Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Deep Learning Approach To Speech Recognition: A Signal Extractor & Producer For Artificial General Intelligence, Ahmad Zuhair S. Hasanain
Deep Learning Approach To Speech Recognition: A Signal Extractor & Producer For Artificial General Intelligence, Ahmad Zuhair S. Hasanain
Theses and Dissertations
The efficient use of a communication bandwidth starts with the data source. The features of the speech signals can be extracted and reconstructed to lower the Internet traffic of the acoustic artificial agents and to increase the quality of the automatic speech recognition systems. The Speech Quefrency Transform (SQT) is hereby introduced in the work to enrich the communication space between the artificial agents and mankind. We describe the motivation, methodology, and deep learning approach in detail as we apply the SQT technology to several applications: sharp pitch track extraction, real-time speech communications, and emotion recognition. The results were excellent. …
A Voice And Facial Recognition System To Protect Students From Being Forgotten Inside School Buses In The Kingdom Of Saudi Arabia, Ibrahim Alferaih
A Voice And Facial Recognition System To Protect Students From Being Forgotten Inside School Buses In The Kingdom Of Saudi Arabia, Ibrahim Alferaih
Theses and Dissertations
In this research, we discuss the situation of students in the three to eight year old age group. Every day in the Kingdom of Saudi Arabia during school days, more than 1,000,000 students are transported throughout the country by more than 15,000 school buses. Everything is dependent on the human element. During school transportation around the world, many children are forgotten inside the school bus and with many of them eventually going missing or even dying. The bus driver is usually busy and tired due to the focus on the road, which may make him lose focus on those on …
Millimeterwave And Mimo Antenna Beamforming For Next-Generationwireless Communications, Ahmed Nadhim Mohammed
Millimeterwave And Mimo Antenna Beamforming For Next-Generationwireless Communications, Ahmed Nadhim Mohammed
Theses and Dissertations
Millimeter wave (mmWave) hybrid precoding systems are likely to have large antenna arrays to overcome the high channel path loss. In such circumstances, low cost hardware and power consumption are the main challenges. Furthermore, the hardware is tasked with computation of high dimensional optimal matrices of hybrid precoding design using Orthogonal Matching Pursuit (OMP). This dissertation addresses two algorithms to enhance the efficiency of the OMP reconstruction algorithm in mmWave precoding design. The spectral efficiency of the mmWave system using the proposed algorithms is compared with previous works and the optimal case (a fully digital precoder). The results show that …
Infrared Electric Field Enhancement Via A Hyperbolic-Metalens-Coupled Nanoantenna, Mohamed Jebril Kyamo
Infrared Electric Field Enhancement Via A Hyperbolic-Metalens-Coupled Nanoantenna, Mohamed Jebril Kyamo
Theses and Dissertations
The development of near- and mid-infrared applications requires high enhancement of the electric field intensity (EFI) and a high absorption cross-section of the electric field. The high enhancement of EFI can be obtained by concentrating optical energy to areas much smaller than the diffraction limit or by using surface plasmon polaritons (SPPs). Noble metals such as gold (Au) or silver (Ag) are not feasible for infrared (IR) applications because of high losses, lack of tunability, low resolution, and low-intensity enhancement. Our methods to solve these problems are based on appropriate metamaterial selection and on coupling systems with optimization of their …