Comment on amt-2021-304

To improve the performance of INS, the Competence Center for Applied Sensor Systems (CCASS) has successfully designed a low-cost INS with 6 accelerometers and 6 gyroscopes. The accuracy of this object-tracking system has been dramatically improved by Shaping-filter and Sensor-error model. According to the application of this navigation system, a pattern recognition algorithm will be developed to improve the stability and accuracy of the INS. This recognition algorithm is based on the Bayesian decision method, because it is a parametric technique with benefits of simplicity. Our developing application has finite start and stop points. In other words, the pattern of the movement might possibly be recognized with pattern recognition algorithms. Then, the position will be estimated based on the result of the developing pattern recognition module and the navigation module compensated with the error module. Moreover, this pattern recognition module might be successfully integrated with the error module, which is based on Kalmanfiltering. It might possible to use the result from the pattern recognition as a reference signal, as well as the reset point of the INS system.

From the Publisher: Solving pattern recognition problems involves an enormous amount ofcomputational effort. By applying genetic algorithms - a computational method based on the way chromosomes in DNA recombine - these problems are more efficiently and more accurately solved. Genetic Algorithms for Pattern Recognition covers a broad range of applications in science and technology, describing the integration of genetic algorithms in pattern recognition and machine learning problems to build intelligent recognition systems. The articles, written by leading experts from around the world, accomplish several objectives: they provide insight into the theory of genetic algorithms; they develop pattern recognition theory in light of genetic algorithms; and they illustrate applications in artificial neural networks and fuzzy logic. The cross-sectional view of current research presented in Genetic Algorithms for Pattern Recognition makes it a unique text, ideal for graduate students and researchers.

Linear and nonlinear methods of pattern classification which have been found useful in laboratory investigations of various recognition tasks are reviewed. The discussion includes correlation methods, maximum likelihood formulations with independence or normality assumptions, the minimax Anderson-Bahadur formula, trainable systems, discriminant analysis, optimal quadratic boundaries, tree and chain expansions of binary probability density functions, and sequential decision schemes. The area of applicability, basic assumptions, manner of derivation, and relative computational complexity of each algorithm are described. Each method is illustrated by means of the same two-class two-dimensional numerical example. The in this example comprises four samples from either class; the test is the set of all points in the normal distributions characterized by the sample means and sample covariance matrices of the training set. Procedural difficulties stemming from an insufficient number of samples, various violations of the underlying statistical models, linear nonseparability, noninvertible covariance matrices, multimodal distributions, and other experimental facts of life are touched on.

Measuring the values of weight on bit (WOB) and differential pressure (DiffP) through accurate taring is critical for ensuring downhole tool health and creating accurate parameter roadmaps for drilling optimization. Current industry standards for taring rely on the driller to manually select a particular time when these values are zero, which is often imprecise and/or inaccurate. This paper will detail the journey this drilling contractor made to automate the taring process as part of a broader connection automation initiative, how initial solutions challenged organizational assumptions on downhole behaviors, and how a pattern recognition algorithm allowed for better tare consistency and accuracy over existing field procedures. An initial process automation procedure was designed and implemented in the rig control system (RCS) to manage the connection process, starting with coming out of slips and ending with tagging bottom. As part of this process, the system included a step to consistently tare when the drill bit is one foot off bottom and descending at a constant rate. During field trials, this method gave encouraging results over previous manual tares. Though the result did show improvement over the traditional manual taring method, discrepancies in the relationship between WOB and DiffP eventually led to an improved method of taring which utilizes a novel pattern recognition algorithm. This algorithm detects when the bit tags bottom and establishes a reference hookload (HKLD) at that point. A pattern recognition algorithm was included into the automation sequence replacing the step to tare one foot from bottom. The initial process automation routine provided consistency to the taring process which was observed during testing. The improvement in consistency revealed inconsistency in WOB tares which was supported by variance in DiffP when WOB was constant. A pattern recognition method was developed to identify when tagging bottom. This algorithm was applied to historical data providing evidence of its benefit to WOB tares. The algorithm was included in an application and then adapted and applied to DiffP tares. The application was run over a historical dataset to qualify its viability. After proving viability, it was exchanged with the taring step in the initial process automation routine and run on live wells. Taring using the pattern-recognition based application presented better results than the manual and initial automation taring methods. The overall operational impacts of each method will be discussed in further detail. The results of this project challenge underlying assumptions about how taring should be performed and improves overall understanding of the impact of different automation routines. The pattern recognition method discussed in this paper constitutes a novel application which utilizes new technology to improve existing processes.

In this paper, a solution is presented to support both existing and future movement rehabilitation applications. The presented method combines the advantages of human computer interaction based movement therapy with the cognitive property of intelligent decision making systems. With this solution, therapy could be fully adapted to the needs of the patients and conditions while maintaining a sense of success in them, thereby motivating them. In our modern digital age, the development of HCI interfaces walk together with the growing of user needs for them. The available technologies have limitations, which can reduce the effectiveness of modern input devices, such as the Kinect sensor or any other similar sensors. In this article, multiple newly developed and modified methods are introduced with the aim to overcome these limitations. This methods can fully adapt the movement pattern recognition to the users’ skills. The main are to apply this method, is movement rehabilitation, where the supervisor, therapist can personalize the rehabilitation exercises due to the Distance Vector Based Gesture Recognition (DVGR), Reference Distance Based Synchronous/Asynchronous Movement Recognition (RDSMR/RDAMR) and the Real-Time Adaptive Movement Pattern Classification (RAMPC) methods. Keywords: cognitive infocommunication, rehabilitation exercises, motivation, Kinect sensor, adaptive interface controller, real-time gesture recognition and classification

This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.

Over the past decade, Machine Learning and Artificial Intelligence have attracted great interest in research and various practical applications. Currently, smart, fast, highly sensitive with excellent selectivity are becoming increasingly interesting due to the high need for environmental safety and medical applications. The main challenge is to improve sensor selectivity, which requires the combination of interdisciplinary research areas to successfully develop smart gas/chemical sensing devices with better performance. In this review, we present a few principles of gas sensing based on low-cost interdigitated electrodes (IDE), such as electrochemical, resistive, capacitive and acoustic sensors. In addition, the most important current methods for improving gas sensing performance, the different materials, the different techniques used to fabricate IDE gas sensors, their advantages and limitations are presented. In addition, a comparison between different machine learning and artificial intelligence algorithms for pattern recognition and classification algorithms is also discussed. The discussion then establishes application cases of smart machine learning algorithms, which provide efficient data processing methods, for the design of smart gas sensors which are highly selective. In addition, the challenges and limitations of machine learning in gas sensor applications are critically discussed. The study shows the importance of machine learning with the need for structural optimization to develop and improve smart, sensitive and selective sensors.

In this paper, have been described using pattern recognition, is also introduced for use Bayes algorithm in pattern recognition. Pattern recognition is the machine identification, computer identification or machine Automatic Identification, aims is to automatically identify things in the machine. After the introduction of the Bayes algorithm, pattern recognition accuracy is improved, and the use of a template approach, so the speed has also been taking into account.

Advanced upper limb prostheses capable of actuating multiple degrees of freedom (DOFs) are now commercially available. Pattern recognition algorithms that use surface electromyography (EMG) signals show great promise as multi-DOF controllers. Unfortunately, current pattern recognition systems are limited to activate only one DOF at a time. This study introduces a novel classifier based on Bayesian theory to provide classification of simultaneous movements. This approach and two other classification strategies for simultaneous movements were evaluated using nonamputee and amputee subjects classifying up to three DOFs, where any two DOFs could be classified simultaneously. Similar results were found for nonamputee and amputee subjects. The new approach, based on a set of conditional parallel classifiers was the most promising with errors significantly less (p < 0.05) than a single linear discriminant analysis (LDA) classifier or a parallel approach. For three-DOF classification, the conditional parallel approach had error rates of 6.6% on discrete and 10.9% on combined motions, while the single LDA had error rates of 9.4% on discrete and 14.1% on combined motions. The low error rates demonstrated suggest than pattern recognition techniques on surface EMG can be extended to identify simultaneous movements, which could provide more life-like motions for amputees compared to exclusively classifying sequential movements.

The authors propose a neural network algorithm for adaptive pattern recognition. The algorithm consists of five steps: local feature vector forming, statistical distribution measurement, adaptive clustering, optimal criteria guidance, and a recursive mechanism. Based on the local feature vectors formed in parallel from the neighbors of the original data set in the correspondent pattern space, the statistical distribution is computed in parallel, and the adaptive pattern recognition is performed on the feature space vectors and not directly on the pattern vectors themselves. The optimal criteria guide the clustering procedure and determine the goodness of the clusters. Asymptotical results in the optimal sense could be achieved by the recursive mechanism. The algorithm is efficient and was applied to the image pattern recognition system. >

Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical.

Accurate measurement of WOB and differential pressure (DP) is essential to preventing downhole tool damage and improving drilling efficiency. These quantities are calculated by measuring changes relative to baseline values, known as "tare" values. Previous work by the authors found success in automating the taring process by applying pattern recognition algorithms to the process of tagging bottom, significantly improving tare accuracy over existing manual methods. After over a year of utilization on dozens of rigs in this contractor's fleet, this work seeks to analyze results and performance of the system at scale. The pattern recognition algorithms have been deployed to all onshore drilling rigs and are being utilized to automate the taring process on approximately 50 rigs. This study conducts an in-depth analysis to evaluate the accuracy of these automated tares and investigate their overall impact on drilling performance. Additionally, the study analyzes the effect of tare accuracy on drill bit health for over 700 drill bit runs. The tare accuracy is evaluated in accordance with expected trends over depth and the correlation between WOB and DP. The bit health analysis is completed by correlating tare error with drill bit dull characteristics. Furthermore, a large-scale review is conducted to identify unexpected behaviors observed in the taring process, identifying improvement areas for retraining to address these issues and ensure complete buy-in from all parties (e.g., operators and drillers). The initial results showed that using pattern recognition algorithms reduced WOB error by up to 50% compared to manual tares, as validated by a significantly better correlation between WOB and DP. Overall, the pattern recognition algorithms improved consistency of tares by over 20% across the sampled rigs. Crucially, several behaviors were observed that, without application of pattern recognition algorithms, would have adversely affected tare accuracy, and consequently impacted drill bit health and drilling performance negatively. These included issues relevant to most onshore drilling rigs, such as the drill bit tagging bottom early, incorrect timing of manual tares, the effect of top drive descent speed on tares, and the interplay between drill string length and the time required to fully incorporate drag and pump pressure into the system. This work identifies and quantifies several behaviors that are endemic to the drilling operations across the industry and highlights how pattern recognition algorithms have been used to limit their impact. Our incorporation of bit dull grade data is a novel analysis and relevant to the industry more broadly.

Chapter 5 - Recognition

Power transformer is one of the most important and expensive equipment in a power system. Its reliability directly affects a power system. To ensure the reliable operation of a power transformer, its condition needs to be continuously monitored and evaluated. Over the past two decades, a number of diagnostic techniques have been developed for transformer condition assessment such as dissolved gas analysis (DGA), degree of polymerization (DP) measurement, polarization and depolarization current (PDC) measurement, frequency domain spectroscopy (FDS), frequency response analysis (FRA), and partial discharge (PD) detection. However, the interpretations of measurement results acquired from these diagnostics are usually based upon the empirical models, which are sometimes inaccurate and incomplete especially in abnormal transformer operation scenarios. Therefore, accurate interpreting on the measurement data obtained by the above techniques and subsequently making explicit condition assessment of transformers is still a challenge task. Nowadays, considerable efforts have been made in the field of transformer condition monitoring and assessment. Majority efforts are dedicated in developing accurate transformer models and reliable transformer fault diagnosis systems. After completing a comprehensive literature review on various diagnostic techniques for transformers condition assessment, this thesis focuses on three main aspects of transformer’s health condition, including oil characteristics and dissolved gases in transformers, moisture concentration of oil-cellulose insulation and hot spot temperature of transformer windings. Since there is a lack of common framework for applying pattern recognition algorithms (i.e. data centric approaches) to interpret oil characteristics and DGA data, this thesis firstly provides a critical review on various pattern recognition techniques for power transformer insulation diagnosis using DGA and oil characteristics datasets. A general pattern recognition application framework is then proposed. The important issues for improving the applicability of pattern recognition techniques for transformer insulation diagnosis are also discussed. To improve the data quality of training database and enhance the diagnostic accuracy of pattern recognition algorithms, a hybrid algorithm, SMOTEBoost is proposed. It adopts Synthetic Minority Over-sampling Technique (SMOTE) to handle the class imbalance problem, where samples belonging to different fault types (insulation conditions) are unevenly distributed in the training database. By using the boosting approach for reweighting and grouping data points in the training database, the SMOTEBoost can facilitate pattern recognition algorithms consistently attaining desirable diagnosis accuracies. To solve the intricate difficulties in moisture estimation of transformer oil-cellulose insulation system, this thesis introduces two modelling approaches, i.e., multi-physics finite element modelling (FEM) and particle tracing method, where the temperature dependent moisture dynamics in transformers’ insulation system is taken into account. In multi-physics approach, moisture dynamics is modelled by coupling the electromagnetic, thermal, fluid flow and moisture migration physics simultaneously. In particle tracing method, moisture diffusion is formulated from a microscopic view of water molecules’ motion. Especially, the transmission probability of water molecules (termed as particles in the paper) is employed to correlate the microscopic particles’ motion with the macroscopic moisture distribution. Extensive ageing and moisture diffusion experiments have been conducted on a prototype transformer to verify the proposed modelling approaches for an accurate estimation of moisture in transformers. This thesis also proposes a distributed parameter model to investigate the effect of moisture dynamics on dielectric response of a transformer’s cellulose insulation. The correlation between moisture distribution (under non-equilibrium conditions due to thermal transients) and dielectric response parameters (dielectric losses and permittivity) of transformer cellulose insulation is revealed. The proposed methodology can help the proper interpretation of dielectric response measurement of field transformers under thermal transients. To overcome the inaccuracy in empirical thermal dynamic models, in this thesis a moisture dependent thermal model (MDTM) is developed for estimating transformer’s hot spot temperature. In this model, nonlinear thermal resistance is formulated by considering both oil and cellulose (paper and pressboard) of the transformer. Especially, the effect of moisture concentration and hot spot temperature on the thermal resistance of cellulose is taken into account. The proposed MDTM is verified by using historical data of moisture-in-oil and temperature measurements on an in-service vegetable oil-filled transformer. To integrate every piece of data and information obtained from different transformer diagnostic measurements and subsequently evaluating the overall health condition of a transformer, this thesis proposes a data and information fusion framework based on Bayesian Network (BN). Within the Bayesian Network, Monte Carlo and Bootstrap methods are employed to extract the most informative characteristics regarding transformer condition from different diagnostic measurements. Results of case studies demonstrate that the proposed data and information fusion framework can evaluate the effectiveness of combinations of different diagnostic measurements and subsequently facilitate determining optimal diagnostic strategies involved in transformer condition assessment. It is expected that the data centric diagnostic approaches developed in this thesis can provide an accurate modelling and reliable assessment of transformer’s health condition.

The purpose of this paper is to illustrate how the construction of a knowledge-based system (KBS) to support nowcasting, can be used to guide and facilitate the development of objective pattern recognition algorithms for use with meteorological data. We believe that a KBS based on the semantic interpretation of weather data, using the concept of weather scenarios, can assist the development and use of objective algorithms for pattern recognition in two ways: 1) it focuses the development of pattern recognition algorithms on only those phenomena which are most useful to operational forecasters; 2) its top-down logic constrains when, where, and how objective algorithms should be applied. We first describe our understanding of nowcasting expertise and the use of pattern recognition (“manual”) by human forecasters. We then briefly review the current use of automatic pattern recognition in nowcasting, present the elements within a scenario and discuss a KBS architecture for using scenarios. Finally, we close by discussing the practical benefits of merging a qualitative KBS with algorithmic pattern recognition techniques.