Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 1,171 records · Page 65Linked to original sources
PubMed1999

A space-time delay neural network for motion recognition and its application to lipreading.

Motion recognition has received increasing attention in recent years owing to heightened demand for computer vision in many domains, including the surveillance system, multimodal human computer interface, and traffic control system. Most conventional approaches classify the motion recognition task into partial feature extraction and time-domain recognition subtasks. However, the information of motion resides in the space-time domain instead of the time domain or space domain independently, implying that fusing the feature extraction and classification in the space and time domains into a single framework is preferred. Based on this notion, this work presents a novel Space-Time Delay Neural Network (STDNN) capable of handling the space-time dynamic information for motion recognition. The STDNN is unified structure, in which the low-level spatiotemporal feature extraction and high-level space-time-domain recognition are fused. The proposed network possesses the spatiotemporal shift-invariant recognition ability that is inherited from the time delay neural network (TDNN) and space displacement neural network (SDNN), where TDNN and SDNN are good at temporal and spatial shift-invariant recognition, respectively. In contrast to multilayer perceptron (MLP), TDNN, and SDNN, STDNN is constructed by vector-type nodes and matrix-type links such that the spatiotemporal information can be accurately represented in a neural network. Also evaluated herein is the performance of the proposed STDNN via two experiments. The moving Arabic numerals (MAN) experiment simulates the object's free movement in the space-time domain on image sequences. According to these results, STDNN possesses a good generalization ability with respect to the spatiotemporal shift-invariant recognition. In the lipreading experiment, STDNN recognizes the lip motions based on the inputs of real image sequences. This observation confirms that STDNN yields a better performance than the existing TDNN-based system, particularly in terms of the generalization ability. In addition to the lipreading application, the STDNN can be applied to other problems since no domain-dependent knowledge is used in the experiment.

Algorithms↗
PubMed1998

Neural network modeling of developmental effects in discrimination shifts.

This paper presents neural network simulations of developmental phenomena in discrimination shifts. The discrimination shift literature is reviewed in order to identify the empirical regularities. Leading theoretical accounts of the development of shift learning are reviewed, and the lack of a thorough account is highlighted. Recent unsuccessful neural network simulations of shift learning are also reviewed. New simulations, using the cascade-correlation algorithm, show that networks can capture the regularities of the discrimination shift literature better than existing psychological theories. Manipulation of the amount of training that networks receive, which affects depth of learning, simulates developmental phenomena. It is suggested that human developmental differences in shift learning arise from spontaneous overtraining by older participants, an interpretation consistent with the overtraining literature.

Adult↗
PubMed1999

Analog circuits for modeling biological neural networks: design and applications.

Computational neuroscience is emerging as a new approach in biological neural networks studies. In an attempt to contribute to this field, we present here a modeling work based on the implementation of biological neurons using specific analog integrated circuits. We first describe the mathematical basis of such models, then present analog emulations of different neurons. Each model is compared to its biological real counterpart as well as its numerical computation. Finally, we demonstrate the possible use of these analog models to interact dynamically with real cells through artificial synapses within hybrid networks. This method is currently used to explore neural networks dynamics.

Animals↗
PubMed2001

Neural networks distinguish between taste qualities based on receptor cell population responses.

Response features of taste receptor cell action potentials were examined using an artificial neural network to determine whether they contain information about taste quality. Using the loose patch technique to record from hamster taste buds in vivo we recorded population responses of single fungiform papillae to NaCl (100 mM), sucrose (200 mM) and the synthetic sweetener NC-00274-01 (NC-01) (200 microM). Features of each response describing both burst and inter-burst characteristics were then presented to an artificial neural network for pairwise classification of taste stimuli. Responses to NaCl could be distinguished from those to both NC-01 and sucrose with accuracies of up to 86%. In contrast, pairwise comparisons between sucrose and NC-01 were not successful, scoring at chance (50%). Also, comparisons between two different concentrations of NaCl, 0.01 and 0.005 M, scored at chance. Pairwise comparisons using only those features that relate to the inter-burst behavior of the response (i.e. bursting rate) did not hinder the performance of the neural network as both sweeteners versus NaCl received scores of 75--85%. Comparisons using features corresponding to each individual burst scored poorly, receiving scores only slightly above chance. We then compared the sweeteners with varying concentrations of NaCl (0.1, 0.01, 0.005 and 0.001 M) using only those features corresponding to bursting rate within a 1 s time window. The neural network was capable of distinguishing between NaCl and NC-01 at all concentrations tested; while comparisons between NaCl and sucrose received high scores at all concentrations except 0.001 M. These results show that two different taste qualities can be distinguished from each other based solely on the bursting rates of action potentials in single taste buds and that this distinction is independent of stimulation intensity down to 0.001 M NaCl. These data suggest that action potentials in taste receptor cells may play a role in taste quality coding.

Action Potentials↗
PubMed2000

Classification of rat behavior with an image-processing method and a neural network.

Video recordings of 11 rats were digitized at five frames per second, and parameters describing the shape and the position of the rat were calculated. The behavior displayed by the rats was observed by an experienced observer. Separate neural networks were trained and validated, using the data for each individual rat. The neural networks correctly classified an average of 76.53% of the frames in the validation set and 98.18% of the frames in the training set. A single neural network was trained with 6 rats and validated with 5 rats. The neural network correctly classified 63.74% of the frames in the validation set and 82.85% of the frames in the training set.

Animals↗
PubMed2001

Neural network and regression predictions of 5-year survival after colon carcinoma treatment.

BACKGROUND: The Commission on Cancer data from the National Cancer Data Base (NCDB) for patients with colon carcinoma was used to develop several artificial neural network and regression-based models. These models were designed to predict the likelihood of 5-year survival after primary treatment for colon carcinoma. METHODS: Two modeling methods were used in the study. Artificial neural networks were used to select the more important variables from the NCDB database and model 5-year survival. A standard parametric logistic regression also was used to model survival and the two methods compared on a prospective set of patients not used in model development. RESULTS: The neural network yielded a receiver operating characteristic (ROC) area of 87.6%. At a sensitivity to mortality of 95% the specificity was 41%. The logistic regression yielded a ROC area of 82% and at a sensitivity to mortality of 95% gave a specificity of 27%. CONCLUSIONS: The neural network found a strong pattern in the database predictive of 5-year survival status. The logistic regression produced somewhat less accurate, but good, results.

Aged↗
PubMed1998

[Medical use of artificial neural networks].

The main aim of the research in medical diagnostics is to develop more exact, cost-effective and handsome systems, procedures and methods for supporting the clinicians. In their paper the authors introduce a new method that recently came into the focus referred to as artificial neural networks. Based on the literature of the past 5-6 years they give a brief review--highlighting the most important ones--showing the idea behind neural networks, what they are used for in the medical field. The definition, structure and operation of neural networks are discussed. In the application part they collect examples in order to give an insight in the neural network application research. It is emphasised that in the near future basically new diagnostic equipment can be developed based on this new technology in the field of ECG, EEG and macroscopic and microscopic image analysis systems.

Artificial Intelligence↗
PubMed1995

Artificial neural networks for recognition of electrocardiographic lead reversal.

Misplacement of electrodes during the recording of an electrocardiogram (ECG) can cause an incorrect interpretation, misdiagnosis, and subsequent lack of proper treatment. The purpose of this study was twofold: (1) to develop artificial neural networks that yield peak sensitivity for the recognition of right/left arm lead reversal at a very high specificity; and (2) to compare the performances of the networks with those of 2 widely used rule-based interpretation programs. The study was based on 11,009 ECGs recorded in patients at an emergency department using computerized electrocardiographs. Each of the ECGs was used to computationally generate an ECG with right/left arm lead reversal. Neural networks were trained to detect ECGs with right/left arm lead reversal. Different networks and rule-based criteria were used depending on the presence or absence of P waves. The networks and the criteria all showed a very high specificity (99.87% to 100%). The neural networks performed better than the rule-based criteria, both when P waves were present (sensitivity 99.1%) or absent (sensitivity 94.5%). The corresponding sensitivities for the best criteria were 93.9% and 39.3%, respectively. An estimated 300 million ECGs are recorded annually in the world. The majority of these recordings are performed using computerized electrocardiographs, which include algorithms for detection of right/left arm lead reversals. In this study, neural networks performed better than conventional algorithms and the differences in sensitivity could result in 100,000 to 400,000 right/left arm lead reversals being detected by networks but not by conventional interpretation programs.

Algorithms↗
PubMed2004

Artificial neural networks and job-specific modules to assess occupational exposure.

Job-specific modules (JSMs) were used to collect information for expert retrospective exposure assessment in a community-based non-Hodgkins Lymphoma study in New South Wales, Australia. Using exposure assessment by a hygienist, artificial neural networks were developed to predict overall and intermittent benzene exposure among the module of tanker drivers. Even with a small data set (189 drivers), neural networks could assess benzene exposure with an average of 90% accuracy. By appropriate choice of cutoff (decision threshold), the neural networks could reliably reduce the expert's workload by approximately 60% by identifying negative JSMs. The use of artificial neural networks shows promise in future applications to occupational assessment by JSMs and expert assessment.

Benzene↗
PubMed1993

Artificial neural network analysis of pyrolysis mass spectrometric data in the identification of Streptomyces strains.

Sixteen representatives of three morphologically distinct groups of streptomycetes were recovered from soil using selective isolation procedures. Duplicated batches of the test strains were examined by Curie-point pyrolysis mass spectrometry and the first data set used for conventional multivariate statistical analyses and as a training set for an artificial neural network. The second set of data was used for 'operational fingerprinting' and for testing the artificial neural network. All of the test strains were correctly identified using the artificial neural network whereas only fifteen of the sixteen strains were assigned to the correct group using the conventional operational fingerprinting procedure. Artificial neural network analysis of pyrolysis mass spectrometric data provides a rapid, cost-effective and reproducible way of identifying and typing large numbers of microorganisms.

Bacterial Typing Techniques↗
PubMed2003

Design and training of a neural network for predicting the solvent accessibility of proteins.

A feed-forward neural network has been developed to predict the solvent accessibility/accessible surface area (ASA) of proteins using improved design and training methods. Several network issues ranging from the coding of ASA states to the problem of local minima of learning curve, have been addressed. Successful new approaches to overcome these problems are presented. Set of trained network weights for each ASA threshold is provided. It has been established that the prediction accuracy results with neural network are better than other reported results of ASA prediction, despite a high test to training data ratio.

Amino Acids↗
PubMed1999

Application of multilayer feed-forward neural networks to automated compound identification in low-resolution open-path FT-IR spectrometry.

A drawback of current open-path Fourier transform infrared (OP/FT-IR) systems is that they need a human expert to determine those compounds that may be quantified from a given spectrum. In this work, multilayer feed-forward neural networks with one hidden layer were used to automatically recognize compounds in an OP/FT-IR spectrum without compensation of absorption lines due to atmospheric H2O and CO2. The networks were trained by fast-back-propagation. The training set comprised spectra that were synthesized by digitally adding randomly scaled reference spectra to actual open-path background spectra measured over a variety of path lengths and temperatures. The reference spectra of 109 compounds were used to synthesize the training spectra. Each neural network was trained to recognize only one compound in the presence of up to 10 other interferences in an OP/FT-IR spectrum. Every compound in a database of vaporphase reference spectra can be encoded in an independent neural network so that a neural network library can be established. When these networks are used for the identification of compounds, the process is analogous to spectral library searching. The effect of learning rate and band intensities on the convergence of network training was examined. The networks were successfully used to recognize five alcohols and two chlorinated compounds in field-measured controlled-release OP/FT-IR spectra of mixtures of these compounds.

Neural Networks, Computer↗
PubMed2002

Using a neural network with flow cytometry histograms to recognize cell surface protein binding patterns.

Flow cytometric systems are being used increasingly in all branches of biological science including medicine. To develop analytic tools for identifying unknown molecules such as the antibodies that recognize different structure in the identical antigens, we explored use of a neural network in flow cytometry data comparison. Peak locations were extracted from flow cytometry histograms and we used the Marquardt backpropagation neural networks to recognize identical or similar binding patterns between antibodies and antigens based on the peak locations. The neural network showed 93.8% to 99.6% correct classification rates for identical or similar molecules. This suggests that the neural network technique can be useful in flow cytometry histogram data analysis.

Antibodies, Monoclonal↗
PubMedDate not supplied

[Application of neural networks using the volume learning algorithm for the study of structure-activity relationship in chemical compounds].

A volume learning algorithm for artificial neural networks was developed to quantitatively describe the three-dimensional structure-activity relationships using as an example N-benzylpiperidine derivatives. The new algorithm combines two types of neural networks, the Kohonen and the feed-forward artificial neural networks, which are used to analyze the input grid data generated by the comparative molecular field approach. Selection of the most informative parameters using the algorithm helped to reveal the most important spatial properties of the molecules, which affect their biological activities. Cluster regions determined using the new algorithm adequately predicted the activity of molecules from a control data set.

Algorithms↗
PubMed2001

Categorization of fetal heart rate patterns using neural networks.

Digitized data from CTG (cardiotocography) measurements (fetal heart rate and uterine contractions) have been used for categorization of typical heart rate patterns before and during delivery. Short time series of CTG data, about 7 min duration, have been used in the categorization process. In the first part of the study, selected CTG data corresponding to 10 typical cases were used for purely auto associative unsupervised training of a Self-Organizing Map Neural Network (SOM). The network may then be used for objective categorization of CTG patterns through the map coordinates produced by the network. The SOM coordinates were then compared. In the second part of the study, a hybrid neural network consisting of a SOM network and a Back-Propagation network (BP) was trained with data corresponding to a number of basic heart rate patterns as described by eight manually selected indices. Test data (different than the training data) were then used to check the performance of the network. The present study shows that the categorization process, in which neural networks were used, can be reliable and agree well with the manual categorization. Since the categorization by neural networks is very fast and does not involve human efforts, it may be useful in patient monitoring.

Cardiotocography↗
PubMed1999

Identification of hemifield single trial PVEP on the basis of generalized dynamic neural network classifiers.

This paper is concerned with the application of generalized dynamic neural networks for the identification of hemifield pattern-reversal visual evoked potentials. The identification process is performed by different networks with time-varying weights using signals from different electrode positions as external inputs. Since dynamic neural networks are able to process time-varying signals, the identification of the stimulated hemiretinae is performed without feature extraction. The performance of the method presented is compared with a reference method based on the values of instantaneous frequency at the occipital electrode positions at P100 latency.

Adult↗
PubMed1997

A neural network approach to markerless measurement of human motion.

Most automatic motion analysis system operates by tracking markers across a field of view. The markers are usually attached to the skin at the joints. For some applications such as measuring the motion of elderly and the disabled persons, this approach can be uncomfortable which ultimately can affect the motion itself. The protocol of some markers can also be a problem for example active markers using infra-red LEDs must continuously be in the field of view of the detectors at all times. This will impose restriction in the motion. Therefore a marker free method is an attractive proposition. Such an approach would allow the subject to move freely thus exhibiting a more natural movement. We have developed a PC based system which uses frames from the video or photographic capture of a motion in the frontal and sagital plane. Key frames are selected and co-ordinate positions of the joints are identified. Joint angles are calculated from these positions based on a multiple link model of the human figure. The angles are then used as training data for a fully connected neural network. The neural network generates a model of the captured motion which is used to reproduce closely the actual motion.

Analog-Digital Conversion↗
PubMed1994

NNERVE: neural network extraction of repetitive vectors for electromyography--Part I: Algorithm.

Artificial neural network (ANN) based signal processing methods have been shown to have significant robustness in processing complex, degraded, noisy, and unstable signals. A novel approach to automated electromyogram (EMG) signal decomposition, using an ANN processing architecture, is presented in this paper. Due to the lack of a priori knowledge of motor unit action potential (MUAP) morphology, the EMG decomposition must be performed in an unsupervised manner. An ANN classifier, consisting of a multilayer perceptron neural network and employing a novel unsupervised training strategy, is proposed. The ANN learns repetitive appearances of MUAP waveforms from their suspected occurrences in a filtered EMG signal in an autoassociative learning task. The same training waveforms are fed into the trained ANN and the output of the ANN is fed back to its input, giving rise to a dynamic retrieval net classifier. For each waveform in the data, the network discovers a feature vector associated with that waveform. For each waveform, classification is achieved by comparing its feature vector with those of the other waveforms. Firing information of each MUAP is further used to refine the classification results of the ANN classifier. Then, individual MUAP waveform shapes are derived and their firing tables are created.

Algorithms↗