Sveikatos tyrimų laboratorija / Health Laboratory
- conference paper[2021][P1a2][S003,T007][6]
; ; WSCG 2021 : 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen, Czech Republic, May 17 – 20, 2021 : Proceedings. Plzen : Vaclav Skala - UNION Agency, 2021. ISBN 9788086943343., p. 109-114Recently, customized manufacturing is gaining much momentum. Consumers do not want mass-produced products but are looking for unique and exclusive ones. It is especially evident in the furniture industry. As it is necessary to set an individual price for each individually manufactured product, companies face the need to quickly estimate a preliminary cost and price as soon as an order is received. The task of estimating costs as precise and timely as possible has become critical in customized manufacturing. The cost estimation problem can be solved as a prediction problem using various machine learning (ML) techniques. In order to obtain more accurate price prediction, it is necessary to delve deeper into the data. Data visualization methods are excellent for this purpose. Moreover, it is necessary to consider that the managers who set the price of the product are not ML experts. Thus, data visualization methods should be integrated into the decision support system. On the one hand, these methods should be simple, easily understandable and interpretable. On the other hand, the methods should include more sophisticated approaches that allowed reveal hidden data structure. Here, dimensionality-reduction methods can be employed. In this paper, we propose a data visualization process that can be useful for data analysis in customized furniture manufacturing to get to know the data better, allowing us to develop enhanced price prediction models.
9Scopus© Citations 1 Early cost estimation in customized furniture manufacturing using machine learningItem type:Publication, research article[2021][S4][T007][6]; ; ;Medvedev, ViktorInternational journal of machine learning and computing. Singapore : IJMLC, 2021, vol. 11, no. 1., p. 28-33Accurate cost estimation at the early stage of a construction project is a key factor in the success of most projects. Many difficulties arise when estimating the cost during the early design stage in customized furniture manufacturing. It is important to estimate the product cost in the earlier manufacturing phase. The cost estimation is related to the prediction of the cost, which commonly includes calculation of the materials, labor, sales, overhead, and other costs. Historical data of the previously manufactured products can be used in the cost estimation process of the new products. In this paper, we propose an early cost estimation approach, which is based on machine learning techniques. The experimental investigation based on the real customized furniture manufacturing data is performed, results are presented, and insights are given.
229 75 Application of machine learning-for cost estimation in customized furniture productionItem type:Publication, conference paper[2018][T1e][T007][1]; ; ; EURO 2018: 29th European conference on operational research, July 8-11, Valencia, Spain : conference handbook. Valencia : European Association of Operational Research Society, 2018. ISBN 9788409029389., p. 11310 Transformative demands for ERP functionalities: knowledge management in customized manufacturingItem type:Publication, conference paper[2018][T1e][S003][1]; ; ; Abstracts of papers presented at the 19th European Conference on Knowledge Management (ECKM 2018) 6 - 7 September 2018, University of Padua, Italy. Reading : Academic Conferences and Publishing International Limited, 2018. ISBN 9781911218944., p. 5711 Transformative demands for ERP functionalities: knowledge management in customized manufacturingItem type:Publication, conference paper[2018][P1a2][S003][8]; ; ; Proceedings of the 19th European conference on knowledge management : (ECKM 2018), 6-7 September 2018, University of Padua, Italy / edited by E. Bolisani, E. Di Maria, E. Scarso. Reading : Published by Academic Conferences and Publishing International Limited, 2018, vol. 1. ISBN 9781911218944., p. 563-570Customized manufacturing requires completely new technological solutions and long and careful prototype development and testing. The new requirements increase production costs, extend manufacturing time and entail frequent errors in the product quality. So far, knowledge management framework provided by ERP systems still has not responded to the customized needs even though ERP’s provide plenty of innovation solutions for prognosis, trending, etc. Additionally, high uncertainty of customization could be managed better by employing diverse expertise of employees if their knowledge could be empowered together with rigid knowledge about the customized order. The goal of this paper is to determine customized manufacturing demands for functionalities of knowledge management systems that can be incorporated in ERP. The research is based on a case study conducted in an SME type company settled in Lithuania. Extended interviews on different issues, including the decision making system, problem solving, strategic decisions and ERP implementation and use, have been conducted during the last 2 years (from June, 2016 to March, 2018) with company leaders, managers, constructers and production workers. Although, one may expect to accrue experience and improve abilities with every new order, the company is still facing difficulties in coping with uncertainties of incoming orders even after ERP was implemented and launched. In conclusions, customized manufacturing is intensively looking for new knowledge management solutions that meet strictly defined requirements with new ERP functionalities that could be explicit as system based on employee participation and machine learning. The main functionalities could be listed as following: 1.) to make prognostic price estimations for customized and unique orders; 2.) to classify new orders specifying what additional capacities are require to develop the product; 3.) to recognize and accumulate any data that can be stored in the system for future solutions; 4.) to provide guidelines for knowledge management at all stages of knowledge acquisition, transformation and application.
5