Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Unsupervised learning method for mineral identification from hyperspectral data(Springer, 2021) Prabhavathy, P.; Tripathy, B.K.; Venkatesan, M.Hyperspectral imagery is one of the research area in the field of Remote sensing. Hyperspectral sensors record reflectance (also called spectra signature) of object or material or region across the electromagnetic spectrum. Mineral identification is an urban application in the field of Remote sensing of Hyperspectral data. EO-1 hyperion dataset is unlabeled data. Various types of clustering algorithms are proposed to identify minerals. In this work principal component analysis is used to reduced it’s dimension by reducing bands. Hard-clustering and soft-clustering algorithms are applied on given data to classify the minerals into classes. K-means is hard type of clustering which classify only non-overlapping cluster however, PFCM is soft type of clustering which allow a data points to belongs more than one cluster. Further, results are compared using cluster validity index using DBI value. Both clustering algorithms are experiments on original HSI image and reduced bands. Result shows that PFCM is perform better than K-means for the both type of images. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.Item Deep Learning-Based Prediction, Classification, Clustering Models for Time Series Analysis: A Systematic Review(Springer Science and Business Media Deutschland GmbH, 2022) Naik, N.N.; Chandrasekaran, K.; Venkatesan, M.; Prabhavathy, P.Analysis of time series is a prominent issue in the field of data analysis. With large amount of existing data in time series, multiple algorithms for analyzing time series data are being proposed. A variety of deep learning models are being designed to enhance the diversity of datasets related to time series across different fields. In comparison with the existing methods, only few have incorporated deep neural networks to perform this task. In most of the cases, deep neural networks are being applied for image data but it can also be used for sequential data such as text and audio. Here, we throw light on the recent advancements in hybrid deep learning models which consist of combination of various frameworks of deep neural networks with statistical models that have led to an improvement in time series analysis. Deep learning models are categorized into discriminative, and generative models provide an insight into the data based on the perception of conditional or joint probability. In this paper, we have surveyed newly devised algorithms and limitations of prediction, classification and clustering for time series analysis which describes how the temporal information can be merged into the analysis of the time series data. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Maximum frequent item set based clustering algorithm for big text data(Blue Eyes Intelligence Engineering and Sciences Publication, 2019) Kanimozhi, K.V.; Rajakumar, K.S.; Venkatesan, M.Due to fast growth of internet and continuous expansion of World Wide Web like digital libraries, online news contributes to massive amount of electronic unstructured text documents on the web. Although lot traditional techniques are available to extract the knowledge from large collection of text documents, still to improve precision of the web search retrieval and to find most appropriate documents from huge text collections proficiently is a big challenge. Clustering techniques helps the search engine to retrieve the documents. The proposed system overcomes existing problems using bivariate n-gram frequent item clustering algorithm by concept of maximum frequent set which maintain the sequence and meaning of sentence in order to reduce huge dimension and and frequent item sets finds similarity. Then based on maximum document occurrence we cluster the documents. Thus our method obtains quality of clusters when compared with existing methodologies and improves the efficiency. The experiment is shown for sample Newsgroup dataset for existing K-Mean and FICMDO (Frequent item clustering method based on maximum document occurrence) and proved the f-measure is higher for our algorithm. Since the f-measure increases, obtains efficient clusters. Hence it is faster and efficient big data method which improves the performance when compared with vector space model like K-Means algorithm. © BEIESP.