Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 14
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Bibliography

  1.  H. Das, J. K. Rout, and S.C.N. Dey, Maharana, Applied Intelligent Decision Making in Machine Learning, CRC Press, 2020.
  2.  B. Zhang, Y. Wu, J. Lu, and K.L. Du, “Evolutionary computation and its applications in neural and fuzzy systems”, Appl. Comput. Intell. Soft Comput. 2011, 938240 (2011), doi: 10.1155/2011/938240
  3.  M. Injadat, A. Moubayed, A.B. Nassif, and A. Shami, “Machine learning towards intelligent systems: applications, challenges, and opportunities”, Artif. Intell. Rev. (2021), https://doi.org/10.1007/s10462-020-09948-w.
  4.  I. Goodfellow, Y. Bengio, and A. Courville, Deep learning, MIT Press, 2016.
  5.  J. Heaton, “Applications of Deep Neural Networks”, arXiv: 2009.05673v2 [cs. LG] 2021, Heaton Research, Inc.
  6.  E. Kayacan and M.A. Khanesar, Fuzzy Neural Networks for Real Time Control Applications: Concepts, Modeling and Algorithms for Fast Learning, Elsevier, 2015.
  7.  A. Burkov, Machine Learning Engineering, True Positive Inc., 2020.
  8.  A. Krizhevsky, I. Sutskever, and G. Hinton, Imagenet classification with deep convolutional neural networks, NIPS, 2012.
  9.  A. Cichocki, R. Zdunek, A. H. Phan, and S.-I. Amari, Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation, Wiley, 2009.
  10.  A. Khan, A. Sohail, U. Zahoora, and A.S. Qureshi, “A survey of the recent architectures of deep convolutional neural networks”, Artif. Intell. Rev. 53, 5455–5516 (2020), doi: 10.1007/s10462-020-09825-6.
  11.  A. Osowska-Kurczab, T. Markiewicz, M. Dziekiewicz, and M. Lorent, “Multi-feature ensemble system for renal tumour classification”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136749 (2021).
  12.  E. Kot, Z. Krawczyk, K. Siwek, P. Czwarnowski, and L. Królicki, “Deep learning-based framework for tumour detection and semantic segmentation”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136750 (2021).
  13.  Z. Krawczyk and J. Starzyński, “Segmentation of bone structures with the use of deep learning techniques”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136751 (2021).
  14.  T. Leś, “U-Net based frames partitioning and volumetric analysis for kidney detection in tomographic images”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e137051 (2021).
  15.  M. Kołodziej, A. Majkowski, P. Tarnowski, R. Rak, and A. Rysz, “A New Method of Cardiac Sympathetic Index Estimation Using 1D-Convolutional Neural Network”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136921 (2021).
  16.  E. Majda-Zdancewicz et al., “Deep learning vs. feature engineering in the assessment of voice signals for diagnosis in Parkinson’s disease”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e137347 (2021).
  17.  F. Gil and S. Osowski, “Fusion of feature selection methods in gene recognition”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136748 (2021).
  18.  K. Godlewski and B. Sawicki, “Optimisation of MCTS player for The Lord of the Rings: the card game”, Bull. Pol. Acad. Sci. Tech. Sci. 69(3), e136752 (2021).
Go to article

Authors and Affiliations

Stanislaw Osowski
1 2
ORCID: ORCID
Bartosz Sawicki
1
Andrzej Cichocki
3

  1. Warsaw University of Technology, Pl. Politechniki 1, 00-661 Warsaw, Poland
  2. Military University of Technology, ul. gen. Sylwestra Kaliskiego 2, 00-908 Warsaw, Poland
  3. RIKEN Center for Brain Science, 2-1 Hirosawa, Wako, Saitama 351-0106, Japan
Download PDF Download RIS Download Bibtex

Abstract

Many stages of growth models have been introduced to clarify management priorities during the early stages of business growth. However, many of these models are conceptual and universal, providing only limited benefits to specific industries and business contexts. The early stages of technology-based ventures have attracted broad interest, while less attention has been paid to the early stages of service-based firms. However, in recent years, interest in service-based businesses, as well as servitisation, has grown. This literature-based study explores and compares the early stages of growth in service-based and technology-based firms. On one hand, this study condenses the basic characteristics of recent empirical studies on the early stages of technology- and service-based firms. On the other, this study clarifies the central themes, sequential patterns and central differences in the early stages of service- and technology-based firms. This study pinpoints the importance of contextual understanding related to the early stages of business growth and encourages the scholars towards bridging the contextual gaps of this stream of literature.
Go to article

Authors and Affiliations

Matti Muhos
1
Martti Saarela
1
Anna-Mari Simunaniemi
1
Del Foit Jr.
2
Lada Rasochova
2

  1. University of Oulu, Kerttu Saalasti Institute, Finland
  2. University of California San Diego, United States
Download PDF Download RIS Download Bibtex

Abstract

Recently, the expand of industrial market has led to have long supply chain network. During the long shipment, the probability of having damaged products is likely to occur. The probability of having damaged products is different between stages and that could lead to higher percentage of damaged products when arrived at retailers. Many companies have rejected the entire shipment because the damaged product percentage was higher than that agreed on. Decision-makers have tried to reduce the percentage of damaged products that happened because the transit, loading unloading the shipment, and natural disasters. Companies started to implement recovery centers in the supply chain network in order to return their system steady statues. Recovery models have been developed in this paper to reduce the damaged percentage at minimum costs to do so. Results show that the possibility of implementing an inspection unit and a recovery centers in the system before sending the entire shipment to the retailer based on examining a sample size that has been selected randomly from the shipment and the minimum cost of committing type I and type II errors. Designing a methodology to minimize the total cost associated with the supply chain system when there is a possibility of damage occurring during shipping is the objective of this research.
Go to article

Authors and Affiliations

Mastoor M. Abushaega
1 4
Yahya H. Daehy
2
Saleh Y. Alghamdi
3
Krishna K. Krishnan
2
Abdulrahman Khamaj
1

  1. Industrial Engineering Department, Jazan University, Jazan, KSA
  2. Industrial and Systems Engineering Department, Wichita State University, Wichita, KS, USA
  3. Industrial Engineering Department, King Khalid University, Abha, KSA
  4. Industrial and Systems Engineering Department, University of Oklahoma, Norman, OK, USA
Download PDF Download RIS Download Bibtex

Abstract

Digitization in the production area represents the integrated planning and management of production and logistics systems and networks based on digital models, methods, and tools, which are built on a common flexible information and communication platform. Currently known and used Lean tools need to be dynamized and oriented to the creation of digital business, where digital models can be heterogeneous, respectively usable in several projects. One of these possibilities is the use of the Lean production method – Value Stream Mapping, the potential of which in the context of the above mentioned is great. The aim of the presented article is based on Gemba analysis of the production process to process the value stream in the environment of the software tool TX Plant Simulation for the needs of flexible reflection on changes in various parameters within the value stream. The case study carried out under this article aims, among other things, to highlight the importance of combining simple Lean Production tools with software in finding, testing, and designing alternative solutions. The potential of using the processed model was also processed for the needs of digitization of business processes in the future.
Go to article

Authors and Affiliations

Miriam Pekarcíková
1
Peter Trebuna
1
Marek Kliment
1
Štefan Král
2
Michal Dic
1

  1. Technical University of Košice, Faculty of Mechanical Engineering, Department of Management, Industrial andDigital Engineering, Park Komenského 9, 040 01 Košice, Slovak Republic
  2. Slovak Legal Metrology n.o., Banska Bystrica, Slovakia
Download PDF Download RIS Download Bibtex

Abstract

The Fourth Industrial Revolution, also known as Industry 4.0, is about connecting the physical world with the virtual world in real-time. With the advent of the Fourth Industrial Revolution, manufacturing companies are introducing a number of solutions that increase productivity and personalize finished products in line with the idea of Industry 4.0. The application of, among others, the following: 3D printing, the Internet of Things, Big Data, cyber-physical systems, computing clouds, robots (collaborating and mobile), Radio-frequency identification systems, and also quality control and reverse engineering systems, is becoming popular. There are still not enough studies and analyses connected with the Polish 3D printing market, and also attempt to determine the attitude of those studies and analyses to the implementation of the Industry 4.0 conception. In connection with what is stated above, the principal objective of this paper is to determine the directions of the 3D printing industry development. In this publication, it is as well the survey respondents’ opinions relevant to opportunities and threats connected with the implementation of the Industry 4.0 conception in an enterprise are presented. The survey was conducted on a group of 100 enterprises and scientific research institutes in Poland, offering and/or applying additive technologies.
Go to article

Authors and Affiliations

Joanna Wozniak
1
Grzegorz Budzik
2
Łukasz Przeszłowski
2
Katarzyna Chudy-Laskowska
1

  1. Rzeszow University of Technology, Faculty of Management, Rzeszów, Poland
  2. Rzeszow University of Technology, Faculty of Mechanical Engineering and Aeronautics, Rzeszów, Poland
Download PDF Download RIS Download Bibtex

Abstract

Knowledge management is a process aimed at enriching and effectively using knowledge assets in various areas of business operations. It also applies to manufacturing enterprises that offer tangible products combining it with the art of processing information and intellectual assets into added value for the customer. A characteristic feature of manufacturing enterprises is assigning their employees a double role: a knowledge user and, at the same time, an internal source of specialist knowledge. In the situation of dynamically changing market conditions, there is an additional need to acquire new knowledge (in practice: often to buy knowledge) from the company’s environment. A solution in the above-mentioned scope in Poland may be digital repositories of science assets as tools for knowledge transfer to SMEs. Research institutes are an important element in the process of knowledge transfer from scientific units to the economy (e.g. they offer their services in open access). The paper presents the concept of such a repository preceded by a diagnosis of the existing state, an analysis of the recipients of the deposited content and the examination and analysis of the requirements of potential users of the repository.
Go to article

Authors and Affiliations

Beata Starzynska
1
ORCID: ORCID
Agnieszka Klembalska
2
ORCID: ORCID

  1. Poznan University of Technology, Faculty of Mechanical Engineering, Poland
  2. Łukasiewicz Research Network – Industrial Institute of Agricultural Engineering, Poland
Download PDF Download RIS Download Bibtex

Abstract

Wear of the working surfaces of the forging dies in the process of manufacturing products with the die forging technique leads to deterioration of their operational properties as well as their technological quality. A characteristic feature of production in small and medium-sized enterprises is the high variability of the product range and short production series, which can be repeated in the case of re-orders by customers. In this type of production conditions, a technological criterion in form of – a change in the characteristic and selected dimension of forging is usually used to assess the quality of products. An important problem is, whether by taking up another order for a series of the same type of product, it will be possible to implement it with the existing die, or should a new die be made? As a result of the research carried out in the company implementing this type of contract, a procedure was proposed for forecasting the abrasive wear of die working surfaces on the basis of a technological criterion, easy to determine in the conditions of small and medium-sized enterprises. The paper presents the results of the wear assessment of a die made out of hot-work tool steel X37CrMoV5-1 (WCL) and dies made of 42CrMo4 alloy structural steel with hardfacing working surfaces by F-818 wire. To determine and forecast the process of die wear, a mathematical model in the form of neural networks was used. Their task was to forecast the ratio of the increment in introduced wear intensity indicator to the number of forgings made during the process. Taking into account
Go to article

Authors and Affiliations

Joanna Krajewska-Spiewak
1
ORCID: ORCID
Jan Turek
2
Józef Gawlik
1
ORCID: ORCID

  1. Cracow University of Technology, Faculty of Mechanical Engineering, Poland
  2. Jasło, Poland
Download PDF Download RIS Download Bibtex

Abstract

Facing severely competitive global markets, managers of the modern transnational corporations must effectively integrate its intra-supply chain system to meet customers’ multiproduct demands with good quality items, minimum operating expenses, and in a timely delivery matter. Inspired by assisting current transnational firms to achieve the mission, this study builds a mathematical model to explore a multiproduct fabrication-shipment problem incorporating an accelerated rate and ensured product quality. A single machine production scheme under a common cycle policy and with random defects, rework, and an accelerated fabrication rate is considered. The speedy rate option is associated with extra setup and linear variable costs, which aims to cut short the common cycle time. Mathematical derivation is employed to find the long-run average system expense. The optimization method is used to jointly derive the decision for common length and delivery frequency per cycle for the problem. Numerical illustration is offered to confirm the applicability of the results and expose the individual/combined influences of diverse crucial system features on the problem, thus facilitate the intra-supply chain’s fabrication-shipment decision making.
Go to article

Authors and Affiliations

Yuan-Shyi Peter Chiu
1
Victoria Chiu
2
Hong-Dar Lin
1
Tiffany Chiu
3

  1. Faculty of Industrial Engineering & Management, Chaoyang University of Technology, Taichung City 413, Taiwan
  2. Faculty of Accounting, Finance and Law, State University of New York at Oswego, Oswego, NY 13126, USA
  3. Faculty of Anisfield School of Business, Ramapo College of New Jersey, Mahwah, NJ 07430, USA
Download PDF Download RIS Download Bibtex

Abstract

castings. The possibility of reducing the total volume of machining allowances, reducing the wear of cutting tools, shortening machining time and eliminating idle machining passes was considered. The tests were carried out on two batches of castings supplied by two independent foundries. Casting geometry measurements were made using a structured light scanner. The analysis included machining with cemented carbide tools and tool ceramics at two machining centers: DMC200U and DMC270U. It has been shown that as a result of eliminating idle machining passes, it is possible to reduce machining time by 12% for the first and by 44% for the second casting supplier. The estimated annual savings for the production volume of 500 pcs of these castings can range from € 7388 to even € 23 346. The actual cost of cheaper casts was also calculated, taking into account the difference in machining cost resulting from larger machining allowances.
Go to article

Authors and Affiliations

Andrzej Gessner
1
ORCID: ORCID

  1. Poznan University of Technology, Institute of Mechanical Technology
Download PDF Download RIS Download Bibtex

Abstract

Traditional clustering algorithms which use distance between a pair of data points to calculate their similarity are not suitable for clustering of boolean and categorical attributes. In this paper, a modified clustering algorithm for categorical attributes is used for segmentation of customers. Each segment is then mined using frequent pattern mining algorithm in order to infer rules that helps in predicting customer’s next purchase. Generally, purchases of items are related to each other, for example, grocery items are frequently purchased together while electronic items are purchased together. Therefore, if the knowledge of purchase dependencies is available, then those items can be grouped together and attractive offers can be made for the customers which, in turn, increase overall profit of the organization. This work focuses on grouping of such items. Various experiments on real time database are implemented to evaluate the performance of proposed approach.
Go to article

Authors and Affiliations

Juhi Singh
1
Mandeep Mittal
2

  1. Department of Computer Science, Amity School of Engineering and Technology, Delhi, India
  2. Department of Mathematics, Amity Institute of Applied Sciences, Amity University Uttar Pradesh, Noida, India
Download PDF Download RIS Download Bibtex

Abstract

This study offers an overview of how changing habits in consuming a cup of tea can contribute to make better environment. As the initial existing scenario, survey for picturing Indonesian consumers in preparing their cup of tea from dried leaves was conducted to urban and suburban citizens. According to the survey, both respondent groups were using LPG as the first choice in boiling water for preparing tea, followed by using an electric dispenser as the second choice. This habit causes CO2 emission from processing a cup of tea by Indonesian consumer was 24 g CO2-eq per cup of tea, excluding the tea organic waste. The portion of CO2 emission from boiling water in tea preparation was 41.93% of whole CO2 emission from plantation to served cup. The emission can be significantly reduced by converting dried tea (initial scenario) into the ready-to-drink product, in the form of powdered tea (second scenario) and boxed tea (third scenario). This study simulated an integrated system of tea product manufacturing system with biogas utilization produced from tea organic waste. Simulation conducted based on daily manufacturing process at the Gamboeng green tea factory. Additional required energies were simulated from the wood pellet, which is the best practice in the Gamboeng Tea factory. By shifting tea consuming habit from dried tea to powdered tea and/or boxed tea, the emission from a cup of tea can be reduced, with range of reduction varied from 8.87 g to 22.13 g CO2-eq per cup of tea. If the Gamboeng green tea daily production capacity of the factory is fully converted into powdered tea, the potency of CO2 emission reduction reaches 26.92 metric ton CO2. However, the factory should pay attention to providing the water for the manufacturing process. The required water was 45.23 m3 of drinking water if all dried tea converted to powdered tea. Moreover, 11.53 m3 of water is required as irrigation for the biogas process in converting all tea organic waste into biogas.
Go to article

Authors and Affiliations

Teuku Beuna Bardant
1
Arief Ameir Rahman Setiawan
2 5
Muthia Syafika Haq
3
Hafiizh Prasetia
5
Adhi Irianto Mastur
3
Sugeng Harianto
3
Agusta Samodra Putra
4 5
Anny Sulaswatty
1
Edi Iswanto Wiloso
5
Ryozo Noguchi
4

  1. Research Center for Chemistry, Indonesian Institute of Sciences (LIPI),Kawasan Puspiptek, Serpong, Tangerang Selatan, Indonesia
  2. Graduate School of Sciences and Engineering, University of Tsukuba, Tsukuba, Japan
  3. Research Institute for Tea and Cinchona, Mekarsari, Gambung, Bandung, Indonesia
  4. Faculty of Life and Environmental Sciences, University of Tsukuba, Tsukuba, Japan
  5. Research Center for Policy and Management of Science, Technology and Innovation,Indonesian Institute of Sciences (LIPI), Jl. Gatot Subroto 10, Jakarta Selatan, Indonesia
Download PDF Download RIS Download Bibtex

Abstract

The paper deals with the problem of production material flow management. The proper way of logistic tasks management has an impact on the production process effectiveness and the cycle time, which is a very important factor in manufacturing. Reducing the production process cycle time results not only in the ability to provide more customers with orders but also in increasing the level of resources usage (machines, operators etc.). In order to reach the aim of improving production effectiveness, the simulation modeling was used. It is a computer method that supports a decision-making process and allows to perform experiments on production without interfering with the real process. The paper also includes a risk analysis performed to evaluate the imperfections of simulation modeling, based on the rules of fuzzy logic.
Go to article

Authors and Affiliations

Anna Burduk
ORCID: ORCID
Dagmara Łapczynska
ORCID: ORCID
Piotr Popiel
Download PDF Download RIS Download Bibtex

Abstract

Horizontal Directional Drilling (HDD) technology is a highly complex process connected with high risk and uncertainty due the high variability underground strata, often limited access to specialised equipment, dynamic natural environment, technical disruptions, human factor and changes in economic environment that further complicate the gathering of reliable information and data. This work presents a new risk evaluation model tailored for HDD technology, in which failure mode and effect analysis (FMEA) modelling were applied. This paper focuses on 15 human risk factors and 9 equipment risk factors in HDD technology. The proposed approach takes into account not only the probability of the risk factor occurrence, but also its severity and the possibility of detecting faults, which were not clearly separated and analyzed in the previous works. Application of the proposed model shows the relationship between occurrence, severity and detection for the analyzed failures. Moreover, many detection possibilities for the identified failures were presented. The calculated risk priority numbers allowed to rank HDD failures and identify the most critical risks for which one should look for risk treatment possibilities beyond risk cause reduction, such as risk effect reduction, risk transfer, risk elimination or active risk retention.
Go to article

Authors and Affiliations

Maria Krechowicz
1
ORCID: ORCID
Wacław Gierulski
1
ORCID: ORCID
Stephen Loneragan
2
Henk Kruse
3

  1. Kielce University of Technology, Poland
  2. HDD Engineering, Australia
  3. Deltares, the Netherlands

This page uses 'cookies'. Learn more