Pattern Recognition Techniques Research Articles

New 2D joint roughness profiles based on pattern recognition technique

New 2D joint roughness profiles based on pattern recognition technique

Nondestructive Metabolomic Fingerprinting: FTIR, NIR and Raman Spectroscopy in Food Screening

In recent years, there has been renewed interest in the maintenance of food quality and food safety on the basis of metabolomic fingerprinting using vibrational spectroscopy combined with multivariate chemometrics. Nontargeted spectroscopy techniques such as FTIR, NIR and Raman can provide fingerprint information for metabolomic constituents in agricultural products, natural products and foods in a high-throughput, cost-effective and rapid way. In the current review, we tried to explain the capabilities of FTIR, NIR and Raman spectroscopy techniques combined with multivariate analysis for metabolic fingerprinting and profiling. Previous contributions highlighted the considerable potential of these analytical techniques for the detection and quantification of key constituents, such as aromatic amino acids, peptides, aromatic acids, carotenoids, alcohols, terpenoids and flavonoids in the food matrices. Additionally, promising results were obtained for the identification and characterization of different microorganism species such as fungus, bacterial strains and yeasts using these techniques combined with supervised and unsupervised pattern recognition techniques. In conclusion, this review summarized the cutting-edge applications of FTIR, NIR and Raman spectroscopy techniques equipped with multivariate statistics for food analysis and foodomics in the context of metabolomic fingerprinting and profiling.

Developing a Neural Network-based Model for Identifying Medicinal Plant Leaves using Image Recognition Techniques

Herbal plants play a vital role in human health and the environment, as they can provide both medical benefits and oxygen. Many herbal plants contain valuable therapeutic elements that can be passed down to future generations. Traditional methods of identifying plant species, such as manual measurement and examination of characteristics, are labor-intensive and time-consuming. There has been a push to develop more efficient methods using technology, such as digital image processing and pattern recognition techniques to address this. The proper identification of plant methods using computer vision and neural network techniques has been proposed. This approach involves neural network models such as CNN, ALexnet and ResNet for identifying the medical plants based on their respective features. Classification metrics give the 96.82 average accuracies. These results have been promising, and further research will involve using a larger dataset and going more into deep-learning neural networks to improve the accuracy of medicinal plant identification. It is hoped that a web or mobile-based system for automatic plant identification can help increase knowledge about medicinal plants, improve species identification techniques, and protect endangered species.

DegronMD: Leveraging Evolutionary and Structural Features for Deciphering Protein-Targeted Degradation, Mutations, and Drug Response to Degrons.

Protein-targeted degradation is an emerging and promising therapeutic approach. The specificity of degradation and the maintenance of cellular homeostasis are determined by the interactions between E3 ubiquitin ligase and degradation signals, known as degrons. The human genome encodes over 600 E3 ligases; however, only a small number of targeted degron instances have been identified so far. In this study, we introduced DegronMD, an open knowledgebase designed for the investigation of degrons, their associated dysfunctional events, and drug responses. We revealed that degrons are evolutionarily conserved and tend to occur near the sites of protein translational modifications, particularly in the regions of disordered structure and higher solvent accessibility. Through pattern recognition and machine learning techniques, we constructed the degrome landscape across the human proteome, yielding over 18,000 new degrons for targeted protein degradation. Furthermore, dysfunction of degrons disrupts the degradation process and leads to the abnormal accumulation of proteins; this process is associated with various types of human cancers. Based on the estimated phenotypic changes induced by somatic mutations, we systematically quantified and assessed the impact of mutations on degron function in pan-cancers; these results helped to build a global mutational map on human degrome, including 89,318 actionable mutations that may induce the dysfunction of degrons and disrupt protein degradation pathways. Multiomics integrative analysis unveiled over 400 drug resistance events associated with the mutations in functional degrons. DegronMD, accessible at https://bioinfo.uth.edu/degronmd, is a useful resource to explore the biological mechanisms, infer protein degradation, and assist with drug discovery and design on degrons.

Developing A Neural Network-Based Model for Identifying Medicinal Plant Leaves Using Image Recognition Techniques

Herbal plants contribute an important role in people's health and the environment, as they can provide both medical benefits and oxygen. Many herbal plants contain valuable therapeutic elements that can be passed down to future generations. Traditional methods of identifying plant species, such as manual measurement and examination of characteristics, are labor-intensive and time-consuming. To address this, there has been a push to develop more efficient methods using technology, such as digital image processing and pattern recognition techniques. The exact recognition of plants uses methodologies like computer vision and neural networks, which have been proposed earlier. This approach involves neural network models such as CNN, ALexnet, and ResNet for identifying the medical plants based on their respective features. Classification metrics give the 96.82 average accuracies. These results have been promising, and further research will involve using a larger dataset and going more into deep-learning neural networks to improve the accuracy of medicinal plant identification. It is hoped that a web or mobile-based system for automatic plant identification can help increase knowledge about medicinal plants, improve techniques for species recognition, and participate in the preservation of species that are considered ad endangered.

Classification of sugar using digital imaging and pattern recognition techniques

This work presents a new analytical methodology based on the use of digital images and multivariate analysis for the classification of sugar samples based on their color. Two studies were evaluated. The first involved the discrimination of refined (RS) and unrefined sugar (US) samples. The second study involved the classification of sugar samples into three different classes: refined sugar for the external market (EMRS); refined sugar for retail (RRS); and US. The frequency distribution of color indices in the red, green, blue, hue, saturation, intensity, and grayscale channels were obtained from digital images. Classification models based on partial least squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) were developed. The best results obtained for the studies with two (97.4 % accuracy) and three (95.7 % accuracy) classes were achieved by applying the genetic algorithm (GA) in association with the linear discriminant analysis (GA-LDA) on the datasets. The proposed method offers several advantages, including low cost, simplicity, absence of chemical reagents, and non-destructiveness of the sample.

Applying Deep Learning and Machine Learning Algorithms for The Identification of Medicinal Plant Leaves Based on Their Spectral Characteristics

The study and consideration of medicinal plants have been ongoing throughout history due to their significant role in maintaining the well-being of mammals. Although identifying medicinal plants can be a valuable skill, it is often time-consuming, tedious, and requires the expertise of a specialist. The project works on the technique of image processing, which identifies the various medicinal plants. There has been a strong emphasis on improving efficiency through the application of technology, with a focus on incorporating digital image processing and pattern recognition techniques. To ensure accurate plant identification, proposals involving the application of computer vision neural network techniques have been advanced. This approach involves neural network models such as CNN, SVM, KNN, and Navie Bay for identifying the medical plants based on their respective features. After the validation step, the project provides a classification of 92.3 precision and 90.56 F1 score.

Connecting Obsidian Artifacts with Their Sources Using Multivariate Statistical Analysis of LIBS Spectral Signatures

With the recent introduction of handheld instruments for field use, laser-induced breakdown spectroscopy (LIBS) is emerging as a practical technology for real-time in situ geochemical analysis in the field. LIBS is a form of optical emission spectroscopy that is simultaneously sensitive to all elements with a single laser shot so that a broadband LIBS spectrum can be considered a diagnostic geochemical fingerprint. Sets of LIBS spectra were collected for seven obsidian centers across north-central California, with data processed using multivariate statistical analysis and pattern recognition techniques. Although all obsidians exhibit similar bulk compositions, different regional obsidian sources were effectively discriminated via partial least squares discriminant analysis. Obsidian artifacts from seven archaeological sites were matched to their putative sources with a high degree of confidence.

English language analysis using pattern recognition and machine learning

Pattern identification and classification in complicated systems are difficult. This study uses optical character recognition (OCR) to digitize handwritten data. OCR segments and categorizes characters using online and offline methods for different input sources. Hindi and Bangladeshi categorization results unite linguistic studies. Handwriting recognition systems create editable digital documents from touchscreens, electronic pens, scanners, and photographs. Statistical, structural, neural network and syntactic methods improve online and offline recognition. In “english language analysis using pattern recognition and machine learning,” the accuracy of various approaches is examined, showing deep convolution neural networks (DCNN) 98% accuracy in recognizing subtle linguistic patterns. Nave Bayes, a trustworthy language analysis approach, has 96.2% accuracy. Table recognition (TR) algorithms retrieve structured information at 97%. This method outperforms others with 98.4% accuracy. This unique strategy could improve english language analysis using cutting-edge pattern recognition and machine learning techniques.

A single recognition unit-based virtual sensor Array: Applying 3D fluorescence spectroscopy to inner filter effect-based sensing

A convenient, fast, low-cost detection and discrimination method is demanded for environmental monitoring but still it remains more technological challenges. Herein, we demonstrate that the inner filter effect (IFE), in combination with three-dimensional fluorescence spectroscopy, can offer a virtual sensor array (VSA) as apropersolution. And with the aid of pattern recognition techniques, it is feasible to recognize compounds with structural similarities economically and effectively. In this study, with the help of visual clustering plots of principal component analysis (PCA), a prediction model based on hierarchical strategy was made using support vector machine (SVM) method for the qualitative profiling of aromatic pollutants. The VSA was constructed by a single metal–organic framework (MOF) recognition unit (MOF-74 (Zn)) with the excitation wavelength as external regulatory factors. Pattern characteristics of four aromatics with very similar structures (phenylamine, chlorobenzene, nitrobenzene, and phenol), both single analyte and binary mixtures, were acquired. The primary constituents of multi-dimensional spectral signals were subsequently extracted and fed into a vector machine to construct a prediction model through 10-fold cross-validation optimization, resulting in a classification accuracy of 100% for single analytes and 96% for mixtures. Quantitative research has shown that, except for chlorobenzene, all three other analytes can be predicted in concentration within an acceptable error range, and the mixture can be predicted proportionally. Moreover, the VSA can be used to distinguish these pollutants in tap and river water also. We propose for the first time a new tack for the construction of VSA in a general manner, namely using three-dimensional full range fluorescence scanning for IFE based sensing to get multiple times of information resulting from different weak interaction between analyte and sensor for decision-making.

Artificial Olfactory System for Distinguishing Oil-Contaminated Soils

Oil-contaminated soils are a major environmental problem for Kazakhstan. Oil spills or leaks lead to profound changes in the physical and agrochemical properties of the soil and the accumulation of hazardous substances. Whilst there are many remote sensing techniques and complex laboratory methods for oil spill detection, developing simple, reliable, and inexpensive tools for detecting the presence of pollutants in the soil is a relevant research task. The study aims to research the possibilities of an electronic nose combining a chemical sensor array with pattern recognition techniques to distinguish volatile organic compounds from several types of hydrocarbon soil pollutants. An electronic nose system was assembled in our laboratory. It includes eight gas metal oxide sensors, a humidity and temperature sensor, an analog-digital processing unit, and a data communication unit. We measured changes in the electrical conductivity of sensors in the presence of volatile organic compounds released from oil and petroleum products and samples of contaminated and uncontaminated soils. The list of experimental samples includes six types of soils corresponding to different soil zones of Kazakhstan, crude oil from three oil fields in Kazakhstan, and five types of locally produced fuel oil (including gasoline, kerosene, diesel fuel, engine oil, and used engine oil). We used principal component analysis to statistically process multidimensional sensor data, feature extraction, and collect the volatile fingerprint dataset. Pattern recognition using machine learning algorithms made it possible to classify digital fingerprints of samples with an average accuracy of about 92%. The study results show that electronic nose sensors are sensitive to soil hydrocarbon content. The proposed approach based on machine olfaction is a fast, accurate, and inexpensive method for detecting oil spills and leaks, and it can complement remote sensing methods based on computer vision.

Damage pattern recognition for corroded beams strengthened by CFRP anchorage system based on acoustic emission techniques

This study presents a damage pattern recognition approach for corroded steel beams strengthened by CFRP anchorage system based on acoustic emission clustering analysis. The proposed method includes four steps: acoustic emission signal acquisition, feature extraction, clustering analysis, and damage pattern recognition. Four corroded beams with different corrosion levels and strengthening schemes were tested under four-point bending loading. The acoustic emission signals were collected during the loading process and analyzed using Gaussian mixture model clustering method. The results showed that the collected AE data were analyzed using clustering analysis, successfully distinguishing the distinct damage patterns associated with each mode. The AE signals exhibited distinct characteristics for different damage modes: concrete matrix damage had high-frequency and low-energy characteristics, CFRP-matrix debonding showed intermediate values for all parameters, and CFRP tearing had longer durations, lower peak frequencies, and high-energy characteristics. Besides, the study identified three stages of the damage process: an initial stage with fewer low-intensity AE signals, a damage development stage characterized by an increase in concrete-matrix damage and CFRP – matrix debonding signals, and a continuous damage growth stage with significant AE signals associated with three damage modes. Furthermore, the degree of corrosion significantly influenced the cumulative AE energy of damage modes. Lower degrees of corrosion led to higher cumulative energy from concrete matrix damage and CFRP-matrix debonding. These findings provide valuable insights for understanding the damage evolution and failure mechanisms of CFRP-strengthened corroded beams. The use of AE techniques for damage pattern recognition can enhance the evaluation and design of CFRP anchorage systems, leading to more effective rehabilitation strategies for corroded structures.

Predictive hierarchical eco-driving control involving speed planning and energy management for connected plug-in hybrid electric vehicles

The connected vehicle technique has offered great opportunities to improve further plug-in hybrid electric vehicles (PHEVs) fuel economy. In this context, a predictive hierarchical eco-driving control scheme is proposed for connected PHEVs under a car-following scenario containing a cloud-layer speed planner and vehicle-layer energy management. In the cloud layer, based on the traffic data separately processed by the dynamic programming (DP) algorithm and k-means clustering method, the reference state of charge (SOC) model, the energy consumption model, the equivalent factor model and the variable-horizon speed predictor can be constructed, respectively. And for ensuring safety, comfort and fuel economy in the car-following process, the energy and SOC models are used separately as the index and state equation in the data-driven speed planning problem. Then, with the driving pattern recognition technique, the power allocation under the planned speed can be conducted by integrating the adaptive equivalent consumption minimization strategy (ECMS) with the model predictive control (MPC), thus guaranteeing fuel economy, adaptability and near-global optimality with high computational efficiency. Compared with other strategies, the effectiveness and advantages of the proposed scheme are validated in the joint simulation platform of MATLAB/Simulink and GT-SUITE.

AI-Infused Algorithmic Trading: Genetic Algorithms and Machine Learning in High-Frequency Trading

In this research we explore the transformative impact of Artificial Intelligence (AI) and Genetic Algorithms (GAs) in the context of algorithmic trading, with a specific focus on High-Frequency Trading (HFT). Algorithmic trading has gained prominence for its automated execution of predefined strategies, and HFT, with its lightning-fast trades, has reshaped financial markets. Leveraging the power of AI and GAs, traders can now make data-driven decisions and optimize strategies like never before. We delve into the theory and principles of GAs, representing trading strategies as chromosomes and using fitness functions for evaluation. Moreover, we highlight practical applications, including strategy optimization, parameter tuning, and portfolio allocation. The role of AI techniques, such as machine learning and deep learning, is explored in market prediction and risk management, enabling real-time assessment and adaptive trading. Additionally, AI-driven pattern recognition techniques offer insights into market anomalies. We discuss the strategic importance of AI in market making and address challenges, such as latency and ethical considerations. Empirical analysis and case studies provide evidence of GA performance and successful AI-driven trading strategies. Looking ahead, we explore emerging AI techniques and potential advancements, emphasizing the significance of continuous exploration to shape the future of algorithmic trading in financial markets.

Big data analytics for mining geochemistry of gold mineralization: The Gandy gold deposit, the Toroud-Chah Shirin (TCS) belt, north Iran

Due to the complexity of the gold element, the mineralogical and geochemical investigations are significant to trace the gold behavior in sedimentary, metamorphic, magmatic, and post-magmatic processes and to identify the physicochemical conditions (i.e., pH, Eh, temperature, pressure) of concentration in the ore bodies. The trace elements may be concentrated as the primary or secondary haloes in endogenic and exogenic deposits with multi-formational types. Identification and separation of multi-formational geochemical halos associated with ore bodies have been the most significant challenge of gold deposits. Mining Geochemistry and Big Data analytics have become essential to identify the multi-formational geochemical anomalies for gold exploration in the Commonwealth of Independent States (CIS) countries. During the last three decades, pattern recognition techniques such as Bayesian and Geochemical spectra have been used to determine mineralogical and geochemical types of multi-formational anomalies. Big Data analytics has been used for integrating multi-type geoscience data and pattern recognition techniques to assess geochemical anomalies. In this study, Big Data analytics were used to generate the mineralogical and geochemical type (MGT) quantitative models based on the Bayesian, geochemical spectrum and hybrid methods for investigating the distribution of trace element contents of pyrite, galena, and sphalerite in the Gandy Gold Deposit, the Toroud-Chah Shirin (TCS) belt, north Iran. The multi-formational geochemical anomalies associated with gold mineralization in the Gandy deposit indicated a multi-MGT anomaly superposition, which is a combination of two MGTs: Au + Polymetals and Au + sulfide. The results of this study demonstrated a new perspective on the distribution of geochemical anomalies and the multi-MGT geochemical modeling for gold exploration in the TCS belt. Consequently, the instigated approach is greatly conceivable and applicable to reveal contrasting near-ore multi-formational geochemical haloes for gold exploration in many other metallogenic provinces.

Parasitic egg recognition using convolution and attention network

Intestinal parasitic infections (IPIs) caused by protozoan and helminth parasites are among the most common infections in humans in low-and-middle-income countries. IPIs affect not only the health status of a country, but also the economic sector. Over the last decade, pattern recognition and image processing techniques have been developed to automatically identify parasitic eggs in microscopic images. Existing identification techniques are still suffering from diagnosis errors and low sensitivity. Therefore, more accurate and faster solution is still required to recognize parasitic eggs and classify them into several categories. A novel Chula-ParasiteEgg dataset including 11,000 microscopic images proposed in ICIP2022 was utilized to train various methods such as convolutional neural network (CNN) based models and convolution and attention (CoAtNet) based models. The experiments conducted show high recognition performance of the proposed CoAtNet that was tuned with microscopic images of parasitic eggs. The CoAtNet produced an average accuracy of 93%, and an average F1 score of 93%. The finding opens door to integrate the proposed solution in automated parasitological diagnosis.

PENERAPAN ALGORITMA C4.5 DALAM MENGUKUR TINGKAT KEPUASAN NASABAH PADA PT BANK MUAMALAT INDONESIA KCU MEDAN BARU BERBASIS WEB

In the field of service providers, sharia banking and conventional banking have differences in their characteristics which lie in the practice of running business operations, where operations are based on sharia principles, and this principle is the main attraction for customers to utilize sharia bank services. Quality of service is a key factor that will become a competitive advantage in today's banking world. This happens because the bank as a service company has the characteristic of being easy to imitate a product that has been marketed. The measurement method for determining customer satisfaction at Bank Muamalat is by applying data mining, where customer data that makes transactions will be inputted into the system and then processed using the C4.5 method with predetermined criteria. Data mining is a process of finding meaningful relationships, patterns and trends by examining large sets of data stored in storage using pattern recognition techniques. According to Algorithm C4.5 is an algorithm used to form a decision tree.

Trading rule discovery using technical analysis and a template matching technique for pattern recognition: Evidence from the Chinese stock market

AbstractThis paper examines the potential profit of bull flag trading rules in the Shangai Stock Exchange Composite Index (SSE) using a template matching technique based on price pattern recognition. This paper fills a gap in the literature by applying a template matching technique for the recognition of bull flag patterns in the Shangai Stock Exchange Composite Index (SSE) during the period of 1991–2021. To the best of our knowledge, no previous study has applied bull flag trading rules to the Chinese stock market. Our results indicate that bull flag trading rules can correctly predict the price movement direction of the index most of the time, achieving significantly positive excess profits. Moreover, shorter fitting windows and better quality of price fit values for lower holding periods are associated with better performance. This research may have relevant practical implications for investors who opt for this indicator in their asset allocation decisions.

Multiplexed Gas Sensor: Fabrication Strategies, Recent Progress, and Challenges.

Due to miscellaneous toxic gases in the vicinity, there is a burgeoning need for advancement in the existing gas sensing technology not only for the survival of mankind but also for the industries based in various fields such as beverage, forestry, health care, environmental monitoring, agriculture, and military security. A gas sensor must be highly selective toward a specific gas in order to avoid incorrect signals while responding to nontarget gases. This may lead to complex scenarios depicting sensor defects, such as low selectivity and cross-sensitivity. Therefore, a multiplex gas sensor is required to address the problems of cross selectivity by combining different gas sensors, signal processing, and pattern recognition techniques along with the currently employed gas sensing technologies. The different sensing materials used in these sensor arrays will produce a unique response signal for developing a set of identifiers as the input that can be used to recognize a specific gas by its "fingerprint". This review provides a comprehensive review of chemiresistive-based multiplex gas sensors, including various fabrication strategies from expensive to low-cost techniques, advances in sensing materials, and a gist of various pattern recognition techniques used for both rigid and flexible gas sensor applications. Finally, the review assesses the current state-of-the-art in multiplex gas sensor technology and discusses various challenges for future research in this direction.

Fault identification method based on generative adversarial network in distributed acoustic sensing

With the rapid development of machine learning and deep learning, neural-network-based pattern recognition techniques have become a trend for distributed acoustic sensing (DAS) systems. However, in some cases, certain types of data are difficult to obtain, which leads to imbalanced sample sets. To solve this problem, a data augmentation method based on a generative adversarial network is proposed in this study. First, normal operation samples, including the normal operation training and testing sets are collected using the DAS system. The cyclegan algorithm is then used to generate fault operation samples, a part of which can be selected as the fault operation training set, whereas the others can be viewed as the fault operation testing set. Furthermore, an effective method of data augmentation, called k-means clustering-synthetic minority oversampling technique deep convolutional generative adversarial network, is proposed to enhance the fault operation training set. Finally, the proposed method is applied to the on-load tap-changer, and the experimental results show that the average accuracy of the validation set for the classification task can reach 97%.