Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Global Data-Driven Model for The Hippocampus and Nucleus Accumbens of Rat From The Local Field Potential Recordings (LFP)

Maedeh Sadeghi, Mahdi Aliyari Shoorehdeli, Shole jamali, Abbas Haghparast

TL;DR

The paper tackles predicting Local Field Potential signals from the hippocampus and nucleus accumbens in freely moving rats across reward and non-reward conditions. It systematically compares five data-driven time-series models (LSTM, ESN, DeepESN, RBF-NN, and LoLiMoT) and finds LoLiMoT to be the strongest performer, enabling a global, pre-trained model. It demonstrates a multi-input multi-output (MIMO) LoLiMoT trained on data from one brain region can predict signals in other regions, indicating cross-region generalization. The results suggest that while rewards influence initial neural states, the underlying dynamical features remain stable, offering a robust framework for cross-subject neural signal prediction with practical implications for neuroscience research and potential clinical translation.

Abstract

In brain neural networks, Local Field Potential (LFP) signals represent the dynamic flow of information. Analyzing LFP clinical data plays a critical role in improving our understanding of brain mechanisms. One way to enhance our understanding of these mechanisms is to identify a global model to predict brain signals in different situations. This paper identifies a global data-driven based on LFP recordings of the Nucleus Accumbens and Hippocampus regions in freely moving rats. The LFP is recorded from each rat in two different situations: before and after the process of getting a reward which can be either a drug (Morphine) or natural food (like popcorn or biscuit). A comparison of five machine learning methods including Long Short Term Memory (LSTM), Echo State Network (ESN), Deep Echo State Network (DeepESN), Radial Basis Function (RBF), and Local Linear Model Tree (LLM) is conducted to develop this model. LoLiMoT was chosen with the best performance among all methods. This model can predict the future states of these regions with one pre-trained model. Identifying this model showed that Morphine and natural rewards do not change the dynamic features of neurons in these regions.

A Global Data-Driven Model for The Hippocampus and Nucleus Accumbens of Rat From The Local Field Potential Recordings (LFP)

TL;DR

The paper tackles predicting Local Field Potential signals from the hippocampus and nucleus accumbens in freely moving rats across reward and non-reward conditions. It systematically compares five data-driven time-series models (LSTM, ESN, DeepESN, RBF-NN, and LoLiMoT) and finds LoLiMoT to be the strongest performer, enabling a global, pre-trained model. It demonstrates a multi-input multi-output (MIMO) LoLiMoT trained on data from one brain region can predict signals in other regions, indicating cross-region generalization. The results suggest that while rewards influence initial neural states, the underlying dynamical features remain stable, offering a robust framework for cross-subject neural signal prediction with practical implications for neuroscience research and potential clinical translation.

Abstract

In brain neural networks, Local Field Potential (LFP) signals represent the dynamic flow of information. Analyzing LFP clinical data plays a critical role in improving our understanding of brain mechanisms. One way to enhance our understanding of these mechanisms is to identify a global model to predict brain signals in different situations. This paper identifies a global data-driven based on LFP recordings of the Nucleus Accumbens and Hippocampus regions in freely moving rats. The LFP is recorded from each rat in two different situations: before and after the process of getting a reward which can be either a drug (Morphine) or natural food (like popcorn or biscuit). A comparison of five machine learning methods including Long Short Term Memory (LSTM), Echo State Network (ESN), Deep Echo State Network (DeepESN), Radial Basis Function (RBF), and Local Linear Model Tree (LLM) is conducted to develop this model. LoLiMoT was chosen with the best performance among all methods. This model can predict the future states of these regions with one pre-trained model. Identifying this model showed that Morphine and natural rewards do not change the dynamic features of neurons in these regions.
Paper Structure (16 sections, 11 equations, 7 figures, 2 tables)

This paper contains 16 sections, 11 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Related Work
  4. Contribution
  5. Outline
  6. Material and data recording
  7. Methodology
  8. Long Short Term Memory (LSTM)
  9. Echo State Network (ESN)
  10. Deep Echo State Network
  11. Radial Basis Function Neural Network (RBF-NN)
  12. Local Linear Model Tree (LoLiMoT)
  13. Experiment and comparison
  14. Data Analysis
  15. Result
  16. ...and 1 more sections

Figures (7)

  • Figure 1: The structure of Long Short Term Memory
  • Figure 2: The structure of Echo State Network
  • Figure 3: The structure of Deep Echo State Network
  • Figure 4: The structure of Radial Basis Function Neural Network
  • Figure 5: The structure of Local Linear Model Tree (LoLiMoT)
  • ...and 2 more figures