Fakülteler / Faculties

Permanent URI for this communityhttps://hdl.handle.net/11727/1395

Browse

Filters

2014 - 2019112020 - 202419

Settings

Type: search.filters.itemtype.Proceedings Paper

Search Results

Now showing 1 - 10 of 30
  • No Thumbnail Available
    Item
    ParsyBot: Chatbot for Baskent University Related FAQs
    (18TH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING, ICSC 2024, 2024-05-17) Karkiner, Zeynep; Yaman, Begum; Zengin, Begum; Cavli, Feride Nursena; Sert, Mustafa
    Reading regulations and instructions may take lots of time and sometimes it results in disappointments. To avoid this issue, people are prone to use sources that provide fast and accurate answers while accessing the information. Chatbots, are one of the most popular trend topics nowadays, and may adapted into various fields e.g., healthcare, finance, and education. This paper proposes the development of ParsyBot which is a Turkish chatbot designed to inform users about the regulations, admissions, departments, scholarships, and social clubs of Baskent University. Furthermore, users may ask via voice in Turkish this feature is not common among the other chatbots. ParsyBot uses a pre-trained BERT model which is specifically trained with regulations and instructions of Baskent University. Parsybot runs on web and mobile platforms to make it available for everyone. Our experiments on the utilized dataset, ParsyBot, reached 0.81 in METEOR, and 0.24 in ROGUE-1, which are promising compared to the ChatGPT 3.5.
  • No Thumbnail Available
    Item
    Implementation of Smooth Transitions for Grid Connected PV System between the Operating Modes
    (18TH INTERNATIONAL CONFERENCE ON COMPATIBILITY, POWER ELECTRONICS AND POWER ENGINEERING, CPE-POWERENG 2024, 2024-10-02) Onar, Burak; Fesli, Ugur; Demirbas, Sevki
    The grid-connected PV microgrid needs coordination among the components, compromising the whole system to supply the power required by the loads. Well-designed energy management and control structures should be ensured to operate grid-connected PV microgrids with smooth and uninterruptible power. Much of the power system instability arises from transitions between grid-connected mode and island mode. This study introduces a control method to ensure a smooth transition between operating modes for PV microgrids operating in both grid-connected and island modes. The proposed control method has been verified with simulation performed with Matlab & Simulink simulation programs.
  • No Thumbnail Available
    Item
    Sarcasm Detection in News Headlines with Deep Learning
    (32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024-12-05) Karkiner, Zeynep; Sert, Mustafa
    Sarcasm detection is one of the recent topics studied in the field of natural language processing. Although sarcasm detection is generally carried out through social media comments in the literature, it can also be applied to news headlines that are expected to be completely objective and reflect reality. In this study, sarcasm detection was carried out using various deep learning models in a dataset containing sarcastic and non-sarcastic news headlines. The accuracy of classification results of BERT, RNN, LSTM, and GRU models and their training time performance were compared. While the BERT model reached the highest accuracy (0.88), RNN was the most successful model in terms of training time performance.
  • No Thumbnail Available
    Item
    A New Approach for Addressing Slip Ratio Optimization and Trajectory Tracking Challenges in Autonomous Tractor Operations
    (32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024) Aydin, Gulsah Demirhan; Aydemir, Ali Bahadir; Kansou, Mohamad Thaer; Altinuc, Kemal Orcun
    The usage of autonomous agricultural machines is increasing. In this study, two controllers have been designed for trajectory following and longitudinal tire slip ratio control of a rear-wheel independent traction electric autonomous tractor. The first controller is model predictive control (MPC) and the second controller is proportional integral derivative (PID) based. To evaluate the performance of the controllers in the simulation environment, a mathematical tractor model is prepared. Simulations have been made and performances of the designed controllers are shared.
  • No Thumbnail Available
    Item
    Lyapunov-based Controller Design for Precise Monitoring, Speed Control and Trajectory Planning in Autonomous Tractors with Trailers
    (32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, 2024-12-05) Aydin, Gulsah Demirhan; Dogan, Deren; Turken, Yusuf Tugberk
    Nowadays, modern technology-based agriculture operations are replacing traditional farming practices. Smart agricultural systems have gained popularity as a result of the demand for more productive and environmentally friendly farming methods. Consequently, the agricultural sector continues to be one of the driving forces behind automation, viewing technological advancements as a means of increasing productivity while lowering costs. Automation in agriculture ranges from tractors built with apparatus that can carry out complicated tasks on their own to cultivation surveillance. This study aims to optimize the speed of an autonomous tractor through a dynamic code based on Lyapunov control method as an innovative approach in smart agriculture. Beyond speed optimization, the research also addresses practical challenges encountered in real-world scenarios, including obstacles such as living entities. By evaluating the potential of Lyapunov control methodology in the effective management of agricultural machinery, this work offers an innovative perspective on smart agricultural technologies.
  • No Thumbnail Available
    Item
    Comparing Software Development Life Cycle Models with Multi-criteria Decision Making Approach
    (2024 10TH INTERNATIONAL CONFERENCE ON CONTROL, DECISION AND INFORMATION TECHNOLOGIES, 2024) Alkis-Bayhan, Nurcan; Ozmen, Esra; Karaman, Ersin
    Various software development life cycle models are adopted in the software domain. The selection of appropriate models is the main concern of this research since many factors affect the selection of these models. Characteristics of models, their advantages and disadvantages, in which projects they will be used, and how important the characteristics of the models have been studied in numerous research. In the scope of this research, first, the most preferred software life cycle development models, their features, and the factors that affect their selection were determined. Second, the study aims to compare the influential factors in selecting these models to determine the critical factors and rank them according to their importance level. An Analytical Hierarchy Process study was adopted and performed to achieve this comparison. Lastly, each software life cycle development model was compared to each other, and the important models were revealed in terms of each factor. According to the research results, the most critical factor in the model selection was "Project size."
  • No Thumbnail Available
    Item
    AI Pair Programming Acceptance: A Value-Based Approach with AHP Analysis
    (2024 10TH INTERNATIONAL CONFERENCE ON CONTROL, DECISION AND INFORMATION TECHNOLOGIES, 2024) Caldag, Murat Tahir
    The emergence of Artificial Intelligence ( AI) tools is transforming every aspect of life with new opportunities and risks. An impact of AI tools can be seen in AI pair programming which is defined as a generative and creative support tool with real-time interaction. The goal of this study is to explore the AI pair programming acceptance. To identify, describe, categorize, and rank the factors affecting the acceptance of AI pairs a literature review, a research model proposal based on an extension of the Value-based Adoption Model (VAM) framework, and an Analytic Hierarchy Process (AHP) analysis is conducted. The proposed model consists of six main factors and twenty-two sub-factors which are validated with an AHP analysis including eleven experts' judgments. The findings presented the most essential factors as productivity, code accuracy, complexity, personal development, and innovativeness. The least significant factors were inspiration, motivation, intellectual property violation, AI interaction, and trust. This study provides insight to AI tool developers and producers in the context of programming on the key factors to consider for success.
  • No Thumbnail Available
    Item
    Applications of Deep Learning Techniques to Wood Anomaly Detection
    (2022) Celik, Yaren; Guney, Selda; Dengiz, Berna; Xu, J; Altiparmak, F.; Hassan, MHA; Marquez, FPG
    Wood products and structures have an important place in today's industry. They are widely used in many fields. However, there are various difficulties in production systems where wood raw material is under many processes. Some difficulty and complexity of production processes result in high variability of raw materials such as a wide range of visible structural defects that must be checked by specialists on line or of line. These issues are not only difficult and biased in manual processes, but also less effective and misleading. To overcome the drawbacks of the manual quality control processes, machine vision-based inspection systems are in great of interest recently for quality control applications. In this study, the wood anomaly has been detected by using deep learning. As it will be a distinction-based method on image processing, the Convolution Neural Network (CNN), which is one of the most suitable methods, has been used for anomaly detection. In addition, it will be tried to obtain the most suitable one among different CNN architectures such as ShuffleNet, AlexNet, GoogleNet for the problem. MobileNet, SqueezeNet, GoogleNet, ShuffleNet among considered methods show promising results in classifying normal and abnormal wood products.
  • No Thumbnail Available
    Item
    Understanding the Effect of Assignment of Importance Scores of Evaluation Criteria Randomly in the Application of DOE-TOPSIS in Decision Making
    (2019) Ic, Yusuf Tansel; Yurdakul, Mustafa; 0000-0001-9274-7467; AGE-3003-2022
    In conventional applications of hybrid DoE-TOPSIS technique in decision making problems, full factorial design layouts are generally used because of their ability to measure the effects of all possible combinations for evaluation factors. In a typical application, for a design layout, a number of replications are generated by assigning different sets of relative importance scores for evaluation factors. A TOPSIS score is then obtained for each experiment and replication pair. Regression analysis is finally applied to obtain a relationship with inputs (values of evaluation factors) and outputs (alternatives' TOPSIS meta-model scores). The key in conventional application of hybrid DoE-TOPSIS technique is generation of relative importance scores. Each set of scores can be assigned by a decision maker or generated randomly. This paper aims to determine whether using either of the two methods in determination of relative importance scores makes any difference in the ranking orders of alternatives.
  • No Thumbnail Available
    Item
    Predicting Bank Return on Equity (ROE) using Neural Networks
    (2021) Balci, Tolgay; Ogul, Hasan
    Measuring the performance and profitability of the banking sector, which is the most important part of a country's financial system, is always important. Thanks to the performance measurement, banks can understand the competitive situation, their potential to grow, and the risk, and be more successful in sustaining their lives. This study is considered all state deposit money banks in Turkey. In the literature, using of artificial neural networks (ANN) in banking performance evaluation is rarely studied. Therefore, this paper aims to examine the possibility of ANN utilization for predicting return on equity of Turkey State Deposit Money Banks. The paper compares the accuracy percentages of optimization algorithms of ANN using eleven years quarterly data of six exogenous variables and eight endogenous variables as independent variables and the average return on equity from quarterly of all Turkey state deposit money banks as dependent variable. Given a number of recorded financial parameters, the task is to predict banks' performances using ANN computation methods and to compare prediction results with real results. To evaluate these methods, we built a data set from Banking Regulation and Supervison of Agency, The Banks Association of Turkey and banks' quarterly financial reports. According to all experimental results in optimization models were estimated with above % 80 accuracy. It is determined that the best optimization model is different for each bank.