Educational Journey
Federal University of Agriculture, Abeokuta
BSc, MSc, PhD Artificial Intelligence Research • Artificial Intelligence Research and Intelligent System Design
Experience
Grants and Awards
Fellow
Global Journal
Research
Deep Learning Algorithm for Speech Recognition Multiplexer System Suitable for World Congress Discussion
The difficulties encountered in building an intelligent speech recognition system and identifying various accents in speeches has been examined by this research. The research has adopted the MFCC extraction techniques using the energy values in the spectrogram generated by the neural algorithm. The sampling procedures ensured that 1/16000 wave amplitude of a second intervals were enough sample size for speech to be recognized. The deep learning neural network architecture is of 5- 9-6-3 configuration coded in python functional programming language with 250epoch runs, while the back propagation method of iteration is used to ensure that the errors are brought to the barest minimum, with average value of about 0.002 0r 0.2% which is okay for training model. The system as a whole is designed as a multiline multiplexer suitable for holding international congress meetings. The MFCC extraction techniques showed that the energy values can be used by the neurons to recognize the usable pitch in a complex sound clips
The Iot-Machine Learning Security Algorithm for Detecting the Intruders Gaining an Unauthorised
The essentiality in the protection of the government restricted areas using the technology of IOT (Internet of Things) has been observed in this research, with the sole aim of providing certain measures to curbing the activities of the terrorists creating dirty scenario within the environment. The neural network employed four input neurons which are the Sensors used as IP address, while the government authorized areas are the clients who receive messages from the IP neurons, there are two separate hidden layers of orders seven each as the processors preceding the output which is the threshold value that has been determined through the sigmoid activation function. The research adopted the deep learning machine language and internet base IP with python socket command lines to address the problem of detecting unauthorized access in the government restricted areas. The unsupervised neural network algorithm used is of configuration 5-7-7-4, which was coded in python functional programming language and trained with the back propagation algorithm with 300 epoch runs to ensure that errors are maintained at about 5% confidence level through the sigmoid activation function. The research concluded that IOT technology if properly annexed is faster and better than conventional security method of narrower view, coverage and limitation to capture intruders invading government protected areas.
