Mühendislik, Mimarlık ve Tasarım Fakültesi

Permanent URI for this community

https://dspace.mudanya.edu.tr/handle/20.500.14362/73

Browse

Now showing 1 - 20 of 20

A comprehensive analysis of apricot drying methods via multi-criteria decision making techniques
(Wiley, 2024-10) Abdulvahitoğlu, Aslı; Abdulvahitoğlu, Adnan; Cengiz, Nurten; 382420
Food and food safety have been among the most important issues for people throughout history. Societies have always tried to be self-sufficient in food and have avoided becoming dependent on foreign sources. However, the fact that most foods are seasonal and the increasing population's food consumption have revealed the need to preserve foodstuffs for a long time. The old and well-known method used today for extending shelf life is the drying process. The drying process is preferred over other preservation methods for reasons such as being more economical, easier to transport, having a longer shelf life, more concentrated nutritional value, and containing fewer additives. This ensures that dried foods are of higher quality in terms of physical, chemical, microbial properties, and nutritional values compared to other packaged foods. While the drying process was traditionally done over a long period, technological advancements have led to the production of higher quality and more valuable commercial products in a shorter time. In this study, traditional and technological methods used in drying apricots were compared according to the parameters determined by experts in the field. Since multiple parameters are effective in the comparison, Multi-Criteria Decision Making (MCDM) techniques were used. The optimum apricot drying method was determined by combining the results obtained from different MCDM techniques with the Borda rule.
A Comprehensive Review of Convolutional Neural Networks based Disease Detection Strategies in Potato Agriculture
(Springer, 2024-09) Gülmez, Burak; 222298
This review paper investigates the utilization of Convolutional Neural Networks (CNNs) for disease detection in potato agriculture, highlighting their pivotal role in efficiently analyzing large-scale agricultural datasets. The datasets used, preprocessing methodologies applied, specific data collection zones, and the efficacy of prominent algorithms like ResNet, VGG, and MobileNet variants for disease classification are scrutinized. Additionally, various hyperparameter optimization techniques such as grid search, random search, genetic algorithms, and Bayesian optimization are examined, and their impact on model performance is assessed. Challenges including dataset scarcity, variability in disease symptoms, and the generalization of models across diverse environmental conditions are addressed in the discussion section. Opportunities for advancing CNN-based disease detection, including the integration of multi-spectral imaging and remote sensing data, and the implementation of federated learning for collaborative model training, are explored. Future directions propose research into robust transfer learning techniques and the deployment of CNNs in real-time monitoring systems for proactive disease management in potato agriculture. Current knowledge is consolidated, research gaps are identified, and avenues for future research in CNN-based disease detection strategies to sustain potato farming effectively are proposed by this review. This study paves the way for future advancements in AI-driven disease detection, potentially revolutionizing agricultural practices and enhancing food security. Also, it aims to guide future research and development efforts in CNN-based disease detection for potato agriculture, potentially leading to improved crop management practices, increased yields, and enhanced food security.
A modern approach to data privacy with federated learning
(Maltepe University, 2023) Kalkavan, Ziya Can; Şahinaslan, Ender; Şahinaslan, Önder; 122635
Today, information technologies and their usage areas are increasing day by day. Advanced technologies such as the internet of things, smart devices and applications, machine learning and arti cial intelligence are a driving force in the spread of their usage areas. The increase in prevalence and use also increases the production and sharing of data. This increase causes various security problems and concerns in terms of data privacy. Therefore, a balance has to be struck between the need for data sharing and its security. For this purpose, the use of federated learning methods has been examined. Traditional data sharing methods focus on centralized solutions for the processing of private and sensitive data of data subjects, but this causes various problems and raises concerns in the sharing of sensitive data. In the federated learning model, it trains locally without data sharing. It has a distributed arti cial intelligence approach that can run di erent resources together. Thus, it o ers an alternative solution that can help address data privacy concerns arising from the traditional method. In this study, the basic principles, usage areas, advantages and difficulties of federated learning, which is also accepted as a modern approach in data privacy, are discussed. The data and examples obtained in the study will be presented.
A novel hybrid MCDM framework combining TOPSIS, PROMETHEE II, and VIKOR for peach drying method selection
(Elsevier, 2024-11) Gülmez, Burak; 222298
The selection of optimal drying technologies for peach processing presents a complex decision-making challenge due to multiple conflicting criteria. This study introduces a novel hybrid multi-criteria decision-making (MCDM) framework combining TOPSIS, VIKOR, and PROMETHEE II methods to evaluate eight drying technologies. The evaluation was conducted across twelve criteria, encompassing product quality, operational efficiency, economic factors, and environmental impact. Data were collected from five industry experts through structured matrices. The results demonstrate that vacuum drying emerged as the optimal technology, maintaining the top position in 75 % of sensitivity scenarios. Freeze drying and heat pump drying consistently ranked among the top three alternatives across all methods. The correlation analysis revealed strong agreement between VIKOR and PROMETHEE II rankings (0.857), while TOPSIS provided complementary insights. Sensitivity analysis identified energy consumption, investment cost, and nutritional retention as the most critical factors influencing technology selection. The findings indicate that advanced drying technologies significantly outperform traditional methods in terms of overall performance. This research provides a comprehensive framework for evidence-based decision-making in food processing technology selection and establishes quantitative benchmarks for future technology evaluations in the fruit drying industry.
Bibliometric analysis and mapping of the benefits and challenges of cloud ERP systems
(İstanbul Üniversitesi, 2023) Şahinaslan, Önder; Şahin, Ahmet; Şahinaslan, Ender; 122635
Enterprise resource planning is an effective tool in achieving management goals. Cloud ERP systems and applications are platform-independent offerings of this management tool in a cloud environment. This study was carried out to make sense of the advantages, difficulties and relationships of the cloud ERP system with scientific studies. For this purpose, the Scopus, Web of Science and Google Scholar databases and the Publish or Perish, WOSviewer and Excel applications were used. Statistical analysis, text mining, word network association, visual mapping and trend analysis were performed. As a result of the analysis, it was found that the total rate of publications produced in the last 3 years was 43%, the most cited work was Springer (20%) and the country was the USA (10%). It was determined that the three most frequently used keywords were ‘cloud ERP’, ‘ERP system’ and ‘ERP’. A strong correlation was found between ‘study’ and ‘challenge’ in text mining. The challenge was closely related to ‘SMEs’, ‘data’, ‘provider’, ‘technology’, ‘literature’ and ‘cloud environment’. In recent studies, the concept of ‘cloud ERP implementation’ in SMEs has come to the fore.
Comparative analysis of different drying methods on strawberry aroma compounds via multi-criteria decision-making techniques
(MDPI, 2025-01) Cengiz, Nurten; Abdulvahitoğlu, Aslı; Abdulvahitoğlu, Adnan; 382420
Food and food safety, as one of the basic issues of human life, has made it necessary to store foods for a long time with the increasing population. One of the oldest and most common methods of extending the shelf life of food products is the drying process. The drying process contributes to the higher quality of foods in terms of physical, chemical, and microbial properties by ensuring that beneficial contents such as vitamins, minerals, and aroma compounds are better preserved. The aroma values of foods, which consist of taste and smell components, gain importance. In foods, the taste is determined by permanent components, while smell is determined by volatile components. The loss of volatile aroma compounds in the strawberry drying process negatively affects product quality. Small changes in aroma compounds can lead to significant differences in product taste. Therefore, strawberry aroma is a critical factor for consumer appeal and commercial success. In this study, the effects of drying methods on the aroma compounds of strawberry fruit were compared with Multi Criteria Decision Making (MCDM) techniques. In this study, PSI-based MCDM techniques were used to make the most appropriate choice among strawberry drying methods. The values of 23 distinct aroma compounds obtained with different drying methods applied to strawberry fruit were analyzed with 7 different MCDM techniques. The calculations gave similar results and these results were combined with the Borda rule. Accordingly, the drying methods with the highest scores were determined as freeze drying.
Enhancing municipal solid waste management efficiency through clustering: a case study
(Taylor and Francis, 2024-11) Çil, Sedat; Karaer, Feza; Salihoğlu, N. Kamil; Tabansız Göç, Gülveren; Çavdur, Fatih; 409903
This study leverages real-time datasets generated through IoT technology and smart city applications to enhance solid waste management in Yalova Province, Turkey. By integrating these datasets with the municipality’s Geographic Information System (GIS) using the ITRF/96 3 UTM X Y Coordinate System, a dynamic waste collection framework was established. The K-Means clustering algorithm was employed to determine the optimal waste container placement, considering capacities of 550, 800, 1,000, and 3,000 liters and walking distances of 50–100 ms. Results indicated that 1,000 and 3,000-liter containers with a 100-m walking distance maximized collection efficiency. Replacing 484 traditional containers with 105 units of 3,000 liters reduced total routes by 34%, transport costs by 42.2%, and CO2 emissions by 33.5%. The study underscores the importance of integrating GIS and IoT technologies for real-time waste management, aligning with the UN’s Sustainable Development Goals (SDG 11 and SDG 13). By combining data-driven decision-making with urban sustainability practices, it offers a replicable model for municipalities seeking to reduce costs and environmental impacts in waste collection.
Evolution of software development process from past to future: an important reflection of digital transformation
(Maltepe University, 2023) Nizamoğlu, Yekta Buğrahan; Şahinaslan, Ender; Şahinaslan, Önder; 122635; Değer, Özkan; Çakallı, Hüseyin
The software development process has undergone a great evolution from past to present. There is a rapid change from traditional software development methods to modern and innovative approaches. This change is an important re ection of digital transformation along with technological developments. Today, developments in many areas such as arti cial intelligence, machine learning, automatic code generation, smart test automation, low code development lead the change in the software development process. In the future, it is predicted that the software development process will evolve into faster, more reliable, exible and innovative methods with the impact of advanced technologies. This will a ect all environments that produce, operate and use the software and will cause radical changes in usage. In this study, the change and current situation of the software development process from past to present will be discussed. Predictions will be shared on how and in what way digital transformation and technological advances may a ect the process in the future.
Introductory Chapter: Tunnel Engineering – Rock Load Estimation and Support Design Methods
(Intechopen, 2022) Tosun, Hasan
Isolation in Sarah Kane's Crave
(Ases, 2024-10) Mustafa, Esma; 392828; Akkoyunlu, Yağmur
Sarah Kane'in yazdığı Crave, isimsiz dört karakterin, A, B, C ve M'nin hayatlarındaki izolasyonun dokunaklı bir incelemesidir. Bu tek perdelik oyun, her karakterin en derin düşüncelerini ve kırılganlıklarını ortaya çıkarmasına izin veren fragmanlı bir anlatı yaklaşımı kullanır. Anımsatıcı ve şiirsel bir dille dolu monologları, yoğun bir yalnızlık ve duygusal boşluk hissini açığa çıkarır. Bu analiz, eserde tasvir edilen iletişim kopukluğu temasını incelemekte ve karakterlerin çağdaş toplum bağlamında anlamlı bağlantılar kurma mücadelelerini vurgulamaktadır. Çalışma, Kane'in bireylerin tecrübe ettiği izolasyonun yaygın doğasını nasıl temsil ettiğini aydınlatmayı amaçlamaktadır. Karakterlerin toplumsal çevrelerinden kopma hissinin arkasındaki nedenleri, izolasyonun onlar üzerindeki etkilerini ve maruz kaldıkları çeşitli izolasyon biçimlerini inceliyor. Bu unsurları mercek altına alan çalışma, Kane'in modern bağlamlarda izolasyonun yaygın ve çok yönlü doğasını nasıl gösterdiğine dair kapsamlı bir anlayış sunmayı amaçlıyor. Crave, kopukluğun damgasını vurduğu bir dünyada gerçek ilişkiler kurmanın zorluğuna dair ilgi çekici bir yorum olmayı sürdürüyor ve izolasyona karşı verilen asırlık mücadeleyi özetliyor. İzleyiciyi, evrensel izolasyon deneyimi ve insanların duygusal engelleri aşma ve gerçek bağlantıları keşfetme mücadelesi üzerine düşünmeye sevk ediyor.
Mathematical model to upcycle end-of-roll leftover fabrics in apparel manufacturing
(Sage, 2024-06) İşeri, Ali; Kızılaslan, Recep; 135066
This study addresses the problem of end-of-roll leftover fabrics originating after the production of baby/child apparel. The ineffective management of these leftovers results in excess inventory, occupies storage space, and imposes economic and environmental loads. To address this challenge, a novel mathematical modeling approach is proposed. The model maximizes the upcycling of leftovers by incorporating these into the manufacturing of garments while adhering to marketing, production, and ordering constraints. This model also introduces the feasibility of ordering new fabrics with a penalty, as defined by the decision makers, to increase utilization. The model was tested using actual end-of-roll leftover data. The upcycling utilization of leftovers was calculated to be between 57% and 87%. Notably, at an upcycling rate of 58%, 96% of the utilized fabrics were sourced from leftovers. The case study results validate the model efficacy and provide insights into leftover-fabric management.
Pareto‑optimal workforce scheduling with worker skills and preferences
(Springer, 2025-02) İşeri, Ali; Güner, Hatice; Güner, Ali Rıza; 135066
This paper addresses employee scheduling in service operations, considering various skill and skill levels and the fuctuating customer demand throughout the day and week. Employee shift and day-of preferences are also considered to enhance morale. We propose a two-stage integer programming model. In the frst stage, the model optimizes the number of employees required for each shift period, ensuring uniform distribution of overstafng to improve customer service. A Pareto frontier approach is applied between the two stages, ofering decision-makers a set of nondominated solutions that balance overstafng and understafng. The second stage uses the selected Pareto-optimal solution to assign shifts and day-ofs to employees, incorporating their skills, preferences, and fairness considerations. Our model implicitly includes shifts and breaks, reducing decision variables and computational time. Using real data from a dining restaurant chain, we validate the model’s efectiveness in enhancing customer service and reducing labor costs by 12.3% compared to manual scheduling. Furthermore, productivity and employee satisfaction improve by considering individual skills and preferences.
Prediction of parking space availability using ARIMA and Neural Networks
(TMMOB Makina Mühendisleri Odası, 2023) Sebatlı Sağlam, Aslı; Cavdur, Fatih
It may be critical for drivers to have information about the occupancy rates of the parking spaces around their destination in order to reduce the traffic density, a non-negligible part of which caused by the trips to find an available parking space. In this study, we predict parking occupancy rates (and thus, space availability) using three different techniques: (i) auto-regressive integrated moving average model, (ii) seasonal auto-regressive integrated moving average model and (iii) neural networks. In the implementation phase, we use the data set of the on-street parking spaces of the well-known “SFpark” project carried out in San Francisco. We take into account not only the past occupancy rates of parking spaces, but also exogenous variables that affect the corresponding occupancy rates as day type and time period of the day. We make predictions with different model structures of each of the considered methods for each parking space with different parking occupancy patterns in the data set and then compare the results to find the best model design for each parking space. We also, evaluate the results in terms of the superiority of the methods over each other and note that the performance of neural networks is better than those of the other approaches in terms of the mean squared errors.
Psychological impact of disaster relief operations: a study following consecutive earthquakes in Turkey
(Cambridge University Press, 2024-05) İşeri, Ali; Baltacı, Recep; 135066
Objective: This cross-sectional study investigates the immediate psychological effects of disaster relief operations on team members following 2 consecutive major earthquakes in Turkey. Methods: A total of 170 participants, including professional firefighters, search and rescue (SAR) workers, and volunteers, were surveyed approximately 1 month after the conclusion of active SAR operations. The study utilizes the DSM-V criteria and the Posttraumatic Stress Disorder Checklist (PCL-5) to assess symptoms of post-traumatic stress disorder (PTSD) among participants. Results: The findings reveal a point prevalence of 35.3% for probable PTSD, highlighting the substantial psychological impact on disaster relief teams. Factors such as age, residency in affected areas, and active SAR involvement significantly influenced probable PTSD rates. Interestingly, actively engaged SAR members had lower probable PTSD rates, possibly due to their training. Those who directly witnessed the earthquakes had higher scores, highlighting the impact of firsthand exposure. Additionally, individuals aged 50 and above displayed a higher mean total severity score compared to younger participants. Conclusions: This research contributes to understanding the mental well-being of disaster relief professionals. The study’s findings underscore the importance of timely mental health support and training for these responders, emphasizing the need for preparedness in disaster relief teams.
Recent Evaluation on Total Risk of Cascade Dams on Murat River of Upper Euphrates Basin, Turkey
(IntechOpen, 2022) Tosun, Hasan
Selecting facility location of gendarmerie search and rescue (GSR) units; an analysis of efficiency in disaster response
(Elsevier, 2024-10) Abdulvahitoğlu, Adnan; Vural, Danişment; Macit, İrfan; 382420
Disasters, referred to as events that result in physical, economic, and social losses for individuals and disrupt the daily activities of human communities, necessitate ongoing preparedness due to their unpredictable nature. Swift response during and after a disaster is crucial for preserving human life. Hence, it is imperative to initiate planning immediately following a disaster to ensure readiness for various tasks. Given these factors, search and rescue units must carefully select a base location that enables them to promptly reach affected areas. Disasters exhibit unique characteristics across different regions of Türkiye. While some regions are prone to earthquakes, others face the risks of landslides, avalanches, or floods. Consequently, the required measures for disaster management vary from region to region. Nevertheless, when the term “disaster” is mentioned in Türkiye, earthquakes often come to mind due to their frequent occurrence and significant impact. The Gendarmerie Search and Rescue (GSR) units have been actively responding to these earthquakes, renowned for their exemplary institutional discipline and working methods. This study aims to examine the operations and deployment locations of GSR units, which play a crucial role in mitigating the impact of frequent earthquakes in Türkiye, utilizing a SWOT analysis. Additionally, a Multi-Criteria Decision Making-based mathematical model will be employed to optimize task activities and to select the most suitable facility locations for GSR units. The use of mathematical modeling in this context ensures that GSR units are strategically positioned to maximize their operational effectiveness and minimize response times. The results will be evaluated through sensitivity analysis.
Special Topics in Dam Engineering
(IntechOpen, 2022) Tosun, Hasan
Stock price prediction using the Sand Cat Swarm Optimization and an improved deep Long Short Term Memory network
(Elsevier, 2025-01) Gülmez, Burak; 222298
Stock price prediction remains a complex challenge in financial markets. This study introduces a novel Long Short-Term Memory (LSTM) model optimized by Sand Cat Swarm Optimization (SCSO) for stock price prediction. The research evaluates multiple algorithms including ANN, LSTM variants, Auto-ARIMA, Gradient Boosted Trees, DeepAR, N-BEATS, N-HITS, and the proposed LSTM-SCSO using DAX index data from 2018 to 2023. Model performance was assessed through Mean Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and out-of-sample R2 metrics. Statistical significance was validated using Model Confidence Set analysis with 5000 bootstrap replications. Results demonstrate LSTM-SCSO's superior performance across all evaluation metrics. The model achieved an annualized return of 66.25% compared to the DAX index's 47.45%, with a Sharpe ratio of 2.9091. The integration of technical indicators and macroeconomic variables enhanced the model's predictive capabilities. These findings establish LSTM-SCSO as an effective tool for stock price prediction, offering practical value for investment decision-making.
Testing the Forecasting Power of Statistical Models for Intercity Rail Passenger Flows in Turkey
(Sage, 2024-11) Ekici, Üsame; Tüydeş Yaman, Hediye; Şendil, Nuri
While going through a major rail transformation, it is important to develop reliable estimation models for rail passenger flows (RPFs) in Turkey. There are two main approaches in RPF estimation, regressions and autoregressive integrated moving-average (ARIMA) models, both of which were in this study developed using the daily RPF data for the period 2011–2015. The ARIMA models (with some variations) were used to forecast first the daily flows in 2016, during which travel restrictions for summer resulted in reduced volumes, successfully captured in the updated ARIMA model. The regression models predicted the expected demand during the restrictions, enabling evaluation of the impact of restrictions, which also showed the models’ power over the longer term. The forecasts were extended to 2017, 2018, and 2019 data. The regression results produced more reliable forecasts over the long term, whereas more accurate predictions were obtained by ARIMA-Sliding (FA-Sld) for short-term planning purposes.
Theory and Practice of Tunnel Engineering
(Intechopen, 2022) Tosun, Hasan

Browse

Browsing Mühendislik, Mimarlık ve Tasarım Fakültesi by Language "en"

Results Per Page

Sort Options