Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

Job Title

Dr. Öğr. Üyesi

Last Name


First Name



Search Results

Now showing 1 - 10 of 24
  • PublicationRestricted
    Global Impact of the Pandemic on Education: A Study of Natural Language Processing
    School closures due to the Covid-19 pandemic have changed education forever and we have witnessed the rise of online learning platforms. The education units of the countries made great efforts to adapt to this new order. The expanding, quick spread of the virus and careful steps have prompted the quest for reasonable choices for continuing education to guarantee students get appropriate education and are not impacted logically or mentally. Different methods were attempted to understand how students were affected by this big change. In addition to the significance of traditional surveys and consulting services, the utilization of social media analysis is used as a supportive approach. This paper analyzes the feedback of students on social media via tweets. Deep sentiment analysis is employed to identify embedded emotions such as negative, neutral, and positive. We also aimed to classify irrelevant tweets as the fourth category. Our experiments showed that the tweets are mostly biased toward negative emotions. © 2022 IEEE.
  • PublicationOpen Access
    A Real-Time CNN-Based Lightweight Mobile Masked Face Recognition System
    (IEEE-Inst Electrical Electronics Engineers Inc., 2022) KOCAÇINAR, BÜŞRA; Taş, Bilal; AKBULUT, FATMA PATLAR; Çatal, Çağatay; Mishra, Deepti
    Due to the global spread of the Covid-19 virus and its variants, new needs and problems have emerged during the pandemic that deeply affects our lives. Wearing masks as the most effective measure to prevent the spread and transmission of the virus has brought various security vulnerabilities. Today we are going through times when wearing a mask is part of our lives, thus, it is very important to identify individuals who violate this rule. Besides, this pandemic makes the traditional biometric authentication systems less effective in many cases such as facial security checks, gated community access control, and facial attendance. So far, in the area of masked face recognition, a small number of contributions have been accomplished. It is definitely imperative to enhance the recognition performance of the traditional face recognition methods on masked faces. Existing masked face recognition approaches are mostly performed based on deep learning models that require plenty of samples. Nevertheless, there are not enough image datasets containing a masked face. As such, the main objective of this study is to identify individuals who do not use masks or use them incorrectly and to verify their identity by building a masked face dataset. On this basis, a novel real-time masked detection service and face recognition mobile application was developed based on an ensemble of fine-tuned lightweight deep Convolutional Neural Networks (CNN). The proposed model achieves 90.40% validation accuracy using 12 individuals' 1849 face samples. Experiments on the five datasets built in this research demonstrate that the proposed system notably enhances the performance of masked face recognition compared to the other state-of-the-art approaches.
  • PublicationRestricted
    Wearable Sensor-Based Evaluation of Psychosocial Stress in Patients With Metabolic Syndrome
    (Elsevier, 2020) AKBULUT, FATMA PATLAR; İkitimur, Barış; Akan, Aydın
    The prevalence of metabolic disorders has increased rapidly as such they become a major health issue recently. Despite the definition of genetic associations with obesity and cardiovascular diseases, they constitute only a small part of the incidence of disease. Environmental and physiological effects such as stress, behavioral and metabolic disturbances, infections, and nutritional deficiencies have now revealed as contributing factors to develop metabolic diseases. This study presents a multivariate methodology for the modeling of stress on metabolic syndrome (MES) patients. We have developed a supporting system to cope with MES patients' anxiety and stress by means of several biosignals such as ECG, GSR, body temperature, SpO(2), glucose level, and blood pressure that are measured by a wearable device. We employed a neural network model to classify emotions with HRV analysis in the detection of stressor moments. We have accurately recognized the stressful situations using physiological responses to stimuli by utilizing our proposed affective state detection algorithm. We evaluated our system with a dataset of 312 biosignal records from 30 participants and the results showed that our proposed method achieved an average accuracy of 92% and 89% in distinguishing stress level in MES and other groups respectively. Both being the focus of an MES group and others proved to be highly arousing experiences which were significantly reflected in the physiological signal. Exposure to the stress in MES and cardiovascular heart disease patients increases the chronic symptoms. An early stage of comprehensive intervention may reduce the risk of general cardiovascular events in these particular groups. In this context, the use of e-health applications such as our proposed system facilitates these processes.
  • PublicationOpen Access
    Wearable Sensor Device for Posture Monitoring and Analysis During Daily Activities: A Preliminary Study
    The increase in technological advancements in recent years has led to the emergence of a new lifestyle. Although being assisted by machines for small-scale tasks in daily housework makes daily life easier, this has caused people to reduce their daily active movements and negatively affects human health. Especially during the COVID-19 pandemic, with the conversion of the working style to the home environment, working hours spent at the desk are more than ever. Due to the prolongation of the working time, the employees stay in the same position more inactive, thus their muscles weaken and they start to have muscle disease. Weaknesses in the muscles have occurred to the formation of postural problems in people. In our study, a smart vest system was developed to detect and control posture disorders. The proposed system is designed to recommend the most suitable exercises to avoid any physical discomforts. It is also aimed to detect hunched posture by collecting data on the person wearing the vest through sensors. Besides, it is encouraged to correct the posture disorder by warning the person audibly during the hunched posture. The experiments conducted with eight participants showed that the proposed system warns the users with necessary posture corrections, proving its potential use.
  • Publication
    A smart wearable system for short-term cardiovascular risk assessment with emotional dynamics
    (Elsevier Sci Ltd, The Boulevard, Langford Lane, Kidlington, Oxford Ox5 1Gb, Oxon, England, 2018-11) Akan, Aydın; AKBULUT, FATMA PATLAR; 2918
    Recent innovative treatment and diagnostic methods developed for heart and circulatory system disorders do not provide the desired results as they are not supported by long-term patient follow-up. Continuous medical support in a clinic or hospital is often not feasible in elderly or aging populations; yet, collecting medical data is still required to maintain a high-quality of life. In this study, a smart wearable system design called Cardiovascular Disease Monitoring (CVDiMo), which provides continuous medical monitoring and creates a health profile with the risk of disease over time. Systematic tests were performed with analysis of six different biosignals from two different test groups with 30 participants. In addition to examining the biosignals of patients, using the physical activity results and stress levels deduced from the emotional state analysis achieved a higher performance in risk estimation. In our experiments, the highest accuracy of determining the short-term health status was obtained as 96%.
  • Publication
    Estimation of beat-to-beat interval from wearable photoplethysmography sensor on different measurement sites during daily activities
    (2018) Lawless, Kevin; Tanneeru, Akhilesh; Rao, Smriti; Lee, Bongmook; Misra, Veena; AKBULUT, FATMA PATLAR
    In this study, we present an algorithm to detect beat-to-beat interval from PPG in the presence of motion artifacts. Our approach includes splitting slowly varying DC components, statistical detrending, and Bessel filtering and Fast Fourier Transform with square window to reduce motion artifacts dependent on spectrum analysis. The algorithm segments beat intervals with a spectrogram to find the characteristic points of the waveform such as systolic and diastolic points. Interbeat intervals (IBI) are determined from these characteristic points to calculate heart rate. The PPG IBI algorithm is validated against ECG RR intervals from five different measurement sites during three daily activities. The results show that the most accurate IBI and HR detection from a wearable PPG device during regular user activity is from the upper arm or finger.
  • PublicationOpen Access
    Stress Detection Using Experience Sampling: A Systematic Mapping Study
    (MDPI, 2022) DOĞAN, GÜLİN; AKBULUT, FATMA PATLAR; Çatal, Çağatay; Mishra, Alok
    Stress has been designated the "Health Epidemic of the 21st Century" by the World Health Organization and negatively affects the quality of individuals' lives by detracting most body systems. In today's world, different methods are used to track and measure various types of stress. Among these techniques, experience sampling is a unique method for studying everyday stress, which can affect employees' performance and even their health by threatening them emotionally and physically. The main advantage of experience sampling is that evaluating instantaneous experiences causes less memory bias than traditional retroactive measures. Further, it allows the exploration of temporal relationships in subjective experiences. The objective of this paper is to structure, analyze, and characterize the state of the art of available literature in the field of surveillance of work stress via the experience sampling method. We used the formal research methodology of systematic mapping to conduct a breadth-first review. We found 358 papers between 2010 and 2021 that are classified with respect to focus, research type, and contribution type. The resulting research landscape summarizes the opportunities and challenges of utilizing the experience sampling method on stress detection for practitioners and academics.
  • PublicationOpen Access
    Bimodal affect recognition based on autoregressive hidden Markov models from physiological signals
    (2020-10) Perros, H.G; Shahzad, M.; AKBULUT, FATMA PATLAR
    Background and objective: Affect provides contextual information about the emotional state of a person as he/she communicates in both verbal and/or non-verbal forms. While human's are great at determining the emotional state of people while they communicate in person, it is challenging and still largely an unsolved problem to computationally determine the emotional state of a person. Methods: Emotional states of a person manifest in the physiological biosignals such as electrocardiogram (ECG) and electrodermal activity (EDA) because these signals are impacted by the peripheral nervous system of the body, and the peripheral nervous system is strongly coupled with the mental state of the person. In this paper, we present a method to accurately recognize six emotions using ECG and EDA signals and applying autoregressive hidden Markov models (AR-HMMs) and heart rate variability analysis on these signals. The six emotions include happiness, sadness, surprise, fear, anger, and disgust. Results: We evaluated our method on a comprehensive new dataset collected from 30 participants. Our results show that our proposed method achieves an average accuracy of 88.6% in distinguishing across the 6 emotions. Conclusions: The key technical depth of the paper is in the use of the AR-HMMs to model the EDA signal and the use of LDA to enable accurate emotion recognition without requiring a large number of training samples. Unlike other studies, we have taken a hierarchical approach to classify emotions, where we first categorize the emotion as either positive or negative and then identify the exact emotion.
  • Publication
    Restoring Fluorescence Microscopy Images by Transfer Learning From Tailored Data
    (IEEE-Inst Electrical Electronics Engineers Inc., 2022) AKBULUT, FATMA PATLAR; TÜREYEN, EZGİ DEMİRCAN; Kamasak, Mustafa E.
    In fluorescence microscopy imaging, noise is a very usual phenomenon. To some extent, it can be suppressed by increasing the amount of the photon exposure; however, it is not preferable since this may not be tolerated by the subjected specimen. Thus, a sophisticated computational method is needed to denoise each acquired micrograph, so that they become more adequate for further feature extraction and image analysis. However, apart from the difficulties of the denoising problem itself, one main challenge is that the absence of the ground-truth images makes the data-driven techniques less applicable. In order to tackle this challenge, we suggest to tailor a dataset by handpicking images from unrelated source datasets. Our tailoring strategy involves exploring some low-level view-based features of the candidate images, and their similarities to those of the fluorescence microscopy images. We pretrain and fine-tune the well-known feed-forward denoising convolutional neural networks (DnCNNs) on our tailored dataset and a very limited amount of fluorescence images, respectively to ensure both the diversity and the content-awareness. The quantitative and visual experimentation show that our approach is able to curate a dataset, which is significantly superior to the arbitrarily chosen source images, and well-approximates to the fluorescence images. Moreover, the combination of the tailored dataset with a few fluorescence data through the use of fine-tuning offers a good balance between the generalization capability and the content-awareness, on the majority of considered scenarios.
  • Publication
    Analysis of the Lingering Effects of COVID-19 on Distance Education
    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.