소셜 네트워크 분석 기법을 활용한 협업필터링의 특이취향 사용자(Gray Sheep) 문제 해결 (Resolving the 'Gray sheep' Problem Using Social Network Analysis (SNA) in Collaborative Filtering (CF) Recommender Systems)
-
- 지능정보연구
- /
- 제20권2호
- /
- pp.137-148
- /
- 2014
상품 검색시간의 단축과 쇼핑에 투입되는 노력의 감소 등, 온라인 쇼핑이 주는 장점에 대한 긍정적인 인식이 확산되면서 전자상거래(e-commerce)의 중요성이 부각되는 추세이다. 전자상거래 기업들은 고객확보를 위해 다양한 인터넷 고객관계 관리(eCRM) 활동을 전개하고 있는데, 개인화된 추천 서비스의 제공은 그 중 하나이다. 정확한 추천 시스템의 구축은 전자상거래 기업의 성과를 좌우하는 중요한 요소이기 때문에, 추천 서비스의 정확도를 높이기 위한 다양한 알고리즘들이 연구되어 왔다. 특히 협업필터링(collaborative filtering: CF)은 가장 성공적인 추천기법으로 알려져 있다. 그러나 고객이 상품을 구매한 과거의 전자상거래 기록을 바탕으로 미래의 추천을 하기 때문에 많은 단점들이 존재한다. 신규 고객의 경우 유사한 구매 성향을 가진 고객들을 찾기 어렵고 (Cold-Start problem), 상품 수에 비해 구매기록이 부족할 경우 상관관계를 도출할 데이터가 희박하게 되어(Sparsity) 추천성능이 떨어지게 된다. 취향이 독특한 사용자를 뜻하는 'Gray Sheep'에 의한 추천성능의 저하도 그 중 하나이다. 이러한 문제인식을 토대로, 본 연구에서는 소셜 네트워크 분석기법 (Social Network Analysis: SNA)과 협업필터링을 결합하여 데이터셋의 특이 취향 사용자 (Gray Sheep) 문제를 해소하는 방법을 제시한다. 취향이 독특한 고객들의 구매데이터를 소셜 네트워크 분석지표를 활용하여 전체 데이터에서 분리해낸다. 그리고 분리한 데이터와 나머지 데이터인 두 가지 데이터셋에 대하여 각기 다른 유사도 기법과 트레이닝 셋을 적용한다. 이러한 방법을 사용한 추천성능의 향상을 검증하기 위하여 미국 미네소타 대학 GroupLens 연구팀에 의해 수집된 무비렌즈 데이터(http://movielens.org)를 활용하였다. 검증결과, 일반적인 협업필터링 추천시스템에 비하여 이 기법을 활용한 협업필터링의 추천성능이 향상됨을 확인하였다.
Convolutional Neural Network (ConvNet)은 시각적 특징의 계층 구조를 분석하고 학습할 수 있는 대표적인 심층 신경망이다. 첫 번째 신경망 모델인 Neocognitron은 80 년대에 처음 소개되었다. 당시 신경망은 대규모 데이터 집합과 계산 능력이 부족하여 학계와 산업계에서 널리 사용되지 않았다. 그러나 2012년 Krizhevsky는 ImageNet ILSVRC (Large Scale Visual Recognition Challenge) 에서 심층 신경망을 사용하여 시각적 인식 문제를 획기적으로 해결하였고 그로 인해 신경망에 대한 사람들의 관심을 다시 불러 일으켰다. 이미지넷 첼린지에서 제공하는 다양한 이미지 데이터와 병렬 컴퓨팅 하드웨어 (GPU)의 발전이 Krizhevsky의 승리의 주요 요인이었다. 그러므로 최근의 딥 컨볼루션 신경망의 성공을 병렬계산을 위한 GPU의 출현과 더불어 ImageNet과 같은 대규모 이미지 데이터의 가용성으로 정의 할 수 있다. 그러나 이러한 요소는 많은 도메인에서 병목 현상이 될 수 있다. 대부분의 도메인에서 ConvNet을 교육하기 위해 대규모 데이터를 수집하려면 많은 노력이 필요하다. 대규모 데이터를 보유하고 있어도 처음부터 ConvNet을 교육하려면 많은 자원과 시간이 소요된다. 이와 같은 문제점은 전이 학습을 사용하면 해결할 수 있다. 전이 학습은 지식을 원본 도메인에서 새 도메인으로 전이하는 방법이다. 전이학습에는 주요한 두 가지 케이스가 있다. 첫 번째는 고정된 특징점 추출기로서의 ConvNet이고, 두번째는 새 데이터에서 ConvNet을 fine-tuning 하는 것이다. 첫 번째 경우, 사전 훈련 된 ConvNet (예: ImageNet)을 사용하여 ConvNet을 통해 이미지의 피드포워드 활성화를 계산하고 특정 레이어에서 활성화 특징점을 추출한다. 두 번째 경우에는 새 데이터에서 ConvNet 분류기를 교체하고 재교육을 한 후에 사전 훈련된 네트워크의 가중치를 백프로퍼게이션으로 fine-tuning 한다. 이 논문에서는 고정된 특징점 추출기를 여러 개의 ConvNet 레이어를 사용하는 것에 중점을 두었다. 그러나 여러 ConvNet 레이어에서 직접 추출된 차원적 복잡성을 가진 특징점을 적용하는 것은 여전히 어려운 문제이다. 우리는 여러 ConvNet 레이어에서 추출한 특징점이 이미지의 다른 특성을 처리한다는 것을 발견했다. 즉, 여러 ConvNet 레이어의 최적의 조합을 찾으면 더 나은 특징점을 얻을 수 있다. 위의 발견을 토대로 이 논문에서는 단일 ConvNet 계층의 특징점 대신에 전이 학습을 위해 여러 ConvNet 계층의 특징점을 사용하도록 제안한다. 본 논문에서 제안하는 방법은 크게 세단계로 이루어져 있다. 먼저 이미지 데이터셋의 이미지를 ConvNet의 입력으로 넣으면 해당 이미지가 사전 훈련된 AlexNet으로 피드포워드 되고 3개의 fully-connected 레이어의 활성화 틀징점이 추출된다. 둘째, 3개의 ConvNet 레이어의 활성화 특징점을 연결하여 여러 개의 ConvNet 레이어의 특징점을 얻는다. 레이어의 활성화 특징점을 연결을 하는 이유는 더 많은 이미지 정보를 얻기 위해서이다. 동일한 이미지를 사용한 3개의 fully-connected 레이어의 특징점이 연결되면 결과 이미지의 특징점의 차원은 4096 + 4096 + 1000이 된다. 그러나 여러 ConvNet 레이어에서 추출 된 특징점은 동일한 ConvNet에서 추출되므로 특징점이 중복되거나 노이즈를 갖는다. 따라서 세 번째 단계로 PCA (Principal Component Analysis)를 사용하여 교육 단계 전에 주요 특징점을 선택한다. 뚜렷한 특징이 얻어지면, 분류기는 이미지를 보다 정확하게 분류 할 수 있고, 전이 학습의 성능을 향상시킬 수 있다. 제안된 방법을 평가하기 위해 특징점 선택 및 차원축소를 위해 PCA를 사용하여 여러 ConvNet 레이어의 특징점과 단일 ConvNet 레이어의 특징점을 비교하고 3개의 표준 데이터 (Caltech-256, VOC07 및 SUN397)로 실험을 수행했다. 실험결과 제안된 방법은 Caltech-256 데이터의 FC7 레이어로 73.9 %의 정확도를 얻었을 때와 비교하여 75.6 %의 정확도를 보였고 VOC07 데이터의 FC8 레이어로 얻은 69.2 %의 정확도와 비교하여 73.1 %의 정확도를 보였으며 SUN397 데이터의 FC7 레이어로 48.7%의 정확도를 얻었을 때와 비교하여 52.2%의 정확도를 보였다. 본 논문에 제안된 방법은 Caltech-256, VOC07 및 SUN397 데이터에서 각각 기존에 제안된 방법과 비교하여 2.8 %, 2.1 % 및 3.1 %의 성능 향상을 보였다.
The duty shifts of hospital nurses not only affect nurses' physical and mental health but also present various personnel management problems which often result in high turnover rates. In this context a study was carried out from October to November 1995 for a period of two months to find out the status of hospital nurses' duty shift patterns, and preferred duty hours and fixed duty shifts. The study population was 867 RNs working in five general hospitals located in Seoul and its vicinity. The questionnaire developed by the writer was used for data collection. The response rate was 85.9 percent or 745 returns. The SAS program was used for data analysis with the computation of frequencies, percentages and Chi square test. The findings of the study are as follows: 1. General characteristics of the study population: 56 percent of respondents was (25 years group and 76.5 percent were "single": the predominant proportion of respondents was junior nursing college graduates(92.2%) and have less than 5 years nursing experience in hospitals(65.5%). For their future working plan in nursing profession, nearly 50% responded as uncertain The reasons given for their career plan was predominantly 'personal growth and development' rather than financial reasons. 2. The interval for rotations of duty stations was found to be mostly irregular(56.4%) while others reported as weekly(16.1%), monthly(12.9%), and fixed terms(4.6%). 3. The main problems related to duty shifts particularly the evening and night duty nurses reported were "not enough time for the family, " "afraid of security problems after the work when returning home late at night." and "lack of leisure time". "problems in physical and physiological adjustment." "problems in family life." "lack of time for interactions with fellow nurses" etc. 4. The forty percent of respondents reported to have '1-2 times' of duty shift rotations while all others reported that '0 time'. '2-3 times'. 'more than 3 times' etc. which suggest the irregularity in duty shift rotations. 5. The majority(62.8%) of study population found to favor the rotating system of duty stations. The reasons for favoring the rotation system were: the opportunity for "learning new things and personal development." "better human relations are possible. "better understanding in various duty stations." "changes in monotonous routine job" etc. The proportion of those disfavor the rotating 'system was 34.7 percent. giving the reasons of"it impedes development of specialization." "poor job performances." "stress factors" etc. Furthermore. respondents made the following comments in relation to the rotation of duty stations: the nurses should be given the opportunity to participate in the. decision making process: personal interest and aptitudes should be considered: regular intervals for the rotations or it should be planned in advance. etc. 6. For the future career plan. the older. married group with longer nursing experiences appeared to think the nursing as their lifetime career more likely than the younger. single group with shorter nursing experiences (
벼의 생육기간중(生育期間中) 논에서의 수력소비(水力消費)에 관(關)하여 연구(硏究)하였던바 다음과 같은 결론(結論)을 얻었다. 1. 엽면(葉面) 및 주간수면증발(株間水面蒸發) 1) 벼의 엽면증발량(葉面蒸發量)은 조(早), 중(中), 만생종(晩生種) 공(共)히 이앙(移秧)후 점차(漸次) 증가(增加)하다가 수잉기(穗孕期)에 급증(急增)하고 수잉기(穗孕期) 말기(末期)에서 출수개화(出穗開花) 초기(初期)(조생종(早生種)은 제6기(第6期), 중(中), 만생종(晩生種)은 제7기(第7期)에 최대량(最大量)에 달(達)하며 그 후 점감(漸減)한다. 2) 벼의 엽면증발작용(葉面蒸發作用)은 조(早), 중(中), 만생종(晩生種) 모두 제5기(第5期)까지는 별(別) 차이(差異)가 없으며 제6기(第6期)에는 조생종(早生種)이 가장 왕성(旺盛)하고 제7기(第7期) 이후(以後)는 만생종(晩生種)이 계속(繼續) 제일(第一) 왕성(旺盛)하다. 3) 엽면증발(葉面蒸發)이 가장 왕성(旺盛)한 시기(時期)인 제6기(第6期) 조생종(早生種)와 제7기(第7期)(중(中), 만생종(晩生種)의 엽면증발량(葉面蒸發量)은 전(全) 생육기간(生育期間)의 총엽면증발량(總葉面蒸發量)의
The objective of this research is to test the feasibility of developing a statewide truck traffic forecasting methodology for Wisconsin by using Origin-Destination surveys, traffic counts, classification counts, and other data that are routinely collected by the Wisconsin Department of Transportation (WisDOT). Development of a feasible model will permit estimation of future truck traffic for every major link in the network. This will provide the basis for improved estimation of future pavement deterioration. Pavement damage rises exponentially as axle weight increases, and trucks are responsible for most of the traffic-induced damage to pavement. Consequently, forecasts of truck traffic are critical to pavement management systems. The pavement Management Decision Supporting System (PMDSS) prepared by WisDOT in May 1990 combines pavement inventory and performance data with a knowledge base consisting of rules for evaluation, problem identification and rehabilitation recommendation. Without a r.easonable truck traffic forecasting methodology, PMDSS is not able to project pavement performance trends in order to make assessment and recommendations in the future years. However, none of WisDOT's existing forecasting methodologies has been designed specifically for predicting truck movements on a statewide highway network. For this research, the Origin-Destination survey data avaiiable from WisDOT, including two stateline areas, one county, and five cities, are analyzed and the zone-to'||'&'||'not;zone truck trip tables are developed. The resulting Origin-Destination Trip Length Frequency (00 TLF) distributions by trip type are applied to the Gravity Model (GM) for comparison with comparable TLFs from the GM. The gravity model is calibrated to obtain friction factor curves for the three trip types, Internal-Internal (I-I), Internal-External (I-E), and External-External (E-E). ~oth "macro-scale" calibration and "micro-scale" calibration are performed. The comparison of the statewide GM TLF with the 00 TLF for the macro-scale calibration does not provide suitable results because the available 00 survey data do not represent an unbiased sample of statewide truck trips. For the "micro-scale" calibration, "partial" GM trip tables that correspond to the 00 survey trip tables are extracted from the full statewide GM trip table. These "partial" GM trip tables are then merged and a partial GM TLF is created. The GM friction factor curves are adjusted until the partial GM TLF matches the 00 TLF. Three friction factor curves, one for each trip type, resulting from the micro-scale calibration produce a reasonable GM truck trip model. A key methodological issue for GM. calibration involves the use of multiple friction factor curves versus a single friction factor curve for each trip type in order to estimate truck trips with reasonable accuracy. A single friction factor curve for each of the three trip types was found to reproduce the 00 TLFs from the calibration data base. Given the very limited trip generation data available for this research, additional refinement of the gravity model using multiple mction factor curves for each trip type was not warranted. In the traditional urban transportation planning studies, the zonal trip productions and attractions and region-wide OD TLFs are available. However, for this research, the information available for the development .of the GM model is limited to Ground Counts (GC) and a limited set ofOD TLFs. The GM is calibrated using the limited OD data, but the OD data are not adequate to obtain good estimates of truck trip productions and attractions .. Consequently, zonal productions and attractions are estimated using zonal population as a first approximation. Then, Selected Link based (SELINK) analyses are used to adjust the productions and attractions and possibly recalibrate the GM. The SELINK adjustment process involves identifying the origins and destinations of all truck trips that are assigned to a specified "selected link" as the result of a standard traffic assignment. A link adjustment factor is computed as the ratio of the actual volume for the link (ground count) to the total assigned volume. This link adjustment factor is then applied to all of the origin and destination zones of the trips using that "selected link". Selected link based analyses are conducted by using both 16 selected links and 32 selected links. The result of SELINK analysis by u~ing 32 selected links provides the least %RMSE in the screenline volume analysis. In addition, the stability of the GM truck estimating model is preserved by using 32 selected links with three SELINK adjustments, that is, the GM remains calibrated despite substantial changes in the input productions and attractions. The coverage of zones provided by 32 selected links is satisfactory. Increasing the number of repetitions beyond four is not reasonable because the stability of GM model in reproducing the OD TLF reaches its limits. The total volume of truck traffic captured by 32 selected links is 107% of total trip productions. But more importantly, ~ELINK adjustment factors for all of the zones can be computed. Evaluation of the travel demand model resulting from the SELINK adjustments is conducted by using screenline volume analysis, functional class and route specific volume analysis, area specific volume analysis, production and attraction analysis, and Vehicle Miles of Travel (VMT) analysis. Screenline volume analysis by using four screenlines with 28 check points are used for evaluation of the adequacy of the overall model. The total trucks crossing the screenlines are compared to the ground count totals. L V/GC ratios of 0.958 by using 32 selected links and 1.001 by using 16 selected links are obtained. The %RM:SE for the four screenlines is inversely proportional to the average ground count totals by screenline .. The magnitude of %RM:SE for the four screenlines resulting from the fourth and last GM run by using 32 and 16 selected links is 22% and 31 % respectively. These results are similar to the overall %RMSE achieved for the 32 and 16 selected links themselves of 19% and 33% respectively. This implies that the SELINICanalysis results are reasonable for all sections of the state.Functional class and route specific volume analysis is possible by using the available 154 classification count check points. The truck traffic crossing the Interstate highways (ISH) with 37 check points, the US highways (USH) with 50 check points, and the State highways (STH) with 67 check points is compared to the actual ground count totals. The magnitude of the overall link volume to ground count ratio by route does not provide any specific pattern of over or underestimate. However, the %R11SE for the ISH shows the least value while that for the STH shows the largest value. This pattern is consistent with the screenline analysis and the overall relationship between %RMSE and ground count volume groups. Area specific volume analysis provides another broad statewide measure of the performance of the overall model. The truck traffic in the North area with 26 check points, the West area with 36 check points, the East area with 29 check points, and the South area with 64 check points are compared to the actual ground count totals. The four areas show similar results. No specific patterns in the L V/GC ratio by area are found. In addition, the %RMSE is computed for each of the four areas. The %RMSEs for the North, West, East, and South areas are 92%, 49%, 27%, and 35% respectively, whereas, the average ground counts are 481, 1383, 1532, and 3154 respectively. As for the screenline and volume range analyses, the %RMSE is inversely related to average link volume. 'The SELINK adjustments of productions and attractions resulted in a very substantial reduction in the total in-state zonal productions and attractions. The initial in-state zonal trip generation model can now be revised with a new trip production's trip rate (total adjusted productions/total population) and a new trip attraction's trip rate. Revised zonal production and attraction adjustment factors can then be developed that only reflect the impact of the SELINK adjustments that cause mcreases or , decreases from the revised zonal estimate of productions and attractions. Analysis of the revised production adjustment factors is conducted by plotting the factors on the state map. The east area of the state including the counties of Brown, Outagamie, Shawano, Wmnebago, Fond du Lac, Marathon shows comparatively large values of the revised adjustment factors. Overall, both small and large values of the revised adjustment factors are scattered around Wisconsin. This suggests that more independent variables beyond just 226; population are needed for the development of the heavy truck trip generation model. More independent variables including zonal employment data (office employees and manufacturing employees) by industry type, zonal private trucks 226; owned and zonal income data which are not available currently should be considered. A plot of frequency distribution of the in-state zones as a function of the revised production and attraction adjustment factors shows the overall " adjustment resulting from the SELINK analysis process. Overall, the revised SELINK adjustments show that the productions for many zones are reduced by, a factor of 0.5 to 0.8 while the productions for ~ relatively few zones are increased by factors from 1.1 to 4 with most of the factors in the 3.0 range. No obvious explanation for the frequency distribution could be found. The revised SELINK adjustments overall appear to be reasonable. The heavy truck VMT analysis is conducted by comparing the 1990 heavy truck VMT that is forecasted by the GM truck forecasting model, 2.975 billions, with the WisDOT computed data. This gives an estimate that is 18.3% less than the WisDOT computation of 3.642 billions of VMT. The WisDOT estimates are based on the sampling the link volumes for USH, 8TH, and CTH. This implies potential error in sampling the average link volume. The WisDOT estimate of heavy truck VMT cannot be tabulated by the three trip types, I-I, I-E ('||'&'||'pound;-I), and E-E. In contrast, the GM forecasting model shows that the proportion ofE-E VMT out of total VMT is 21.24%. In addition, tabulation of heavy truck VMT by route functional class shows that the proportion of truck traffic traversing the freeways and expressways is 76.5%. Only 14.1% of total freeway truck traffic is I-I trips, while 80% of total collector truck traffic is I-I trips. This implies that freeways are traversed mainly by I-E and E-E truck traffic while collectors are used mainly by I-I truck traffic. Other tabulations such as average heavy truck speed by trip type, average travel distance by trip type and the VMT distribution by trip type, route functional class and travel speed are useful information for highway planners to understand the characteristics of statewide heavy truck trip patternS. Heavy truck volumes for the target year 2010 are forecasted by using the GM truck forecasting model. Four scenarios are used. Fo~ better forecasting, ground count- based segment adjustment factors are developed and applied. ISH 90 '||'&'||' 94 and USH 41 are used as example routes. The forecasting results by using the ground count-based segment adjustment factors are satisfactory for long range planning purposes, but additional ground counts would be useful for USH 41. Sensitivity analysis provides estimates of the impacts of the alternative growth rates including information about changes in the trip types using key routes. The network'||'&'||'not;based GMcan easily model scenarios with different rates of growth in rural versus . . urban areas, small versus large cities, and in-state zones versus external stations. cities, and in-state zones versus external stations.