Label-Based Feature Classification Model for Extracting Information with Dynamic Load Balancing

Efficient extraction of information from various sources is very tedious. Achieving this requires very sophisticated feature classification model and ability of the system to adapt to changing environments of data and its random distributions with an efficient use of computational resources. Label-based feature classification model (LFCM) with dynamic load balancing is proposed to address an efficient model to extract information in data set. This technique is effective in data analysis to discover the new feature set. Label approach incorporates unique label concept and it avoids any data duplication using labels. Each data sample is assigned to only one label to improve the accuracy and effectiveness of the retrieval process. Based on the data relevancy and specific features that can be extracted using proposed algorithm, classification model and semantic representation of data in vector form minimizes the data loss, and dimensionality reduction plays a vital role in building an efficient model. Various graphs and results obtained from the experiments show an improvement of information extraction using this proposed labeled LFCM approach. This approach brings lots of real time challenges that are handled to bring accuracy factor as the main focus in this proposed system. Both classification and extraction uses different model to obtain the intended results.