42
Archived Theses
0
DOIs Assigned
0%
DOI Rate
Archived Theses
A critical study on sustainability within environmental assessment methodologies: Evaluating Volu-te in search of an alternative vision in architecture
This thesis focuses on the evaluation of sustainability in architecture and the environmental assessment methodologies as its tools. These methodologies act as measuring mechanism of sustainability of the architectural product; however, they also work as a wheel of the current capitalist system by labelling and certification requirements. Therefore, this study aims to focus on evaluating ecological impact and financial stress on the project. It shows that BREEAM certification adds a triple amount of project budget and Passive House certification adds double the amount of the total cost of the project. In this evaluation Volu-te has been used as an architectural product to discuss and make the cost effect of these certification systems on micro scale living projects.
Comparing audio features for speech emotion recognition using machine learning algorithms
Voice is an integral part of our lives. The demand for voice technology in both art and human-machine interaction systems has recently been increased. More information can be transferred quickly by voice. Speech is a natural way of communicating and as a result of this, it is primarily preferred for contacting users in technological areas. Our voice conveys both linguistic and paralinguistic messages in the course of speaking. The paralinguistic part, for example, rhythm and pitch, provides emotional cues to the speaker. Emotions consist of cognitive, physiological and behavioural changes and all these phenomena are interrelated. Generally, an emotion is a state that affects the thoughts and is capable of determining behaviour. Emotion also creates physical and psychological changes. Speech Emotion Recognition topic examines the question 'How is it said?' and an algorithm detects the emotional state of the speaker from an audio record. Within the scope of this study, machine learning models are developed with classification methods to resolve the problem of speech emotion recognition. Voice consists of a lot of characteristics. However, the optimal audio feature set related to the emotional state cannot be determined yet. The main aim in this study is obtaining the most distinctive emotional features. For this purpose, in order to compare audio features based on different domains Root Mean Square Energy (RMSE), Zero Crossing Rate (ZCR), Chroma and Mel Frequency Cepstral Coefficients (MFCC) features are examined for emotion recognition. A pre-trained model namely wav2vec Large which has been developed more recently is used to create the inputs also. Support Vector Machine, Multi-Layer Perceptron and Convolutional Neural Network techniques are utilized for developing learning models for comparing traditional features and the pre-trained model representations. In this paper emotions namely, Happy, Calm, Angry, Boredom, Disgust, Fear, Neutral, Sad and Surprise are classified, and furthermore, the models are trained and tested with English and German speech datasets. When the classification results are examined, it is concluded that the most successful predictions are obtained with the pre-trained representations. The weighted accuracy ratio is 91% for both Convolutional Neural Network and Multilayer Perceptrons models while this ratio is 87% for the Support Vector Machine models. Among the emotional states, Fear has the highest recognition ratio with 95% f-score with Convolutional Neural Network technique which uses a pre-trained model.
The use of pretrained language models in sentiment analysis
Natural language processing is one of the sub-topics of linguistic science and artificial intelligence. Sentiment analysis classifies a text on any topic according to its subjective content. It is one of the methods used to examine, analyze and interpret data such as the thoughts, feelings or attitudes of individuals about a subject on various platforms. The increase in social media shares has also increased the sentiment analysis studies conducted on these platforms. Different methods are used during sentiment analysis. Classification is carried out by sentiment analysis using machine learning and natural language processing algorithms. In recent years, pre-trained language models have been used together with machine learning methods or alone. The aim of this thesis is to test the hypothetical advantages of sentiment analysis in social media comments with pre-trained language models. For this purpose, sentiment analysis was performed for Covid-19 related tweets on Twitter. Emotion intensities were determined using pre-trained language models and the results were compared. BERT, RoBERTa and BERTweet were used in the analysis. The results show that NLP techniques for sentiment analysis are as successful as other techniques.
Enmeshed experience through existential characteristic of a micro living unit Volu-te
This thesis focuses on the unity of body and space within the scope of the notion, experience. Revealing the experience of architectural space through its characteristics has been questioned. In this context, the definitions of body and space were examined from a phenomenological perspective and the relationship between subject and object is questioned. With the concept of "experienced space", the space is positioned at the centre of the experience. Since the subject and the object create each other, the perception of the body through the senses has been questioned. Thus the reading of the space was done through the sensation. The thesis argues that the "existential characteristics of the object" should be examined to reveal the experience. In this context, the micro-housing unit called Volu-te (designed and produced during the graduate program Alternative Architectural Practices ) has been discussed as an architectural object. It has been aimed to start a discussion on the experience from the perception of Volu-te by deciphering the existential characteristics. During this discussion, the spatial perception of which these characteristics provide to the subject has been emphasised. In order to express the experience revealed in Volu-te, a terminology of Steven Holl was used. "Enmeshed Experience" is a concept that used to express an urban perception that has been redefined over the micro-housing unit. In this way, the possibility of revealing the experience has been explored.
Prototyping as a tool and a process in architectural education
Prototyping for architecture, as a concept and practice, exceeds generating a tangible working-model as in other fields. It encompasses a holistic, instructive process in which design continues while building and by which simultaneous experience can be achieved. Also, prototyping can become an action that helps to understand the fluctuating field of architecture between theory and practice. The goal of this thesis work is to identify the benefits of incorporating the concept of prototyping to architectural studies, mainly architectural education. Over time, the architectural knowledge transferred from its master to its apprentice has turned into a formal system given in its schools at the intersection of art and engineering. In contrast to this situation, in the educational process, not only creating the architectural product praxis as a design on paper but also imagining the construction processes and after, enables the designer and the student to face different field potentials and produce solutions. Programs that include building in their education curricula are critical examples in this regard. In this thesis, the construction practice will be read through prototype production and the assessment will be done utilizing information on various Design-Build Programs. In addition, design-construction-post will be evaluated as a process in a response to the changing architect subject and architectural practice in the 21st century. Five programs from five different geographies, namely AA Hooke Park, ITKE University of Stuttgart, Rural Studio, Ciudad Abierta/Open City, and MEF FADA DBS/AAP, which care about learning by building; prototyping approaches, learning processes, participants, and tools they use will be examined.
Interviewster: A chatbot evaluating competency based interviews using transformer models
Recruitment is one of the most verbal and communicative area of Human Resources (HR). This department has many aspects that is open to innovation but also open to the bias, because of the dominance of the human factor. This brings the need (and chance) of many innovation possibilities coming up with the progress in artificial intelligence technologies. Here we will focus on creating a chatbot named as "Interviewster" that welcomes candidates, gathers information (such as name-surname, work status, computer knowledge, education, hobbies), and provides competency-based questions about their past experience and helps them to answer these questions correctly. This chatbot welcomes a candidate and starts the conversation, saves the data collected from the candidate, conducts a competency based interview and decides if candidate has the required competency or not by using natural language processing techniques that utilize neural network architectures and transformer-based technologies. The chatbot is running on the web, coded in python, published to the web by Flask, works on a python core with a Mysql database. In this thesis, interview practices are first introduced, and the methods and applications of competency-based interviews are described. The architecture of the chatbot named as Interviewster is then explained by providing details of the technologies, libraries and machine learning techniques being used. Finally, the results of an evaluation study where the transformer-based models BERT, DeBERTa, and ELECTRA models are applied to the competency-based interview results of real candidates are discussed in detail.
Examining volu-te as a dormitory model in the context of existenzminimum principles
Today's living conditions and changing world order, the period we live in (2021) remains uncertain. Health problems arising from global warming and population growth constitute this period of uncertainty. As part of this period, students have to meet their accommodation needs within unclear timeframes. When the number of students and dormitory capacities are compared; insufficient capacities and pricing that low-income families cannot reach. In order to determine the dormitory problems, an analysis of the dormitories in Istanbul and a detailed analysis of Istanbul Technical University state-owned dormitories were made. Dormitory rooms should be areas where maximum efficiency should be achieved in the minimum area that provides the minimum living conditions. The Volu-te Project, which was designed on the concept of "Small Scale", constitutes one of the main examples of the thesis. "Volu-te Project" is a micro accommodation unit proposal for individuals in need of temporary accommodation. It is the end product of a collective research-design process by MEF University students1 and studio instructor2. Volu-te aims to reveal the potentials of surplus areas created in dense and complex city planning in mega cities such as Istanbul. In this direction, it was determined that the dormitory problems were similar to the problems that were effective in the formation of the "Existenzminimum" concept, and a parallel reading was made. The 5 panel topics3 discussed in CIAM II were determined as Existenzminimum design principles. Alternative dormitory projects were examined with reference to Existenzminimum design principles. "Volute" as an alternative dormitory was discussed in line with these principles. As a result of the dormitory and minimum life review, the Volu-te project is presented to Istanbul Technical University as a dormitory proposal. The situations that we may encounter in the future scenarios and the advantages of alternative projects on the other hand are discussed.
Evaluating cognitive absorption, technology acceptance, and online educational software usability of students in online programming courses
This thesis examines the online self-learning, cognitive absorption, and technology acceptance models of students in online programming courses. This thesis discussed the role and impact of various factors on the learning of programming students. Besides investigating the effect of the educational learning-based online course content of Comp109 Introduction to Programming (Java), Comp110 Object Oriented Programming ve Comp210 Data Structures and Algorithms courses on student success, the effects of students' cognitive absorption, the acceptance, and usability of educational online learning environments were discussed. The subjects of the research are a total of 181 online students in the student group. The researcher carried out the application of the questionnaire tools to the students in the programming courses. Based on the questionnaires, this research aims to examine the effect of students' cognitive absorption, technology acceptance, and online educational software usability on student success in programming courses. In this study, the following scales were applied in the survey measurements, respectively: Cognitive absorption scale (13 items), technology acceptance model (14 items), online educational software usability (39 items). The preparation, ethical approval and implementation of the relevant survey and data analysis research took three months. This study evaluates students' cognitive assimilation, technology acceptance, and e-education software usability scale and suitability for online education in online programming courses. Each of these three scales was examined from seven different perspectives: Gender, Course Code, Department, Age, Expertise, Frequency of Internet use, and Interest in technology. Normality test, ANOVA, Mann-Whitney U Test and Kruskal Wallis Test were used to compare and evaluate these measurements. In addition to these test measurements, the MANOVA test was also applied for multivariate analysis. MANOVA test was carried out in detail from 4 different perspectives. The results of each of these scales were investigated from seven different perspectives and compared with related studies, and suggestions were presented based on the obtained results. In line with my findings, the positive effect of online programming courses on cognitive absorption has been demonstrated. However, it was also shown that there was no significant difference between demographic variables. In addition to these, a literature search was made for all three scales for discussion and a discussion was written. Results are written according to the discussion and analysis.
Predicting the preference of liking using fNIRS and machine learning algorithms
The fMRI method, which is generally used to detect behavioral patterns, draws attention with its expensive and impractical features. On the other hand, the near-infrared spectroscopy (fNIRS) method is less expensive and portable, but it is as effective as fMRI in creating a good prediction model. With this method, a model has been developed that can predict whether a person likes a visual stimulus or not, using various classical machine learning algorithms including Support Vector Machines (SVM), Random Forests, XGBoost, LightGBM and K-Nearest Neighbors (KNN). With implementing tree-based and booster algorithms in addition to SVM and KNN which have been frequently used algorithms in this fNIRS domain, it was aimed to do a complementary comparison in addition to these acknowledged algorithms. Moreover, various missing value imputation methodologies were used to find the best suitable approach for this kind of classification problem. K-Means clustering, which is an unsupervised learning method, was also utilized to cluster similar fNIRS measurements of participants that may improve classification results by one-hot encoding those groups. Furthermore, certain feature extraction and wrapper methodologies were also applied for an attempt to enhance the performance of liking prediction models as a secondary goal. PCA, Isomap and t-SNE methodologies were implemented as feature extraction approaches, and forward selection wrapper design was utilized as an additional step to further development of the model by comparing their scores with each other. Cross-validation F1-scores of these models were used to find out the best model among them. Leave-one-group-out cross validation was exploited in comparison of the models. This meant that these cross-validation results corresponded to each of participants' data i.e. testing every participants' fNIRS measurements alone in each fold. This way both every score specific to each participant could be seen and it ensured models' results were statistically reliable. Following evaluations also included permutation and Wilcoxon Signed-Rank tests to compare each model's performance with each other by testing the statistical significance of those results. Keywords: machine learning, decision-making, optical brain imaging, fnirs, feature extraction, feature selection
Customer transaction predictive modeling via machine learning algorithms
Bu çalışmanın temel amacı faktoring sektöründe aktif olarak faaliyet gösteren bir şirketin müşterilerinin davranışlarını ve özelliklerini saptayabilmek, buna bağlı olarak da müşterilerin geçmiş verilerinden yola çıkarak, keşifçi veri analiziyle ölçülebilir parametreler yakalayabilmek ve akabinde hedefe yönelik tahminsel modellemeler gerçekleştirebilmektir. Sınıflandırma modeli algoritmalarından SVM ve Extra Trees modellerinde %80 seviyesi üzerinde isabet oranı yakalanmıştır. Bu sayede yüksek potansiyel gösteren, yani sorgulattığı çeki, işletme olarak onayladıktan ve teklif yapıldıktan sonra kabul etme ihtimali yüksek olan müşterileri tahmin edilmesi daha etkin, verimli ve doğru yaklaşımlar içerisinde hareket edip aksiyon alarak, işletme bazında işlem hacmine doğrudan katkısı sağlanması amaçlanmıştır.