Yazılım Mühendisliği Bölümü / Department of Software Engineering

Permanent URI for this collectionhttps://hdl.handle.net/11413/8848

Browse

Now showing 1 - 9 of 9

Biosignals, Facial Expressions, and Speech as Measures of Workplace Stress: Workstress3d Dataset
(Elsevier, 2024) Doğan, Gülin; AKBULUT, FATMA PATLAR; Çatal, Çağatay
WorkStress3D is a comprehensive collection of multimodal data for the research of stress in the workplace. This dataset contains biosignals, facial expressions, and speech signals, making it an invaluable resource for stress analysis and related studies. The ecological validity of the dataset was ensured by the fact that the data were collected in actual workplace environments. The biosignal data contains measurements of electrodermal activity, blood volume pressure, and cutaneous temperature, among others. High-resolution video recordings were used to capture facial expressions, allowing for a comprehensive analysis of facial cues associated with tension. In order to capture vocal characteristics indicative of tension, speech signals were recorded. The dataset contains samples from both stress-free and stressful work situations, providing a proportionate representation of various stress levels. The dataset is accompanied by extensive metadata and annotations, which facilitate in-depth analysis and interpretation. WorkStress3D is a valuable resource for developing and evaluating stress detection models, examining the impact of work environments on stress levels, and exploring the potential of multimodal data fusion for stress analysis.
NeuroBioSense: A Multidimensional Dataset for Neuromarketing Analysis
(Elsevier, 2024) KOCAÇINAR, BÜŞRA; İNAN, PELİN; ZAMUR, ELA NUR; ÇALŞİMŞEK, BUKET; AKBULUT, FATMA PATLAR; Çatal, Çağatay
In the context of neuromarketing, sales, and branding, the investigation of consumer decision-making processes presents complex and intriguing challenges. Consideration of the effects of multicultural influences and societal conditions from a global perspective enriches this multifaceted field. The application of neuroscience tools and techniques to international marketing and consumer behavior is an emerging interdisciplinary field that seeks to understand the cognitive processes, reactions, and selection mechanisms of consumers within the context of branding and sales. The NeuroBioSense dataset was prepared to analyze and classify consumer responses. This dataset includes physiological signals, facial images of the participants while watching the advertisements, and demographic information. The primary objective of the data collection process is to record and analyze the responses of human subjects to these signals during a carefully designed experiment consisting of three distinct phases, each of which features a different form of branding advertisement. Physiological signals were collected with the Empatica e4 wearable sensor device, considering non-invasive body photoplethysmography (PPG), electrodermal activity (EDA), and body temperature sensors. A total of 58 participants, aged between 18 and 70, were divided into three different groups, and data were collected. Advertisements prepared in the categories of cosmetics for 18 participants, food for 20 participants, and cars for 20 participants were watched. On the emotion evaluation scale, 7 different emotion classes are given: Joy, Surprise, anger, disgust, sadness, fear, and neutral. This dataset will help researchers analyse responses, understand and develop emotion classification studies, the relationship between consumers and advertising, and neuromarketing methods.
Wallet-Based Transaction Fraud Prevention Through LightGBM With the Focus on Minimizing False Alarms
(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Iscan, Can; Kumas, Osman; AKBULUT, FATMA PATLAR; Akbulut, Akhan
E-wallets' rising popularity can be attributed to the fact that they facilitate a wide variety of financial activities such as payments, transfers, investments, etc., and eliminate the need for actual cash or cards. The confidentiality, availability, and integrity of a user's financial information stored in an electronic wallet can be compromised by threats such as phishing, malware, and social engineering; therefore, fintech platforms employ intelligent fraud detection mechanisms to mitigate the problem. The purpose of this study is to detect fraudulent activity using cutting-edge machine learning techniques on data obtained from the leading e-wallet platform in Turkey. After a comprehensive analysis of the dataset's features via feature engineering procedures, we found that the LightGBM approach had the highest detection accuracy of fraudulent activity with 97% in the experiments conducted. An additional key objective of reducing false alerts was accomplished, as the number of false alarms went from 13,024 to 6,249. This approach resulted in the establishment of a machine-learning model suitable for use by relatively small fraud detection teams.
Neurophysiological and Biosignal Data for Investigating Occupational Mental Fatigue: MEFAR Dataset
(Elsevier, 2024) Derdiyok, Şeyma; AKBULUT, FATMA PATLAR; Çatal, Çağatay
The prevalence of mental fatigue is a noteworthy phenomenon that can affect individuals across diverse professions and working routines. This paper provides a comprehensive dataset of physiological signals obtained from 23 participants during their professional work and questionnaires to analyze mental fatigue. The questionnaires included demographic information and Chalder Fatigue Scale scores indicating mental and physical fatigue. Both physiological signal measurements and the Chalder Fatigue Scale were performed in two sessions, morning and evening. The present dataset encompasses diverse physiological signals, including electroencephalogram (EEG), blood volume pulse (BVP), electrodermal activity (EDA), heart rate (HR), skin temperature (TEMP), and 3-axis accelerometer (ACC) data. The NeuroSky MindWave EEG device was used for brain signals, and the Empatica E4 smart wristband was used for other signals. Measurements were carried out on individuals from four different occupational groups, such as academicians, technicians, computer engineers, and kitchen workers. The provision of comprehensive metadata supplements the dataset, thereby promoting inquiries about the neurophysiological concomitants of mental fatigue, autonomic activity patterns, and the repercussions of a cognitive burden on human proficiency in actual workplace settings. The accessibility of the aforementioned dataset serves to facilitate progress in the field of mental fatigue research while also laying the groundwork for the creation of customized fatigue evaluation techniques and interventions in diverse professional domains.
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.
Sentiment Analysis of Tweets on Online Education During COVID-19
(Springer Science and Business Media Deutschland GmbH, 2023) YAZGAN, HARUN; ÖZBEK, ONUR; GÜNAY, AHMET CAN; AKBULUT, FATMA PATLAR; ELİF, YILDIRIM; KOCAÇINAR, BÜŞRA; ŞENGEL, ÖZNUR
The global coronavirus disease (COVID-19) pandemic has devastated public health, education, and the economy worldwide. As of December 2022, more than 524 million individuals have been diagnosed with the new coronavirus, and nearly 6 million people have perished as a result of this deadly sickness, according to the World Health Organization. Universities, colleges, and schools are closed to prevent the coronavirus from spreading. Therefore, distance learning became a required method of advancing the educational system in contemporary society. Adjusting to the new educational system was challenging for both students and instructors, which resulted in a variety of complications. People began to spend more time at home; thus, social media usage rose globally throughout the epidemic. On social media channels such as Twitter, people discussed online schooling. Some individuals viewed online schooling as superior, while others viewed it as a failure. This study analyzes the attitudes of individuals toward distance education during the pandemic. Sentiment analysis was performed using natural language processing (NLP) and deep learning methods. Recurrent neural network (RNN) and one-dimensional convolutional neural network (1DCNN)-based network models were used during the experiments to classify neutral, positive, and negative contents.
Investigating the Effects of Stress on Achievement: BIOSTRESS Dataset
(Elsevier Inc., 2023) ÇÖPÜRKAYA, ÇAĞLA; MERİÇ, ELİF; ERİK, ELİF BERRA; KOCAÇINAR, BÜŞRA; AKBULUT, FATMA PATLAR; Çatal, Çağatay
The effects of chronic stress on academic and professional achievement can have a substantial impact. This relationship is highlighted through a dataset that includes questionnaires and physiological data from a group of individuals. The questionnaire data of 48 individuals, the physiological data of 20 individuals during sessions with a psychologist, and the exam data of 8 individuals were analyzed. The questionnaire data collected includes demographic information and scores on the TOAD stress scale. Physiological data was captured using the Empatica e4, a wearable device, which measured various signals such as blood volume pulse, electrodermal activity, body temperature, interbeat intervals, heart rate, and 3-axis accelerometer data. These measurements were taken under different stress conditions, both high and low, during therapy sessions and an exam respectively. Overall, this study significantly contributes to our understanding of how stress affects achievement. By providing a large dataset consisting of questionnaires and physiological data, this research helps researchers gain a better understanding of the complex relationship between stress and achievement. It also enables them to develop innovative strategies for managing stress and enhancing academic and professional success.
Multi-Modal Fusion Learning Through Biosignal, Audio, and Visual Content for Detection of Mental Stress
(Springer London Ltd., 2023) GÜLİN, DOĞAN; AKBULUT, FATMA PATLAR
Mental stress is a significant risk factor for several maladies and can negatively impact a person's quality of life, including their work and personal relationships. Traditional methods of detecting mental stress through interviews and questionnaires may not capture individuals' instantaneous emotional responses. In this study, the method of experience sampling was used to analyze the participants' immediate affective responses, which provides a more comprehensive and dynamic understanding of the participants' experiences. WorkStress3D dataset was compiled using information gathered from 20 participants for three distinct modalities. During an average of one week, 175 h of data containing physiological signals such as BVP, EDA, and body temperature, as well as facial expressions and auditory data, were collected from a single subject. We present a novel fusion model that uses double-early fusion approaches to combine data from multiple modalities. The model's F1 score of 0.94 with a loss of 0.18 is very encouraging, showing that it can accurately identify and classify varying degrees of stress. Furthermore, we investigate the utilization of transfer learning techniques to improve the efficacy of our stress detection system. Despite our efforts, we were unable to attain better results than the fusion model. Transfer learning resulted in an accuracy of 0.93 and a loss of 0.17, illustrating the difficulty of adapting pre-trained models to the task of stress analysis. The results we obtained emphasize the significance of multi-modal fusion in stress detection and the importance of selecting the most suitable model architecture for the given task. The proposed fusion model demonstrates its potential for achieving an accurate and robust classification of stress. This research contributes to the field of stress analysis and contributes to the development of effective models for stress detection.
Deep Learning-Based User Experience Evaluation in Distance Learning
(Springer, 2023) SADIGOV, RAHIM; YILDIRIM, ELİF; KOCAÇINAR, BÜŞRA; AKBULUT, FATMA PATLAR; Çatal, Çağatay
The Covid-19 pandemic caused uncertainties in many different organizations, institutions gained experience in remote working and showed that high-quality distance education is a crucial component in higher education. The main concern in higher education is the impact of distance education on the quality of learning during such a pandemic. Although this type of education may be considered effective and beneficial at first glance, its effectiveness highly depends on a variety of factors such as the availability of online resources and individuals' financial situations. In this study, the effectiveness of e-learning during the Covid-19 pandemic is evaluated using posted tweets, sentiment analysis, and topic modeling techniques. More than 160,000 tweets, addressing conditions related to the major change in the education system, were gathered from Twitter social network and deep learning-based sentiment analysis models and topic models based on latent dirichlet allocation (LDA) algorithm were developed and analyzed. Long short term memory-based sentiment analysis model using word2vec embedding was used to evaluate the opinions of Twitter users during distance education and also, a topic model using the LDA algorithm was built to identify the discussed topics in Twitter. The conducted experiments demonstrate the proposed model achieved an overall accuracy of 76%. Our findings also reveal that the Covid-19 pandemic has negative effects on individuals 54.5% of tweets were associated with negative emotions whereas this was relatively low on emotion reports in the YouGov survey and gender-rescaled emotion scores on Twitter. In parallel, we discuss the impact of the pandemic on education and how users' emotions altered due to the catastrophic changes allied to the education system based on the proposed machine learning-based models.

Browse

Recent Submissions