| Author | Prashanth, Kolaneru |
| Note | A thesis submitted in partial fulfillment of the requirements for the
degree of Master of Engineering in
Microelectronics and Embedded systems
|
| Publisher | Asian Institute of Technology |
| Abstract | The aim of thesis is to design a device to detect baby cry. This device can play a vital role in providing better infant care. Mostly the working parents and deaf parents benefited from this system. The designed system detects baby cry when baby starts crying and using GSM network send information in the form SMS alerts to be registered mobile number, so that the parents able to assist the baby. To detect baby cry Mel frequency cepstral coefficients (MFCC) of baby cry sound was extracted and trained those prominent features with Convolutional Neural Network (CNN) algorithm. The CNN model training accuracy is 98 percent and testing accuracy is 96.3 percent. Similarly trained this sound features using different machine learning models like SVM, ANN, and KNN. Comparatively the CNN model got highest test accuracy 96.3%. The system architecture consists of microprocessor Raspberry pi 3B, a microphone to take input sound and GSM module to send SMS. |
| Year | 2019 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Microelectronics (ME) |
| Chairperson(s) | Mongkol Ekpanyapong; |
| Examination Committee(s) | Abeykoon, A. M. Harsha S.;Bohez, Erik L.J. ; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Thesis (M. Eng.) -- Asian Institute of Technology, 2019 |