Machine Learning-Assisted Detection of Action Potentials in Extracellular Multi-Unit Recordings

Bârzan, Harald; Ichim, Ana-Maria; Mureșan, Raul C.

doi:10.1109/aqtr49680.2020.9130026

Cited by 4 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, when the noise level reached 0.5, the accuracy became 85.6%. As can be seen from table (2), the spike1 (sp1) and spike2 (sp2) were less affected when the noise levels became higher. On the other hand, the recall for the SP1=100% and SP2=84.6 % and SP3 decreased to reach 69.7%.…”

Section: A Template Matching Methodsmentioning

confidence: 87%

Improving the Accuracy of Neurons Spike Sorting by Using Supervised Machine Learning

Ahmed Hussein,

Khorsheed Mohammed

2024

ACAD J NAWROZ UNIV

View full text Add to dashboard Cite

The brain is important for both the functioning and reasoning ability of the body. It plays a fundamental role in the coordination of body functioning as well as reasoning and thinking. To understand how the brain is working, we need to know how neurons communicate with each other by firing (Action potential) which is known as spike. To record these activities neurologists used the multi-electrode which record thousands of spikes at the same time. Therefore, neurologists used the Spike Sorting Algorithm (SSA) to know which spike belongs to which neuron. The accuracy of the spike sorting is the most important point. Accordingly, machine learning is used to improve the accuracy of the spike sorting. In this paper, the Principal Component Analysis (PCA) is implemented to extract features and for clustering step, the Supervised Machine Learning is applied by using the Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) to compare the accuracy of the supervised clustering with the Template Matching method. A comparison between the results of Applied Machine Learning is achieved at different levels of noise to check the accuracy of each algorithm. The results showed that when the noise level was low, KNN accuracy reached 100% while SVM reached 95% and template 100 %. However, when the noise level increased to 0.5, the accuracy of KNN became 94 % and template 85.6 % and SVM 90 %.

show abstract

Section: A Template Matching Methodsmentioning

confidence: 87%

Improving the Accuracy of Neurons Spike Sorting by Using Supervised Machine Learning

Ahmed Hussein,

Khorsheed Mohammed

2024

ACAD J NAWROZ UNIV

View full text Add to dashboard Cite

show abstract

“…The multi-unit activity (MUA) was obtained by band-pass filtering the extracellular recorded data using a bidirectional Butterworth IIR filter, order 3 with cut-off frequencies between 300 Hz and 7 kHz. Subsequently, an amplitude threshold was calculated based on the standard deviation (SD) of the filtered signal and set at a factor of the SD [typically between 3 and 5 ( Bârzan et al, 2020 )]. All threshold crossings were identified as spikes and subsequently used as input for the feature extraction algorithm.…”

Section: Methodsmentioning

confidence: 99%

Improved space breakdown method – A robust clustering technique for spike sorting

Ardelean

Ichim²,

Dînşoreanu³

et al. 2023

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

Space Breakdown Method (SBM) is a clustering algorithm that was developed specifically for low-dimensional neuronal spike sorting. Cluster overlap and imbalance are common characteristics of neuronal data that produce difficulties for clustering methods. SBM is able to identify overlapping clusters through its design of cluster centre identification and the expansion of these centres. SBM’s approach is to divide the distribution of values of each feature into chunks of equal size. In each of these chunks, the number of points is counted and based on this number the centres of clusters are found and expanded. SBM has been shown to be a contender for other well-known clustering algorithms especially for the particular case of two dimensions while being too computationally expensive for high-dimensional data. Here, we present two main improvements to the original algorithm in order to increase its ability to deal with high-dimensional data while preserving its performance: the initial array structure was substituted with a graph structure and the number of partitions has been made feature-dependent, denominating this improved version as the Improved Space Breakdown Method (ISBM). In addition, we propose a clustering validation metric that does not punish overclustering and such obtains more suitable evaluations of clustering for spike sorting. Extracellular data recorded from the brain is unlabelled, therefore we have chosen simulated neural data, to which we have the ground truth, to evaluate more accurately the performance. Evaluations conducted on synthetic data indicate that the proposed improvements reduce the space and time complexity of the original algorithm, while simultaneously leading to an increased performance on neural data when compared with other state-of-the-art algorithms.Code available athttps://github.com/ArdeleanRichard/Space-Breakdown-Method.

show abstract

“…In order to evaluate the generality of the proposed method, the detection is evaluated by measuring the accuracy (ACC), sensitivity (TPR) and the false-alarm rate (FAR), given by Equations ( 1)- (3).…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Brain-machine interfaces (BMIs) or Brain Silicon Interfaces (BSIs) enable the communication between the brain and the outside environment by conveying signals acquired from the brain to control actuators such as computers or robotic arms, with potential to restore motor function in individuals with disabilities [1,2]. Advances in microelectronics made it possible to use high-density microelectrode arrays (MEAs) which provide measurements of high accuracy and, consequently, the possibility to simultaneously record large neuronal populations at high spatiotemporal resolution with a good signal-to-noise ratio (SNR) [3]. The newer implantable neural interfaces can record up to 1000 s channels, however such a large number of channels poses major challenges for the communication link, for both wired and wireless systems [4,5].…”

Section: Introductionmentioning

confidence: 99%

A Low Power 1024-Channels Spike Detector Using Latch-Based RAM for Real-Time Brain Silicon Interfaces

Saggese

Strollo

2021

Electronics

View full text Add to dashboard Cite

High-density microelectrode arrays allow the neuroscientist to study a wider neurons population, however, this causes an increase of communication bandwidth. Given the limited resources available for an implantable silicon interface, an on-fly data reduction is mandatory to stay within the power/area constraints. This can be accomplished by implementing a spike detector aiming at sending only the useful information about spikes. We show that the novel non-linear energy operator called ASO in combination with a simple but robust noise estimate, achieves a good trade-off between performance and consumption. The features of the investigated technique make it a good candidate for implantable BMIs. Our proposal is tested both on synthetic and real datasets providing a good sensibility at low SNR. We also provide a 1024-channels VLSI implementation using a Random-Access Memory composed by latches to reduce as much as possible the power consumptions. The final architecture occupies an area of 2.3 mm2, dissipating 3.6 µW per channels. The comparison with the state of art shows that our proposal finds a place among other methods presented in literature, certifying its suitability for BMIs.

show abstract

Machine Learning-Assisted Detection of Action Potentials in Extracellular Multi-Unit Recordings

Cited by 4 publications

References 13 publications

Improving the Accuracy of Neurons Spike Sorting by Using Supervised Machine Learning

Improving the Accuracy of Neurons Spike Sorting by Using Supervised Machine Learning

Improved space breakdown method – A robust clustering technique for spike sorting

A Low Power 1024-Channels Spike Detector Using Latch-Based RAM for Real-Time Brain Silicon Interfaces

Contact Info

Product

Resources

About