This paper will analyze and implement a time series dynamic neural network to predict daily closing stock prices. Neural networks possess unsurpassed abilities in identifying underlying patterns in chaotic, non-linear, and seemingly random data, thus providing a mechanism to predict stock price movements much more precisely than many current techniques. Contemporary methods for stock analysis, including fundamental, technical, and regression techniques, are conversed and paralleled with the performance of neural networks. Also, the Efficient Market Hypothesis (EMH) is presented and contrasted with Chaos theory using neural networks. This paper will refute the EMH and support Chaos theory. Finally, recommendations for using neural networks in stock price prediction will be presented.
This report describes the design and proposal of a wireless link capable of broadcasting at 1 Gbps. For this application, isotropic antennas, 256 QAM modulation, and BER level less than 1e-5, without using error correction coding, were implemented. A frequency of 5GHz was employed to achieve such high data rates. For unlicensed operations in this frequency range, the FCC allocates a 5.15 - 5.35 GHz frequency range with maximum acceptable power levels no greater than 250mW(~24dBm)[2]. Due to its inexpensiveness and simplicity, the transceiver architecture and all its subsystems used the homodyne system. The complete system architecture is described with some of their most significant performance characteristics, including modulation, fundamental and 3rd harmonics, power spectra, and constellation diagrams. To conclude, a Bill of Materials (BOM), costs, and associated specifications were included.