Artificial Neural networks are often used as a powerful discriminating classifier for tasks in medical diagnosis for early detection of diseases. They have several advantages over parametric classifiers such as discriminate analysis. The objective of this paper is to diagnose kidney stone disease by using three different neural network algorithms which have different architecture and characteristics. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ), two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF) networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA) version 3.7.5 as simulation tool which is an open source tool. The data set we used for diagnosis is real world data with 1000 instances and 8 attributes. In the end part we check the performance comparison of different algorithms to propose the best algorithm for kidney stone diagnosis. So this will helps in early identification of kidney stone in patients and reduces the diagnosis time.
Inhaltsverzeichnis (Table of Contents)
- Introduction
- Artificial Neural Networks Introduction
- Related Work
- Kidney Stone Dataset
- Artificial Neural Networks Classifiers Used
- Radial Basis Function Networks
- Multilayer Perceptron with BPA
- Learning Vector Quantization Algorithm
- Simulation Tool Used
- Experiment Results and Discussion
- Conclusion
Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)
This paper aims to diagnose kidney stone disease using three different neural network algorithms: Learning Vector Quantization (LVQ), two-layer feed forward perceptron trained with backpropagation, and Radial basis function (RBF) networks. The performance of these algorithms is compared on the basis of accuracy, training time, and data set size. This research utilizes real-world data with 1000 instances and 8 attributes to assess the best algorithm for kidney stone diagnosis. This approach can facilitate early identification and reduce diagnosis time for patients.
- Diagnosis of kidney stone disease using artificial neural networks
- Performance comparison of different neural network algorithms
- Early detection and diagnosis of kidney stones
- Application of machine learning techniques in medical diagnostics
- Evaluation of neural network models for classification accuracy and efficiency
Zusammenfassung der Kapitel (Chapter Summaries)
- Introduction: This section provides a brief overview of kidney stone disease, its causes, and the importance of early diagnosis. It highlights the challenges in medical diagnostics, emphasizing the need for fast and accurate algorithms. Artificial neural networks are introduced as a potential solution for complex and fuzzy medical diagnosis processes.
- Artificial Neural Networks Introduction: This chapter explains the fundamentals of artificial neural networks, including their structure, working principles, and applications in various domains. It focuses on the multilayer perceptron architecture and its advantages in solving complex problems.
- Related Work: This section presents a review of relevant research studies on medical diagnosis using neural networks. The paper discusses various approaches used for diseases such as cancer, diabetes, and heart attack. It highlights the use of non-invasive ultrasound techniques and vibro-acoustography for kidney stone diagnosis.
- Kidney Stone Dataset: This chapter describes the real-world dataset used in the study. It details the characteristics of the data, including the number of instances, attributes, and their meaning. The attributes represent symptoms of kidney stones used to train and test the neural network models.
- Artificial Neural Networks Classifiers Used: This section introduces the three neural network algorithms used in the research - Radial Basis Function Networks, Multilayer Perceptron with Back Propagation Algorithm, and Learning Vector Quantization Algorithm. It provides detailed explanations of each algorithm's architecture, functioning, and advantages.
- Simulation Tool Used: This chapter describes the software tool used for simulating and testing the neural networks, WEKA version 3.7.5. It highlights the tool's capabilities, open-source nature, and functionalities for data preprocessing, classification, regression, and clustering.
- Experiment Results and Discussion: This section presents the results of the experiments conducted using the three neural network algorithms on the kidney stone dataset. It compares the accuracy, training time, and other performance metrics of each algorithm. The paper discusses the advantages and limitations of each approach based on the experimental findings.
Schlüsselwörter (Keywords)
Kidney Stone Disease, Artificial Neural Networks, Multilayer Perceptrons, Radial Basis Function Networks, Learning Vector Quantization, Diagnosis, Medical Diagnostics, Machine Learning, Data Analysis, Classification Accuracy, Training Time, Early Detection, Performance Comparison.
- Citation du texte
- Koushal Kumar (Auteur), B. Abhishek (Auteur), 2012, Artificial Neural Networks for Diagnosis of Kidney Stones Disease, Munich, GRIN Verlag, https://www.grin.com/document/196640
