Thesis (Bachelor of Science in Computer Science)

Browse

End date: 2019Subject: search.filters.subject.EEG

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Factor analysis of ad liking and prediction of purchase intent through emotionomics
    (BRAC University, 2019-12) Toma, Syeda Tanzina Farhin; Bhuiyan, Shahan Jamil; Dawood, Tahmid; Saha, Chandan Kumar; Alam, Md.Golam Rabiul
    Marketing strategy is being a new challenge in this modern era. Along with the global market, people's choices are also changing so to grab the focus of buyers, organizations are making changes in their marketing policy based on user's choice to increase the possibility of their product being sold. Advertisements are the way to promote products and they are available on every media platform nowadays. The focus was always to gather public attention through different messages but which factors of advertising were needed more was not fixed. To recognize the dependencies of a successful advertisement and identify the factors which create good impression in people mind we lead this study. Using supervised machine learning algorithms and feature extraction method we find out the factors of ad liking and predict the purchase intent through emotionomics which makes an ad successful.
  • Thumbnail Image
    Item
    Consumer behaviour analysis using EEG signals for Neuromarketing Application
    (BRAC University, 2019-12) Amin, Chowdhury Rabith; Hasin, Mirza Farhan; Leon, Tasin Shafi; Aurko, Abrar Bareque; Parvez, Mohammad Zavid
    Neuromarketing is applying neuropsychology in marketing research which studies consumer sensory-motor such as cognitive and affective response to marketing stimuli with the help of modern technologies. It is one of the most recent marketing research strategies and might be the future of marketing research. In our study, we demonstrated how marketing may benefit from Neuromarketing through analysing consumer behavior with the help of EEG signal. Consumer’s responses toward marketing strategies and their behavior towards purchasing or selecting products or goods can be studied and analyzed for a better producer and consumer relationship. To do so we took a sample of our population for collecting EEG signals of different ages, groups and gender for a better understanding of consumer behavior towards a marketing policy. Through analyzing the data we tried to uncover how and why they like certain marketing policies and how different part of the human brain reacts while those marketing policies are applied to them.We used some machine learning approaches where Decision Tree achieved highest accuracy of 95%. We also tested whether neuropsychological measures can capture differences in consumer’s actions in different marketing stimuli. And also if studies in this field can bring a change and improve marketing strategies for the betterment of both producer and consumer and result in the mutual benefit of both. We believe that neuropsychological measures soon will be widely acknowledged and used as a complimentary method in classical marketing research. We tried to contribute to this field by doing as much as we could with our work.
  • Thumbnail Image
    Item
    Applying tDCS over the dominant Hemisphere to observe event-related Desynchronization
    (BRAC University, 2019-12) Khan, Akif Ahmed; Bastob, Abu Wakkas; Ahmed, Bushra; Reza, Abdullah Al; Parvez, Mohammad Zavid
    Although keeping us alive is arguably the most important function of the human brain, the human brain is responsible for a host of functions|including processing of environmental stimuli. Electroencephalography (EEG) is a psychophysiological technique used to measure electro-cortical activity in the brain. It is a noninvasive technique that provides a direct measure of the brain's electrical activity through placement of electrodes on the scalp which is quite precise and instantaneous. A set of probes or electrodes are placed on the scalp which receive EEG signals or brain waves. Using EEG signals we may analyze the mechanisms behind language, cognition, sensory functions, and brain oscillations. After gathering the eeg signals, it can be used as a neurofeedback - a process by which eeg signals are again applied to the brain with the same electrodes. By applying neurofeedback of some speci c pattern or feature we can enhance those features and reduce the other features. Transcarnial Direct Current Stimulation (tDCs) is also another non-invasive method of neuromodulation which is used to constatly apply a small amount of electric current on the head with the use of electrodes. With adequate amount of training with neurofeedback, tdcs individuals may learn to control their own brain waves and thus changing their state of self at will. We have initiated a system where we use EEG-based neurofeedback and tDCs on the left hemisphere of the brain and observe Event-related desynchronization occuring on the right hemisphere. After applying ve-fold cross validation method of classi cation we acquired an accuracy of 86.67% for anodal stimulation and 88.33% for cathodal stimulation.
  • Thumbnail Image
    Item
    Classi fication of motor imagery tasks based on BCI paradigm
    (BRAC University, 2019-09) Hossain, Nahid; Hasan, Bhuiyan Itmam; Mohona, Mahfuza Humayra; Noshin, Kantat Rehnuma; Parvez, Mohammad Zavid
    Motor imagery tasks are mental processes by which individual practices a set of actions in their mind without actually performing the physical movements. Research in the motor imagery tasks allow us to acquire critical information on how the human brain works, which further enables us to integrate the knowledge with brain-computer interface (BCI) technologies to improve neurological rehabilitation along with, commercial uses such as communication, entertainment, etc. Electroencephalogram (EEG) is a commonly used process to observe and classify brain activities. However, EEG signal is non-stationary in nature, therefore, feature extraction based on EEG signals is quite hard. In our thesis, empirical mode decomposition (EMD) was used to break down the original signal into intrinsic mode functions (IMFs) in order of higher frequency to lower frequency. Convolution neural network (CNN) is then used on IMFs' feature vector and classify di erent motor imagery tasks. Our proposed model achieves around 78% accuracy, where the dataset was captured from nine participants.
  • Thumbnail Image
    Item
    Emotion recognition using EEG signal and deep learning approach
    (BRAC University, 2019-08) Islam, Sayedi Hassan Bin; Mehdi, Md. Quamar; Rohan, Bhuiyan Yash; Mahmood, Syed Atif Imtiaz; Parvez, Mohammad Zavid
    Emotion is a mental state, which originates in the brain and is closely related to the nervous system. Emotion can be defined as a feeling expressed through, or detectable by voice intonation, facial expression body language, as response from one’s mood relationship with others and most importantly the circumstance they are in. Although, Brain Computer Interface (BCI) are being developed to find a better human-machine interaction system using brain activity and it is frequently implemented by Electroencephalogram (EEG) signals. EEG is a well established approach to measure the brain activities which can be analyzed and processed to distinguish different emotions. In this thesis, we present an approach to classify human emotions using EEG signal by Convolutional Neural Network(CNN). In our model, we use the Dataset for Emotion Analysis using Physiological signals (DEAP) dataset, a benchmark for emotion classification research, to transform the EEG signal from time domain to frequency domain and extract the features to classify the emotions. Emotion can be classified based on the two dimensions of valence and arousal. Previous researches have used fewer channels and participants. Our approach which was carried out on 32 participants, has achieved an accuracy of 94.75% for the valence and 95.75% on the arousal detection, which is quite competitive with other methods of emotion recognition.
  • Thumbnail Image
    Item
    EEG signals analysis for motor imagery brain computer interface
    (BRAC University, 2019-08) Rahman, La z Maruf; Alam, Zawad; Rahman, Md. Musta-E-Nur; Parvez, Mohammad Zavid
    A brain{computer interface is a medium for communication which converts neuronal signals into commands towards controlling external system. This thesis presented the process of classifying three motor imagery tasks using EEG signals which can be further evolved into BCI system that can remotely control external devices. Different bands are ltered from EEG signals in order to extract di erent frequency distributed features. These features are used to classify di erent motor imagery tasks based on SVM and ANN. Experimental results show that SVM carried higher accuracy (i.e., 80%) compared to other machine learning algorithms where seven subjects participated in this experiment.