Abstract: A WRAN discriminates between authentic incumbent and spurious/malicious signals by collaboratively sensing the frequency environment, classifying and fusing the sensed results, and categorizing each signal as valid or invalid. Embodiments categorize signals according to reports from at least two nodes, thereby increasing detection confidence and resisting denial-of-service attacks. A “voting-rule” can be applied whereby a signal is authentic only if it is detected by a specified percentage of the nodes. Some embodiments categorized signals by comparing sensed analog signal properties, such as amplitude, bandwidth, pulse width, mean, variance, modulation, standard deviation, moments, cumulants, and rise and fall times, with properties of known incumbents and/or known incumbent types.

Abstract: A WRAN discriminates between authentic incumbent and spurious/malicious signals by collaboratively sensing the frequency environment, classifying and fusing the sensed results, and categorizing each signal as valid or invalid. Embodiments categorize signals according to reports from at least two nodes, thereby increasing detection confidence and resisting denial-of-service attacks. A “voting-rule” can be applied whereby a signal is authentic only if it is detected by a specified percentage of the nodes. Some embodiments categorized signals by comparing sensed analog signal properties, such as amplitude, bandwidth, pulse width, mean, variance, modulation, standard deviation, moments, cumulants, and rise and fall times, with properties of known incumbents and/or known incumbent types.

Abstract: An improved compact, secure localization tag useful for identifying and tracking the tag in an environment comprising discrete areas is disclosed. Further, systems and methods for area-based localization of tags using received signal strengths is also disclosed. Tracking the location of an asset can be facilitated by attaching a tag that transmits a beacon signal to the asset. The beacon signal can be received and measured by beacon receivers so as to locate the asset and the attached tag.

Abstract: A channel equalizer is formed using a self-learning neural network. During a training period, the neural network is taught the channel response function. The network is then used to equalize distortions introduced into signals by the channel. The neural network may be a Boltzmann Machine type of neural network comprising neurons arranged in an input layer, a hidden layer, and an output layer. The neurons are interconnected by bidirectional symmetric weighted synapses. Each neuron is preferably implemented by an analog integrated circuit. Direct communication between the input and output layers helps in faster channel acquisition. The scheme can very easily be extended to multilevel and multisymbol modulation schemes such as QAM and PSK.