Learning and Sequential Decision Making For Medical Data Streams Using Rl Algorithm
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2013, Vol 2, Issue 7
Abstract
Data stream mining has obtained a high attraction due to the importance of its applications and increase in the generation of streaming information. The data streams are the set of data, which are moving in specified distribution. Extracting knowledge structures represented in models and patterns in non stopping streams of information is known as data stream mining. Increasing access to incredibly large, non stationary data sets and corresponding demands to analyze these data has led to use reinforcement learning algorithm on data streams. For diabetes data set it is difficult to differentiate between the value of blood glucose level and value of insulin doses. Also it is difficult to take decision about giving specific quantity of insulin dose to the diabetes patient. In this paper we implement the reinforcement learning algorithm on diabetes data streams. The algorithm process the data streams and differentiate the values for blood glucose level and insulin dose and take the decision for next insulin dose. Depending on state and action taken the payoff is assign to the decision. This helps in classifying the data for diabetes doses and also helps in making decisions for giving specific quantity of dose at a particular time. In comparison with other methods our proposed algorithm is faster. A proposed methodology is tested on diabetes data.
Authors and Affiliations
Prof. Pramod Patil, Dr. Parag Kulkarni, Ms. Rachana Shirsath
Keywords
Related Articles
- EP ID EP27602
- DOI -
- Views 289
- Downloads 3
Automated Sentiment Analysis System Using Machine Learning Algorithms
Sentiment analysis can be very useful for business if employed correctly. In this article, I will attempt to demystify the process, provide context, and offer some concrete examples of how businesses can utilize it....
A Hybrid Routing Protocol for Unobservable Security in Mobile Ad-hoc Networks
Security of mobile ad hoc network is crucial due to infra structure less network and mobility of wireless media. In this paper, we propose an Hybrid Routing Protocol for Unobservable Secured (HRPUS) to offer privacy...
Short Term Load Forecasting OF 132/33Kv Maiduguri Transmission Substation Using Artificial Neural Network (ANN)
This paper presents a novel approach for 1 to 24 hours ahead load forecasting using multilayer perceptron (MLP) also referred to as multilayer feed forward artificial neural network (ANN) of a utility company located...
Performance Analysis of Rotating Induction Machines for Air-Gap Eccentricity & Rotor Bar Faults using Finite Element Method
In this paper analysis used to diagnose Air-gap eccentricity and broken rotor bar fault especially in high voltage Rating machine. The analysis carried out to evaluate the performance of the machine during operation...
LACK OF TRAINING DATA IN SENTIMENT CLASSIFICATION: CURRENT SOLUTIONS
In recent years, sentiment classification has attracted much attention from natural language processing researchers. Most of researchers in this field consider sentiment classification as a supervised classification p...