SEARCH · PubMed Health

Results for “machine learning algorithms”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 487 records · Page 27Linked to original sources

PubMed1999

Comparing expert systems for identifying chest x-ray reports that support pneumonia.

We compare the performance of four computerized methods in identifying chest x-ray reports that support acute bacterial pneumonia. Two of the computerized techniques are constructed from expert knowledge, and two learn rules and structure from data. The two machine learning systems perform as well as the expert constructed systems. All of the computerized techniques perform better than a baseline keyword search and a lay person, and perform as well as a physician. We conclude that machine learning can be used to identify chest x-ray reports that support pneumonia.

Algorithms↗

PubMed2006

Multitraining support vector machine for image retrieval.

Relevance feedback (RF) schemes based on support vector machines (SVMs) have been widely used in content-based image retrieval (CBIR). However, the performance of SVM-based RF approaches is often poor when the number of labeled feedback samples is small. This is mainly due to 1) the SVM classifier being unstable for small-size training sets because its optimal hyper plane is too sensitive to the training examples; and 2) the kernel method being ineffective because the feature dimension is much greater than the size of the training samples. In this paper, we develop a new machine learning technique, multitraining SVM (MTSVM), which combines the merits of the cotraining technique and a random sampling method in the feature space. Based on the proposed MTSVM algorithm, the above two problems can be mitigated. Experiments are carried out on a large image set of some 20,000 images, and the preliminary results demonstrate that the developed method consistently improves the performance over conventional SVM-based RFs in terms of precision and standard deviation, which are used to evaluate the effectiveness and robustness of a RF algorithm, respectively.

Algorithms↗

PubMed2006

[Non-linear registration of MR brain images integrated with machine learning].

This paper presents a machine learning method to select best geometric features for deformable brain registration for each brain location. By incorporating those learned best attribute vector into the framework of HAMMER registration algorithm, The accuracy has increased by about 10% in estimating the simulated deformation fields. At the same time, on real MR brain images, we have found a great deal of improvement of registration in cortical regions.

Algorithms↗

PubMed2006

A novel incremental principal component analysis and its application for face recognition.

Principal component analysis (PCA) has been proven to be an efficient method in pattern recognition and image analysis. Recently, PCA has been extensively employed for face-recognition algorithms, such as eigenface and fisherface. The encouraging results have been reported and discussed in the literature. Many PCA-based face-recognition systems have also been developed in the last decade. However, existing PCA-based face-recognition systems are hard to scale up because of the computational cost and memory-requirement burden. To overcome this limitation, an incremental approach is usually adopted. Incremental PCA (IPCA) methods have been studied for many years in the machine-learning community. The major limitation of existing IPCA methods is that there is no guarantee on the approximation error. In view of this limitation, this paper proposes a new IPCA method based on the idea of a singular value decomposition (SVD) updating algorithm, namely an SVD updating-based IPCA (SVDU-IPCA) algorithm. In the proposed SVDU-IPCA algorithm, we have mathematically proved that the approximation error is bounded. A complexity analysis on the proposed method is also presented. Another characteristic of the proposed SVDU-IPCA algorithm is that it can be easily extended to a kernel version. The proposed method has been evaluated using available public databases, namely FERET, AR, and Yale B, and applied to existing face-recognition algorithms. Experimental results show that the difference of the average recognition accuracy between the proposed incremental method and the batch-mode method is less than 1%. This implies that the proposed SVDU-IPCA method gives a close approximation to the batch-mode PCA method.

Algorithms↗

PubMed2006

Facial attractiveness: beauty and the machine.

This work presents a novel study of the notion of facial attractiveness in a machine learning context. To this end, we collected human beauty ratings for data sets of facial images and used various techniques for learning the attractiveness of a face. The trained predictor achieves a significant correlation of 0.65 with the average human ratings. The results clearly show that facial beauty is a universal concept that a machine can learn. Analysis of the accuracy of the beauty prediction machine as a function of the size of the training data indicates that a machine producing human-like attractiveness rating could be obtained given a moderately larger data set.

Algorithms↗

PubMed1997

Adaptive classification of two-dimensional gel electrophoretic spot patterns by neural networks and cluster analysis.

The interpretation of two-dimensional gel electrophoresis spot profiles can be facilitated by statistical and machine learning programs. Two different approaches to classification of spot profiles - cluster analysis and neural networks - are discussed. Neural networks for two different model patterns were designed and an algorithm for training of the net for the classification was developed. It was shown that the performance of neural networks is higher compared to cluster and principal component analysis. The possibility of combining both approaches into one process can increase reliability and speed of classification. Artificially created training sets with added random noise can be used for network training. The analysis was applied on the Streptomyces coelicolor developmental two-dimensional (2-D) gel database.

Cluster Analysis↗

PubMed2006

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

Algorithms↗

PubMed2001

Knowledge discovery approach to automated cardiac SPECT diagnosis.

The paper describes a computerized process of myocardial perfusion diagnosis from cardiac single proton emission computed tomography (SPECT) images using data mining and knowledge discovery approach. We use a six-step knowledge discovery process. A database consisting of 267 cleaned patient SPECT images (about 3000 2D images), accompanied by clinical information and physician interpretation was created first. Then, a new user-friendly algorithm for computerizing the diagnostic process was designed and implemented. SPECT images were processed to extract a set of features, and then explicit rules were generated, using inductive machine learning and heuristic approaches to mimic cardiologist's diagnosis. The system is able to provide a set of computer diagnoses for cardiac SPECT studies, and can be used as a diagnostic tool by a cardiologist. The achieved results are encouraging because of the high correctness of diagnoses.

Artificial Intelligence↗

PubMed2006

The use of genetic programming in the analysis of quantitative gene expression profiles for identification of nodal status in bladder cancer.

BACKGROUND: Previous studies on bladder cancer have shown nodal involvement to be an independent indicator of prognosis and survival. This study aimed at developing an objective method for detection of nodal metastasis from molecular profiles of primary urothelial carcinoma tissues. METHODS: The study included primary bladder tumor tissues from 60 patients across different stages and 5 control tissues of normal urothelium. The entire cohort was divided into training and validation sets comprised of node positive and node negative subjects. Quantitative expression profiling was performed for a panel of 70 genes using standardized competitive RT-PCR and the expression values of the training set samples were run through an iterative machine learning process called genetic programming that employed an N-fold cross validation technique to generate classifier rules of limited complexity. These were then used in a voting algorithm to classify the validation set samples into those associated with or without nodal metastasis. RESULTS: The generated classifier rules using 70 genes demonstrated 81% accuracy on the validation set when compared to the pathological nodal status. The rules showed a strong predilection for ICAM1, MAP2K6 and KDR resulting in gene expression motifs that cumulatively suggested a pattern ICAM1 > MAP2K6 > KDR for node positive cases. Additionally, the motifs showed CDK8 to be lower relative to ICAM1, and ANXA5 to be relatively high by itself in node positive tumors. Rules generated using only ICAM1, MAP2K6 and KDR were comparably robust, with a single representative rule producing an accuracy of 90% when used by itself on the validation set, suggesting a crucial role for these genes in nodal metastasis. CONCLUSION: Our study demonstrates the use of standardized quantitative gene expression values from primary bladder tumor tissues as inputs in a genetic programming system to generate classifier rules for determining the nodal status. Our method also suggests the involvement of ICAM1, MAP2K6, KDR, CDK8 and ANXA5 in unique mathematical combinations in the progression towards nodal positivity. Further studies are needed to identify more class-specific signatures and confirm the role of these genes in the evolution of nodal metastasis in bladder cancer.

Algorithms↗

PubMed2003

Functional discrimination of gene expression patterns in terms of the gene ontology.

The ever-growing amount of experimental data in molecular biology and genetics requires its automated analysis, by employing sophisticated knowledge discovery tools. We use an Inductive Logic Programming (ILP) learner to induce functional discrimination rules between genes studied using microarrays and found to be differentially expressed in three recently discovered subtypes of adenocarcinoma of the lung. The discrimination rules involve functional annotations from the Proteome HumanPSD database in terms of the Gene Ontology, whose hierarchical structure is essential for this task. While most of the lower levels of gene expression data (pre)processing have been automated, our work can be seen as a step toward automating the higher level functional analysis of the data. We view our application not just as a prototypical example of applying more sophisticated machine learning techniques to the functional analysis of genes, but also as an incentive for developing increasingly more sophisticated functional annotations and ontologies, that can be automatically processed by such learning algorithms.

Adenocarcinoma↗

PubMed2005

PCP: a program for supervised classification of gene expression profiles.

UNLABELLED: PCP (Pattern Classification Program) is an open-source machine learning program for supervised classification of patterns (vectors of measurements). The principal use of PCP in bioinformatics is design and evaluation of classifiers for use in clinical diagnostic tests based on measurements of gene expression. PCP implements leading pattern classification and gene selection algorithms and incorporates cross-validation estimation of classifier performance. Importantly, the implementation integrates gene selection and class prediction stages, which is vital for computing reliable performance estimates in small-sample scenarios. Additionally, the program includes automated and efficient model selection (optimization of parameters) for support vector machine (SVM) classifier. The distribution includes Linux and Windows/Cygwin binaries. The program can easily be ported to other platforms. AVAILABILITY: Free download at http://pcp.sourceforge.net

Algorithms↗

PubMed2004

Towards the development of a conceptual distance metric for the UMLS.

The objective of this work is to investigate the feasibility of conceptual similarity metrics in the framework of the Unified Medical Language System (UMLS). We have investigated an approach based on the minimum number of parent links between concepts, and evaluated its performance relative to human expert estimates on three sets of concepts for three terminologies within the UMLS (i.e., MeSH, ICD9CM, and SNOMED). The resulting quantitative metric enables computer-based applications that use decision thresholds and approximate matching criteria. The proposed conceptual matching supports problem solving and inferencing (using high-level, generic concepts) based on readily available data (typically represented as low-level, specific concepts). Through the identification of semantically similar concepts, conceptual matching also enables reasoning in the absence of exact, or even approximate, lexical matching. Finally, conceptual matching is relevant for terminology development and maintenance, machine learning research, decision support system development, and data mining research in biomedical informatics and other fields.

Algorithms↗

PubMed2004

Prediction of transmembrane regions of beta-barrel proteins using ANN- and SVM-based methods.

This article describes a method developed for predicting transmembrane beta-barrel regions in membrane proteins using machine learning techniques: artificial neural network (ANN) and support vector machine (SVM). The ANN used in this study is a feed-forward neural network with a standard back-propagation training algorithm. The accuracy of the ANN-based method improved significantly, from 70.4% to 80.5%, when evolutionary information was added to a single sequence as a multiple sequence alignment obtained from PSI-BLAST. We have also developed an SVM-based method using a primary sequence as input and achieved an accuracy of 77.4%. The SVM model was modified by adding 36 physicochemical parameters to the amino acid sequence information. Finally, ANN- and SVM-based methods were combined to utilize the full potential of both techniques. The accuracy and Matthews correlation coefficient (MCC) value of SVM, ANN, and combined method are 78.5%, 80.5%, and 81.8%, and 0.55, 0.63, and 0.64, respectively. These methods were trained and tested on a nonredundant data set of 16 proteins, and performance was evaluated using "leave one out cross-validation" (LOOCV). Based on this study, we have developed a Web server, TBBPred, for predicting transmembrane beta-barrel regions in proteins (available at http://www.imtech.res.in/raghava/tbbpred).

Algorithms↗

PubMedDate not supplied

Autonomous mental development in high dimensional context and action spaces.

Autonomous Mental Development (AMD) of robots opened a new paradigm for developing machine intelligence, using neural network type of techniques and it fundamentally changed the way an intelligent machine is developed from manual to autonomous. The work presented here is a part of SAIL (Self-Organizing Autonomous Incremental Learner) project which deals with autonomous development of humanoid robot with vision, audition, manipulation and locomotion. The major issue addressed here is the challenge of high dimensional action space (5-10) in addition to the high dimensional context space (hundreds to thousands and beyond), typically required by an AMD machine. This is the first work that studies a high dimensional (numeric) action space in conjunction with a high dimensional perception (context state) space, under the AMD mode. Two new learning algorithms, Direct Update on Direction Cosines (DUDC) and High-Dimensional Conjugate Gradient Search (HCGS), are developed, implemented and tested. The convergence properties of both the algorithms and their targeted applications are discussed. Autonomous learning of speech production under reinforcement learning is studied as an example.

Learning↗

PubMed1996

Structure-activity relationships derived by machine learning: the use of atoms and their bond connectivities to predict mutagenicity by inductive logic programming.

We present a general approach to forming structure-activity relationships (SARs). This approach is based on representing chemical structure by atoms and their bond connectivities in combination with the inductive logic programming (ILP) algorithm PROGOL. Existing SAR methods describe chemical structure by using attributes which are general properties of an object. It is not possible to map chemical structure directly to attribute-based descriptions, as such descriptions have no internal organization. A more natural and general way to describe chemical structure is to use a relational description, where the internal construction of the description maps that of the object described. Our atom and bond connectivities representation is a relational description. ILP algorithms can form SARs with relational descriptions. We have tested the relational approach by investigating the SARs of 230 aromatic and heteroaromatic nitro compounds. These compounds had been split previously into two subsets, 188 compounds that were amenable to regression and 42 that were not. For the 188 compounds, a SAR was found that was as accurate as the best statistical or neural network-generated SARs. The PROGOL SAR has the advantages that it did not need the use of any indicator variables handcrafted by an expert, and the generated rules were easily comprehensible. For the 42 compounds, PROGOL formed a SAR that was significantly (P < 0.025) more accurate than linear regression, quadratic regression, and back-propagation. This SAR is based on an automatically generated structural alert for mutagenicity.

Algorithms↗

PubMed1999

Evaluating variable selection methods for diagnosis of myocardial infarction.

This paper evaluates the variable selection performed by several machine-learning techniques on a myocardial infarction data set. The focus of this work is to determine which of 43 input variables are considered relevant for prediction of myocardial infarction. The algorithms investigated were logistic regression (with stepwise, forward, and backward selection), backpropagation for multilayer perceptrons (input relevance determination), Bayesian neural networks (automatic relevance determination), and rough sets. An independent method (self-organizing maps) was then used to evaluate and visualize the different subsets of predictor variables. Results show good agreement on some predictors, but also variability among different methods; only one variable was selected by all models.

Algorithms↗

PubMed1994

Improving prediction of preterm birth using a new classification scheme and rule induction.

Prediction of preterm birth is a poorly understood domain. The existing manual methods of assessment of preterm birth are 17%-38% accurate. The machine learning system LERS was used for three different datasets about pregnant women. Rules induced by LERS were used in conjunction with a classification scheme of LERS, based on "bucket brigade algorithm" of genetic algorithms and enhanced by partial matching. The resulting prediction of preterm birth in new, unseen cases is much more accurate (68%-90%).

Algorithms↗

PubMed1996

A generalized hidden Markov model for the recognition of human genes in DNA.

We present a statistical model of genes in DNA. A Generalized Hidden Markov Model (GHMM) provides the framework for describing the grammar of a legal parse of a DNA sequence (Stormo & Haussler 1994). Probabilities are assigned to transitions between states in the GHMM and to the generation of each nucleotide base given a particular state. Machine learning techniques are applied to optimize these probabilities using a standardized training set. Given a new candidate sequence, the best parse is deduced from the model using a dynamic programming algorithm to identify the path through the model with maximum probability. The GHMM is flexible and modular, so new sensors and additional states can be inserted easily. In addition, it provides simple solutions for integrating cardinality constraints, reading frame constraints, "indels", and homology searching. The description and results of an implementation of such a gene-finding model, called Genie, is presented. The exon sensor is a codon frequency model conditioned on windowed nucleotide frequency and the preceding codon. Two neural networks are used, as in (Brunak, Engelbrecht, & Knudsen 1991), for splice site prediction. We show that this simple model performs quite well. For a cross-validated standard test set of 304 genes [ftp:@www-hgc.lbl.gov/pub/genesets] in human DNA, our gene-finding system identified up to 85% of protein-coding bases correctly with a specificity of 80%. 58% of exons were exactly identified with a specificity of 51%. Genie is shown to perform favorably compared with several other gene-finding systems.

Chromosomes, Human↗