• 한국정보전자통신기술학회논문지
• /
• 제9권6호
• /
• pp.609-616
• /
• 2016

본 논문에서는 SVM과 협업적 필터링을 이용한 소비자 맞춤형 시장 분석 기법을 제안하였다. 제안하는 소비자 맞춤형 시장 분석 기법은 DC(Data Classification) 모듈, ICF(Improved Collaborative Filtering) 모듈, 그리고 CMA(Customized Market Analysis) 모듈로 구성된다. DC 모듈은 SVM을 이용하여 온 오프라인 쇼핑몰과 전통시장의 특성을 가격, 품질평가, 주력상품으로 분류하고, ICF 모듈은 나이 가중치와 직업 가중치를 추가한 유사도를 생성하고, 사용자들간의 구매 아이템에 대한 유사도를 이용하여 네트워크를 생성하고, 이웃 노드의 추천 리스트를 생성한다. 그리고 CMA 모듈은 DC모듈의 데이터 분류 결과와 ICF 모듈의 추천 리스트를 이용하여 사용자 맞춤형 시장 분석 결과를 제공한다. 제안된 사용자 맞춤형 추천리스트와 기존의 사용자기반 추천 리스트를 비교한 결과, 기존의 협업적 필터링기법을 이용한 추천리스트의 경우, precision는 0.53, recall은 0.56, F-measure은 0,57인데 반해, 제안하는 소비자 맞춤형 추천리스트는 precision이 0.78, recall은 0.85, 그리고 F-measure은 0.81로 나타났다. 즉, 제안하는 소비자 맞춤형 추천리스트가 좀 더 정확한 것으로 나타났다.

• 인터넷정보학회논문지
• /
• 제24권1호
• /
• pp.39-47
• /
• 2023

The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.

• 한국의류학회지
• /
• 제45권6호
• /
• pp.949-964
• /
• 2021

Accumulation of high-quality data is crucial for AI learning. The goal of using AI in fashion service is to propose of a creative, personalized solution that is close to the know-how of a human operator. These customized solutions require an understanding of fashion products and emotions. Therefore, it is necessary to accumulate data on the attributes of fashion products and fashion emotion. The first step for accumulating fashion data is to standardize the attribute with coherent system. The purpose of this study is to propose a fashion emotional classification system. For this, images of fashion products were collected, and metadata was obtained by allowing consumers to describe their emotions about fashion images freely. An emotional classification system with a hierarchical structure, was then constructed by performing frequency and CONCOR analyses on metadata. A final classification system was proposed by supplementing attribute values with reference to findings from previous studies and SNS data.

• 한국컴퓨터정보학회논문지
• /
• 제16권2호
• /
• pp.33-46
• /
• 2011

이메일이 중요한 정보 전달과 의사소통의 수단으로 널리 활용된 이래 사람들은 이메일을 내용에 따라 적절하게 분류하는 작업에 많은 노력을 기울려 왔다. 이메일은 문서의 길이나 문체가 다양하며 사용되는 단어들이 비정규적이다. 또한 이메일 분류 기준은 일반적으로 해당 이메일 사용자의 주관에 따라 정의된다. 따라서 기존의 일반적인 문서분류 기법으로는 이메일을 효율적으로 분류하는데 어려움이 있다. 상업용 이메일 프로그램에서 제공되는 분류 기능은 메일 클라이언트에서 지원하는 텍스트 필터링을 이용한다. 한편 이메일의 자동 분류에 관한 연구는 확률 기반의 나이브 베이지안 기법을 응용하여 정확도를 높일 수 있는 연구가 주로 진행되어 왔으며, 대부분 영문 이메일에 대한 연구이다. 본 논문에서는 빈발 패턴 마이닝 기법을 적용하여 한글 이메일에 대한 개인 맞춤형 폴더 추천기법을 제시한다. 이메일의 맞춤형 폴더 추천 기법은 이메일에 대한 전처리 과정과 빈발 항목집합을 이용한 메일 폴더의 프로파일 생성과정으로 구성된다. 생성된 프로파일은 분류 대상이 되는 각 메일이 개인별 맞춤형 기준에 따라 가장 적합한 이메일 폴더로 효과적으로 분류되는데 활용된다. 또한 제안된 기법을 적용한 이메일 분류 시스템을 구현한다.

• 한국보건간호학회지
• /
• 제26권3호
• /
• pp.491-503
• /
• 2012

Purpose: The purpose of this study was to measure empowerment and to identify factors influencing empowerment. Method: Subjects included 767 clients registered with the customized home visiting health services in Daegu. Data collection was performed from June 3 to July 30, 2011. Descriptive statistics, ${\chi}^2$ test, ANOVA, and stepwise multiple regression were used in this study. Results: The mean score for total empowerment was 3.01(${\pm}0.28$). In subscales of total empowerment, the score for individual empowerment was 2.97(${\pm}0.36$), the score for interpersonal relationship empowerment was 3.09(${\pm}0.34$), and the score for political-social empowerment was 2.96(${\pm}0.48$). Job, education, economic status, living arrangement, and client classification were significant factors related to total empowerment in these clients. Job, education, economic status, types of health insurance, living arrangement, age, and client classification were significant factors related to individual empowerment, interpersonal relationship empowerment and political-social empowerment. 4.4 percent of the variance in total empowerment can be explained by education and living arrangement (Cum $R^2=0.044$, F=13.207, p<.001). Individual empowerment, interpersonal relationship empowerment, and political-social empowerment can be explained by education, job, economic status, and living arrangement. Conclusion: An empowerment intervention that includes general characteristics of clients is essential to improving empowerment of customized home visiting health care services beneficiaries.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1433-1443
• /
• 2016

In the cases of the major cities, high poverty rate of the elderly, immature pension policies, and insufficient market conditions, policies and services for the employment of the elderly decrease the desire for the job participation. It is time to prevent the problems of the elderly, and induce the reachable seniors to participate in social activities. This research provides the location-based, customized job-search service for the elderly in order to actively support the participation in the economic activities of the elderly. The goal of SSJS(Smart Senior Job Search) is to provide the individual elderly with the customized position. It prints the appropriate positions near user location based on the residential area, job classification, and the physical condition, and provides the mash-up of the selectable job range in the unit distance based on the map. This customized service, which enables the seniors to select the type of the jobs based on their physical, mental and life conditions of the seniors, supports the participation in economic activities of the elderly people, and contribute to the expansion of the social job positions for the elderly and the equalization of the local development.

• 한국의류산업학회지
• /
• 제23권6호
• /
• pp.790-798
• /
• 2021

With digital technology innovation, increased data access and mobile network use by consumers, products and services are changing toward pursuing differentiated values for personalization, and personalized markets are rapidly emerging in the fashion industry. This study aims to identify trends in digital customized automation technology by deriving types of digital customizing and analyzing cases by type, and to present directions for the development of digital customizing processes and the use of technology in the future. As a research method, a literature study for a theoretical background, a case study for classification and analysis of types was conducted. The results of the study are as follows. The types of digital customizing can be classified into three types: 'cooperative customization', 'selective composition and combination', 'transparent suggestion', and automation technologies shown in each type include 3D printing, 3D virtual clothing, robot mannequin, human automatic measurement program, AR-based fitting service, big data, and AI-based curation function. With the development of digital automation technology, the fashion industry environment is also changing from existing manufacturing-oriented to consumer-oriented, and the production process is rapidly changing with IT and artificial intelligence-based automation technology. The results of this study hope that digital customized automation technology will meet various needs of personalization and customization and present the future direction of digital fashion technology, where fashion brands will expand based on the spread of digital technology.

• 도시과학
• /
• 제9권2호
• /
• pp.21-30
• /
• 2020

The purpose of this study is to present a plan to distinguish 229 local governments nationwide by taking into account various characteristics such as population, employment, housing, and industry of the region for customized urban policies in the era of metropolitan areas. The National Statistical Portal (KOSIS) collected and standardized data related to population, housing, industry, and finance by region from 2000 to 2015 for the classification of regional types necessary for customized urban policies, and this was used to classify them into regional types that considered population, employment, housing and industry. The summary of the analysis results is as follows. First, as a result of the regional type classification, 10 key employment sites (4.4%), 5 employment centers (2.2%), 38 residential centers (16.6%), 20 growth areas (8.7%), 26 industrial cities (11.4%), 35 low-fertile farming and fishing villages (15.3%) and 95 stagnant areas (41.5%). Second, the Seoul metropolitan area is the most diverse type of metropolitan area in the country, with most of its core employment sites inside Seoul, residential centers inside and outside Seoul, and growth areas in the southeastern part of the country (Busan, Ulsan, and Gyeongsangnam-do) are mixed with industrial and growth areas centered around Busan, Ulsan and surrounding areas, while the rest of the local governments are found to be low-fertile farming villages or stagnant areas. Daegu (Daegu, Gyeongbuk) is an industrial city in Daegu, and the rest of the local governments are either low-density farming and fishing villages or stagnant areas. The Honam region (Gwangju and Jeolla) was found to be a low-mill farming and fishing village or stagnant area except for Gwangju, while the Chungcheong region (Daejeon, Sejong, and Chungcheong) was seen as a growth area with areas adjacent to Daejeon, Sejong, and the Seoul metropolitan area, and some industrial cities were included. Finally, the Gangwon area was mostly classified as low-density farming and fishing villages and stagnant areas.

• 한국컴퓨터정보학회논문지
• /
• 제27권10호
• /
• pp.59-66
• /
• 2022

본 논문에서는 음성 데이터에서 특징벡터를 추출한 후 이를 분석하여 화자의 성별을 분류하는 연구를 진행하였다. 본 연구는 고객이 전화 등 음성을 통해 서비스를 요청할 시 요청한 고객의 성별을 자동으로 인식함으로써 직접 듣고 분류하지 않아도 되는 편의성을 제공한다. 학습된 모델을 활용하여 성별을 분류한 후 성별마다 요청 빈도가 높은 서비스를 분석하여 고객 맞춤형 추천 서비스를 제공하는 데에 유용하게 활용할 수 있다. 본 연구는 공백을 제거한 남성 및 여성의 음성 데이터를 기반으로 각각의 데이터에서 MFCC를 통해 특징벡터를 추출한 후 SVM 모델을 활용하여 기계학습을 진행하였다. 학습한 모델을 활용하여 음성 데이터의 성별을 분류한 결과 94%의 성별인식률이 도출되었다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권3호
• /
• pp.117-124
• /
• 2023

농림축산식품부는 2008년 조직개편을 통해 식품 정책에 대한 기능이 이관되어 보건복지부 등에 산재하여 있던 식품산업을 통합관리 하게 되었고, 1, 2, 3차 산업을 포괄한 종합 정책을 수립하고 있다. 최근 4차 산업혁명과 더불어 농축산식품산업에도 스마트팜, 푸드테크 등 새로운 사업개념이 등장하였다. 농림축산식품부는 4차산업에 적합한 정책을 수립하기 위해 농축식품산업의 사업체 규모를 정확히 추정하는 것이 필요하게 되었다. 농림축산식품부는 전방과 후방 산업의 연계분석을 통한 부가가치 산출과 농축산식품산업의 정확한 모집단을 추정하기 위해서 2017년부터 농축산식품산업 특수분류를 위해 연구하기 시작하였고 통계청으로부터 농축산식품 특수분류 승인을 받았다. 특수 분류를 기반으로 한 농축산식품산업의 모집단 추정은 매출액, 종사자 수 등 전 산업에서 차지하는 비중이 정책의 수립과 중요도에 많은 영향을 미치기 때문에 매우 중요하다. 본 논문은 농축산식품 특수분류와 한국표준산업분류에서의 추출된 표본을 이용하여 현재적격률을 산정하고 모집단을 추정하는 과정과 현재적격률을 보완하기 위한 추정적격률을 제안하여 보다 모집단을 잘 반영하는 방안을 제시하고자 한다.