• 지능정보연구
• /
• 제13권4호
• /
• pp.65-78
• /
• 2007

추천시스템은 개인화 서비스를 구현하는 방법 중의 하나이다. 추천시스템은 다양한 기법을 통해 구축될 수 있는데, 최근 전자상거래 분야에서 사용되는 기법들 중에서 대표적인 것이 협업필터링이다. 협업필터링은 영화나 음악 같이 명시적인 속성만으로 그 특성을 기술하는데 한계가 있는 아이템의 추천문제에 효과적으로 적용되어 왔다. 하지만, 이 기법은 희박성, 확장성 및 투명성 등의 문제점을 가지고 있는데, 본 연구에서는 희박성과 확장성 문제를 극복하는 방안으로 장르별 협업필터링 방법을 제안한다. 장르별 협업필터링 방법은 아이템을 최종적으로 추천하기 전에 아이템의 상위 카테고리, 즉 장르에 대한 정보를 활용하는 방법이다. 본 연구에서 제안하는 방법의 실용성을 보이기 위하여, 영화 추천시스템인 GenreWise_CF를 개발하여, 공개 데이터인 MovieLens Data에 적용하여 평가하였다. 실험 결과, 본 연구에서 제안한 GenreWise_CF가 전통적인 협업 필터링을 적용하여 개발한 추천시스템인 Basic_CF보다 향상된 성능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권2호
• /
• pp.31-40
• /
• 2012

홍채 인식은 홍채 패턴 정보를 이용하여 사람의 신원을 확인하는 생체 인식 기술이다. 이러한 홍채 인식 시스템에 있어 조명의 영향이나 동공의 크기, 머리의 기울어짐 등으로 인해 발생될 수 있는 홍채 패턴의 변화에 대해 무관한 특징을 추출하는 것은 중요한 과제이다. 본 논문에서는 Zernike Moment를 이용해 홍채의 회전에 강인한 홍채 인식 방법을 제안하였다. 빠르고 효과적인 인식을 위한 Zernike Moment를 선택하기 위해 전역 최적 차수를 이용하였고, 각각의 홍채 클래스와 매칭하기 위하여 국소 최적 차수를 사용 하였다. 제안된 방법은 특징 추출 및 특징 비교 시 회전에 대해 별도의 처리가 필요하지 않아 고속의 특징 추출 및 특징 비교가 가능하며 성능도 기존의 방법과 대등함을 실험을 통하여 확인하였다.

• 동아시아경상학회지
• /
• 제9권4호
• /
• pp.1-15
• /
• 2021

Purpose - In a difficult time for a firm, it seems impossible to change circumstances by a firm. Nevertheless, the firm must do whatever it can do by however it can do. Therefore, the purpose of this study is to analyze the effect of HRM practice on organizational effectiveness with the status quo of the firm as a moderator. Based on the result of this study, the managerial implication could be suggested as a contextual response to each status quo of the firm in improving and managing organizational effectiveness by HRM practice. Research design, data, and methodology - This study measured organizational effectiveness with employee satisfaction and organizational commitment. HRM practice includes two HR management areas, HR system, and HR attitude. HR system includes education & training and additional wage welfare. HR attitude includes employee stress and empowerment. As for the status quo of the firm, this study considered three construct; firm feature, strategic feature, environment change feature. This study analyzed 397 employees of 24 company data from the 7th HCCP of KRIVET. Result - Hypothesis 1 through Hypothesis 3 were partially supported. The results of this study suggest that to increase organizational effectiveness(job satisfaction and organizational commitment), employee stress and education & training participation need to be managed. And circumstance of an organization as given the Status Quo of the firm needs to be managed differently like firm size, environment change in demand, and technology. Conclusion - This study suggests best-practice implications based on the result between HRM practice and organizational effectiveness. And also suggest differentiation in management to increase the best-fit in management.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.701-720
• /
• 2023

Aerial objects are more challenging to segment than normal objects, which are usually smaller and have less textural detail. In the process of segmentation, target objects are easily omitted and misdetected, which is problematic. To alleviate these issues, we propose local aggregation feature pyramid networks (LAFPNs) and pyramid integrated context modules (PICMs) for aerial object segmentation. First, using an LAFPN, while strengthening the deep features, the extent to which low-level features interfere with high-level features is reduced, and numerous dense and small aerial targets are prevented from being mistakenly detected as a whole. Second, the PICM uses global information to guide local features, which enhances the network's comprehensive understanding of an entire image and reduces the missed detection of small aerial objects due to insufficient texture information. We evaluate our network with the MS COCO dataset using three categories: airplanes, birds, and kites. Compared with Mask R-CNN, our network achieves performance improvements of 1.7%, 4.9%, and 7.7% in terms of the AP metrics for the three categories. Without pretraining or any postprocessing, the segmentation performance of our network for aerial objects is superior to that of several recent methods based on classic algorithms.

• Korean Journal of Radiology
• /
• 제22권6호
• /
• pp.880-889
• /
• 2021

Objective: This study aimed to investigate the regional amyloid burden and myocardial deformation using T1 mapping and strain values in patients with cardiac amyloidosis (CA) according to late gadolinium enhancement (LGE) patterns. Materials and Methods: Forty patients with CA were divided into 2 groups per LGE pattern, and 15 healthy subjects were enrolled. Global and regional native T1 and T2 mapping, extracellular volume (ECV), and cardiac magnetic resonance (CMR)-feature tracking strain values were compared in an intergroup and interregional manner. Results: Of the patients with CA, 32 had diffuse global LGE (group 2), and 8 had focal patchy or no LGE (group 1). Global native T1, T2, and ECV were significantly higher in groups 1 and 2 than in the control group (native T1: 1384.4 ms vs. 1466.8 ms vs. 1230.5 ms; T2: 53.8 ms vs. 54.2 ms vs. 48.9 ms; and ECV: 36.9% vs. 51.4% vs. 26.0%, respectively; all, p < 0.001). Basal ECV (53.7%) was significantly higher than the mid and apical ECVs (50.1% and 50.0%, respectively; p < 0.001) in group 2. Basal and mid peak radial strains (PRSs) and peak circumferential strains (PCSs) were significantly lower than the apical PRS and PCS, respectively (PRS, 15.6% vs. 16.7% vs. 26.9%; and PCS, -9.7% vs. -10.9% vs. -15.0%; all, p < 0.001). Basal ECV and basal strain (2-dimensional PRS) in group 2 showed a significant negative correlation (r = -0.623, p < 0.001). Group 1 showed no regional ECV differences (basal, 37.0%; mid, 35.9%; and apical, 38.3%; p = 0.184). Conclusion: Quantitative T1 mapping parameters such as native T1 and ECV may help diagnose early CA. ECV, in particular, can reflect regional differences in the amyloid deposition in patients with advanced CA, and increased basal ECV is related to decreased basal strain. Therefore, quantitative CMR parameters may help diagnose CA and determine its severity in patients with or without LGE.

• 복식문화연구
• /
• 제20권6호
• /
• pp.923-936
• /
• 2012

Apparel companies define their target customers to integrate consumers' needs into their product development processes. The sizing standards play a significant role in ready-to-wear garment business. Consumers' body build and sizes are different according to gender, age, and body type. The consumers' morphological feature of the one geographical area has changed with immigration, aging, and lifestyle change. In this study the way of defining body types in the standard garment sizing systems published in USA., UK, Germany, Japan, and Korea were compared. The results of this study show that most of the systems classified the body types by the index value. The chest-waist drop value was used for men's body type classification. Women's body types were defined by hip proportion. The hip-bust drop value was used for it. German and European garment sizing systems provide a wide range of men's body types. US men's garment sizes are developed for very conservative body type. US women's garment sizing system has had clearly defined women's body types. The Misses body types projected in the US garment sizing system had changed as women's waist girth got bigger compared to the past. In 2011 the US Misses sizes were divided into Curvy Misses size and Straight Misses size by the hip-waist drop value. The Curvy Misses sizes have smaller waist girth and larger hip girth than the Straight Misses sizes.

• 유통과학연구
• /
• 제18권4호
• /
• pp.27-37
• /
• 2020

Purpose: This exploratory research is to give managerial implication to sales personal management. This study focused on antecedents of job satisfaction and organizational commitment specially in HRD programs and system by participation and effect toward job. Research design, data and methodology: This research focuses on relationship analysis among job satisfaction, organizational commitment and HRD programs of logistics and sales personnel in Korea. HRD program consider two parts one is participation and other is effect toward job. And three HRD program is included education & training, system and self-directed Learning. This study used 7th HCCP data from KRIVET and 748 employee data is analyzed. SPSS18 is used and frequency, reliability, correlation and regression analysis are conducted. Results: Result shows that job satisfaction is positively affected by education & training participation, HRD system participation and HRD system effect toward job. Organizational commitment is positively affected by education & training participation, HRD system participation, education & training effect toward job and HRD system effect toward job. However self-directed Learning participation negatively affect organizational commitment. Lastly job satisfaction partially mediates between HRD and organizational commitment. Conclusions: Based on the results, this paper provide implication to academic, practical HRD and suggest feature research.

• 한국환경복원기술학회지
• /
• 제19권5호
• /
• pp.11-17
• /
• 2016

The purposes of this research are to estimate area of greenable roof and to monitor maintaining of green roofs using World-View 2 images. The contents of this research are development of World-View 2 application technologies for estimation of green roof area and development of monitoring and maintaining of green roofs using World-View 2 images. The available green roof areas in Gwangjin-gu Seoul, a case for this study, were estimated using digital maps and World-View 2 images. The available green roof area is approximately 12.17% ($2,153,700m^2$) of the total area, and the roof vegetation accounts for 0.46% ($80,660m^2$) of the total area. For verification of the extracted roof vegetation, Vworld 3D Desktop map service was applied. The study results may be used as a decision-making tool by the government and local governments in determining the feasibility of green roof projects. In addition, the project implementer may periodically monitor to see whether roof greening has maintained for efficient management of projects, and a vast amount of World-View 2 images may be regularly used before and after the projects to contribute to sharing of satellite images information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.692-710
• /
• 2013

Conventional interference alignment (IA) for a MIMO interference channel (IFC) requires global and perfect channel state information at transmitter (CSIT) to achieve the optimal degrees of freedom (DoF), which prohibits practical implementation. In order to alleviate the global CSIT requirement caused by the coupled relation among all of IA equations, we propose an IA scheme with a single feedback link of each receiver in a limited feedback environment for a three-user MIMO IFC. The main feature of the proposed scheme is that one of users takes out a fraction of its maximum number of data streams to decouple IA equations for three-user MIMO IFC, which results in a single link feedback structure at each receiver. While for the conventional IA each receiver has to feed back to all transmitters for transmitting the maximum number of data streams. With the assumption of a random codebook, we analyze the upper bound of the average throughput loss caused by quantized channel knowledge as a function of feedback bits. Analytic results show that the proposed scheme outperforms the conventional IA scheme in term of the feedback overhead and the sum rate as well.

• 한국측량학회지
• /
• 제35권5호
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.