Prathwini
@nmamit.nitte.edu.in
Assistant Professor Master of computer applications
NMAMIT Institute of technology
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Engineering, Artificial Intelligence, Computer Science Applications
Scopus Publications
Scopus Publications
Prathwini - and Prathyakshini -
The Science and Information Organization
—Emotion detection from videos plays a pivotal role in understanding human behavior and interaction. This study delves into a cutting-edge method that leverages Recurrent Neural Networks (RNN), Support Vector Machines (SVM), K-Nearest Neighbours (KNN), Convolutional Neural Networks (CNN) and to precisely detect emotions exhibited in video content, holding significant importance in comprehending human behavior and interactions. The devised approach entails a multi-phase procedure: initially, employing CNN-based feature extraction to isolate facial expressions and pertinent visual cues by extracting and pre-processing video frames. These extracted features capture intricate patterns and spatial information crucial for discerning emotions. The results of the trials show that CNN, SVM, KNN, and RNN have promising performance, highlighting their potential. Among the other machine learning models, RNN has attained a 95% accuracy rate in recognizing and classifying emotions in video information. This combination of approaches provides a thorough plan for identifying emotions in dynamic visual material in real time.
Prathwini, Anisha P. Rodrigues, P. Vijaya, and Roshan Fernandes
Institute of Electrical and Electronics Engineers (IEEE)
Language is a primary means of communication, but it is not the only means; knowing a language does, however, assist speed up the process. Many distinct languages are spoken worldwide, and people use them to communicate. This is only one of the many reasons why language is so crucial. Based on the literature survey, it is evident that there is a lack of available translators for the Tulu language. Despite being prevalent predominantly in Karnataka, the Tulu language has not been as widely spoken as other Indian languages until recently, although it gained enough recognition to become the second language in Karnataka. The purpose of our research work aims at translating the English language into the Tulu language. During the evaluation the system was tested on a dataset consisting of handwritten characters during the evaluation process Convolutional Neural Networks used achieved an accuracy rate of 92%. To translate English to the Tulu language, we employed a parallel sentence dataset for the neural approach and a parallel word dataset for the rule-based approach. The rule-based approach resulted in an 89% accuracy rate for word-based analysis and an 81% accuracy rate for sentence-based analysis for the English-to-Tulu language translation. The neural machine translation approach of the Encoder-Decoder model with LSTM is been used to accomplish translation from English to Tulu with a BLEU score of 0.83 and Tulu to English with a BLUE score of 0.65. The model also employed hybrid machine translation to enhance the translation.
Prathyakshini and Prathwini
IEEE
Gestures through hands and fingers, popularly called Hand gestures, are a common way for human-robot interaction. Hand motions are a type of nonverbal correspondence that can be utilised in a few fields, for example, correspondence between hard of hearing quiet individuals, robot controlled, Human and Computer communication, house mechanisation and clinical areas. Research articles in view of hand and finger motions have embraced various strategies, including those in light of instrumented sensor innovation and PC vision. Hand gesture recognition gives a canny, normal and helpful method of Human-Computer Interaction (HCI). Hand gesture recognition has numerous applications in medical, engineering and even military research areas. As the reliance of our general public on innovation develops step by step, the utilisation of gadgets like cell phones, PCs are additionally expanding. Hand signals are utilized as a contribution to our framework. Hand gesture recognition based man-machine point of interaction is being grown overwhelmingly lately. Because of the effect of lighting and complex foundation, many hand gesture recognition frameworks work well. A versatile skin variety model in light of face recognition is used to identify skin variety areas like hands. To order the unique hand signals, a straightforward and quick movement history picture based strategy is used. Four gatherings of hand directional examples were prepared for the up, down, left, and right hand signals classifiers.
Preethi Salian K, Prathyakshini, Prathwini, Jayashree, and Supriya Salian
IEEE
Music genres are some groups of terms generated for the sake of categories the music. Music genres have some typical characteristics. The characteristics are associated with harmonic content of the music, rhythmic structure, and instrumentation. Basically, these Genre hierarchies are utilized to arrange the big collection of songs on the internet. At present this is done manually, so automatic classification is necessary in order to aid the human user. Also, automatic genre classification for music imparts an outline for evaluating and developing attributes for the interpretation of musical signals. For classification purpose different genre classes such as Blues, classical, pop, disco, hip-hop, jazz, reggae, country, metal, and rock. In this proposed work four widely known machine learning algorithms are used to train and test the classifier with a well-known dataset for audio data classification to envisage the genre of music that the audio given as input belongs to. Convolution Neural Network(CNN), Feed-Forward Neural Network(FNN), K- Nearest Neighbours(KNN), Support Vector Machine(SVM) classifiers are used out of which Convolution Neural Network achieved highest accuracy of 81%.
Prathwini, Roshan Fernandes, and Anisha P Rodrigues
IEEE
Emotions is the way of understanding the human action mainly those conveyed with facial expression. We understand only one third of other people feeling through their words and tone of voice and rest two third comes from the facial expression. Emotion detection is carried out using deep learning approaches. Surveying social media content through text, speech, and images and video should be essential in various uses. Emotion recognition can be applied to images, videos, text and written content. In this paper we have applied emotion recognition to video as it carries human face in motion and gives more information on human feelings. In this paper deep learning techniques are used to recognise human emotions in stored video. We have considered the Convolutional Neural Networks (CNN) to forecast the different emotions namely anger, surprise, happiness and neutral portrayed in a stored video. Convolution Neural Network applied to emotion detection has provided promising results. Emotion recognition technology can be applied to activities like market research and can be beneficial for security purpose utilizing CCTVs to catch the behavior of some unspecified person and forecast either he/she is suspicious or not.