• Journal of Internet Computing and Services
• /
• v.12 no.6
• /
• pp.83-94
• /
• 2011

Main researching issue in affective computing is to give a machine the ability to recognize the emotion of a person and to react it properly. Efforts in that direction have mainly focused on facial and oral cues to get emotions. Postures have been recently considered as well. This paper aims to discriminate emotions posture by identifying and measuring the saliency of posture features that play a role in affective expression. To do so, affective postures from human subjects are first collected using a motion capture system, then emotional features in posture are described with spatial ones. Through standard statistical techniques, we verified that there is a statistically significant correlation between the emotion intended by the acting subjects, and the emotion perceived by the observers. Discriminant Analysis are used to build affective posture predictive models and to measure the saliency of the proposed set of posture features in discriminating between 6 basic emotional states. The evaluation of proposed features and models are performed using a correlation between actor-observer's postures set. Quantitative experimental results show that proposed set of features discriminates well between emotions, and also that built predictive models perform well.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.6
• /
• pp.117-125
• /
• 2015

In the modern age, it is important for people to maintain a good sitting posture because they spend long hours sitting. Posture correction treatment requires a great deal of time and expenses with continuous observation by a specialist. Therefore, there is a need for a system with which users can judge and correct their postures on their own. In this study, we collected users' postures and judged whether they are normal or abnormal. To obtain a user's posture, we propose a four-joint motion capture system that uses inertial sensors. The system collects the subject's postures, and features are extracted from the collected data to build a database. The data in the DB are classified into normal and abnormal postures after posture learning using the K-means clustering algorithm. An experiment was performed to classify the posture from the joints' rotation angles and positions; the normal posture judgment reached a success rate of 99.79%. This result suggests that the features of the four joints can be used to judge and help correct a user's posture through application to a spinal disease prevention system in the future.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.29 no.3
• /
• pp.375-382
• /
• 2019

Objectives: This study was to examine the features of work and posture analysis outputs in assessment of exposure to musculoskeletal disorder (MSD) risk factors in general hospital nurses. Methods: Work and posture analyses were carried out using observational approaches for nurses at general hospitals across Korea. With development of a taxonomy for assessing exposure to MSD risk factors, nursing tasks were documented in frequency (%time) for 8 hours a day in work analyses. Rapid Entire Body Assessment (REBA) scores were obtained for mode and maximum risk levels, respectively, during posture analyses. Results: A total of 27 nurses were observed while conducting 7 nursing tasks at 6 general hospitals. For both the work analyses and posture analyses, the taxonomy was developed and used. In the work analyses, 'Video display terminal task' and 'Nursing examination/ treatment' were the highest as 25%time for 8 hours a day, followed by 'Patient care' and 'Room rounding' as 13%time in order. In the posture analyses, the mode REBA scores were 2 or less for all nursing tasks while the maximum REBA scores were 7 for upper limbs at 'Room rounding' and 6 for trunk/neck/legs at 'Patient care'. Conclusions: The results showed the study nurses are occasionally at a risk for MSD, a medium level as designated in the REBA risk level, suggesting that it is important to control awkward posture at the nursing tasks such as 'Room rounding' and 'Patient care', in priority, for preventing MSD in the hospital sector including the study general hospitals.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.271-274
• /
• 2006

This paper deals with a similarity decision method between the shape of hand-postures and their structures to improve performance of the vision-based hand-posture recognition system. Hand-posture recognition by vision sensors has difficulties since the human hand is an object with high degrees of freedom, and hence grabbed images present complex self-occlusion effects and, even for one hand-posture, various appearances according to viewing directions. Therefore many approaches limit the relative angle between cameras and hands or use multiple cameras. The former approach, however, restricts user's operation area. The latter requires additional considerations on the way of merging the results from each camera image to get the final recognition result. To recognize hand-postures, we use both of appearance and structural features and decide the similarity between the two types of features by learning.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.39-49
• /
• 2006

This paper proposes a hand-posture recognition method using reinforcement learning for the performance improvement of vision-based hand-posture recognition. The difficulties in vision-based hand-posture recognition lie in viewing direction dependency and self-occlusion problem due to the high degree-of-freedom of human hand. General approaches to deal with these problems include multiple camera approach and methods of limiting the relative angle between cameras and the user's hand. In the case of using multiple cameras, however, fusion techniques to induce the final decision should be considered. Limiting the angle of user's hand restricts the user's freedom. The proposed method combines angular features and appearance features to describe hand-postures by a two-layered data structure and reinforcement learning. The validity of the proposed method is evaluated by appling it to the hand-posture recognition system using three cameras.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.897-907
• /
• 2023

Purpose: In this study, We aim to estimate a untrained person's three postures using a 2D CNN model which is trained with minimal FFT data collected by a 24GHz FMCW radar. Method: In an indoor space, we collected FFT data for three distinct postures (standing, sitting, and lying) from three different individuals. To apply this data to a 2D CNN model, we first converted the collected data into 2D images. These images were then trained using the 2D CNN model to recognize the distinct features of each posture. Following the training, we evaluated the model's accuracy in differentiating the posture features across various individuals. Result: According to the experimental results, the average accuracy of the proposed scheme for the three postures was shown to be a 89.99% and it outperforms the conventional 1D CNN and the SVM schemes. Conclusion: In this study, we aim to estimate any person's three postures using a 2D CNN model and a 24GHz FMCW radar for disastrous situations in indoor. it is shown that the different posture of any persons can be accurately estimated even though his or her data is not used for training the AI model.

• Journal of Oral Medicine and Pain
• /
• v.21 no.1
• /
• pp.55-65
• /
• 1996

This study was performed to investigate the effects of head posture and occlusal splint on the vertical dimension in mandibular rest position and swallowing. Thirty health dental students ware selected lot this study and BioEGNⓡ(Bioresearch Inc., USA) was used for measuring interocclusal distance during rest - swallowing - rest - tapping movement. This swallowing movements were observed in both normal head posture(NHP) and forward head posture (FHP). Thickness of occlusal splint was about 2mm at posterior molar area and even tooth contact were achieved on light biting. The four mandibular positions at which interocclusal distance measured were swallowing position, after swallowing position in which interocclusal distance was maximum, rest position follows swallowing, and tapping position after rest. Changes of distance in each position were measured for three mandibular planes, that is, sagittal, frontal, and horizontal plane, respectively. The results obtained were as follows : 1. In normal head posture, the mandible was raised 1.03mm without splint, and 0.77mm with splint on swallowing, and there was no significant difference between the two. In horizontal plane, however, mandible was displaced more anteriorly in both swallowing position and tapping position with splint. 2. In forward head posture, the mandible was less raised with splint on swallowing, but features in horizontal plane were almost same as those in normal head posture. 3. In natural dentition, significant difference between NHP and FHP were observed in horizontal plane trajectory for swallowing and tapping position. But the difference for same positions were observed in frontal trajectory with splint. 4. Total amount of mandibular movement of two groups classified with sagittal interocclusal distance of swallowing position generally showed significant difference between the higher and the lower height group in head posture without splint. 5. Correlationship among total amount of mandibular movement for three mandibular planes were observed between sagittal plane and horizontal plane, and between sagittal plane and frontal plane in head posture without splint.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.768-775
• /
• 2005

For sign languages are main communication means among hearing-impaired people, there are communication difficulties between speaking-oriented people and sign-language-oriented people. Automated sign-language recognition may resolve these communication problems. In sign languages, finger spelling is used to spell names and words that are not listed in the dictionary. There have been research activities for gesture and posture recognition using glove-based devices. However, these devices are often expensive, cumbersome, and inadequate for recognizing elaborate finger spelling. Use of colored patches or gloves also cause uneasiness. In this paper, a vision-based finger spelling recognition system is introduced. In our method, captured hand region images were separated from the background using a skin detection algorithm assuming that there are no skin-colored objects in the background. Then, hand postures were recognized using a two-dimensional grid analysis method. Our recognition system is not sensitive to the size or the rotation of the input posture images. By optimizing the weights of the posture features using a genetic algorithm, our system achieved high accuracy that matches other systems using devices or colored gloves. We applied our posture recognition system for detecting Korean Sign Language, achieving better than $93\%$ accuracy.

• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.435-448
• /
• 2008

3D posture recognition is a solution to overcome the limitation of 2D posture recognition. There are many researches carried out for 3D posture recognition using 3D data. The 3D data consist of massive surface points which are rich of information. However, it is difficult to extract the important features for posture recognition purpose. Meanwhile, it also consumes lots of processing time. In this paper, we introduced a dimension reduction method that transform 3D surface points of an object to 2D data representation in order to overcome the issues of feature extraction and time complexity of 3D posture recognition. For a better feature extraction and matching process, a cylindrical boundary is introduced in meshless parameterization, its offer a fast processing speed of dimension reduction process and the output result is applicable for recognition purpose. The proposed approach is applied to hand and human posture recognition in order to verify the efficiency of the feature extraction.

• Journal of Oral Medicine and Pain
• /
• v.23 no.2
• /
• pp.127-141
• /
• 1998

This study was performed to investigate the clinical features of internal derangement of temporomandibular joint. For this study, 117 patients with temporomandibular disorders and 81 dental students without any signs and symptoms of temporomandibular disorders were selected as the patients group and as the control group, respectively. Preferred chewing side, Angle's classification, lateral guidance pattern, maximal mouth opening range, and affected side were recorded clinically. Head and shouldeer posture was measured in a groundplate on which square diagram of five centimeters each had been drawn, and cephalograph was also taken for measurement of head and neck posture. Sonopak of Biopak system (Bioresearch inc., USA) was used to record joint vibration for evaluation of internal healthy status of temporomandibular joint. The data collected were analyzed by SAS statistical program. The results of this study were as follows : 1. Frequency of left side chewing subjects was higher in patients than in control group, but there was no difference in distribution of subjects by Angle's classification. Other types was prvalent in patients whereas group function was more in control group for lateral guidance pattern. 2. As to lateral guidance pattern by clinical diagnosis, patients with internal derangement and/or degenerative joint disease showed higher frequency was consistent with the result by Sonopak impression. 3. There was no difference for shoulder height between the two groups, however, tilting of head and backward extension of cervical spine was more frequent in control group. 4. Acromion was positioned more anteriorly in patients with internal derangement and/or degenerative joint disease than in control group and angle between eye and tragus was larger in patients. Patients with degenerative joint disease showed more flexed head posture than control group did in cephalometric profile. 5. Maximal mouth opening range in patients with internal derangement was the least in all subgroups in patients classified by Sonopak impression.