Using deep neural networks to detect complex spikes of cerebellar Purkinje cells

Purkinje cell “complex spikes,” fired at perplexingly low rates, play a crucial role in cerebellum-based motor learning. Careful interpretations of these spikes require manually detecting them, since conventional online or offline spike sorting algorithms are optimized for classifying much simpler waveform morphologies. We present a novel deep learning approach for identifying complex spikes, which also measures additional relevant neurophysiological features, with an accuracy level matching that of human experts yet with very little time expenditure.

Download Full-text

Using deep neural networks to detect complex spikes of cerebellar Purkinje Cells

10.1101/600536 ◽

2019 ◽

Cited By ~ 1

Author(s):

Akshay Markanday ◽

Joachim Bellet ◽

Marie E. Bellet ◽

Ziad M. Hafed ◽

Peter Thier

Keyword(s):

Motor Control ◽

Deep Learning ◽

Action Potential ◽

Purkinje Cell ◽

Purkinje Cells ◽

Local Field ◽

Visual Inspection ◽

Complex Spike ◽

Cerebellar Purkinje Cells ◽

Complex Spikes

AbstractOne of the most powerful excitatory synapses in the entire brain is formed by cerebellar climbing fibers, originating from neurons in the inferior olive, that wrap around the proximal dendrites of cerebellar Purkinje cells. The activation of a single olivary neuron is capable of generating a large electrical event, called “complex spike”, at the level of the postsynaptic Purkinje cell, comprising of a fast initial spike of large amplitude followed by a slow polyphasic tail of small amplitude spikelets. Several ideas discussing the role of the cerebellum in motor control are centered on these complex spike events. However, these events are extremely rare, only occurring 1-2 times per second. As a result, drawing conclusions about their functional role has been very challenging, as even few errors in their detection may change the result. Since standard spike sorting approaches cannot fully handle the polyphasic shape of complex spike waveforms, the only safe way to avoid omissions and false detections has been to rely on visual inspection of long traces of Purkinje cell recordings by experts. Here we present a supervised deep learning algorithm for rapidly and reliably detecting complex spikes as an alternative to tedious visual inspection. Our algorithm, utilizing both action potential and local field potential signals, not only detects complex spike events much faster than human experts, but it also excavates key features of complex spike morphology with a performance comparable to that of such experts.Significance statementClimbing fiber driven “complex spikes”, fired at perplexingly low rates, are known to play a crucial role in cerebellum-based motor control. Careful interpretations of these spikes require researchers to manually detect them, since conventional online or offline spike sorting algorithms (optimized for analyzing the much more frequent “simple spikes”) cannot be fully trusted. Here, we present a deep learning approach for identifying complex spikes, which is trained on local field and action potential recordings from cerebellar Purkinje cells. Our algorithm successfully identifies complex spikes, along with additional relevant neurophysiological features, with an accuracy level matching that of human experts, yet with very little time expenditure.

Download Full-text

Assessment of bilateral knee pain from MR imaging using deep neural networks

10.1101/463497 ◽

2018 ◽

Author(s):

Gary H. Chang ◽

David T. Felson ◽

Shangran Qiu ◽

Terence D. Capellini ◽

Vijaya B. Kolachalama

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Neural Networks ◽

Deep Learning ◽

Knee Pain ◽

Deep Neural Networks ◽

Learning Approach ◽

Mr Images ◽

Bilateral Knee ◽

Machine Learning Approach

ABSTRACTBackground and objectiveIt remains difficult to characterize pain in knee joints with osteoarthritis solely by radiographic findings. We sought to understand how advanced machine learning methods such as deep neural networks can be used to analyze raw MRI scans and predict bilateral knee pain, independent of other risk factors.MethodsWe developed a deep learning framework to associate information from MRI slices taken from the left and right knees of subjects from the Osteoarthritis Initiative with bilateral knee pain. Model training was performed by first extracting features from two-dimensional (2D) sagittal intermediate-weighted turbo spin echo slices. The extracted features from all the 2D slices were subsequently combined to directly associate using a fused deep neural network with the output of interest as a binary classification problem.ResultsThe deep learning model resulted in predicting bilateral knee pain on test data with 70.1% mean accuracy, 51.3% mean sensitivity, and 81.6% mean specificity. Systematic analysis of the predictions on the test data revealed that the model performance was consistent across subjects of different Kellgren-Lawrence grades.ConclusionThe study demonstrates a proof of principle that a machine learning approach can be applied to associate MR images with bilateral knee pain.SIGNIFICANCE AND INNOVATIONKnee pain is typically considered as an early indicator of osteoarthritis (OA) risk. Emerging evidence suggests that MRI changes are linked to pre-clinical OA, thus underscoring the need for building image-based models to predict knee pain. We leveraged a state-of-the-art machine learning approach to associate raw MR images with bilateral knee pain, independent of other risk factors.

Download Full-text

Combining content and social features in a deep learning approach to Vietnamese email prioritization

REV Journal on Electronics and Communications ◽

10.21553/rev-jec.271 ◽

2021 ◽

Author(s):

Ha Thanh Nguyen ◽

Quan Dinh Dang ◽

Anh Quang Tran

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

New Method ◽

Learning Approach ◽

Field Of Study ◽

Learning Techniques ◽

Email Overload ◽

Social Features

The email overload problem has been discussed in numerous email-related studies. One of the possible solutions to this problem is email prioritization, which is the act of automatically predicting the importance levels of received emails and sorting the user’s inbox accordingly. Several learning-based methods have been proposed to address the email prioritization problem using content features as well as social features. Although these methods have laid the foundation works in this field of study, the reported performance is far from being practical. Recent works on deep neural networks have achieved good results in various tasks. In this paper, the authors propose a novel email prioritization model which incorporates several deep learning techniques and uses a combination of both content features and social features from email data. This method targets Vietnamese emails and is tested against a self-built Vietnamese email corpus. Conducted experiments explored the effects of different model configurations and compared the effectiveness of the new method to that of a previous work.

Download Full-text

Deep learning in Arabic sentiment analysis: An overview

Journal of Information Science ◽

10.1177/0165551519865488 ◽

2019 ◽

pp. 016555151986548

Author(s):

Amal Alharbi ◽

Mounira Taileb ◽

Manal Kalkatawi

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Sentiment Analysis ◽

Deep Neural Networks ◽

The Internet ◽

Learning Approach ◽

Comprehensive Overview ◽

Exponential Increase ◽

Arabic Sentiment Analysis

Sentiment analysis became a very motivating area in both academic and industrial fields due to the exponential increase of the online published reviews and recommendations. To solve the problem of analysing and classifying those reviews and recommendations, several techniques have been proposed. Lately, deep neural networks showed promising outcomes in sentiment analysis. The growing number of Arab users on the Internet along with the increasing amount of published Arabic reviews and comments encouraged researchers to apply deep learning to analyse them. This article is a comprehensive overview of research works that utilised the deep learning approach for Arabic sentiment analysis.

Download Full-text

Direct translation of climbing fiber burst-mediated sensory coding into post-synaptic Purkinje cell dendritic calcium

eLife ◽

10.7554/elife.61593 ◽

2020 ◽

Vol 9 ◽

Cited By ~ 1

Author(s):

Seung-Eon Roh ◽

Seung Ha Kim ◽

Changhyeon Ryu ◽

Chang-Eop Kim ◽

Yong Gyu Kim ◽

...

Keyword(s):

Purkinje Cell ◽

Purkinje Cells ◽

Sensory Information ◽

Sensory Coding ◽

Information Coding ◽

Direct Translation ◽

Spike Number ◽

Cerebellar Purkinje Cells ◽

Complex Spikes

Climbing fibers (CFs) generate complex spikes (CS) and Ca2+ transients in cerebellar Purkinje cells (PCs), serving as instructive signals. The so-called 'all-or-none' character of CSs has been questioned since the CF burst was described. Although recent studies have indicated a sensory-driven enhancement of PC Ca2+ signals, how CF responds to sensory events and contributes to PC dendritic Ca2+ and CS remains unexplored. Here, single or simultaneous Ca2+ imaging of CFs and PCs in awake mice revealed the presynaptic CF Ca2+ amplitude encoded the sensory input’s strength and directly influenced post-synaptic PC dendritic Ca2+ amplitude. The sensory-driven variability in CF Ca2+ amplitude depended on the number of spikes in the CF burst. Finally, the spike number of the CF burst determined the PC Ca2+ influx and CS properties. These results reveal the direct translation of sensory information-coding CF inputs into PC Ca2+, suggesting the sophisticated role of CFs as error signals.

Download Full-text

A Deep Learning Approach for Malware and Software Piracy Threat Detection

Engineering, Technology & Applied Science Research ◽

10.48084/etasr.4412 ◽

2021 ◽

Vol 11 (6) ◽

pp. 7757-7762

Author(s):

K. Aldriwish

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Software Piracy ◽

Classification Performance ◽

Learning Approach ◽

Threat Detection ◽

Deep Convolutional Neural Networks ◽

Combined Model ◽

Security Of Iot

Internet of Things (IoT) -based systems need to be up to date on cybersecurity threats. The security of IoT networks is challenged by software piracy and malware attacks, and much important information can be stolen and used for cybercrimes. This paper attempts to improve IoT cybersecurity by proposing a combined model based on deep learning to detect malware and software piracy across the IoT network. The malware’s model is based on Deep Convolutional Neural Networks (DCNNs). Apart from this, TensorFlow Deep Neural Networks (TFDNNs) are introduced to detect software piracy threats according to source code plagiarism. The investigation is conducted on the Google Code Jam (GCJ) dataset. The conducted experiments prove that the classification performance achieves high accuracy of about 98%.

Download Full-text

Evaluation of anti-EGFR-iRGD recombinant protein with GOLD nanoparticles: synergistic effect on antitumor efficiency using optimized deep neural networks

RSC Advances ◽

10.1039/c9ra01975h ◽

2019 ◽

Vol 9 (34) ◽

pp. 19261-19270 ◽

Cited By ~ 3

Author(s):

Aman Chandra Kaushik ◽

Yan-Jing Wang ◽

Xiangeng Wang ◽

Ajay Kumar ◽

Satya P. Singh ◽

...

Keyword(s):

Neural Networks ◽

Gold Nanoparticles ◽

Deep Learning ◽

Recombinant Protein ◽

Synergistic Effect ◽

Deep Neural Networks ◽

Learning Approach ◽

Biochemical Pathway ◽

Biological Circuits

NP screening through a deep learning approach against Anti-EGFR and validation through docking with AuNP. Biochemical pathway and simulation of AuNP with Anti-EGFR and further implementation in biological circuits.

Download Full-text

A spike-sorting method based on hierarchical clustering to discriminate extracellularly recorded simple spikes and complex spikes from cerebellar Purkinje cells

10.1101/2021.09.30.462526 ◽

2021 ◽

Author(s):

Takayuki Michikawa ◽

Keisuke Isobe ◽

Shigeyoshi Itohara

Keyword(s):

Purkinje Cell ◽

Purkinje Cells ◽

Quantitative Evaluation ◽

Cerebellar Cortex ◽

Single Unit ◽

Spike Sorting ◽

Sorting Method ◽

Single Unit Recordings ◽

Cerebellar Purkinje Cells ◽

Complex Spikes

Background: In the cerebellar cortex, Purkinje cells are the only output neurons and exhibit two types of discharge. Most Purkinje cell discharges are simple spikes, which are commonly appearing action potentials exhibiting a rich variety of firing patterns with a rate of up to 400 Hz. More infrequent discharges are complex spikes, which consist of a short burst of impulses accompanied by a massive increase in dendritic Ca2+ with a firing rate of around 1 Hz. The discrimination of these spikes in extracellular single-unit recordings is not always straightforward, as their waveforms vary depending on recording conditions and intrinsic fluctuations. New Method: To discriminate complex spikes from simple spikes in the extracellular single-unit data, we developed a semiautomatic spike-sorting method based on divisive hierarchical clustering. Results: Quantitative evaluation using parallel in vivo two-photon Ca2+ imaging of Purkinje cell dendrites indicated that 96.6% of the complex spikes were detected using our spike-sorting method from extracellular single-unit recordings obtained from anesthetized mice. Comparison with Existing Method(s): No reports have conducted a quantitative evaluation of spike-sorting algorithms used for the classification of extracellular spikes recorded from cerebellar Purkinje cells. Conclusions: Our method could be expected to contribute to research in information processing in the cerebellar cortex and the development of a fully automatic spike-sorting algorithm by providing ground-truth data useful for deep learning.

Download Full-text

Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal

Sensors ◽

10.3390/s20061579 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1579

Author(s):

Dongqi Wang ◽

Qinghua Meng ◽

Dongming Chen ◽

Hupo Zhang ◽

Lisheng Xu

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Channel Model ◽

Expert Knowledge ◽

Automatic Detection ◽

Data Representation ◽

Learning Technology ◽

Arrhythmia Detection ◽

Automatic Feature Extraction

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition.

Download Full-text

Enabling deeper learning on big data for materials informatics applications

Scientific Reports ◽

10.1038/s41598-021-83193-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Dipendra Jha ◽

Vishu Gupta ◽

Logan Ward ◽

Zijiang Yang ◽

Christopher Wolverton ◽

...

Keyword(s):

Neural Networks ◽

Big Data ◽

Deep Learning ◽

Deep Neural Networks ◽

Materials Science ◽

Prediction Models ◽

Model Performance ◽

Materials Informatics ◽

Learning Framework ◽

Significant Attention

AbstractThe application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

Download Full-text