Blind Source Separation Research Articles

On the impact of interlayer misalignment for dual-layer data detection in three dimensional magnetic recording

Three-dimensional magnetic recording (3DMR) is a crucial technology for significantly increasing the storage capacity of hard disk drives (HDDs). However, the presence of inter-symbol interference (ISI), intertrack interference (ITI), and interlayer interference (ILI) poses significant challenges to the accurate detection of data stored on multiple layers. This study addresses the impact of interlayer misalignment on the bit error rate (BER) performance in 3DMR systems. We evaluate the performance based on a neural network estimator for reconstructing the top-layer read response signal using feedback from a Viterbi detector. This enables the separation of bottom-layer signals by subtraction from the mixed readback signal. We introduce a dual-layer partial response maximum likelihood (PRML) detector for simultaneous bit retrieval from both layers. Furthermore, we investigate methods of a per-layer binary classifier and a dual-layer four-class classifier based on neural networks. Our study demonstrates the BER performance of these detection schemes influenced by the interlayer misalignment, especially when the offset is 0, 10%, 50%, and 90% of the bit dimensions between the two layers. The results show that the neural network-based reconstruction and separation method achieves better bottom-layer BER performance under a slight interlayer misalignment. The BER performance benefits more from a mild downtrack offset than the crosstrack offset. The neural network-based separation detection and the dual-layer PRML achieve the lowest top-layer BER and the worst bottom-layer BER when the interlayer misalignment is half a bit.

Patterns identification using blind source separation with application to neural activities associated with anticipated falls

Exploring the nature of neural activity in humans attracts much attention in human-machine interfaces. However, there is still a lack of understanding about the neural activities associated with human anticipated falls. This study examines how the brain responds to anticipated falls by identifying the patterns of neural activities associated with anticipated falls with Electroencephalograms (EEG). We developed a method for pattern identification of neural activities with second-order blind identification in the machine learning framework. The effects of artifact removal within EEG data are compared between the second-order blind identification (SOBI) algorithm and a related method. Experiments involving 135 anticipated falls and 135 walk controls show that the median sample entropy of the EEG signals in the anticipated falls is from 0.1151 to 0.2267 smaller (p-value <0.01) than those in the walk controls. In anticipated falls detection, the average accuracy with random forests is 85.2% for channel O2, which is nearly 10% higher than the channel temporal cerebral cortex (T3 and T4). The results can further guide us in developing new systems of human–machine interfaces, such as EEG data-augmented wearable airbags, to prevent anticipated falls.

Development of an integrated framework for dissecting source-oriented ecological and health risks of heavy metals in soils

Heavy metals (HMs) in soils pose significant risks on ecosystem and human health. To design targeted regulatory measures for mitigating and controlling the risk, it is necessary to accurately identify the pollution sources and environmental risks of soil HMs, as well as to reveal the linkages between them. To date, yet systematic investigation aimed at deciphering the links between source apportionment of soil HMs and their associated environmental risks is still lacking. To fill the gap, an integrated framework has been developed in this study and applied for dissecting the source-sink relationship and source-oriented ecological and health risks of soil HMs in Shanxi, a province with rich coal resource, in which long-term coal mining activities in history has resulted in soil HMs pollution and unavoidably posed environmental risks. Two advanced receptor models, multivariate curve resolution alternating least squares based on maximum likelihood principal component analysis (MCR-ALS/MLPCA) and multilinear engine 2 (ME2), have been employed for apportioning the potential sources, and their apportionment results are jointly incorporated into a modified ecological risk index and a probabilistic health risk assessment model for identifying the source-oriented ecological and health risks posed by soil metals. The results show that the soils in study area have been polluted by HMs (i.e., Cd, Cr, Hg and As) to varying degrees. Industrial activities (35%–35.8%), agricultural activities (11.1%–20.5%), atmospheric deposition (10.5%–13%) and mix source (31.5%–42.6%) are apportioned as the main contributors of soil HMs in the area. The source-oriented ecological risk assessment suggests Hg has presented significant ecological risk and largely contributed by the sources from atmospheric deposition and industrial activities. The source-oriented health risk assessment shows the non-carcinogenic hazard level and carcinogenic risk posed by soil HMs in the study area are acceptable. Relatively, industrial activities and mix source have contributed more on the health risks.

Voluntary co-contraction of ankle muscles alters motor unit discharge characteristics and reduces estimates of persistent inward currents.

Motoneuronal persistent inward currents (PICs) are facilitated by neuromodulatory inputs but are highly sensitive to local inhibitory circuits. Estimates of PICs are reduced by group Ia reciprocal inhibition, and increased with the diffuse actions of neuromodulators released during remote muscle contraction. However, it remains unknown how motoneurons function in the presence of simultaneous excitatory and inhibitory commands. To probe this topic, we investigated motor unit discharge patterns and estimated PICs during voluntary co-contraction of ankle muscles, which simultaneously demands the contraction of agonist-antagonist pairs. Twenty participants performed triangular ramps of both co-contraction (simultaneous dorsiflexion and plantar flexion) and isometric dorsiflexion to a peak of 30% of their maximum muscle activity from a maximal voluntary contraction. Motor unit spike trains were decomposed from high-density surface EMG activity recorded from tibialis anterior using blind source separation algorithms. Voluntary co-contraction altered motor unit discharge rate characteristics. Discharge rate at recruitment and peak discharge rate were modestly reduced (∼6% change; P<0.001; d=0.22) and increased (∼2% change; P=0.001, d=-0.19), respectively, in the entire dataset but no changes were observed when motor units were tracked across conditions. The largest effects during co-contraction were that estimates of PICs (ΔF) were reduced by ∼20% (4.47 vs. 5.57 pulses per second during isometric dorsiflexion; P<0.001, d=0.641). These findings suggest that, during voluntary co-contraction, the inhibitory input from the antagonist muscle overcomes the additional excitatory and neuromodulatory drive that may occur due to the co-contraction of the antagonist muscle, which constrains PIC behaviour. KEY POINTS: Voluntary co-contraction is a unique motor behaviour that concurrently provides excitatory and inhibitory synaptic input to motoneurons. Co-contraction of agonist-antagonist pairs alters agonist motor unit discharge characteristics, consistent with reductions in persistent inward current magnitude.

Overlapping Signals Separation for Two Light Sources Based on Mode-Mixed PD Arrays

Overlapping Signals Separation for Two Light Sources Based on Mode-Mixed PD Arrays

Refining hemodynamic correction in in vivo wide-field fluorescent imaging through linear regression analysis

Accurate interpretation of in vivo wide-field fluorescent imaging (WFFI) data requires precise separation of raw fluorescence signals into neural and hemodynamic components. The classical Beer-Lambert law-based approach, which uses concurrent 530-nm illumination to estimate relative changes in cerebral blood volume (CBV), fails to account for the scattering and reflection of 530-nm photons from non-neuronal components leading to biased estimates of CBV changes and subsequent misrepresentation of neural activity. This study introduces a novel linear regression approach designed to overcome this limitation. This correction provides a more reliable representation of CBV changes and neural activity in fluorescence data. Our method is validated across multiple datasets, demonstrating its superiority over the classical approach.

Improving the technological process of balancing electric machine rotors on a balancing machine

The object of research is the process of dynamic balancing of rotors on a balancing machine in the process of restoring electric machines. The work is aimed at improving the quality of balancing rotors in the process of major repairs of traction electric motors for electric trains. The problem addressed was the quality of balancing the rotors of electric machines on stationary balancing machines. According to the conventional balancing technology, the rotor to be balanced is mounted on the supports of the balancing machine with support surfaces that usually have mechanical defects. These defects cannot be eliminated by machining due to the peculiarities of rotor repair technology. Theoretical and experimental studies of the effect of damage to the rotor support surfaces on the balancing parameters have been carried out. It has been proven that the properties of the bearing surfaces of the rotor during its balancing on a balancing machine significantly affect the results of determining the imbalance. At the same time, the difference in the mass values of balancing loads can reach 25 %. This is because damage to the bearing surfaces of the rotor generates false signals unrelated to the imbalance. In order to increase the accuracy of determining the mass of balancing loads during rotor balancing, it is proposed to improve the technological process of balancing. The improvement involves the inclusion of a frequency filter in the signal conversion chain of acceleration sensors. The filter is designed to separate signals with a frequency greater than the rotational frequency of the rotor. A condition for the practical application of the research results is the expediency of introducing a frequency filter of signals of acceleration sensors with a threshold frequency of filtering signals that exceeds the rotational frequency of the rotor into the schematic diagram of the balancing machine.

Vibration separation method for permanent magnet guideway irregularity measurement

High-temperature superconducting (HTS) pinning maglev has the potential to achieve high operational speed while having a low maintenance cost, attracting a lot of attention. The HTS pinning maglev system realizes the levitation of the vehicle through the flux pinning characteristics between the high-temperature superconducting bulk and the magnetic field of the permanent magnet guideway (PMG). Thus, the profile of the magnetic field of the PMG can significantly affect the levitation status of the vehicle, which makes the PMG irregularity become one of the main excitation sources of the system. The magnetic induction intensity on the surface of the PMG can be used to characterize the PMG irregularity, but the non-contact dynamic measurement may produce large errors by the vibration of the measurement system during the process. In order to evaluate the PMG irregularity, the vibration component needs to be separated from the overall signal. In this paper, through the synchronous measurement of the Hall sensor and accelerometer, the vibration separation method of the PMG irregularity measurement is simplified to the optimal filter estimation. The particle swarm optimization (PSO) algorithm is used to calculate the parameters of the optimal filter based on the correlation coefficient criterion. The effectiveness of the proposed method is verified by the test. The separated signal is more accurate in both time domain and frequency domain for the characterization of PMG irregularity.

Jazz Trio Database: Automated Annotation of Jazz Piano Trio Recordings Processed Using Audio Source Separation

Recent advances in automatic music transcription have facilitated the creation of large databases of symbolic transcriptions of improvised music forms including jazz, where traditional notated scores are not normally available. In conjunction with music source separation models that enable audio to be “demixed” into separate signals for multiple instrument classes, these algorithms can also be applied to generate annotations for every musician in a performance. This can enable the analysis of interesting performer-level and ensemble-level features that have often been difficult to explore. To this end, we introduce Jazz Trio Database (JTD), a dataset of 44.5 h of jazz piano solos accompanied by bass and drums, with automatically generated annotations for each performer. These annotations consist of onset, beat, and downbeat timestamps, alongside MIDI for the piano soloist. Suitable recordings, broadly representative of the “straight-ahead” jazz style, were identified by scraping user-based listening and discographic data; source separation models were applied to isolate audio for each performer in the trio; annotations were generated by applying appropriate algorithms to both the separated and the mixed audio sources. Onset annotations generated by the pipeline achieved a mean F-measure of 0.94 when compared with ground truth annotations. We conduct several analyses of JTD, including with relation to swing and inter-performer synchronization. We anticipate that JTD will be useful in a variety of music information–retrieval tasks, including artist identification and expressive performance modeling. We have made JTD, including the annotations and associated source code, available at https://github.com/HuwCheston/Jazz-Trio-Database

Recent Visual Experience Reshapes V4 Neuronal Activity and Improves Perceptual Performance.

Recent visual experience heavily influences our visual perception, but how neuronal activity is reshaped to alter and improve perceptual discrimination remains unknown. We recorded from populations of neurons in visual cortical area V4 while two male rhesus macaque monkeys performed a natural image change detection task under different experience conditions. We found that maximizing the recent experience with a particular image led to an improvement in the ability to detect a change in that image. This improvement was associated with decreased neural responses to the image, consistent with neuronal changes previously seen in studies of adaptation and expectation. We found that the magnitude of behavioral improvement was correlated with the magnitude of response suppression. Furthermore, this suppression of activity led to an increase in signal separation, providing evidence that a reduction in activity can improve stimulus encoding. Within populations of neurons, greater recent experience was associated with decreased trial-to-trial shared variability, indicating that a reduction in variability is a key means by which experience influences perception. Taken together, the results of our study contribute to an understanding of how recent visual experience can shape our perception and behavior through modulating activity patterns in the mid-level visual cortex.

An adaptive spatiotemporal filter for ultrasound localization microscopy based on density canopy clustering

Ultrasound Localization Microscopy (ULM) facilitates structural and hemodynamic imaging of microvessels with a resolution of tens of micrometers. In ULM, the extraction of effective microbubble signals is crucial for image quality. Singular Value Decomposition (SVD) is currently the most prevalent method for microbubble signal extraction in ULM. Most existing ULM studies employ a fixed SVD filter threshold using empirical values which will lead to imaging quality degradation due to the insufficient separation of blood signals. In this study, we propose an adaptive and non-threshold SVD filter based on canopy-density clustering, termed DCC-SVD. This filter automatically classifies the components of the SVD based on the density of their spatiotemporal features, eliminating the need for parameter selection. In in vitro tube phantom, DCC-SVD demonstrated its ability to adaptive separation of blood and bubble signal at varying microbubble concentrations and flow rates. We compared the proposed DCC-SVD method with the Block-match 3D (BM3D) filter and a classical adaptive method called spatial similarity matrix (SSM), using concentration-variable in vivo rat brain data, as well as open-source rat kidney and mouse tumor datasets. The proposed DCC-SVD improved the global spatial resolution by approximately 4 μm from 30.39 μm to 26.02 μm. It also captured vessel structure absent in images obtained by other methods and yielded a smoother vessel intensity profile, making it a promising spatiotemporal filter for ULM imaging.

Intelligent Identification and Quantitative Evaluation Method of Fluid Components from T2-T1 2D NMR Logging

Summary T2-T1 2D nuclear magnetic resonance (NMR) logging plays an important role in fluid identification and reservoir evaluation. When the signal/noise ratio (SNR) is low, the response of the fluid component overlaps on the NMR 2D spectrum, and the fluid characteristic map obtained in the laboratory could not be directly applied to 2D NMR logging data. In this work, we proposed a T2-T1 2D NMR fluid identification and quantitative evaluation method based on blind source separation (BSS) and hierarchical clustering. This method fixes the number of fluid components of BSS as eight and utilizes a hierarchical clustering method to further process the 2D spectra obtained from BSS, so that each spectrum contains only one fluid component response. Subsequently, the fluid types are determined according to the response characteristics, and the fluid volumes are quantitatively calculated. Based on the synthetic data of T2-T1 2D NMR logging, this method was used to calculate the volumes of the fluid components, and the accuracy of the method was verified by comparing with the model and other four methods. This method was applied to 2D NMR logging data from Well Z and Well G and verified by oil test results. The results show that the relative error between the fluid volumes calculated by the proposed method and the model is smaller than other methods. The data processing results of Well Z and Well G are consistent with those of the oil test. Both synthetic data and actual logging data show that this method can provide the accurate fluid identification and quantitative evaluation results of T2-T1 2D NMR logging data.

RF-GymCare: Introducing Respiratory Prior for RF Sensing in Gym Environments

Exercise-induced sudden death has become an increasingly serious health issue in recent years. Fortunately, respiratory monitoring can serve as an effective early prevention solution. In particular, radio frequency (RF) sensing has emerged as a promising solution due to its contactless nature and privacy preservation. Existing RF-based respiratory monitoring solutions for homes, offices, or vehicles would suffer from significant performance degradation when deployed in typical gym workouts, where respiratory and physical movements are mixed in the RF signals in an unpredictable manner, leading to a blind source separation (BSS) problem. What is worse, the prior assumptions of source independence in existing BSS algorithms no longer hold, leaving respiratory monitoring in gym scenarios as an open issue. In this paper, we propose RF-GymCare, which introduces respiratory priors into the BSS problem and utilizes knowledge distillation to transfer these priors, aiming to learn the demixing weight from mixed signals. With the demixing weight, the respiratory signal can be obtained through a linear combination of the mixed signals. Our experiments with 13 hours of data across nine types of exercises demonstrate its superiority over existing methods, achieving a median similarity of 0.75 and a median rate error of 0.5 respiration per minute (RPM), respectively.

Research on blind source separation of operation sounds of metro power transformer through an Adaptive Threshold REPET algorithm

PurposeThe safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system. Through voiceprint technology, the sounds emitted by the transformer can be monitored in real-time, thereby achieving real-time monitoring of the transformer’s operational status. However, the environment surrounding power transformers is filled with various interfering sounds that intertwine with both the normal operational voiceprints and faulty voiceprints of the transformer, severely impacting the accuracy and reliability of voiceprint identification. Therefore, effective preprocessing steps are required to identify and separate the sound signals of transformer operation, which is a prerequisite for subsequent analysis.Design/methodology/approachThis paper proposes an Adaptive Threshold Repeating Pattern Extraction Technique (REPET) algorithm to separate and denoise the transformer operation sound signals. By analyzing the Short-Time Fourier Transform (STFT) amplitude spectrum, the algorithm identifies and utilizes the repeating periodic structures within the signal to automatically adjust the threshold, effectively distinguishing and extracting stable background signals from transient foreground events. The REPET algorithm first calculates the autocorrelation matrix of the signal to determine the repeating period, then constructs a repeating segment model. Through comparison with the amplitude spectrum of the original signal, repeating patterns are extracted and a soft time-frequency mask is generated.FindingsAfter adaptive thresholding processing, the target signal is separated. Experiments conducted on mixed sounds to separate background sounds from foreground sounds using this algorithm and comparing the results with those obtained using the FastICA algorithm demonstrate that the Adaptive Threshold REPET method achieves good separation effects.Originality/valueA REPET method with adaptive threshold is proposed, which adopts the dynamic threshold adjustment mechanism, adaptively calculates the threshold for blind source separation and improves the adaptability and robustness of the algorithm to the statistical characteristics of the signal. It also lays the foundation for transformer fault detection based on acoustic fingerprinting.

An Enhanced Collaborative Localization Method Based on Belief Propagation Aided by 3D Terrain Modelling

Navigation system performance degrades significantly in complex environments. It is important to analyze satellite visibility through 3D terrain modelling and separate the satellite signals propagated by NLOS to suppress the NLOS error. However, the traditional 3D terrain modelling visibility analysis method based on the pure terrain cover angle is only suitable for determining the visibility of GNSS satellites and may incorrectly separate LOS propagate measurement signals from members with low relative ranges and elevation angles under air–ground swarm conditions. To this end, this paper proposes a belief-propagating cooperative navigation method based on air–ground visibility analysis, which avoids mistakenly separating close-range LOS cooperative navigation signals by simultaneously considering the distances, elevation angles, and azimuths of the signal sources relative to the air–ground swarm members. The simulation shows that the cooperative navigation NLOS identification method based on air–ground visibility analysis proposed in this paper can more accurately realize the separation of NLOS signals under cooperative conditions than the traditional pure angular 3D terrain modelling visibility analysis method can, and the localization error of the members to be assisted is significantly reduced.

Three layered sparse dictionary learning algorithm for enhancing the subject wise segregation of brain networks

Independent component analysis (ICA) and dictionary learning (DL) are the most successful blind source separation (BSS) methods for functional magnetic resonance imaging (fMRI) data analysis. However, ICA to higher and DL to lower extent may suffer from performance degradation by the presence of anomalous observations in the recovered time courses (TCs) and high overlaps among spatial maps (SMs). This paper addressed both problems using a novel three-layered sparse DL (TLSDL) algorithm that incorporated prior information in the dictionary update process and recovered full-rank outlier-free TCs from highly corrupted measurements. The associated sequential DL model involved factorizing each subject’s data into a multi-subject (MS) dictionary and MS sparse code while imposing a low-rank and a sparse matrix decomposition restriction on the dictionary matrix. It is derived by solving three layers of feature extraction and component estimation. The first and second layers captured brain regions with low and moderate spatial overlaps, respectively. The third layer that segregated regions with significant spatial overlaps solved a sequence of vector decomposition problems using the proximal alternating linearized minimization (PALM) method and solved a decomposition restriction using the alternating directions method (ALM). It learned outlier-free dynamics that integrate spatiotemporal diversities across brains and external information. It differs from existing DL methods owing to its unique optimization model, which incorporates prior knowledge, subject-wise/multi-subject representation matrices, and outlier handling. The TLSDL algorithm was compared with existing dictionary learning algorithms using experimental and synthetic fMRI datasets to verify its performance. Overall, the mean correlation value was found to be 26%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$26\\%$$\\end{document} higher for the TLSDL than for the state-of-the-art subject-wise sequential DL (swsDL) technique.

Application of Singular Spectrum Analysis to InSAR time-series for constraining the postseismic deformation due to moderate magnitude earthquakes: the case of 2019 Mw 6 Mirpur earthquake, NW Himalaya

Summary Detection and separation of the subtle postseismic deformation signals associated with moderate magnitude earthquakes from Interferometric Synthetic Aperture Radar (InSAR) time-series is often challenging. Singular Spectrum Analysis (SSA) is a statistical non-parametric technique used to decompose and reconstruct signals from complex time-series data. We show that the SSA analysis effectively distinguished the postseismic signal associated with the 2019 Mw 6 Mirpur earthquake from periodic and noise components. The SSA derived postseismic deformation signal is smoother and fits better to an exponential model with a decay time of 34 days. The postseismic deformation is confined to the southeast of the rupture area and lasted for ∼90 days following the mainshock. Inversion of the postseismic deformation suggests an afterslip mechanism with a maximum slip of ∼0.07 m on the shallow, up-dip portions of the Main Himalayan Thrust. The 2019 Mirpur earthquake and afterslip together released less than 12 per cent of the accumulated strain energy since the 1555 Kashmir earthquake and implies continued seismic hazard in the future.

Investigating the quality of extraction and quantification of bioactive compounds in berries through liquid chromatography and multivariate curve resolution

Berries are a rich source of natural antioxidant compounds, which are essential to profile, as they add to their nutritional value. However, the complexity of the matrix and the structural diversity of these compounds pose challenges in extraction and chromatographic separation. By relying on multivariate curve resolution alternating least squares (MCR-ALS) ability to extract components from complex spectral mixtures, our study evaluates the contributions of various extraction techniques to interference, extractability, and quantifying different groups of overlapping compounds using liquid chromatography diode array detection (LC-DAD) data. Additionally, the combination of these methods extends its applicability to evaluate polyphenol degradation in stored berry smoothies, where evolving factor analysis (EFA) is also used to elucidate degradation products. Results indicate that among the extraction techniques, ultrasonication-assisted extraction employing 1% formic acid in methanol demonstrated superior extractability and selectivity for the different phenolic compound groups, compared with both pressurized liquid extraction and centrifugation of the fresh berry smoothie. Employing MCR-ALS on the LC-DAD data enabled reliable estimation of total amounts of compound classes with high spectral overlaps. Degradation studies revealed significant temperature-dependent effects on anthocyanins, with at least 50% degradation after 7 months of storage at room temperature, while refrigeration and freezing maintained fair stability for at least 12 months. The EFA model estimated phenolic derivatives as the main possible degradation products. These findings enhance the reliability of quantifying polyphenolic compounds and understanding their stability during the storage of berry products.Graphical abstract

A dynamic generative model can extract interpretable oscillatory components from multichannel neurophysiological recordings.

Modern neurophysiological recordings are performed using multichannel sensor arrays that are able to record activity in an increasingly high number of channels numbering in the 100s to 1000s. Often, underlying lower-dimensional patterns of activity are responsible for the observed dynamics, but these representations are difficult to reliably identify using existing methods that attempt to summarize multivariate relationships in a post hoc manner from univariate analyses or using current blind source separation methods. While such methods can reveal appealing patterns of activity, determining the number of components to include, assessing their statistical significance, and interpreting them requires extensive manual intervention and subjective judgment in practice. These difficulties with component selection and interpretation occur in large part because these methods lack a generative model for the underlying spatio-temporal dynamics. Here, we describe a novel component analysis method anchored by a generative model where each source is described by a bio-physically inspired state-space representation. The parameters governing this representation readily capture the oscillatory temporal dynamics of the components, so we refer to it as oscillation component analysis. These parameters - the oscillatory properties, the component mixing weights at the sensors, and the number of oscillations - all are inferred in a data-driven fashion within a Bayesian framework employing an instance of the expectation maximization algorithm. We analyze high-dimensional electroencephalography and magnetoencephalography recordings from human studies to illustrate the potential utility of this method for neuroscience data.

Forensic differentiation of blue pen inks using time-of-flight secondary ion mass spectrometry and multivariate statistical methods

This study investigates the use of time-of-flight secondary ion mass spectrometry (ToF-SIMS) combined with multivariate statistical analysis for the identification of blue pen strokes in document forgery cases. Strokes of six commercially available blue pens were analysed using ToF-SIMS, and the data were interpreted using principal component analysis (PCA) and multivariate curve resolution (MCR). PCA effectively reduced the dimensionality of the complex ToF-SIMS data, enabling clear differentiation of the blue pen inks based on the obtained PCA scores. The first three principal components accounted for most of the variance, with PCA score plots showing distinct clusters of samples corresponding to the spectra of each pen. PCA analysis of the large-area ToF-SIMS images further revealed some characteristic spatial patterns and variations across the pen strokes; however, this analysis was less useful for the identification process. On the other hand, MCR provided a more chemically intuitive analysis by extracting pure component spectra from the complex mixtures. Each MCR factor was individually associated with a specific pen, allowing for exact identification of the pen stroke made. MCR score images displayed clear correlations with individual pen strokes, and the associated loadings identified signals at particular m/z values that were characteristic of each pen. This study shows that an efficient method for non-destructive forensic analysis of blue pen strokes can be achieved by combining ToF-SIMS with PCA and MCR. This analytical method provides reliable identification, which is crucial for forgery detection without requiring any sample pretreatment, i.e. the samples (pen strokes) were used just as they were made on paper.