Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this communityhttps://hdl.handle.net/11413/11

Browse

Now showing 1 - 20 of 50

Metadata only
Analysis of the Lingering Effects of COVID-19 on Distance Education
(Springer Science and Business Media Deutschland GmbH, 2023) KOCAÇINAR, BÜŞRA; QARIZADA, NASIBULLAH; DİKKAYA, CİHAN; AZGUN, EMİRHAN; ELİF, YILDIRIM; AKBULUT, FATMA PATLAR
Education has been severely impacted by the spread of the COVID-19 virus. In order to prevent the spread of the COVID-19 virus and maintain education in the current climate, governments have compelled the public to adopt online platforms. Consequently, this decision has affected numerous lives in various ways. To investigate the impact of COVID-19 on students’ education, we amassed a dataset consisting of 10,000 tweets. The motivations of the study are; (i) to analyze the positive, negative, and neutral effects of COVID-19 on education; (ii) to analyze the opinions of stakeholders in their tweets about the transition from formal education to e-learning; (iii) to analyze people’s feelings and reactions to these changes; and (iv) to analyze the effects of different training methods on different groups. We constructed emotion recognition models utilizing shallow and deep techniques, including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long-short Term Memory (LSTM), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and Logical Regression (LR). RF algorithms with a bag-of-words model outperformed with over 80% accuracy in recognizing emotions.
Metadata only
An Analytical Approach to Machine Layout Design at a High-Pressure Die Casting Manufacturer
(Springer-Verlag Singapore Pte Ltd., 2022) EMİR, OĞUZ; AKTİN, AYŞE TÜLİN
Sahin Metal was founded in 1975 on a 7500 m(2) area in.Istanbul to supply high-pressure aluminum casting parts to a variety of industries, especially automotive manufacturers. 64 different products are produced with various routings through 14 workstations in the plant. Being a Tier 2 company, these products are then sent to Tier 1 firms and finally reach the leading vehicle manufacturers. Nowadays, increasing competition, changing customer demands, and quality targets bring the necessity of restructuring internal processes. In this regard, Sahin Metal plans to rearrange the existing machine layout to minimize the distance traveled between departments by taking into account the material flow. This study aims to determine an efficient machine layout design by implementing analytical approaches. The study is started by visiting the production facility and meeting with the company's engineers to determine the project roadmap. Following that, the data collection process is initiated, and ABC analysis is performed to define product classes. After this identification, two approaches are utilized simultaneously. The Hollier method is employed to find a logical machine arrangement. In addition, a mathematical model based on the Quadratic Assignment Problem (QAP) is developed to obtain the optimum machine layout. The developed integer nonlinear model is solved by CONOPT using GAMS software under various scenarios. Finally, these results are compared with the existing system, and a convenient layout design is proposed to the company.
Metadata only
Analyzing the Operations at a Textile Manufacturer’s Logistics Center Using Lean Tools
(Springer Science and Business Media Deutschland GmbH, 2024) GÜNAY, AHMET CAN; ÖZBEK ,ONUR; MUTLU, FİLİZ; AKTİN, AYŞE TÜLİN
Compliance with delivery times is crucial for businesses in the logistics sector. Numerous research has been conducted to improve distribution performance. Many of these studies touch on lean production as well. The strategies used in lean manufacturing are often employed by businesses and have a positive impact on performance. This study focuses on the overseas shipping department of a textile company’s logistics center. Workflow starts with product acceptance from manufacturers and ends with shipment to customers abroad. After a thorough examination, some bottlenecks that increase delivery times are observed. Value Stream Mapping (VSM), which is a lean manufacturing technique, is chosen as the main method to be used. It aims to determine value added and non-value-added activities, resulting in minimizing or eliminating the non-value-added ones. Initially, necessary data are gathered through workshops and interviews, and observations on Current State VSM are made. During these workshops, various improvements are proposed and evaluated together with the company’s engineers. After takt time and cycle time calculations, label change station is identified as the bottleneck. In the next step, Kaizens are suggested for the stations, and some lean techniques are employed to solve different workflow problems. Finally, short-term applicability of proposed improvements is discussed, and Future State VSM is drawn. It can be concluded that significant improvements are achieved especially in lead time, changeover time, productivity rate and production speed. By reducing or eliminating non-value-added activities and identifying deficiencies that slow process flow, a standard, sustainable and developable process is proposed to the company. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Metadata only
ANNs-Based Prediction Models for Consistency and Compaction Characteristics of Bentonite–Sand Mixtures
(Springer Nature, 2024) Yücel, Melda; Akbay Arama, Zülal; GENÇDAL, HAZAL BERRAK; BAŞBUĞ, BEGÜM; SEÇKİN, EDİP
This study is fictionalized with the use of ANNs logic to estimate the compaction parameters of bentonite–sand mixtures. Totally 230 sets of tests were digitized from the nine well-accepted literature sources to specify the grain size, consistency, and compaction parameters of the bentonite–sand mixtures. Matlab R2018a software is used to perform the estimation process of the compaction parameters, and representative expressions were derived to ease the determination process of mixtures. Consequently, the applicability of the suggested expressions has been checked by the determination and comparison of well-known international metric measurements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Metadata only
The Applicability of Regression Analysis and Artificial Neural Networks to the Prediction Process of Consistency and Compaction Properties of High Plastic Clays
(Springer Science and Business Media Deutschland GmbH, 2021) Akbay Arama, Zülal; GENÇDAL, HAZAL BERRAK; Nuray, Said Enes; Yücel, Melda
In all kinds of site investigation reports prepared to acquire the current situation of the project site, it is a common fact to perform the consistency tests which are specialized as Atterberg limit tests. Consistency can be defined as an important term, especially for fine-grained soils, to appoint the current state of the water content of soil formation in the field. Based on the ease and cost-effectiveness of the Atterberg tests, it has become a traditional solution to determine the fundamental design properties such as the rigidity and strength of the soil formation with the use of empirical approaches that are developed according to them. In this context, “compaction” can be an interesting term to investigate the appropriateness of determination of special characteristics of the phenomenon such as the optimum water content and the maximum dry unit weight with the development of a new perspective based on a simplest experimental process formed with only the evaluation of water content. Because it is a complicated and time-consuming process to apply the compaction test beginning of the sample preparation step to the ultimate evaluation step. Hence, in this paper, an integrated study is performed for highly plastic clays to acquire the consistency and the compaction properties together with a direct relationship. A huge database was prepared according to the data’s given in the well-accepted literature sources by the transmission of liquid limit and plastic limit test results conducted for only the high plastic clays. Besides, simple equations are tried to be obtained to calculate the plasticity index and approximations are proposed to find the maximum dry unit weight and the optimum water content of the soil, respectively. As a result, the applicability of both the regression analysis and the artificial neural network studies to the attainment process of both consistency characteristics and compaction problem were compared with each other to procure a reliable determination process. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Metadata only
Assessment of Seismic Demand and Damping of a Reinforced Concrete Building After CFRP Jacketing of Columns
(Techno-Press, 2022) KOÇAK, PINAR İNCİ; Göksu, Çağier; Töre, Erkan; Binbir, Ergun; Ateş, Ali Osman; İlki, Alper
While the lateral confinement provided by an FRP jacket to a concrete column is passive in nature, confinement is activated when the concrete expands due to additional compression stresses or significant shear deformations. This characteristic of FRP jacketing theoretically leads to similar initial stiffness properties of FRP retrofitted buildings as the buildings without retrofit. In the current study, to validate this theoretical assumption, the initial stiffness characteristics, and thus, the potential seismic demands were investigated through forced vibration tests on two identical full-scale substandard reinforced concrete buildings with or without FRP retrofit. Power spectral density functions obtained using the acceleration response data captured through forced vibration tests were used to estimate the modal characteristics of these buildings. The test results clearly showed that the natural frequencies and the mode shapes of the buildings are quite similar. Since the seismic demand is controlled by the fundamental vibration modes, it is confirmed using vibration-based full-scale tests that the seismic demands of RC buildings remain unchanged after CFRP jacketing of columns. Furthermore, the damping characteristics were also found similar for both structures.
Metadata only
Cloud-Based AI Role in Intelligent Pharmaceutical Manufacturing Facilities
(Springer Science and Business Media Deutschland GmbH, 2024) DARABSEH, ESRAA; TARHAN, İBRAHİM ETHEM
Cloud-based Artificial Intelligence (AI) brings advanced computing capabilities into manufacturing facilities without capital expenditures. Cloud AI is capable of assisting turn traditional factories into intelligent factories at low cost. The disruptive innovation of cloud and artificial intelligence equipment in smart factory management leads to increased economic growth and the development of a production pipeline [1]. This article investigates how adopting Cloud-based AI services in intelligent pharmaceutical manufacturing facilities affects the factory’s internal process management. The article uses SWOT/PESTEL analysis to evaluate internal and external factors affecting such facilities based on a case study. In addition, the article uses Minitab to perform linear regression analysis on the case study to determine the outcomes of adopting Cloud-based AI in such factories. The article finds a positive effect of adopting modern technologies, such as Cloud-based AI, on creating a highly efficient production environment, reducing costs, and increasing revenues. However, further investigation is needed to conduct similar research on other pharmaceutical manufacturing facilities of different sizes to understand improved how such implementation affects these facilities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Metadata only
Comparative Evaluation of Different Classification Techniques for Masquerade Attack Detection
(Inderscience Enterprises Ltd., 2020) Elmasry, Wisam; AKBULUT, AKHAN; Zaim, Abdul Halim
Masquerade detection is a special type of intrusion detection problem. Effective and early intrusion detection is a crucial basis for computer security. Although of considerable work has been focused on masquerade detection for more than a decade, achieving a high level of accuracy and a comparatively low degree of false alarm rate is still a big challenge. In this paper, we present an extensive empirical study in the area of user behaviour profiling-based masquerade detection using six of different existed machine learning methods in Azure Machine Learning (AML) studio. In order to surpass previous studies on this subject, we used four free and publicly available datasets with seven data configurations are implemented from them. Moreover, eight well-known masquerade detection evaluation metrics are used to assess methods performance against each data configuration. Finally, intensive quantitative and ROC curves analyses of results are provided at the end of this paper.
Metadata only
A Comparative Sectoral Analysis of Industry 4.0 Readiness Levels of Turkish SMEs
(Springer Science and Business Media Deutschland GmbH, 2021) EMİR, OĞUZ; GERGİN, ZEYNEP; YÜKSEKTEPE, FADİME ÜNEY; Dündar, Uğurcan; Gençyılmaz, Güneş M.; Çavdarlı, Ali Ihsan
The concept of Industry 4.0 brings new standards and has an essential impact on business models, work organizations, and processes. Nowadays, companies are enforced to perform such challenges as meeting personal customer requests, flexibility, responsiveness, customer-oriented solutions, and delivering continuous value to survive in the competitive market. The most innovative companies are resourceful to integrate new digital tools into their business models by following initial trends. For Small and Medium-Sized Enterprises (SMEs), adopting these new industrial challenges, and responding to them quickly is vital when it is considered that they have 99.8% of the enterprise share of Turkey. To do so, an intensive effort is needed to integrate Industry 4.0 applications within the enterprises. It has been suggested in the literature that manufacturing organizations should begin with understanding their current level of maturity by defining their strengths and weaknesses. Further, a significant effort is required with the collaboration of government, academia, and industry leaders to guide enterprises for improving their capabilities in an objective and standardized manner. Despite the diversity of approaches directed to Industry 4.0 concepts, it is not easy to find a study that measures how the manufacturing sector is adopting Industry 4.0 and compares manufacturing sectors with each other. To this end, broad research is initiated in March 2018 to identify the current situation of SMEs in Turkey. In this paper, it is intended to extend the study by providing a comparative sector analysis for manufacturing SMEs in Turkey in terms of Industry 4.0 transformation. Possible action plan suggestions are presented according to the results obtained at the end of the paper. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.
Metadata only
Customer Oriented Intelligent DSS Based on Two-Phased Clustering and Integrated Interval Type-2 fuzzy AHP and Hesitant Fuzzy TOPSIS
(IOS Press BV, 2020) Şenvar, Özlem; AKBURAK, DİLEK; Yel, Necla
Firms need to integrate multiple business functions in order to acquire, analyze, model, and evaluate information necessary for better understanding customer behaviors and making data-driven decisions to enhance the customer experience journey. This study proposes a customer oriented intelligent decision support system (IDSS) to ultimately improve the customer experience journey. Besides, a real application study is handled for a multinational company located in Turkey, considering its abrasives product sales for years of 2017 and 2018. For the data utilized in application study, the proposed methodology is constructed for customer segmentation to develop appropriate data-driven marketing strategies for customers with similar values, preferences and other factors for creating customer-centric organizations. In this regard; firstly two-phased clustering process, which involves the hierarchical multivariate average linkage clustering algorithm and partitional k-means clustering algorithm, is used to present the number of clusters on the basis of three variables (expenditure, transaction and unit cost) and then to assign the customers to the related clusters (VIP, Platinum, Gold and Bronze), respectively. Secondly, the performances of company's departments are ranked according to the preferences of customers from each segment considering 4Ps marketing mix concept via integrated methodology of interval type-2 Fuzzy AHP and hesitant fuzzy TOPSIS.
Metadata only
Cyberbullying Detection Through Deep Learning: A Case Study of Turkish Celebrities on Twitter
(IOS Press, 2023) Karadağ, Bulut; AKBULUT, AKHAN; Zaim, Abdul Halim
One of the ways that celebs maintain their fame in the modern era is by posting updates and photos to social media platforms like Twitter, Instagram, and Facebook. Comments left on their posts, however, expose them to cyberbullying. Cyberbullying, as a form of electronic device-based harassment, negatively impacts the lives of individuals. Thirty famous people from the fields of acting, art, music, politics, sports, and writing were chosen for this research. These notable figures include the top five Twitter followers of Turkey in each demographic. Between December 2019 and December 2020, comment responses for each celebrity were collated. Using the Deep Learning model, we were able to detect abuse content with an accuracy of 89%. Additionally, the percentage of celebrities exposed to cyberbullying by group was presented.
Metadata only
A Decision Support Tool for Classification of Turkish SMEs’ Industry 4.0 Score Levels
(Springer Science and Business Media Deutschland GmbH, 2021) Dündar, Uğurcan; YÜKSEKTEPE, FADİME ÜNEY; GERGİN, ZEYNEP; EMİR, OĞUZ; Gençyılmaz, Güneş M.; Çavdarlı, Ali İhsan
The concept of industry 4.0 aims to enhance the employment of digitalization with the help of burst in computer usage after the third major revolution in industry. Hence, to keep up with the new trends in industry, companies should transform their processes into digital platforms. In Turkey, 99.8% of the companies are SMEs, so in order to be in the global economic competition Turkey should enable their SMEs to make the process shifts to digitalization. In this manner, in 2018 a project is initiated by KOSGEB to evaluate the readiness of SMEs and help them for Industry 4.0. As the last step of this project, a decision support tool is created with classification algorithm behind. In this paper, chosen instruments are used to predict the Industry 4.0 score of SMEs that are calculated with previously published algorithm in the scope of the project. In terms of classification, three algorithms are compared with ROC metric. CatBoost algorithm which is specifically created for categorical classification is compared with Support Vector Machine algorithms (SVM and µ-SVM) that performed best in previous research. CatBoost outperformed other algorithms and is used as base classification method in decision support tool. This decision support tool will be used in decision making process of KOSGEB to which companies to help. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.
Metadata only
Determining a New Warehouse Location for an Electrical Home Appliances Company
(Springer Science and Business Media Deutschland GmbH, 2024) KIZILKAYA, İLAYDA; KEVSER, TOLGAHAN; OFLUOĞLU, HANDE; ÖLÇÜCÜER, FEYZA; DEMİREL, DUYGUN FATİH
In today’s businesses, supply chain management is a critical factor in terms of efficiency, profitability and cost savings. The success of the supply chain is possible with the right management of the rings such as warehousing and logistics activities. Deficiencies in warehouse and logistics management can lead to inefficiencies and errors in the supply chain, which can have negative effects on business profitability and customer satisfaction. Strategic decisions regarding warehouse locations are vital for cost policies. In this study, a warehouse location selection procedure is proposed for an electrical home appliances company considering the distances to the customers, their transaction volumes, and various other costs. The approach is basically a two-stage facility layout problem that first solves a weighted Euclidean minisum model defined on a continuous plane. Then, four alternative locations that are close to the result obtained in the first step are determined. In addition, two lands owned by the firm are added to the set of alternatives. Next, a p-median (1-median) model is solved and the most suitable warehouse location is determined. Through sensitivity analysis, the changes in the solution are searched for various rent values. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Metadata only
Development of Textile Nanocomposites With Thermal Energy Storage Capability
(Natl Inst Science Communication-Niscair, 2021) Önder, Emel; SARIER, NİHAL
In this study, textile-based composites with dynamic heat storage capability have been designed and developed, in addition to their existing passive insulation capacity. First, poly(acrylonitrile) (PAN) shell and poly(ethylene glycol) (PEG1000 or PEG1500) cores are produced by coaxial electrospinning. Then, these are incorporated into felt based composite structures, which demonstrate enhanced thermal properties as well as buffering function against temperature changes in the environment. The thermal energy absorption and release capacities of the felt composites including PANPEG1000 or PAN-PEG1500 nanowebs are measured as high as 81 Jg(-1) between 33 degrees C and 46 degrees C, and 48 Jg(-1) between 46 degrees C and 54 degrees C respectively. Felt composites, combined with PAN-PEG nanowebs offer forthcoming production applications in the field of dynamic thermal management in various industries.
Metadata only
The Effect of Heuristic Methods Toward Performance of Health Data Analysis
(Springer Science and Business Media Deutschland GmbH, 2022) ÖZOĞUR, HATİCE NİZAM; Orman, Zeynep
Analysis and prediction of health data make essential contributions to the detection, control, and prevention of diseases in the early stages without special examinations. In the analysis of health data, the balance of the datasets, the accuracy and completeness of the data, and the selection of features to represent the disease are very important as they affect the performance of machine learning methods. They have also become popular in various health data analysis studies such as classification of diseases, selection of features to represent the disease, imputation of missing value in dataset since heuristic methods give successful result in the optimization of many problems. In this chapter, various studies that combine heuristic methods and machine learning algorithms for health data analysis between 2010 and 2021 have been examined. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Metadata only
The Effect of Seed Value Choice in an Incomplete Fuzzy Preference Relations Guided by Social Influence
(Springer International Publishing, 2022) ÇİÇEKLİ, SEVRA; Gürbüz, Tuncay
Nowadays, there is an enormous increase in alternatives almost in every area with the development of technology. Thus, it has become harder for a single decision maker (DM) to completely evaluate each alternative for a problem on hand. In group decision making (GDM) problems, each DM has a different effect on the final decision because of their background. Also, it has been observed that DM's judgments are affected by those of other DMs in the group. This is defined as social influence (SI). Social Influence Network (SIN) is useful especially when there is incomplete preference information. In this paper, a proposed model has been used to demonstrate the effect of seed value choice in completion process of missing fuzzy information given by DMs.
Metadata only
Enhancing Targeting in CRM Campaigns Through Explainable AI
(Springer Science and Business Media Deutschland GmbH, 2024) Ayaz, Teoman Berkay; Özara, Muhammet Furkan; Sezer, Emrah; Çelik, Ahmet Erkan; AKBULUT, AKHAN
Modern customer relationship management (CRM) solutions are vital to firms because they streamline the administration of customer interactions, sales processes, and marketing initiatives. To fully exploit the potential of massive volumes of customer data, these platforms need help from AI techniques to quickly evaluate and extract useful insights, personalize customer experiences, and optimize decision-making to improve business outcomes. This study delves into the use of explainable AI methods like SHAP, LIME, and ELI5 to analyze CRM campaign outcomes. The purpose of this research is to discover essential traits that serve as indications for successful targeting by analyzing a dataset that captures the results of customers’ interactions with campaign content as responder or non-responder. Using these methods improves interpretability and closes the gap between AI-driven decision-making and human understanding. The findings add to the field by offering clear rationales for consumer actions, which in turn helps companies fine-tune their targeting tactics and boost the efficiency of their campaigns. This study emphasizes the value of AI systems being transparent and interpretable in order to promote trust and enable data-driven decision-making in CRM contexts. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Metadata only
Examining the Effects of Forest Fires: A Framework for Integrating System Dynamics and Remote Sensing Approaches
(IGI Global, 2024) Eriş, Müjgan Bilge; DEMİREL, DUYGUN FATİH; Sezer, Eylül Damla Gönül
Forest fires have been a major concern for many countries over an extended period of time due to natural and human induced factors. In recent years, detection of forest fires has progressively shifted toward advanced technologies where the remote sensing approaches are fully operational. To enhance fire management strategies, it is crucial to gain a comprehensive understanding of the fire dynamics and its consequences on the environment, operational sources, and economic sectors. Therefore, this chapter develops an integrated framework to predict and analyze the effects of forest fires by using system dynamics approach and remote sensing technology, ultimately leading to the establishment of a conceptual model and conclusive insights. © 2024, IGI Global. All rights reserved.
Metadata only
Examining the Impacts of Military Expenditures on Economic Productivity: A System Dynamics Approach
(SAGE Publications Ltd., 2023) Damla Gönül-Sezer, Eylül; DEMİREL, DUYGUN FATİH
The relationship between military expenditures and economic productivity has taken the attention of many researchers and there exist an important number of studies approaching the topic through several techniques. However, there is no consensus among the scholars whether military expenditures trigger economic growth, productivity, and other macroeconomic indicators. Such arguments are mainly due to unclear results obtained from the existing studies, in which the complex relationships between military expenditures and macroeconomics are not fully incorporated. Considering the bidirectional and nonlinear relationships among macroeconomic indicators and complex feedback mechanisms, a system dynamics (SD) model for examining the impacts of military expenditures on economic productivity in Turkey is proposed. The proposed SD model aims to reflect the complex environment surrounding the military spending–economic productivity nexus and to analyze the feedback structures that lead to miscellaneous consequences with delays. A stock–flow model is developed to represent the complex nonlinear relationships and causalities between the variables. Data from SIPRI, the World Bank, and several local statistical sources covering the years 2009–2018 are utilized to simulate the existing case, warfare in neighbors, economic shrinkage scenarios, and the combination of the latter two. The results obtained from the scenarios suggest that short fixes such as importing military products instead of national investments give rise to chronic issues like continual dependence on foreign supply, hence, leading to decrease in overall economic growth. To the best of our knowledge, this is the first attempt to integrate SD methodology with military expenditure and economic productivity analysis.
Metadata only
An Excel-Based Stock Management System for a Leather Label Manufacturer
(Springer Science and Business Media Deutschland GmbH, 2024) UÇUCU, EMİNE; ERASLAN, FATMA BEYZA; KAYMAKLI, ZEYNEB NUR; EMİR, OĞUZ; AKTİN, AYŞE TÜLİN
This paper presents a proposal for an Excel-based digital inventory tracking system to address the operational challenges faced by a leather label manufacturer located in Istanbul, Turkey. The company is currently reliant on manual stock keeping and tracking methods for its leather labels and raw materials, resulting in significant functional difficulties due to the absence of a systematic and efficient inventory tracking system. The proposed system aims to enhance overall productivity and decision-making processes within the company. By implementing the new tracking system, the company can overcome the limitations of manual stock management, leading to improved efficiency and organization in inventory control. Furthermore, the installation of a barcode system is suggested to augment the tracking system’s capabilities, and the profitability of the proposed system is evaluated using three different financial analysis methods. This research contributes to the advancement of inventory management practices and provides valuable insights into the potential benefits of adopting digital solutions for stock control in the leather label industry. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Browse

Browsing Mühendislik Fakültesi / Faculty of Engineering by Rights "info:eu-repo/semantics/closedAccess"