Rimita Lahiri

Evolutionary approach for selection of optimal EEG electrode positions and features for classification of cognitive tasks

This paper proposes a novel evolutionary approach to the optimal selection of electrodes as well as relevant EEG features for effective classification of cognitive tasks. The problem has been formulated in the framework of a single objective optimization problem with an aim to simultaneously satisfy three criteria. The first criterion deals with maximization of the correlation between the features of EEG sources before and after the selection of the optimal electrodes. The second criterion is concerned with minimization of the mutual information between the features of the selected EEG electrodes. The last criterion aims at maximization of the ratio of the difference between the selected features of the EEG sources between and within any two cognitive tasks. A self-adaptive variant of firefly algorithm is proposed to solve the above optimization problem by proficiently balancing the trade-off between the computational accuracy and the run-time complexity. Experiments undertaken over wide variety of cognitive tasks reveal that the proposed algorithm outperforms the other standard algorithms (applied to the same problem) in terms of accuracy and computational overhead.

HMM-based gesture recognition system using kinect sensor for improvised human-computer interaction

Currently, gesture recognition from continuous video sequences is one of the most exciting research areas. This paper proposes a novel HMM-based gesture recognition scheme that can be implemented for developing an improved HCI system capable of providing enhanced performance. This framework explores the high potential of Microsofts Kinect sensor in gesture recognition by utilizing it in the data acquisition phase. The primary novelty of the work lies in the choice of an active difference signature-based feature descriptor that contains time-warped information in a single sequence over the classically used geometric features. The discussed framework has been tested for 12 distinct gestures embodied by 60 different subjects and it is important to note that for all the gestures the proposed scheme has attained a fairly high recognition rate of nearly 90% which proves the worth of the present work in real time applications. Further, to check the efficacy of the newly formulated framework the performance of the same has been validated against the existing standard technologies.

A novel approach to TSK model based gesture driven robot movement

This paper presents a novel fuzzy based approach to gesture driven human robot interaction. Now a day, gestures are considered to be the most effective communicative medium for remotely controlling a robot. In this work, the gestures are employed to instruct a Khepera II robot to move from a specific starting position to a goal position following a specific path. The main highlight is the determination of exact degree of rotation with proper application of acceleration and brake in order to reach the specified goal position without hitting the obstacles. A Takagi-Sugeno-Kang based fuzzy model with two antecedents (type-2 fuzzy sets) and one consequent (crisp value) has been employed to determine the angle of rotation. The performance of the proposed framework has been tested in terms of a number of parameters like accuracy, precision, error rate etc. And in each case, the formulated strategy has proved its worth.

Evolutionary perspective for optimal selection of EEG electrodes and features

Abstract This paper proposes a novel evolutionary approach to the optimal selection of electroencephalogram (EEG) electrodes as well as relevant features for effective classification of cognitive tasks. The EEG electrode and feature selection (EFS) problem here has been formulated in the framework of an optimization problem with an aim to simultaneously satisfying four criteria. The first criterion deals with maximization of the correlation between the selected features of EEG source signals, before and after the selection of optimum electrodes. It thus ensures the preservation of information of the cortical sources corresponding to a cognitive task even after reducing the number of electrodes. The second criterion is concerned with minimization of the mutual information between the selected features of the EEG signals recorded by the selected electrodes. It helps in identifying the unique information by reducing the redundancy in the EEG signals recorded by the selected electrodes for a specific cognitive task. The third criterion aims at optimal selection of EEG electrodes and EEG features in an attempt to i) minimize the difference between the selected EEG source-features (to ensure their similarity) for a specific cognitive task and ii) maximize the difference between the selected EEG source-features (to ensure the efficient categorization) of different cognitive tasks. The last criterion is concerned with maximization of the classification accuracy of different cognitive tasks based on the selected EEG source-features, corresponding to the selected EEG electrodes. The originality of the paper lies in obtaining the sets of optimum EEG electrodes and EEG features by independent optimization of individual objectives. These sets of optimum EEG electrodes and EEG features are then ranked based on their fuzzy memberships to satisfy individual four objectives. A self-adaptive variant of firefly algorithm (referred to as SAFA) is proposed to optimize individual objectives by proficiently balancing the trade-off between the computational accuracy and the run-time complexity. Experiments undertaken over wide variety of cognitive tasks reveal that the proposed algorithm outperforms the other standard algorithms (applied to the same problem) in terms of accuracy and computational overhead.

Human skeleton matching for e-learning of dance using a probabilistic neural network

With the growing interest in the domain of human computer interaction (HCI) these days, budding research professionals are coming up with novel ideas of developing more versatile and flexible modes of communication between a man and a machine. Using the attributes of internet, the scientists have been able to create a web based social platform for learning any desired art by the subject himself/herself, and this particular procedure is termed as electronic learning or e-learning. In this paper, we propose a novel application of gesture dependent e-learning of dance. This e-learning procedure may provide help to many dance enthusiasts who cannot learn the art because of the scarcity of resources despite having great zeal. The paper mainly deals with recognition of different dance gestures of a trained user such that after detecting the discrepancies between the gestures shown and actually performed by a novice; the user can rectify his faults. The elementary knowledge of geometry has been employed to introduce the concept of planes in the feature extraction stage. Actually, five planes have been constructed to signify major body parts while keeping the synchronous parts in one unit. Then four distances and four angular features have been obtained to provide entire positional information of the different body joints. Finally, using a probabilistic neural network the dance gestures have been classified after training the said network with sufficient amount of data recorded from numerous subjects to maintain generality.

A novel approach to American sign language recognition using MAdaline neural network

Sign language interpretation is gaining a lot of research attention because of its social contributions which is proved to be extremely beneficial for the people suffering from hearing or speaking disabilities. This paper proposes a novel image processing sign language detection framework that employs MAdaline network for classification purpose. This paper mainly highlights two novel aspects, firstly it introduces an advanced feature set comprising of seven distinct features that has not been used widely for sign language interpretation purpose, more over utilization of such features negates the cumbersome step of cropping of irrelevant background image, thus reducing system complexity. Secondly it suggests a possible solution of the concerned problem can be obtained using an extension of the traditional Adaline network, formally termed as MAdaline Network. Although the concept of MAdaline network has originated much earlier, the provision of application of this framework in this domain definitely help in designing an improved sign language interpreting interface. The newly formulated framework has been implemented to recognize standardized American sign language containing 26 English alphabets from ‘A’ to ‘Z’. The performance of the proposed algorithm has also been compared with the standardized algorithms, and in each case the former one outperformed its contender algorithms by a large margin establishing the efficiency of the same.

Discriminating Motor Imagery EEG signals using an improvised regularised CSP algorithm

Common Spatial Pattern is considered as one of the most efficient feature extraction methods for rehabilitative BCI paradigms. In the past many researchers have devoted their financial and intellectual resources in the said domain with an aim to regularize the concept of CSP by adding prior information in order to reach closer to the desired objective. In this paper; a novel penalty term has been introduced as an extension of one of the most popular variants of RCSP algorithms; formally termed as Weighted Tikhonov Regularized CSP. The proposed strategy has been implemented for deciphering four class Motor Imagery signals recorded from different users while performing four imagined movements of right hand and left hand. An ensemble classifier comprising of k-NN layers has been used for the classification purpose and finally; the efficiency of the proposed framework has been tested against the traditionally used standard classifiers and in each case the designed algorithm outperformed the others.

Discriminating different color from EEG signals using Interval-Type 2 fuzzy space classifier (a neuro-marketing study on the effect of color to cognitive state)

Color perception is one of the most important cognitive features of human brain. Different colors lead to different cognitive activities and different mental arousal levels; as revealed by power spectral density obtained from EEG signals. As the color plays an important role in marketing and packaging industry; so neuro-marketing research; based on color stimuli is considered to be an important tool for market researcher. In order to assess the impact of each color; prime focus is to detect different colors from EEG signals. This study employs four color stimuli; e.g. red; green; yellow and blue; that were shown to various subjects and EEG signal corresponding to the mentioned stimulus was acquired. Power spectral density of each color was estimated and different activation areas of brain for each stimulus is illustrated in figures. This paper also employs an Interval-Type-II fuzzy space classifier for distinguishing between different stimuli that are considered for the concerned experiment. It is noted that classification rate is maximum for red color and minimum in case of yellow color. Precision and recall values also have been highlighted here. For detailed analysis; the performance of IT2FS classifier has been compared with other standard classifiers by Friedman Test.

SOFM and T1FS based measurement of correctness in dance postures for e-learning applications

Dance posture recognition has emerged as one of the most enriched and pragmatic research genre because of its wide applications for facilitating learning of dance by exploiting electronic means only. Ballet dance is one of the most ancient dance forms; moreover the artistic postures and unprecedented elegance of the ballet dance form fascinate the dance enthusiasts a lot. This motivated us to design a system enabling e-learning of ballet dance that allows a user to learn the art all by himself with the help of associative devices and to correct the postures by measuring the extent of correctness, thus not requiring the presence of any instructor to identify the flaws. In this paper, the principles of Type 1 Fuzzy Inference rules have been embedded in the correctness measurement phase of Self Organizing Feature Map. This paper primarily employs Self Organizing Feature Map because it serves the purpose of dance posture recognition and correctness measurement employing Type 1 Fuzzy rules inside a single hybrid framework. This scheme deals with 20 different body joint oriented features covering entire human skeleton and thus provides significantly better results. After analyzing and comparing the experimental findings it can be easily inferred that the designed scheme surpasses the existing methodologies by a noticeable margin.