Papers by Harikrishna Mulam
Advances in engineering research, Dec 31, 2022
Advances in engineering research, Dec 31, 2022
Advances in engineering research, Dec 31, 2022
Biomedical Engineering / Biomedizinische Technik, 2020
In recent times, the control of human-computer interface (HCI) systems is triggered by electroocu... more In recent times, the control of human-computer interface (HCI) systems is triggered by electrooculography (EOG) signals. Eye movements recognized based on the EOG signal pattern are utilized to govern the HCI system and do a specific job based on the type of eye movement. With the knowledge of various related examinations, this paper intends a novel model for eye movement recognition based on EOG signals by utilizing Grey Wolf Optimization (GWO) with neural network (NN). Here, the GWO is used to minimize the error function from the classifier. The performance of the proposed methodology was investigated by comparing the developed model with conventional methods. The results reveal the loftier performance of the adopted method with the error minimization analysis and recognition performance analysis in correspondence with varied performance measures such as accuracy, sensitivity, specificity, precision, false-positive rate (FPR), false-negative rate (FNR), negative predictive value (...
Computer Vision – ECCV 2012, 2012
We consider the problem of semi-supervised bootstrap learning for scene categorization. Existing ... more We consider the problem of semi-supervised bootstrap learning for scene categorization. Existing semi-supervised approaches are typically unreliable and face semantic drift because the learning task is under-constrained. This is primarily because they ignore the strong interactions that often exist between scene categories, such as the common attributes shared across categories as well as the attributes which make one scene different from another. The goal of this paper is to exploit these relationships and constrain the semi-supervised learning problem. For example, the knowledge that an image is an auditorium can improve labeling of amphitheaters by enforcing constraint that an amphitheater image should have more circular structures than an auditorium image. We propose constraints based on mutual exclusion, binary attributes and comparative attributes and show that they help us to constrain the learning problem and avoid semantic drift. We demonstrate the effectiveness of our approach through extensive experiments, including results on a very large dataset of one million images.
Applied Nanoscience, Jul 26, 2022
Advances in Engineering Software
2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS), 2017
Recent researches are made in Electrooculography (EOG) signal to control the Human-Computer Inter... more Recent researches are made in Electrooculography (EOG) signal to control the Human-Computer Interface (HCI) system by classifying the signal. Since then, the investigations were extended to understand the characteristics of EOG. This paper proposes a novel model for recognizing the eye movements using EOG signals. Furthermore, we have proposed a statistical procedure for the dimensionality reduction of the EOG signal. In addition, we have depicted Neural Network (NN) classifier for classifying the EOG signal. The proposed methodology is compared to the existing method and it is observed that the proposed methodology gives the better performance in terms of Accuracy, Specificity, Precision, False Negative Rate (FNR), False Positive Rate (FPR), Sensitivity, Negative Predictive Value (NPV), False Discovery Rate (FDR), Mathews Correlation Coefficient (MCC) and F1_Score.
2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2017
This paper presents a novel method for eye movement recognition using Electrooculography (EOG) si... more This paper presents a novel method for eye movement recognition using Electrooculography (EOG) signals which are being used to control the Human-Computer Interface (HCI) systems. With the knowledge of several related investigations, this paper develops a methodology for eye movement recognition by introducing a feature mapping process. The proposed feature mapping process transforms the decomposed EOG signal into a transformation plane, where the intra-class margin is low. To accomplish the transformation, this proposed feature mapping process exploits Grey Wolf Optimization (GWO). The resultant features are used to classify the eye movements using Neural Network (NN). Later, the paper validates the superior performance of the proposed method with suitable performance analysis related to error minimization, mapping margin and recognition performance.
2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT)
The Human-Computer Interface (HCI) systems are recently being regulated by the Electrooculography... more The Human-Computer Interface (HCI) systems are recently being regulated by the Electrooculography (EOG) signals, which preserves the information related to the eye movements. Along with the diverse investigations related with this subject, this paper proposes a novel model for recognizing the eye movements from EOG signals using Grey Wolf Optimization (GWO) based Neural Network (NN). GWO here is used to reduce the error function of the classifier outcome. Further, it compares the performance of the proposed method with the conventional method, i.e. NN with traditional learning algorithm. The results reveal the superior performance of the proposed method with the error minimization analysis, gradient analysis and recognition performance analysis in terms of several performance measures.
Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine
Many research works are in progress in classification of the eye movements using the electrooculo... more Many research works are in progress in classification of the eye movements using the electrooculography signals and employing them to control the human–computer interface systems. This article introduces a new model for recognizing various eye movements using electrooculography signals with the help of empirical mean curve decomposition and multiwavelet transformation. Furthermore, this article also adopts a principal component analysis algorithm to reduce the dimension of electrooculography signals. Accordingly, the dimensionally reduced decomposed signal is provided to the neural network classifier for classifying the electrooculography signals, along with this, the weight of the neural network is fine-tuned with the assistance of the Levenberg–Marquardt algorithm. Finally, the proposed method is compared with the existing methods and it is observed that the proposed methodology gives the better performance in correspondence with accuracy, sensitivity, specificity, precision, fals...
Biomedical Engineering / Biomedizinische Technik
In recent times, the control of human-computer interface (HCI) systems is triggered by electroocu... more In recent times, the control of human-computer interface (HCI) systems is triggered by electrooculography (EOG) signals. Eye movements recognized based on the EOG signal pattern are utilized to govern the HCI system and do a specific job based on the type of eye movement. With the knowledge of various related examinations, this paper intends a novel model for eye movement recognition based on EOG signals by utilizing Grey Wolf Optimization (GWO) with neural network (NN). Here, the GWO is used to minimize the error function from the classifier. The performance of the proposed methodology was investigated by comparing the developed model with conventional methods. The results reveal the loftier performance of the adopted method with the error minimization analysis and recognition performance analysis in correspondence with varied performance measures such as accuracy, sensitivity, specificity, precision, false-positive rate (FPR), false-negative rate (FNR), negative predictive value (...
IET Image Processing
The human eye movement tracking is possible with the assistance of the electrooculography (EOG) s... more The human eye movement tracking is possible with the assistance of the electrooculography (EOG) signals. The human eye tracking system allows researchers to analyse the participant's eye movements during certain activities. This study offers the EOG signals to control the human–computer interface systems with the help of Empirical Mean Curve Decomposition (EMCD) decomposition model. At first, the input EOG signal is provided as input to the EMCD decomposition model, later the resultant signal is given to principal component analysis for dimensional reduction, and then the dimensional reduced signal is offered to multi-wavelet decomposition model. The resultant dimensionally reduced multi-wavelet decomposed signal is passed to the proposed Feature Mapping (FM) model, using the k-means clustering model. Then, the Grey Wolf Optimization (GWO) algorithm is utilised to tune the margin. Next to mapping, the obtained features are provided to the nearest neighbour classifier, to obtain the eye movement. Next to the implementation, the proposed method is compared with the existing methods, and it is witnessed that the proposed methodology gives the superior performance in correspondence with accuracy, sensitivity, specificity, precision, false positive rate, false negative rate, negative predictive value, false discovery rate, F1 score and Mathews correlation coefficient.
Uploads
Papers by Harikrishna Mulam