检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Islam, Md. Parvez Shinagawa, K. Hatou, K. Abdurrakhman, Arief Dian, K. Department of Biomechanical Systems Faculty of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan United Graduate School of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan Department of Instrumentation Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Business Mathematics Program Study School of Applied STEM Universitas Prasetiya Mulya BSD Campus BSD City Kav. Edutown I.1 Tangerang15339 Indonesia Indonesia

We investigated the optimum hand-picking time of Nagano Purple, a rare Japanese table grape variety. The color sensitivity between pure red–purple–black and pure purple–black makes it difficult for farmers to harvest these fruits at the right time while maintaining high sweetness level. We manually extracted 13 color parameters, namely, X, Y, Z, x, y, L*, a*, b*, L, a, b, C*, and h, from 355 grape skin samples using a colorimeter, which is a time-consuming and expensive process. In addition, we developed a 15-layer shallow long short-term memory (LSTM) and bidirectional long short-term memory (BLSTM) neural network, namely, GrapeNet_Lv1, with a learnable parameter of 1.39E+06. This network is compact and requires low computational cost for training. Furthermore, it has the ability to prevent the problems of vanishing gradient and overfitting. The combination of all the 13 aforementioned parameters yielded promising results in predicting color and sweetness levels, with test accuracies of 0.83 and 0.76, respectively. In the prediction of color level, our proposed network GrapeNet_Lv1 achieves a high validation accuracy of 0.92, F1 score of 0.88, recall of 0.87, low validation loss of 0.39, and RMSE of 0.31. However, in the prediction of sweetness level, GrapeNet_Lv1 achieves a relatively low validation accuracy of 0.79, F1 score of 0.70, recall of 0.69, high validation loss of 0.72, and RMSE of 0.33. Further research can help improve the accuracy. GrapeNet_Lv1 can be applied to other crops, where, predicting the whose optimal hand-picking time is difficult to predict based on color recognition. Keywords: Neural network;LSTM-BLSTM;Nagano Purple, color, sweetness © 2025, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Greening the supply chain: A model for green performance assesment 22

Greening the supply chain: A model for green performance ass...

引用

22nd International Conference on Production Research, ICPR 2013

作者： Sellitto, M.A. Borchardt, M. Pereira, G.M. Silva, R.I. Production and Systems Engineering Graduate Program UNISINOS São Leopoldo RS Brazil

The purpose of this article is to introduce and test a model for green performance assessment in supply chains. The research method was the qualitative modeling. By literature review a model was proposed, consisting of three constructs described and appraised by categorical indicators: green strategy;green innovation;and green operations. The model originated a scale, with five degrees for the measurement of the indicators: very good=1;good=0.75;neutral=0.5;bad=0.25;very bad=0. An application was made in a supply chain of the footwear industry. Focal company managers were asked to distribute importance among the constructs and fulfill the scale. Outcomes obtained, with uniform distribution, and weighted by AHP methods, reached close to 40% of the maximum possible. The worst-performing construct and indicators were operations, reverse logistics and green distribution. Actions have been proposed to improve them.

关键词： Environmental management

来源：评论

学校读者我要写书评

暂无评论

Model for supply chain performance measurement 22

Model for supply chain performance measurement

引用

22nd International Conference on Production Research, ICPR 2013

作者： Sellitto, M.A. Pereira, G.M. Borchardt, M. Silva, R.I. Production and Systems Engineering Graduate Program UNISINOS São Leopoldo RS Brazil

This article presents a model for performance measurement in supply chains. The methodology had two-steps: a qualitative part to identify constructs and indicators and a quantitative one to measure them. The model has two dimensions: SCOR model process: source, make, deliver, and return;and priorities: cost, quality, delivery, flexibility. A 4 x 4 matrix resulted, weighted by AHP. In the cells, indicators, with ranges and five categories [very good, good, neutral, bad, very bad] were allocated to appraise the priority in the process. The ranges were set in the planning process of SCOR. An application was done in the hard core of a supply chain of the footwear industry, including 72 indicators in four suppliers;the focal company;three distribution channels;and a return channel. The SC overall performance reached near 80% of the maximum possible value. Worst performance was flexibility in deliver and delivery in make.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Machine learning techniques in bank credit analysis of companies: A case study of a Brazilian bank 49

Machine learning techniques in bank credit analysis of compa...

引用

49th International Conference on Computers and Industrial engineering, CIE 2019

作者： Assef, F.M. Steiner, M.T.A. Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Paraná Curitiba Brazil

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, not always did the best accuracy represent the best technique for the assessment of this problem. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study. © 2019, Computers and Industrial engineering. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Approach to Semantic Interoperability for Product Development Through Automatic Requirement Extraction and Semantic Reconciliation 16th

An Approach to Semantic Interoperability for Product Develop...

引用

16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019

作者： Canciglieri, Matheus Beltrame de Moura Leite, Athon Francisco Curi Staben Szejka, Anderson Luis Junior, Osiris Canciglieri Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)9783030422493

The strong competitiveness challenges manufacturing industry to rationalize different ways of bringing new products to the market in the shortest time with competitive prices while ensuring higher quality. Industries need to effectively share product requirements, which comes from various sources and are heterogeneous in nature, during the Product Development Process (PDP) to stay competitive. However, problems with misinterpretation of such requirements have been identified during its sharing due to semantic interoperability obstacles related to the process of automatically gathering requirements and their translation and reuse. This research proposes an approach to automatically gather product requirements, extracting its knowledge and translate it for further use and reuse along PDP. The research structure consisted of firstly studying the current issues of the topic, secondly by exploring an approach, to be validated in an experimental case. Current issues point out to gaps related to the process of semantic reconciliation and knowledge extraction perspectives, giving it a multi-dimensional panorama where semantic issues are intertwined among different perspectives. The later solution presents an approach which considers raw information being processed into product features, refining knowledge during PDP and making it reusable in different cycles. The approach brings a new view on practical methods for automatically collect product requirements, extract its knowledge and translate it into product features, based on knowledge extraction methods and by using semantic reconciliation as means for translating product’s requirements. Further research will focus on expanding the approach and including more features to increasingly complex cases, to explore the full potential of the approach. © 2019, IFIP International Federation for Information Processing.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Industry 4.0 and Lean Manufacturing Contribute to the Development of the PDP and Market Performance? A Framework 1

引用

22nd IFIP WG 6.11 Conference on e-Business, e-Services and e-Society, I3E 2023

作者： Tardio, Paulo Roberto Schaefer, Jones Luís Gonçalves, Marcelo Carneiro Nara, Elpidio Oscar Benitez Industrial and Systems Engineering Graduate Program Pontifical Catholic University PR Curitiba Brazil

ISBN: (数字)9783031500404

ISBN: (纸本)9783031500398

To improve production processes, manufacturing companies have made efforts to implement Industry 4.0 technologies and spread the use of Lean Manufacturing (LM) tools. Besides, in addition to the improvements in production processes, these efforts have also been reflected in other issues such as in the Product Development Process (PDP) and Market Performance. In this sense, the objective of this article is to elaborate a conceptual framework covering the constructs of Industry 4.0, LM, and PDP, and to evaluate the importance of these constructs on Market Performance in manufacturing companies in the South of Brazil. The conceptual framework, elaborated with the help of high-impact articles in the area, was evaluated by managers of 111 manufacturing companies in the southern Brazil. The research showed that the implementation of LM tools is more related to the PDP than Industry 4.0 and that large companies have had more positive effects in the implementation of both Industry 4.0 technologies and LM tools. This research can serve as a guide for manufacturing companies, showing the benefits, challenges and opportunities regarding the implementation of LM and Industry 4.0 tools and technologies aiming to improve PDP and Market Performance. It is possible to observe through a structured and systemic framework. © IFIP International Federation for Information Processing 2023.

关键词： Lean production

来源：评论

学校读者我要写书评

暂无评论

Computer Vision with Cognitive Learning to Improve the Decision-Making During the Sales Process in Physical Stores 16th

Computer Vision with Cognitive Learning to Improve the Decis...

引用

16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019

作者： da Silva Ramalho, Vinícius Szejka, Anderson Luis Rudek, Marcelo Junior, Osiris Canciglieri Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)9783030422493

In a world where the information is obtained faster than ever seem, new methods to process that high volume of data are being developed frequently. This is more notorious in a virtual ambient where the data is generated in a manner that is faster and easier to analyze than in the real world. This is very evident in the retail field, where virtual stores have easy access to all the advertisement a user visited and simple to obtain user profile, on the other hand physical stores are limited to basically create a register in a database when there is a purchase. In an attempt to improve the retailers experience from physical stores to manage their business this document has the objective to develop a computational tool that will analyze the people flux going in the establishment, trying to inform the retailer the amount of people and their gender to help the sales process in physical stores. To this end, computational vision methods and algorithms were raised, which after selection, theoretical conception and tool’s implementation it was tested with benchmarks to operate locally and in real time by accessing the cameras installed strategically in a real scenario. Two scenarios were tested: static ambient light and dynamic light. Two tests were conducted: YOLOv2 against background subtraction-based counter;gender classification using full body features. Even though the results were not as positive as needed for commercial use, the tool demonstrated potential and space for improvements. © 2019, IFIP International Federation for Information Processing.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Discrete Differential Evolution with Local Search to Solve the Traveling Salesman Problem: Fundamentals and Case Studies

Discrete Differential Evolution with Local Search to Solve t...

引用

7th IEEE International Conference on Cybernetic Intelligent systems

作者： Sauer, Joao Guilherme Coelho, Leandro dos Santos Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana (PPGEPS/PUCPR) Curitiba Parana Brazil

ISBN: (纸本)9781424429141

Traveling Salesman Problem (TSP) is one of the most difficult problems in the Combinatorial Optimization area. The goal of TSP is to find one path that can travel between all the nodes (instances) of the graph just once (Hamiltonian tour) in the smallest tour, that is, smallest Euclidian distance. In this context, many other meta-heuristics techniques based on evolutionary algorithms have been propose in literature to solve TSP problems. Differential Evolution (DE) is a relatively new simple evolutionary algorithm, which is an effective adaptive approach to global optimization over continuous search spaces. The design principles of DE are simplicity and efficiency. The most distinct feature of DE is that it mutates vectors by adding weighted. random vector differentials to them. Since its invention. DE has been applied with high success on many numerical optimization problems outperforming other more popular meta-heuristics such as the genetic algorithms. Recently. some researchers extended with success the application of DE to complex combinatorial optimization problems with discrete decision variables such as the traveling salesman problem, the machine layout problem, the now-shop scheduling problem. In this paper, the following discrete DE approaches for the TSP are proposed and evaluated: i) DE approach without local search, ii) DE with local search based on Lin-Kernighan-Heulsgaun (LKH) method, and iii) DE with local search based on Variable Neighborhood Search (VNS) and together with LKH method. Numerical study is carried out using the TSPLIB of test TSP problems. In this context, the computational results are compared with the other results in the recent TSP literature. The obtained results show that LKH method is the best method to reach optimal results for TSPLIB benchmarks, but for largest problems, the ED+VNS improve the quality of obtained results.

关键词： Optimization Traveling salesman problem Evolutionary Algorithm Differential Evolution Variable Neighbor Search Local Search Lin-Kernighan-Heulsgaun

来源：评论

学校读者我要写书评

暂无评论

Application of Linear Electromagnetic Actuators in Vehicular Suspensions 12

Application of Linear Electromagnetic Actuators in Vehicular...

引用

12th SAE BRASIL Colloquium on Suspensions and Road Implements and engineering Exhibition, BRASILCOLL 2023

作者： Eckert, Paulo Roberto Boff, Ben Hur Bandeira Follmann, Lucas Da Silva Oliveira, Eduardo Filho, Aly Ferreira Flores Flores, Jeferson Vieira Perondi, Eduardo Andre Lenz, Augusto Schmidt Poli, Mariana Damm Marcolin, Vinicius Campagnaro Struck, Rodrigo Graduate Program in Electrical Engineering Federal Universi Russia Graduate Program in Mechanical Engineering Federal Universi Russia Suspensys Automotive Systems RS Caxias do Sul Brazil

This study comprehensively describes the application of linear electromagnetic actuators in automotive suspension systems, focusing on the electromagnetic force necessary in suspension systems operating in passive, semi-active, and active modes and their capability for energy regeneration. The use of electromagnetic actuators as an alternative to traditional shock absorbers makes easy the energy harvesting that is typically lost during vertical vehicle displacement. An initial sizing technique for dimensioning electromagnetic actuators is applied to estimate the requirements for heavy vehicles. Experimental tests are conducted to validate the proposed method and assess the performance of the electromagnetic actuator in the suspension system for passive, semi-active, and active operations. A suitable extrapolation of the validated data is performed to determine the feasibility of the application of the proposed solution for heavy vehicles and identify potential applications and markets based on the road conditions of the ISO 8608 standard. This study offers a comprehensive approach to determining the actuator force for the suspension system and/or studying its potential for energy regeneration. As a result, it becomes possible to analyze the viability of the actuator replacement and provides important insights for further research and development. © 2023 SAE International. All rights reserved.

关键词： Shock absorbers

来源：评论

学校读者我要写书评

暂无评论

Self-Aware Smart Products: Systematic Literature Review, Conceptual Design and Prototype Implementation

引用

Procedia Manufacturing 2017年 11卷 1471-1480页

作者： Filho, Marcelo Feliciano Liao, Yongxin Loures, Eduardo Rocha Canciglieri, Osiris Graduate Program in Industrial and Systems Engineering (PPGEPS) Pontifical University Catholic of Paraná Curitiba 80215-901 Brazil

The fourth industrial revolution makes more effective use of data generated during manufacturing processes and creates a more interconnected manufacturing network. The data stored inside a product can be updated, analyzed and protected throughout its life cycle. It is currently becoming a reality to speed up the modern mass-customization. The aim of this paper is firstly to explore the state of art about smart products through a systematic literature review. Second, to design a self-aware smart product in a smart factory production environment based on the review findings. Finally, to turn the conceptual design into a prototype implementation. © 2017

关键词： CPS Industrie 4.0 Intelligent Products IoT RFID Smart Factory Smart Products Systematic Literature Review

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：