Academic literature on the topic 'Automatic classification Statistical methods'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Automatic classification Statistical methods.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Automatic classification Statistical methods"
1
Couvreur, Christophe, and Yoram Bresler. "Automatic classification of environmental noise sources by statistical methods." Noise Control Engineering Journal 46, no. 4 (1998): 167. http://dx.doi.org/10.3397/1.2828469.
Full text
2
Garnsey, Margaret R. "Automatic Classification of Financial Accounting Concepts." Journal of Emerging Technologies in Accounting 3, no. 1 (January 1, 2006): 21–39. http://dx.doi.org/10.2308/jeta.2006.3.1.21.
Full textAbstract:
Information and standards overload are part of the current business environment. In accounting, this is exacerbated due to the variety of users and the evolving nature of accounting language. This article describes a research project that determines the feasibility of using statistical methods to automatically group related accounting concepts together. Starting with the frequencies of words in documents and modifying them for local and global weighting, Latent Semantic Indexing (LSI) and agglomerative clustering were used to derive clusters of related accounting concepts. Resultant clusters were compared to terms generated randomly and terms identified by individuals to determine if related terms are identified. A recognition test was used to determine if providing individuals with lists of terms generated automatically allowed them to identify additional relevant terms. Results found that both clusters obtained from the weighted term-document matrix and clusters from a LSI matrix based on 50 dimensions contained significant numbers of related terms. There was no statistical difference in the number of related terms found by the methods. However, the LSI clusters contained terms that were of a lower frequency in the corpus. This finding may have significance in using cluster terms to assist in retrieval. When given a specific term and asked for related terms, providing individuals with a list of potential terms significantly increased the number of related terms they were able to identify when compared to their free-recall.
3
Christlieb, N., L. Wisotzki, and G. Graßhoff. "Statistical methods of automatic spectral classification and their application to the Hamburg/ESO Survey." Astronomy & Astrophysics 391, no. 1 (July 29, 2002): 397–406. http://dx.doi.org/10.1051/0004-6361:20020830.
Full text
4
Ştefan, Raluca-Mariana, Măriuţa Şerban, Iulian-Ion Hurloiu, and Bianca-Florentina Rusu. "Kernel Methods for Data Classification." International conference KNOWLEDGE-BASED ORGANIZATION 22, no. 3 (June 1, 2016): 572–75. http://dx.doi.org/10.1515/kbo-2016-0098.
Full textAbstract:
Abstract In the past decades, the exponential evolution of data collection for macroeconomic databases in digital format caused a huge increase in their volume. As a consequence, the automatic organization and the classification of macroeconomic data show a significant practical value. Various techniques for categorizing data are used to classify numerous macroeconomic data according to the classes they belong to. Since the manual construction of some of the classifiers is difficult and time consuming, are preferred classifiers that learn from action examples, a process which forms the supervised classification type. A variant of solving the problem of data classification is the one of using the kernel type methods. These methods represent a class of algorithms used in the automatic analysis and classification of information. Most algorithms of this section focus on solving convex optimization problems and calculating their own values. They are efficient in terms of computation time and are very stable statistically. Shaw-Taylor, J. and Cristianini, N. have demonstrated that this type of approach to data classification is robust and efficient in terms of detection of existing stable patterns in a finite array of data. Thus, in a modular manner data will be incorporated into a space where it can cause certain linear relationship.
5
Siracusano, Giulio, Francesca Garescì, Giovanni Finocchio, Riccardo Tomasello, Francesco Lamonaca, Carmelo Scuro, Mario Carpentieri, Massimo Chiappini, and Aurelio La Corte. "Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning." Applied Sciences 11, no. 24 (December 17, 2021): 12059. http://dx.doi.org/10.3390/app112412059.
Full textAbstract:
In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven structural health monitoring (SHM) systems is gaining in popularity. This is due to the large availability of big data from low-cost sensors with communication capabilities and advanced modeling tools such as deep learning. A promising method suitable for smart SHM is the analysis of acoustic emissions (AEs), i.e., ultrasonic waves generated by internal ruptures of the concrete when it is stressed. The advantage in respect to traditional ultrasonic measurement methods is the absence of the emitter and the suitability to implement continuous monitoring. The main purpose of this paper is to combine deep neural networks with bidirectional long short term memory and advanced statistical analysis involving instantaneous frequency and spectral kurtosis to develop an accurate classification tool for tensile, shear and mixed modes originated from AE events (cracks). We investigated effective event descriptors to capture the unique characteristics from the different types of modes. Tests on experimental results confirm that this method achieves promising classification among different crack events and can impact on the design of the future of SHM technologies. This approach is effective to classify incipient damages with 92% of accuracy, which is advantageous to plan maintenance.
6
GHOSH, ANIL KUMAR, and SMARAJIT BOSE. "FEATURE EXTRACTION FOR CLASSIFICATION USING STATISTICAL NETWORKS." International Journal of Pattern Recognition and Artificial Intelligence 21, no. 07 (November 2007): 1103–26. http://dx.doi.org/10.1142/s0218001407005855.
Full textAbstract:
In a classification problem, quite often the dimension of the measurement vector is large. Some of these measurements may not be important for separating the classes. Removal of these measurement variables not only reduces the computational cost but also leads to better understanding of class separability. There are some methods in the existing literature for reducing the dimensionality of a classification problem without losing much of the separability information. However, these dimension reduction procedures usually work well for linear classifiers. In the case where competing classes are not linearly separable, one has to look for ideal "features" which could be some transformations of one or more measurements. In this paper, we make an attempt to tackle both, the problems of dimension reduction and feature extraction, by considering a projection pursuit regression model. The single hidden layer perceptron model and some other popular models can be viewed as special cases of this model. An iterative algorithm based on backfitting is proposed to select the features dynamically, and cross-validation method is used to select the ideal number of features. We carry out an extensive simulation study to show the effectiveness of this fully automatic method.
7
AMARO-CAMARGO, ERIKA, CARLOS A. REYES-GARCÍA, EMILIO ARCH-TIRADO, and MARIO MANDUJANO-VALDÉS. "STATISTICAL VECTORS OF ACOUSTIC FEATURES FOR THE AUTOMATIC CLASSIFICATION OF INFANT CRY." International Journal of Information Acquisition 04, no. 04 (December 2007): 347–55. http://dx.doi.org/10.1142/s0219878907001423.
Full textAbstract:
With the objective of helping diagnose some pathologies in recently born babies, we present the experiments and results obtained in the classification of infant cry using a variety of single classifiers, and ensembles from the combination of them. Three kinds of cry were classified: normal, hypoacoustic (deaf), and asphyxia. The feature vectors were formed by the extraction of Mel Frequency Cepstral Coefficients (MFCC). The vectors were then processed and reduced through the application of five statistics operations, namely: minimum, maximum, average, standard deviation and variance. LDA, a data reduction technique is implemented with the purpose of comparing the results of our proposed method. Four supervised machine learning methods including Support Vector Machines, Neural Networks, J48, Random Forest and Naive Bayes are used. The ensembles tested were combinations of these under different approaches like Majority Vote, Staking, Bagging and Boosting.
8
A. S. Hazaa, Muneer, Nazlia Omar, Fadl Mutaher Ba-Alwi, and Mohammed Albared. "Automatic Extraction Of Malay Compound Nouns Using A Hybrid Of Statistical And Machine Learning Methods." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 3 (June 1, 2016): 925. http://dx.doi.org/10.11591/ijece.v6i3.9663.
Full textAbstract:
Identifying of compound nouns is important for a wide spectrum of applications in the field of natural language processing such as machine translation and information retrieval. Extraction of compound nouns requires deep or shallow syntactic preprocessing tools and large corpora. This paper investigates several methods for extracting Noun compounds from Malay text corpora. First, we present the empirical results of sixteen statistical association measures of Malay <N+N> compound nouns extraction. Second, we introduce the possibility of integrating multiple association measures. Third, this work also provides a standard dataset intended to provide a common platform for evaluating research on the identification compound Nouns in Malay language. The standard data set contains 7,235 unique N-N candidates, 2,970 of them are N-N compound nouns collocations. The extraction algorithms are evaluated against this reference data set. The experimental results demonstrate that a group of association measures (T-test , Piatersky-Shapiro (PS) , C_value, FGM and rank combination method) are the best association measure and outperforms the other association measures for <N+N> collocations in the Malay corpus. Finally, we describe several classification methods for combining association measures scores of the basic measures, followed by their evaluation. Evaluation results show that classification algorithms significantly outperform individual association measures. Experimental results obtained are quite satisfactory in terms of the Precision, Recall and F-score.
9
A. S. Hazaa, Muneer, Nazlia Omar, Fadl Mutaher Ba-Alwi, and Mohammed Albared. "Automatic Extraction Of Malay Compound Nouns Using A Hybrid Of Statistical And Machine Learning Methods." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 3 (June 1, 2016): 925. http://dx.doi.org/10.11591/ijece.v6i3.pp925-935.
Full textAbstract:
Identifying of compound nouns is important for a wide spectrum of applications in the field of natural language processing such as machine translation and information retrieval. Extraction of compound nouns requires deep or shallow syntactic preprocessing tools and large corpora. This paper investigates several methods for extracting Noun compounds from Malay text corpora. First, we present the empirical results of sixteen statistical association measures of Malay <N+N> compound nouns extraction. Second, we introduce the possibility of integrating multiple association measures. Third, this work also provides a standard dataset intended to provide a common platform for evaluating research on the identification compound Nouns in Malay language. The standard data set contains 7,235 unique N-N candidates, 2,970 of them are N-N compound nouns collocations. The extraction algorithms are evaluated against this reference data set. The experimental results demonstrate that a group of association measures (T-test , Piatersky-Shapiro (PS) , C_value, FGM and rank combination method) are the best association measure and outperforms the other association measures for <N+N> collocations in the Malay corpus. Finally, we describe several classification methods for combining association measures scores of the basic measures, followed by their evaluation. Evaluation results show that classification algorithms significantly outperform individual association measures. Experimental results obtained are quite satisfactory in terms of the Precision, Recall and F-score.
10
Protopapas, Pavlos. "Workshop on Algorithms for Time-Series Analysis." Proceedings of the International Astronomical Union 7, S285 (September 2011): 271. http://dx.doi.org/10.1017/s1743921312000737.
Full textAbstract:
SummaryThis Workshop covered the four major subjects listed below in two 90-minute sessions. Each talk or tutorial allowed questions, and concluded with a discussion.Classification: Automatic classification using machine-learning methods is becoming a standard in surveys that generate large datasets. Ashish Mahabal (Caltech) reviewed various methods, and presented examples of several applications.Time-Series Modelling: Suzanne Aigrain (Oxford University) discussed autoregressive models and multivariate approaches such as Gaussian Processes.Meta-classification/mixture of expert models: Karim Pichara (Pontificia Universidad Católica, Chile) described the substantial promise which machine-learning classification methods are now showing in automatic classification, and discussed how the various methods can be combined together.Event Detection: Pavlos Protopapas (Harvard) addressed methods of fast identification of events with low signal-to-noise ratios, enlarging on the characterization and statistical issues of low signal-to-noise ratios and rare events.
Dissertations / Theses on the topic "Automatic classification Statistical methods"
1
Latino, Diogo Alexandre Rosa Serra. "Automatic learning for the classification of chemical reactions and in statistical thermodynamics." Doctoral thesis, FCT - UNL, 2008. http://hdl.handle.net/10362/1752.
Full textAbstract:
This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds.
NMR-based classification of photochemical and enzymatic reactions. Photochemical
and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen
SOMs) and Random Forests (RFs) taking as input the difference between the 1H
NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data.
A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases
was able to correctly classify 75% of an independent test set in terms of the EC
number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used.
This study was performed with NMR data simulated from the molecular structure by
the SPINUS program. In the design of one test set, simulated data was combined with
experimental data. The results support the proposal of linking databases of chemical
reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions.
Genome-scale classification of enzymatic reactions from their reaction equation.
The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP
descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken,
changed, and made during a chemical reaction.
The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods
should be available to automatically compare metabolic reactions and for the automatic
assignment of EC numbers to reactions still not officially classified.
In this study, the genome-scale data set of enzymatic reactions available in the KEGG
database was encoded by the MOLMAP descriptors, and was submitted to Kohonen
SOMs to compare the resulting map with the official EC number classification, to explore
the possibility of predicting EC numbers from the reaction equation, and to assess the
internal consistency of the EC classification at the class level.
A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions.
RFs were also used to assign the four levels of the EC hierarchy from the reaction
equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases
(for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively.
In the course of the experiments with metabolic reactions we suggested that the
MOLMAP / SOM concept could be extended to the representation of other levels of
metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different
types of metabolism and pathways that do not share similarities in terms of EC numbers.
Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential
function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function.
The results indicated that for LJ-type potentials, NNs can be trained to generate
accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better
results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown.
The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping
of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo,
the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes.
Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task.
The data consisted of energy values, from Density Functional Theory (DFT) calculations,
at different distances, for several molecular orientations and three electrode
adsorption sites. The results indicate that NNs require a data set large enough to cover
well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions.
Therefore, they can be used in molecular simulations, particularly for the ethanol/Au
(111) interface which is the case studied in the present Thesis. Once properly trained,
the networks are able to produce, as output, any required number of energy points for
accurate interpolations.
2
Arshad, Irshad Ahmad. "Using statistical methods for automatic classifications of clouds in ground-based photographs of the sky." Thesis, University of Essex, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.250129.
Full text
3
Shepherd, Gareth William Safety Science Faculty of Science UNSW. "Automating the aetiological classification of descriptive injury data." Awarded by:University of New South Wales. School of Safety Science, 2006. http://handle.unsw.edu.au/1959.4/24934.
Full textAbstract:
Injury now surpasses disease as the leading global cause of premature death and disability, claiming over 5.8 millions lives each year. However, unlike disease, which has been subjected to a rigorous epidemiologic approach, the field of injury prevention and control has been a relative newcomer to scientific investigation. With the distribution of injury now well described (i.e. ???who???, ???what???, ???where??? and ???when???), the underlying hypothesis is that progress in understanding ???how??? and ???why??? lies in classifying injury occurrences aetiologically. The advancement of a means of classifying injury aetiology has so far been inhibited by two related limitations: 1. Structural limitation: The absence of a cohesive and validated aetiological taxonomy for injury, and; 2. Methodological limitation: The need to manually classify large numbers of injury cases to determine aetiological patterns. This work is directed at overcoming these impediments to injury research. An aetiological taxonomy for injury was developed consistent with epidemiologic principles, along with clear conventions and a defined three-tier hierarchical structure. Validation testing revealed that the taxonomy could be applied with a high degree of accuracy (coder/gold standard agreement was 92.5-95.0%), and with high inter- and intra- coder reliability (93.0-96.3% and 93.5-96.3%). Practical application demonstrated the emergence of strong aetiological patterns which provided insight into causative sequences leading to injury, and led to the identification of effective control measures to reduce injury frequency and severity. However, limitations related to the inefficient and error-prone manual classification process (i.e. average 4.75 minute/case processing time and 5.0-7.5% error rate), revealed the need for an automated approach. To overcome these limitations, a knowledge acquisition (KA) software tool was developed, tested and applied, based on an expertsystems technique known as ripple down rules (RDR). It was found that the KA system was able acquire tacit knowledge from a human expert and apply learned rules to efficiently and accurately classify large numbers of injury cases. Ultimately, coding error rates dropped to 3.1%, which, along with an average 2.50 minute processing time, compared favourably with results from manual classification. As such, the developed taxonomy and KA tool offer significant advantages to injury researchers who have a need to deduce useful patterns from injury data and test hypotheses regarding causation and prevention.
4
Monroy, Chora Isaac. "An investigation on automatic systems for fault diagnosis in chemical processes." Doctoral thesis, Universitat Politècnica de Catalunya, 2012. http://hdl.handle.net/10803/77637.
Full textAbstract:
Plant safety is the most important concern of chemical industries. Process faults can cause economic loses as well as human and environmental damages. Most of the operational faults are normally considered in the process design phase by applying methodologies such as Hazard and Operability Analysis (HAZOP). However, it should be expected that failures may occur in an operating plant. For this reason, it is of paramount importance that plant operators can promptly detect and diagnose such faults in order to take the appropriate corrective actions. In addition, preventive maintenance needs to be considered in order to increase plant safety.
Fault diagnosis has been faced with both analytic and data-based models and using several techniques and algorithms. However, there is not yet a general fault diagnosis framework that joins detection and diagnosis of faults, either registered or non-registered in records. Even more, less efforts have been focused to automate and implement the reported approaches in real practice.
According to this background, this thesis proposes a general framework for data-driven Fault Detection and Diagnosis (FDD), applicable and susceptible to be automated in any industrial scenario in order to hold the plant safety. Thus, the main requirement for constructing this system is the existence of historical process data. In this sense, promising methods imported from the Machine Learning field are introduced as fault diagnosis methods. The learning algorithms, used as diagnosis methods, have proved to be capable to diagnose not only the modeled faults, but also novel faults. Furthermore, Risk-Based Maintenance (RBM) techniques, widely used in petrochemical industry, are proposed to be applied as part of the preventive maintenance in all industry sectors. The proposed FDD system together with an appropriate preventive maintenance program would represent a potential plant safety program to be implemented.
Thus, chapter one presents a general introduction to the thesis topic, as well as the motivation and scope. Then, chapter two reviews the state of the art of the related fields. Fault detection and diagnosis methods found in literature are reviewed. In this sense a taxonomy that joins both Artificial Intelligence (AI) and Process Systems Engineering (PSE) classifications is proposed. The fault diagnosis assessment with performance indices is also reviewed. Moreover, it is exposed the state of the art corresponding to Risk Analysis (RA) as a tool for taking corrective actions to faults and the Maintenance Management for the preventive actions. Finally, the benchmark case studies against which FDD research is commonly validated are examined in this chapter.
The second part of the thesis, integrated by chapters three to six, addresses the methods applied during the research work. Chapter three deals with the data pre-processing, chapter four with the feature processing stage and chapter five with the
diagnosis algorithms. On the other hand, chapter six introduces the Risk-Based Maintenance techniques for addressing the plant preventive maintenance. The third part includes chapter seven, which constitutes the core of the thesis. In this chapter the proposed general FD system is outlined, divided in three steps: diagnosis model construction, model validation and on-line application. This scheme includes a fault detection module and an Anomaly Detection (AD) methodology for the detection of novel faults. Furthermore, several approaches are derived from this general scheme for continuous and batch processes. The fourth part of the thesis presents the validation of the approaches. Specifically, chapter eight presents the validation of the proposed approaches in continuous processes and chapter nine the validation of batch process approaches. Chapter ten raises the AD methodology in real scaled batch processes. First, the methodology is applied to a lab heat exchanger and then it is applied to a Photo-Fenton pilot plant, which corroborates its potential and success in real practice. Finally, the fifth part, including chapter eleven, is dedicated to stress the final conclusions and the main contributions of the thesis. Also, the scientific production achieved during the research period is listed and prospects on further work are envisaged.La seguridad de planta es el problema más inquietante para las industrias químicas. Un fallo en planta puede causar pérdidas económicas y daños humanos y al medio ambiente. La mayoría de los fallos operacionales son previstos en la etapa de diseño de un proceso mediante la aplicación de técnicas de Análisis de Riesgos y de Operabilidad (HAZOP). Sin embargo, existe la probabilidad de que pueda originarse un fallo en una planta en operación. Por esta razón, es de suma importancia que una planta pueda detectar y diagnosticar fallos en el proceso y tomar las medidas correctoras adecuadas para mitigar los efectos del fallo y evitar lamentables consecuencias. Es entonces también importante el mantenimiento preventivo para aumentar la seguridad y prevenir la ocurrencia de fallos. La diagnosis de fallos ha sido abordada tanto con modelos analíticos como con modelos basados en datos y usando varios tipos de técnicas y algoritmos. Sin embargo, hasta ahora no existe la propuesta de un sistema general de seguridad en planta que combine detección y diagnosis de fallos ya sea registrados o no registrados anteriormente. Menos aún se han reportado metodologías que puedan ser automatizadas e implementadas en la práctica real. Con la finalidad de abordar el problema de la seguridad en plantas químicas, esta tesis propone un sistema general para la detección y diagnosis de fallos capaz de implementarse de forma automatizada en cualquier industria. El principal requerimiento para la construcción de este sistema es la existencia de datos históricos de planta sin previo filtrado. En este sentido, diferentes métodos basados en datos son aplicados como métodos de diagnosis de fallos, principalmente aquellos importados del campo de “Aprendizaje Automático”. Estas técnicas de aprendizaje han resultado ser capaces de detectar y diagnosticar no sólo los fallos modelados o “aprendidos”, sino también nuevos fallos no incluidos en los modelos de diagnosis. Aunado a esto, algunas técnicas de mantenimiento basadas en riesgo (RBM) que son ampliamente usadas en la industria petroquímica, son también propuestas para su aplicación en el resto de sectores industriales como parte del mantenimiento preventivo. En conclusión, se propone implementar en un futuro no lejano un programa general de seguridad de planta que incluya el sistema de detección y diagnosis de fallos propuesto junto con un adecuado programa de mantenimiento preventivo. Desglosando el contenido de la tesis, el capítulo uno presenta una introducción general al tema de esta tesis, así como también la motivación generada para su desarrollo y el alcance delimitado. El capítulo dos expone el estado del arte de las áreas relacionadas al tema de tesis. De esta forma, los métodos de detección y diagnosis de fallos encontrados en la literatura son examinados en este capítulo. Asimismo, se propone una taxonomía de los métodos de diagnosis que unifica las clasificaciones propuestas en el área de Inteligencia Artificial y de Ingeniería de procesos. En consecuencia, se examina también la evaluación del performance de los métodos de diagnosis en la literatura. Además, en este capítulo se revisa y reporta el estado del arte correspondiente al “Análisis de Riesgos” y a la “Gestión del Mantenimiento” como técnicas complementarias para la toma de medidas correctoras y preventivas. Por último se abordan los casos de estudio considerados como puntos de referencia en el campo de investigación para la aplicación del sistema propuesto. La tercera parte incluye el capítulo siete, el cual constituye el corazón de la tesis. En este capítulo se presenta el esquema o sistema general de diagnosis de fallos propuesto. El sistema es dividido en tres partes: construcción de los modelos de diagnosis, validación de los modelos y aplicación on-line. Además incluye un modulo de detección de fallos previo a la diagnosis y una metodología de detección de anomalías para la detección de nuevos fallos. Por último, de este sistema se desglosan varias metodologías para procesos continuos y por lote. La cuarta parte de esta tesis presenta la validación de las metodologías propuestas. Específicamente, el capítulo ocho presenta la validación de las metodologías propuestas para su aplicación en procesos continuos y el capítulo nueve presenta la validación de las metodologías correspondientes a los procesos por lote. El capítulo diez valida la metodología de detección de anomalías en procesos por lote reales. Primero es aplicada a un intercambiador de calor escala laboratorio y después su aplicación es escalada a un proceso Foto-Fenton de planta piloto, lo cual corrobora el potencial y éxito de la metodología en la práctica real. Finalmente, la quinta parte de esta tesis, compuesta por el capítulo once, es dedicada a presentar y reafirmar las conclusiones finales y las principales contribuciones de la tesis. Además, se plantean las líneas de investigación futuras y se lista el trabajo desarrollado y presentado durante el periodo de investigación.
5
Fu, Qiang. "A generalization of the minimum classification error (MCE) training method for speech recognition and detection." Diss., Georgia Institute of Technology, 2008. http://hdl.handle.net/1853/22705.
Full textAbstract:
The model training algorithm is a critical component in the statistical pattern recognition approaches which are based on the Bayes decision theory. Conventional applications of the Bayes decision theory usually assume uniform error cost and result in a ubiquitous use of the maximum a posteriori (MAP) decision policy and the paradigm of distribution estimation as practice in the design of a statistical pattern recognition system. The minimum classification error (MCE) training method is proposed to overcome some substantial limitations for the conventional distribution estimation methods.
In this thesis, three aspects of the MCE method are generalized. First, an optimal classifier/recognizer design framework is constructed, aiming at minimizing non-uniform error cost.A generalized training criterion named weighted MCE is proposed for pattern and speech recognition tasks with non-uniform error cost.
Second, the MCE method for speech recognition tasks requires appropriate management of multiple recognition hypotheses for each data segment.
A modified version of the MCE method with a new approach to selecting and organizing recognition hypotheses is proposed for continuous phoneme recognition. Third, the minimum verification error (MVE) method for detection-based automatic speech recognition (ASR) is studied. The MVE method can be viewed as a special version of the MCE method which aims at minimizing detection/verification errors. We present many experiments on pattern recognition and speech recognition tasks to justify the effectiveness of our generalizations.
6
Gorecki, Christophe. "Classification par échantillonnage de la densité spectrale d'énergie : Application à l'étude statistique des surfaces et à l'analyse de particules." Besançon, 1989. http://www.theses.fr/1989BESA2015.
Full textAbstract:
Etude d'un profilometre optique base sur la defocalisation d'un faisceau de lumiere blanche. Etude de deux dispositifs optonumeriques d'analyse statistique utilisant les techniques de fourier optiques: un analyseur de particules et un dispositif de classement automatique des surfaces non polies
7
Dimara, Euthalie. "L'agriculture grecque : une étude chronologique et régionale par l'analyse des correspondances et la classification automatique." Paris 6, 1988. http://www.theses.fr/1988PA066199.
Full textAbstract:
Dans une étude statistique de la production agricole grecque durant la période 1970-1981, on fait une correspondance ternaire entre trois ensembles de données: les 53 départements grecs, 56 productions différentes et l'ensemble des dix années. Il ressort que l'agriculture grecque a un caractère traditionnel ou le facteur temps n'a pas d'influence significative. On peut distinguer deux zones agraires: productions subméditerranéennes au nord, produits typiquement méditerranéens au sud et dans les iles.
8
Sastre, Jurado Carlos. "Exploitation du signal pénétrométrique pour l'aide à l'obtention d'un modèle de terrain." Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC003/document.
Full textAbstract:
Ce travail porte sur la reconnaissance de sols à faible profondeur grâce aux données de résistance de pointe recueillies à l'aide de l'essai de pénétration dynamique à énergie variable, Panda®. L'objectif principal est d'étudier et de proposer un ensemble d'approches dans le cadre d'une méthode globale permettant d'exploiter les mesures issues d'une campagne de sondages Panda afin de bâtir un modèle géotechnique du terrain.Ce manuscrit est structuré en quatre parties, chacune abordant un objectif spécifique :dans un premier temps, on rappelle les principaux moyens de reconnaissance des sols, notamment l'essai de pénétration dynamique Panda. Ensuite on réalise un bref aperçu sur le modèle géotechnique et les techniques mathématiques pour décrire l'incertitude dans la caractérisation des propriétés du sol;la deuxième partie porte sur l'identification automatique des unités homogènes du terrain, à partir du signal pénétrométrique Panda. Suite à l'étude réalisée sur l'identification "experte" des couches à partir du signal Panda, des approches statistiques basées sur une fenêtre glissante ont été proposées. Ces techniques ont été étudiées et validées sur la base d'un protocole d'essais en laboratoire et sur des essais effectués en sites naturels et en conditions réelles;la troisième partie porte sur l'identification automatique des matériaux composant les unités homogènes détectées dans le signal Panda à partir des méthodes proposées en partie II. Une méthode de classification automatique basée sur des réseaux de neurones artificiels a été proposée et appliquée aux deux cas d'étude : la caractérisation de sols naturels et la classification d'un matériau granulaire argileux industrialisé (bentonite) ; enfin, la dernière partie est consacrée à la production d'un modèle de terrain basé sur la modélisation et la simulation de la résistance de pointe dynamique au moyen de fonctions aléatoires de l'espace. Cette modélisation est basée sur une approche par champs aléatoires conditionnés par les sondages Panda du terrain. Sa mise en œuvre a été étudiée pour un terrain expérimental situé dans la plaine deltaïque méditerranéenne en Espagne. Des études complémentaires en vue de raffiner cette démarche ont été réalisées pour un deuxième site expérimental dans la plaine de la Limagne en FranceThis research focuses on the site characterization of shallow soils using the dynamic cone penetrometer Panda® which uses variable energy. The main purpose is to study and propose several techniques as part of an overall method in order to obtain a ground model through a geotechnical campaign based on the Panda test.This work is divided into four parts, each of them it is focused on a specific topic :first of all, we introduce the main site characterization techniques, including the dynamic penetrometer Panda. Then, we present a brief overview of the geotechnical model and the mathematical methods for the characterization of uncertainties in soil properties;the second part deals with the automatic identification of physical homogeneous soil units based on penetration's mechanical response of the soil using the Panda test. Following a study about the soil layers identification based only on expert's judgment, we have proposed statistical moving window procedures for an objective assessment. The application of these statistical methods have been studied for the laboratory and in situ Panda test;the third part focuses on the automatic classification of the penetrations curves in the homogeneous soil units identified using the statistical techniques proposed in part II. An automatic methodology to predict the soil grading from the dynamic cone resistance using artificial neural networks has been proposed. The framework has been studied for two different research problems: the classification of natural soils and the classification of several crushed aggregate-bentonite mixtures;finally, the last chapter was devoted to model the spatial variability of the dynamic cone resistance qd based on random field theory and geostatistics. In order to reduce uncertainty in the field where Panda measurements are carried out, we have proposed the use of conditional simulation in a three dimensional space. This approach has been applied and studied to a real site investigation carried out in an alluvial mediterranean deltaic environment in Spain. Complementary studies in order to improve the proposed framework have been explored based on another geotechnical campaign conducted on a second experimental site in France
9
Wei, Yi. "Statistical methods on automatic aircraft recognition in aerial images." Thesis, University of Strathclyde, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.248947.
Full text
10
Kim, Heeyoung. "Statistical methods for function estimation and classification." Diss., Georgia Institute of Technology, 2011. http://hdl.handle.net/1853/44806.
Full textAbstract:
This thesis consists of three chapters. The first chapter focuses on adaptive smoothing splines for fitting functions with varying roughness. In the first part of the first chapter, we study an asymptotically optimal procedure to choose the value of a discretized version of the variable smoothing parameter in adaptive smoothing splines. With the choice given by the multivariate version of the generalized cross validation, the resulting adaptive smoothing spline estimator is shown to be consistent and asymptotically optimal under some general conditions. In the second part, we derive the asymptotically optimal local penalty function, which is subsequently used for the derivation of the locally optimal smoothing spline estimator. In the second chapter, we propose a Lipschitz regularity based statistical model, and apply it to coordinate measuring machine (CMM) data to estimate the form error of a manufactured product and to determine the optimal sampling positions of CMM measurements. Our proposed wavelet-based model takes advantage of the fact that the Lipschitz regularity holds for the CMM data. The third chapter focuses on the classification of functional data which are known to be well separable within a particular interval. We propose an interval based classifier. We first estimate a baseline of each class via convex optimization, and then identify an optimal interval that maximizes the difference among the baselines. Our interval based classifier is constructed based on the identified optimal interval. The derived classifier can be implemented via a low-order-of-complexity algorithm.
Books on the topic "Automatic classification Statistical methods"
1
Statistical methods for speech recognition. Cambridge, Mass: MIT Press, 1997.
Find full text
2
Logunova, Oksana, Petr Romanov, and Elena Il'ina. Processing of experimental data on a computer. ru: INFRA-M Academic Publishing LLC., 2020. http://dx.doi.org/10.12737/1064882.
Full textAbstract:
The textbook provides information about the main methods and tools for automating computational processes used in data processing; methods for representing and generating models of experimental data; data models and classification of processing tasks; and the organization of the user interface in automated systems for processing experimental data. Contains structured chapters on the specifics of experimental research. The features of using software for processing experimental data are clearly and logically described. Theoretical material and basic algorithms for processing experimental data used in industrial statistics are presented. Examples of processing experimental data in the field of metallurgy and management in higher education are given. Meets the requirements of the Federal state educational standards of higher education of the latest generation. For students and postgraduates of higher educational institutions.
3
Ambergen, A. W. Statistical uncertainties in posterior probabilities. Amsterdam: Centrum voor Wiskunde en Informatica, 1993.
Find full text
4
Vasilʹev, D. V. Uskorennoe statisticheskoe modelirovanie sistem upravlenii͡a︡. Leningrad: Ėnergoatomizdat, Leningradskoe otd-nie, 1987.
Find full text
5
T, Denison David G., ed. Bayesian methods for nonlinear classification and regression. Chichester, England: Wiley, 2002.
Find full text
6
A, Oliver M., and Webster R, eds. Statistical methods in soil and land resource survey. Oxford [England]: Oxford University Press, 1990.
Find full text
7
Canada, Canada Agriculture, ed. Optimal set covering for biological classification. Ottawa: Agriculture Canada, 1993.
Find full text
8
Clarke, Stevens H. Probationer recidivism in North Carolina: Measurement and classification of risk. [Chapel Hill]: Institute of Government, University of North Carolina at Chapel Hill, 1988.
Find full text
9
Griffiths, A. Evaluation of clustering methods for automatic document classification: Final report for the period October 1982 to September 1984. Sheffield: Dept. of Information Studies, University of Sheffield, 1985.
Find full text
10
Seo, Eun-Gyoung. An experiment in automatic indexing with Korean texts: A comparison of syntactico-statistical and manual methods. Ann Arbor, Mich: University Microfilms International, 1993.
Find full textBook chapters on the topic "Automatic classification Statistical methods"
1
Dey, Abhishek, and Kashi Nath Dey. "Automated Glaucoma Detection from Fundus Images of Eye Using Statistical Feature Extraction Methods and Support Vector Machine Classification." In Lecture Notes in Networks and Systems, 511–21. Singapore: Springer Singapore, 2017. http://dx.doi.org/10.1007/978-981-10-3953-9_49.
Full text
2
Wehenkel, Louis A. "Statistical Methods." In Automatic Learning Techniques in Power Systems, 47–70. Boston, MA: Springer US, 1998. http://dx.doi.org/10.1007/978-1-4615-5451-6_3.
Full text
3
Rizzi, Alfredo. "Statistical Methods for Cryptography." In Data Analysis and Classification, 13–21. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. http://dx.doi.org/10.1007/978-3-642-03739-9_2.
Full text
4
Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. "Linear Methods for Classification." In The Elements of Statistical Learning, 1–37. New York, NY: Springer New York, 2008. http://dx.doi.org/10.1007/b94608_4.
Full text
5
Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. "Linear Methods for Classification." In The Elements of Statistical Learning, 101–37. New York, NY: Springer New York, 2008. http://dx.doi.org/10.1007/978-0-387-84858-7_4.
Full text
6
Hastie, Trevor, Jerome Friedman, and Robert Tibshirani. "Linear Methods for Classification." In The Elements of Statistical Learning, 79–113. New York, NY: Springer New York, 2001. http://dx.doi.org/10.1007/978-0-387-21606-5_4.
Full text
7
Eguchi, Shinto, and Osamu Komori. "Classification." In Minimum Divergence Methods in Statistical Machine Learning, 179–95. Tokyo: Springer Japan, 2022. http://dx.doi.org/10.1007/978-4-431-56922-0_7.
Full text
8
Tsuda, Koji. "Graph Classification Methods in Chemoinformatics." In Handbook of Statistical Bioinformatics, 335–51. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. http://dx.doi.org/10.1007/978-3-642-16345-6_16.
Full text
9
Honerkamp, Josef. "Statistical Tests and Classification Methods." In Graduate Texts in Physics, 483–507. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-28684-1_13.
Full text
10
Honerkamp, Josef. "Statistical Tests and Classification Methods." In Advanced Texts in Physics, 445–69. Berlin, Heidelberg: Springer Berlin Heidelberg, 2002. http://dx.doi.org/10.1007/978-3-662-04763-7_13.
Full textConference papers on the topic "Automatic classification Statistical methods"
1
Alqadah, Hatim F., H. Howard Fan, and John A. Plaga. "Comparison of Time-Frequency Classification Methods for Intelligent Automatic Jettisoning Device of Helmet- Mounted Display Systems." In 2007 IEEE/SP 14th Workshop on Statistical Signal Processing. IEEE, 2007. http://dx.doi.org/10.1109/ssp.2007.4301355.
Full text
2
Dima, M., and T. Dima. "DEEP LEARNING FOR AUTOMATIC RF-MODULATION CLASSIFICATION." In 9th International Conference "Distributed Computing and Grid Technologies in Science and Education". Crossref, 2021. http://dx.doi.org/10.54546/mlit.2021.28.31.001.
Full textAbstract:
Classical methods use statistical-moments to determine the type of modulation in question. Thisessentially correct approach for discerning amplitude modulation (AM) from frequency modulation(FM) fails for more demanding cases such as AM vs. AM-LSB (lower side-band rejection) - radiosignals being richer in information than statistical moments. Parameters with good discriminatingpower were selected in a data conditioning phase and binary deep-learning classifiers were trained forAM-LSB vs. AM-USB, FM vs. AM, AM vs. AM-LSB, etc. The parameters were formed asfeatures, from wave reconstruction primary parameters: rolling pedestal, amplitude, frequency andphase. Very encouraging results were obtained for AM-LSB vs. AM-USB with stochastic training,showing that this particularly difficult case (inaccessible with stochastic moments) is well solvablewith multi-layer perceptron (MLP) neuromorphic software.
3
Ramakrishnan, Sabitha, V. Akshaya, S. Kishor, and T. Thyagarajan. "Real time implementation of arrhythmia classification algorithm using statistical methods." In 2017 Trends in Industrial Measurement and Automation (TIMA). IEEE, 2017. http://dx.doi.org/10.1109/tima.2017.8064824.
Full text
4
Ucar, Ferhat, Omer Faruk Alcin, Besir Dandil, and Fikret Ata. "Machine learning based power quality event classification using wavelet — Entropy and basic statistical features." In 2016 21st International Conference on Methods and Models in Automation and Robotics (MMAR). IEEE, 2016. http://dx.doi.org/10.1109/mmar.2016.7575171.
Full text
5
Blazquez, Desamparados, Josep Domenech, José A. Gil, and Ana Pont. "Automatic detection of e-commerce availability from web data." In CARMA 2016 - 1st International Conference on Advanced Research Methods and Analytics. Valencia: Universitat Politècnica València, 2016. http://dx.doi.org/10.4995/carma2016.2016.3603.
Full textAbstract:
In the transition to the digital economy, the implementation of e-commerce strategies contributes to foster economic growth and obtain competitive advantages. Indeed, national and supranational statistics offices monitor the adoption of e-commerce solutions by conducting periodic surveys to businesses. However, the information about e-commerce adoption is often available online in each company corporate website, which is usually public and suitable for being automatically retrieved and processed.In this context, this work proposes and develops an intelligent system for automatically detecting and monitoring e-commerce availability by analyzing data retrieved from corporate websites. This system combines web scraping techniques with some learning methods for Big Data, and has been evaluated with a data set consisting of 426 corporate websites of manufacturing firms based in France and Spain.Results show that the proposed model reaches a classification precision of about 85% in the test set. A more detailed analysis evidences that websites with e-commerce tend to include some specific keywords and have a private area. Our proposal opens up the opportunity to monitor e-commerce adoption at a large scale, with highly granular information that otherwise would have required every firm to complete a survey.
6
Alibekov, M. R. "Diagnosis of Plant Biotic Stress by Methods of Explainable Artificial Intelligence." In 32nd International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2022. http://dx.doi.org/10.20948/graphicon-2022-728-739.
Full textAbstract:
Methods for digital image preprocessing, which significantly increase the efficiency of ML methods, and also a number of ML methods and models as a basis for constructing simple and efficient XAI networks for diagnosing plant biotic stresses, have been studied. A complex solution has been built, which includes the following stages: automatic segmentation; feature extraction; classification by ML models. The best classifiers and feature vectors are selected. The study was carried out on the open dataset PlantVillage Dataset. The single-layer perceptron (SLP) trained on a full vector of 92 features (20 statistical, 72 textural) became the best according to the F1- score=93% criterion. The training time on a PC with an Intel Core i5-8300H CPU took 189 minutes. According to the criterion “F1-score/number of features”, SLP trained on 7 principal components with F1-score=85% also became the best. Training time - 29 minutes. The criterion “F1- score/number+interpretability of features” favors the selected 9 features and the random forest model, F1-score=83%. The research software package is made in a modern version of Python using the OpenCV and deep learning model libraries, and is able for using in precision farming.
7
Chen, Yubao. "Intelligent Diagnosis of the Root Cause for Rejects in the Automatic Transmission Assembly Process." In ASME 1998 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 1998. http://dx.doi.org/10.1115/imece1998-1021.
Full textAbstract:
Abstract This paper presents a method for the diagnosis of reject root causes in automatic transmission assembly process based on the fuzzy multiple voting scheme. As the first step, data from all the valid test points were collected and studied based on their statistical characteristics. An information-gain-based procedure was followed to quantitatively evaluate the relevance of each test point to the diagnosis process. Accordingly, an objective rank of all relevant test points was generated for a particularly reject. The root cause of rejects was then identified by a procedure based on a fuzzy multiple voting classification algorithms. This method has been tested with top five rejects in a transmission assembly process and promising results have been obtained.
8
Lima Angelo dos Santos, Laura, Nadege Bize-Forest, Giovanna de Fraga Cameiro, Adna Grazielly Paz de Vasconcelos, and Patrick Pereira Machado. "Unsupervised Facies Pattern Recognition of Brazilian Pre-Salt Carbonates Borehole Images." In 2022 SPWLA 63rd Annual Symposium. Society of Petrophysicists and Well Log Analysts, 2022. http://dx.doi.org/10.30632/spwla-2022-0129.
Full textAbstract:
We apply our novel automated image interpretation workflow to Brazilian pre-salt ultrasonic borehole image data. We obtain an immediate, un-biased classification of the full data, requiring no further input data beyond the borehole image itself. This interactive solution combines statistical and deep learning algorithms for image embedding to provide data-driven, multi-purpose borehole image interpretation. Borehole images are a source of important information for building static reservoir models. Textures observed in these high-resolution well logs are the results of and provide insights into the different processes that have occurred: from the moment of the deposition until the image acquisition. Each field, reservoir, well, and interval has a unique textural assemblage, consequence of its own depositional facies, diagenetic processes, geomechanics and wellbore conditions or well intervention and completion. Efforts to automate facies interpretation in our industry often rely on applying supervised machine learning models. These supervised algorithms are restricted to executing very specific tasks, based on extensive amounts of consistently labeled data. In the example of depositional geological classification, generating labeled data can be a complex and extensive task, subject to interpreters’ experience – resulting in a low human performance benchmark. The solution proposed here comprises a sequence of five steps: • Prepare data; • Apply a first embedding step using statisticalmethods or convolutional autoencoders; • Apply PCA or t-SNE techniques as the secondembedding step; • Perform manual or automatic clustering; • Finally, assign a facies class to each textural group. This paper discusses applying this innovative workflow to acoustic borehole images of pre-salt carbonates from the Santos basin. Various preprocessing and embedding options were tested and compared to the geological core interpretation. Using statistics, semi-supervised t-SNE and k-means clustering methods, we divide the data into textural groups and describe these groups according to their distinct geological, diagenetic or geomechanical characteristics. With this new approach, facies are defined based solely on borehole image logs in a fast, consistent and less user-biased form. Ultimately, our innovative workflow allows us to not only gain insights into the depositional, geological and geomechanical processes and their correlation with the pre-salt carbonates reservoir quality, but to establish a more efficient, reliable method for borehole image interpretation in general.
9
Britto, Larissa, and Luciano Pacífico. "Classificação de Espécies de Plantas Usando Extreme Learning Machine." In Encontro Nacional de Inteligência Artificial e Computacional. Sociedade Brasileira de Computação - SBC, 2019. http://dx.doi.org/10.5753/eniac.2019.9268.
Full textAbstract:
Plants play an important role in nature, but correct plant species identification is still a challenging task for non-specialized people. Many works have been proposed towards the development of automatic plant species recognition systems through Machine Learning methods, but most of them lack the proper experimental analysis. In this work, we evaluate the performance of a general-purpose Artificial Neural Network to perform plant classification task: the Extreme Learning Machine (ELM).We compare ELM with several classifiers from plant recognition literature by means of three real-world data sets obtained from different image processing and feature extraction processes. A statistical hypothesis test is employed to perform proper experimental evaluation.
10
Bobby, Thomas Christy, and Swaminathan Ramakrishnan. "Evaluation of Human Femur Bone Radiographic Images Using AdaBoost and Support Vector Machines." In ASME 2011 International Mechanical Engineering Congress and Exposition. ASMEDC, 2011. http://dx.doi.org/10.1115/imece2011-65107.
Full textAbstract:
In this work, classification of normal and abnormal human femur bone images are carried out using Support Vector Machines (SVM) and AdaBoost classifiers. The trabecular (soft bone) regions of human femur bone images (N = 44) recorded under standard conditions are used for the study. The acquired images are subjected to auto threshold binarization algorithm to recognize the presence of mineralization and trabecular structures in the digitized images. The mechanical strength regions such as primary compressive and tensile are delineated by semi-automated image processing methods from the digitized femur bone images. The first and higher order statistical parameters are calculated from the intensity values of the delineated regions of interest and their gray level co-occurrence matrices respectively. The significant parameters are found using principal component analysis. The first two most significant parameters are used as input to the classifiers. Statistical classification tools such as SVM and AdaBoost are employed for the classification. Results show that the AdaBoost classifier performs better in terms of sensitivity and specificity for the chosen parameters for primary compressive and tensile regions compared to SVM.
Reports on the topic "Automatic classification Statistical methods"
1
Ryan, F. M., D. N. Anderson, K. K. Anderson, D. N. Hagedorn, K. T. Higbee, N. E. Miller, T. Redgate, and A. C. Rohay. Statistical classification methods applied to seismic discrimination. Office of Scientific and Technical Information (OSTI), June 1996. http://dx.doi.org/10.2172/257361.
Full text
2
Engel, Bernard, Yael Edan, James Simon, Hanoch Pasternak, and Shimon Edelman. Neural Networks for Quality Sorting of Agricultural Produce. United States Department of Agriculture, July 1996. http://dx.doi.org/10.32747/1996.7613033.bard.
Full textAbstract:
The objectives of this project were to develop procedures and models, based on neural networks, for quality sorting of agricultural produce. Two research teams, one in Purdue University and the other in Israel, coordinated their research efforts on different aspects of each objective utilizing both melons and tomatoes as case studies. At Purdue: An expert system was developed to measure variances in human grading. Data were acquired from eight sensors: vision, two firmness sensors (destructive and nondestructive), chlorophyll from fluorescence, color sensor, electronic sniffer for odor detection, refractometer and a scale (mass). Data were analyzed and provided input for five classification models. Chlorophyll from fluorescence was found to give the best estimation for ripeness stage while the combination of machine vision and firmness from impact performed best for quality sorting. A new algorithm was developed to estimate and minimize training size for supervised classification. A new criteria was established to choose a training set such that a recurrent auto-associative memory neural network is stabilized. Moreover, this method provides for rapid and accurate updating of the classifier over growing seasons, production environments and cultivars. Different classification approaches (parametric and non-parametric) for grading were examined. Statistical methods were found to be as accurate as neural networks in grading. Classification models by voting did not enhance the classification significantly. A hybrid model that incorporated heuristic rules and either a numerical classifier or neural network was found to be superior in classification accuracy with half the required processing of solely the numerical classifier or neural network. In Israel: A multi-sensing approach utilizing non-destructive sensors was developed. Shape, color, stem identification, surface defects and bruises were measured using a color image processing system. Flavor parameters (sugar, acidity, volatiles) and ripeness were measured using a near-infrared system and an electronic sniffer. Mechanical properties were measured using three sensors: drop impact, resonance frequency and cyclic deformation. Classification algorithms for quality sorting of fruit based on multi-sensory data were developed and implemented. The algorithms included a dynamic artificial neural network, a back propagation neural network and multiple linear regression. Results indicated that classification based on multiple sensors may be applied in real-time sorting and can improve overall classification. Advanced image processing algorithms were developed for shape determination, bruise and stem identification and general color and color homogeneity. An unsupervised method was developed to extract necessary vision features. The primary advantage of the algorithms developed is their ability to learn to determine the visual quality of almost any fruit or vegetable with no need for specific modification and no a-priori knowledge. Moreover, since there is no assumption as to the type of blemish to be characterized, the algorithm is capable of distinguishing between stems and bruises. This enables sorting of fruit without knowing the fruits' orientation. A new algorithm for on-line clustering of data was developed. The algorithm's adaptability is designed to overcome some of the difficulties encountered when incrementally clustering sparse data and preserves information even with memory constraints. Large quantities of data (many images) of high dimensionality (due to multiple sensors) and new information arriving incrementally (a function of the temporal dynamics of any natural process) can now be processed. Furhermore, since the learning is done on-line, it can be implemented in real-time. The methodology developed was tested to determine external quality of tomatoes based on visual information. An improved model for color sorting which is stable and does not require recalibration for each season was developed for color determination. Excellent classification results were obtained for both color and firmness classification. Results indicted that maturity classification can be obtained using a drop-impact and a vision sensor in order to predict the storability and marketing of harvested fruits. In conclusion: We have been able to define quantitatively the critical parameters in the quality sorting and grading of both fresh market cantaloupes and tomatoes. We have been able to accomplish this using nondestructive measurements and in a manner consistent with expert human grading and in accordance with market acceptance. This research constructed and used large databases of both commodities, for comparative evaluation and optimization of expert system, statistical and/or neural network models. The models developed in this research were successfully tested, and should be applicable to a wide range of other fruits and vegetables. These findings are valuable for the development of on-line grading and sorting of agricultural produce through the incorporation of multiple measurement inputs that rapidly define quality in an automated manner, and in a manner consistent with the human graders and inspectors.
3
Burks, Thomas F., Victor Alchanatis, and Warren Dixon. Enhancement of Sensing Technologies for Selective Tree Fruit Identification and Targeting in Robotic Harvesting Systems. United States Department of Agriculture, October 2009. http://dx.doi.org/10.32747/2009.7591739.bard.
Full textAbstract:
The proposed project aims to enhance tree fruit identification and targeting for robotic harvesting through the selection of appropriate sensor technology, sensor fusion, and visual servo-control approaches. These technologies will be applicable for apple, orange and grapefruit harvest, although specific sensor wavelengths may vary. The primary challenges are fruit occlusion, light variability, peel color variation with maturity, range to target, and computational requirements of image processing algorithms. There are four major development tasks in original three-year proposed study. First, spectral characteristics in the VIS/NIR (0.4-1.0 micron) will be used in conjunction with thermal data to provide accurate and robust detection of fruit in the tree canopy. Hyper-spectral image pairs will be combined to provide automatic stereo matching for accurate 3D position. Secondly, VIS/NIR/FIR (0.4-15.0 micron) spectral sensor technology will be evaluated for potential in-field on-the-tree grading of surface defect, maturity and size for selective fruit harvest. Thirdly, new adaptive Lyapunov-basedHBVS (homography-based visual servo) methods to compensate for camera uncertainty, distortion effects, and provide range to target from a single camera will be developed, simulated, and implemented on a camera testbed to prove concept. HBVS methods coupled with imagespace navigation will be implemented to provide robust target tracking. And finally, harvesting test will be conducted on the developed technologies using the University of Florida harvesting manipulator test bed. During the course of the project it was determined that the second objective was overly ambitious for the project period and effort was directed toward the other objectives. The results reflect the synergistic efforts of the three principals. The USA team has focused on citrus based approaches while the Israeli counterpart has focused on apples. The USA team has improved visual servo control through the use of a statistical-based range estimate and homography. The results have been promising as long as the target is visible. In addition, the USA team has developed improved fruit detection algorithms that are robust under light variation and can localize fruit centers for partially occluded fruit. Additionally, algorithms have been developed to fuse thermal and visible spectrum image prior to segmentation in order to evaluate the potential improvements in fruit detection. Lastly, the USA team has developed a multispectral detection approach which demonstrated fruit detection levels above 90% of non-occluded fruit. The Israel team has focused on image registration and statistical based fruit detection with post-segmentation fusion. The results of all programs have shown significant progress with increased levels of fruit detection over prior art.