scispace - formally typeset
Search or ask a question
Author

Chamandeep Kaur

Bio: Chamandeep Kaur is an academic researcher from Panjab University, Chandigarh. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 5, co-authored 12 publications receiving 185 citations. Previous affiliations of Chamandeep Kaur include University Institute of Engineering and Technology, Panjab University.

Papers
More filters
Proceedings ArticleDOI
21 Feb 2015
TL;DR: The purpose of this paper is to give a brief introduction to the EEG signals and BCI system and a review on the conventional methods that are used for feature extraction of the signal.
Abstract: Brain Computer Interface (BCI) systems are the devices which are proposed to help the disabled, people who are incapable of making motor response to communicate with computer using brain signal. The aim of BCI is to interpret brain activity into digital form which acts as a command for a computer. One key challenge in current BCI research is how to extract features of random time-varying EEG signals and its classification as accurately as possible. Feature extraction techniques are used to extract the features which represent a unique property obtained from pattern of brain signal. Earlier EEG analysis was restricted to visual inspection only. The visual inspection of the signal is very subjective and hardly allows any standardization or statistical analysis. Hence, several different techniques were intended in order to quantify the information of the brain signal. Many linear and non-linear methods for feature extraction exist. The purpose of this paper is to give a brief introduction to the EEG signals and BCI system. The paper also includes a review on the conventional methods that are used for feature extraction of the signal.

138 citations

Journal ArticleDOI
TL;DR: A broad spectrum of neural mechanics under a variety of meditation styles has been reviewed and the controversial subject of epileptiform EEG changes and other adverse effects during meditation has been raised.
Abstract: Meditation advances positivity but how these behavioral and psychological changes are brought can be explained by understanding neurophysiological effects of meditation. In this paper, a broad spectrum of neural mechanics under a variety of meditation styles has been reviewed. The overall aim of this study is to review existing scientific studies and future challenges on meditation effects based on changing EEG brainwave patterns. Albeit the existing researches evidenced the hold for efficacy of meditation in relieving anxiety and depression and producing psychological well-being, more rigorous studies are required with better design, considering client variables like personality characteristics to avoid negative effects, randomized controlled trials, and large sample sizes. A bigger number of clinical trials that concentrate on the use of meditation are required. Also, the controversial subject of epileptiform EEG changes and other adverse effects during meditation has been raised.

51 citations

Journal ArticleDOI
TL;DR: The main aim of this paper is to present the investigation carried out to suppress the noise found in EEG signals of depression, and to compare the effectiveness of the physiological signal denoising approaches based on discrete wavelet transform and wavelet packet transform combined with VMD with other approaches.

43 citations

Journal ArticleDOI
TL;DR:
Abstract: Traditionally, nonlinear data processing has been approached via the use of polynomial filters, which are straightforward expansions of many linear methods, or through the use of neural network techniques. In contrast to linear approaches, which often provide algorithms that are simple to apply, nonlinear learning machines such as neural networks demand more computing and are more likely to have nonlinear optimization difficulties, which are more difficult to solve. Kernel methods, a recently developed technology, are strong machine learning approaches that have a less complicated architecture and give a straightforward way to transforming nonlinear optimization issues into convex optimization problems. Typical analytical tasks in kernel-based learning include classification, regression, and clustering, all of which are compromised. For image processing applications, a semisupervised deep learning approach, which is driven by a little amount of labeled data and a large amount of unlabeled data, has shown excellent performance in recent years. For their part, today’s semisupervised learning methods operate on the assumption that both labeled and unlabeled information are distributed in a similar manner, and their performance is mostly impacted by the fact that the two data sets are in a similar state of distribution as well. When there is out-of-class data in unlabeled data, the system’s performance will be adversely affected. When used in real-world applications, the capacity to verify that unlabeled data does not include data that belongs to a different category is difficult to obtain, and this is especially true in the field of synthetic aperture radar image identification (SAR). Using threshold filtering, this work addresses the problem of unlabeled input, including out-of-class data, having a detrimental influence on the performance of the model when it is utilized to train the model in a semisupervised learning environment. When the model is being trained, unlabeled data that does not belong to a category is filtered out by the model using two different sets of data that the model selects in order to optimize its performance. A series of experiments was carried out on the MSTAR data set, and the superiority of our method was shown when it was compared against a large number of current semisupervised classification algorithms of the highest level of sophistication. This was especially true when the unlabeled data had a significant proportion of data that did not fall into any of the categories. The performance of each kernel function is tested independently using two metrics, namely, the false alarm (FA) and the target miss (TM), respectively. These factors are used to calculate the proportion of incorrect judgments made using the techniques.

39 citations

Journal ArticleDOI
TL;DR: A novel hybrid framework based on three classifiers, including SVM, logistic regression, and random forest, is proposed in this paper and has worked well and has been compared to other methods based on several performance metrics, such as accuracy, precision, recall, and recall.
Abstract: The Sentimental Analysis approach is typically used for analyzing a user's ideas, sentiments, and text subjectivity, all of which are expressed through text. Sentimental analysis, also known as "opinion mining," is a type of data mining that follows the concept of emotional analysis presented by people in a thoughtful manner. Based on historical evidence, websites are the most effective venue for soliciting customer feedback. Existing methodologies based on sentimental analysis are ineffective. As a result, a novel hybrid framework based on three classifiers, including SVM, logistic regression, and random forest, is proposed in this paper. Based on user feedback or historical data, the hybrid model serves as an effective classifier, assisting in the development of more accurate classification results. Furthermore, the proposed model has worked well and has been compared to other methods based on several performance metrics, such as accuracy, precision, recall, and recall.

29 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A modified regression approach using Bayesian adaptive regression splines to filter the electrooculogram (EOG) before computing correction factors supported the use of regression-based and PCA-based ocular artifact correction and suggested a need for further studies examining possible spectral distortion from ICA-based corrections.

221 citations

Journal ArticleDOI
22 Mar 2016-PeerJ
TL;DR: The Emotiv EPOC device may be more suitable for control tasks using the attention/meditation level or eye blinking than the Neurosky MindWave device, which exhibits high variability and non-normality of attention and meditation data.
Abstract: We present the evaluation of two well-known, low-cost consumer-grade EEG devices: the Emotiv EPOC and the Neurosky MindWave. Problems with using the consumer-grade EEG devices (BCI illiteracy, poor technical characteristics, and adverse EEG artefacts) are discussed. The experimental evaluation of the devices, performed with 10 subjects asked to perform concentration/relaxation and blinking recognition tasks, is given. The results of statistical analysis show that both devices exhibit high variability and non-normality of attention and meditation data, which makes each of them difficult to use as an input to control tasks. BCI illiteracy may be a significant problem, as well as setting up of the proper environment of the experiment. The results of blinking recognition show that using the Neurosky device means recognition accuracy is less than 50%, while the Emotiv device has achieved a recognition accuracy of more than 75%; for tasks that require concentration and relaxation of subjects, the Emotiv EPOC device has performed better (as measured by the recognition accuracy) by ∼9%. Therefore, the Emotiv EPOC device may be more suitable for control tasks using the attention/meditation level or eye blinking than the Neurosky MindWave device.

170 citations

Journal ArticleDOI
TL;DR: This review seeks to provide the detail of the products supplied by the major players, summarize studies that evaluate consumer product’s performance against research grade devices, the key areas of applications that these consumer grade devices have been employed in over the past five years or so, and finally give perspectives on the limitations and what these innovative tools could offer going forward.
Abstract: Since the launch of the first consumer grade EEG measuring sensors ‘NeuroSky Mindset’ in 2007, the market has witnessed an introduction of at least one new product every year by competing manufacturers, which include NeuroSky, Emotiv, interaXon and OpenBCI. There are numerous variations in the make and versions, but these products clearly share the key selling points of affordability, portability, and ease of use. These features are patently well placed provided one of the main objectives for their development is to attract a new target group of commercial users. Nevertheless, with several decades of traditional EEG usage in clinical and experimental settings, the shift toward commercial and engineering sides has not been achieved without skepticism. With this in mind, researchers in related fields have been tirelessly working to ensure that these putatively novel features were not introduced at the expense of efficiency and accuracy by conducting validation studies to compare the performance of data derived from consumer grade EEG devices with ones from standard research grade counterparts. In this review, we seek to provide the detail of the products supplied by the major players, summarize studies that evaluate consumer product’s performance against research grade devices, the key areas of applications that these consumer grade devices have been employed in over the past five years or so, and finally give our perspectives on the limitations and what these innovative tools could offer going forward in terms of research and commercial applications.

144 citations

Journal ArticleDOI
04 Apr 2020-Sensors
TL;DR: Results show that the proposed approach is superior to, or on par with, the reference subject-independent EEG emotion recognition studies identified in literature and has limited complexity due to the elimination of the need for feature extraction.
Abstract: The electroencephalogram (EEG) has great attraction in emotion recognition studies due to its resistance to deceptive actions of humans. This is one of the most significant advantages of brain signals in comparison to visual or speech signals in the emotion recognition context. A major challenge in EEG-based emotion recognition is that EEG recordings exhibit varying distributions for different people as well as for the same person at different time instances. This nonstationary nature of EEG limits the accuracy of it when subject independency is the priority. The aim of this study is to increase the subject-independent recognition accuracy by exploiting pretrained state-of-the-art Convolutional Neural Network (CNN) architectures. Unlike similar studies that extract spectral band power features from the EEG readings, raw EEG data is used in our study after applying windowing, pre-adjustments and normalization. Removing manual feature extraction from the training system overcomes the risk of eliminating hidden features in the raw data and helps leverage the deep neural network's power in uncovering unknown features. To improve the classification accuracy further, a median filter is used to eliminate the false detections along a prediction interval of emotions. This method yields a mean cross-subject accuracy of 86.56% and 78.34% on the Shanghai Jiao Tong University Emotion EEG Dataset (SEED) for two and three emotion classes, respectively. It also yields a mean cross-subject accuracy of 72.81% on the Database for Emotion Analysis using Physiological Signals (DEAP) and 81.8% on the Loughborough University Multimodal Emotion Dataset (LUMED) for two emotion classes. Furthermore, the recognition model that has been trained using the SEED dataset was tested with the DEAP dataset, which yields a mean prediction accuracy of 58.1% across all subjects and emotion classes. Results show that in terms of classification accuracy, the proposed approach is superior to, or on par with, the reference subject-independent EEG emotion recognition studies identified in literature and has limited complexity due to the elimination of the need for feature extraction.

132 citations

Journal ArticleDOI
07 Sep 2020-Sensors
TL;DR: A survey of the pertinent scientific literature from 2015 to 2020 presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective and provides insights for future developments.
Abstract: Affecting computing is an artificial intelligence area of study that recognizes, interprets, processes, and simulates human affects. The user's emotional states can be sensed through electroencephalography (EEG)-based Brain Computer Interfaces (BCI) devices. Research in emotion recognition using these tools is a rapidly growing field with multiple inter-disciplinary applications. This article performs a survey of the pertinent scientific literature from 2015 to 2020. It presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective. Our survey gives an overview of datasets, emotion elicitation methods, feature extraction and selection, classification algorithms, and performance evaluation. Lastly, we provide insights for future developments.

131 citations