Artificial Intelligence-Based Speech Analysis System for Medical Support

김의선,신동진,조성태,정경진 대한배뇨장애요실금학회 2023 International Neurourology Journal Vol.27 No.2

Purpose: Prior research has indicated that stroke can influence the symptoms and presentation of neurogenic bladder, with various patterns emerging, including abnormal facial and linguistic characteristics. Language patterns, in particular, can be easily recognized. In this paper, we propose a platform that accurately analyzes the voices of stroke patients with neurogenic bladder, enabling early detection and prevention of the condition. Methods: In this study, we developed an artificial intelligence-based speech analysis diagnostic system to assess the risk of stroke associated with neurogenic bladder disease in elderly individuals. The proposed method involves recording the voice of a stroke patient while they speak a specific sentence, analyzing it to extract unique feature data, and then offering a voice alarm service through a mobile application. The system processes and classifies abnormalities, and issues alarm events based on analyzed voice data. Results: In order to assess the performance of the software, we first obtained the validation accuracy and training accuracy from the training data. Subsequently, we applied the analysis model by inputting both abnormal and normal data and tested the outcomes. The analysis model was evaluated by processing 30 abnormal data points and 30 normal data points in real time. The results demonstrated a high test accuracy of 98.7% for normal data and 99.6% for abnormal data. Conclusions: Patients with neurogenic bladder due to stroke experience long-term consequences, such as physical and cognitive impairments, even when they receive prompt medical attention and treatment. As chronic diseases become increasingly prevalent in our aging society, it is essential to investigate digital treatments for conditions like stroke that lead to significant sequelae. This artificial intelligence-based healthcare convergence medical device aims to provide patients with timely and safe medical care through mobile services, ultimately reducing national social costs.

반사판을 갖는 평판 다이폴 안테나의 특성 개선

김의선,박용욱,이상수,최학근 한국인터넷방송통신학회 2005 한국인터넷방송통신학회 논문지 Vol.5 No.1

고령층 안면근육이상분석에 따른 뇌졸중 초기단계 진단 시스템

김의선,허지민,은성종 차세대컨버전스정보서비스학회 2022 차세대컨버전스정보서비스기술논문지 Vol.11 No.1

The United Nations refers to an aging society if the population aged 65 or older exceeds 7% of the total population, and refers to an aging society if it exceeds 14%, and classifies it as a super-aged society if it exceeds 20%. Korea is already classified as an aging society in 2000, and the United States entered 1942 and Japan entered 1970. In 2018, Korean society entered the aged society at a rapid pace from an aging society, and diseases of the elderly are also increasing social expenditure. In order to reduce these social costs, various diagnostic technologies are being introduced to prevent cardiovascular disease, which is more than 40% of the diseases that can occur in the elderly. Among cardiovascular diseases, stroke should not miss the golden time within 5 hours of the disease. In other words, there is a desperate need for diagnostic technology that performs the function of notifying patients and guardians of the occurrence of a disease in the early stages of stroke. To this end, an artificial intelligence stroke early stage analysis software was developed that can alarm the early stage of stroke with a hit performance of more than 80% through facial muscle abnormalities analysis of the elderly. 유엔은 만 65세 이상 인구가 전체 인구의 7%를 넘으면 고령화 사회라고 지칭하고, 14%를 넘으면 고령사회로 지칭하고 20%를 넘으면 초고령 사회로 분류한다. 한국은 2000년에 이미 고령화 사회로 분류되고 있으며 미국은 1942년, 일본은 1970년에 진입하였다. 2018년 한국사회는 고령화 사회에서 고령사회로 초고속 진입을 하였으며, 이와 더불어 고령층 질병 또한 사회적 비용지출을 증가시키고 있다. 이러한 사회적 비용을 줄이고자 고령층에 나타날 수 있는 질병중 40% 이상인 심혈관질환 예방에 다양한 진단기술들이 도입되고 있다. 심혈관 질환중 뇌졸중은 질병 발생한 이후 5시간 이내의 골든 타임을 놓쳐서는 안된다. 즉 뇌졸중 초기단계에서 질병 발생을 환자와 보호자에게 알려주는 기능을 수행하는 진단 기술이 절실한 상황이다. 이를 위하여 고령층 안면근육이상분석을 통하여 뇌졸중 초기단계를 80%이상의 적중 성능을 가지고 알람할 수 있는 인공지능 뇌졸중 초기단계 분석 소프트웨어를 개발하였다.

분산처리서버에서의 멀티 쓰레드 방식을 적용한 원격얼굴인식 시스템

김의선,고일주 한국차세대컴퓨팅학회 2017 한국차세대컴퓨팅학회 논문지 Vol.13 No.5

IP보안 카메라의 보급으로 원격에서 얼굴인식을 수행함에 있어 서버의 부하를 줄이기 위한 여러 가지 방법들이 구현되고 있다. 본 논문에서는 원격지에 있는 IP 보안 카메라 영상을 얼굴검출기능이 탑재된 DSP 보드를 통해 입력받아 얼굴검출을 수행 한 후 해당 얼굴영역 이미지를 서버로 전송하여 이를 얼굴인식 분산 처리를 통해 얼굴인식 기능을 수행한다. 결과적으로 전체적인 서버시스템 로드를 상당히 줄이는 성과와 실시간 얼굴 인식처리를 최대 256 대의 카메라를 연동하면서 수행할 수 있는 장점을 가지고 있다. 이를 수행할 수 있는 기술은 분산처리 서버기술을이용하여 한 서버 당 64채널 얼굴인식을 수행하며, 4개 분산처리 서버를 운영할 경우 250여개 카메라 채널을 통한얼굴검출 결과를 처리하는 성과를 가져올 수 있었다. Various methods for reducing the load on the server have been implemented in performing face recognition remotely by the spread of IP security cameras. In this paper, IP surveillance cameras at remote sites are input through a DSP board equipped with face detection function, and then face detection is performed. Then, the facial region image is transmitted to the server, and the face recognition processing is performed through face recognition distributed processing . As a result, the overall server system load and significantly reduce processing and real-time face recognition has the advantage that you can perform while linked up to 256 cameras. The technology that can accomplish this is to perform 64-channel face recognition per server using distributed processing server technology and to process face search results through 250 camera channels when operating four distributed processing servers there was.

고령자 뇌졸중 위험 분석을 위한 딥러닝 기반 구음 분석 시스템

김의선,은성종 차세대컨버전스정보서비스학회 2023 차세대컨버전스정보서비스기술논문지 Vol.12 No.3

Cerebrovascular disease in the elderly has become an important disease in Korea, ranking second among all causes of mortality. Stroke is a disease that needs to be managed and prevented at all times, and it is important to visit a hospital within the golden time of 6 hours after the onset of stroke to receive appropriate treatment. Therefore, it is important to determine the risk of stroke in advance, and it is necessary to develop technology to support this. In this paper, we developed a system that determines whether a person is at risk of stroke by learning features such as speech tone and intonation based on spoken data of stroke patients. MFCC and CNN methods were used for feature analysis and judgment processing of spoken data, and a high accuracy of 97.9% was obtained as a result of performance evaluation based on spoken clinical data. The abnormal symptom information is shared with patients and managing clinicians as a alert service, which indicates the risk of stroke. In future research, we plan to further learn and analyze data from various stroke patients at home and abroad, and to advance the technology and commercialization of the stroke alert service platform. 초고령화 사회로 진입한 한국 사회에서의 고령층 심뇌혈관 질환은 전체 사망률 원인 중 2위에 속하는 중요한 질환이 되었다. 뇌졸중 질환은 발현 후 6시간 이내의 골든타임 내 병원에 내원하여 적절한 치료를 받아야 하며, 상시 관리 및 예방이 중요한 질환이다, 이로 인해 뇌졸중은 사전 위험 판단이 중요하며, 이를 지원해주는 기술 개발도 필요한 실정이다. 이에 본 논문은 뇌졸중 질환자의 구음 데이터를 기반으로 말투, 억양 등의 특징을 학습하여, 입력된 구음 데이터의 뇌졸중 위험 여부를 판단해주는 시스템을 개발하였다. 구음 데이터의 특징 분석과 판단 처리에는 MFCC 및 CNN 방법을 사용하였고, 구음 임상 데이터를 기반으로 성능평가 결과 평균 97.9%의 높은 정확도를 도출하였다. 해당 이상 증상 정보는 뇌졸중 위험이 있음을 알려주는 정보로, 환자와 관리 임상의에게 알림 서비스로 공유되어 진다. 향후 연구로는 국내외의 다양한 뇌졸중 환자의 데이터를 추가 학습 및 분석하여, 뇌졸중 알림 서비스 플랫폼의 기술 고도화 및 사업화를 추진하고자 한다.

유튜버 엄마의 보람찬 하루

김의선 샘터사 2020 월간 샘터 Vol.600 No.-

부산 북부지역 모암에 따른 토양의 구성광물 및 화학성분

김의선,황진연,김진섭,함세영 한국암석학회 2000 한국암석학회 학술발표회 논문집 Vol.- No.-

Development of Early-Stage Stroke Diagnosis System for the Elderly Neurogenic Bladder Prevention

김의선,허지민,은성종,이준영 대한배뇨장애요실금학회 2022 International Neurourology Journal Vol.26 No.S1

Purpose: There are various neurogenic bladder patterns that occur in patients during stroke. Among these patterns, the focus was mainly on the patient’s facial parsy diagnosis. Stroke requires early response, and it is most important to identify initial symptoms such as facial parsy. There is an urgent need for a diagnostic technology that notifies patients and caregivers of the onset of disease in the early stages of stroke. We developed an artificial intelligence (AI) stroke early-stage analysis software that can alert the early stage of stroke through analysis of facial muscle abnormalities for the elderly neurogenic bladder prevention. Methods: The method proposed in this paper developed a learning-based deep learning analysis technology that outputs the initial stage of stroke after acquiring a high-definition digital image and then deep learning face analysis. The applied AI model was applied as a multimodal deep learning concept. The system is linked and integrated with the existing urine management integrated system to support patient management with a total-care concept. Results: We developed an AI stroke early-stage analysis software that can alert the early stage of stroke with 86% hit performance through analysis of facial muscle abnormalities in the elderly. This result shows the validation result of the landmark image learning model based on the distance learning model. Conclusions: We developed an AI stroke early-stage diagnostic system as a wellness personal medical service plan and prevent cases of missing golden time when existing stroke occurs. In order to secure and facilitate distribution of this, it was developed in the form of AI analysis software so that it can be mounted on various hardware products. In the end, it was found that using AI for these stroke diagnoses and making them quickly and accurately had a positive effect indirectly, if not directly, on the neurogenic bladder.

자기저항 센서를 이용한 지능형 자율주행 전기자동차의 신경회로망 조향 제어기 개발

김태곤,손석준,유영재,김의선,임영철,이주상 제어로봇시스템학회 2000 제어로봇시스템학회 국내학술대회 논문집 Vol.2000 No.10

이산신호에서 실시간 저주파 진동 파라미터 추정 Part Ⅱ : 응용

김의선(Eui-Sun Kim),심관식(Kwan-Shik Shim),문채주(Chae-Joo Moon) 대한전기학회 2008 대한전기학회 학술대회 논문집 Vol.2008 No.7(초록집)