Classification of News Articles using Supervised Machine Learning Approach

Today the big challenge for NEWS organization to well organize the news and well categorize the news in automatically no need the data entry people to enter and select the category and then based on the category and its sub-category they will be manually selected and enter the details and then after this the analysis will later on used for different aspects. The news is almost every second used in different sources of media in soft and hard. We use the both sources of the Pakistan News in dual languages English and Urdu both and process them and prepare them for machine learning and based on the Machine learning trained data we build a very effective and efficient model that can predict the title category of the news and category of description of the news. We use different machine learning algorithms and different features extraction finally we build the model using the machine learning algorithm with 89% accuracy with logistic regression.

Fuzzy Logic and Neural Network Application in Medical Information

Medical practitioner often makes decisions based on incomplete, vague, or uncertain information. Recently fuzzy based techniques have shown a more promising way to handle imprecise data. The approach consists in using the capacities of the commercial database management system while adding a supplementary layer assuring the interface between fuzzy queries. Such a fuzzy relational database management system (FRDBMS) deals more effectively in many applications enhancing the efficiency of processing fuzzy queries even in relational database management system (RDBMS). The implementation from RDBMS to FRDBMS requires knowledge of legacy database, knowledge about fuzzy logic and mapping from crisp to fuzzy values. Software layer is used with RDBMS to convert to FRDBMS, where fuzzy information is to be designed with care. The main feature of FRDBMS is linguistic fuzzy modeling, where the interpretability of the obtained model is the main requirement, together with its accuracy. The research of moving from RDBMS to FRDBMS is limited and not much work has been carried out. The research work presented in this thesis shows fuzzy RDBMS implementation using our developed FDSL Tool, where input to this tool is fuzzy SQL query and output is fuzzy linguistic value results. The FDSL Tool can be used with many fuzzy expert system applications. The developed Fuzzy Model is tested successfully on heart and diabetes datasets. Our implementation achieved an accuracy higher than other contemporary setups working on the same datasets as considered in this work. The improved results were attributed due to the incorporation of linguistic data and its implementation in metadata function.