Tracking recurrence of correlation structure in neuronal recordings

Detecting patterns in high-dimensional multivariate datasets is non-trivial. Clustering and dimensionality reduction techniques often help in discerning inherent structures. In biological datasets such as microbial community composition or gene expression data, observations can be generated from a continuous process, often unknown. Estimating data points' `natural ordering' and their corresponding uncertainties can help researchers draw insights about the mechanisms involved. We introduce a Bayesian Unidimensional Scaling (BUDS) technique which extracts dominant sources of variation in high dimensional datasets and produces their visual data summaries, facilitating the exploration of a hidden continuum. The method maps multivariate data points to latent one dimensional coordinates along their underlying trajectory, and provides estimated uncertainty bounds. By statistically modeling dissimilarities and applying a DiSTATIS registration method to their posterior samples, we are able to incorporate visualizations of uncertainties in the estimated data trajectory across different regions using confidence contours for individual data points. We also illustrate the estimated overall data density across different areas by including density clouds. One-dimensional coordinates recovered by BUDS help researchers discover sample attributes or covariates that are factors driving the main variability in a dataset. We demonstrated usefulness and accuracy of BUDS on a set of published microbiome 16S and RNA-seq and roll call data. Our method effectively recovers and visualizes natural orderings present in datasets. Automatic visualization tools for data exploration and analysis are available at: https://nlhuong.shinyapps.io/visTrajectory/

Distributed feature selection (DFS) strategy for microarray gene expression data to improve the classification performance

DBFS: An effective Density Based Feature Selection scheme for small sample size and high dimensional imbalanced data sets

Introduction: Deep brain stimulation (DBS) has been an established surgical procedure in the field of functional neurosurgery for many years. The experimental electrophysiological method of local field potential (LFP) recordings in postsurgically externalized patients has made substantial contributions to the better understanding of pathophysiologies underlying movement disorders. As interest in LFP recordings for the development of improved stimulation strategies increases, this study’s aim was to provide evidence concerning safety of this research method, in a major DBS center. Methods: We retrospectively analyzed incidence and infection characteristics in adult patients who underwent two-staged DBS surgery with temporary externalization of leads in our center between January 2008 and November 2019. We focused on whether patients had participated in LFP recordings, and evaluated incidence of infections at 3 months and 1 year after the surgery based on medical records. Infection rates were compared to major DBS studies and reports focusing on the risk of infection due to externalization of DBS leads. Results were visualized using descriptive statistics. Results: Between January 2008 and November 2019, DBS surgery was performed in 528 patients (389/139 patients in the LFP/non-LFP group), mainly for movement disorders such as Parkinson’s disease (308), dystonia (93), and essential tremor (86). Of the patients, 72.9% participated in LFP recordings. The incidence of infections in the acute postsurgical phase (3 months) was 2.46% and did not differ significantly between the LFP group (1.8%) and the non-LFP group (4.32%). The overall incidence after 1 year amounted to 3.6% (19 patients) with no difference between LFP/non-LFP groups. Incidence rates reported in the literature show a large variety (2.6–10%), and the incidence reported here is within the lower range of reported incidences. Discussion/Conclusion: This study demonstrates that DBS is a surgical procedure with a low risk of infection in a large patient cohort. Importantly, it shows that LFP recordings do not have a significant effect on the incidence of infections in patients with externalization. With a representative cohort of more than 380 patients participating in LFP-recordings, this underlines LFP as a safe method in research and supports further use of this method, for example, for the development of adaptive stimulation protocols.

Occam's razor in dimension reduction: Using reduced row Echelon form for finding linear independent features in high dimensional microarray datasets

Network intrusion detection system are significant features that contribute to the enterprises and organization network success. In the past decade, Intrusion Detection system (IDS) using several methods have been proposed and implemented to safeguard the networks within an organization to be reliable, secure, and readily available. Although, some of these methods are built utilizing machine learning concepts. IDS utilizing machine learning techniques are accurate, effective and efficient in spotting attacks. However, the machine learning model performance reduces with high dimensional intrusion dataset. Therefore, it is sacrosanct to implement an efficient feature selection technique that can generate a great impact on the classification stage. Also, the feature selection phase is the most serious phase in IDS based on machine learning. This phase is expensive both in time and efforts. Furthermore, most of the proposed machine learning intrusion detection system suffered from low detection accuracy and high false positive rate when the models are experimented on high dimensional dataset. The aim of this paper is to propose a binary firefly algorithm (BFFA) based feature selection for IDS. We first performed normalization in the first stage of the model. Subsequently, the BFFA algorithm was used for feature selection stage. We adopted random forest algorithm for the classification phase. The experiment was performed on high dimensional University of New South Wales-NB 2015 (UNSW-NB15) dataset with seventy five percent of the data used for training the model and twenty percent for testing. The findings showed an accuracy of 99.72%, detection rate of 99.84%, precision of 99.27%, recall of 99.84% and F-score of 99.56%. The results were gauge with the state-of-the-art results and our results were found outstanding.

Advanced target identification in STN-DBS with beta power of combined local field potentials and spiking activity

GCaMP6f is among the most widely used genetically encoded calcium indicators for monitoring neuronal activity. Applications are at both the cellular and population levels. Here, we explore two important and under-explored issues. First, we have tested if GCaMP6f is sensitive enough for the detection of population activity with sparse firing, similar to the sensitivity of the local field potential (LFP). Second, we have tested if GCaMP6f is fast enough for the detection of fast network oscillations critical for the encoding and consolidation of memory. We have focused this study on the activity of the hippocampal network including sharp waves (SWs), carbachol-induced theta oscillations, and interictal-like spikes. We compare simultaneous LFP and optical GCaMP6f fluorescent recordings in Thy1-GCaMP6f mouse hippocampal slices. We observe that SWs produce a clear population GCaMP6f signal above noise with an average magnitude of 0.3% ΔF/F. This population signal is highly correlated with the LFP, albeit with a delay of 40.3 ms (SD 10.8 ms). The population GCaMP6f signal follows the LFP evoked by 20 Hz stimulation with high fidelity, while electrically evoked oscillations up to 40 Hz were detectable with reduced amplitude. GCaMP6f and LFP signals showed a large amplitude discrepancy. The amplitude of GCaMP6f fluorescence increased by a factor of 28.9 (SD 13.5) between spontaneous SWs and carbachol-induced theta bursts, while the LFP amplitude increased by a factor of 2.4 (SD 1.0). Our results suggest that GCaMP6f is a useful tool for applications commonly considered beyond the scope of genetically encoded calcium indicators. In particular, population GCaMP6f signals are sensitive enough for detecting synchronous network events with sparse firing and sub-threshold activity, as well as asynchronous events with only a nominal LFP. In addition, population GCaMP6f signals are fast enough for monitoring theta and beta oscillations (<25 Hz). Faster calcium indicators (e.g., GCaMP7) will further improve the frequency response for the detection of gamma band oscillations. The advantage of population optical over LFP recordings are that they are non-contact and free from stimulation artifacts. These features may be particularly useful for high-throughput recordings and applications sensitive to stimulus artifact, such as monitoring responses during continuous stimulation.

Metaheuristic algorithms have been hybridized with the standard K-means to address the latter’s challenges in finding a solution to automatic clustering problems. However, the distance calculations required in the standard K-means phase of the hybrid clustering algorithms increase as the number of clusters increases, and the associated computational cost rises in proportion to the dataset dimensionality. The use of the standard K-means algorithm in the metaheuristic-based K-means hybrid algorithm for the automatic clustering of high-dimensional real-world datasets poses a great challenge to the clustering performance of the resultant hybrid algorithms in terms of computational cost. Reducing the computation time required in the K-means phase of the hybrid algorithm for the automatic clustering of high-dimensional datasets will inevitably reduce the algorithm’s complexity. In this paper, a preprocessing phase is introduced into the K-means phase of an improved firefly-based K-means hybrid algorithm using the concept of the central limit theorem to partition the high-dimensional dataset into subgroups of randomly formed subsets on which the K-means algorithm is applied to obtain representative cluster centers for the final clustering procedure. The enhanced firefly algorithm (FA) is hybridized with the CLT-based K-means algorithm to automatically determine the optimum number of cluster centroids and generate corresponding optimum initial cluster centroids for the K-means algorithm to achieve optimal global convergence. Twenty high-dimensional datasets from the UCI machine learning repository are used to investigate the performance of the proposed algorithm. The empirical results indicate that the hybrid FA-K-means clustering method demonstrates statistically significant superiority in the employed performance measures and reducing computation time cost for clustering high-dimensional dataset problems, compared to other advanced hybrid search variants.

An imbalanced dataset influences the supervised learning model. Most of the existing real world datasets are imbalanced and often high dimensional. The existing classification methods tend to perform extremely well on the majority class and give least importance to the minority class. Most of the solutions provided for the imbalanced datasets do not fit in for the high dimensional imbalanced datasets. This paper compares the performance of an existing balancing method (cluster concentric circle based under sampling-C3BUS) over low dimensional imbalanced dataset versus high dimensional imbalanced datasets. This work shows that C3BUS works quiet well for low dimensional imbalanced dataset when compared to high dimensional imbalanced dataset and proves that class imbalance and high dimensionality are one of the two main issues in supervised learning process.

High-dimensional datasets with low sample sizes (HDLSS) are pivotal in the fields of biology and bioinformatics. One of core objective of HDLSS is to select most informative features and discarding redundant or irrelevant features. This is particularly crucial in bioinformatics, where accurate feature (gene) selection can lead to breakthroughs in drug development and provide insights into disease diagnostics. Despite its importance, identifying optimal features is still a significant challenge in HDLSS. To address this challenge, we propose an effective feature selection method that combines gradual permutation filtering with a heuristic tribrid search strategy, specifically tailored for HDLSS contexts. The proposed method considers inter-feature interactions and leverages feature rankings during the search process. In addition, a new performance metric for the HDLSS that evaluates both the number and quality of selected features is suggested. Through the comparison of the benchmark dataset with existing methods, the proposed method reduced the average number of selected features from 37.8 to 5.5 and improved the performance of the prediction model, based on the selected features, from 0.855 to 0.927. The proposed method effectively selects a small number of important features and achieves high prediction performance.

The present work strives to investigate the effect of using dimensionality reduction techniques (DRTs) on breast cancer (BC) classification problem. Primarily, we focused on the following five (DRTs): Auto-Encoders (AE), T-Distributed Stochastic Neighbor Embedding (T- SNE), Recursive Feature Elimination (RFE), Isometric Feature Mapping (Isomap), and Principle Component analysis (PCA). These methods are combined with two famous classifiers that are Support Vector Machine (SVM) and Multilayer perceptron (MLP). They are used for BC classification. Breast Cancer Wisconsin Diagnostic (WDBC) data set was used to validate the experiments of this work. The former was provided by the University of California, Irvine (UCI) machine learning repository. The results demonstrated that combining MLP with the chosen (DRTs) methods increased the classification accuracy for almost all built models by at least 0.7%. In addition, they revealed a decrease in the classification accuracy using SVM as a classifier for almost all built models.KeywordsMachine learningDeep learningDimensionality reductionNeural networksBreast cancer predictionMedical dataset

Regarding the magnificent ability of the fuzzy logic in explanation and analyzing the real phenomena, using fuzzy data is growing rapidly. But the tools for doing data mining in a fuzzy data set; especially in high dimension, are not sufficient. Considering the remarkable ability of the LoOP (Local Outlier Probabilities) method in outlier detecting in high dimensional crisp data set, like supplying for each data object, determining outlier probability as scar which is easily explainable competitor on various synthetic and real world data sets, the aim of this article is to present an extended version of this method for using in high dimensional fuzzy database. In order to provide a completely fuzzy strategy, first we propose a new approach to assigning distance between fuzzy high dimension data based on Hausdorff and Vertex distance. After proving that this distance measuring is a metric, since LoOP is a distance based method, we redefined the LoOP algorithm step by step based on the new meter. Then we allocate an outlier score in the range of [0,1] to each data based on LoOP idea, to identify the outliers. The presented numerical tests show the efficiency of the new method, for random cases of knowing and unknowing the outlier and a real case. The results shows also the stability and robustness of the presented method more that its accuracy.

We investigated whether entorhinal cortex (EC) layer IV neurons are hyperexcitable in the post-selfsustaining limbic status epilepticus (post-SSLSE) animal model of temporal lobe epilepsy. We studied naive rats (n = 44), epileptic rats that had experienced SSLSE resulting in spontaneous seizures (n = 45), and electrode controls (n = 7). There were no differences between electrode control and naive groups, which were pooled into a single control group. Intracellular and extracellular recordings were made from deep layers of EC, targeting layer IV, which was activated by stimulation of the superficial layers of EC or the angular bundle. There were no differences between epileptic and control neurons in basic cellular characteristics, and all neurons were quiescent under resting conditions. In control tissue, 77% of evoked intracellular responses consisted of a short-duration [8.6 +/- 1.3 (SE) ms] excitatory postsynaptic potential and a single action potential followed by gamma-aminobutyric acid-A (GABAA) and GABAB inhibitory post synaptic potentials (IPSPs). Ten percent of controls did not contain IPSPs. In chronically epileptic tissue, evoked intracellular responses demonstrated prolonged depolarizing potentials (256 +/- 39 ms), multiple action potentials (13 +/- 4), and no IPSPs. Ten percent of epileptic responses were followed by rhythmic "clonic" depolarizations. Epileptic responses exhibited an all-or-none response to progressive increases in stimulus intensity and required less stimulation to elicit action potentials. In both epileptic and control animals, intracellular responses correlated precisely in morphology and duration with extracellular field potentials. Severing the hippocampus from the EC did not alter the responses. Duration of intracellular epileptic responses was reduced 22% by the N-methyl--aspartate (NMDA) antagonist (-)-2-amino-5-phosphonovaleric acid (APV), but they did not return to normal and IPSPs were not restored. Epileptic and control responses were abolished by the non-NMDA antagonist 6, 7-dinitroquinoxaline-2-3-dione (DNQX). A monosynaptic IPSP protocol was used to test connectivity of inhibitory interneurons to primary cells by direct activation of interneurons with a stimulating electrode placed near the recording electrode in the presence of APV and DNQX. Using this protocol, IPSPs similar to control (P > 0.05) were seen in epileptic cells. The findings demonstrate that deep layer EC cells are hyperexcitable or "epileptiform" in this model. Hyperexcitability is not due to interactions with the hippocampus. It is due partially to augmented NMDA-mediated excitation. The lack of IPSPs in epileptic neurons may suggest inhibition is impaired, but we found evidence that inhibitory interneurons are connected to their target cells and are capable of inducing IPSPs.

High-dimensional data sets are often available in genome-enabled predictions. Such data sets include nonlinear relationships with complex dependence structures. For such situations, vine copula-based (quantile) regression is an important tool. However, the current vine copula-based regression approaches do not scale up to high and ultra-high dimensions. To perform high-dimensional sparse vine copula-based regression, we propose 2 methods. First, we show their superiority regarding computational complexity over the existing methods. Second, we define relevant, irrelevant, and redundant explanatory variables for quantile regression. Then, we show our method's power in selecting relevant variables and prediction accuracy in high-dimensional sparse data sets via simulation studies. Next, we apply the proposed methods to the high-dimensional real data, aiming at the genomic prediction of maize traits. Some data processing and feature extraction steps for the real data are further discussed. Finally, we show the advantage of our methods over linear models and quantile regression forests in simulation studies and real data applications.