• Title/Summary/Keyword: Algorithms and Procedures

Search Result 242, Processing Time 0.031 seconds

Application of ML algorithms to predict the effective fracture toughness of several types of concret

  • Ibrahim Albaijan;Hanan Samadi;Arsalan Mahmoodzadeh;Hawkar Hashim Ibrahim;Nejib Ghazouani
    • Computers and Concrete
    • /
    • v.34 no.2
    • /
    • pp.247-265
    • /
    • 2024
  • Measuring the fracture toughness of concrete in laboratory settings is challenging due to various factors, such as complex sample preparation procedures, the requirement for precise instruments, potential sample failure, and the brittleness of the samples. Therefore, there is an urgent need to develop innovative and more effective tools to overcome these limitations. Supervised learning methods offer promising solutions. This study introduces seven machine learning algorithms for predicting concrete's effective fracture toughness (K-eff). The models were trained using 560 datasets obtained from the central straight notched Brazilian disc (CSNBD) test. The concrete samples used in the experiments contained micro silica and powdered stone, which are commonly used additives in the construction industry. The study considered six input parameters that affect concrete's K-eff, including concrete type, sample diameter, sample thickness, crack length, force, and angle of initial crack. All the algorithms demonstrated high accuracy on both the training and testing datasets, with R2 values ranging from 0.9456 to 0.9999 and root mean squared error (RMSE) values ranging from 0.000004 to 0.009287. After evaluating their performance, the gated recurrent unit (GRU) algorithm showed the highest predictive accuracy. The ranking of the applied models, from highest to lowest performance in predicting the K-eff of concrete, was as follows: GRU, LSTM, RNN, SFL, ELM, LSSVM, and GEP. In conclusion, it is recommended to use supervised learning models, specifically GRU, for precise estimation of concrete's K-eff. This approach allows engineers to save significant time and costs associated with the CSNBD test. This research contributes to the field by introducing a reliable tool for accurately predicting the K-eff of concrete, enabling efficient decision-making in various engineering applications.

Efficient Route Determination Technique in LBS System

  • Kim, Sung-Soo;Kim, Kwang-Soo;Kim, Jae-Chul;Lee, Jong-Hun
    • Proceedings of the KSRS Conference
    • /
    • 2003.11a
    • /
    • pp.843-845
    • /
    • 2003
  • Shortest Path Problems are among the most studied network flow optimization problems, with interesting applications in various fields. One such field is the route determination service, where various kinds of shortest path problems need to be solved in location-based service. Our research aim is to propose a route technique in real-time locationbased service (LBS) environments according to user’s route preferences such as shortest, fastest, easiest and so on. Turn costs modeling and computation are important procedures in route planning. There are major two kinds of cost parameters in route planning. One is static cost parameter which can be pre-computed such as distance and number of traffic-lane. The other is dynamic cost parameter which can be computed in run-time such as number of turns and risk of congestion. In this paper, we propose a new cost modeling method for turn costs which are traditionally attached to edges in a graph. Our proposed route determination technique also has an advantage that can provide service interoperability by implementing XML web service for the OpenLS route determination service specification. In addition to, describing the details of our shortest path algorithms, we present a location-based service system by using proposed routing algorithms.

  • PDF

Development of Fitness and Interactive Decision Making in Multi-Objective Optimization (다목적 유전자 알고리즘에 있어서 적합도 평가방법과 대화형 의사결정법의 제안 )

  • Yeboon Yun;Dong Joon Park;Min Yoon
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.45 no.4
    • /
    • pp.109-117
    • /
    • 2022
  • Most of real-world decision-making processes are used to optimize problems with many objectives of conflicting. Since the betterment of some objectives requires the sacrifice of other objectives, different objectives may not be optimized simultaneously. Consequently, Pareto solution can be considered as candidates of a solution with respect to a multi-objective optimization (MOP). Such problem involves two main procedures: finding Pareto solutions and choosing one solution among them. So-called multi-objective genetic algorithms have been proved to be effective for finding many Pareto solutions. In this study, we suggest a fitness evaluation method based on the achievement level up to the target value to improve the solution search performance by the multi-objective genetic algorithm. Using numerical examples and benchmark problems, we compare the proposed method, which considers the achievement level, with conventional Pareto ranking methods. Based on the comparison, it is verified that the proposed method can generate a highly convergent and diverse solution set. Most of the existing multi-objective genetic algorithms mainly focus on finding solutions, however the ultimate aim of MOP is not to find the entire set of Pareto solutions, but to choose one solution among many obtained solutions. We further propose an interactive decision-making process based on a visualized trade-off analysis that incorporates the satisfaction of the decision maker. The findings of the study will serve as a reference to build a multi-objective decision-making support system.

AutoFe-Sel: A Meta-learning based methodology for Recommending Feature Subset Selection Algorithms

  • Irfan Khan;Xianchao Zhang;Ramesh Kumar Ayyasam;Rahman Ali
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.17 no.7
    • /
    • pp.1773-1793
    • /
    • 2023
  • Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

Computational aspects of guided wave based damage localization algorithms in flat anisotropic structures

  • Moll, Jochen;Torres-Arredondo, Miguel Angel;Fritzen, Claus-Peter
    • Smart Structures and Systems
    • /
    • v.10 no.3
    • /
    • pp.229-251
    • /
    • 2012
  • Guided waves have shown a great potential for structural health monitoring (SHM) applications. In contrast to traditional non-destructive testing (NDT) methodologies, a key element of SHM approaches is the high process of automation. The monitoring system should decide autonomously whether the host structure is intact or not. A basic requirement for the realization of such a system is that the sensors are permanently installed on the host structure. Thus, baseline measurements become available that can be used for diagnostic purposes, i.e., damage detection, localization, etc. This paper contributes to guided wave-based inspection in anisotropic materials for SHM purposes. Therefore, computational strategies are described for both, the solution of the complex equations for wave propagation analysis in composite materials based on exact elasticity theory and the popular global matrix method, as well as the underlying equations of two active damage localization algorithms for anisotropic structures. The result of the global matrix method is an angular and frequency dependent wave velocity characteristic that is used subsequently in the localization procedures. Numerical simulations and experimental investigations through time-delay measurements are carried out in order to validate the proposed theoretical model. An exemplary case study including the calculation of dispersion curves and damage localization is conducted on an exemplary unidirectional composite structure where the ultrasonic signals processed in the localization step are simulated with the spectral element method. The proposed study demonstrates the capabilities of the proposed algorithms for accurate damage localization in anisotropic structures.

Bayesian Algorithms for Evaluation and Prediction of Software Reliability (소프트웨어 신뢰도의 평가와 예측을 위한 베이지안 알고리즘)

  • Park, Man-Gon;Ray
    • The Transactions of the Korea Information Processing Society
    • /
    • v.1 no.1
    • /
    • pp.14-22
    • /
    • 1994
  • This paper proposes two Bayes estimators and their evaluation algorithms of the software reliability at the end testing stage in the Smith's Bayesian software reliability growth model under the data prior distribution BE(a, b), which is more general than uniform distribution, as a class of prior information. We consider both a squared-error loss function and the Harris loss function in the Bayesian estimation procedures. We also compare the MSE performances of the Bayes estimators and their algorithms of software reliability using computer simulations. And we conclude that the Bayes estimator of software reliability under the Harris loss function is more efficient than other estimators in terms of the MSE performances as a is larger and b is smaller, and that the Bayes estimators using the beta prior distribution as a conjugate prior is better than the Bayes estimators under the uniform prior distribution as a noninformative prior when a>b.

  • PDF

Practical Algorithms on Lunar Reference Frame Transformations for Korea Pathfinder Lunar Orbiter Flight Operation

  • Song, Young-Joo;Lee, Donghun;Kim, Young-Rok;Bae, Jonghee;Park, Jae-ik;Hong, SeungBum;Kim, Dae-Kwan;Lee, Sang-Ryool
    • Journal of Astronomy and Space Sciences
    • /
    • v.38 no.3
    • /
    • pp.185-192
    • /
    • 2021
  • This technical paper deals the practical transformation algorithms between several lunar reference frames which will be used for Korea pathfinder lunar orbiter (KPLO) flight operation. Despite of various lunar reference frame definitions already exist, use of a common transformation algorithm while establishing lunar reference frame is very important for all members related to KPLO mission. This is because use of slight different parameters during frame transformation may result significant misleading while reprocessing data based on KPLO flight dynamics. Therefore, details of practical transformation algorithms for the KPLO mission specific lunar reference frames is presented with step by step implementation procedures. Examples of transformation results are also presented to support KPLO flight dynamics data user community which is expected to give practical guidelines while post processing the data as their needs. With this technical paper, common understandings of reference frames that will be used throughout not only the KPLO flight operation but also science data reprocessing can be established. It is expected to eliminate, or at least minimize, unnecessary confusion among all of the KPLO mission members including: Korea Aerospace Research Institute (KARI), National Aeronautics and Space Administration (NASA) as well as other organizations participating in KPLO payload development and operation, or further lunar science community world-wide who are interested in KPLO science data post processing.

Rough Cut Tool Path Planning in Fewer-axis CNC Machinig (저축 CNC 환경에서의 황삭가공)

  • 강지훈;서석환;이정재
    • Korean Journal of Computational Design and Engineering
    • /
    • v.2 no.1
    • /
    • pp.19-27
    • /
    • 1997
  • This paper presents rough cut tool path planning for the fewer-axis machine consisting of a three-axis CNC machine and a rotary indexing table. In the problem dealt with in this paper, the tool orientation is "intermediately" changed, distinguished from the conventional problem where the tool orientation is assumed to be fixed. The developed rough cut path planning algorithm tries to minimize the number of tool orientation (setup) changes together with tool changes and the machining time for the rough cut by the four procedures: a) decomposition of the machining area based on the possibility of tool interference (via convex hull operation), b) determination of the optimal tool size and orientation (via network graph theory and branch-and bound algorithm), c) generation of tool path for the tool and orientation (based on zig-zag pattern), and d) feedrate adjustment to maintain the cutting force at an operation level (based on average cutting force). The developed algorithms are validated via computer simulations, and can be also used in pure fiveaxis machining environment without modification.

  • PDF

Utilisation of IoT Systems as Entropy Source for Random Number Generation

  • Oguzhan ARSLAN;Ismail KIRBAS
    • International Journal of Computer Science & Network Security
    • /
    • v.24 no.4
    • /
    • pp.77-86
    • /
    • 2024
  • Using random numbers to represent uncertainty and unpredictability is essential in many industries. This is crucial in disciplines like computer science, cryptography, and statistics where the use of randomness helps to guarantee the security and dependability of systems and procedures. In computer science, random number generation is used to generate passwords, keys, and other security tokens as well as to add randomness to algorithms and simulations. According to recent research, the hardware random number generators used in billions of Internet of Things devices do not produce enough entropy. This article describes how raw data gathered by IoT system sensors can be used to generate random numbers for cryptography systems and also examines the results of these random numbers. The results obtained have been validated by successfully passing the FIPS 140-1 and NIST 800-22 test suites.

Scientific Inspection Method of PC Box Bridges Using Remote Control Tarantula Robot (원격제어 로봇을 이용한 PSC Box교량 내부 점검방법)

  • Lee, Byeong-Ju;Shin, Jae-In;Seo, Jin-Won;Lee, Ji-Yeong;Park, Yeong-Ha
    • Proceedings of the Korea Concrete Institute Conference
    • /
    • 2009.05a
    • /
    • pp.561-562
    • /
    • 2009
  • The needs for inspection automation for more systematic and efficient maintenance were gradually increased by several inspectors and researchers. With the robotic and digital image processing technologies, in this paper, new inspection automation system were introduced and tested in the real PSC box crack inspection procedures The configuration and scheme of robotic inspection and digital image processing algorithms were represented. The designed robotic sensors and image processing system were tested and the feasibility and possibility of the robot based automatic inspection were approved in the real PSC box bridges.

  • PDF