Single-sample Data Research Articles

Multivariable correlation feature network construction and health condition assessment for unlabeled single-sample data

The construction of effective health indicators is crucial for assessing system degradation, enabling anomaly detection and health condition assessment, which contribute to reducing costs, improving productivity, and enhancing system availability. However, there are notable challenges in the health condition assessment for unlabeled single-sample data. In this paper, a multivariable correlation feature network—the Nested Autoencoder (NAE) network, is proposed, which incorporates inter-variable correlations to constrain the construction of latent space, thereby enhancing the accuracy of health condition assessment. Moreover, the autoencoder parameters calculated with each discrete interval data are leveraged to construct latent feature graphs, enabling component anomaly detection. Furthermore, a comprehensive indicator is introduced to describe the topological changes of the graphs, facilitating the assessment of the health conditions of the system. Finally, the effectiveness of our method is validated on the N-CMAPSS dataset as well as a real satellite dataset.

Identifying the critical state of cancers by single-sample Markov flow entropy.

The progression of complex diseases sometimes undergoes a drastic critical transition, at which the biological system abruptly shifts from a relatively healthy state (before-transition stage) to a disease state (after-transition stage). Searching for such a critical transition or critical state is crucial to provide timely and effective scientific treatment to patients. However, in most conditions where only a small sample size of clinical data is available, resulting in failure when detecting the critical states of complex diseases, particularly only single-sample data. In this study, different from traditional methods that require multiple samples at each time, a model-free computational method, single-sample Markov flow entropy (sMFE), provides a solution to the identification problem of critical states/pre-disease states of complex diseases, solely based on a single-sample. Our proposed method was employed to characterize the dynamic changes of complex diseases from the perspective of network entropy. The proposed approach was verified by unmistakably identifying the critical state just before the occurrence of disease deterioration for four tumor datasets from The Cancer Genome Atlas (TCGA) database. In addition, two new prognostic biomarkers, optimistic sMFE (O-sMFE) and pessimistic sMFE (P-sMFE) biomarkers, were identified by our method and enable the prognosis evaluation of tumors. The proposed method has shown its capability to accurately detect pre-disease states of four cancers and provide two novel prognostic biomarkers, O-sMFE and P-sMFE biomarkers, to facilitate the personalized prognosis of patients. This is a remarkable achievement that could have a major impact on the diagnosis and treatment of complex diseases.

Accurate Label Refinement From Multiannotator of Remote Sensing Data

The remote sensing (RS) field has an increasing research interest in using deep learning (DL) models to recognize kinds of RS data, leading to a great demand for training data annotation. Due to the high cost of expertise, using nonexperts to label data has become an important way to improve labeling efficiency. Commonly, a single data sample is labeled by multiple annotators and the most voted label is accepted to promise accuracy. But in the RS context, the widely admitted strategy could lose effect. Usually RS data involve considerable classes on account of the complexity of surface environments, which is prone to interclass similarity difficult to distinguish. Annotators without expertise probably make mistakes on these indistinguishable classes, thus causing error voted labels. Although classification of different characteristics in RS data has been widely documented, the nonexpert annotators are unfamiliar with these expertise, and it is difficult to force them to handle specialized labeling skills. To address the issues, this article bases multiannotator label selection on the investigation of annotators’ own ability in distinguishing similar classes of images. A quality evaluation process is designed which weights the labels from capable annotators higher than those from weak ones. By a multi-round quality evaluation algorithm, correct labels could outcompete the wrong ones even disadvantaged in numbers. Experimental results demonstrate the advance of the proposed method on the RS datasets.

Optimisation-free density estimation and classification with quantum circuits

We demonstrate the implementation of a novel machine learning framework for probability density estimation and classification using quantum circuits. The framework maps a training data set or a single data sample to the quantum state of a physical system through quantum feature maps. The quantum state of the arbitrarily large training data set summarises its probability distribution in a finite-dimensional quantum wave function. By projecting the quantum state of a new data sample onto the quantum state of the training data set, one can derive statistics to classify or estimate the density of the new data sample. Remarkably, the implementation of our framework on a real quantum device does not require any optimisation of quantum circuit parameters. Nonetheless, we discuss a variational quantum circuit approach that could leverage quantum advantage for our framework.

Towards a method to anticipate dark matter signals with deep learning at the LHC

We study several simplified dark matter (DM) models and their signatures at the LHC using neural networks. We focus on the usual monojet plus missing transverse energy channel, but to train the algorithms we organize the data in 2D histograms instead of event-by-event arrays. This results in a large performance boost to distinguish between standard model (SM) only and SM plus new physics signals. We use the kinematic monojet features as input data which allow us to describe families of models with a single data sample. We found that the neural network performance does not depend on the simulated number of background events if they are presented as a function of S/\sqrt{B}S/B, for reasonably large BB, where SS and BB are the number of signal and background events per histogram, respectively. This provides flexibility to the method, since testing a particular model in that case only requires knowing the new physics monojet cross section. Furthermore, we also discuss the network performance under incorrect assumptions about the true DM nature. Finally, we propose multimodel classifiers to search and identify new signals in a more general way, for the next LHC run.

The impact of time standardising TCATA by modality data on the multisensory profile of beer

Temporal sensory profiles are increasingly assessed ‘by modality’ to investigate complex profiles and multisensory properties of foods and beverages. Panellists’ noise in temporal data caused by differences in oral and cognitive processing cannot entirely be removed by training or strict experimental setups. Therefore, time standardisation can be applied to align onsets of sensations and standardise temporal data. This paper compared raw temporal data collected in a preceding study performed by a trained expert panel (n = 10) using a TCATA by modality approach with the same data time standardised either by modality or with merged modalities. Binary data, durations and citation proportions were evaluated and subjected to Repeated Measures (RM-) Analysis of Variance (ANOVA), Canonical Variate Analysis (CVA), and Multiple Factor Analysis (MFA) to investigate the differences between sensory properties and dynamic profiles. Time standardisation with merged modalities was able to reduce some noise related to panel repeatability from the raw data while also improving panel agreement indices in the taste and mouthfeel data. Time standardisation by modality reduced some of the panel heterogeneity, but distorted patterns in the flavour data. The main reason for distorted patterns in single sample data and resulting sample discrimination was the different impact of time standardisation on samples described by quickly fading versus long lasting sensations. No substantial effects were observed on the samples’ overall profiles in their sensory space. Time standardisation by modality could not reduce panellists’ noise in the data. Only a slight noise reduction was achieved in the time standardised data with merged modalities supporting the use of the raw data for further analyses. The findings indicated several differences between raw and time standardised data and highlighted advantages and disadvantages of pre-processing TCATA by modality data obtained to describe samples inducing complex, multisensory sensations.

Identifying Critical States of Complex Diseases by Single-Sample Jensen-Shannon Divergence.

MotivationThe evolution of complex diseases can be modeled as a time-dependent nonlinear dynamic system, and its progression can be divided into three states, i.e., the normal state, the pre-disease state and the disease state. The sudden deterioration of the disease can be regarded as the state transition of the dynamic system at the critical state or pre-disease state. How to detect the critical state of an individual before the disease state based on single-sample data has attracted many researchers’ attention.MethodsIn this study, we proposed a novel approach, i.e., single-sample-based Jensen-Shannon Divergence (sJSD) method to detect the early-warning signals of complex diseases before critical transitions based on individual single-sample data. The method aims to construct score index based on sJSD, namely, inconsistency index (ICI).ResultsThis method is applied to five real datasets, including prostate cancer, bladder urothelial carcinoma, influenza virus infection, cervical squamous cell carcinoma and endocervical adenocarcinoma and pancreatic adenocarcinoma. The critical states of 5 datasets with their corresponding sJSD signal biomarkers are successfully identified to diagnose and predict each individual sample, and some “dark genes” that without differential expressions but are sensitive to ICI score were revealed. This method is a data-driven and model-free method, which can be applied to not only disease prediction on individuals but also targeted drug design of each disease. At the same time, the identification of sJSD signal biomarkers is also of great significance for studying the molecular mechanism of disease progression from a dynamic perspective.

Multimodal person detection system

Person detection is often critical for personal safety, property protection, and national security. Most person detection technologies implement unimodal classification, making predictions based on a single sensor data modality, which is most often vision. There are many ways to defeat unimodal person detectors, and many more reasons to ensure technologies responsible for detecting the presence of a person are accurate and precise. In this paper, we design and implement a multimodal person detection system which can acquire data from multiple sensors and detect persons based on a variety of unimodal classifications and multimodal fusions. We present two methods of generating system-level predictions: (1) device perspectives which makes a final decision based on multiple device-level predictions and (2) system perspectives which combines data samples from multiple devices into a single data sample and then makes a decision. Our experimental results show that system-level predictions from system perspectives are generally more accurate than system-level predictions from device perspectives. We achieve an accuracy of 100%, zero false positive rate and zero false negative rate with fusion of system perspectives motion and distance data.

Subway Obstacle Perception and Identification Method Based on Cloud Edge Collaboration

The traditional analysis method of train obstacle uses isomorphic sensors to obtain the state information and completes detection and identification analysis at the remote end of a network. A single data sample and more processing links will reduce the accuracy and speed analysis for subway encountering obstacles. To solve this problem, this paper proposes a subway obstacle perception and identification method based on cloud edge cooperation. The subway monitoring cloud platform realizes the training and construction of a detection model, and the network edge side completes the situation awareness of track state and real‐time action when the train encounters obstacles. Firstly, the railroad track position is detected by cameras, and subway running track is identified by Mask RCNN algorithm to determine the detection area of obstacles in the process of subway train running. At the edge of network, the feature‐level fusion of data collected by sensor cluster is carried out to provide reliable data support for detection work. Then, based on the DeepSort and YOLOv3 network models, the subway obstacle detection model is constructed on the subway monitoring cloud platform. Moreover, a trained model is distributed to the network edge side, so as to realize the fast and efficient perception and action of obstacles. Finally, the simulation verification is implemented based on actual collected datasets. Experimental results show that the proposed method has good detection accuracy and efficiency, which maintains 98.9% and 1.43 s for obstacle detection accuracy and recognition time in complex scenes.

Disease characterization using a partial correlation-based sample-specific network

A single-sample network (SSN) is a biological molecular network constructed from single-sample data given a reference dataset and can provide insights into the mechanisms of individual diseases and aid in the development of personalized medicine. In this study, we proposed a computational method, a partial correlation-based single-sample network (P-SSN), which not only infers a network from each single-sample data given a reference dataset but also retains the direct interactions by excluding indirect interactions (https://github.com/hyhRise/P-SSN). By applying P-SSN to analyze tumor data from the Cancer Genome Atlas and single cell data, we validated the effectiveness of P-SSN in predicting driver mutation genes (DMGs), producing network distance, identifying subtypes and further classifying single cells. In particular, P-SSN is highly effective in predicting DMGs based on single-sample data. P-SSN is also efficient for subtyping complex diseases and for clustering single cells by introducing network distance between any two samples.

Feature embedding and conditional neural processes for data imputation

This Letter addresses the missing value prediction problem in data. Existing missing value prediction studies apply their algorithms after replacing missing values with a constant value, which does not represent the missing values clearly and has disadvantages in processing data with a high missing rate. The authors propose a model that generalises a single data sample from its observations and predicts the value of a query feature. The authors' model can deal with an incomplete data sample independently of missing values. In this process, the feature embedding matrix and feature importance weights are introduced to represent each feature and learned jointly with the proposed model. Through experiments, they verify that the proposed model effectively predicts the missing values of data.

Single-sample landscape entropy reveals the imminent phase transition during disease progression

The time evolution or dynamic change of many biological systems during disease progression is not always smooth but occasionally abrupt, that is, there is a tipping point during such a process at which the system state shifts from the normal state to a disease state. It is challenging to predict such disease state with the measured omics data, in particular when only a single sample is available. In this study, we developed a novel approach, i.e. single-sample landscape entropy (SLE) method, to identify the tipping point during disease progression with only one sample data. Specifically, by evaluating the disorder of a network projected from a single-sample data, SLE effectively characterizes the criticality of this single sample network in terms of network entropy, thereby capturing not only the signals of the impending transition but also its leading network, i.e. dynamic network biomarkers. Using this method, we can characterize sample-specific state during disease progression and thus achieve the disease prediction of each individual by only one sample. Our method was validated by successfully identifying the tipping points just before the serious disease symptoms from four real datasets of individuals or subjects, including influenza virus infection, lung cancer metastasis, prostate cancer and acute lung injury. https://github.com/rabbitpei/SLE. Supplementary data are available at Bioinformatics online.

Parameter distribution characteristics of material fatigue life using improved bootstrap method

The bootstrap method is mostly used to estimate statistical characteristics of small sample data. However, the limitations of the bootstrap method itself lead to a reduction in the reliability of small-sample estimates. In this article, an improved bootstrap method is developed to address this problem. In the statistically significant error range (the sample average error and the limit error of sampling) of the original single sample data, expanding the virtual test data that obey two distributions to overcome the limitations of the bootstrap method itself. This article compares and analyses these two methods through the case; the result indicates that the improved bootstrap method can enhance the reliability of the estimation results without changing its probability distribution. We also discussed how to reduce the fluctuation of the improved bootstrap method. And the effectiveness and feasibility of this improved method are discussed in the analysis of fatigue life test data.

An Effective Crowdsourcing Data Reporting Scheme to Compose Cloud-Based Services in Mobile Robotic Systems

The smart device combined with artificial intelligence can act as robot system to perform data collection task. To minimize the data collection cost and to guarantee the quality of service (QoS) of tasks are two vital issue in such mobile robot system. Data collection platform and data reporter often needs to negotiate with each other before start of data collection which will generate a certain cost. Once the platform and the data reporter agree to the cooperation, data reporter will collect and report data for a period. However, in previous researches, it was often considered that data reporters can report data at any time without considering the cost of interaction and negotiation, which is not suitable for the practice. In this paper, we propose an efficiency cost data collection scheme (ECDCS) in which the data reporter is selected according to the contribution that all the data it collects have on the whole system rather than a single data samples. Because there exists correlation in data, matrix completion technology can be adopted to recover the missing data samples with partial data while guarantee the QoS of the task. So, a data reporter selection scheme ECDCS based on the matrix completion technology is proposed in which the selection is in terms of the cooperation effect of the reporters rather than a single data sample. The main goal is to select the reporter set with low cost and high QoS which has the best cooperative effect. By doing so, in the proposed data collection scheme, the missing of partial data can be tolerated which can reduce data collection cost while guarantee the QoS. The extensive experiments results indicate that the proposed scheme can effectively reduce the data cost while maintain the QoS of application.

A Novel Multi-Sine Excitation Procedure for Impedance Spectroscopy Supports Automatic Drift Correction and Online Error Determination

The traditional way to measure impedance using single-sine (monochromatic) excitation is the most transparent and robust way to find reliable EIS data. Compared to the time saving polychromatic (i.e. multi-sine) excitation, the advantage of single-sine excitation is the unequivocal assignment of harmonic content in the response signal to unwanted interference. Systematic analysis of these harmonics allows for the determination of a reliable measurement variance for every single data sample immediately after raw data collection is complete. For decades, such a procedure named “Weighted Harmonics Autocorrelation” has proven its benefit for the EIS instruments of the authors group [1]. Another helpful feature is owed to the periodicity of the monochromatic excitation: unwanted time drift contributions can be calculated from succeeding periods of the response signal for the reconstruction of the drift-free response. This allows for an automatic drift correction [2]. These valuable features are hardly achievable using standard multi sine techniques. Here, even in the absence of interference, the response signals are neither periodic nor free of harmonics. In spite of the fact that monochromatic techniques have the better relationship between information density and time effort [3], it is sometimes preferable to use multi-sine whenever the total measurement time is crucial for practical reasons. In this poster, a novel multi-sine excitation method will be presented that keeps the advantages of automatic drift correction and online error determination analogous to the monochromatic single-sine procedure. Keywords: EIS, error determination, drift correction, multi-sine, single-sine

High speed FPGA-based data acquisition system

An application that involves high speed signal changes at input side makes it very important to have a high speed Data Acquisition without loss of any data. This paper discusses FPGA design architecture programed by VHDL firmware which involves high speed Analog to digital converter (ADC) with sampling rate of 80 mega samples per second, Direct Memory Access (DMA) programed in such a way which transfers data without loss of single data sample and high speed Dual Data Rate 3 (DDR3) SDRAM to store digitized data for further manipulations. It also describes data-rate, and speed achieved to transfer data and plot a graph of digital value which shows there is no loss of data.

Estimation of random errors for lidar based on noise scale factor**Project supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDB05040300) and the National Natural Science Foundation of China (Grant No. 41205119).

Estimation of random errors, which are due to shot noise of photomultiplier tube (PMT) or avalanche photodiode (APD) detectors, is very necessary in lidar observation. Due to the Poisson distribution of incident electrons, there still exists a proportional relationship between standard deviation and square root of its mean value. Based on this relationship, noise scale factor (NSF) is introduced into the estimation, which only needs a single data sample. This method overcomes the distractions of atmospheric fluctuations during calculation of random errors. The results show that this method is feasible and reliable.

Measurement of the principal quasi-isentrope of lead to ~3Mbar using the "Z" machine

We have measured the principal quasi-isentrope of pure lead to ~3 Mbar, using magnetically-driven ramp compression on SNL's "Z" machine. Multiple point-VISARs were used to measure the surface velocities of the compressed samples, and iterative Lagrangian analysis was used to find the wave speed as a function of ramp velocity to an accuracy of <2%. This was then integrated to longitudinal stress as a function of volume on the quasi-isentrope. The experiment used a stripline configuration with samples arranged in pairs at each of 4 vertical positions on opposite drive panels: three of the four pair positions held two lead samples of different thicknesses, while the fourth consisted of one lead sample and a bare panel for drive measurement. The thicker samples of the 3 pairs experienced weak shocks at low stress so their quasi-isentrope data is unreliable there. The single-sample data was good at low stress but affected at high stress by either effects of closure of the stripline gap and / or reflections of the compression pulse from the drive-panel rear surfaces. Data from both methods overlapped at intermediate stresses so have been combined to give the required quasi-isentrope data.

Comparing a few SNP calling algorithms using low-coverage sequencing data

BackgroundMany Single Nucleotide Polymorphism (SNP) calling programs have been developed to identify Single Nucleotide Variations (SNVs) in next-generation sequencing (NGS) data. However, low sequencing coverage presents challenges to accurate SNV identification, especially in single-sample data. Moreover, commonly used SNP calling programs usually include several metrics in their output files for each potential SNP. These metrics are highly correlated in complex patterns, making it extremely difficult to select SNPs for further experimental validations.ResultsTo explore solutions to the above challenges, we compare the performance of four SNP calling algorithm, SOAPsnp, Atlas-SNP2, SAMtools, and GATK, in a low-coverage single-sample sequencing dataset. Without any post-output filtering, SOAPsnp calls more SNVs than the other programs since it has fewer internal filtering criteria. Atlas-SNP2 has stringent internal filtering criteria; thus it reports the least number of SNVs. The numbers of SNVs called by GATK and SAMtools fall between SOAPsnp and Atlas-SNP2. Moreover, we explore the values of key metrics related to SNVs’ quality in each algorithm and use them as post-output filtering criteria to filter out low quality SNVs. Under different coverage cutoff values, we compare four algorithms and calculate the empirical positive calling rate and sensitivity. Our results show that: 1) the overall agreement of the four calling algorithms is low, especially in non-dbSNPs; 2) the agreement of the four algorithms is similar when using different coverage cutoffs, except that the non-dbSNPs agreement level tends to increase slightly with increasing coverage; 3) SOAPsnp, SAMtools, and GATK have a higher empirical calling rate for dbSNPs compared to non-dbSNPs; and 4) overall, GATK and Atlas-SNP2 have a relatively higher positive calling rate and sensitivity, but GATK calls more SNVs.ConclusionsOur results show that the agreement between different calling algorithms is relatively low. Thus, more caution should be used in choosing algorithms, setting filtering parameters, and designing validation studies. For reliable SNV calling results, we recommend that users employ more than one algorithm and use metrics related to calling quality and coverage as filtering criteria.

A New Fuzzing Method Using Multi Data Samples Combination

Knowledge-based Fuzzing technologies have been applied successfully in software vulnerability mining, however, its current methods mainly focus on Fuzzing target software using a single data sample with one or multi-dimension input mutation [1], and thus the vulnerability mining results are not stable, false negatives of vulnerability are high and the selection of data sample depends on human analysis. To solve these problems, this paper proposes a model named Fuzzing Test Suite Generation model using multi data sample combination (FTSGc), which can automatically select multi data samples combination from a large scale data sample set to fuzz target software and generate the test cases that can cover more codes of the software vulnerabilities. To solve Data Sample Coverage Problem (DSCP) in the proposed FTSGc, a method of covering maximum nodes’ semantic attributes with minimum running cost is put forward and a theorem named Maximum Coverage Theorem is given to select the data sample combination. We conclude that DSCP is actually the Set Covering Problem (SCP). Practical experimental results show that the proposed Fuzzing method works much better than the other current Fuzzing method on the Ability of Vulnerability Mining (AVM).