Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 6
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The structure of Austempered Ductile Iron (ADI) is depend of many factors at individual stages of casting production. There is a rich literature documenting research on the relationship between heat treatment and the resulting microstructure of cast alloy. A significant amount of research is conducted towards the use of IT tools for indications production parameters for thin-walled castings, allowing for the selection of selected process parameters in order to obtain the expected properties. At the same time, the selection of these parameters should make it possible to obtain as few defects as possible. The input parameters of the solver is chemical composition Determined by the previous system module. Target wall thickness and HB of the product determined by the user. The method used to implement the solver is the method of Particle Swarm Optimization (PSO). The developed IT tool was used to determine the parameters of heat treatment, which will ensure obtaining the expected value for hardness. In the first stage, the ADI cast iron heat treatment parameters proposed by the expert were used, in the next part of the experiment, the settings proposed by the system were used. Used of the proposed IT tool, it was possible to reduce the number of deficiencies by 3%. The use of the solver in the case of castings with a wall thickness of 25 mm and 41 mm allowed to indication of process parameters allowing to obtain minimum mechanical properties in accordance with the PN-EN 1564:2012 standard. The results obtained by the solver for the selected parameters were verified. The indicated parameters were used to conduct experimental research. The tests obtained as a result of the physical experiment are convergent with the data from the solver.
Go to article

Authors and Affiliations

K. Jaśkowiec
1 2
ORCID: ORCID
A. Opaliński
2
ORCID: ORCID
P. Kustra
2
D. Jach
3
D. Wilk-Kołodziejczyk
1 2
ORCID: ORCID

  1. Lukasiewicz Research Network-Krakow Institute of Technology, Poland
  2. AGH University of Science and Technology, Department of Applied Computer Science and Modelling, Poland
  3. Kutno Foundry, Poland
Download PDF Download RIS Download Bibtex

Abstract

The computational intelligence tool has major contribution to analyse the properties of materials without much experimentation. The B4C particles are used to improve the quality of the strength of materials. With respect to the percentage of these particles used in the micro and nano, composites may fix the mechanical properties. The different combinations of input parameters determine the characteristics of raw materials. The load, content of B4C particles with 0%, 2%, 4%, 6%, 8% and 10% will determine the wear behaviour like CoF, wear rate etc. The properties of materials like stress, strain, % of elongation and impact energy are studied. The temperature based CoF and wear rate is analysed. The temperature may vary between 30°C, 100°C and 200°C. In addition, the CoF and wear rate of materials are predicted with respect to load, weight % of B4C and nano hexagonal boron nitride %. The intelligent tools like Neural Networks (BPNN, RBNN, FL and Decision tree) are applied to analyse these characteristics of micro / nano composites with the inclusion of B4C particles and nano hBN % without physically conducting the experiments in the Lab. The material properties will be classified with respect to the range of input parameters using the computational model.

Go to article

Authors and Affiliations

P. Radha
N. Selvakumar
R. Harichandran
Download PDF Download RIS Download Bibtex

Abstract

Construction planning always requires labour productivity estimation. Often, in the case of monolithic construction works, the available catalogues of productivity rates do not provide a reliable assessment. The paper deals with the problem of labour estimation for reinforcement works. An appropriate model of labour prediction problem is being introduced. It includes, between others, staff experience and reinforcement buildability. In the paper it is proposed, that labour requirements can be estimated with aggregated classifiers. The work is a continuation of earlier studies, in which the possibility of using classifier ensembles to predict productivity in monolithic works was investigated.

Go to article

Authors and Affiliations

A. Krawczyńska-Piechna
Download PDF Download RIS Download Bibtex

Abstract

Work safety control and analysis of accidents during the construction performance are some of the most important issues of the construction management. The paper focuses on the post-accident absence as an element of the occupational safety management. The occurrence of the post-accident absence of workers can be then treated as an indicator of building performance safety. The ability to estimate its length can also facilitate works planning and scheduling in case of the accident. The paper attempts to answer the question whether it is possible and how to use decision trees and their ensembles to predict the severity of the post-accident absence and which classification algorithm is the most promising to solve the prediction problem. The paper clarifies the model of the prediction problem, introduces 5 different decision tress and different aggregation algorithms in order to build the model. Thanks to the use of aggregation methods it is possible to build classifiers that predict precisely and do not require any initial data treatment, which simplifies the prediction process significantly. To identify the most promising classifier or classifier ensemble the prediction accuracy measures of selected classification algorithms were analyzed. The data to build the model was gathered on national (Polish) construction sites and was taken from literature. Models obtained within simulations can be used to build advisory or safety management systems allowing to detect threats while construction works are being planned or carried out.

Go to article

Authors and Affiliations

Anna Krawczyńska-Piechna
Download PDF Download RIS Download Bibtex

Abstract

Classification techniques have been widely used in different remote sensing applications and correct classification of mixed pixels is a tedious task. Traditional approaches adopt various statistical parameters, however does not facilitate effective visualisation. Data mining tools are proving very helpful in the classification process. We propose a visual mining based frame work for accuracy assessment of classification techniques using open source tools such as WEKA and PREFUSE. These tools in integration can provide an efficient approach for getting information about improvements in the classification accuracy and helps in refining training data set. We have illustrated framework for investigating the effects of various resampling methods on classification accuracy and found that bilinear (BL) is best suited for preserving radiometric characteristics. We have also investigated the optimal number of folds required for effective analysis of LISS-IV images.
Go to article

Authors and Affiliations

Pattathal Vijayakumar Arun
Download PDF Download RIS Download Bibtex

Abstract

Cyber-attacks are increasing day by day. The generation of data by the population of the world is immensely escalated. The advancements in technology, are intern leading to more chances of vulnerabilities to individual’s personal data. Across the world it became a very big challenge to bring down the threats to data security. These threats are not only targeting the user data and also destroying the whole network infrastructure in the local or global level, the attacks could be hardware or software. Central objective of this paper is to design an intrusion detection system using ensemble learning specifically Decision Trees with distinctive feature selection univariate ANOVA-F test. Decision Trees has been the most popular among ensemble learning methods and it also outperforms among the other classification algorithm in various aspects. With the essence of different feature selection techniques, the performance found to be increased more, and the detection outcome will be less prone to false classification. Analysis of Variance (ANOVA) with F-statistics computations could be a reasonable criterion to choose distinctives features in the given network traffic data. The mentioned technique is applied and tested on NSL KDD network dataset. Various performance measures like accuracy, precision, F-score and Cross Validation curve have drawn to justify the ability of the method.
Go to article

Bibliography

[1] Ektefa, M. Mohammadreza, S. Sara and A. Fatimah, “Intrusion detection using data mining techniques,” 200 - 203. DOI: 10.1109/INFRKM.2010.5466919.
[2] Y. Wang, W. Cai and P. Wei, “A Deep Learning Approach For Detecting Malicious Javascript Code,” Wiley Online Library . February 2016.
[3] C. Yin , Y. Zhu, J. Fei and H. Xinzheng, “A Deep Learning Approach For Intrusion Detection Using Recurrent Neural Networks,” IEEE Access. November 7, 2017.
[4] Q. Niyaz, W. Sun, Y Javaid and A. Mansoor, “A Deep Learning Approach For Network Intrusion Detection system,” In Eai Endorsed Transactions on Security and Safety, Vol. 16, Issue 9, 2016.
[5] M. Preeti, V. Vijay, T. Uday and S. P. Emmanuel, “A Detailed Investigation And Analysis Of Using Machine Learning Techniques For Intrusion Detection,” IEEE Communications Surveys & Tutorials, Volume: 21, Issue:1, First quarter 2019.
[6] Y. Li, M. Rong And R. Jiao, “A Hybrid Malicious Code Detection Method Based On Deep Learning,” International Journal of Software Engineering and Its Applications 9(5):205-216, May 2015.
[7] Gulshan and Krishan, “A Multi-Objective Genetic Algorithm Based Approach For Effective Intrusion Detection Using Neural Networks,” Springer. 2015.
[8] K. Levent and D. C. Alan, “Network Intrusion Detection Using A Hidden Naïve Bayes Binary Classifier,” 2015 17th Uksim-Amss International Conference on Modelling and Simulation (Uksim).
[9] A. Nadjaran, K. Mohsen, “A New Approach To Intrusion Detection Based On An Evolutionary Soft Computing Model Using Neuro-Fuzzy Classifiers,” July 2007, Computer Communications 30(10):2201-2212.
[10] D. Amin and R Mahmood, “Feature Selection Based On Genetic Algorithm And Support Vector Machine For Intrusion Detection System,” The Second International Conference On Informatics Engineering & Information Science (Icieis2013).
[11] A. Preeti and S. Sudhir, “Analysis of KDD Dataset Attributes - Class wise for Intrusion Detection,” Procedia Computer Science, Volume 57, 2015, 842-851,
[12] D. M. Doan, D. H. Jeong and S. Ji, “Designing a Feature Selection Technique for Analyzing Mixed Data,” 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2020, pp. 0046-0052, doi: 10.1109/CCWC47524.2020.9031193.
[13] Campbell and Zachary, “Differentially Private ANOVA Testing,” 2018 1st International Conference on Data Intelligence and Security (ICDIS) (2018): 281-285.
[14] S. K. Murthy, “Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey. Data Mining and Knowledge Discovery 2, 345–389 (1998).
[15] S. Dhaliwal, A. Nahid and R. Abbas, “Effective Intrusion Detection System Using XGBoost. Information 2018, 9, 149.
[16] Pedregosa et al., “Scikit-learn: Machine Learning in Python,” JMLR 12, pp. 2825-2830, 2011.

Go to article

Authors and Affiliations

Shaikh Shakeela
1
N. Sai Shankar
1
P Mohan Reddy
1
T. Kavya Tulasi
1
M. Mahesh Koneru
1

  1. ECM, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, India

This page uses 'cookies'. Learn more