Tracking density in universities is essential for planning services like food, transportation, and social activities on campus. However, food waste remains a critical challenge in campus dining operations, leading to significant environmental and economic consequences. Addressing this issue is crucial not only for minimizing environmental impact but also for achieving sustainable operational efficiency. Campus food services significantly influence students’ university choices; thus, forecasting meal consumption and preferences enables effective planning. This study tackles food waste by analyzing daily campus data with machine learning, revealing strategic insights related to food variety and sustainability. The algorithms Linear Regression, Extra Tree Regressor, Lasso, Decision Tree Regressor, XGBoost Regressor, and Gradient Boosting Regressor were used to predict food preferences and daily meal counts. Among these, the Lasso algorithm demonstrated the highest accuracy with an R² metric value of 0.999, while the XGBRegressor also performed well with an R² metric value of 0.882. The results underline that factors such as meal variety, counts, revenue, campus mobility, and temperature effectively influence food preferences. By balancing production with demand, this model significantly reduced food waste to 28%. This achievement highlights the potential for machine learning models to enhance sustainable dining services and operational efficiency on university campuses.

Günümüzde akıllı şehirlerin, akıllı evlerin ve nesnelerin ortaya çıkması ile Nesnelerin İnterneti (Internet of Things - IoT) değeri artan bir teknoloji olarak gelişmektedir. 2025 yılına kadar internete bağlı olan IoT cihaz sayısının 70 milyarı geçmesi beklenmektedir. IoT sistemleri sınırlı kaynaklara ve hesaplama yeteneğine sahip olmaları, merkezi topolojiye sahip olmamaları nedeniyle pek çok gizlilik ve güvenlik sorunlarını oluşturmaktadır. Veri gizliliği ve veri bütünlüğü IoT veri aktarımında oldukça kritik parametrelerdir, bu nedenle IoT çözümlerinde, hizmet potansiyeli ve hassas verileri içermesi açısından topladıkları ve işledikleri verilerin güvenliği ve gizliliği önemlidir. IoT sistemlerde oluşan veri güvenliği problemleri için blokzincir teknolojisi potansiyel çözümler sağlamaktadır. Bu çalışmada, IoT cihazlarından alınan verilerin güvenliğini sağlamak için blokzincir teknolojisi kullanılmıştır. Akıllı bir ev sistemi için tasarlanan IoT ağı uygulaması üzerinde IoT cihazlarındaki güvenlik açıklıklarından kaynaklanan veri mahremiyeti problemi için blokzincir oluşturulmuş ve cihazlar arasındaki veri iletişiminde iletilen verilerin güvenliği oluşturulan hash algoritmaları ile sağlanırken aynı zamanda veri bütünlüğü testleri yapılarak iletilen verilerin doğruluğu kanıtlanmıştır.

Informing the drivers are very important for ensuring the traffic flow properly and safely in highway transportation. Mobile devices take part in technologies that support the improvement of intelligent systems in traffic management and control systems which vehicle and way knowledge are shared. Due to the GPS, Accelaration, wi-fi etc. features of smart phones developed by using built-in sensors are prefered to use in traffic. In this study, how diagnostic tool ELM327, which reads data through vehicle network, communicates with mobile devices, what type of software are used for data tracking and which data is transmitted from the vehicle are explained. In smart transportation systems which added the smart phones features , Providing bi-directional communication applications like warning drivers against possible accidents, determining road congestion, communication vehicles each other, sharing and displaying highway knowledge on mobile devices. It is expected that it contribute to the development of systems which enable traffic management and control beside server-based data sharing and informing drivers. Keywords: CAN Bus, ELM327 Diagnostic, OBD II, Smartphone, TMS, ITS.

Vehicle use is becoming more widespread day by day due to the world population growth. Within the scope of intelligent transportation systems, the information technologies sector and the transportation sector work in an integrated manner to solve the problems caused by the increasing number of vehicles. Data obtained with sensors and cameras are analyzed with artificial intelligence-based information technologies and used in autonomous vehicles, security, traffic management, navigation and passenger information systems. Computer vision enables machines to extract meaningful patterns and relationships from images by combining image processing and deep learning technologies. Computer vision techniques are applied in many fields such as tourism, health, industry, defense, transportation, service, e-commerce, etc. The applications developed provide solutions to various challenges in the transportation sector. For vehicles using Liquified Petroleum Gas (LPG) fuel, the gases in LPG tanks are flammable and pose a potential explosion hazard, especially in certain areas in cities. Entry of LPG vehicles is prohibited in institutions and organizations such as hospitals, shopping malls, hotels that have indoor parking services. The control method of the ban is carried out by assigning a personnel and checking the vehicle trunks. In this study, LPG fueled vehicles were automatically detected using computer vision techniques. Vehicle image data captured by mobile cameras in different provinces in Turkey were trained and compared with four different deep learning models. As a result of training and performance tests on the models, the YOLOv8 model was more effective than the other models with an accuracy of 0.994 mAP and a speed of 11.6 ms. It has been shown to be a stable model in terms of real-time monitoring in real life. It is envisaged that the developed system can contribute to the applications of computer vision techniques as well as benefit the national economy, public life safety and environmental protection.

The power generated from wind turbines is of critical importance as one of the fundamental components of sustainable and renewable energy systems. However, the complex and nonlinear nature of wind flow and the influence of interconnected factors make turbine power estimation significantly difficult. This study aims to evaluate the performance of different forecasting models using real-time data obtained from wind turbines and to determine the most effective model for wind power generation. The analyses are performed based on performance metrics that measure the agreement between the predicted and actual values. The study results reveal that the Decision Tree Regressor model provides the highest accuracy with 0.998 R² value and low error rates (RMSE: 0.151, MAE: 0.036) and that tree-based models are more effective in wind power estimation. These models, trained using large datasets, offer significant potential in terms of increasing power grid stability and ensuring the optimization of wind farms. The study shows that advanced methods used in turbine power estimation are an effective tool for optimizing renewable energy use by contributing to sustainable energy targets.