Pattern Recognition Tools Research Articles

Data-driven fingerprint nanoelectromechanical mass spectrometry

Fingerprint analysis is a ubiquitous tool for pattern recognition with applications spanning from geolocation and DNA analysis to facial recognition and forensic identification. Central to its utility is the ability to provide accurate identification without an a priori mathematical model for the pattern. We report a data-driven fingerprint approach for nanoelectromechanical systems mass spectrometry that enables mass measurements of particles and molecules using complex, uncharacterized nanoelectromechanical devices of arbitrary specification. Nanoelectromechanical systems mass spectrometry is based on the frequency shifts of the nanoelectromechanical device vibrational modes that are induced by analyte adsorption. The sequence of frequency shifts constitutes a fingerprint of this adsorption, which is directly amenable to pattern matching. Two current requirements of nanoelectromechanical-based mass spectrometry are: (1) a priori knowledge or measurement of the device mode-shapes, and (2) a mode-shape-based model that connects the induced modal frequency shifts to mass adsorption. This may not be possible for advanced nanoelectromechanical devices with three-dimensional mode-shapes and nanometer-sized features. The advance reported here eliminates this impediment, thereby allowing device designs of arbitrary specification and size to be employed. This enables the use of advanced nanoelectromechanical devices with complex vibrational modes, which offer unprecedented prospects for attaining the ultimate detection limits of nanoelectromechanical mass spectrometry.

Clustering data analytics of urban land use for change detection

In this study, the author proposes and details a workflow for the spatial-temporal demarcation of urban areal features in 8 cities of Tamilnadu, India. During the inception phase, functional requirements and non-functional parameters are analyzed and designed, within a suitable pixel area and object-oriented derived paradigm. Land use categories are defined from OpenStreetMap (OSM) related works with the scope of conducting climate change, using multispectral sensors onboard Landsat series. Furthermore, we augment the bands dataset with Spatially Invariant Feature Transform (SIFT), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Leaf Area Index (LAI), and Texture base indices, as a means of spatially integrating auto-covariance to stationarity patterns. In doing so, change detection can be pursuit by scaling up the segmentation of regional/zonal boundaries in a multi-dimensional environment, with the aid of Wide Area Networks (WAN) cluster computers such as the BEOWULF/Google Earth Engine clusters. GeoAnalytical measures are analyzed in the design of local and zonal spatial models (GRID, RASTER, DEM, IMAGE COLLECTION). Finally, multi variate geostatistical works are ensued for precision and recall in predictive data analytics. The author proposes reusing machine learning tools (filtering by attribute-based indexing in PaaS clouds) for pattern recognition and visualization of features and feature collection.

Clustering data analytics of urban land use for change detection

In this study, the author proposes and details a workflow for the spatial-temporal demarcation of urban areal features in 8 cities of Tamilnadu, India. During the inception phase, functional requirements and non-functional parameters are analyzed and designed, within a suitable pixel area and object-oriented derived paradigm. Land use categories are defined from OpenStreetMap (OSM) related works with the scope of conducting climate change, using multispectral sensors onboard Landsat series. Furthermore, we augment the bands dataset with Spatially Invariant Feature Transform (SIFT), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Leaf Area Index (LAI), and Texture base indices, as a means of spatially integrating auto-covariance to stationarity patterns. In doing so, change detection can be pursuit by scaling up the segmentation of regional/zonal boundaries in a multi-dimensional environment, with the aid of Wide Area Networks (WAN) cluster computers such as the BEOWULF/Google Earth Engine clusters. GeoAnalytical measures are analyzed in the design of local and zonal spatial models (GRID, RASTER, DEM, IMAGE COLLECTION). Finally, multi variate geostatistical works are ensued for precision and recall in predictive data analytics. The author proposes reusing machine learning tools (filtering by attribute-based indexing in PaaS clouds) for pattern recognition and visualization of features and feature collection.

Quantifying the Microstructure of Dried Deposits Using Height-Height Correlation Function.

Colloidal self-assembly has garnered significant attention in recent research, owing to applications in medical and engineering domains. Understanding the arrangement of particles in self-assembled systems is crucial for comprehending the underlying physics and synthesizing complex nano- and microscale structures. In this study, we introduce a novel methodology for analyzing the spatial distribution of particles in colloidal assemblies, focusing specifically on quantifying the microstructure of deposits formed by the evaporation of colloidal particle-laden drops. Utilizing a height-height correlation-function-based approach, we quantify variations in the height profile of deposits in radial and azimuthal directions. This approach enables the classification of the patterns into typical examples encountered in an evaporation-driven assembly. The method is demonstrated to be robust for quantifying synthetic and experimentally obtained deposit patterns, exhibiting excellent agreement in the estimated parameters. The mapping developed between pattern morphology and the quantitative measures introduced in this work may be used in a variety of applications including disease diagnosis as well as in developing pattern recognition tools.

Modern Approach in Pattern Recognition Using Circular Fermatean Fuzzy Similarity Measure for Decision Making with Practical Applications

The circular Fermatean fuzzy (CFF) set is an advancement of the Fermatean fuzzy (FF) set and the interval-valued Fermatean fuzzy (IVFF) set which deals with uncertainty. The CFF set is represented as a circle of radius ranging from 0 to 2 with the center at the degree of association (DA) and degree of nonassociation (DNA). If multiple people are involved in making decisions, the CFF set, as an alternative to the FF and IVFF sets, can deal with ambiguity more effectively by encircling the decision values within a circle rather than taking an average. Using algorithms, a pattern can be observed computationally or visually. Machine learning algorithm utilizes pattern recognition as an instrument for identifying patterns and also similarity measure (SM) is a beneficial pattern recognition tool used to classify items, discover variations, and make future predictions for decision making. In this work, we introduce the CFF cosine and Dice similarity measures (CFFDMs and CFFSMs), and their properties are studied. Unlike traditional approaches of decision making, which emphasize a single number, the proposed CFFSMs observe the pattern over the circular region to help in dealing with uncertainty more effectively. We introduce an innovative decision-making method in the FF setting. Available bank loans and applicants’ eligibility levels are represented as CFF set using their FF criteria and are taken as loan patterns and customer eligibility patterns. The loan is allocated to the applicant by measuring the CFFCSM and CFFDSM between the two patterns. Also, laptops are suggested to the customers by measuring the similarity between specification pattern and requirement pattern. The correctness and consistency of the proposed models are ensured by comparison analysis and graphical simulations of the input and similarity CFFNs.

Quaternion fast and accurate polar harmonic Fourier moments for color image analysis and object recognition

Image moments, as a kind of global feature descriptor of images, have become a valuable tool for pattern recognition and image analysis. However, traditional methods are mainly used to deal with grayscale images. In this paper, we apply quaternions to fast and accurate polar harmonic Fourier moments, proposing a kind of quaternion fast and accurate polar harmonic Fourier moment (QFAPHFM) capable of handling color images. Furthermore, this paper provides a detailed analysis of the invariance of QFAPHFMs under rotation, scaling, and translation transformations. The experimental results show that QFAPHFMs exhibit excellent performance in both image reconstruction and object recognition tasks. QFAPHFMs achieve accurate image reconstruction under noiseless and noisy conditions, and demonstrate excellent recognition performance in the color-based object recognition tasks.

Information Technology for Detecting Fakes and Propaganda Based on Machine Learning and Sentiment Analysis

This article provides a comprehensive study of modern approaches used to identify fakes and propaganda. Machine learning is emerging as a dynamic tool for pattern recognition and adaptation that facilitates real-time analysis. In addition, the article provides an analysis of propaganda based on emotional colouring, which reveals the differences between propaganda and non-propaganda. The average emotional value for propaganda news is 0.151 and for non-propaganda news is 0.116. The average degree of subjectivity for propaganda news is 0.365 and for non-propaganda news is 0.283. The average value of positive emotion for propaganda news is 0.087 and for non-propaganda news is 0.082. The average negative emotion for propaganda news is 0.064 and for non-propaganda news is 0.034. -The average value of the complex emotional colouring for propaganda news is 0.021, and for non-propaganda news - 0.010. Keywords – propaganda, fakes, NLP, natural language processing, disinformation detection, machine learning, multimodal analysis.

Strict intuitionistic fuzzy distance/similarity measures based on Jensen-Shannon divergence

Being a pair of dual concepts, the normalized distance and similarity measures are important tools for decision-making and pattern recognition under the intuitionistic fuzzy set framework. In this paper, we first construct some counterexamples to illustrate that two existing similarity measures do not meet the axiomatic definition of intuitionistic fuzzy similarity measures. We then show that (1) these two measures cannot effectively distinguish some intuitionistic fuzzy values (IFVs); (2) except for the endpoints, there exist infinitely many pairs of IFVs, where the maximum distance “1” can be achieved under these two distances, leading to counter-intuitive results. To overcome these drawbacks, we introduce the concept of strict intuitionistic fuzzy distance measure (SIFDisM) and strict intuitionistic fuzzy similarity measure (SIFSimM), and propose an improved intuitionistic fuzzy distance measure based on Jensen-Shannon divergence. Moreover, we prove that (1) it is a SIFDisM; (2) its dual similarity measure is a SIFSimM; (3) its induced entropy is an intuitionistic fuzzy entropy. Comparative analysis and numerical examples demonstrate that our proposed distance measure is superior to the existing ones. In particular, our proposed distance measure can better distinguish and rank intuitionistic fuzzy sets.

Precision forecasting of spray-dry desulfurization using Gaussian noise data augmentation and k-fold cross-validation optimized neural computing

Perceptron models have become integral tools for pattern recognition and classification problems in engineering fields. This study envisioned implementing artificial neural networks to forecast the performance of a mini-spray dryer for desulfurization activities. This work adopted k-fold cross-validation, a rigorous technique that evaluates model performance across multiple data segments. Several ANN models (21) were trained on data obtained from sulfation conditions, including sulfation temperature (120 °C–200 °C), slurry pH (4–12), stoichiometric ratio (0.5–2.5), slurry solid concentration (6%–14%) as the feed input and sulfur capture as the response. Three hundred synthetic datasets generated using the Gaussian noise data augmentation underwent a 10-fold cross-validation process before simulation on neural networks triggered by the logsig and tansig activation functions. The computation accuracy was further evaluated by altering the number of hidden cells from 2 to 10. The ANN architectures were assessed using statistical metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and the coefficient of determination (R 2) techniques. Overall, error estimation suggests cross-validation and data augmentation are critical in efficient neural network generalization. The logsig function trained with 10 hidden cells presented closer data articulation when mapped onto actual values.

Efficient and Stable Unsupervised Feature Selection Based on Novel Structured Graph and Data Discrepancy Learning.

Unsupervised feature selection is an important tool in data mining, machine learning, and pattern recognition. Although data labels are often missing, the number of data classes can be known and exploited in many scenarios. Therefore, a structured graph, whose number of connected components is identical to the number of data classes, has been proposed and is frequently applied in unsupervised feature selection. However, methods based on the structured graph learning face two problems. First, their structured graphs are not always guaranteed to maintain the same number of connected components as the data classes with existing optimization algorithms. Second, they usually lack strategies for choosing moderate hyperparameters. To solve these problems, an efficient and stable unsupervised feature selection method based on a novel structured graph and data discrepancy learning (ESUFS) is proposed. Specifically, the novel structured graph, consisting of a pairwise data similarity matrix and an indicator matrix, can be efficiently learned by solving a discrete optimization problem. Data discrepancy learning focuses on features that maximize the difference among data and helps in selecting discriminative features. Extensive experiments conducted on various datasets show that ESUFS outperforms state-of-the-art methods not only in accuracy (ACC) but also in stability and speed.

Gastroenterologist-level detection of gastric precursor lesions and neoplasia with a deep convolutional neural network

Background: Gastric precursor lesions and neoplasia with very delicate changes in the gastric mucosa could be easily missed or misdiagnosed under endoscopy. Here we developed an automatic real-time pattern recognition tool based on convolutional neural networks (CNNs) algorithm to help endoscopists in detection of chronic atrophic gastritis (CAG) and gastric cancer (GC) lesions. Methods: The five-convolution-layer ZF model and thirteen-convolution-layer VGG16 model were combined in our neural network A total of 10,014 CAG and 3724 GC annotated images were used in the network training. Another independent set consisted of 50 CAG, 50 GC and 100 negative controls images were used to evaluate the performance of the final network. Results: In CAG detection, the performance of our model was much better than the average performance of the 77 endoscopists in sensitivity, specificity and accuracy (95% versus 74%, 86% versus 82%, 90% versus 78%, respectively). In GC detection, the performance of our model achieved a slightly higher sensitivity (90% versus 87%), but a lower specificity (50% versus 74%) and accuracy (70% versus 80%) than the average performance of the 89 endoscopists. Conclusion: In conclusion, we provided a CNN based computational tool to improve the detection of CAG and GC under endoscopy, and simplify diagnostic procedures.

Leveraging a multivariate approach towards enhanced development of direct compression extended release tablets

Extended release formulations play a crucial role in the pharmaceutical industry by maintaining steady plasma levels, reducing side effects, and improving therapeutic efficiency and compliance. One commonly used method to develop extended release formulations is direct compression, which offers several advantages, such as simplicity, time savings, and cost-effectiveness. However, successful direct compression-based extended release formulations require careful assessment and an understanding of the excipients’ attributes. The scope of this work is the characterization of the compaction behavior of some matrix-forming agents and diluents for the development of extended release tablets. Fifteen excipients commonly used in extended release formulations were evaluated for physical, compaction and tablet properties. Powder properties (e.g., particle size, flow properties, bulk density) were evaluated and linked to the tablet’s mechanical properties in a fully integrated approach, and data were analyzed by constructing a principal component analysis (PCA). Significant variability was observed among the various excipients. The present work successfully demonstrates the applicability of PCA as an effective tool for comparative analysis, pattern and clustering recognition and correlations between excipients and their properties, facilitating the development and manufacturing of direct compressible extended release formulations.

Application of Pattern Recognition and Computer Vision Tools to Improve the Morphological Analysis of Microplastic Items in Biological Samples.

Since, in many routine analytical laboratories, a stereomicroscope coupled with a digital camera is not equipped with advanced software enabling automatic detection of features of observed objects, in the present study, a procedure of feature detection using open-source software was proposed and validated. Within the framework of applying microscopic expertise coupled with image analysis, a set of digital images of microplastic (MP) items identified in organs of fish was used to determine shape descriptors (such as length, width, item area, etc.). The edge points required to compute shape characteristics were set manually in digital images acquired by the camera coupled with a binocular, and respective values were computed via the use of built-in MotiConnect software. As an alternative, a new approach consisting of digital image thresholding, binarization, the use of connected-component labeling, and the computation of shape descriptors on a pixel level via using the functions available in an OpenCV library or self-written in C++ was proposed. Overall, 74.4% of the images were suitable for thresholding without any additional pretreatment. A significant correlation was obtained between the shape descriptors computed by the software and computed using the proposed approach. The range of correlation coefficients at a very high level of significance, according to the pair of correlated measures, was higher than 0.69. The length of fibers can be satisfactorily approximated using a value of half the length of the outer perimeter (r higher than 0.75). Compactness and circularity significantly differ for particles and fibers.

Application of EMD ANN and DNN for Self-Aligning Bearing Fault Diagnosis

Self-aligning roller bearings are an integral part of the industrial machinery. The proper analysis and prediction of the various faults that may happen to the bearing beforehand contributes to an increase in the working life of the bearing. This study aims at developing a novel method for the analysis of the various faults in self-aligning bearings as well as the automatic classification of faults using artificial neural network (ANN) and deep neural network (DNN). The vibration data is collected for six different faults as well as for the healthy bearing. Empirical mode decomposition (EMD) followed by Hilbert Huang transform is used to extract instantaneous frequency peaks which are used for fault analysis. Time domain and time-frequency domain features are then extracted which are used to implement the neural networks through the pattern recognition tool in MATLAB. A comparative study of the outputs from the two neural networks is also performed. From the confusion matrix, the efficiency of the ANN has been found to be 95.7% and using DNN has been found to be 100%.

Efficient unsupervised learning of biological images with compressed deep features

Machine learning has significantly impacted the analysis of biological images and is now an important part of many biological data analysis pipelines. A variety of biological and biomedical domain-related tasks is gaining benefit from image analysis and pattern recognition tools developed currently. Applications include diagnostic histopathology, environmental monitoring, synthetic biology, genomics, and proteomics. Particularly in the last decade, several deep learning and advanced computer vision methods such as convolutional neural networks (CNNs), typically trained in a supervised fashion, have started to be largely employed in biological image classification. Moreover, the advancement of automatic acquisition systems has been generating a massive amount of biological data, which requires to be analyzed by domain experts. However, the cost of manual annotation of such data has become a bottleneck, impairing the application of supervised machine learning algorithms. Biological images generally have an intrinsic high variability, whose identity is sometimes hard to assign and strongly dependent on the annotator’s expertise. In this context, a limited number of annotation-free (i.e., unsupervised) learning solutions have been proposed, typically based on hand-crafted features, specifically tailored for a certain biological domain. Nonetheless, a successful unsupervised learning approach must be accurate, and sufficiently robust to deal with different biological domains. This paper aims at providing a viable solution to these issues, proposing an unsupervised learning algorithm based on compressed deep features for image classification. We exploit features extracted from ImageNet pre-trained transformers and CNNs, further compressed with a customized β-Variational AutoEncoder (β-VAE), that we call reconstruction VAE (R-VAE). We test our algorithm on biological images coming from diverse domains characterized by high variability in shape and texture information and acquired with widely differing imaging platforms. Considered image datasets range from multi-cellular organisms (plankton, coral) to sub-cellular organelles (budding yeast vacuoles, human cells’ nuclei, etc.). Our results show that the compressed deep features extracted from different pre-trained vision models establish new unsupervised learning state-of-the-art performances for the investigated datasets.

Architectural graphics and the experience of space. Freehand drawing and photograph to deepen on communicative qualities in linear perspective

Architecture communication on photo-sharing social networking services like Instagram focuses on photorealism. Meanwhile, the conceptual intention or the experience of the architectural space has less impact in these media. Some architectural graphics techniques are closer to this purpose due to their nature. The main objective is to identify the visual qualities of the architectural space experience from a linear perspective. To do this, the research proposes the design of a visual pattern recognition tool and applies it to pairs of images (photography and drawing) from the same place. The results provide the strategy design based on five variables: the level of human presence, the distortion of perspective, the chromatic distortion, the overlay realism and the emphasis. Finally, the visual summaries lead to values that help to understand the communicative qualities of the experience of space due to their ability to compare main milestones of visual information.

DeepQ Feature Selection and Recognition of Handwritten Prediction Using Convolutional Neural Networks

Purpose: Deep learning (DL) is referred to as the "hot subject" in pattern recognition and machine learning. The unmatched potential of deep learning allows for the resolution of the majority of complex machine learning issues, and it is evident that it will receive attention within the framework for mobile devices. There are tools for pattern recognition that can be used by smart applications of the next generation to make huge changes. Design/Methodology/Approach: The deep feature convolutional network (DEEPQ-CNN) extracts the high representation and features of the hierarchical image from the relevant training data when data-driven learning is enabled. In addition, the DEEPQ-CNN characterization strategies are adapted to a couple of datasets in the boundaries and construction. The running time of the neural network and the network's weight are essential requirements for mobile computing. Finding/Results: In the proposed system, the design of the image processing module is based on the characteristics of a mobile device's convolutional neural network. However, the use of mobile devices for data collection, processing, and construction is described. Last but not least, the computing conditions and mobile device data features are taken into account. Original Value: For optical character recognition (OCR), specific datasets support the lightweight network structure. CNN is utilized to approve the proposed framework when examinations are made with the results of past methods to perceive the optical person. Paper Type: Research

Analyzing abnormal pattern of hotelling [formula omitted] control chart for compositional data using artificial neural networks

Compositional data (CoDa) has been monitored in statistical process monitoring, where multivariate control charts (CCs) such as Hotelling TC2, MEWMA-CoDa, and MCUSUM-CoDa are commonly used to determine if a process is in-control. However, these charts can encounter problems when there is an out-of-control (OOC) process due to various factors such as shifts in variables, outliers, or trends. To address this issue, a pattern recognition (PR) tool using multilayer feed-forward neural networks (MLFFNN) is proposed to accurately recognize CoDa patterns. In the simulation study, six different models in simplex sample space are used to induce trends and shifts in CoDa, and sufficient samples are generated to evaluate the proposed PR model’s performance. The isometric log-ratio (ilr) transformation is applied to CoDa to convert the data from simplex sample space to real space. The Hotelling TC2 statistic is obtained from the generated values after applying the ilr transformation. TC2 statistic is then standardized for MLFFNN, and a back-propagation learning algorithm is used to accurately fit the PR model. Results show the proposed model accurately identifies the CCs pattern, even during OOC processes. A time budget CoDa is analyzed to demonstrate the proposed model’s effectiveness in recognizing patterns.

Morphological assessment of cavitation caused damage of cordierite and zircon based materials using principal component analysis

The pattern recognition approach, explored by this study, applies the principal component analysis (PCA) as the most widely used statistical method with the aim of assessing the initiation and propagation of the cracks and defects that appear on the surface of material exposed to the cavitation. The experiment was performed in four stages: (a) synthesis of two ceramic materials (cordierite and zircon); (b) subjecting the samples to the cavitation; (c) using image analysis software for collecting the data about morphological characteristics that describe defects; (d) principal component analysis as a pattern recognition tool in order to characterize the defects at the material surface. Besides that, according to standard, cavitation erosion was monitored by determining material mass loss during the cavitation. Large experimental datasets collected from morphological descriptors by image analysis are multivariate and difficult to interpret, thus are processed by principal component analysis as the most informative technique for extracting possible differences. The performed approach proved that this method has a great potential for better assessment of induced defects by proper distinguishing among them at different levels and that can be considered a very efficient and cost-effective one.

Pattern Recognition of GC-FID Profiles of Volatile Compounds in Brandy de Jerez Using a Chemometric Approach Based on Their Instrumental Fingerprints

Brandy de Jerez is a unique spirit produced in Southern Spain under Protected Geographical Indication “Brandy de Jerez” (PGI). Two key factors for the production of quality brandies are the original wine spirit and its aging process. They are significantly conditioned by specific variables related to the base wine and the distillation method employed to produce the wine spirit used to obtain a finally aged brandy. This final beverage is therefore strongly influenced by its production process. The chromatographic instrumental fingerprints (obtained by GC FID) of the major volatile fraction of a series of brandies have been examined by applying a chemometric approach based on unsupervised (hierarchical cluster analysis and principal component analysis) and supervised pattern recognition tools (partial least squares–discriminant analysis and support vector machine). This approach was able to identify the fermentation conditions of the original wine, the distillation method used to produce the wine spirit, and the aging process as the most influential factors on the volatile profile.