Pattern Recognition Tools Research Articles

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.

On-chip dielectrophoretic device for cancer cell manipulation: A numerical and artificial neural network study.

Breast cancer, as one of the most frequent types of cancer in women, imposes large financial and human losses annually. MCF-7, a well-known cell line isolated from the breast tissue of cancer patients, is usually used in breast cancer research. Microfluidics is a newly established technique that provides many benefits, such as sample volume reduction, high-resolution operations, and multiple parallel analyses for various cell studies. This numerical study presents a novel microfluidic chip for the separation of MCF-7 cells from other blood cells, considering the effect of dielectrophoretic force. An artificial neural network, a novel tool for pattern recognition and data prediction, is implemented in this research. To prevent hyperthermia in cells, the temperature should not exceed 35 °C. In the first part, the effect of flow rate and applied voltage on the separation time, focusing efficiency, and maximum temperature of the field is investigated. The results denote that the separation time is affected by both the input parameters inversely, whereas the two remaining parameters increase with the input voltage and decrease with the sheath flow rate. A maximum focusing efficiency of 81% is achieved with a purity of 100% for a flow rate of and a voltage of . In the second part, an artificial neural network model is established to predict the maximum temperature inside the separation microchannel with a relative error of less than 3% for a wide range of input parameters. Therefore, the suggested label-free lab-on-a-chip device separates the target cells with high-throughput and low voltages.

Alterations in the Cellular Metabolic Footprint Induced by Mayaro Virus

Mayaro virus is a neglected virus that causes a mild, dengue-like febrile syndrome characterized by fever, headache, rash, retro-orbital pain, vomiting, diarrhea, articular edemas, myalgia, and severe arthralgia, symptoms which may persist for months and become very debilitating. Though the virus is limited to forest areas and is most frequently transmitted by Haemagogus mosquitoes, Aedes mosquitoes can also transmit this virus and, therefore, it has the potential to spread to urban areas. This study focuses on the metabolic foot-printing of Vero cells infected with the Mayaro virus. Nuclear magnetic resonance combined with multivariate analytical methods and pattern recognition tools found that metabolic changes can be attributed to the effects of Mayaro virus infection on cell culture. The results suggest that several metabolite levels vary in infection conditions at different time points. There were important differences between the metabolic profile of non-infected and Mayaro-infected cells. These organic compounds are metabolites involved in the glycolysis pathway, the tricarboxylic acid cycle, the pentose phosphate pathway, and the oxidation pathway of fatty acids (via β-oxidation). This exometabolomic study has generated a biochemical profile reflecting the progressive cytopathological metabolic alterations induced by Mayaro virus replication in the cells and can contribute to the knowledge of the molecular mechanisms involved in viral pathogenesis.

Recovery of Biologically Active Compounds from Stinging Nettle Leaves Part II: Processing of Exhausted Plant Material after Supercritical Fluid Extraction

Stinging nettle (Urtica dioica L.) is one fantastic plant widely used in folk medicine, pharmacy, cosmetics, and food. This plant's popularity may be explained by its chemical composition, containing a wide range of compounds significant for human health and diet. This study aimed to investigate extracts of exhausted stinging nettle leaves after supercritical fluid extraction obtained using ultrasound and microwave techniques. Extracts were analyzed to obtain insight into the chemical composition and biological activity. These extracts were shown to be more potent than those of previously untreated leaves. The principal component analysis was applied as a pattern recognition tool to visualize the antioxidant capacity and cytotoxic activity of extract obtained from exhausted stinging nettle leaves. An artificial neural network model is presented for the prediction of the antioxidant activity of samples according to polyphenolic profile data, showing a suitable anticipation property (the r2 value during the training cycle for output variables was 0.999).

Использование персистентной энтропии для топологического анализа данных

Persistent homology and persistent entropy have recently become useful tools for pattern recognition. In the paper, requirements are found under which the persistent entropy is stable to small perturbations of the input data and is scale invariant. Stable summary functions are described that combine the persistent entropy and the Betti curve.

Transformation of PET raw data into images for event classification using convolutional neural networks.

In positron emission tomography (PET) studies, convolutional neural networks (CNNs) may be applied directly to the reconstructed distribution of radioactive tracers injected into the patient's body, as a pattern recognition tool. Nonetheless, unprocessed PET coincidence data exist in tabular format. This paper develops the transformation of tabular data into n-dimensional matrices, as a preparation stage for classification based on CNNs. This method explicitly introduces a nonlinear transformation at the feature engineering stage and then uses principal component analysis to create the images. We apply the proposed methodology to the classification of simulated PET coincidence events originating from NEMA IEC and anthropomorphic XCAT phantom. Comparative studies of neural network architectures, including multilayer perceptron and convolutional networks, were conducted. The developed method increased the initial number of features from 6 to 209 and gave the best precision results (79.8) for all tested neural network architectures; it also showed the smallest decrease when changing the test data to another phantom.

Neutrosophic-based Machine Learning Techniques in the Context of Supply Chain Management: A Survey

Supply Chain Management (SCM) plays a critical role in the success of any business organization. Individuals involved in business activities often have to make decisions regarding different aspects of the supply chain, including planning, procurement, production, inventory management, transportation, distribution, and customer relationship management. The combination of neutrosophic logic and machine learning has gained significant attention in the field of SCM as a means to tackle uncertainties and improve decision-making. This paper highlights the potential benefits and applications of integrating neutrosophic reasoning and machine learning in SCM. Neutrosophic reasoning provides a framework for handling imprecise and uncertain information, while machine learning techniques offer powerful tools for data analysis, pattern recognition, and predictive modeling. By leveraging machine learning algorithms within the context of neutrosophic logic, SCM practitioners can enhance demand forecasting accuracy, optimize inventory management, improve transportation and routing decisions, and strengthen supply chain collaboration. The integration of neutrosophic logic and machine learning enables the handling of complex supply chain data, accommodates dynamic and uncertain environments, and supports proactive decision-making. Furthermore, the combination of these approaches can contribute to improved supply chain resilience, sustainability, and customer satisfaction. This paper applied the neutrosophic AHP method as a feature section to select the highest importance criteria as an input to machine learning. Then we applied two machine learning models named random forest and decision. The results show the random forest has the highest accuracy followed by a decision tree.

A Novel Feature Selection Strategy Based on Salp Swarm Algorithm for Plant Disease Detection

Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition. However, it has limited interpretability for deep features. With the transfer of expert knowledge, handcrafted features provide a new way for personalized diagnosis of plant diseases. However, irrelevant and redundant features lead to high dimensionality. In this study, we proposed a swarm intelligence algorithm for feature selection [salp swarm algorithm for feature selection (SSAFS)] in image-based plant disease detection. SSAFS is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of features. To verify the effectiveness of the developed SSAFS algorithm, we conducted experimental studies using SSAFS and 5 metaheuristic algorithms. Several evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from PlantVillage. Experimental results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms, confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image classification. This computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.

Identification of Paddy Rice Diseases Using Deep Convolutional Neural Networks

In modern digital agricultural applications, automatic identification and diagnosis of plant diseases using artificial intelligence is becoming popular and widespread. Deep learning is a promising tool in pattern recognition and machine learning and it can be used to identify and classify diseases in paddy rice. In this study, 2 different paddy rice diseases, including rice blast and brown spot, were investigated in the district of İpsala in the province of Edirne between the 2020 and 2021 production seasons by collecting 1569 images. These diseases are very common and important in Edirne province and surrounding rice production areas. Therefore, practical methods are needed to identify and classify these two diseases. A Convolutional Neural Network (CNN) model was created by applying pre-processing techniques such as rescaling, rotation, and data augmentation to the paddy rice disease images. The classification model was created in Google Colab, which is a web-based Python editor using Tensorflow and Keras libraries. The CNN model was able to classify rice blast and brown spot diseases with high accuracy of 91.70%.

Intellectualization of Moving Transport Objects Recognition

The purpose of the article is to research, analyze, and consider current problems and prospects for the development of software for the recognition of transport objects based on the use of pattern recognition theory, methods, and tools of artificial intelligence, and different types of neural networks.
 The research methodology is basic methods and algorithms of pattern recognition, methods and means of artificial intelligence, and different types of neural networks. The article considers the main problems of intellectualization of processes occurring in transport. The main attention is paid to the intellectualization of the processes of transport objects’ recognition. The article analyzes the most common recognition methods. A study of these methods and approaches to the recognition of moving vehicles is conducted. It is determined which methods have high and which have low computational complexity. Among the considered methods are those that recognize static transport objects (primarily transport infrastructure objects) using intelligent technologies, statistical, probabilistic, and other methods. The main attention is paid to methods that recognize dynamic transport objects. The basis of intellectualization of the processes of recognition of this group of objects is the use of neural networks, in particular convolutional, recurrent, neural networks with long short-term memory (LSTM), etc.
 The scientific novelty of the research is the analysis of modern methods of moving transport objects’ recognition, the results of which can be used in the development of their software product. The article emphasizes that the proposed modern approach to the recognition of transport objects (moving vehicles and transport infrastructure) involves solving a wide range of problems based on the use of intelligent technologies, in particular neural networks.
 Conclusions. The most common methods for solving current problems of recognition of transport objects (vehicles and transport infrastructure) have been investigated and analyzed. Based on the analysis of methods for recognizing moving vehicles, it has been determined which methods have high and low computational complexity. The basis of the intellectualization of the recognition processes for this group of transport objects is the use of various neural networks.

A machine learning attack on illegal trading

We design an adaptive framework for the detection of illegal trading behavior. Its key component is an extension of a pattern recognition tool, originating from the field of signal processing and adapted to modern electronic systems of securities trading. The new method combines the flexibility of dynamic time warping with contemporary approaches from extreme value theory to explore large-scale transaction data and accurately identify illegal trading patterns. Importantly, our method does not need access to any confirmed illegal transactions for training. We use a high-frequency order book dataset provided by an international investment firm to show that the method achieves remarkable improvements over alternative approaches in the identification of suspected illegal insider trading cases.

Kernel embedding transformation learning for graph matching

• Developing a kernel embedding transformation learning model for graph matching. • Combining the kernelized unary alignment and local structure alignment into a joint framework. • Proposing an effective optimization algorithm to solve the joint framework. • Improving the matching performance significantly in the graph matching tasks with deformation and rotation variations. Graph matching , which aims to establish correspondences between two geometrical graphs, is a general and powerful tool for pattern recognition and computer vision . However, many factors degrade the matching accuracy. The graph structure suffering from deformation and rotation variations is a key issue in the process of matching. In this work, we propose a joint framework in the reproducing kernel Hilbert space (RKHS) for graph matching with deformation and rotation variations, which incorporates the kernelized unary alignment and local structure alignment into a joint framework. Specifically, the proposed method is able to enhance the node to node correspondence and the edge to edge correspondence and avoids the effect of deformation and rotation by maximizing the similarities between the source graph and the transformed target graph in the reproducing kernel Hilbert space. Meanwhile, an effective algorithm is presented to solve the joint framework. Comprehensive discussion, involving convergence analysis and parameter sensitive analysis , are as well proposed. Promising experimental results in the variety of graph matching tasks such as deformation and rotation are provided to evidence the superiority of the proposed method.

Down Syndrome Detection Through Graphical Analysis of Facial Dysmorphic Features in Newborn Children With Ethnicity/Racial Slicing: An AI/ML-Based Approach

Background Down syndrome (DS) is associated with high mortality in India, due to nondiagnosis/late-diagnosis caused by unavailability of qualified doctors and/or lack of access to expensive medical/diagnostic facilities, especially in rural India. Using artificial intelligence/machine learning graphical pattern recognition tools, relevant facial points can be extracted from children’s photographs, facial anomalies can be identified, and probability of DS affliction can be predicted. Methods: Trained Google’s Cloud Vision AutoML Image Classification model was employed with ~2,000 photographs of DS positive children and ~3,000 photographs of DS negative children. A subset of 300 images, 100 each of Asian, Caucasian, and Other-Race children, was used to train and test 3 race-specific models. These results were compared against a unified model trained and tested with same 300 images. Results: The CloudML model trained with ~5,000 images initially achieved: Sensitivity—94.6%, specificity—96.9%, and accuracy—96.0%. Upon optimizing confidence threshold to 0.1, model maximized sensitivity at 99.6%, specificity dropped to 93.8%, and accuracy maintained at 96.0%. Each of the race-specific models trained with 100 images each, after optimization, yielded perfect scores on sensitivity, specificity, and accuracy of 100% each. Against this, the unified model with 300 images yielded overall accuracy of 98% (100% sensitivity, 83% specificity for Caucasian children, and 100% sensitivity, 100% specificity for Asian/Other children). Conclusions: Post optimization, this model can be used as an effective postnatal screening tool for DS detection. Preliminary results indicate that race-specific models can achieve even higher accuracy, sensitivity, and specificity.

HighMLR: An open-source package for R with machine learning for feature selection in high dimensional cancer clinical genome time to event data

Machine learning techniques, popularly used as a tool for dimensionality reduction and pattern recognition of features, have been utilized extensively in data mining. In survival analysis, where the primary outcome is the time until a specific event occurs, identifying relevant features for building an efficient prediction model is essential. This is where machine learning can be a suitable option. However, there is an existing gap in utilizing machine learning techniques in high-dimensional survival data due to the non-availability of convenient programming functions and packages. In this article, we have developed an efficient machine learning procedure for analyzing survival data associated with high-dimensional gene expressions. Though there are several R libraries available for performing machine learning, no package support is available to implement machine learning with classification on high-dimensional survival data. highMLR, our developed R package, is capable of implementing machine learning methods on high dimensional survival data and provides a way of feature selection based on the logarithmic loss function. Several statistical methods for survival analysis have been incorporated into this machine learning algorithm. A high-dimensional gene expression dataset has been analyzed using the proposed R library to show its efficacy in feature selection.

Valorization of avocado seeds with antioxidant capacity using pressurized hot water extraction

The pulp of avocado (Persea Americana) is widely consumed as the primary food source, while the seed is often discarded as food waste. Increased consumption of avocado would inevitably results in production of waste by-products such as avocado seeds, hence the ability to extract phytochemicals from such waste, and upcycling to potential nutraceutical products is of great interest. The overall aim of this study is to explore avocado seeds as potential functional food through the combined use of a green extraction method, chemical standardization and pattern recognition tools, and biological characterization assays. Specifically, this study utilized an organic solvent-free extraction method, pressurized hot water extraction (PHWE) to extract phytochemicals from avocado seeds and liquid chromatography mass spectrometry (LCMS) was used to identify the phytochemicals present in the avocado seeds. Our results demonstrated that avocado seed extracts have antioxidant activity and inhibited oxidative stress-induced metabolomics changes in endothelial cells, suggesting that avocado seed extracts have vasoprotective actions.

Multi-Chain Semi-Markov Analysis of Intrapartum Cardiotocography.

Visual assessment of the evolution of fetal heart rate (FHR) and uterine pressure (UP) patterns is the standard of care in the intrapartum period. Unfortunately, this assessment has high levels of intra- and inter-observer variability. This study processed and analyzed FHR and UP patterns using computerized pattern recognition tools. The goal was to evaluate differences in FHR and UP patterns between fetuses with normal outcomes and those who developed hypoxic-ischemic encephalopathy (HIE). For this purpose, we modeled the sequence of FHR patterns and uterine contractions using Multi-Chain Semi-Markov models (MCSMMs). These models estimate the probability of transitioning between FHR or UP patterns and the dwell time of each pattern. Our results showed that in comparison to the control group, the HIE group had: (1) more frequent uterine contractions during the last 12 hours before birth; (2) more frequent FHR decelerations during the last 12 hours before birth; (3) longer decelerations during the last eight hours before birth; and (4) shorter baseline durations during the last five hours before birth. These results demonstrate that the fetuses in the HIE group were subject to a more stressful environment than those in the normal group. Clinical Relevance- Our results revealed statistically significant differences in FHR/UP patterns between the normal and HIE groups in the hours before birth. This indicates that features derived using MCSMMs may be useful in a machine learning framework to detect infants at increased risk of developing HIE allowing preventive interventions.

(Digital Presentation) Data-Driven Prognosis of Battery Failure Detection and Prediction

Although the electric vehicle market is witnessing an unprecedented evolution, the fast adoption of these vehicles requires a more thorough status analysis of the battery performance's functionality and reliability. Due to their rechargeable nature, Lithium-ion batteries (LIBs) operation is subject to different irreversible processes during their charging and discharging cycles and causing capacity fade due to various degradation mechanisms. These processes generally result in battery capacity degradation, which usually results in battery failure, with consequences ranging from loss of operation, reduced capability, downtime, and catastrophic malfunctions. To address the issues mentioned above, numerous studies have been dedicated to proposing proper degradation model mechanisms for improving the reliability and availability of LIBs. However, due to accuracy and computational complexity challenges, most existing remaining useful life (RUL) and health prediction models focus on special degradation effects and ignore the integrated deterioration mechanisms, which generally involve batteries' capacity fade associated with the inadequacy of current health estimation tools. Thus, these shortcomings ultimately echo the need to devise novel tools to identify the dominant criteria negatively affecting battery performance and accurately predict the system's failure. The above challenges eventually necessitate a robust and reliable predictive or prognostic capability for prognostics and health monitoring (PHM) under a complexly hostile working environment. In this context, this investigation aims at proposing a novel data-driven approach called data-driven prognosis (DDP) that estimates the relevant constitutive parameters in situ and captures deviations from the expected degradation dynamics of the LIBs in addition to precise modeling of the degradation and capacity models. This talk will present a new data-driven approach using statistical pattern recognition and machine learning tools to detect batteries' anomalies and failures.

Design of a high-tech system to evaluate fresh strawberry quality-based on the principal component analysis

This study was designed to investigate the differences in the physicochemical properties among twelve strawberry cultivars by using pattern recognition tools, to provide a theoretical basis for quality variation among samples. The data of 14 indicators were subjected to principal component analysis (PCA), descriptive statistical analysis, correlation analysis, and hierarchical cluster analysis, to filter core evaluation factors. Quality evaluation index weights and quality comprehensive evaluation were determined by an analytic hierarchy process. Of the 14 indicators selected as indices of fresh strawberry quality evaluation index, including a value, sugar-acid ratio, firmness, vitamin C, TAC, and TPC. The data were deployed to adjust the multivariate kinetics using Analytic Hierarchy Process (AHP), and the results were compared to those sensory score using sensory personnel. Results showed that the correlation coefficient of sensory scores and AHP comprehensive score is 0.9239. This high correlation coefficient indicates that the use of our mathematical model for strawberry quality evaluation is feasible. The information herein provides a practical strategy for the evaluation of strawberry quality.