Comparison Study of Partial Least Squares Regression Analysis and Principal Component Analysis in Fast-Scan Cyclic Voltammetry

Kim, Jae‐Kyung; Oh, Yoonbae; Park, Cheonho; Kang, Yu Min; Shin, Hojin; Kim, In Young; Jang, Dong Pyo

doi:10.20964/2019.07.03

Cited by 11 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3b, meaning that lower magnitude responses were still considered by the model due to inclusion of the background, but not as heavily as in standardization. Thus, normalization was used as the preprocessing method for the in vivo data to retain current amplitudes associated with a small training set size and for comparison to previous studies [63,65].…”

Section: In Vivo Model Construction and Deploymentmentioning

confidence: 99%

“…To compare waveforms and analyses, R 2 Y and Q 2 Y scores were generated for different model/waveform/background-subtracted combinations using the in vivo post-calibration training set data (Table 1). In addition to two-component models, R 2 Y and Q 2 Y values were computed for three-and five-component models (Table 2) due to literature precedent [65]. Greater numbers of components were expected and found to produce erroneous results (negative concentrations, noisy oscillations), likely due to model overfitting.…”

Section: Waveform-model Combination Comparisonsmentioning

confidence: 99%

“…The PLSR approach is a supervised machine learning technique (i.e., it models input and output); PCA and PCR are considered unsupervised (i.e., only input data is modeled). The use of PLSR was shown to improve predictive accuracy over PCR when analyzing FSCV data for mixtures of neurochemicals [65]. Other uses included prediction and correction of FSCV background drift and pH changes [53,55].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous serotonin and dopamine monitoring across timescales by rapid pulse voltammetry with partial least squares regression

et al. 2021

View full text Add to dashboard Cite

Many voltammetry methods have been developed to monitor brain extracellular dopamine levels. Fewer approaches have been successful in detecting serotonin in vivo. No voltammetric techniques are currently available to monitor both neurotransmitters simultaneously across timescales, even though they play integrated roles in modulating behavior. We provide proof-of-concept for rapid pulse voltammetry coupled with partial least squares regression (RPV-PLSR), an approach adapted from multi-electrode systems (i.e., electronic tongues) used to identify multiple components in complex environments. We exploited small differences in analyte redox profiles to select pulse steps for RPV waveforms. Using an intentionally designed pulse strategy combined with custom instrumentation and analysis software, we monitored basal and stimulated levels of dopamine and serotonin. In addition to faradaic currents, capacitive currents were important factors in analyte identification arguing against background subtraction. Compared to fast-scan cyclic voltammetry-principal components regression (FSCV-PCR), RPV-PLSR better differentiated and quantified basal and stimulated dopamine and serotonin associated with striatal recording electrode position, optical stimulation frequency, and serotonin reuptake inhibition. The RPV-PLSR approach can be generalized to other electrochemically active neurotransmitters and provides a feedback pipeline for future optimization of multi-analyte, fit-for-purpose waveforms and machine learning approaches to data analysis. Graphical abstract

show abstract

Section: In Vivo Model Construction and Deploymentmentioning

confidence: 99%

Section: Waveform-model Combination Comparisonsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous serotonin and dopamine monitoring across timescales by rapid pulse voltammetry with partial least squares regression

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The time resolution is 10 s, which is slower than FSCV but is well-matched to the timescale of changes in tonic concentrations of dopamine relevant to the pathologies of interest ( Schultz, 2007 ). Since M-CSWV utilizes square waveforms, M-CSWV is able to harvest higher dimensional data for analysis that leads to higher sensitivity and selectivity than other tonic level measurement techniques ( Kim et al, 2019 ; Kim et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Cocaine-Induced Changes in Tonic Dopamine Concentrations Measured Using Multiple-Cyclic Square Wave Voltammetry in vivo

et al. 2021

View full text Add to dashboard Cite

For over 40 years, in vivo microdialysis techniques have been at the forefront in measuring the effects of illicit substances on brain tonic extracellular levels of dopamine that underlie many aspects of drug addiction. However, the size of microdialysis probes and sampling rate may limit this technique’s ability to provide an accurate assessment of drug effects in microneural environments. A novel electrochemical method known as multiple-cyclic square wave voltammetry (M-CSWV), was recently developed to measure second-to-second changes in tonic dopamine levels at microelectrodes, providing spatiotemporal resolution superior to microdialysis. Here, we utilized M-CSWV and fast-scan cyclic voltammetry (FSCV) to measure changes in tonic or phasic dopamine release in the nucleus accumbens core (NAcc) after acute cocaine administration. Carbon-fiber microelectrodes (CFM) and stimulating electrodes were implanted into the NAcc and medial forebrain bundle (MFB) of urethane anesthetized (1.5 g/kg i.p.) Sprague-Dawley rats, respectively. Using FSCV, depths of each electrode were optimized by determining maximal MFB electrical stimulation-evoked phasic dopamine release. Changes in phasic responses were measured after a single dose of intravenous saline or cocaine hydrochloride (3 mg/kg; n = 4). In a separate group, changes in tonic dopamine levels were measured using M-CSWV after intravenous saline and after cocaine hydrochloride (3 mg/kg; n = 5). Both the phasic and tonic dopamine responses in the NAcc were augmented by the injection of cocaine compared to saline control. The phasic and tonic levels changed by approximately x2.4 and x1.9, respectively. These increases were largely consistent with previous studies using FSCV and microdialysis. However, the minimal disruption/disturbance of neuronal tissue by the CFM may explain why the baseline tonic dopamine values (134 ± 32 nM) measured by M-CSWV were found to be 10-fold higher when compared to conventional microdialysis. In this study, we demonstrated phasic dopamine dynamics in the NAcc with acute cocaine administration. M-CSWV was able to record rapid changes in tonic levels of dopamine, which cannot be achieved with other current voltammetric techniques. Taken together, M-CSWV has the potential to provide an unprecedented level of physiologic insight into dopamine signaling, both in vitro and in vivo, which will significantly enhance our understanding of neurochemical mechanisms underlying psychiatric conditions.

show abstract

“…Apart from that, principal components regression (PCR) and partial least squares regression (PLSR) have been the main techniques for FSCV signal analysis [ 17 ]. For instance, Kim et al provided a comparison of the performance between PCR and PLSR and concluded that PLSR should be preferred over PCR in FSCV data analysis [ 18 ]. Puthongkham et al applied an image recognition method of the structural similarity index to distinguish adenosine [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Resource-constrained FPGA/DNN co-design

Zhang

Kouzani

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Deep neural networks (DNNs) have demonstrated super performance in most learning tasks. However, a DNN typically contains a large number of parameters and operations, requiring a high-end processing platform for high-speed execution. To address this challenge, hardware-and-software co-design strategies, which involve joint DNN optimization and hardware implementation, can be applied. These strategies reduce the parameters and operations of the DNN, and fit it into a low-resource processing platform. In this paper, a DNN model is used for the analysis of the data captured using an electrochemical method to determine the concentration of a neurotransmitter and the recoding electrode. Next, a DNN miniaturization algorithm is introduced, involving combined pruning and compression, to reduce the DNN resource utilization. Here, the DNN is transformed to have sparse parameters by pruning a percentage of its weights. The Lempel-Ziv-Welch algorithm is then applied to compress the sparse DNN. Next, a DNN overlay is developed, combining the decompression of the DNN parameters and DNN inference, to allow the execution of the DNN on a FPGA on the PYNQ-Z2 board. This approach helps avoid the need for inclusion of a complex quantization algorithm. It compresses the DNN by a factor of 6.18, leading to about 50% reduction in the resource utilization on the FPGA. Keywords Lempel-Ziv-Welch compression Á Deep neural network Á Hardware-and-software co-design Á Electrochemical sensing Á Field-programmable gate array Neural Computing and Applications

show abstract

Comparison Study of Partial Least Squares Regression Analysis and Principal Component Analysis in Fast-Scan Cyclic Voltammetry

Cited by 11 publications

References 23 publications

Simultaneous serotonin and dopamine monitoring across timescales by rapid pulse voltammetry with partial least squares regression

Simultaneous serotonin and dopamine monitoring across timescales by rapid pulse voltammetry with partial least squares regression

Cocaine-Induced Changes in Tonic Dopamine Concentrations Measured Using Multiple-Cyclic Square Wave Voltammetry in vivo

Resource-constrained FPGA/DNN co-design

Contact Info

Product

Resources

About