Neuromorphic circuit for temporal odor encoding in turbulent environments

• URL: http://arxiv.org/abs/2412.20117v1
• Date: Sat, 28 Dec 2024 11:12:18 GMT
• Title: Neuromorphic circuit for temporal odor encoding in turbulent environments
• Authors: Shavika Rastogi, Nik Dennler, Michael Schmuker, André van Schaik,
• Abstract summary: We investigate Metal-Oxide (MOx) gas sensor recordings of constant airflow-embedded artificial odor plumes. We design a neuromorphic electronic nose front-end circuit for extracting and encoding this feature into analog spikes for gas detection and concentration estimation. The resulting neuromorphic nose could enable data-efficient, real-time robotic plume navigation systems.
• Score: 0.48748194765816943
• License:
• Abstract: Natural odor environments present turbulent and dynamic conditions, causing chemical signals to fluctuate in space, time, and intensity. While many species have evolved highly adaptive behavioral responses to such variability, the emerging field of neuromorphic olfaction continues to grapple with the challenge of efficiently sampling and identifying odors in real-time. In this work, we investigate Metal-Oxide (MOx) gas sensor recordings of constant airflow-embedded artificial odor plumes. We discover a data feature that is representative of the presented odor stimulus at a certain concentration - irrespective of temporal variations caused by the plume dynamics. Further, we design a neuromorphic electronic nose front-end circuit for extracting and encoding this feature into analog spikes for gas detection and concentration estimation. The design is inspired by the spiking output of parallel neural pathways in the mammalian olfactory bulb. We test the circuit for gas recognition and concentration estimation in artificial environments, where either single gas pulses or pre-recorded odor plumes were deployed in a constant flow of air. For both environments, our results indicate that the gas concentration is encoded in -- and inversely proportional to the time difference of analog spikes emerging out of two parallel pathways, similar to the spiking output of a mammalian olfactory bulb. The resulting neuromorphic nose could enable data-efficient, real-time robotic plume navigation systems, advancing the capabilities of odor source localization in applications such as environmental monitoring and search-and-rescue.

Related papers

• The Neuromorphic Analog Electronic Nose [0.48748194765816943]
  We introduce a simple analog front-end for one MOx sensor that encodes the gas concentration in the time difference between pulses of two separate pathways. We show that for a gas pulse injected in a constant airflow, the time difference between pulses decreases with increasing gas concentration, similar to the spike time difference between the two principal output neurons in the olfactory bulb.
  arXiv  Detail & Related papers  (2024-10-22T04:20:51Z)
• Q-learning with temporal memory to navigate turbulence [47.28605705112213]
  We consider the problem of olfactory searches in a turbulent environment. We develop a reinforcement learning algorithm using a small set of interpretable olfactory states. We show that two salient features of odor traces, discretized in few olfactory states, are sufficient to learn navigation in a realistic odor plume.
  arXiv  Detail & Related papers  (2024-04-26T15:51:20Z)
• Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks [59.38765771221084]
  We present a physiologically inspired speech recognition architecture compatible and scalable with deep learning frameworks. We show end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network. Our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronising neural activity to improve recognition performance.
  arXiv  Detail & Related papers  (2024-04-22T09:40:07Z)
• Learning with Chemical versus Electrical Synapses -- Does it Make a Difference? [61.85704286298537]
  Bio-inspired neural networks have the potential to advance our understanding of neural computation and improve the state-of-the-art of AI systems. We conduct experiments with autonomous lane-keeping through a photorealistic autonomous driving simulator to evaluate their performance under diverse conditions.
  arXiv  Detail & Related papers  (2023-11-21T13:07:20Z)
• Spike-time encoding of gas concentrations using neuromorphic analog sensory front-end [0.06752396542927405]
  We propose a simple analog circuit design inspired by the spiking output of the mammalian olfactory bulb and by event-based vision sensors. Our circuit encodes the gas concentration in the time difference between the pulses of two separate pathways.
  arXiv  Detail & Related papers  (2023-10-11T13:23:37Z)
• Limitations in odour recognition and generalisation in a neuromorphic olfactory circuit [0.07589017023705934]
  We present an odour-learning algorithm that runs on a neuromorphic architecture and is inspired by circuits described in the mammalian olfactory bulb. They assess the algorithm's performance in "rapid online learning and identification" of gaseous odorants and odorless gases.
  arXiv  Detail & Related papers  (2023-09-20T18:00:05Z)
• DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals [62.997667081978825]
  We develop a novel statistical point process model-called driven temporal point processes (DriPP) We derive a fast and principled expectation-maximization (EM) algorithm to estimate the parameters of this model. Results on standard MEG datasets demonstrate that our methodology reveals event-related neural responses.
  arXiv  Detail & Related papers  (2021-12-08T13:07:21Z)
• Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals [77.34726150561087]
  We propose a methodology based on deep metric learning to address the need for automated post-hoc cleaning and robust separation filters. We validate this method with an artificially corrupted label set based on source-separated high-density surface electromyography recordings. This approach enables a neural network to learn to accurately decode neurophysiological time series using any imperfect method of labelling the signal.
  arXiv  Detail & Related papers  (2021-10-13T21:51:56Z)
• Emergent behavior and neural dynamics in artificial agents tracking turbulent plumes [1.8065361710947974]
  We use deep reinforcement learning to train recurrent neural network (RNN) agents to locate the source of simulated turbulent plumes. Our analyses suggest an intriguing experimentally testable hypothesis for tracking plumes in changing wind direction.
  arXiv  Detail & Related papers  (2021-09-25T20:57:02Z)
• Neuromorphic adaptive spiking CPG towards bio-inspired locomotion of legged robots [58.720142291102135]
  Spiking Central Pattern Generator generates different locomotion patterns driven by an external stimulus. The locomotion of the end robotic platform (any-legged robot) can be adapted to the terrain by using any sensor as input.
  arXiv  Detail & Related papers  (2021-01-24T12:44:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.