Department of Modeling and Design Engineering Systems
Permanent URI for this collection
Browse
Browsing Department of Modeling and Design Engineering Systems by Subject "industrial engineering"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
Item ARTIFICIAL NEURAL NETWORK BASED DECISIVE PREDICTION MODELS ON HIGH FREQUENCY FINANCIAL DATA(2017-01-07) Karaçor, Adil Gürsel; Erkan, Turan ErmanHigh frequency financial data are somewhat hard to model or predict, if not totally impossible, as stochastic processes and many other random factors are involved. In this thesis; a novel Artificial Intelligence model is designed and developed for financial time series prediction and decision making. Possibility to enhance prediction accuracy for foreign exchange rates is investigated in two ways: first applying an outside the box approach by bringing about methodology and techniques to facilitate the use of predictive models in engineering design to model price graphs by exploiting their visual properties together with principles of chaos theory, and secondly employing the most efficient methods to detect patterns to classify the direction of movement. The approach that exploits the visual properties of price graphs makes use of density regions along with high and low values describing the shape just as in Machine Vision. Mainly Artificial Neural Networks are used in modeling. However, other state-of-the-art methods; Extreme Gradient Boosting and Support Vector Machine are too used for comparison. The designed system is also software coded as a real-time trading robot. Comparable prediction results and profits are achieved in tests and simulations.Item DEVELOPMENT OF DECISION SUPPORT MODEL FOR SELECTING AN EQUIPMENT MAINTENANCE PLAN USING A FUZZY MCDM APPROACH(2022-01-26) ABDULGADER, Fathia Sghayer; Erdebilli, BabekIn complex decision making, using multi-criteria decision making (MCDM) methodologies is the most scientific way to ensure an informed and justified decision between several alternatives. MCDM’s have been used in different ways and with several applications that proved their efficiency in achieving this goal. In this research, the advantages and disadvantages of the different MCDM methodologies are studied, along with the different techniques implemented to increase their accuracy and precision. The main aim of the study is to develop a hybrid MCDM process that combines the strengths of several MCDM methods and apply it to choose the best fit maintenance policy/ strategy for industrial application. Moreover, fuzzy linguistic terms are utilized in all of the used MCDM techniques in order to eliminate the uncertainty and ambiguity of the results. Through an extensive literature review performed on studies that have used MCDM methods in a hybrid context and using fuzzy linguistic terms, a model is developed to use fuzzy DEMATEL-AHP-TOPSIS hybrid technique. The model with its application is the first of its kind, which combines the strengths of fuzzy DEMATEL in establishing interrelationships between the several criteria, as well as performing a pairwise comparison between the criteria for prioritization using the fuzzy AHP method. Thereafter, the alternatives are compared using fuzzy TOPSIS method by establishing negative and positive solutions and calculating the relative closeness for each of the alternatives. Furthermore, six main criteria, twenty-four sub criteria, and five alternatives are selected from the literature for the model application. The findings of the research show that predictive maintenance is the best choice as a maintenance plan, followed closely by preventive maintenance. The results of the research confirmed the success of the developed model to select maintenance plans based on experts’ inputs and using the developed fuzzy MCDM approach.Item DEVELOPMENT OF EFFECTIVE METHODOLOGY FOR IMPROVING UNDERGRADUATE PROGRAM CURRICULUM IN HIGHER EDUCATION UTILIZING SIX SIGMA APPROACH(2022-02-15) Dakhil, Abdulmuhsen; Özkil, AltanThe curriculum structure of undergraduate programs in all universities is based on the required knowledge, skills, and attitudes needed in business life by graduates of related department. Graduates will use their knowledge, skills, and competencies to fulfill the requirements of jobs related with selected department. However, there is a general concern that the existing undergraduate programs of universities are not providing graduates with the required level of knowledge, skills, and attitudes that they will need in order to succeed in professional practice. This simply shows the gap between what is taught in university and what is needed in industry. For that reason, a considerable number of graduates are employed in the industrial environment where there isn’t often close match between the elements of their education, and the skills and knowledge required for the success in the industry. As a result, the academia has been attempting to improve curricula for many years. Some new courses are added, some of current courses are deleted, and some of the current courses are combined. A remarkable amount of research has been conducted on curriculum development. What is lacking, a methodology that incorporates the many dimensions that affecting the process of curriculum improvement as well as quantitative tools that address the requirements of the various stakeholders that are essential to improving the curriculum. The aim of this study is developing a quantitative methodology utilizing Six-Sigma quality improvement approach to make the changes required for improving undergraduate program curriculum of higher education institutions. The changes needed for improving the curriculum can be identified in terms of knowledge, skills, and competencies that graduate from a particular program curriculum need to possess by implementing this methodology. The developed methodology was implemented to make improvement in one of the engineering departments in higher education. Manufacturing engineering department was selected for this purpose. A set of desired competencies were developed from the exiting data related to manufacturing engineering programs. This set is then used in the development of a comprehensive survey to capture different perspectives from various stakeholders such as graduates, employers, and academics. Statistical analysis of the survey was done by SPSS to get some information about the importance and their roles in the performance of developed competencies to identify where improvement efforts to be targeted. Some changes to the current curriculum of the manufacturing engineering department were proposed by using the developed methodology. Proposed changes were verified by using commercial recruitment adds for the manufacturing engineering department in kariyer.net.Item INTEGRATING LEAN SIX SIGMA WITH AGILE SOFTWARE DEVELOPMENT METHODOLOGY(2022-02-16) Badwe, Safia; ERKAN, Turan ErmanIn the last two decades, the Six Sigma approach has also experienced extended introduction into the software development industry, with lean thinking emerging as a new paradigm to make the process more efficient. Some software companies have been trying to adapt Six Sigma and Lean for their business and development initiatives. Lean Six Sigma (LSS) accelerates the test and reconciliation aspects of item advancement and makes room for providing top-notch products to purchasers. Still, a need for constant change and transformation has forced organizations into adopting to complex and new working environments, resulting in software development methodologies to become a framework for planning and coordinating programs and communicating with customers so as to collect the requirements. In this respect, LSS and Agile methodologies are regarded as a set of development initiatives to satisfy such demands at an early stage and incorporate high-quality changes into the software development process; hence the present study explores the relationship between the methodologies mentioned above in software development. This research presents the results from a theoretical and empirical part. The first part is to introduce a model that combines the operational stages to examine Six Sigma, Lean, Lean Six Sigma, Agile and Scrum methodologies to try and devise a new approach called ‗LSS-Agile‘ methodology. The second part presents the results of a survey study conducted with practitioners of software development companies in Turkey and abroad. The questionnaire focuses on several aspects, most importantly: benefits implementation, critical success factors, satisfaction, change requirements, experiences, and problems faced when using methodologies. The empirical perspective is analyzed by developing hypotheses about the concepts and factors on the study of methodologies and their impact on software development. The results highlight the most important factors leading to the success and failure of software development as well as the most beneficial aspects of the performance of methodologies. To this end, the analysis of the Lean Six Sigma and Agile methodology, their interrelationships helps to better understand the idea of integrating the two. As a comparisons carried out between a number of Turkish and Canadian companies specializing in this field, the results confirm that Turkish companies in the software development sector entered the world market from the widest successfully and have become one of the most competitive countries in this field.Item LOAD DEMAND FORECASTING USING ARTIFICIAL NEURAL NETWORKS AND FUZZY LOGIC METHODS(2022-05-12) AL-ANI, BARQ RAAD KHASHEI; ERKAN, Turan ErmanThis study proposes using artificial neural networks (ANNs) and fuzzy logic (FL) to estimate load demand data to forecast hourly electricity loads in Turkey or 2017 and 2018. We used Real Time Consumption as hourly electric load based on EPİAŞ data for 2017 to 2018. The load forecast was actualized using two machine learning techniques: ANN and fuzzy logic FL. The predicted data was compared to the actual data by plotting on a graph. This study used the ANN and FL methods to optimise the demand for load forecast in Turkey's power systems. The first and last 200 hours were plotted on ANN to get a better visualisation pattern, and the overall estimated hourly load for Turkey was calculated by adding the hourly estimations from each area. The minimum and maximum readings for the year 2017 are 18851.35 MWh and 47062.40 MWh whereas the mean and standard deviation readings are 33102.19 Mwh and 4968.67 MWh. As a result, the comparison of these models was used to forecast the load, all of which have different load patterns and origins. The series are stationary across the year and it peaks during the month of August. The MAPE values for FL for 2017 and 2018 are 3.7986094 and 5.28635983 respectively which is very good and falls in high accurate forecasting results. It can be concluded that the FL gives a better prediction than the ANN for both years. Electrical peak reduction is a vital component of any plan for managing energy demand, and forecasting electric load assists in planning peak load demand reductions to meet energy demand management targets. It can be concluded that the FL gives us a better prediction than the ANN for both years. Home, energy management research will benefit from the new load forecasting models proposed in this study.Item STRATEGIC PLAN MEASUREMENT AND EVALUATION TOOL (SMET) FOR ORGANIZATIONS(2022-02-28) Kuyrukçu, Ayşe; Özkil, Altan; Özaktaş, HakanThe corporate level performance evaluation for strategic management has become a challenge for business world. Over time, many performance measurement techniques have been developed and used to measure strategic level performance. There are some models and methodologies developed for this purpose. An outstanding approach, Balanced Scorecard (BSC), developed by Kaplan and Norton in 1992, has become popular and has been successful in comparison to others. The primary weakness of all these methods is not to offer clear answers about how the performance criteria defined at the operational level should be reflected to the top of strategic plan’s hierarchy. What is common in most implementations is to adjust the company constraints to make them suitable with the solution tool with the help of expert and technical support instead of tayloring the solution tool to company needs. This would mean the renewal of the strategic plan of the company disregarding the older one and hence an unpreferable option in most cases. In this study, a methodology was developed by using Saaty scale for prioritization and Simple Additive Weighting Method (SAW) in reflecting the upper level categorization of operational level. With the addition of Simple Multi Attribute Rating Technique (SMART) method to this methodology, a novel decision support system software, called SMET (Strategic-plan Measurement and Evaluation Tool) has been developed. An organization which prepares a strategic plan may measure and evaluate its success ratio to satisfy all its objectives and aims with different set of priorities by providing actual and ideal performance indicators using SMET. An organization which identifies its current strategic plan in SMET will be able to calculate the realization ratio of the firm's strategic plan within seconds based on the five different prioritization methods in the system (scoring, ranking, pairwise comparison, weighted pair-wise comparison and user's own choice).