지압점 자유선택 및 지압강도 가변이 가능한 스마트 지압침대 개발

안도현(Do-Hyun Ahn),김해용(Hae-Yong Kim),이종민(Jongmin Lee),허성필(Sung-Phil Heo) 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.6

지압강도 및 위치 가변형 지압침대의 개발 및 성능 평가

안도현(Do-Hyun Ahn),김해용(Hae-Yong Kim),이강호(Kang-Ho Lee),이종민(Jongmin Lee),허성필(Sung-Phil Heo) 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.11

지압은 척추 유관 질환자의 통증 감소 및 증상 완화에 효과가 좋은 것으로 알려져 있다. 마사지 침대는 지압이나 뜸을 편리하게 제공하는 기기이다. 하지만 기존에는 바퀴가 정해진 레일을 따라 이동하는 마사지 방식으로 사용자가 원하는 부위와 강도를 정할 수 없었다. 이를 개선하기 위하여 침대 내부에 삼차원 지압점 이동모듈을 탑재한 침대를 개발하였다. 또한 의료전문가 명의 지압력을 측정한 결과 최대 33kgf의 지압력이 필요함을 확인하였고 개발침대의 성능평가의 결과 지압력의 세기는 최대 40.1kgf까지 구현되며 해상도는 53.kgf, 지압율 오차율은 1.89%로 정밀하게 구현되었음을 확인하였다. Acupressure is known to be effective in reducing pain and relieving symptoms in patients with spinal related diseases. A massage bed is a device that conveniently provides acupressure or moxibustion. However, in the past, the massage method in which the wheels move along a set rail did not allow the user to determine the desired part and strength. To improve this, we developed a bed equipped with a three-dimensional acupressure point moving module inside the bed. Also, as a result of measuring acupressure by 7 medical experts, it was confirmed that acupressure of up to 33kgf was required. It was confirmed that the strength of the body was realized up to 40.1kgf, the resolution was 5.3kgf, and the acupressure rate error rate was 1.89%.

Effect of Vertically Rising Pressure Providing Spinal Canal Segment Motion on Symptom Relief in Patients with Parkinson's Disease

안도현(Do-Hyun Ahn),최현우(Hyeun Woo Choi),정경미(Kyung-Mi Jung),김나영(Na-Young Kim),이종민(Jong-Min Lee) 한국방사선학회 2022 한국방사선학회 논문지 Vol.16 No.6

본 연구는 온열·마사지 자극이 가능한 기계식 침대 적용을 통해 척추를 수직으로 자극하여, 파킨슨병의 통증 감소 및 증상 완화를 확인하고자 하였다. 이를 위해 파킨슨병 환자를 대상으로 의료용 조합자극 침대를 사용함에 따른 척추의 분절운동을 확인한 후 시각아날로그척도, 요통 기능 장애, 보행 능력, 나선형 그리기 검사를 실시하고 해당 변수 간의 관계를 파악하였다. 10일간의 시각아날로그척도, 요통 기능 장애 평가에서 침대 사용 후 평균이 감소하는 경향을 확인하였다. 보행 능력은 이동 시간의 감소와 이동 거리의 증가를 관찰하였다. 나선형 그리기 검사에서 침대 사용 후 검사 시간의 평균이 전보다 유의하게 낮았다. 그 결과, 기계식 온열 및 마사지로 척추 분절운동이 발생함에 따른 파킨슨병 환자의 회복 및 통증 완화를 위한 보조적인 방법으로 사용할 수 있는 가능성을 제시하였다. 그러나 본 연구는 예비적 연구로 피험자수가 적어 향후 피험자수와 상태를 세부적으로 고려한 추가적 연구가 필요하다. The purpose of this study was to confirm the reduction of pain and symptom relief of Parkinson's disease by vertically stimulating the spine through the application of a mechanical bed capable of thermal and massage stimulation. For this purpose, after confirming the segmental motion of the spine due to the use of a medical combination stimulation bed for Parkinson's disease patients, VAS, ODI, gait ability, and spiral drawing tests were performed, and the relationship between the variables was identified. In the 10-day visual analog scale and evaluation of low back pain dysfunction, the average trend of decreasing after bed use was confirmed. For walking ability, a decrease in the moving time and an increase in the moving distance were observed. In the spiral drawing test, the mean test time after using bed was significantly lower than before. As a result, it suggested the possibility of using it as an auxiliary method for recovery and pain relief of Parkinson's disease patients due to spinal segmental movement with mechanical heating and massage. However, this study is a preliminary study, and there is a small number of subjects, so additional research is needed that considers the number and condition of future subjects in detail.

인터넷 쇼핑몰을 위한 데이터마이닝 기반 개인별 상품추천방법론의 개발

김재경(Jae Kyeong Kim),안도현(Do Hyun Ahn),조윤호(Yoon Ho Cho) 한국지능정보시스템학회 2003 지능정보연구 Vol.9 No.3

상품추천시스템은 고객들에게 추천 상품 리스트를 만들어 고객들이 구매 가능성이 있는 상품을 쉽게 찾도록 도와주는 개인화 된 정보필터링 기술이다. 협업 필터링(collaborative filtering)이 가장 성공적인 상품추천 기법으로 알려져 있으며 많이 이용되고 있다. 그러나, 인터넷 쇼핑몰에서 관리하는 상품과 고객의 수가 급속히 증가하면서 협업필터링에 기반한 상품추천시스템은 입력 데이터의 희박성(Sparsity) 문제와 시스템 확장성(Scalability) 문제가 노출되고 있다. 따라서 본 연구에서는 협업필터링 기반 상품추천시스템의 상품추천 효과 및 성능을 개선하기 위해 웹 마이닝과 군집분석 기법에 기반을 둔 개인별 상품추천 방법론을 개발한다. 또한 실제 인터넷 쇼핑몰에서 개인별로 상품을 추천할 때 개발된 상품추천 방법론을 적용하여 다른 기존 상품추천 방법론과 실험적으로 비교함으로써 개발 방법론의 효과 및 성능을 검증한다. Recommender systems are a personalized information filtering technology to help customers find the products they would like to purchase. Collaborative filtering is the most successful recommendation technology. Web usage mining and clustering analysis are widely used in the recommendation field. In this paper, we propose several hybrid collaborative filtering-based recommender procedures to address the effect of web usage mining and cluster analysis. Through the experiment with real e-commerce data, it is found that collaborative filtering using web log data can perform recommendation tasks effectively, but using cluster analysis can perform efficiently.

e-비즈니스 모형과 전략 수립 방법론에 관한 연구:KNK 유학원 사례를 중심으로

김재경(Jae Kyeong Kim),안도현(Do Hyun Ahn),김희동(Hee Dong Kim) 한국IT서비스학회 2003 한국IT서비스학회지 Vol.2 No.2

The Internet affects all economic activities. Physical world business must either adopt new digital strategies, launch new digital business to complement their physical world models, or be forced to completely revise their strategies. The purpose of this paper is to provide a framework that organizes the managerial decision-making process to assist managers in crafting and implementing e-business strategy. We applied the methodology to the case of KNK Educational Institute to explain the process. Core competence of KNK JUNIOR is researched according to our suggested methodology and activities and roles of KNK JUNIOR have been arranged.

변동형 대차 구동방식의 지압 침대 개발 및 유효성 평가

허성필(Sung-Phil Heo),박세진(Se-Jin Park),안도현(Do-Hyun Ahn) 한국산업정보학회 2020 한국산업정보학회논문지 Vol.25 No.6

지압은 신체의 특정 부위에 압력을 가하는 치료행위로 주로 한의학 분야에서 통증 경감에 활용되어 왔다. 하지만 시술자의 역량, 경험, 체력에 따라 치료 효과가 달라지는 경우가 많아 표준화된 지압이 필요하며 관련하여 기구가 출시되고 있으나 주로 롤링 마사지 방식이어서 에너지 집중도가 떨어지며 부상의 위험성이 있었다. 따라서 본 연구에서는 변동형 대차를 기반으로 수직 지압을 제공하는 장치를 구현하였다. 장치의 지압력 유효성 확인을 위해 하중 실험 및 체압 분포, 만족도를 실험한 결과 지압봉은 150kg까지 버티며, 체압비는 0 % < x ≤ 5% 구간에서 비교품의 체압 비율에 비해 낮게 측정되었으며, 또한 주관적 만족도는 평균 2.11점의 높은 점수를 받았다. 따라서 수직 지압이 적용된 장치가 기존 제품과 비교하면 체압 분산에 효과가 있었으며 만족도가 높다고 볼 수 있었다. 향후 연구에서는 수직 지압 사용 그룹과 전문 치료사의 지압 그룹을 구성하여 개발 기기가 사람에 비해 균일한 지압을 제공하는지 비교 평가할 필요가 있다. The acupressure is a treatment that applies pressure to certain parts of the body and has been mainly used for pain relief in the field of oriental medicine. However, the treatment effect is often different depending on the practitioner"s ability, experience, and physical strength, so standardized acupressure is needed. In this regard, the equipment is being released, but this is mainly a rolling massage method, which reduces energy concentration and poses a risk of injury. Therefore, in this study, a device that provides vertical acupressure based on variable bogie (wheel truck) was implemented. As a result of experimenting with load and body pressure distribution and desirability to validate the device"s bearing pressure, the acupressure rod held up to 150kg, the body pressure ratio was measured lower than the body pressure ratio of the comparison item in section 0%<x≤ 5%, and the subjective satisfaction was also scored high by an average of 2.11 points. Thus, the device with vertical acupressure was more effective in dispersion of body pressure than conventional products and was more satisfying. In future studies, it is necessary to organize a group of vertical acupressure use and a group of professional therapists to assess whether the development device provides a uniform acupressure compared to humans.

설명기능을 추가한 협업필터링 기반 개인별 상품추천시스템

조윤호(Yoon Ho Cho),김재경(Jae Kyeong Kim),안도현(Do Hyun Ahn),이희애(Hee Ae Lee) 한국경영학회 2006 經營學硏究 Vol.35 No.2

The continuous growth of the Internet and e-commerce has allowed companies to provide customers with more choices on products. Increasing choice has also caused product overload where the customer is no longer able to effectively choose the products he/she is exposed to. A promising technology to overcome the product overload problem is recommender systems that help customers find the products they would like to purchase. To date, a variety of recommendation techniques have been developed. Collaborative Filtering (CF) is the most successful recommendation technique, which has been used in a number of different applications such as recommending movies, articles, books, Web pages, etc. However, its widespread use has exposed some limitations, such as sparsity, scalability, and black box. Many researchers have focused on sparsity and scalability problems but a little has tried to solve the black box problem. Most CF recommender systems are black boxes, providing no transparency into the working of the recommendation. To overcome the black box problem, it is developed a recommender system named WebCF-Exp (Web usage mining driven Collaborative Filtering with Explanation facilities). Explanation facilities make it possible to expose the reasoning and data behind a recommendation. Therefore, they provide us with a mechanism for handling errors that come with a recommendation. Furthermore, it is proposed to use web usage mining and product taxonomy to enhance the recommendation quality for e-commerce environment. Web usage mining populates the rating database by tracking customers’shopping behaviors in the Web, thereby leading to better recommendations. The product taxonomy is used to improve the performance through dimensionality reduction of the rating database.The overall procedure of WebCF-Exp consists of two phases: recommendation phase and explanation phase. The recommendation phase is divided into four sub-phases: grain specification, customer profile creation, neighborhood formation, and recommendation generation. The explanation phase consists of white box model and black box model. A white box model is one way to build explanation interfaces using detailed process or data such as neighbor ratings, the ratio of click, and the ratio of purchase. Black box model is the other way of which there is no detailed process or data available. In black box model, we focus on ways to justify recommendation that are independent of the process such as marketing or event information.WebCF-Exp recommender system is operated by four agents: Web log analysis agent, Data transformation agent, Recommendation agent, and Explanation agent. Web log analysis agent manages Web log database through periodic collecting, parsing and analyzing Web server log files such as access logs, referrer logs, agent logs and cookie files. Thus, the users can easily access and analyze them like other operation databases. Data transformation agent creates and manages the data mart that provides data indispensable to accomplish recommendation tasks. Recommendation agent makes a personalized recommendation list for each target customer. Explanation agent provides interfaces which expose the reasoning and data behind a recommendation. Twenty different explanation interfaces are developed as white box model and black box model. To test the performance of WebCF-Exp, it is developed a prototype internet shopping mall named EBIB (e-Business & Intelligent Business) and interactive interfaces. Experiments are conducted with the data provided by EBIB Research Internet shopping mall. Our experimental result shows that WebCF-Exp recommendation system shows better performance than the CF recommendation system without explanation facilities. And explanation types of five stars, simple graph, and showing the evaluation results of similar customers, show better performance than other types. Furthermore, as customers understand explanation interfaces better, it results that customers

신체적 구조 특성을 반영한 지압강도 가변이 가능한 스마트 지압 침대 개발

김재훈(Jae-Hun Kim),김해용(Hea-yong Kim),박상욱(Sang-Wook Park),안도현(Do-Hyun Ahn),장호경(Ho-Gyeong Chang),허성필(Sung-Phil Heo) 한국정보기술학회 2023 Proceedings of KIIT Conference Vol.2023 No.11

재구성된 제품 계층도를 이용한 협업 추천 방법론 및 그 평가

조윤호,박수경,안도현,김재경 한국경영과학회 2004 한국경영과학회지 Vol.29 No.2

Recommendation is a personalized information filtering technology to help customers find which products they would like to purchase. Collaborative filtering works by matching customer preferences to other customers in making recommendations. But collaborative filtering based recommendations have two major limitations, sparsity and scalability. To overcome these problems we suggest using adjusted product hierarchy, grain. This methodology focuses on dimensionality reduction and uses a marketer's specific knowledge or experience to improve recommendation quality. The quality of recommendations using each grain is compared with others by several experimentations. Experiments present that the usage of a grain holds the promise of allowing CF-based recommendations to scale to large data sets and at the same time produces better recommendations. In addition, our methodology is proved to save the computation time by 3-4 times compared with collaborative filtering.