Spiking information of individual neurons is essential for functional and behavioral analysis in neuroscience research. Calcium imaging techniques are generally employed to obtain activities of neuronal populations. However, these techniques result in slowly-varying fluorescence signals with low temporal resolution. Estimating the temporal positions of the neuronal action potentials from these signals is a challenging problem. In the literature, several generative model-based and data-driven algorithms have been studied with varied levels of success. This article proposes a neural network-based signal-to-signal conversion approach, where it takes as input raw-fluorescence signal and learns to estimate the spike information in an end-to-end fashion. Theoretically, the proposed approach formulates the spike estimation as a single channel source separation problem with unknown mixing conditions. The source corresponding to the action potentials at a lower resolution is estimated at the output. Experimental studies on the spikefinder challenge dataset show that the proposed signal-to-signal conversion approach significantly outperforms state-of-the-art-methods in terms of Pearson’s correlation coefficient, Spearman’s rank correlation coefficient and yields comparable performance for the area under the receiver operating characteristics measure. We also show that the resulting system: (a) has low complexity with respect to existing supervised approaches and is reproducible; (b) is layer-wise interpretable, and (c) has the capability to generalize across different calcium indicators.
In human perception and understanding, a number of different and complementary cues are adopted according to different modalities. Various emotional states in communication between humans reflect this variety of cues across modalities. Recent developments in multi-modal emotion recognition utilize deeplearning techniques to achieve remarkable performances, with models based on different features suitable for text, audio and vision. This work focuses on cross-modal fusion techniques over deep learning models for emotion detection from spoken audio and corresponding transcripts. We investigate the use of long short-term memory (LSTM) recurrent neural network (RNN) with pre-trained word embedding for text-based emotion recognition and convolutional neural network (CNN) with utterance-level descriptors for emotion recognition from speech. Various fusion strategies are adopted on these models to yield an overall score for each of the emotional categories. Intra-modality dynamics for each emotion is captured in the neural network designed for the specific modality. Fusion techniques are employed to obtain the inter-modality dynamics. Speaker and session-independent experiments on IEMOCAP multi-modal emotion detection dataset show the effectiveness of the proposed approaches. This method yields state-of-the-art results for utterance-level emotion recognition based on speech and text.
Spiking information of individual neurons is essential for functional and behavioural analysis in neuroscience. During electrophysiological experiments in animals, calcium imaging techniques are employed to obtain activities of individual neurons and neuronal populations and they result in slowly-varying fluorescence signals with poor temporal resolution. Estimating the temporal positions of action potentials from these signals is a challenging problem. In the literature, a number of generative model based and data-driven algorithms have been studied with limited success. In this article, we propose a neural network based signal-to-signal (S2S) conversion approach, where the neural network takes as input raw-fluorescence signal and learns to predict spike information signal in an end-to-end manner. Theoretically, the proposed approach formulates the problem of spike estimation from the fluorescence signal as a single channel source separation problem with unknown mixing conditions. Through experimental studies on spikefinder bench-marking dataset, we show that the proposed S2S conversion approach outperforms state-of-the-art-methods. We show that the resulting system: (a) has low complexity with respect to existing approaches and is reproducible; (b) is layer-wise interpretable; and (c) has the capability to generalise across different calcium indicators. Author summaryInformation processing by a population of neurons is studied using two-photon calcium imaging techniques. A neuronal spike results in an increased intra-cellular calcium concentration. Fluorescent calcium indicators change their brightness upon a change in the calcium concentration and this change is captured in the imaging technique. The task of estimating the actual spike positions from the brightness variation is referred to as spike estimation. Several signal processing and machine learning-based algorithms have been proposed to solve this problem. However, the task is still far from being solved. Here we present a novel neural network based data-driven algorithm for this task. Our method takes the fluorescence recording as the input and synthesises the spike information signal which is well-correlated with the actual spike positions. Our method outperforms state-of-the-art methods in spike estimation on standard evaluation framework. We analyse different components of the model and discuss its benefits. Introduction 1 Analysis of brain circuitry requires understanding the information encoded in the 2 neuronal spikes at micro and macro levels. Latest scanning methods track the activity 3 of a population of neurons by making use of fluorescence emitting capability of calcium 4 indicator proteins/dye [1-4]. The calcium fluorescence recording of each neuron, 5 however, is only an indirect indicator of the actual spiking process. Presence of 6 fluorescence level fluctuations, slow dynamics of calcium fluorescence signal, and 7 unknown noise-levels makes it hard to identify the exact underlying spike information 8 [5-7]. Hence, technologies capable ...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.