Artificial Metaplasticity Research Articles

IMPROVED ARTIFICIAL NEURAL NETWORK FOR EPILEPTIC SEIZURES DETECTION

Electroencephalogram (EEG) is a fundamental and unique tool for exploring human brain activity in general and epileptic mechanism in particular. It offers significant information about epileptic seizures source known as epileptogenic area. However, it is often complicated to detect critical changes in EEG signals by visual examination, since this signal aspect of epileptic persons seems to be normal out of the seizure. Thus, the challenge is to design such a robust and automatic system to detect these unseen changes and use them for diagnosis. In this research, we apply the Artificial Metaplasticity Multi-Layer Perceptron (AMMLP) together with discrete wavelet transform (DWT) to Bonn EEG signals for seizure detection goal. Significant features were then extracted from the well-known EEG brainwaves. Aiming to decrease the computational time and improve classification accuracy, we performed a features ranking and selection employing the Relief algorithm. The obtained AMMLP classification accuracy of 98.97% proved the effctiveness of the applied approach. Our results were compared to recent researches results on the same database, proving to be superior or at least an interesting alternative for seizures detection within EEG signals.

Natural Language Processing method for the identification of the factors influencing road accident severity

Although road safety has improved in the last decades, the rate of accidents with severe and fatal consequences is still exceeding the safety objectives (European Commission 2019; World Health Organization 2018).This work explores the possibility of using Natural Language Processing (NLP) techniques for the automatic extraction of knowledge from road accidents reports, with the objective of supporting the safety management of the road infrastructure system (Persia et al. 2016).To this aim, we consider databases of textual reports on road accidents, provided by the local public authorities. These reports contain the descriptions of the accidents and the results of the post-accident investigations. The aim is to analyze the reports by NLP to extract the features that most influence the accidents, for informing road safety management.For the analysis of the reports, we develop a method that combines Hierarchical Dirichlet Processes (HDPs) (Teh et al. 2006), Artificial Neural Networks (ANNs) and a feature selection technique based on the Sequential Forward Selection (SFS) strategy (Marcano-Cedeño et al. 2010). HDPs allow representing each report as a mixture of topics, i.e. distributions of words co-occurring in the reports. In practice, each report is transformed into a vector whose elements are the degrees of membership to each topic, i.e. a measure of the contribution of each topic to the description of the report. ANNs are then used to classify the reports, represented by the extracted vectors, into classes characterizing the severity of the accident consequences. Finally, the SFS technique is used for identifying those topics which most influence the reports classification. In this way, the factors causing the accidents and influencing its evolution are automatically extracted. The developed method is validated considering a database of real accident reports.
 ReferencesEuropean Commission. 2019. “EU Road Safety Policy Framework 2021-2030 - Next Steps towards ‘Vision Zero.’” Brussels,19.6.2019 SWD(2019) 283 final.Marcano-Cedeño, A, J Quintanilla-Domínguez, M G Cortina-Januchs, and D Andina. 2010. “Feature Selection Using Sequential Forward Selection and Classification Applying Artificial Metaplasticity Neural Network.” In IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society, Glendale, AZ, 2845–50. https://doi.org/10.1109/IECON.2010.5675075.Persia, Luca, Davide Shingo, Flavia De Simone, Véronique Feypell, De La Beaumelle, George Yannis, Alexandra Laiou, et al. 2016. “Management of Road Infrastructure Safety.” Transportation Research Procedia 14: 3436–45. https://doi.org/10.1016/j.trpro.2016.05.303.Teh, Yee Whye, Michael I Jordan, Matthew J Beal, and David M Blei. 2006. “Hierarchical Dirichlet Processes.” Journal of the American Statistical Association, 1566–81. https://doi.org/10.1198/016214506000000302.World Health Organization. 2018. “Global Status Report on Road Safety.” Geneva: World Health Organization.

Fundamentals of artificial metaplasticity in radial basis function networks for breast cancer classification

Modern medicine generates data commonly used for the development of clinical decision support systems, whose usefulness often lies in the performance of the machine learning algorithms used for the processing of that data. Several lines of research seek to resemble artificial neural networks to biological ones by incorporating new bioinspired mechanisms. One of these mechanisms is the biological concept of metaplasticity, defined as the plasticity of synaptic plasticity and which has been shown to be directly related to learning and memory. It has also been shown that incorporating this mechanism into a multilayer perceptron improves the neural network performance in both accuracy and learning rate when diagnosing breast cancer. The early detection of breast cancer is one of the most important strategies to prevent deaths from this disease. In this work, we have modeled synaptic metaplasticity in a radial base function network, which converges faster than multilayer perceptrons, with the motivation to achieve a more accurate solution in the diagnosis of breast cancer.

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

Artificial metaplasticity is the machine learning algorithm inspired in the biological metaplasticity of neural synapses. Metaplasticity stands for plasticity of plasticity, and as long as plasticity is related to memory, metaplasticity is related to learning. Implemented in supervised learning assuming input patterns distribution or a related function, it has proved to be very efficient in performance and in training convergence for multidisciplinary applications. Now, for the first time, this kind of artificial metaplasticity is implemented in an unsupervised neural network, achieving also excellent results that are presented in this paper. To compare results, a modified self-organization map is applied to the classification of MIT-BIH cardiac arrhythmias database.

Microcalcifications Detection Using Image Processing

Breast cancer is the most common cause of death in women and the second leading cause of cancer deaths worldwide. Primary prevention in the early stages of the disease becomes complex as the causes remain almost unknown. However, some typical signatures of this disease, such as masses and microcalcifications appearing on mammograms, can be used to improve early diagnostic techniques, which is critical for women’s quality of life. X-ray mammography is the main test used for screening and early diagnosis, and its analysis and processing are the keys to improving breast cancer prognosis. In this work, an effective methodology to detect microcalcifications in digitized mammograms is presented. This methodology is based on the synergy of image processing, pattern recognition and artificial intelligence. The methodology consists in four stages: image selection, image enhancement and feature extraction based on mathematical morphology operations applying coordinate logic filters, image segmentation based on partitional clustering methods such as k-means and self organizing maps and finally a classifier such as an artificial metaplasticity multilayer perceptron. The proposed system constitutes a promising approach for the detection of Microcalcifications. The experimental results show that the proposed methodology can locate Microcalcifications in an efficient way. The best values obtained in the experimental results are: accuracy 99.93% and specificity 99.95%, These results are very competitive with those reported in the state of the art.

Tackling business intelligence with bioinspired deep learning

To tackle the complex problem of providing business intelligence solutions based on business data, bioinspired deep learning has to be considered. This paper focuses on the application of artificial metaplasticity learning in business intelligence systems as an alternative paradigm of achieving a deeper information extraction and learning from arbitrary size data sets. As a case study, artificial metaplasticity multilayer perceptron applied to the automation of credit approval decision based on collected client data is analyzed, showing its potential and improvements over the state-of-the-art techniques. This paper successfully introduces the relevant novelty that the artificial neural network itself estimates the pdf of the input data to be used in the metaplasticity learning, so it is much closer to the biologic reality than previous implementations of artificial metaplasticity.

Robustness of artificial metaplasticity learning algorithm

Artificial metaplasticity learning algorithm is inspired by the biological metaplasticity property of neurons and Shannon׳s information theory. It is based on the bio-inspired hypothesis that neurons do not learn in the same amount (metaplasticity of biological learning) from unfrequent patterns than from common ones, as the former are expected to contain more information than the latter (information entropy concept). On MLPs, the artificial metaplasticity can be formulated as an improvement in regular backpropagation algorithm by using a variable learning rate affecting all the weights in each iteration step and so resembling heterosynaptic plasticity of biological neurons. The variable rate involves statistical inference on the training set and it is common to successfully assume Gaussian distribution for the training patterns. Nevertheless, Gaussian assumption may diverge from the real one and using statistical information extracted from the training patterns may be necessary. In this research, robustness to significative variations on Gaussian assumption is evaluated using input sets generated with different probability distributions. For the cases where Gaussian assumption shows to degrade learning, a general algorithm is applied. This algorithm takes advantage of the inherent statistical inference performed by the MLP through the a posteriori probabilities of input patterns estimation provided by its outputs. The generality of this last algorithm for any input distribution is then demonstrated.

Cardiac arrhythmias classification using artificial metaplasticity algorithm

Electrocardiogram (ECG) arrhythmias such as ventricular and atrial arrhythmias are one of the common causes of death. These abnormalities of heart activity may cause immediate death or damage to the heart. If the abnormal symptoms can be detected and diagnosed early, time is saved to prevent the occurrence of heart attack. Therefore, it is necessary to have an effective method for early detection and early treatment. We propose, in this paper, an intelligent method to accurately classify the heartbeat of ECG signals through the Artificial Metaplasticity Multilayer Perceptron (AMMLP). The MIT-BIH database is used to classify arrhythmias into three different types: Premature Ventricular Contraction (PVC), Right Bundle Branch Block (RBBB) and Left Bundle Branch Block (LBBB); normal ECG signals are also used in the study. The obtained AMMLP classification accuracy of 98.25% is an excellent result compared to the classical MLP and recent classification techniques applied to the same database.

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC(©). The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC(©) and the outcome of the patient after a 3-5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

Artificial Metaplasticity can Improve Artificial Neural Networks Learning

Abstract Metaplasticity property of biological synapses is interpreted in this paper as the concept of placing greater emphasis on training patterns that are less frequent. A novel implementation is proposed in which, during the network learning phase, a priority is given to weight updating of less frequent activations over the more frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested on the Multilayer Perceptron type network with Backpropagation training. The results obtained for the chosen application show a much more efficient training, while at least maintaining the Multilayer Perceptron performance.

On the biological plausibility of artificial metaplasticity learning algorithm

The training algorithm studied in this paper is inspired by the biological metaplasticity property of neurons. During the training phase, the Artificial Metaplasticity Learning Algorithm could be considered a new probabilistic version of the presynaptic rule, as during this phase the algorithm assigns higher values for updating the weights in the less probable activations than in the ones with higher probability. The algorithm is proposed for Artificial Neural Networks in general, although results at the moment have only been implemented and tested for Multilayer Perceptrons. Tested on different multidisciplinary applications, experiments show a much more efficient training, improving also Multilayer Perceptron results till the performance of the best systems in the state of the art, systems that usually are much more complex.

WBCD breast cancer database classification applying artificial metaplasticity neural network

The correct diagnosis of breast cancer is one of the major problems in the medical field. From the literature it has been found that different pattern recognition techniques can help them to improve in this domain. These techniques can help doctors form a second opinion and make a better diagnosis. In this paper we present a novel improvement in neural network training for pattern classification. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon’s information theory. During the training phase the Artificial metaplasticity Multilayer Perceptron (AMMLP) algorithm gives priority to updating the weights for the less frequent activations over the more frequent ones. In this way metaplasticity is modeled artificially. AMMLP achieves a more effcient training, while maintaining MLP performance. To test the proposed algorithm we used the Wisconsin Breast Cancer Database (WBCD). AMMLP performance is tested using classification accuracy, sensitivity and specificity analysis, and confusion matrix. The obtained AMMLP classification accuracy of 99.26%, a very promising result compared to the Backpropagation Algorithm (BPA) and recent classification techniques applied to the same database.

Breast cancer classification applying artificial metaplasticity algorithm

A novel improvement in neural network training for pattern classification is presented in this paper. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon's information theory. This algorithm is applicable to artificial neural networks (ANNs) in general, although here it is applied to a multilayer perceptron (MLP). During the training phase, the artificial metaplasticity multilayer perceptron (AMMLP) algorithm assigns higher values for updating the weights in the less frequent activations than in the more frequent ones. AMMLP achieves a more efficient training and improves MLP performance. The well-known and readily available Wisconsin Breast Cancer Database (WBCD) has been used to test the algorithm. Performance of the AMMLP was tested through classification accuracy, sensitivity and specificity analysis, and confusion matrix analysis. The results obtained by AMMLP are compared with the backpropagation algorithm (BPA) and other recent classification techniques applied to the same database. The best result obtained so far with the AMMLP algorithm is 99.63%.