Speech Emotion Recognition using LSTM and RNN
Authors: R. Nihaal Datta Sai, Syed Shahbaaz, U. Bhanu Prakash
Abstract
Deep learning methods are being applied in various recognition tasks such as image, speech, and music recognition. Convolutional Neural Networks (CNNs) especially show remarkable recognition performance for computer vision tasks. In addition, Recurrent Neural Networks (RNNs) and Long short- term memory (LSTM) show considerable success in many sequential data processing tasks. In this study, we investigate the result of the Speech Emotion Recognition (SER) algorithm based on LSTM-RNN trained using an emotional speech database. The main goal of our work is to propose a SER method based on concatenated CNNs and . By applying the propose methods to an emotional speech database, the classification result was verified to have better accuracy than that achieved using conventional classification methods. As Emotion recognition from speech signals is an important but challenging component of Human Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized or speech-based emotion recognition. The review covers databases used, emotions extracted contributions made toward speech emotion recognition and limitations related to it.
COVID-19 Future Forecasting using supervised Machine learning
Authors: Divyashree. G Mrs. Meghashree. A. C, Dr. G .F. Ali Ahammed
Abstract
Machine learning (ML) is the study of computer algorithm that improves automatically through experience and by the use of data, and it is based on forecasting mechanisms have proved their signification to outcomes to improve the decision making on the future course of actions. The ML has proved itself as a prominent field of study over the last decade by solving many very complex and sophisticated real world problems such as health care, autonomous vehicle (AV), business applications, natural language processing (NLP), and intelligent robots. This study demonstrates the capability of ML models to forecast the number of upcoming patients affected by covid-19 which is presently consider as a potential threat to mankind. In particular, four standard forecasting models, such as liner regression, least absolute shrinkage and selection operator, support vector machine, and exponential smoothing is used for study to forecast the threatening factors of COVID-19. This study aims to provide an early forecast model for the spread an early novel disease corona virus. Three types of prediction are detected by the model such are [1] the number of newly infected cases, [2] the number of deaths, and [3]the number of recoveries in the next 10days. This are the three results detected from this model this is most important application in the pandemic covid year.
Experimental analysis of The Performance of R22, R134a, R32 and R32/R134a Refrigerants with Different Standard Geometry of Filter-Driers on Air-Conditioning Test Rig
Authors: Narendra Solanki, Dr. Parag Mishra, Dr. Ajay Singh
Abstract
n this research work we have presented three variation of filter-driers with the various new alternative of R22, the new refrigerant are R134a, R32 at different proportion are taken ratio of the new refrigerant R32/R134a are 10:90, 20:80 and 30:70 by mass percentage. The coefficient of performance of refrigerant R32/R134a and blending ratio 30/70 by mass percentage at 3/8 inch and length 104mm is 62.30% more than R22, 50.38% more than R134a, 46.67% more than R32, 48.50% more than blending ratio 10:90, 41.14% more than blending ratio 20:80. For filter-drier of size 1/4 inch and 104mm length the coefficient of performance of refrigerant R32/R134a and blending ratio 30/70 by mass percentage is 52.38% more than R22, 33.19% more than R134a, 44.23% more than R32, 21.53% more than R32/R134a blending ratio 10:90, 14.31% more than R32/R134a blending ratio 20:80. The coefficient of performance of refrigerant R32 and 1/2 inch and length 104mm is 55.62% more than R22, 39.96 more than R134a, 41.62 more than R32/R134a blending ratio 10:90, 32.54% more than R32/R134a blending ratio 20:80 by mass percentage, 12.80% more than R32/R134a blending ratio 30:70 by mass percentage. Therefore R32/R134a 30:70 by mass percentage is an energy efficient refrigerant to replace R22 used in air conditioning test rig.