• Asia pacific journal of information systems
• /
• 제17권4호
• /
• pp.187-206
• /
• 2007

The development of computer and information technology has been combined with the information superhighway internet infrastructure, so information widely spreads not only in special fields but also in the daily lives of people. Information ubiquity influences the traditional way of transaction, and leads a new E-commerce which distinguishes from the existing E-commerce. Not only goods as physical but also service as non-physical come into E-commerce. As the scale of E-Commerce is being enlarged as well. It keeps people from finding information they want. Recommender systems are now becoming the main tools for E-Commerce to mitigate the information overload. Recommender systems can be defined as systems for suggesting some Items(goods or service) considering customers' interests or tastes. They are being used by E-commerce web sites to suggest products to their customers who want to find something for them and to provide them with information to help them decide which to purchase. There are several approaches of recommending goods to customer in recommender system but in this study, the main subject is focused on collaborative filtering technique. This study presents a possibility of pre-evaluation for the prediction performance of customer's preference in collaborative filtering before the process of customer's preference prediction. Pre-evaluation for the prediction performance of each customer having low performance is classified by using the statistical features of ratings rated by each customer is conducted before the prediction process. In this study, MovieLens 100K dataset is used to analyze the accuracy of classification. The classification criteria are set by using the training sets divided 80% from the 100K dataset. In the process of classification, the customers are divided into two groups, classified group and non classified group. To compare the prediction performance of classified group and non classified group, the prediction process runs the 20% test set through the Neighborhood Based Collaborative Filtering Algorithm and Correspondence Mean Algorithm. The prediction errors from those prediction algorithm are allocated to each customer and compared with each user's error. Research hypothesis : Two research hypotheses are formulated in this study to test the accuracy of the classification criterion as follows. Hypothesis 1: The estimation accuracy of groups classified according to the standard deviation of each user's ratings has significant difference. To test the Hypothesis 1, the standard deviation is calculated for each user in training set which is divided 80% from MovieLens 100K dataset. Four groups are classified according to the quartile of the each user's standard deviations. It is compared to test the estimation errors of each group which results from test set are significantly different. Hypothesis 2: The estimation accuracy of groups that are classified according to the distribution of each user's ratings have significant differences. To test the Hypothesis 2, the distributions of each user's ratings are compared with the distribution of ratings of all customers in training set which is divided 80% from MovieLens 100K dataset. It assumes that the customers whose ratings' distribution are different from that of all customers would have low performance, so six types of different distributions are set to be compared. The test groups are classified into fit group or non-fit group according to the each type of different distribution assumed. The degrees in accordance with each type of distribution and each customer's distributions are tested by the test of ${\chi}^2$ goodness-of-fit and classified two groups for testing the difference of the mean of errors. Also, the degree of goodness-of-fit with the distribution of each user's ratings and the average distribution of the ratings in the training set are closely related to the prediction errors from those prediction algorithms. Through this study, the customers who have lower performance of prediction than the rest in the system are classified by those two criteria, which are set by statistical features of customers ratings in the training set, before the prediction process.

• 한국ITS학회 논문지
• /
• 제3권1호
• /
• pp.31-44
• /
• 2004

최근 몇 년간 도시교통문제의 해결책으로 부각되어온 지능형교통체계(ITS : Intelligent Transport System)의 한 분야로 첨단여행자 정보체계(ATIS : Advanced Travellers Information System)는 자동차에 장착된 항법장치(CNS)를 통해 운전자에게 원하는 목적지까지 최적경로를 제공하거나 경로에 대한 통행시간 정보를 제공 또는 예측해 주는 시스템이다. 본 연구에서는 이러한 최적경로 제공이나 통행시간 예측에 있어 좀 더 효율적인 통행시간 예측모형을 개발하고자 하였다. 현재까지의 통행시간 예측은 운전자가 통행을 시작할 때의 교통상황에 대한 정보이기 때문에 운전 중에 달라지는 교통상황을 반영할 수 없어 이로 인해 운전자가 경험하는 통행시간과 큰 차이를 발생시킬 수 있다. 본 연구에서는 이러한 불합리적인 예측시스템을 개선시킬 수 있는 예측된(predicted) 통행시간 예측 모형을 개발하고자 하였다. 이를 위해 우선 통행시간 예측모형을 특정링크에 적용시켜 모형들의 예측치와 실제 통행시간을 비교하여 교통량 흐름 패턴에 따라 어느 모형이 적합한지, 또 예측시간이 달라짐에 따라 모형들의 적합도와 첨두와 비첨두시 예측시간 간격에 따라 예측치와 실측치의 오차율을 알아보았다, 이를 통해 선정된 확률과정 모형과 칼만 필터링 예측모형을 서울시의 4개축에 대해서 다시 적용해 보았다. 그 결과 단기통행시간 예측에 있어서는 칼만필터링모형이, 장기 통행시간 예측에 있어서는 확률과정 모형이 통행시간 예측에 있어 우수한 모형임을 밝혀냈다. 마지막으로 서울시 28개 교통축의 5분 후 통행시간 예측에 칼만필터링 모형을 이용하여 오차분석을 적용하여 보았다. 그 결과 칼만필터링 모형이 신뢰할 만한 오차율을 보였다.

• 한국정보전자통신기술학회논문지
• /
• 제16권5호
• /
• pp.325-330
• /
• 2023

본 논문은 머신러닝을 활용하여 교량 데이터 설계 시 기존 엔지니어의 구조해석결과 또는 경험 및 주관에 따라 슬래브 두께를 예측하여 왔던 프로세스를 머신러닝 기법을 적용하여 디지털 기반 의사결정이 가능하도록 제시한다. 본 연구에서는 슬래브 두께 선정을 구조해석 외에 머신러닝 기법을 활용하여 엔지니어에게 가이드 값을 제공하게 함으로써 신뢰성 있는 설계 환경을 구축하고자 한다. 교량 데이터 중 가장 많은 비중을 차지하고 있는 거더교를 기준으로 상부구조물 중 슬래브 두께를 예측하기 위한 예측모델 프로세스를 정의 하였다. 각 프로세스 별 예측 값을 산출하기 위하여 다양한 머신러닝 모델 (Linear Regress, Decision Tree, Random Forest, Muliti-layer Perceptron)을 프로세스별 경합하여 최적의 모델을 도출하였다. 본 연구를 통해 기존 구조해석을 통해서만 슬래브 두께 예측을 하였던 영역에 머신러닝 기법의 적용 가능성을 확인하였으며 정확도 또한 95.4%를 도출하였다, 향후 프로세스 확장 및 데이터를 지속 확보하여 예측모델 정확도를 향상시킨다면 공사 환경에 머신러닝 모델이 지속 활용될 수 있을 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• 통합자연과학논문집
• /
• 제12권4호
• /
• pp.105-115
• /
• 2019

In this paper, a prediction system is proposed to control the brightness of smart street lamps by predicting the moving path through the reduction of consumption power and information of pedestrian's past moving direction while meeting the function of existing smart street lamps. The brightness of smart street lamps is adjusted by utilizing the walk tracking vector and soft hand-off characteristics obtained through the motion sensing sensor of smart street lamps. In addition, the motion vector is used to analyze and predict the pedestrian path, and the GPU is used for high-speed computation. Pedestrians were detected using adaptive Gaussian mixing, weighted difference imaging, and motion vectors, and motions of pedestrians were analyzed using the extracted motion vectors. The preprocessing process using linear interpolation is performed to improve the performance of the proposed prediction system. Fuzzy prediction system and neural network prediction system are designed in parallel to improve efficiency and rough set is used for error correction.

• 한국컴퓨터정보학회논문지
• /
• 제22권10호
• /
• pp.9-17
• /
• 2017

The student dropout prediction is an indispensable for many intelligent systems to measure the educational system and success rate of all university. Therefore, in this paper, we propose an intelligent dropout prediction system that minimizes the situation by adopting the proactive process through an effective model that predicts the students who are at risk of dropout. In this paper, the main data sets for students dropout predictions was used as questionnaires and university information. The questionnaire was constructed based on theoretical and empirical grounds about factor affecting student's performance and causes of dropout. University Information included student grade, interviews, attendance in university life. Through these data sets, the proposed dropout prediction model techniques was classified into the risk group and the normal group using statistical methods and Naive Bays algorithm. And the intelligence dropout prediction system was constructed by applying the proposed dropout prediction model. We expect the proposed study would be used effectively to reduce the students dropout in university.

• Interdisciplinary Bio Central
• /
• 제4권4호
• /
• pp.14.1-14.6
• /
• 2012

Splice site prediction in DNA sequence is a basic search problem for finding exon/intron and intron/exon boundaries. Removing introns and then joining the exons together forms the mRNA sequence. These sequences are the input of the translation process. It is a necessary step in the central dogma of molecular biology. The main task of splice site prediction is to find out the exact GT and AG ended sequences. Then it identifies the true and false GT and AG ended sequences among those candidate sequences. In this paper, we survey research works on splice site prediction based on support vector machine (SVM). The basic difference between these research works is nucleotide encoding technique and SVM kernel selection. Some methods encode the DNA sequence in a sparse way whereas others encode in a probabilistic manner. The encoded sequences serve as input of SVM. The task of SVM is to classify them using its learning model. The accuracy of classification largely depends on the proper kernel selection for sequence data as well as a selection of kernel parameter. We observe each encoding technique and classify them according to their similarity. Then we discuss about kernel and their parameter selection. Our survey paper provides a basic understanding of encoding approaches and proper kernel selection of SVM for splice site prediction.

• 환경영향평가
• /
• 제16권6호
• /
• pp.407-419
• /
• 2007

This study investigated the predicted and abserved outflow of groundwater which occurred during tunnel constructions. Among the 586 road construction projects from 1986 to 2006, 4 route 25 tunnel construction areas and 26 waste water treatment facilities under construction were studied. Most of the tunnel outflow prediction in EIA (Environmental Impact Assessment) process have been classified into the 17 types of units depending on the assessor's options, which have not conformed to the request of the residents and non government organizations. The investigation results showed that the outflow of underground water in tunnel construction areas averaged about $0.133m^3/km{\cdot}min$ with the maximum $0.386m^3/km{\cdot}min$, and that the outflow mostly occurred in the early stage of tunnel excavation and diminished gradually. The prediction of outflow of underground water in the EIA process showed excessive results compared to observed outflow, the even 51.7 times. Consequently for more realistic prediction, current EIA method for prediction of outflow of underground water in tunnel construction areas has to adopt numerical methods coupled with hydraulics and geologic informations from unit methods of present time.

• Journal of Advanced Marine Engineering and Technology
• /
• 제36권1호
• /
• pp.85-93
• /
• 2012

본 연구에서는 용접부의 형상을 고려하여 머플러의 피로수명을 예측하는 프로세스를 개발하였다. 피로수명 예측 프로세스 개발을 위해 머플러의 굽힘 피로시험을 진행한 후 M-N선도를 획득하고, 파손이 발생한 용접부의 형상을 모델링 한 후 정적하중해석을 실시하고, 해석결과를 이용하여 응력집중계수를 구하였다. 응력집중계수는 피로노치계수를 구하는데 사용되며, 이를 바탕으로 피로수명을 예측하였다. 시험결과와 예측결과의 비교를 통해서 피로수명 예측의 타당성을 검증하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제12권4호
• /
• pp.305-317
• /
• 2011

This paper presents an overview on flutter boundary prediction in tests which is principally based on a system stability measure, named Jury's stability criterion, defined in the discrete-time domain, accompanied with the use of autoregressive moving-average (AR-MA) representation of a sampled sequence of wing responses excited by continuous air turbulences. Stability parameters applicable to two-, three- and multi-mode systems, that is, the flutter margin for discrete-time systems derived from Jury's criterion are also described. Actual applications of these measures to flutter tests performed in subsonic, transonic and supersonic wind tunnels, not only stationary flutter tests but also a nonstationary one in which the dynamic pressure increased in a fixed rate, are presented. An extension of the concept of nonstationary process approach to an analysis of flutter prediction of a morphing wing for which the instability takes place during the process of structural morphing will also be mentioned. Another extension of analytical approach to a multi-mode aeroelastic system is presented, too. Comparisons between the prediction based on the digital techniques mentioned above and the traditional damping method are given. A future possible application of the system stability approach to flight test will be finally discussed.