deficit. Conclusions: Minimally invasive fixation via a locking compression plate and an endosteal fibula strut allograft in Neer classification 3-or 4-part fractures with severe osteoporosis in elderly patients can achieve good clinical results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Clinics in Shoulder and Elbow
• /
• v.26 no.4
• /
• pp.373-379
• /
• 2023

Background: The purpose of this study was to determine the association between smoking and clinical outcomes of hook plate fixation for acute acromioclavicular (AC) joint injuries. Methods: This study retrospectively investigated 82 patients who underwent hook plate fixation for acute AC joint dislocation between March 2014 to June 2022. The patients were grouped by smoking status, with 49 in group N (nonsmokers) and 33 in group S (smokers). Functional scores and active range of motion were compared among the groups at the 1-year follow-up. Coracoclavicular distance (CCD) was measured, and difference with the uninjured side was compared at initial injury and 6 months after implant removal. Results: No significant differences were observed between the two groups in demographic factors such as age and sex, as well as parameters related to initial injury status, which included time from injury to surgery, the preoperative CCD difference value, and the Rockwood classification. However, the postoperative CCD difference was significantly higher in group S (3.1±2.6 mm) compared to group N (1.7±2.4 mm). Multivariate regression analysis indicated that smoking and the preoperative CCD difference independently contributed to an increase in the postoperative CCD difference. Despite the radiographic differences, the postoperative clinical outcome scores and active range of motion measurements were comparable between the groups. Conclusions: Smoking had a detrimental impact on ligament healing after hook plate fixation for acute AC joint dislocations. This finding emphasizes the importance of smoking cessation to optimize reduction maintenance after AC joint injury. Level of evidence: III.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.7
• /
• pp.508-514
• /
• 2018

An electroencephalogram (EEG) evaluates the electrical activity generated by brain cell interactions that occur during brain activity, and an EEG can evaluate the brain activity caused by hand movement. In this study, a 16-channel EEG was used to measure the EEG generated before and after hand movement. The measured data can be classified as a supervised learning model, a support vector machine (SVM). To shorten the learning time of the SVM, a feature extraction and vector dimension reduction by filtering is proposed that minimizes motion-related information loss and compresses EEG information. The classification results showed an average of 72.7% accuracy between the sitting position and the hand movement at the electrodes of the frontal lobe.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.299-308
• /
• 2014

Various literatures related computing of information processing have been recently shown the researches inspired from the remarkably excellent human capabilities which recognize and categorize very complex visual patterns such as body motions and facial expressions. Applied from human's outstanding ability of perception, the classification function of visual sequences without context information is specially crucial task for computer vision to understand both the coding and the retrieval of spatio-temporal patterns. This paper presents a biological process based action recognition model of computer vision, which is inspired from visual information processing of human brain for action recognition of visual sequences. Proposed model employs the structure of neural fields of bio-inspired visual perception on detecting motion sequences and discriminating visual patterns in human brain. Experimental results show that proposed recognition model takes not only into account several biological properties of visual information processing, but also is tolerant of time-warping. Furthermore, the model allows robust temporal evolution of classification compared to researches of action recognition. Presented model contributes to implement bio-inspired visual processing system such as intelligent robot agent, etc.