• 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.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.2
• /
• pp.114-126
• /
• 2009

In this paper, a versatile multi-criteria optimization concept for fatigue life prediction is introduced. Multi-criteria decision making in engineering design refers to obtaining a preferred optimal solution in the context of conflicting design objectives. Compromise decision support problems are used to model engineering decisions involving multiple trade-offs. These methods typically rely on a summation of weighted attributes to accomplish trade-offs among competing objectives. This paper gives an interpretation of the decision parameters as governing both the relative importance of the attributes and the degree of compensation between them. The approach utilizes a response surface model, the compromise decision support problem, which is a multi-objective formulation based on goal programming. Examples illustrate the concepts and demonstrate their applicability.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.24 no.4
• /
• pp.441-447
• /
• 2015

This paper proposes a novel fuzzy-based multi-criteria decision making method and implements a footstep planner for humanoid robots with it. Humanoid robots require additional footstep planning process in addition to path planning for the autonomous navigation. Moreover, it is necessary to consider safety and energy consumption as well as path efficiency and multi-criteria decision making is indispensable. The proposed method can provide not only well- distributed and non-dominated, but also more preferable solutions for users. The planned footsteps by the proposed method were verified through simulation. The results indicate that the user's preference is properly reflected in optimized solutions maintaining solution quality.

• The Journal of Industrial Distribution & Business
• /
• v.5 no.3
• /
• pp.5-14
• /
• 2014

Purpose - This study illustrates research product industrial engineering, which needs to be promoted to encourage knowledge intensive businesses. Research traditions related to industrial business products and a fuzzy multi criteria decision approach in technology management for product design industries have undergone continuous changes over time. However, there is no clarity on the present situation, and there is a need to reform business enterprises. Research design, data, and methodology - Using fuzzy theory and appraising multi-goal plans, the manner of promoting the competitive advantage of industrial businesses is analyzed using a case study. In the case study, various aspects are examined, such as product design and manufacture, fuzzy set decisions with multi attribute policy making, flaws in the present system, and a review of the related literature. Results - New fuzzy and multi criteria designs can improve the existing keyboard by solving product problems, resulting in a clear and durable typeface for a creative LED keyboard. Conclusion - Using a fuzzy set with multi attribute policy-making influences the achievements appraisal system and can help achieve the anticipated strategy goal of product design.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.49-54
• /
• 2017

Pathfinding for pedestrians provided by various navigation programs is based on a shortest path search algorithm. There is no big difference in their guide results, which makes the path quality more important. Multiple criteria should be included in the search cost to calculate the path quality, which is called a multi-criteria pathfinding. In this paper we propose a user adaptive pathfinding algorithm in which the cost function for a multi-criteria pathfinding is defined as a weighted sum of multiple criteria and the weights are learned automatically by Perceptron learning. Weight learning is implemented in two ways: short-term weight learning that reflects weight changes in real time as the user moves and long-term weight learning that updates the weights by the average value of the entire path after completing the movement. We use the weight update method with momentum for long-term weight learning, so that learning speed is improved and the learned weight can be stabilized. The proposed method is implemented as an app and is applied to various movement situations. The results show that customized pathfinding based on user preference can be obtained.

• Journal of Korea Technology Innovation Society
• /
• v.2 no.2
• /
• pp.201-218
• /
• 1999

The article contains an introduction of possibility of applying Multi-Attribute Utility Theory(MAUT) for priority setting of R&D projects. MAUT is compared with AHP, which is widely used recently. These two techuiques are applied to set priorities of R&D projects In a Government-funded Research Institute. Six criteria are chosen from consultation with decision makers. They are composed of 1) validity as representative projects, 2) possibility of resource mobilization, 3) spillover effect of developed technologies, 4) possibility of success, 5) scope of participation and 6) clarity of research goal. To set priorities of R&D projects, SMART(Simple MultiAttribute Rating Technique) and DVM(Difference Value Measurement) out of many MAUT methods are used to design the utility function and to determine the weights among criteria. The aggregation model is additive on the assumption the criteria are independent. AHP executes pairwise comparisons for criteria and alternatives. From the results of the case study, the results and theoretical characteristics are compared.

• IE interfaces
• /
• v.16 no.spc
• /
• pp.14-20
• /
• 2003

This paper presents a multi-criteria decision model and Multi-Criteria Generic Algorithm(MCGA) approach to improve backbone topology by leveraging the Virtual Link(VL) system in an hierarchical Link-State(LS) routing domain. Given that the sound backbone topology structure has a great impact on the overall routing performance in an hierarchical LS domain, the importance of this research is evident. The proposed decision model is to find an optimal configuration of VLs that properly meets two-pronged engineering goals in installing and maintaining VLs: i.e., operational costs and network reliability. The experiment results clearly indicates that it is essential to the effective operations of hierarchical LS routing domain to consider not only engineering aspects but also specific benefits from systematical layout of VLs, thereby presenting the validity of the decision model and MCGA.

• Journal of the Society of Naval Architects of Korea
• /
• v.46 no.4
• /
• pp.409-416
• /
• 2009

The structural design problems are acknowledged to be commonly multi-criteria in nature. The various multi-criteria optimization methods are reviewed and the most efficient and easy-to-use Pareto optimal solution methods are applied to structural optimization of a truss and a beam. The result of the study shows that Pareto optimal solution methods can easily be applied to structural optimization with multiple objectives, and the designer can have a choice from those Pareto optimal solutions to meet an appropriate design environment.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.45
• /
• pp.11-23
• /
• 1998

This paper presents a more efficient evaluation of alternatives by use of multi-criteria decision making methodlogy under fuzzy intersectional dependence relations. The performance evaluation of most systems such as weapons, enterprise systems etc. are multiple criteria decision making problems. The descriptions and judgements on these systems are usually linguistic and fuzzy. The traditional methods of Analytic Hierarchy Process(AHP) are mainly used in crisp(non-fuzzy) decision applications with a very unbalanced scale of judgements and rank reversal. To overcome these problems, we will propose a new, general decision making method for evaluation models using fuzzy AHP(FAHP) under fuzzy intersectional dependence relations. The T.M.S alternatives A, B and C will be evaluted by the Fuzzy Analytic Hierachy Process (FAHP) based on entropy weight in this study. We will use symmetric triangular fuzzy numbers to indicate the relative strength of the elements in the hierachy and degree of intersection between criteria. These problems are evaluated by five criteria : tactical criteria, technology criteria, maintenance criteria, economy criteria, advacement criteria.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.3
• /
• pp.11-19
• /
• 2017

The decision-making process is the act of finding the best solution among various alternatives through comparison between various criteria based on objectives of the project, evaluation standard, and conditions. However, in practice it is not easy to simply decide the optimum decision, especially for selecting malfunctioning reservoirs because no systematic evaluation criteria or standard assessment process are available. Therefore, this study adopted AHP method, which is a MCDM (multi-criteria decision making technique) to identify the malfunctioning reservoirs for efficient management of reservoirs. Important criteria of the selection of malfunctioning reservoirs and priority weights of each criteria were determined based on results of expert's survey under a stepwise hierarchical approach. The most important factor for the decision of malfunctioning reservoirs was obtained as Reservoir efficiency among the selected criteria including Reservoir efficiency decrease, Disaster Risk, Reservoir efficiency, Available water storage, Future water demand, Resident Needs. The AHP technique was applied on 11 reservoirs in Andong region to verify its applicability. Scoring method was applied for the comparison with the results of AHP method.