• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.541-543
• /
• 2022

In recent years, retinal disorders have become a serious health concern. Retinal disorders develop slowly and without obvious signs. To avoid vision deterioration, early detection and treatment are critical. Optical coherence tomography (OCT) is a non-invasive and non-contact medical imaging technique used to acquire informative and high-resolution image of retinal area and underlying layers. Disease signs are difficult to detect because OCT images have many areas which are not related to any disease. In this paper, we present a deep learning-based method to perform multi-label classification on a long-tailed OCT dataset. Our method first extracts the region of interest and then performs the classification task. We achieve 98% accuracy, 92% sensitivity, and 99% specificity on our private OCT dataset. Using the heatmap generated from trained convolutional neural network, our method is more robust and explainable than previous approaches because it focuses on areas that contain disease signs.

• PNF and Movement
• /
• 제18권2호
• /
• pp.287-296
• /
• 2020

Purpose: The study aims were to develop a wearable inertial sensor-based gait analysis device that uses machine learning algorithms, and to validate this novel device using temporal gait parameters. Methods: Thirty-four healthy young participants (22 male, 12 female, aged 25.76 years) with no musculoskeletal disorders were asked to walk at three different speeds. As they walked, data were simultaneously collected by a motion capture system and inertial measurement units (Reseed®). The data were sent to a machine learning algorithm adapted to the wearable inertial sensor-based gait analysis device. The validity of the newly developed instrument was assessed by comparing it to data from the motion capture system. Results: At normal speeds, intra-class correlation coefficients (ICC) for the temporal gait parameters were excellent (ICC [2, 1], 0.99~0.99), and coefficient of variation (CV) error values were insignificant for all gait parameters (0.31~1.08%). At slow speeds, ICCs for the temporal gait parameters were excellent (ICC [2, 1], 0.98~0.99), and CV error values were very small for all gait parameters (0.33~1.24%). At the fastest speeds, ICCs for temporal gait parameters were excellent (ICC [2, 1], 0.86~0.99) but less impressive than for the other speeds. CV error values were small for all gait parameters (0.17~5.58%). Conclusion: These results confirm that both the wearable inertial sensor-based gait analysis device and the machine learning algorithms have strong concurrent validity for temporal variables. On that basis, this novel wearable device is likely to prove useful for establishing temporal gait parameters while assessing gait.

• 대한한방소아과학회지
• /
• 제16권1호
• /
• pp.105-124
• /
• 2002

With the progress of civilization, the disorders due to the stress, which derived from the social-structural complexity and diversity, are on an increasing trend in our times. Accordingly, the accurate diagnosis and appropriate treatment for them are required. Especially in the current years, children's disorders delivered by the emotional problems keep increasing. In this research, the researcher tried to figure out the cause of the children's stress and its treatment, studied the theories of the stress in the modem medicine and the sever emotions in oriental medicine, and came to the conclusion as follows: 1. The stress can be defined as the combination of the reaction to noxious stimuli and its defense mechanism of the body, In oriental medicine, it is considered as pathological notions which includes seven emotions as the internal factor, six evils as the external factor and other foods, expectoration, ecchymoma as the non-internal/external factors. 2. Children usually get stressed by various reasons in a growth process such as schooling, relationship with friends, the opposite sex of family, or change of surroundings, and these can cause the various disorders. 3. In the study of the children's stress symptoms, it is found that the silent reaction is uncommon. It usually appeared in both reactions: firs, physical reactions such as stomachache, vomiting, headache, neural frequent urination, bronchial asthma or excessive respiration and/or, second, behavioral reactions such as a decline of performance, alimentary disorder, e.g. anorexia nervosa or bulimia, sleep disorder, e.g. nightmare or panic in sleep, anthrophobia, refusal to a school attendance or hyperactiveness. Besides, the peculiar mental disorder such as paroxysm of anger, tic, autism, nocturnal enuresis, lack of attentiveness, impediment in linguistic development, learning difficulty, intellectual decline, etc. can be appeared, and the heavy stress during the babyhood can cause the regression of behavior or the immaturity of formation of character. 4. The appropriate treatments for the children's stress are Osteopathy, Manpulation, Aroma Therapy, Alexander Technique, Autonomic Never Control Treatment, Biofeedback, Chiropractic, Dance Therapy, Feldenkrasis Technique, Gravity Therapy, Homepathy, Aquatherapy, Hypnotherapy, Naturopathy and Meditation.

• 한국음향학회지
• /
• 제28권1호
• /
• pp.32-43
• /
• 2009

본 논문은 자동 분할과 extreme learning machine (ELM)을 이용하여 연속 심음신호에 의한 심장질환 분류의 성능을 개선한다. 자동 분할을 위한 전처리 단계에서 비정상적인 심음신호는 심잡음 (murmur)과 클릭음 (click)을 포함하고 있기 때문에 제1음 (S1)과 제2음 (S2) 시작점 검출 결과가 부정확하거나 누락되어 기존의 심장질환 분류 시스템의 정확도를 저하시키게된다. 이러한 분할 오류에 의한 성능 저하를 감소하기 위해 S1 및 S2의 위치를 찾고, S1 및 S2의 시간 차이를 이용하여 부정확한 시작점을 교정한 다음 한 주기 심음 신호를 추출한다. 특징벡터로는 단일 주기의 심음 신호로부터 추출된 멜척도 필터뱅크 로그 에너지 계수와 포락선을 사용한다. 심장질환을 분류하기 위하여 한 개의 은닉층을 가진 ELM 알고리듬을 사용한다. 9가지 심장질환 분류 실험을 수행한 결과, 제안 방법은 81.6%의 분류 정확도를 나타내며, multi-layer perceptron(MLP), support vector machine (SVM), hidden Markov model (HMM) 중에서 가장 높은 분류 정확도를 보여준다.

• Biomolecules & Therapeutics
• /
• 제21권5호
• /
• pp.381-390
• /
• 2013

The purpose of this study was to examine whether ginsenoside Rg3 (GRg3) could improve learning and memory impairments and inflammatory reactions induced by injecting lipopolysaccharide (LPS) into the brains of rats. The effects of GRg3 on proinflammatory mediators in the hippocampus and the underlying mechanisms of these effects were also investigated. Injection of LPS into the lateral ventricle caused chronic inflammation and produced deficits in learning in a memory-impairment animal model. Daily administration of GRg3 (10, 20, and 50 mg/kg, i.p.) for 21 consecutive days markedly improved the LPS-induced learning and memory disabilities demonstrated on the step-through passive avoidance test and Morris water maze test. GRg3 administration significantly decreased expression of pro-inflammatory mediators such as tumor necrosis factor-${\alpha}$, interleukin-1${\beta}$, and cyclooxygenase-2 in the hippocampus, as assessed by reverse transcription-polymerase chain reaction analysis and immunohistochemistry. Together, these findings suggest that GRg3 significantly attenuated LPS-induced cognitive impairment by inhibiting the expression of pro-inflammatory mediators in the rat brain. These results suggest that GRg3 may be effective for preventing or slowing the development of neurological disorders, including Alzheimer's disease, by improving cognitive and memory functions due to its anti-inflammatory activity in the brain.

• 동의생리병리학회지
• /
• 제36권1호
• /
• pp.18-22
• /
• 2022

To investigate effects of cognitive function improvement whether against Taegeuk ginseng on scopolamine-induced memory impairment in rats. All experiments were conducted in three groups: the control group (CTR), the scopolamine 0.4mg/kg (SCP), and the scopolamine (SCP+T) treated with Taegeuk ginseng 100 mg/kg. Taegeuk ginseng 100 mg/kg daily was orally administered for one month and treated with scopolamine was only for 7 consecutive days on the Morris water maze task. 3 weeks after oral administration of Taegeuk ginseng, subjects were performed the Morris water maze test for 8 days and then the open-field exploration test which to assessed for cognitive function improvement. After behavioral testing, subjects were sacrificed and microdissected brains for neurochemical analysis. In the cognitive-behavioral test, long-term administration of Taegeuk ginseng improved spatial navigation learning task compared with the impeded by scopolamine treatment. In neurochemistry, the expression of the synaptic marker PSD95 (postsynaptic density protein 95) was increased in the hippocampus compared to the scopolamine group. Also, brain-derived neurotrophic factor (BDNF) expression was significantly increased in the taegeuk ginseng administration group. These data suggested that long-term administration of taegeuk ginseng might improve cognitive-behavioral functions on hippocampal related spatial learning memory, and it was correlated with neurotropic and synaptic reinforcement. In conclusion, treatment with taegeuk ginseng may positive outcome on learning and memory deficit disorders.

• Safety and Health at Work
• /
• 제13권4호
• /
• pp.379-386
• /
• 2022

Emergency medical services (EMS) personnel are at high risk for adverse mental health outcomes during disease outbreaks. To support the development of evidence-informed mitigation strategies, we conducted a scoping review to identify the extent of research pertaining to EMS personnel's mental health during disease outbreaks and summarized key factors associated with mental health outcomes. We systematically searched three databases for articles containing keywords within three concepts: EMS personnel, disease outbreaks, and mental health. We screened and retained original peer-reviewed articles that discussed, in English, EMS personnel's mental health during disease outbreaks. Where inferential statistics were reported, the associations between individual and work-related factors and mental health outcomes were synthesized. Twenty-five articles were eligible for data extraction. Our findings suggest that many of the contributing factors for adverse mental health outcomes are related to inadequacies in fulfilling EMS personnel's basic safety and informational needs. In preparation for future disease outbreaks, resources should be prioritized toward ensuring adequate provisions of personal protective equipment and infection prevention and control training. This scoping review serves as a launching pad for further research and intervention development.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• 동의생리병리학회지
• /
• 제25권5호
• /
• pp.876-880
• /
• 2011

Gammakdaejo-Tang (GMT) is a traditional oriental medicinal formula, a mixture of 3 crude drugs, and it has been clinically used for treating mild depressive disorders. The purpose of the study was to examine the effect of Gammakdaejo-Tang (GMT) on repeated stress-induced alterations of learning and memory on a passive avoidance test (PAT) test and also the anxiety-related behavior on the elevated pulse maze (EPM) in ovariectomized female rats. We assessed the changes in the reactivity of the cholinergic system by measuring the immunoreactive neurons of choline acetyltransferase (ChAT) in the hippocampus after behavioral testing. The rats were exposed to the immobilization (IMO) stress for 14 days (2hours/day), and Gammakdaejo-Tang (400 mg/kg, p.o.) was administered 30 min before IMO stress. Treatments with GMT caused significant reversals of the stress-induced deficits in learning and memory on a working memory test, and it also produced an anxiolytic-like effect on the EPM, and increased the ChAT reactivities (p<0.001, respectively). These results suggest that Gammakdaejo-Tang might prove to be an effective antidepressant agent.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.552-554
• /
• 2019

농아는 청각장애인과 언어장애인을 말하며 청각장애인과 언어장애인은 음성으로 의사소통하는 것에 어려움이 있기 때문에 수화나 구화 등을 이용하여 의사소통을 한다. 그러나 수화는 모든 사람들이 사용하는 통신 수단이 아니기 때문에 수화를 알지 못하는 사람과의 의사소통하는 데 있어 한계가 생길 수밖에 없다. 본 논문에서는 장애인과 비장애인이 어려움 없이 의사소통할 수 있는 수단으로 지화 번역 시스템을 제안하고 설계 및 구현하였다. 립 모션으로 지화를 인식하였고 인식률을 높이기 위해 머신 러닝 기술을 이용하여 지화 데이터를 스스로 학습시켰다. 구현 및 실험 결과를 통해 제안한 알고리즘 적용으로 인식률 개선이 이뤄졌음을 확인하였다.