Research Of Classification And Prediction Model In The Realtime Representation Neurons

The research of the neurons firing activity is an important aspect in neuroscience, psychology and artificial intelligence. The core of this subject is that if we could capture the intrinsic regularity of the neurons firing activity in special stimuli, or the relation between brain structure and its function. In recent twenty years, Cognitive function of brain imaging techniques, the Electroencephalograph, Functional magnetic resonance imaging etc. have gain a huge development, but this techniques have more or less accurate problems in spatial or temporal. If we could get massive data of independent neurons firing data, and analysis this data directly, definitely is a better way to research the brain structure and its function. On the other hand, understanding the network-level organizing principles that allow the brain to form real-time neural representations of episodic experiences is a central issue in neuroscience. Anatomically, the hippocampus, and especially its CA1 subregion, is known to be a crucial site for the formation of episodic memories of events and places. In fact, individual hippocampal neurons have been shown to respond to many external inputs. Yet, the response variability at the level of individual neurons poses a theoretical obstacle to the understanding how the brain achieves its robust real-time neural coding of the stimulus representation. It has been long thought that mnemonic encoding of information may involve the coordinated activity of large numbers of individual neurons. However, virtually little is known about the actual real-time network-level encoding patterns and their underlying organizing principles and mechanisms.To study these issues, we have developed a high-density recording technique for mice. In parallel, we also designed a set of simple, and yet robust , behavioral paradigms by using startling episodes. We reasoned that such episodic events are likely to involve large numbers of neurons, thereby greatly increasing the chance of finding them simultaneously and, consequently, facilitating the analysis of network-level real-time encoding patterns in the brain.In our paper , we main introduce the process the technique that we capture the neuron firing data , and the main algorithm of many kinds of discriminant analysis and nearest shrunken centroids, and the combination of these two algorithm. We main use these three algorithm to process our data. Experiments shows that the validity of the proposed methods , prove that the intrinsic pattern of the neuron firing and the feasibility of the classification and prediction to the different stimuli through the analysis of the ensemble firing patterns.