• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.386-398
• /
• 2019

The transmission capacity of transmission lines is affected by environmental parameters such as ambient temperature, wind speed, wind direction and so on. The environmental parameters can be measured by the installed measuring devices. However, it is impossible to install the environmental measuring devices throughout the line, especially considering economic cost of power grid. Taking into account the limited number of measuring devices and the distribution characteristics of environment parameters and transmission lines, this paper first studies the environmental parameter estimating method of inverse distance weighted interpolation and ordinary Kriging interpolation. Dynamic thermal rating of transmission lines based on IEEE standard and CIGRE standard thermal equivalent equation is researched and the key parameters that affect the load capacity of overhead lines is identified. Finally, the distributed thermal rating of transmission line is realized by using the data obtained from China meteorological data network. The cost of the environmental measurement device is reduced, and the accuracy of dynamic rating is improved.

• Asia pacific journal of information systems
• /
• v.25 no.3
• /
• pp.579-596
• /
• 2015

Many studies have focused on the prediction of corporate credit rating using various data mining techniques. One of the most frequently used algorithms is support vector machines (SVM), and recently, novel techniques such as SVM+ and SVM+MTL have emerged. This paper intends to show the applicability of such new techniques to multi-classification and corporate credit rating and compare them with conventional SVM regarding prediction performance. We solve multi-class SVM+ and SVM+MTL problems by constructing several binary classifiers. Furthermore, to demonstrate the robustness and outstanding performance of SVM+MTL algorithm over other techniques, we utilized four typical multi-class processing methods in our experiments. The results show that SVM+MTL outperforms both conventional SVM and novel SVM+ in predicting corporate credit rating. This study contributes to the literature by showing the applicability of new techniques such as SVM+ and SVM+MTL and the outperformance of SVM+MTL over conventional techniques. Thus, this study enriches solving techniques for addressing multi-class problems such as corporate credit rating prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.75-82
• /
• 2023

In collaborative filtering systems, the item rating prediction values calculated by the systems are very important for customer satisfaction with the recommendation list. In the time-aware system, predictions are calculated by reflecting the rating time of users, and in general, exponentially lower weights are assigned to past rating values. In this study, to find out whether the influence of rating time on the rating value varies according to various factors, the correlation between user rating value and rating time is investigated by the degree of user rating activity, the popularity of items, and item genres. As a result, using two types of public datasets, especially in the sparse dataset, significantly different correlation index values were obtained for each factor. Therefore, it is confirmed that the influence weight of the rating time on the rating prediction value should be set differently in consideration of the above-mentioned various factors as well as the density of the dataset.

• Journal of the Korean Society of Food Culture
• /
• v.16 no.1
• /
• pp.20-26
• /
• 2001

The rating instrument to evaluate the quality of nutrition information websites was developed and ten websites which were maintained by nutrition expert(s) and frequently linked to other related sites were evaluated. The rating instrument with 15 questions on credibility, content, purpose, and design was developed. Eleven college students majoring in Food and Nutrition rated each question as 'Yes', 'No', 'Cannot tell' while visiting each site. The questions rated most often as 'Yes' were 'Is it capable for a user to interact with a responsible person for the site?', 'Is the information provided by nutrition expert?', 'Does the information fit in with dietary guideline?' in the order. The questions rated most often as 'No' were 'Is the source of the information indicated?', 'Is the purpose of the site stated?', and 'Is an internal search engine working?', indicating these categories need betterment. The questions rated most often as 'Cannot tell' were 'Is the information current?', 'Is the information provider credible?', indicating that these may be difficult questions for college students to evaluate. Individuals or institutions who are providing nutrition information on the internet now or plan to provide later are expected to consider the problems pointed out in this study, and offer highly qualified information to the users in an effective way. Various rating instruments to evaluate the quality of nutrition information websites can be developed based on a variety of criteria. It is, however, to be desired that a standardized rating instrument would be developed by a leading group of nutrition experts, and the results of site review with the instrument be open to the public in order to improve the quality of Korean nutrition information on the internet.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6097-6120
• /
• 2019

Online consumer reviews (OCRs) provide product information and recommendations especially pictures in reviews depict the true information about the product. This study investigates the influence of pictured reviews on online seller (for a particular product of a seller) rating with moderating effect of price, brand type (foreign vs local), goods type (experience vs search), and brand familiarity. Multiple robust linear regression analysis with moderation interaction and quadratic effect used to explain the relationship of the explanatory variables with the criterion variable. We collected cross-sectional data from the two most renowned Chinese online shopping platforms (B2C) of total 15,621 product links. Results show that higher number of reviews with a low ratio of picture reviews response negative effect on rating, whereas the lower number of reviews with a high ratio of picture reviews response positive effect on the rating. In overall picture in the reviews improve the online seller product rating. For the moderation effect, results show that price and brand familiarity have a positive interaction effect on the relation of pictured reviews and rating whereas experience goods have less negative effect comparing search goods. Finally, local brand has less negative interaction effect comparing foreign brand to pictured reviews and rating.

• The Korean Journal of Financial Management
• /
• v.22 no.2
• /
• pp.107-133
• /
• 2005

The object of this study is to examine the informational effect of the rating change announcement on the capital market. For this study, daily stock prices from January 1993 to February 2001 and daily bond prices from July 2000 to February 2001, for the bond market are used. In the stock market, we could not observe any statistically significant stock price reaction to rate change announcements from July 2000 to February 2001. However, if rating agencies announce more than two degradation for the period of January 1993 to February 2001, statistically negative significant stock price reactions are observed. On the other hand, there is no statistically significant stock price reaction to any other rating change announcement. In the bond market, there is no statistically test on the bond price reaction, but the general directions of bond price movements are consistent with the effect we can expect from rating change announcements. Generally, when the rating agencies degraded more than two grades at once, a cumulative abnormal returns move negatively during the overall period. In this case, we can say that rating agencies' role is to confirm information or investor's expectations. However, for the other cases, we could not observe my significant movement before or on the event data.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.571-578
• /
• 2005

Corporate credit rating analysis has drawn a lot of research interests in previous studies, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper applies support vector machines (SVMs) to the corporate credit rating problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, the researcher uses a grid-search technique using 5-fold cross-validation to find out the optimal parameter values of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM, the researcher compares its performance with those of multiple discriminant analysis (MDA), case-based reasoning (CBR), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.175-183
• /
• 2012

The study investigates peer rating, one of the most commonly used sources of performance rating other than those of supervisors. On the whole, both field and laboratory studies indicate that peer assessment is a valid and reliable evaluation procedure, but on average, peer rating is not usually accurate. The aim of the investigation is to explore the relationship of beliefs and attitude about the performance appraisal system as well as a dispositional characteristic as self-monitoring with rating behavior. In particular, the study tests whether the relationship between rating context variables-appraisal self efficacy and appraisal validity- and rating behavior depends in part on the personality of the rater. Data from 445 undergraduate students are analyzed for hypotheses testing. The study finds evidences that the high on appraisal self efficacy and appraisal validity are more likely to affect discriminating rating tendency and to reduce rating level. Results also show that self-monitoring make the moderating effects between contextual factors and rating behaviors. Some implications, future research directions, and limitations are discussed.

• Information Systems Review
• /
• v.18 no.3
• /
• pp.155-183
• /
• 2016

Research on personalized recommender service that uses big data has gained considerable attention given the increasing volume of contents being created. This development indicates the need for service providers to collect personal information and content rating data to personalize content recommendations. Previous studies on this topic proposed algorithms to offer improved recommendations using minimal rating data or service designs and increase the number of ratings. However, limited studies have been conducted on the factors that motivate the ratings input of users, as well as the factors that influence their continuous usage of recommender service. The present study explored the factors that motivate users to enter ratings by conducting in-depth interviews with users who use recommender services. The meanings of these ratings were also explored. Results show that the meaning and usage range of ratings differed based on the stage of a user's with utilization of the service. When users input an initial rating, they treat such a rating as a database to save the impression of a past experience. Such a rating is then used as a tool to reflect the current feeling and thoughts of a user. In the end, users were not only interested in their own rating system, but they also actively sought out the meaning of the rating systems of others and utilized them. Users also expressed mistrust in the recommendations of the service because they were aware of the limitation of the algorithms. This study identified a number of practical implications regarding recommender services.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10B
• /
• pp.957-964
• /
• 2003

The circulation of unwholesome information such as obscene and violent information is gradually increasing based on the rapid expansion of information communications infrastructure. Those kinds of information are harmful to the adolescents and even cause social problems so that active countermeasure is requited. In order to cope with the spread of unwholesome information, appropriate regulating methods are absolutely in need by establishing or revising information communications-related laws. In this paper, we had analyzed domestic and foreign programs with existing harmful information blocking method, and then designed and implemented a selective blocking program based on Platform for Internet Contents Selection(PICS) by using selective blocking technology based on Internet contents rating system. We also proposed a compromised rating system blocking method that consists of selective filtering function by age and the popular blocking list. The proposed system has advantages in that there would be no increase in network load resulting from blocking list update and inquiry, it is possible to perform active selective filtering considering user's age, and it may introduce self-imposed rating.