Bayesian Neural Network Algorithm Research Articles

Recognition of signs of Parkinson's disease based on the analysis of voice markers and motor activity

Objectives. The problem of IT diagnostics of signs of Parkinson's disease is solved by analyzing changes in the voice and slowing down the movement of patients. The urgency of the task is associated with the need for early diagnosis of the disease. A method of complex recognition of Parkinson's disease using machine learning is proposed, based on markers of voice analysis and changes in the patient's movements on known data sets.Methods. The time-frequency function (the wavelet function) and the Meyer kepstral coefficient function, the KNN algorithm (k-Nearest Neighbors, KNN) and the algorithm of a two-layer neural network are used for training and testing on publicly available datasets on speech changes and motion retardation in Parkinson's disease. A Bayesian optimizer is also used to improve the hyperparameters of the KNN algorithm.Results. The KNN algorithm was used for speech recognition of patients, the test accuracy of 94.7% was achieved in the diagnosis of Parkinson's disease by voice change. The Bayesian neural network algorithm was applied to recognize the slowing down of the patients' movements, it gave a test accuracy of 96.2% for the diagnosis of Parkinson's disease.Conclusion. The obtained results of recognition of signs of Parkinson's disease are close to the world level. On the same set of data on speech changes of patients, one of the best indicators of foreign studies is 95.8%. On the same set of data on motion deceleration, one of the best indicators of foreign researchers is 98.8%. The proposed author's technique is intended for use in the subsystem of IT diagnostics of neurological diseases of a Smart city.

Health-diagnosis of electromechanical system with a principal-component bayesian neural network algorithm

This study proposes a cloud tele-measurement technique on an electromechanical system, and uses a neural network algorithm based on principal-component analysis (PCA) to quickly diagnose its performance. Three vibration, three temperature, electrical voltage, and current sensors were mounted on the electromechanical system, and the external braking device was used to provide different load-states to simulate the operating states of the motor under different conditions. Moreover, a single-chip multiprocessor was used through the sensor to instantly measure the various load-state simulations of the motor. The operating states of the electromechanical system were classified as normal, abnormal, and required-to-be-turned-off states using a principal-component Bayesian neural network algorithm (PBNNA), to enable their quick diagnosis. Furthermore, PBNNA successfully reduces the dimensionality of the multivariate dataset for rapid analysis of the electromechanical system’s performance. The accuracy rates of health-diagnosis based on the Bayesian neural network algorithm and PBNNA models were obtained as 97.7% and 98%, respectively. Finally, the single-chip multiprocessor based on PBNNA is used to automatically upload the measurement and analysis results of the electromechanical system to the cloud website server. The establishment of this model system can optimize prediction judgment and decision-making based on the damage situation to achieve the goals of intelligence and optimization of factory reconstruction.

E-Posters

Lifelong surveillance is not cost-effective after endovascular aneurysm repair (EVAR), but is required to detect aortic complications which are fatal if untreated (type 1/3 endoleak, sac expansion, device migration). Aneurysm morphology determines the probability of aortic complications and therefore the need for surveillance, but existing analyses have proven incapable of identifying patients at sufficiently low risk to justify abandoning surveillance. This study aimed to improve the prediction of aortic complications, through the application of machine-learning techniques. Patients undergoing EVAR at 2 centres were studied from 2004–2010. Aneurysm morphology had previously been studied to derive the SGVI Score for predicting aortic complications. Bayesian Neural Networks were designed using the same data, to dichotomise patients into groups at low- or high-risk of aortic complications. Network training was performed only on patients treated at centre 1. External validation was performed by assessing network performance independently of network training, on patients treated at centre 2. Discrimination was assessed by Kaplan-Meier analysis to compare aortic complications in predicted low-risk versus predicted high-risk patients. 761 patients aged 75 +/− 7 years underwent EVAR in 2 centres. Mean follow-up was 36+/− 20 months. Neural networks were created incorporating neck angu- lation/length/diameter/volume; AAA diameter/area/volume/length/tortuosity; and common iliac tortuosity/diameter. A 19-feature network predicted aor- tic complications with excellent discrimination and external validation (5-year freedom from aortic complications in predicted low-risk vs predicted high-risk patients: 97.9% vs. 63%; p < 0.0001). A Bayesian Neural-Network algorithm can identify patients in whom it may be safe to abandon surveillance after EVAR. This proposal requires prospective study.

A program for the Bayesian Neural Network in the ROOT framework

We present a Bayesian Neural Network algorithm implemented in the TMVA package (Hoecker et al., 2007 [1]), within the ROOT framework (Brun and Rademakers, 1997 [2]). Comparing to the conventional utilization of Neural Network as discriminator, this new implementation has more advantages as a non-parametric regression tool, particularly for fitting probabilities. It provides functionalities including cost function selection, complexity control and uncertainty estimation. An example of such application in High Energy Physics is shown. The algorithm is available with ROOT release later than 5.29. Program summary Program title: TMVA-BNN Catalogue identifier: AEJX_v1_0 Program summary URL: http://cpc.cs.qub.ac.uk/summaries/AEJX_v1_0.html Program obtainable from: CPC Program Library, Queenʼs University, Belfast, N. Ireland Licensing provisions: BSD license No. of lines in distributed program, including test data, etc.: 5094 No. of bytes in distributed program, including test data, etc.: 1,320,987 Distribution format: tar.gz Programming language: C++ Computer: Any computer system or cluster with C++ compiler and UNIX-like operating system Operating system: Most UNIX/Linux systems. The application programs were thoroughly tested under Fedora and Scientific Linux CERN. Classification: 11.9 External routines: ROOT package version 5.29 or higher ( http://root.cern.ch) Nature of problem: Non-parametric fitting of multivariate distributions Solution method: An implementation of Neural Network following the Bayesian statistical interpretation. Uses Laplace approximation for the Bayesian marginalizations. Provides the functionalities of automatic complexity control and uncertainty estimation. Running time: Time consumption for the training depends substantially on the size of input sample, the NN topology, the number of training iterations, etc. For the example in this manuscript, about 7 min was used on a PC/Linux with 2.0 GHz processors.

Bayesian Neural Network Analysis of Undrained Side Resistance of Drilled Shafts

A Bayesian neural network algorithm was used to model the relationship between the soil undrained shear strength, the effective overburden stress, and the undrained side resistance alpha factor for drilled shafts. The database comprised 127 field load tests. The Bayesian approach to learning in neural networks is a recent enhancement to improve the generalization ability of neural networks. Instead of just giving a single “optimum” prediction, the Bayesian approach provides information on the characteristic error of the prediction that arises from the uncertainty associated with interpolating noisy data. The developed neural network model provides good estimates of the undrained side resistance adhesion factor. Parametric studies using the trained neural network model suggest that the effective overburden stress directly or indirectly has an influence on the adhesion factor for drilled shafts. One distinct benefit of this neural network model is the computation of the error bars on the predictions of the ...