• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.

• Journal of the Korea Management Engineers Society
• /
• v.23 no.4
• /
• pp.165-177
• /
• 2018

Smart technology has been utilized in various fields of all kinds of industries. Manufacturing industry has built its smart technology environment appropriate for its manufacturing fields in order to strengthen its manufacturing performance and competitiveness. The advance of smart technology for manufacturing industry needs to efficiently produce products, and response customer's demands and services in a global industrial environment. The smart technology capability of manufacturing fields is very crucial for the innovative production and efficient operation activities, and for efficient advancement of the manufacturing performance. We have necessitated a scientific and objective method that can gauge a smart technology ability in order to manage and strengthen the smart technology ability of manufacturing fields. This research provides a comprehensive framework that can rationally gauge the smart technology capability of manufacturing fields for effectively managing and advancing their smart technology capabilities. In this research, we especially develop a structural framework that can gauge the smart technology capability for a smart factory of manufacturing fields, with verifying by reliability analysis and factor analysis based on previous literature. This study presents a 13-item framework that can measure the smart technology capability for a smart factory of manufacturing fields in a smart technology perspective.

• Journal of Korean Society for Quality Management
• /
• v.49 no.1
• /
• pp.47-60
• /
• 2021

Purpose: This study proposes methods and procedures for evaluating imaging security systems quality of cabinet x-ray screening system to enhance performance certification technology. Also, conducted a comparative analysis of the literature of test-kit for imaging security quality evaluation. Methods: Comparative analysis of the test-kits and related documents for image quality assessment of cabinet x-ray screening equipment. This allows assessment items were selected and the methods for each assessment item were proposed. In addition, the configuration method of the assessment team was established by applying the technology readiness assessment(TRA). Results: Four of the assessment items were selected when estimate image quality by a comparative analysis of literature. For each assessment item, the evaluation method and minimum level of availability were determined. Finally, this paper proposes an imaging quality assessment of cabinet X-ray imaging security systems. Conclusion: Development of imaging security systems evaluation procedures for cabinet X-ray screening systems can be help improve performance certification of aviation security equipment.

• Health Policy and Management
• /
• v.3 no.1
• /
• pp.84-101
• /
• 1993

The current method of rate adjustment is based on the evaluation of the financial performance of hospitals. The method has the disadvantages such as too complicated, expensive process as well as low reliability due to small sample size. This study, therefore, develops a new model for the rate adjustment with the use of the composite index. In addition to that, it examines the validity of the model by comparing the result of the new method with that of the conventional method. The idea of the new model comes from the Medicare Economic Index(MEI) on which physician fees for the Medicare patients are adjusted periodically in the United States. Medical costs are classified into three groups : labor costs, materials and other expenses. Labor costs are subdivided into physicians and other personnels. Materials are subdivided into drugs and others. Other expenses are subdivided into 5 items. Macro economic indices are selected for each cost item in order to reflect the cost inflation during the specific period. Then the composite index which integrate all items according to the ration of each item in the total costs is calculated. The result from the application of empirical data to the new model is very similar to that of the current method. Furthermore, this method is very simple and also to easy to get social concensus. This model can be replaced the current method based on the analysis of the financial performance for the adjustment of medical fees.

• Journal of Korean Institute of Industrial Engineers
• /
• v.24 no.2
• /
• pp.279-285
• /
• 1998

A quality inspection procedure interchangeably using the performance and screening variables is proposed. At the start of the inspection, the performance variable is measured for all items. As soon as i consecutive items are found to be free of defects, the screening variable is measured instead of the performance variable. If an item is rejected, the inspection based on the performance variable is resumed. All nonconforming items found in the inspection are either reworked or replaced with conforming items. It is assumed that the performance variable is dichotomous, and the screening variable given the performance variable is normally distributed with known mean and variance. The average outgoing quality (AOQ) expression is derived, and the methods of finding the inspection procedure with a specified average outgoing quality limit (AOQL) are presented.

• 한국경영정보학회:학술대회논문집
• /
• 2007.11a
• /
• pp.23-28
• /
• 2007

In e-Business environment, end-user e-Business capability is necessitated for performing his or her given tasks and improving his or her business performance in an enterprise of e-Business environment. An instrument of an end-user e-Business competency is extracted from the major components of a general competency. Through a pilot test, this study performed factor analysis, and proposed a 16-item instrument that can measure an end-user e-Business competency in e-Business environment. The application of the instrument is confirmed by applying it to measuring e-Business competency of end-users in an enterprise of e-Business environment and by presenting the measurement results for them.

• Journal of Korean Institute of Industrial Engineers
• /
• v.30 no.2
• /
• pp.84-92
• /
• 2004

A process control procedure is proposed when 100% inspection is performed in a process with excellent capability. Only the incomplete measurement data is assumed to be available, i.e. the specific measurement value of the quality characteristic is not available for each item but it can be determined to be smaller or larger than any prescribed value. In the suggested model, a signal limit is introduced to determine whether the process under study is in control or not. If the quality characteristic of an incoming item exceeds the upper signal or the lower signal limit, the process is determined to be stopped or not by comparing the number of consecutively accepted items with a predetermined threshold number. The procedure is designed based on the type I and II errors. The performance of the model is evaluated by the expected number of items produced under the in-control and out-of-control states until the process is stopped.

• Industrial Engineering and Management Systems
• /
• v.13 no.4
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.3
• /
• pp.29-39
• /
• 2009

In an environment of global competition, the success of a manufacturing corporation is directly related to how it plans and executes production in particular as well as to the optimization level of its process in general. This paper proposes a production planning algorithm for the Multi-Level, multi-item Capacitated Lot Sizing Problem (MLCLSP) in supply chain network considering back-order. MLCLSP corresponds to a mixed integer programming (MIP) problem and is NP-hard. Therefore, this paper proposes an effective algorithm, GRHS (GRASP-based Rolling Horizon Search) that solves this problem within reasonable computational time and evaluates its performance under a variety of problem scenarios.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.671-674
• /
• 2006

Due to the stricter requests of the human perception of images, many industrial standards such as TCO'03 have been made to survey the Flat Panel Displays (FPD) nowadays. The angular-dependence luminance uniformity is an important item to evaluate the performance of FPD. In this article, we focus on the above test item base on TCO'03 standard in the case of vertical direction of ${\pm}15^{\circ}$. With controlling the driving voltage toward the liquid crystals of TN-type TFT-LCD, there exists a voltage-driving range which can achieve the value of the $L_{max}/L_{min}$ at ${\pm}15^{\circ}\;{\leq}1.7$ readily. Both experiment and simulation have been well analysis.