Causality Network of Infectious Disease Revealed With Causal Decomposition.

Causal inference in the field of infectious disease attempts to gain insight into the potential causal nature of an association between risk factors and diseases. Simulated causality inference experiments have shown preliminary promise in improving understanding of the transmission of infectious diseases but still lack sufficient quantitative causal inference studies based on real-world data. Here, we investigate the causal interactions between three different infectious diseases and related factors, using causal decomposition analysis, to characterize the nature of infectious disease transmission. We show that the complex interactions between infectious disease and human behavior have a quantifiable impact on transmission efficiency of infectious diseases. Our findings, by shedding light on the underlying transmission mechanism of infectious diseases, suggest that causal inference analysis is a promising approach to determine epidemiological interventions.

Unsupervised model adaptation for multivariate calibration by domain adaptation-regularization based kernel partial least square.

In chemometrics, calibration model adaptation is desired when training- and test-samples come from different distributions. Domain-invariant feature representation is currently a successful strategy to realize model adaptation and has received wide attention. The paper presents a nonlinear unsupervised model adaptation method termed as domain adaption regularization-based kernel partial least squares regression (DarKPLS). DarKPLS aims to minimize the source and target distributions in a low-dimensional latent space projected from the reproducing kernel Hilbert space (RKHS) generated with the labeled source data and unlabeled target data. Specially, the distributional means and variances between source and target latent variables are aligned in the RKHS. By extending existing domain invariant partial least square regression (di-PLS) with the projected maximum mean discrepancy (PMMD) to reduce the mean discrepancy in the RKHS further, DarKPLS could realize fine-grained domain alignment that further improves the adaptation performance. DarKPLS is applied to the γ-polyglutamic acid fermentation dataset, tobacco dataset and corn dataset, and it demonstrates improved prediction results in comparison with No adaptation partial least squares (PLS), null augmented regression (NAR), extended linear joint trained framework (ExtJT), scatter component analysis (SCA) and domain-invariant iterative partial least squares (DIPALS).

Bioinformatics and In silico approaches to identify novel biomarkers and key pathways for cancers that are linked to the progression of female infertility: A comprehensive approach for drug discovery.

Despite modern treatment, infertility remains one of the most common gynecologic diseases causing severe health effects worldwide. The clinical and epidemiological data have shown that several cancerous risk factors are strongly linked to Female Infertility (FI) development, but the exact causes remain unknown. Understanding how these risk factors affect FI-affected cell pathways might pave the door for the discovery of critical signaling pathways and hub proteins that may be targeted for therapeutic intervention. To deal with this, we have used a bioinformatics pipeline to build a transcriptome study of FI with four carcinogenic risk factors: Endometrial Cancer (EC), Ovarian Cancer (OC), Cervical Cancer (CC), and Thyroid Cancer (TC). We identified FI sharing 97, 211, 87 and 33 differentially expressed genes (DEGs) with EC, OC, CC, and TC, respectively. We have built gene-disease association networks from the identified genes based on the multilayer network and neighbour-based benchmarking. Identified TNF signalling pathways, ovarian infertility genes, cholesterol metabolic process, and cellular response to cytokine stimulus were significant molecular and GO pathways, both of which improved our understanding the fundamental molecular mechanisms of cancers associated with FI progression. For therapeutic intervention, we have targeted the two most significant hub proteins VEGFA and PIK3R1, out of ten proteins based on Maximal Clique Centrality (MCC) value of cytoscape and literature analysis for molecular docking with 27 phytoestrogenic compounds. Among them, sesamin, galangin and coumestrol showed the highest binding affinity for VEGFA and PIK3R1 proteins together with favourable ADMET properties. We recommended that our identified pathway, hub proteins and phytocompounds may be served as new targets and therapeutic interventions for accurate diagnosis and treatment of multiple diseases.

Self-organizing maps-based generalized feature set selection for model adaption without reference data for batch process.

When fourier transform infrared spectroscopy (FTIR) techniques combined with multivariate calibration are used to measure the key process features or analyte concentrations during batch process, model adaption is indispensable for maintaining the predictability of a primary calibration model in new secondary batches. Many model adaption methods conforming to the actual application scenario of batch process have been proposed. Here we report on a novel standard-free model adaption method without reference measurement called variable selection strategy with self-organizing maps (VSSOM). It uses self-organizing maps (SOM) to classify the whole spectral variables into multiple classes according to the spectra from primary batch and secondary batch, respectively; and the corresponding primary feature subsets and secondary feature subsets are formed firstly. Secondly, candidate feature subsets without empty elements are generated by operating intersection between any primary feature subsets and any secondary feature subsets. Thirdly, the candidate feature subset with minimum root mean square error of cross-validation (RMSECV) for the primary calibration set is selected as the optimal feature subset. In this manner, the optimal feature subset can be identified from the candidate feature subsets. In other words, VSSOM aims to create a stable and consistent feature subset across different batches provided that it selects better features within the intersection sets between primary feature subsets and any secondary feature subsets. Two batch process datasets (γ-polyglutamic acid fermentation and paeoniflorin extraction) are presented for comparing the VSSOM method with No transfer partial least squares (PLS), boxcar signal transfer (BST), successive projection algorithm (SPA), transfer component analysis (TCA) and domain-invariant iterative partial least squares (DIPALS). Experimental results show that VSSOM has superior performance and comparable prediction performance in all the scenarios.

Bioinformatics and system biology approaches to identify pathophysiological impact of COVID-19 to the progression and severity of neurological diseases.

The Coronavirus Disease 2019 (COVID-19) still tends to propagate and increase the occurrence of COVID-19 across the globe. The clinical and epidemiological analyses indicate the link between COVID-19 and Neurological Diseases (NDs) that drive the progression and severity of NDs. Elucidating why some patients with COVID-19 influence the progression of NDs and patients with NDs who are diagnosed with COVID-19 are becoming increasingly sick, although others are not is unclear. In this research, we investigated how COVID-19 and ND interact and the impact of COVID-19 on the severity of NDs by performing transcriptomic analyses of COVID-19 and NDs samples by developing the pipeline of bioinformatics and network-based approaches. The transcriptomic study identified the contributing genes which are then filtered with cell signaling pathway, gene ontology, protein-protein interactions, transcription factor, and microRNA analysis. Identifying hub-proteins using protein-protein interactions leads to the identification of a therapeutic strategy. Additionally, the incorporation of comorbidity interactions score enhances the identification beyond simply detecting novel biological mechanisms involved in the pathophysiology of COVID-19 and its NDs comorbidities. By computing the semantic similarity between COVID-19 and each of the ND, we have found gene-based maximum semantic score between COVID-19 and Parkinson's disease, the minimum semantic score between COVID-19 and Multiple sclerosis. Similarly, we have found gene ontology-based maximum semantic score between COVID-19 and Huntington disease, minimum semantic score between COVID-19 and Epilepsy disease. Finally, we validated our findings using gold-standard databases and literature searches to determine which genes and pathways had previously been associated with COVID-19 and NDs.

Coulombic effects on resolution of ion mobility spectrometry and its application in online qualitative analysis.

Ion mobility spectrometry is an important gas analysis method used in the rapid detection field. However, due to a lacking of explicit mathematical model of ion peak, it is difficult to extract characteristic analyte peaks from a spectrum containing overlapping peaks to achieve online qualitative analysis. Here, we present an asymmetric peak model for processing ion mobility peaks. For the asymmetric peak model, the key is to accurately estimate the standard deviation of the peak model and the fitting function of the tailing edge. We focused on the Coulombic effects on resolution of ion mobility spectrometry based on a new hypothesis of ion cloud shape and derived a formula for calculating the standard deviation taking the initial pulse width, diffusion and Coulomb repulsion factors into account. The proposed asymmetric peak model combines the advantages of optimal physical and chemical interpretation and explicit mathematical meaning. A fast decomposition method based on the peak model was developed to decompose overlapping peaks. Two overlapping simulated data sets and one real data set (a mixture of acetone and methyl salicylate) were used to test the method. The results indicated that our proposed method successfully decomposed the overlapping spectrum into individual peaks and performed markedly better than other three available methods in terms of the execution time. The proposed method meets the requirements for online qualitative analysis.

Automatic classification of excitation location of snoring sounds.

STUDY OBJECTIVES: For surgical treatment of patients with obstructive sleep apnea-hypopnea syndrome, it is crucial to locate accurately the obstructive sites in the upper airway; however, noninvasive methods for locating the obstructive sites have not been well explored. Snoring, as the cardinal symptom of obstructive sleep apnea-hypopnea syndrome, should contain information that reflects the state of the upper airway. Through the classification of snores produced at four different locations, this study aimed to test the hypothesis that snores generated by various obstructive sites differ. METHODS: We trained and tested our model on a public data set that comprised 219 participants. For each snore episode, an acoustic and a physiological feature were extracted and concatenated, forming a 59-dimensional fusion feature. A principal component analysis and a support machine vector were used for dimensional reduction and snore classification. The performance of the proposed model was evaluated using several metrics: sensitivity, precision, specificity, area under the receiver operating characteristic curve, and F1 score. RESULTS: The unweighted average values of sensitivity, precision, specificity, area under the curve, and F1 were 86.36%, 89.09%, 96.4%, 87.9%, and 87.63%, respectively. The model achieved 98.04%, 80.56%, 72.73%, and 94.12% sensitivity for types V (velum), O (oropharyngeal), T (tongue), and E (epiglottis) snores. CONCLUSIONS: The characteristics of snores are related to the state of the upper airway. The machine-learning-based model can be used to locate the vibration sites in the upper airway.

Bioinformatics and machine learning methodologies to identify the effects of central nervous system disorders on glioblastoma progression.

Glioblastoma (GBM) is a common malignant brain tumor which often presents as a comorbidity with central nervous system (CNS) disorders. Both CNS disorders and GBM cells release glutamate and show an abnormality, but differ in cellular behavior. So, their etiology is not well understood, nor is it clear how CNS disorders influence GBM behavior or growth. This led us to employ a quantitative analytical framework to unravel shared differentially expressed genes (DEGs) and cell signaling pathways that could link CNS disorders and GBM using datasets acquired from the Gene Expression Omnibus database (GEO) and The Cancer Genome Atlas (TCGA) datasets where normal tissue and disease-affected tissue were examined. After identifying DEGs, we identified disease-gene association networks and signaling pathways and performed gene ontology (GO) analyses as well as hub protein identifications to predict the roles of these DEGs. We expanded our study to determine the significant genes that may play a role in GBM progression and the survival of the GBM patients by exploiting clinical and genetic factors using the Cox Proportional Hazard Model and the Kaplan-Meier estimator. In this study, 177 DEGs with 129 upregulated and 48 downregulated genes were identified. Our findings indicate new ways that CNS disorders may influence the incidence of GBM progression, growth or establishment and may also function as biomarkers for GBM prognosis and potential targets for therapies. Our comparison with gold standard databases also provides further proof to support the connection of our identified biomarkers in the pathology underlying the GBM progression.

Amplitude spectrum trend-based feature for excitation location classification from snore sounds.

OBJECTIVE: Successful surgical treatment of obstructive sleep apnea (OSA) depends on the precise location of the vibrating tissue. Snoring is the main symptom of OSA and can be utilized to detect the active location of tissues. However, existing approaches are limited, owing to their inability to capture the characteristics of snoring produced from the upper airway. This paper proposes a new approach to better distinguish different snoring sounds that are generated from four different excitation locations. APPROACH: First, we propose a robust null space pursuit algorithm for extracting the trend from the amplitude spectrum of snoring. Second, a new feature from this extracted amplitude spectrum trend, which outperforms the Mel-frequency cepstral coefficient (MFCC) feature, is designed. Subsequently, the newly proposed feature, namely the trend-based MFCC (TCC), is reduced in dimensionality by using principal component analysis. Finally, a support vector machine is employed for the classification task. MAIN RESULTS: By using the TCC, the proposed approach achieves an unweighted average recall of 87.5% on the classification of four excitation locations on the public dataset Munich Passau Snore Sound Corpus. SIGNIFICANCE: The TCC is a promising feature for capturing the characteristics of snoring. The proposed method can effectively perform snore classification and assist in accurate OSA diagnosis.

Multiscale orthogonal matching pursuit algorithm combined with peak model for interpreting ion mobility spectra and achieving quantitative analysis.

Ion mobility spectrometry is an important rapid analysis method. However, it is difficult to achieve quantitative analysis when spectral peaks overlap. A new method for analyzing ion mobility spectra is presented here. The method achieves quantitative analysis by combining the advantages of the peak model (in terms of optimal physical and chemical interpretation of the system of interest) and the multiscale orthogonal matching pursuit algorithm (in terms of extracting characteristic peaks). A simulated data set, constructed using the peak model, containing overlapping peaks was analyzed to demonstrate the ability of the multiscale orthogonal matching pursuit algorithm to decompose overlapping peaks. Real data sets for methyl salicylate and a mixture of acetone and methyl salicylate at sixteen concentrations were generated using a vapor generator (using permeation tubes). The characteristic peaks were extracted using the multiscale orthogonal matching pursuit algorithm. Univariate calibrations using the peak area and peak height were prepared to allow quantitative analyses to be performed. Multivariate calibrations using partial-least-squares and poly-partial-least-squares were prepared and the results were compared with the univariate calibration results. Markedly better or similar predictions were made using the univariate calibration models involving physical and chemical interpretations than using the multivariate calibration models.

A Network-Based Bioinformatics Approach to Identify Molecular Biomarkers for Type 2 Diabetes that Are Linked to the Progression of Neurological Diseases.

Neurological diseases (NDs) are progressive disorders, the progression of which can be significantly affected by a range of common diseases that present as comorbidities. Clinical studies, including epidemiological and neuropathological analyses, indicate that patients with type 2 diabetes (T2D) have worse progression of NDs, suggesting pathogenic links between NDs and T2D. However, finding causal or predisposing factors that link T2D and NDs remains challenging. To address these problems, we developed a high-throughput network-based quantitative pipeline using agnostic approaches to identify genes expressed abnormally in both T2D and NDs, to identify some of the shared molecular pathways that may underpin T2D and ND interaction. We employed gene expression transcriptomic datasets from control and disease-affected individuals and identified differentially expressed genes (DEGs) in tissues of patients with T2D and ND when compared to unaffected control individuals. One hundred and ninety seven DEGs (99 up-regulated and 98 down-regulated in affected individuals) that were common to both the T2D and the ND datasets were identified. Functional annotation of these identified DEGs revealed the involvement of significant cell signaling associated molecular pathways. The overlapping DEGs (i.e., seen in both T2D and ND datasets) were then used to extract the most significant GO terms. We performed validation of these results with gold benchmark databases and literature searching, which identified which genes and pathways had been previously linked to NDs or T2D and which are novel. Hub proteins in the pathways were identified (including DNM2, DNM1, MYH14, PACSIN2, TFRC, PDE4D, ENTPD1, PLK4, CDC20B, and CDC14A) using protein-protein interaction analysis which have not previously been described as playing a role in these diseases. To reveal the transcriptional and post-transcriptional regulators of the DEGs we used transcription factor (TF) interactions analysis and DEG-microRNAs (miRNAs) interaction analysis, respectively. We thus identified the following TFs as important in driving expression of our T2D/ND common genes: FOXC1, GATA2, FOXL1, YY1, E2F1, NFIC, NFYA, USF2, HINFP, MEF2A, SRF, NFKB1, USF2, HINFP, MEF2A, SRF, NFKB1, PDE4D, CREB1, SP1, HOXA5, SREBF1, TFAP2A, STAT3, POU2F2, TP53, PPARG, and JUN. MicroRNAs that affect expression of these genes include mir-335-5p, mir-16-5p, mir-93-5p, mir-17-5p, mir-124-3p. Thus, our transcriptomic data analysis identifies novel potential links between NDs and T2D pathologies that may underlie comorbidity interactions, links that may include potential targets for therapeutic intervention. In sum, our neighborhood-based benchmarking and multilayer network topology methods identified novel putative biomarkers that indicate how type 2 diabetes (T2D) and these neurological diseases interact and pathways that, in the future, may be targeted for treatment.

Principal component analysis or kernel principal component analysis based joint spectral subspace method for calibration transfer.

To transfer a calibration model in the case where only the master and slave spectra of standardization samples are available, principal component analysis (PCA) and kernel principal component analysis (KPCA) based joint spectral space (termed as JPCA or JKPCA) methods are proposed. As a feature subspace shared by master and slave spectra, the joint spectral subspace in JPCA and JKPCA are the projection of the joint spectral matrix comprising all the spectra of standardization by utilizing PCA and KPCA, respectively. The two corresponding low-dimensional feature matrices for master and slave spectra are extracted from the joint spectral subspace, and then a transfer matrix is estimated based on the least square criterion. In JKPCA, a partial least squares (PLS) model, named the primary model, is constructed using the low-dimensional feature matrix of master calibration spectra, and the model is then used to predict the transferred low-dimensional feature matrix of slave test spectra. Different from JKPCA, JPCA firstly reconstructs master calibration spectra and transferred slave test spectra, respectively. Then the primary model built on the reconstructed version of master calibration spectra is applied to predict the reconstructed version of transferred slave test spectra. A comparative study of the two proposed methods, multiplicative scatter correction (MSC), orthogonal signal correction (OSC), piecewise direct standardization (PDS), canonical correlation analysis based calibration transfer (CCACT), generalized least squares (GLS), slope and bias correction (SBC) and spectral space transformation (SST) is conducted on two datasets. All the statistical results together exhibit that the transfer ability of JKPCA is the best. Except JKPCA, JPCA performs at least comparable with the GLS or SST, and frequently better than the other methods.

A fast progressive spectrum denoising combined with partial least squares algorithm and its application in online Fourier transform infrared quantitative analysis.

Fourier transform infrared (FTIR) spectroscopy is an important method in analytical chemistry. A material can be qualitatively and quantitatively analyzed from its FTIR spectrum. Spectrum denoising is commonly performed before online FTIR quantitative analysis. The average method requires a long time to collect spectra, which weakens real-time online analysis. The Savitzky-Golay smoothing method makes peaks smoother with the increase of window width, causing useful information to be lost. The sparse representation method is a common denoising method, that is used to reconstruct spectrum. However, for the randomness of noise, we can't achieve the sparse representation of noise. Traditional sparse representation algorithms only perform denoising once, and the noise can not be removed completely. FTIR spectrum denoising should therefore be performed in a progressive way. However, it is difficult to determine to what degree of denoising is required. Here, a fast progressive spectrum denoising combined with partial least squares method was developed for online FTIR quantitative analysis. Two real sample data sets were used to test the performance of the proposed method. The experimental results indicated that the progressive spectrum denoising method combined with the partial least squares method performed markedly better than other methods in terms of root mean squared error of prediction and coefficient of determination in the FTIR quantitative analysis.

Calibration Transfer Based on Affine Invariance for NIR without Transfer Standards.

Calibration transfer is an important field for near-infrared (NIR) spectroscopy in practical applications. However, most transfer methods are constructed with standard samples, which are expensive and difficult to obtain. Taking this problem into account, this paper proposes a calibration transfer method based on affine invariance without transfer standards (CTAI). Our method can be utilized to adjust the difference between two instruments by affine transformation. CTAI firstly establishes a partial least squares (PLS) model of the master instrument to obtain score matrices and predicted values of the two instruments, and then the regression coefficients between each of the score vectors and predicted values are computed for the master instrument and the slave instrument, respectively. Next, angles and biases are calculated between the regression coefficients of the master instrument and the corresponding regression coefficients of the slave instrument, respectively. Finally, by introducing affine transformation, new samples are predicted based on the obtained angles and biases. A comparative study between CTAI and the other five methods was conducted, and the performances of these algorithms were tested with two NIR spectral datasets. The obtained experimental results show clearly that, in general CTAI is more robust and can also achieve the best Root Mean Square Error of test sets (RMSEPs). In addition, the results of statistical difference with the Wilcoxon signed rank test show that CTAI is generally better than the others, and at least statistically the same.

Stacked ensemble extreme learning machine coupled with Partial Least Squares-based weighting strategy for nonlinear multivariate calibration.

With its simple theory and strong implementation, extreme learning machine (ELM) becomes a competitive single hidden layer feed forward networks for nonlinear multivariate calibration in chemometrics. To improve the generalization and robustness of ELM further, stacked generalization is introduced into ELM to construct a modified ELM model called stacked ensemble ELM (SE-ELM). The SE-ELM is to create a set of sub-models by applying ELM repeatedly to different sub-regions of the spectra and then combine the predictions of those sub-models according to a weighting strategy. Three different weighting strategies are explored to implement the proposed SE-ELM, such as the Winner-takes-all (WTA) weighting strategy, the constraint non-negative least squares (CNNLS) weighing strategy and the partial least squares (PLS) weighting strategy. Furthermore, PLS is suggested to be selected as the optimal weighting method that can handle the multi-colinearity among the predictions yielded by all the sub-models. The experimental assessment of the three SE-ELM models with different weighting strategies is carried out on six real spectroscopic datasets and compared with ELM, back-propagation neural network (BPNN) and Radial basis function neural network (RBFNN), statistically tested by the Wilcoxon signed rank test. The obtained experimental results suggest that, in general, all the SE-ELM models are more robust and more accurate than traditional ELM. In particular, the proposed PLS-based weighting strategy is at least statistically not worse than, and frequently better than the other two weighting strategies, BPNN, and RBFNN.

Nonlinear least squares with local polynomial interpolation for quantitative analysis of IR spectra.

When using spectroscopic instrumentation for quantitative analysis of mixture, spectral intensity non-linearity and peak shift make it challenging for building calibration model. In this study, we investigated the performance of a nonlinear model, namely nonlinear least squares with local polynomial interpolation (NLSLPI). In NLSLPI, the parameters to be optimized are the concentrations of the components. Levenberg-Marquardt (L-M) method is used to solve the nonlinear-least-squares optimization problem and local polynomial interpolation is used to generate the nonlinear function for each component. We tested the robustness of NLSLPI on a computer-simulation dataset. We also compared NLSLPI, in terms of RMSEP, to partial least squares (PLS), classical least squares (CLS) and piecewise classical least squares (PCLS) on a real-world dataset. Experimental results demonstrate the effectiveness of the proposed method.

SnoreNet: Detecting Snore Events from Raw Sound Recordings.

Snoring is one of the earliest symptoms of Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS). Snore detection is the first step in developing non-invasive, low-cost, and totally sound-based OSAHS analysis approaches. In this work, we propose a simple yet effective deep neural network, named SnoreNet, for detecting snores from a continuous sound recording. Without manually crafted features, SnoreNet can capture the characteristics of snores. Since snore varies in temporal length, SnoreNet combines output from multiple feature maps to detect snore. In each feature map, SnoreNet uses a set of default bounding box generated by a base length and different scales to match snores. SnoreNet adjusts the box to better locate snores and predicts a score for the presence of snore in each default bounding box. The performance of SnoreNet was evaluated on a newly collected snore pattern classes dataset, which achieves 81.82% average precision (AP).

Apnea and Hypopnea Events Classification Using Amplitude Spectrum Trend Feature of Snores.

Research on snores for Obstructive Sleep Apnea Syndrome (OSAS) diagnosis is a new trend in recent years. In this paper, we proposed a snore-based apnea and hypopnea events classification approach. Firstly, we define the snores after the apnea event and during the hypopnea event as apnea-event-snore (AES) and hypopnea-event-snore (HES), respectively. Then, we design a new feature from the trend of the amplitude spectrum of snores. The newly proposed feature can be viewed as an improvement of the Mel-frequency cepstral coefficient (MFCC) feature, which is well-known for speech recognition. The extracted features were fed to principle component analysis (PCA) for dimension reduction and support vector machine (SVM) for apnea and hypopnea events classification. The experimental results demonstrate the efficiency of the proposed algorithm in using snores to classify apnea and hypopnea events.

Exposing splicing forgery based on color temperature estimation.

Splicing is one of the most common tampering techniques for image manipulation in many forensic cases. Normally color shift in images due to color temperature of illumination can be seen as intrinsic features relative to imaging process. In splicing forgeries, copied area and pasted target image come from different imaging process, and are likely to have different color shift. In this paper, a novel automated authentication method is presented to expose splicing manipulation and locate manipulated areas by discriminating the inconsistencies of color shift in an image. In order to minimize human interaction on detection of splicing forgeries as well as localization of manipulated areas, a forensic image is divided into blocks with grid-based strategy. After calculation on color temperature of each blocks with white-point algorithm, reference color temperature is obtained with a random restricted algorithm. Then color temperature distance between each block and reference area is calculated sequentially. At last, by comparing color temperature distance with an optimized threshold determined by OSTU algorithm. This method enables us to judge if splicing has occurred and furthermore localize manipulated area simultaneously. Experiments show that the proposed method can speed up the quantitative detection of possible splicing manipulation and localize manipulated area automatically.

Simultaneous spectrum fitting and baseline correction using sparse representation.

Sparse representation has been applied in many domains, such as signal processing, image processing and machine learning. In this paper, a redundant dictionary with each column composed of a Voigt-like lineshape is constructed to represent the pure spectrum of the sample. With the prior knowledge that the baseline is smooth and sparse representation coefficient for a pure spectrum, a method simultaneously fitting the pure spectrum and baseline is proposed. Since the pure spectrum is nonnegative, the representation coefficients are also made to be nonnegative. Then through alternating optimization, a surrogate function based algorithm is used to obtain the sparse coefficients. Finally, we adopt one simulated data set and two real data sets to evaluate our method. The results of quantitative analysis show that our method successfully estimates the baseline and pure spectrum and is superior compared to other baseline correction and preprocessing methods.