Fast and Accurate Detection of Action Potentials From Somatic Calcium Fluctuations

2008 ◽  
Vol 100 (3) ◽  
pp. 1668-1676 ◽  
Author(s):  
Takuya Sasaki ◽  
Naoya Takahashi ◽  
Norio Matsuki ◽  
Yuji Ikegaya
Keyword(s):  
Calcium Imaging ◽  
Action Potentials ◽  
Large Scale ◽  
Simple Algorithm ◽  
Principal Component ◽  
Support Vector ◽  
Human Errors ◽  
Brain Functions ◽  
Promising Strategy ◽  
Human Operators

Large-scale recording from a population of neurons is a promising strategy for approaching the study of complex brain functions. Taking advantage of the fact that action potentials reliably evoke transient calcium fluctuations in the cell body, functional multineuron calcium imaging (fMCI) monitors the suprathreshold activity of hundreds of neurons. However, a limitation of fMCI is its semi-manual procedure of spike extraction from somatic calcium fluctuations, which is not only time consuming but is also associated with human errors. Here we describe a novel automatic method that combines principal-component analysis and support vector machine. This simple algorithm determines the timings of the spikes in calcium fluorescence traces more rapidly and reliably than human operators.

scholarly journals In vivo calcium imaging of CA3 pyramidal neuron populations in adult mouse hippocampus

2021 ◽  
Author(s):  
Gwendolin Schoenfeld ◽  
Stefano Carta ◽  
Peter Rupprecht ◽  
Aslı Ayaz ◽  
Fritjof Helmchen
Keyword(s):  
Calcium Imaging ◽  
Action Potentials ◽  
Pyramidal Neurons ◽  
Population Level ◽  
Calcium Transients ◽  
Population Activity ◽  
Brain Functions ◽  
State Dependent ◽  
Multiple Imaging ◽  
Ca3 Pyramidal Neurons

Neuronal population activity in the hippocampal CA3 subfield is implicated in cognitive brain functions such as memory processing and spatial navigation. However, because of its deep location in the brain, the CA3 area has been difficult to target with modern calcium imaging approaches. Here, we achieved chronic two-photon calcium imaging of CA3 pyramidal neurons with the red fluorescent calcium indicator R-CaMP1.07 in anesthetized and awake mice. We characterize CA3 neuronal activity at both the single-cell and population level and assess its stability across multiple imaging days. During both anesthesia and wakefulness, nearly all CA3 pyramidal neurons displayed calcium transients. Most of the calcium transients were consistent with a high incidence of bursts of action potentials, based on calibration measurements using simultaneous juxtacellular recordings and calcium imaging. In awake mice, we found state-dependent differences with striking large and prolonged calcium transients during locomotion. We estimate that trains of >30 action potentials over 3 s underlie these salient events. Their abundance in particular subsets of neurons was relatively stable across days. At the population level, we found that coactivity within the CA3 network was above chance level and that co-active neuron pairs maintained their correlated activity over days. Our results corroborate the notion of state-dependent spatiotemporal activity patterns in the recurrent network of CA3 and demonstrate that at least some features of population activity, namely coactivity of cell pairs and likelihood to engage in prolonged high activity, are maintained over days.

scholarly journals Identification of dominant sources of sea level pressure for precipitation forecasting over Wales

2012 ◽  
Vol 15 (3) ◽  
pp. 1002-1021 ◽  
Author(s):  
Azadeh Ahmadi ◽  
Dawei Han
Keyword(s):  
General Circulation ◽  
Large Scale ◽  
Circulation Model ◽  
Principal Component ◽  
Support Vector ◽  
Monthly Precipitation ◽  
Climate Variables ◽  
Forward Selection ◽  
Precipitation Forecasting ◽  
Variable Combination

Downscaling methods are utilized to assess the effects of large scale atmospheric circulation on local hydrological variables such as precipitation and runoff. In this paper, a methodology of statistical downscaling using a support vector machine (SVM) approach is presented to simulate and predict the precipitation using general circulation model (GCM) data. Due to the complexity and issues related to finding a relationship between the large scale climatic parameters and local precipitation, the climate variables (predictors) affecting monthly precipitation variations over Wales are identified using a combination of the methods including the principal component analysis (PCA), fuzzy clustering, backward selection, forward selection, and Gamma test (GT). The effectiveness of those tools is illustrated through their implementations in the case study. It has been found that although the GT itself fails to identify the best input variable combination, it provides useful and narrowed-down options for further exploration. The best input variable combination is achieved by the GT and forward selection method. This approach can be a useful way for assessing the impacts of climate variables on precipitation forecasting.

scholarly journals Large-scale calcium imaging with a head-mount axial scanning 3D fluorescence microscope

2021 ◽  
Author(s):  
Yuichiro Hayashi ◽  
Ko Kobayakawa ◽  
Reiko Kobayakawa
Keyword(s):  
Calcium Imaging ◽  
Large Scale ◽  
Low Cost ◽  
3D Structure ◽  
Three Dimensional ◽  
Brain Structures ◽  
Volumetric Imaging ◽  
Brain Functions ◽  
Local Circuits ◽  
Axial Scanning

AbstractMiniaturized fluorescence microscopes are becoming more important for deciphering the neural codes underlying various brain functions. Using gradient index (GRIN) lenses, these devices enable the recording of neuronal activity in deep brain structures. However, to minimize any damage to brain tissue and local circuits, the diameter of the GRIN lens should be 0.5–1 mm, which results in a small field of view. Considering the three-dimensional (3D) structure of neural circuits in the brain, volumetric imaging capability would increase the number of neurons imaged through the lenses. To observe 3D calcium dynamics, we developed a miniaturized microscope with an electrically tunable lens. Using this microscope, we performed 3D calcium imaging in behaving mice and were able to image approximately twice the number of cells as could be recorded using a 2D imaging technique. This simple low-cost 3D microscope will improve the efficiency of calcium imaging in behaving animals.

scholarly journals Rapid Classification of Wheat Grain Varieties Using Hyperspectral Imaging and Chemometrics

2019 ◽  
Vol 9 (19) ◽  
pp. 4119 ◽  
Author(s):  
Yidan Bao ◽  
Chunxiao Mi ◽  
Na Wu ◽  
Fei Liu ◽  
Yong He
Keyword(s):  
Hyperspectral Imaging ◽  
Large Scale ◽  
Scatter Correction ◽  
Principal Component ◽  
Support Vector ◽  
Wheat Grain ◽  
Successive Projections Algorithm ◽  
Accurate Identification ◽  
Wheat Varieties

The classification of wheat grain varieties is of great value because its high purity is the yield and quality guarantee. In this study, hyperspectral imaging combined with the chemometric methods was applied to explore and implement the varieties classification of wheat seeds. The hyperspectral images of all the samples covering 874–1734 nm bands were collected. Exploratory analysis was first carried out while using principal component analysis (PCA) and linear discrimination analysis (LDA). Spectral preprocessing methods including standard normal variate (SNV), multiplicative scatter correction (MSC), and wavelet transform (WT) were introduced, and their effects on discriminant models were studied to eliminate the interference of instrumental and environmental factors. PCA loading, successive projections algorithm (SPA), and random frog (RF) were applied to extract feature wavelengths for redundancy elimination owing to the possibility of existing redundant spectral information. Classification models were developed based on full wavelengths and feature wavelengths using LDA, support vector machine (SVM), and extreme learning machine (ELM). This optimal model was finally utilized to generate visualization map to observe the classification performance intuitively. When comparing with other models, ELM based on full wavelengths achieved the best accuracy up to 91.3%. The overall results suggested that hyperspectral imaging was a potential tool for the rapid and accurate identification of wheat varieties, which could be conducted in large-scale seeds classification and quality detection in modern seed industry.

scholarly journals DDI-PULearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions

2019 ◽  
Vol 20 (S19) ◽  
Author(s):  
Yi Zheng ◽  
Hui Peng ◽  
Xiaocai Zhang ◽  
Zhixun Zhao ◽  
Xiaoying Gao ◽  
...  
Keyword(s):  
Drug Interactions ◽  
Large Scale ◽  
Dimensional Space ◽  
Principal Component ◽  
Computational Prediction ◽  
Superior Performance ◽  
Support Vector ◽  
Learning Method ◽  
K Nearest Neighbors ◽  
Lower Dimensional Space

Abstract Background Drug-drug interactions (DDIs) are a major concern in patients’ medication. It’s unfeasible to identify all potential DDIs using experimental methods which are time-consuming and expensive. Computational methods provide an effective strategy, however, facing challenges due to the lack of experimentally verified negative samples. Results To address this problem, we propose a novel positive-unlabeled learning method named DDI-PULearn for large-scale drug-drug-interaction predictions. DDI-PULearn first generates seeds of reliable negatives via OCSVM (one-class support vector machine) under a high-recall constraint and via the cosine-similarity based KNN (k-nearest neighbors) as well. Then trained with all the labeled positives (i.e., the validated DDIs) and the generated seed negatives, DDI-PULearn employs an iterative SVM to identify a set of entire reliable negatives from the unlabeled samples (i.e., the unobserved DDIs). Following that, DDI-PULearn represents all the labeled positives and the identified negatives as vectors of abundant drug properties by a similarity-based method. Finally, DDI-PULearn transforms these vectors into a lower-dimensional space via PCA (principal component analysis) and utilizes the compressed vectors as input for binary classifications. The performance of DDI-PULearn is evaluated on simulative prediction for 149,878 possible interactions between 548 drugs, comparing with two baseline methods and five state-of-the-art methods. Related experiment results show that the proposed method for the representation of DDIs characterizes them accurately. DDI-PULearn achieves superior performance owing to the identified reliable negatives, outperforming all other methods significantly. In addition, the predicted novel DDIs suggest that DDI-PULearn is capable to identify novel DDIs. Conclusions The results demonstrate that positive-unlabeled learning paves a new way to tackle the problem caused by the lack of experimentally verified negatives in the computational prediction of DDIs.

Customer Churn Analysis Model in Manufacturing Industry

2009 ◽  
Vol 69-70 ◽  
pp. 675-679
Author(s):  
D.S. Liu ◽  
Chun Hua Ju
Keyword(s):  
Large Scale ◽  
Manufacturing Industry ◽  
Principal Component ◽  
Support Vector ◽  
Redundant Information ◽  
Analysis Model ◽  
Customer Churn ◽  
Model Based ◽  
Churn Analysis ◽  
Better Than

To address the problem of customer churn in CRM in manufacturing industry, this paper proposes a prediction model based on Support Vector Machine (SVM). Considering the large-scale and imbalanced churn data, principal component analysis (PCA) is adopted to reduce dimensions and eliminate redundant information, which makes the sample space for SVM more compact and reasonable. An improved SVM is used to predict customer churn. Firstly, PCA is adopted to process 17 dimensional feature vectors of customer churn data, and then the application in manufacturing industry verifies that this model based on both PCA and SVM performs better than the model based on SVM only and other traditional models.

A FAST SVM TRAINING ALGORITHM

2003 ◽  
Vol 17 (03) ◽  
pp. 367-384 ◽  
Author(s):  
JIAN-XIONG DONG ◽  
CHING Y. SUEN ◽  
ADAM KRZYŻAK
Keyword(s):  
Data Mining ◽  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Large Scale ◽  
Principal Component ◽  
Learning Problems ◽  
Support Vector ◽  
Training Algorithm ◽  
Test Set ◽  
Handwritten Digit

A fast support vector machine (SVM) training algorithm is proposed under SVM's decomposition framework by effectively integrating kernel caching, digest and shrinking policies and stopping conditions. Kernel caching plays a key role in reducing the number of kernel evaluations by maximal reusage of cached kernel elements. Extensive experiments have been conducted on a large handwritten digit database MNIST to show that the proposed algorithm is much faster than Keerthi et al.'s improved SMO, about nine times. Combined with principal component analysis, the total training for ten one-against-the-rest classifiers on MNIST took less than an hour. Moreover, the proposed fast algorithm speeds up SVM training without sacrificing the generalization performance. The 0.6% error rate on MNIST test set has been achieved. The promising scalability of the proposed scheme paves a new way to solve more large-scale learning problems in other domains such as data mining.

Dehydroepiandrosterone (DHEA) and its Sulphate (DHEAS) in Alzheimer’s Disease

2020 ◽  
Vol 17 (2) ◽  
pp. 141-157 ◽  
Author(s):  
Dubravka S. Strac ◽  
Marcela Konjevod ◽  
Matea N. Perkovic ◽  
Lucija Tudor ◽  
Gordana N. Erjavec ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Large Scale ◽  
Therapeutic Potential ◽  
Relevant Literature ◽  
Comprehensive Overview ◽  
Brain Functions ◽  
Specific Effects ◽  
And Behavior

Background: Neurosteroids Dehydroepiandrosterone (DHEA) and Dehydroepiandrosterone Sulphate (DHEAS) are involved in many important brain functions, including neuronal plasticity and survival, cognition and behavior, demonstrating preventive and therapeutic potential in different neuropsychiatric and neurodegenerative disorders, including Alzheimer’s disease. Objective: The aim of the article was to provide a comprehensive overview of the literature on the involvement of DHEA and DHEAS in Alzheimer’s disease. Method: PubMed and MEDLINE databases were searched for relevant literature. The articles were selected considering their titles and abstracts. In the selected full texts, lists of references were searched manually for additional articles. Results: We performed a systematic review of the studies investigating the role of DHEA and DHEAS in various in vitro and animal models, as well as in patients with Alzheimer’s disease, and provided a comprehensive discussion on their potential preventive and therapeutic applications. Conclusion: Despite mixed results, the findings of various preclinical studies are generally supportive of the involvement of DHEA and DHEAS in the pathophysiology of Alzheimer’s disease, showing some promise for potential benefits of these neurosteroids in the prevention and treatment. However, so far small clinical trials brought little evidence to support their therapy in AD. Therefore, large-scale human studies are needed to elucidate the specific effects of DHEA and DHEAS and their mechanisms of action, prior to their applications in clinical practice.

QSAR Study of PARP Inhibitors by GA-MLR, GA-SVM and GA-ANN Approaches

2020 ◽  
Vol 16 (8) ◽  
pp. 1088-1105
Author(s):  
Nafiseh Vahedi ◽  
Majid Mohammadhosseini ◽  
Mehdi Nekoei
Keyword(s):  
Present Report ◽  
Principal Component ◽  
Parp Inhibitors ◽  
Support Vector ◽  
Ann Model ◽  
Statistical Parameters ◽  
Qsar Study ◽  
Data Set ◽  
Test Set ◽  
Non Linear

Background: The poly(ADP-ribose) polymerases (PARP) is a nuclear enzyme superfamily present in eukaryotes. Methods: In the present report, some efficient linear and non-linear methods including multiple linear regression (MLR), support vector machine (SVM) and artificial neural networks (ANN) were successfully used to develop and establish quantitative structure-activity relationship (QSAR) models capable of predicting pEC50 values of tetrahydropyridopyridazinone derivatives as effective PARP inhibitors. Principal component analysis (PCA) was used to a rational division of the whole data set and selection of the training and test sets. A genetic algorithm (GA) variable selection method was employed to select the optimal subset of descriptors that have the most significant contributions to the overall inhibitory activity from the large pool of calculated descriptors. Results: The accuracy and predictability of the proposed models were further confirmed using crossvalidation, validation through an external test set and Y-randomization (chance correlations) approaches. Moreover, an exhaustive statistical comparison was performed on the outputs of the proposed models. The results revealed that non-linear modeling approaches, including SVM and ANN could provide much more prediction capabilities. Conclusion: Among the constructed models and in terms of root mean square error of predictions (RMSEP), cross-validation coefficients (Q2 LOO and Q2 LGO), as well as R2 and F-statistical value for the training set, the predictive power of the GA-SVM approach was better. However, compared with MLR and SVM, the statistical parameters for the test set were more proper using the GA-ANN model.

Application of Machine Learning in Animal Disease Analysis and Prediction

2020 ◽  
Vol 15 ◽  
Author(s):  
Shuwen Zhang ◽  
Qiang Su ◽  
Qin Chen
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Support Vector ◽  
Animal Disease ◽  
Human Beings ◽  
Animal Diseases ◽  
Disease Analysis

Abstract: Major animal diseases pose a great threat to animal husbandry and human beings. With the deepening of globalization and the abundance of data resources, the prediction and analysis of animal diseases by using big data are becoming more and more important. The focus of machine learning is to make computers learn how to learn from data and use the learned experience to analyze and predict. Firstly, this paper introduces the animal epidemic situation and machine learning. Then it briefly introduces the application of machine learning in animal disease analysis and prediction. Machine learning is mainly divided into supervised learning and unsupervised learning. Supervised learning includes support vector machines, naive bayes, decision trees, random forests, logistic regression, artificial neural networks, deep learning, and AdaBoost. Unsupervised learning has maximum expectation algorithm, principal component analysis hierarchical clustering algorithm and maxent. Through the discussion of this paper, people have a clearer concept of machine learning and understand its application prospect in animal diseases.

Sign in / Sign up

Export Citation Format

Share Document