Parkinson‟s Disease Prediction using Modified Gauss-Newton Method in Feed-Forward Neural Network

Parkinson’s disease (PD) is a brain disorder, characterized by the relapse of the nervous system that spreads gradually in the body. The symptom of PD includes a loss of body control (moderate movement, resting tremors, postural shakiness etc.). So, it is required to detect at an early stage. Machine learning (ML) deals with a variety of probabilistic methods to identify a pattern in a dataset. Therefore, the research is carried out to predict the PD using Multilayer Feed-Forward Neural Network. In Neural Network (NN), weight optimization performed at each layer that plays a major role in the prediction. First-order weight optimization techniques are slow in computation because they reduce the sum of square error using parameter updating in the steepest descent way. In proposed work, a modified recursive Gauss-Newton method is used to optimize the weights for speed up the performance of Feed-Forward NN. This approach is compared with widely used optimization techniques. The Proposed method found better than other techniques and performs fast in Apache Spark than R-Studio framework.

Download Full-text

Prediction of Drug-likeness of Central Nervous System Drug Candidates Using a Feed-Forward Neural Network Based on Chemical Structure

10.26434/chemrxiv.12887102 ◽

2020 ◽

Author(s):

Yi-Gao Yuan ◽

Xiao Wang

Keyword(s):

Neural Network ◽

Central Nervous System ◽

Nervous System ◽

Chemical Structure ◽

Early Stage ◽

Medical Science ◽

Well Being ◽

New Drugs ◽

Feed Forward Neural Network ◽

Feed Forward

Modern medical science has been greatly advanced by the development of new drugs, despite the fact that the process of developing new drugs is costly and time-consuming. An accurate prediction method for the drug-likeness in the early stage of drug discovery is highly desirable, as it will facilitate the discovery process and reduce the overall cost and eventually contribute to human well-being. Based on a central nervous system (CNS) drug dataset, we constructed an artificial neural network (NN) to predict the CNS drug-likeness of a given bioactive compound. We first constructed a simple feed-forward neural network, to learn and predict the possible correlations between twelve physiochemical properties and the CNS drug-likeness. The accuracy of prediction has reached 80%, which has been improved from previous reports. We further constructed a neural network based on chemical structure, and the accuracy has increased to 86%. The successful prediction of the CNS drug-likeness renders this NN a powerful tool for virtual drug screening. <br>

Download Full-text

Brain Tumor Detection with Biologically Inspired Watershed Segmentation and Classification Based on Feed-Forward Neural Network (FNN)

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3909 ◽

2021 ◽

Vol 11 (12) ◽

pp. 3181-3190

Author(s):

G. S. Gopika ◽

J. Shanthini ◽

M. S. Kavitha ◽

R. Sabitha

Keyword(s):

Neural Network ◽

Image Segmentation ◽

High Resolution ◽

Training Model ◽

The Body ◽

Quality Analysis ◽

Watershed Segmentation ◽

Feed Forward Neural Network ◽

Feed Forward ◽

High Resolution Images

Image segmentation plays a very vital role in gathering information by dividing the images into various segments to achieve the meaningful information, whereas the image segmentation gives importance in the area of medical imaging to analyze and process the anatomical structures of various internal organs of the body with high resolution images that are captured during medical examination. Medical experts will go through the reports which give the various reasons for the existence of the disease. Brain which is considered the important part of the body so the detection and the segmentation of brain tumors will be considered as the major task of the medical field whereas they are using the high resolution images in the form of MRI reports. The MRI images are considered as the vital source for the identification of tumors in the brain. The accuracy of the segmentation and identification of the tumor depends upon the experience of the radiologist and also it is time consuming task. Therefore the watershed segmentation is performed for the extraction of the tumor region and the features are extracted for the classification, whereas the classification is carried out by the Feed-Forward Neural Network (FNN). The experimental results are evaluated based on the performance and the quality analysis, Furthermore the results give the accuracy of 91.2% in the training model and 71.8% as the testing during the classification process.

Download Full-text