Search results for: test case selection
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 20852

Search results for: test case selection

20732 Site Selection of CNG Station by Using FUZZY-AHP Model (Case Study: Gas Zone 4, Tehran City Iran)

Authors: Hamidrza Joodaki

Abstract:

The most complex issue in urban land use planning is site selection that needs to assess the verity of elements and factors. Multi Criteria Decision Making (MCDM) methods are the best approach to deal with complex problems. In this paper, combination of the analytical hierarchy process (AHP) model and FUZZY logic was used as MCDM methods to select the best site for gas station in the 4th gas zone of Tehran. The first and the most important step in FUZZY-AHP model is selection of criteria and sub-criteria. Population, accessibility, proximity and natural disasters were considered as the main criteria in this study. After choosing the criteria, they were weighted based on AHP by EXPERT CHOICE software, and FUZZY logic was used to enhance accuracy and to approach the reality. After these steps, criteria layers were produced and weighted based on FUZZY-AHP model in GIS. Finally, through ARC GIS software, the layers were integrated and the 4th gas zone in TEHRAN was selected as the best site to locate gas station.

Keywords: multiple criteria decision making (MCDM), analytic hierarchy process (AHP), FUZZY logic, geographic information system (GIS)

Procedia PDF Downloads 330
20731 The Study on Blast Effect of Polymer Gel by Trazul Lead Block Test and Concrete Block Test

Authors: Young-Hun Ko, Seung-Jun Kim, Khaqan Baluch, Hyung- Sik Yang

Abstract:

In this study, the polymer gel was used as coupling material in a blasting hole and its comparison was made with other coupling materials like sand, water, and air. Trazul lead block test and AUTODYN numerical analysis were conducted to analyze the effects of the coupling materials on the intensity of the explosion, as well as the verification tests were conducted by using concrete block test. The emulsion explosives were used in decoupling conditions, sand, water, and polymer gel were used as the coupling materials. The lead block test and the numerical analysis showed that the expansion of the blast hole in the lead block was similar to that of the water and gelatin and followed by sand and air conditions. The validation of concrete block test result showed the similar result as Trazul lead block test and the explosion strength was measured at 0.8 for polymer gel, 0.7 for sand, and 0.6 for no coupling material, in comparison to the full charge (1.0) case.

Keywords: Trazul lead block test, AUTODYN numerical analysis, coupling material, polymer gel, soil covering concrete block explosion test

Procedia PDF Downloads 265
20730 Prioritization of Customer Order Selection Factors by Utilizing Conjoint Analysis: A Case Study for a Structural Steel Firm

Authors: Burcu Akyildiz, Cigdem Kadaifci, Y. Ilker Topcu, Burc Ulengin

Abstract:

In today’s business environment, companies should make strategic decisions to gain sustainable competitive advantage. Order selection is a crucial issue among these decisions especially for steel production industry. When the companies allocate a high proportion of their design and production capacities to their ongoing projects, determining which customer order should be chosen among the potential orders without exceeding the remaining capacity is the major critical problem. In this study, it is aimed to identify and prioritize the evaluation factors for the customer order selection problem. Conjoint analysis is used to examine the importance level of each factor which is determined as the potential profit rate per unit of time, the compatibility of potential order with available capacity, the level of potential future order with higher profit, customer credit of future business opportunity, and the negotiability level of production schedule for the order.

Keywords: conjoint analysis, order prioritization, profit management, structural steel firm

Procedia PDF Downloads 364
20729 Machine Learning Approach for Mutation Testing

Authors: Michael Stewart

Abstract:

Mutation testing is a type of software testing proposed in the 1970s where program statements are deliberately changed to introduce simple errors so that test cases can be validated to determine if they can detect the errors. Test cases are executed against the mutant code to determine if one fails, detects the error and ensures the program is correct. One major issue with this type of testing was it became intensive computationally to generate and test all possible mutations for complex programs. This paper used reinforcement learning and parallel processing within the context of mutation testing for the selection of mutation operators and test cases that reduced the computational cost of testing and improved test suite effectiveness. Experiments were conducted using sample programs to determine how well the reinforcement learning-based algorithm performed with one live mutation, multiple live mutations and no live mutations. The experiments, measured by mutation score, were used to update the algorithm and improved accuracy for predictions. The performance was then evaluated on multiple processor computers. With reinforcement learning, the mutation operators utilized were reduced by 50 – 100%.

Keywords: automated-testing, machine learning, mutation testing, parallel processing, reinforcement learning, software engineering, software testing

Procedia PDF Downloads 170
20728 Managing the Local Manager: A Comparative Study of Core HRM Functions in Multinationals

Authors: Maria Khan

Abstract:

Framing good core Human Resource Management (HRM) functions like recruitment, selection, training and development, which if executed effectively, can become a strategic advantage for a company. HRM policies related to mid-level managers can depend on the type of top management. This may be due to the difference in perception of effective HRM policies of an expatriate and local leadership. This comparative case study assesses how local mid-level managers are managed in leading multinational telecom companies in Pakistan. Core HRM functions related to managers were analysed through field research based on semi-structured interviews with relevant Human Resource Managers. Results suggest that recruitment and selection practices are not too different and are in compliance with best HRM practices. However, there is a difference in the effective implementation of Training and Development policies. Changing global management trends and skill development dictate that MNCs continuously develop the local talent effectively for local and international success.

Keywords: recruitment, selection, training, development, core HRM, human resource management, subsidiary, international staffing, managers, MNC, expatriate

Procedia PDF Downloads 292
20727 Evaluation of QSRR Models by Sum of Ranking Differences Approach: A Case Study of Prediction of Chromatographic Behavior of Pesticides

Authors: Lidija R. Jevrić, Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević

Abstract:

The present study deals with the selection of the most suitable quantitative structure-retention relationship (QSRR) models which should be used in prediction of the retention behavior of basic, neutral, acidic and phenolic pesticides which belong to different classes: fungicides, herbicides, metabolites, insecticides and plant growth regulators. Sum of ranking differences (SRD) approach can give a different point of view on selection of the most consistent QSRR model. SRD approach can be applied not only for ranking of the QSRR models, but also for detection of similarity or dissimilarity among them. Applying the SRD analysis, the most similar models can be found easily. In this study, selection of the best model was carried out on the basis of the reference ranking (“golden standard”) which was defined as the row average values of logarithm of retention time (logtr) defined by high performance liquid chromatography (HPLC). Also, SRD analysis based on experimental logtr values as reference ranking revealed similar grouping of the established QSRR models already obtained by hierarchical cluster analysis (HCA).

Keywords: chemometrics, chromatography, pesticides, sum of ranking differences

Procedia PDF Downloads 350
20726 Determining a Suitable Maintenance Measure for Gentelligent Components Using Case-Based Reasoning

Authors: Maximilian Winkens, Peter Nyhuis

Abstract:

Components with sensory properties such as gentelligent components developed at the Collaborative Research Center 653 offer a new angle on the full utilization of the remaining service life in case of a preventive maintenance. The developed methodology of component status driven maintenance analyses the stress data obtained during the component's useful life and on the basis of this knowledge assesses the type of maintenance called for in this case. The procedure is derived from the case-based reasoning method and will be elucidated in detail. The method's functionality is demonstrated with real-life data obtained during test runs of a racing car prototype.

Keywords: gentelligent component, preventive maintenance, case-based reasoning, sensory

Procedia PDF Downloads 339
20725 Practical Methods for Automatic MC/DC Test Cases Generation of Boolean Expressions

Authors: Sekou Kangoye, Alexis Todoskoff, Mihaela Barreau

Abstract:

Modified Condition/Decision Coverage (MC/DC) is a structural coverage criterion that aims to prove that all conditions involved in a Boolean expression can influence the result of that expression. In the context of automotive, MC/DC is highly recommended and even required for most security and safety applications testing. However, due to complex Boolean expressions that often embedded in those applications, generating a set of MC/DC compliant test cases for any of these expressions is a nontrivial task and can be time consuming for testers. In this paper we present an approach to automatically generate MC/DC test cases for any Boolean expression. We introduce novel techniques, essentially based on binary trees to quickly and optimally generate MC/DC test cases for the expressions. Thus, the approach can be used to reduce the manual testing effort of testers.

Keywords: binary trees, MC/DC, test case generation, nontrivial task

Procedia PDF Downloads 404
20724 A Review of Feature Selection Methods Implemented in Neural Stem Cells

Authors: Natasha Petrovska, Mirjana Pavlovic, Maria M. Larrondo-Petrie

Abstract:

Neural stem cells (NSCs) are multi-potent, self-renewing cells that generate new neurons. Three subtypes of NSCs can be separated regarding the stages of NSC lineage: quiescent neural stem cells (qNSCs), activated neural stem cells (aNSCs) and neural progenitor cells (NPCs), but their gene expression signatures are not utterly understood yet. Single-cell examinations have started to elucidate the complex structure of NSC populations. Nevertheless, there is a lack of thorough molecular interpretation of the NSC lineage heterogeneity and an increasing need for tools to analyze and improve the efficiency and correctness of single-cell sequencing data. Feature selection and ordering can identify and classify the gene expression signatures of these subtypes and can discover novel subpopulations during the NSCs activation and differentiation processes. The aim here is to review the implementation of the feature selection technique on NSC subtypes and the classification techniques that have been used for the identification of gene expression signatures.

Keywords: feature selection, feature similarity, neural stem cells, genes, feature selection methods

Procedia PDF Downloads 111
20723 A Rare Case of Acquired Benign Tracheoesophageal Fistula: Case Report and Literature Review

Authors: Sarah Bouayyad, Ajay Nigam, Meera Beena

Abstract:

Acquired benign tracheoesophageal fistula is a rare medical condition that usually results from trauma, foreign bodies, or granulomatous infections. This is an unusual presentation of a male patient with a history of laryngectomy who had had over a period of several years inappropriately and vigorously used valve cleaning brushes to clean tracheal secretions, which had led to the formation of a tracheoesophageal fistula. Due to the patient’s obsessive habit, we couldn’t manage him using conventional surgical methods. Instead, we opted for the placement of a salivary bypass tube, which yielded good results and recovery. To the best of our knowledge, no other case of similar etiology has been published. We would like to highlight the importance of appropriate patient selection and education prior to performing a tracheoesophageal puncture to avoid developing life-threatening complications as demonstrated in our case report.

Keywords: tracheoesophageal fistula, speech valve, endoscopic insertion of salivary bypass tube, head and neck malignancies

Procedia PDF Downloads 101
20722 A Fuzzy-Rough Feature Selection Based on Binary Shuffled Frog Leaping Algorithm

Authors: Javad Rahimipour Anaraki, Saeed Samet, Mahdi Eftekhari, Chang Wook Ahn

Abstract:

Feature selection and attribute reduction are crucial problems, and widely used techniques in the field of machine learning, data mining and pattern recognition to overcome the well-known phenomenon of the Curse of Dimensionality. This paper presents a feature selection method that efficiently carries out attribute reduction, thereby selecting the most informative features of a dataset. It consists of two components: 1) a measure for feature subset evaluation, and 2) a search strategy. For the evaluation measure, we have employed the fuzzy-rough dependency degree (FRFDD) of the lower approximation-based fuzzy-rough feature selection (L-FRFS) due to its effectiveness in feature selection. As for the search strategy, a modified version of a binary shuffled frog leaping algorithm is proposed (B-SFLA). The proposed feature selection method is obtained by hybridizing the B-SFLA with the FRDD. Nine classifiers have been employed to compare the proposed approach with several existing methods over twenty two datasets, including nine high dimensional and large ones, from the UCI repository. The experimental results demonstrate that the B-SFLA approach significantly outperforms other metaheuristic methods in terms of the number of selected features and the classification accuracy.

Keywords: binary shuffled frog leaping algorithm, feature selection, fuzzy-rough set, minimal reduct

Procedia PDF Downloads 188
20721 On Hyperbolic Gompertz Growth Model (HGGM)

Authors: S. O. Oyamakin, A. U. Chukwu,

Abstract:

We proposed a Hyperbolic Gompertz Growth Model (HGGM), which was developed by introducing a stabilizing parameter called θ using hyperbolic sine function into the classical gompertz growth equation. The resulting integral solution obtained deterministically was reprogrammed into a statistical model and used in modeling the height and diameter of Pines (Pinus caribaea). Its ability in model prediction was compared with the classical gompertz growth model, an approach which mimicked the natural variability of height/diameter increment with respect to age and therefore provides a more realistic height/diameter predictions using goodness of fit tests and model selection criteria. The Kolmogorov-Smirnov test and Shapiro-Wilk test was also used to test the compliance of the error term to normality assumptions while using testing the independence of the error term using the runs test. The mean function of top height/Dbh over age using the two models under study predicted closely the observed values of top height/Dbh in the hyperbolic gompertz growth models better than the source model (classical gompertz growth model) while the results of R2, Adj. R2, MSE, and AIC confirmed the predictive power of the Hyperbolic Monomolecular growth models over its source model.

Keywords: height, Dbh, forest, Pinus caribaea, hyperbolic, gompertz

Procedia PDF Downloads 416
20720 A Selection Approach: Discriminative Model for Nominal Attributes-Based Distance Measures

Authors: Fang Gong

Abstract:

Distance measures are an indispensable part of many instance-based learning (IBL) and machine learning (ML) algorithms. The value difference metrics (VDM) and inverted specific-class distance measure (ISCDM) are among the top-performing distance measures that address nominal attributes. VDM performs well in some domains owing to its simplicity and poorly in others that exist missing value and non-class attribute noise. ISCDM, however, typically works better than VDM on such domains. To maximize their advantages and avoid disadvantages, in this paper, a selection approach: a discriminative model for nominal attributes-based distance measures is proposed. More concretely, VDM and ISCDM are built independently on a training dataset at the training stage, and the most credible one is recorded for each training instance. At the test stage, its nearest neighbor for each test instance is primarily found by any of VDM and ISCDM and then chooses the most reliable model of its nearest neighbor to predict its class label. It is simply denoted as a discriminative distance measure (DDM). Experiments are conducted on the 34 University of California at Irvine (UCI) machine learning repository datasets, and it shows DDM retains the interpretability and simplicity of VDM and ISCDM but significantly outperforms the original VDM and ISCDM and other state-of-the-art competitors in terms of accuracy.

Keywords: distance measure, discriminative model, nominal attributes, nearest neighbor

Procedia PDF Downloads 89
20719 Feature Extraction and Classification Based on the Bayes Test for Minimum Error

Authors: Nasar Aldian Ambark Shashoa

Abstract:

Classification with a dimension reduction based on Bayesian approach is proposed in this paper . The first step is to generate a sample (parameter) of fault-free mode class and faulty mode class. The second, in order to obtain good classification performance, a selection of important features is done with the discrete karhunen-loeve expansion. Next, the Bayes test for minimum error is used to classify the classes. Finally, the results for simulated data demonstrate the capabilities of the proposed procedure.

Keywords: analytical redundancy, fault detection, feature extraction, Bayesian approach

Procedia PDF Downloads 503
20718 Analysis of the Engineering Judgement Influence on the Selection of Geotechnical Parameters Characteristic Values

Authors: K. Ivandic, F. Dodigovic, D. Stuhec, S. Strelec

Abstract:

A characteristic value of certain geotechnical parameter results from an engineering assessment. Its selection has to be based on technical principles and standards of engineering practice. It has been shown that the results of engineering assessment of different authors for the same problem and input data are significantly dispersed. A survey was conducted in which participants had to estimate the force that causes a 10 cm displacement at the top of a axially in-situ compressed pile. Fifty experts from all over the world took part in it. The lowest estimated force value was 42% and the highest was 133% of measured force resulting from a mentioned static pile load test. These extreme values result in significantly different technical solutions to the same engineering task. In case of selecting a characteristic value of a geotechnical parameter the importance of the influence of an engineering assessment can be reduced by using statistical methods. An informative annex of Eurocode 1 prescribes the method of selecting the characteristic values of material properties. This is followed by Eurocode 7 with certain specificities linked to selecting characteristic values of geotechnical parameters. The paper shows the procedure of selecting characteristic values of a geotechnical parameter by using a statistical method with different initial conditions. The aim of the paper is to quantify an engineering assessment in the example of determining a characteristic value of a specific geotechnical parameter. It is assumed that this assessment is a random variable and that its statistical features will be determined. For this purpose, a survey research was conducted among relevant experts from the field of geotechnical engineering. Conclusively, the results of the survey and the application of statistical method were compared.

Keywords: characteristic values, engineering judgement, Eurocode 7, statistical methods

Procedia PDF Downloads 272
20717 Recruitment Model (FSRM) for Faculty Selection Based on Fuzzy Soft

Authors: G. S. Thakur

Abstract:

This paper presents a Fuzzy Soft Recruitment Model (FSRM) for faculty selection of MHRD technical institutions. The selection criteria are based on 4-tier flexible structure in the institutions. The Advisory Committee on Faculty Recruitment (ACoFAR) suggested nine criteria for faculty in the proposed FSRM. The model Fuzzy Soft is proposed with consultation of ACoFAR based on selection criteria. The Fuzzy Soft distance similarity measures are applied for finding best faculty from the applicant pool.

Keywords: fuzzy soft set, fuzzy sets, fuzzy soft distance, fuzzy soft similarity measures, ACoFAR

Procedia PDF Downloads 318
20716 The Effects of Training Load on Some Selected Fitness Variables in the Case of U-17 Female Volleyball Project Players, Central Ethiopia

Authors: Behailu Shigute Habtemariam

Abstract:

The aim of the study was to examine the effects of training load on some selected fitness performance variables of volleyball players in the case of U-17 female volleyball project players in the central Ethiopia region. Methods: In this study, quasi-experimental design was used. For the purpose of this study, twenty-three volleyball players were used as a subject from the two projects. The data collected through fitness performance assessment were analyzed and interpreted into a meaningful idea using manually as well as with computer in order to compare physical fitness variables and changes observed among participants. Those are taking part in the effects of training load on some selected physical fitness variables. The collected data were analyzed by means of the Statistical Package for Social Science version (SPSS V 20). The independent t-test was used to show the mean differences between the groups, and the paired T-test was used to compare the mean differences of the pre and post-training within each group. The level of significance will be set at Alfa 0.05. Results: The results are displayed using tables and figures. A significant difference was found in the mean differences of pre-test values (19.7 cm) and post-test values (37.5 cm) of the Durame city project on the flexibility test (MD =17.8 cm, P = 0.00). On the other hand, there was a significant difference in the mean difference of pre-test values of (18 cm) and post-test values (26.3 cm) of the Hosana city project on the flexibility test ( MD = 8.3 cm, P = 0.00). Conclusion: According to the results of the present studies, there were significant improvements from pre to post-test at Durame City and Hosana City projects on agility, flexibility, power, and speed fitness tests. On the other hand, a significant difference was not found before beginning the exercise between the two projects; however, a significant difference was found after 12 weeks of training.

Keywords: overload, performance, training, volleyball

Procedia PDF Downloads 60
20715 Application of Artificial Intelligence in EOR

Authors: Masoumeh Mofarrah, Amir NahanMoghadam

Abstract:

Higher oil prices and increasing oil demand are main reasons for great attention to Enhanced Oil Recovery (EOR). Comprehensive researches have been accomplished to develop, appraise, and improve EOR methods and their application. Recently, Artificial Intelligence (AI) gained popularity in petroleum industry that can help petroleum engineers to solve some fundamental petroleum engineering problems such as reservoir simulation, EOR project risk analysis, well log interpretation and well test model selection. This study presents a historical overview of most popular AI tools including neural networks, genetic algorithms, fuzzy logic, and expert systems in petroleum industry and discusses two case studies to represent the application of two mentioned AI methods for selecting an appropriate EOR method based on reservoir characterization infeasible and effective way.

Keywords: artificial intelligence, EOR, neural networks, expert systems

Procedia PDF Downloads 465
20714 Design of a Tool for Generating Test Cases from BPMN

Authors: Prat Yotyawilai, Taratip Suwannasart

Abstract:

Business Process Model and Notation (BPMN) is more important in the business process and creating functional models, and is a standard for OMG, which becomes popular in various organizations and in education. Researches related to software testing based on models are prominent. Although most researches use the UML model in software testing, not many researches use the BPMN Model in creating test cases. Therefore, this research proposes a design of a tool for generating test cases from the BPMN. The model is analyzed and the details of the various components are extracted before creating a flow graph. Both details of components and the flow graph are used in generating test cases.

Keywords: software testing, test case, BPMN, flow graph

Procedia PDF Downloads 529
20713 Analytic Network Process in Location Selection and Its Application to a Real Life Problem

Authors: Eylem Koç, Hasan Arda Burhan

Abstract:

Location selection presents a crucial decision problem in today’s business world where strategic decision making processes have critical importance. Thus, location selection has strategic importance for companies in boosting their strength regarding competition, increasing corporate performances and efficiency in addition to lowering production and transportation costs. A right choice in location selection has a direct impact on companies’ commercial success. In this study, a store location selection problem of Carglass Turkey which operates in vehicle glass branch is handled. As this problem includes both tangible and intangible criteria, Analytic Network Process (ANP) was accepted as the main methodology. The model consists of control hierarchy and BOCR subnetworks which include clusters of actors, alternatives and criteria. In accordance with the management’s choices, five different locations were selected. In addition to the literature review, a strict cooperation with the actor group was ensured and maintained while determining the criteria and during whole process. Obtained results were presented to the management as a report and its feasibility was confirmed accordingly.

Keywords: analytic network process (ANP), BOCR, multi-actor decision making, multi-criteria decision making, real-life problem, location selection

Procedia PDF Downloads 445
20712 Partner Selection in International Strategic Alliances: The Case of the Information Industry

Authors: H. Nakamura

Abstract:

This study analyzes international strategic alliances in the information industry. The purpose of this study is to clarify the strategic intention of an international alliance. Secondly, it investigates the influence of differences in the target markets of partner companies on alliances. Using an international strategy theory approach to analyze the global strategies of global companies, the study compares a database business and an electronic publishing business. In particular, these cases emphasized factors attributable to "people" and "learning", reliability and communication between organizations and the evolution of the IT infrastructure. The theory evolved in this study validates the effectiveness of these strategies.

Keywords: database business, electronic library, international strategic alliances, partner selection

Procedia PDF Downloads 351
20711 A Survey on the Status of Test Automation

Authors: Andrei Contan, Richard Torkar

Abstract:

Aim: The process of test automation and its practices in industry have to be better understood, both for the industry itself and for the research community. Method: We conducted a quantitative industry survey by asking IT professionals to answer questions related to the area of test automation. Results: Test automation needs and practices vary greatly between organizations at different stages of the software development life cycle. Conclusions: Most of the findings are general test automation challenges and are specific to small- to medium-sized companies, developing software applications in the web, desktop or mobile domain.

Keywords: survey, testing, test automation, status of test automation

Procedia PDF Downloads 621
20710 Literature Review: Application of Artificial Intelligence in EOR

Authors: Masoumeh Mofarrah, Amir NahanMoghadam

Abstract:

Higher oil prices and increasing oil demand are main reasons for great attention to Enhanced Oil Recovery (EOR). Comprehensive researches have been accomplished to develop, appraise and improve EOR methods and their application. Recently Artificial Intelligence (AI) gained popularity in petroleum industry that can help petroleum engineers to solve some fundamental petroleum engineering problems such as reservoir simulation, EOR project risk analysis, well log interpretation and well test model selection. This study presents a historical overview of most popular AI tools including neural networks, genetic algorithms, fuzzy logic and expert systems in petroleum industry and discusses two case studies to represent the application of two mentioned AI methods for selecting an appropriate EOR method based on reservoir characterization in feasible and effective way.

Keywords: artificial intelligence, EOR, neural networks, expert systems

Procedia PDF Downloads 382
20709 Balanced Ischemia Misleading to a False Negative Myocardial Perfusion Imaging (Stress) Test

Authors: Devam Sheth

Abstract:

Nuclear imaging with stress myocardial perfusion (stress test) is the preferred first line investigation for noninvasive evaluation of ischaemic heart condition. The sensitivity of this test is close to 90 % making it a very reliable test. However, rarely it gives a false negative result which can be explained by the phenomenon termed as “balanced ischaemia”. We present the case of a 78 year Caucasian female without any significant past cardiac history, who presents with chest pain and shortness of breath since one day. The initial ECG and cardiac enzymes were non-impressive. Few hours later, she had some substernal chest pain along with some ST segment depression in the lateral leads. Stress test comes back negative for any significant perfusion defects. However, given her typical symptoms, she underwent a cardiac catheterization which revealed significant triple vessel disease mandating her to get a bypass surgery. This unusual phenomenon of false nuclear stress test in the setting of positive ECG changes can be explained only by balanced ischemia wherein due to global myocardial ischemia, the stress test fails to reveal relative perfusion defects in the affected segments.

Keywords: balanced, false positive, ischemia, myocardial perfusion imaging

Procedia PDF Downloads 274
20708 A Comparative Study of k-NN and MLP-NN Classifiers Using GA-kNN Based Feature Selection Method for Wood Recognition System

Authors: Uswah Khairuddin, Rubiyah Yusof, Nenny Ruthfalydia Rosli

Abstract:

This paper presents a comparative study between k-Nearest Neighbour (k-NN) and Multi-Layer Perceptron Neural Network (MLP-NN) classifier using Genetic Algorithm (GA) as feature selector for wood recognition system. The features have been extracted from the images using Grey Level Co-Occurrence Matrix (GLCM). The use of GA based feature selection is mainly to ensure that the database used for training the features for the wood species pattern classifier consists of only optimized features. The feature selection process is aimed at selecting only the most discriminating features of the wood species to reduce the confusion for the pattern classifier. This feature selection approach maintains the ‘good’ features that minimizes the inter-class distance and maximizes the intra-class distance. Wrapper GA is used with k-NN classifier as fitness evaluator (GA-kNN). The results shows that k-NN is the best choice of classifier because it uses a very simple distance calculation algorithm and classification tasks can be done in a short time with good classification accuracy.

Keywords: feature selection, genetic algorithm, optimization, wood recognition system

Procedia PDF Downloads 513
20707 Decision Support System for Examination Selection

Authors: Katejarinporn Chaiya, Jarumon Nookong, Nutthapat Kaewrattanapat

Abstract:

The purposes of this research were to develop and find users’ satisfaction after using the Decision Support System for Examination Selection. This research presents the design of information systems. In order to find the necessary examination of the statistics. Based on the examination of the candidate and then taking the easy difficulty setting statistics applied to the test. In addition, research has also made performance appraisals from experts and user satisfaction. By results of analysis showed that the performance appraisals from experts on the system as a whole and at a good level. mean was 3.44 and S.D. was 0.55 and user satisfaction per system as a whole and the good level mean was 3.37 and S.D. was 0.42 can conclude that effective systems are in a good level. Work has been completed in accordance with the scope of work. The website used developing this project is PHP, MySQL.5.0.45 for database.

Keywords: secision support system, examination, PHP, information systems

Procedia PDF Downloads 422
20706 Ranking of Inventory Policies Using Distance Based Approach Method

Authors: Gupta Amit, Kumar Ramesh, P. C. Tewari

Abstract:

Globalization is putting enormous pressure on the business organizations specially manufacturing one to rethink the supply chain in innovative manners. Inventory consumes major portion of total sale revenue. Effective and efficient inventory management plays a vital role for the successful functioning of any organization. Selection of inventory policy is one of the important purchasing activities. This paper focuses on selection and ranking of alternative inventory policies. A deterministic quantitative model-based on Distance Based Approach (DBA) method has been developed for evaluation and ranking of inventory policies. We have employed this concept first time for this type of the selection problem. Four inventory policies Economic Order Quantity (EOQ), Just in Time (JIT), Vendor Managed Inventory (VMI) and monthly policy are considered. Improper selection could affect a company’s competitiveness in terms of the productivity of its facilities and quality of its products. The ranking of inventory policies is a multi-criteria problem. There is a need to first identify the selection criteria and then processes the information with reference to relative importance of attributes for comparison. Criteria values for each inventory policy can be obtained either analytically or by using a simulation technique or they are linguistic subjective judgments defined by fuzzy sets, like, for example, the values of criteria. A methodology is developed and applied to rank the inventory policies.

Keywords: inventory policy, ranking, DBA, selection criteria

Procedia PDF Downloads 356
20705 Web Service Architectural Style Selection in Multi-Criteria Requirements

Authors: Ahmad Mohsin, Syda Fatima, Falak Nawaz, Aman Ullah Khan

Abstract:

Selection of an appropriate architectural style is vital to the success of target web service under development. The nature of architecture design and selection for service-oriented computing applications is quite different as compared to traditional software. Web Services have complex and rigorous architectural styles to choose. Due to this, selection for accurate architectural style for web services development has become a more complex decision to be made by architects. Architectural style selection is a multi-criteria decision and demands lots of experience in service oriented computing. Decision support systems are good solutions to simplify the selection process of a particular architectural style. Our research suggests a new approach using DSS for selection of architectural styles while developing a web service to cater FRs and NFRs. Our proposed DSS helps architects to select right web service architectural pattern according to the domain and non-functional requirements. In this paper, a rule base DSS has been developed using CLIPS (C Language Integrated Production System) to support decisions using multi-criteria requirements. This DSS takes architectural characteristics, domain requirements and software architect preferences for NFRs as input for different architectural styles in use today in service-oriented computing. Weighted sum model has been applied to prioritize quality attributes and domain requirements. Scores are calculated using multiple criterions to choose the final architecture style.

Keywords: software architecture, web-service, rule-based, DSS, multi-criteria requirements, quality attributes

Procedia PDF Downloads 332
20704 A Review of the Parameters Used in Gateway Selection Schemes for Internet Connected MANETs

Authors: Zainab S. Mahmood, Aisha H. Hashim, Wan Haslina Hassan, Farhat Anwar

Abstract:

The wide use of the internet-based applications bring many challenges to the researchers to guarantee the continuity of the connections needed by the mobile hosts and provide reliable Internet access for them. One of proposed solutions by Internet Engineering Task Force (IETF) is to connect the local, multi-hop, and infrastructure-less Mobile Ad hoc Network (MANET) with Internet structure. This connection is done through multi-interface devices known as Internet Gateways. Many issues are related to this connection like gateway discovery, hand off, address auto-configuration and selecting the optimum gateway when multiple gateways exist. Many studies were done proposing gateway selection schemes with a single selection criterion or weighted multiple criteria. In this research, a review of some of these schemes is done showing the differences, the features, the challenges and the drawbacks of each of them.

Keywords: Internet Gateway, MANET, mobility, selection criteria

Procedia PDF Downloads 396
20703 Mastering Test Automation: Bridging Gaps for Seamless QA

Authors: Rohit Khankhoje

Abstract:

The rapid evolution of software development practices has given rise to an increasing demand for efficient and effective test automation. The paper titled "Mastering Test Automation: Bridging Gaps for Seamless QA" delves into the crucial aspects of test automation, addressing the obstacles faced by organizations in achieving flawless quality assurance. The paper highlights the importance of bridging knowledge gaps within organizations, emphasizing the necessity for management to acquire a deeper comprehension of test automation scenarios, coverage, report trends, and the importance of communication. To tackle these challenges, this paper introduces innovative solutions, including the development of an automation framework that seamlessly integrates with test cases and reporting tools like TestRail and Jira. This integration facilitates the automatic recording of bugs in Jira, enhancing bug reporting and communication between manual QA and automation teams as well as TestRail have all newly added automated testcases as soon as it is part of the automation suite. The paper demonstrates how this framework empowers management by providing clear insights into ongoing automation activities, bug origins, trend analysis, and test case specifics. "Mastering Test Automation" serves as a comprehensive guide for organizations aiming to enhance their quality assurance processes through effective test automation. It not only identifies the common pitfalls and challenges but also offers practical solutions to bridge the gaps, resulting in a more streamlined and efficient QA process.

Keywords: automation framework, API integration, test automation, test management tools

Procedia PDF Downloads 46