Pattern Recognition Tools Research Articles

Bridging Classical Methodologies in Salmonella Investigation with Modern Technologies: A Comprehensive Review.

Advancements in genomics and machine learning have significantly enhanced the study of Salmonella epidemiology. Whole-genome sequencing has revolutionized bacterial genomics, allowing for detailed analysis of genetic variation and aiding in outbreak investigations and source tracking. Short-read sequencing technologies, such as those provided by Illumina, have been instrumental in generating draft genomes that facilitate serotyping and the detection of antimicrobial resistance. Long-read sequencing technologies, including those from Pacific Biosciences and Oxford Nanopore Technologies, offer the potential for more complete genome assemblies and better insights into genetic diversity. In addition to these sequencing approaches, machine learning techniques like decision trees and random forests provide powerful tools for pattern recognition and predictive modeling. Importantly, the study of bacteriophages, which interact with Salmonella, offers additional layers of understanding. Phages can impact Salmonella population dynamics and evolution, and their integration into Salmonella genomics research holds promise for novel insights into pathogen control and epidemiology. This review revisits the history of Salmonella and its pathogenesis and highlights the integration of these modern methodologies in advancing our understanding of Salmonella.

Machine-Learning-Assisted Materials Discovery from Electronic Band Structure.

Traditional methods of materials discovery, often relying on intuition and trial-and-error experimentation, are time-consuming and limited in their ability to explore the vast design space effectively. The emergence of machine learning (ML) as a powerful tool for pattern recognition has opened exciting opportunities to revolutionize materials discovery. This work explores the application of ML techniques to assist in the discovery of materials using band structure data. The electronic band structure, which describes the energy levels of electrons in a material, holds vital information regarding its electronic and optical properties. The band structure data of 63,588 materials, including metals and insulators, have been retrieved from the Materials Project database. The data were grouped into 85 batches based on the band path in the first Brillouin zone. Three ML clustering algorithms were trained on the band structure data after performing feature selection and engineering, followed by noise reduction. The models were validated by comparing the materials' properties in a cluster.

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.

Design of a computational intelligence system for detection of multiple sclerosis with visual evoked potentials

In this study, a new approach for modification of membership functions of a fuzzy inference system (FIS) is demonstrated, in order to serve as a pattern recognition tool for classification of patients diagnosed with multiple sclerosis (MS) from healthy controls (HC) using their visually evoked potential (VEP) recordings. The new approach utilizes Krill Herd (KH) optimization algorithm to modify parameters associated with membership functions of both inputs and outputs of an initial Sugeno-type FIS, while making sure that the error corresponding to training of the network is minimized.This novel pattern recognition system is applied for classification of VEP signals in 11 MS patients and 11 HC's. A feature extraction routine was performed on the VEP signals, and later substantial features were selected in an optimized feature subset selection scheme employing Ant Colony Optimization (ACO) and Simulated Annealing (SA) algorithms. This alone provided further information regarding clinical value of many previously unused VEP features as an aide for making the diagnosis. The newly designed computational intelligence system is shown to outperform popular classifiers (e.g., multilayer perceptron, support-vector machine, etc.) and was able to distinguish MS patients from HC's with an overall accuracy of 90%.

Mathematical Analysis of Power Quality Disturbances in Electrical Distribution Systems: Detection, Classification, and Mitigation Strategies

Maintaining a high-quality power source is an important part of modern electricity distribution systems for making sure that many industrial, business, and domestic uses work reliably and efficiently. Power quality disruptions, on the other hand, make this goal much harder to reach. This essay gives a thorough statistical study of power quality problems, focused on how to find them, classify them, and find ways to fix them. The first part of the study talks about how to find power quality problems, which means finding changes in voltage, current, or frequency that don't make sense. Different signal processing methods, like Fourier analysis, wavelet transform, and advanced machine learning algorithms, are tested to see how well they can find and describe different kinds of problems. Second, the paper talks about how to classify power quality problems, which is important for figuring out what causes them and choosing the best ways to fix them. There are different kinds of disturbances, such as voltage sags, swells, interruptions, harmonics, and transients. Each type needs a different way of being analyzed and dealt with. Researchers are looking into whether statistical methods, pattern recognition tools, and artificial intelligence can correctly group events based on their unique features. Lastly, the paper talks about ways to lessen the bad effects of power quality problems on electrical distribution systems and loads that are related to them. These methods include both preventative steps, like making equipment better designed and rearranging networks, and defensive ones, like using active power filters, voltage controls, and energy storage systems. Coordinating spread energy resources with smart grid technologies is also being looked into as a way to make the system more resistant to disruption. In general, the mathematical analysis in this paper gives us useful information about how complicated power quality problems are and gives us a way to find them, sort them into groups, and fix them. Electrical companies, equipment makers, and system workers can come up with better ways to make sure that modern distribution systems have a stable and high-quality power source by using advanced mathematical methods and new technologies.

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.