{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:35:25Z","timestamp":1760243725530,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2012,9,14]],"date-time":"2012-09-14T00:00:00Z","timestamp":1347580800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Signals acquired by sensors in the real world are non-linear combinations, requiring non-linear mixture models to describe the resultant mixture spectra for the endmember\u2019s (pure pixel\u2019s) distribution. This communication discusses inferring class fraction through a novel hybrid mixture model (HMM). HMM is a three-step process, where the endmembers are first derived from the images themselves using the N-FINDR algorithm. These endmembers are used by the linear mixture model (LMM) in the second step that provides an abundance estimation in a linear fashion. Finally, the abundance values along with the training samples representing the actual ground proportions are fed into neural network based multi-layer perceptron (MLP) architecture as input to train the neurons. The neural output further refines the abundance estimates to account for the non-linear nature of the mixing classes of interest. HMM is first implemented and validated on simulated hyper spectral data of 200 bands and subsequently on real time MODIS data with a spatial resolution of 250 m. The results on computer simulated data show that the method gives acceptable results for unmixing pixels with an overall RMSE of 0.0089 \u00b1 0.0022 with LMM and 0.0030 \u00b1 0.0001 with the HMM when compared to actual class proportions. The unmixed MODIS images showed overall RMSE with HMM as 0.0191 \u00b1 0.022 as compared to the LMM output considered alone that had an overall RMSE of 0.2005 \u00b1 0.41, indicating that individual class abundances obtained from HMM are very close to the real observations.<\/jats:p>","DOI":"10.3390\/info3030420","type":"journal-article","created":{"date-parts":[[2012,9,15]],"date-time":"2012-09-15T05:08:08Z","timestamp":1347685688000},"page":"420-441","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A Neural Network Based Hybrid Mixture Model to Extract Information from Non-linear Mixed Pixels"],"prefix":"10.3390","volume":"3","author":[{"given":"Uttam","family":"Kumar","sequence":"first","affiliation":[{"name":"Energy & Wetlands Research Group, Centre for Ecological Sciences, Indian Institute of Science, Bangalore 560012, India"},{"name":"Centre for Sustainable Technologies, Indian Institute of Science, Bangalore 560012, India"},{"name":"Department of Management Studies, Indian Institute of Science, Bangalore 560012, India"}]},{"given":"Kumar S.","family":"Raja","sequence":"additional","affiliation":[{"name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires, 35042 Rennes cedex, France"},{"name":"Technicolor Research & Innovation, 35576 Cesson S\u00e9vign\u00e9, France"}]},{"given":"Chiranjit","family":"Mukhopadhyay","sequence":"additional","affiliation":[{"name":"Department of Management Studies, Indian Institute of Science, Bangalore 560012, India"}]},{"given":"T.V.","family":"Ramachandra","sequence":"additional","affiliation":[{"name":"Energy & Wetlands Research Group, Centre for Ecological Sciences, Indian Institute of Science, Bangalore 560012, India"},{"name":"Centre for Sustainable Technologies, Indian Institute of Science, Bangalore 560012, India"}]}],"member":"1968","published-online":{"date-parts":[[2012,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1109\/36.957296","article-title":"A quantitative and comparative analysis of linear and nonlinear spectral mixture models using radial basis neural networks","volume":"39","author":"Guilfoyle","year":"2001","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1080\/014311697218836","article-title":"Mapping sub-pixel proportional land cover with AVHRR imagery","volume":"18","author":"Atkinson","year":"1997","journal-title":"Int. J. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/79.974727","article-title":"Spectral unmixing","volume":"19","author":"Keshava","year":"2002","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Elleithy, K. (2008). Innovations and Advanced Techniques in Systems, Computing Sciences and Software Engineering, Springer.","DOI":"10.1007\/978-1-4020-8735-6"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1080\/01431169408954100","article-title":"Subpixel land cover composition estimation using a linear mixture model and fuzzy membership functions","volume":"15","author":"Foody","year":"1994","journal-title":"Int. J. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1080\/01431169208904164","article-title":"Land-cover discrimination in SPOT imagery by artificial neural network-a twenty class experiment","volume":"13","author":"Kanellopoulos","year":"1992","journal-title":"Int. J. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.rse.2004.09.004","article-title":"Comparison of non-linear mixture models: Sub-pixel classification","volume":"94","author":"Liu","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1016\/S0034-4257(02)00172-4","article-title":"Gaussian mixture discriminant analysis and sub-pixel and sub-pixel land cover characterization in remote sensing","volume":"84","author":"Ju","year":"2003","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1016\/j.asr.2007.04.096","article-title":"Non-linear mixture model of mixed pixels in remote sensing satellite images based in Monte Carlo simulation","volume":"42","author":"Arai","year":"2008","journal-title":"Adv. Space Res."},{"key":"ref_10","first-page":"251","article-title":"Spectral analysis for Earth science: investigations using remote sensing data","volume":"Volume 3","author":"Rencz","year":"1999","journal-title":"Remote Sensing for the Earth Sciences: Manual of Remote Sensing"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Adams, J.B., and Gillespie, A.R. (2006). Remote Sensing of Landscapes with Spectral Images: A Physical Modeling Approach, Cambridge University Press.","DOI":"10.1017\/CBO9780511617195"},{"key":"ref_12","unstructured":"Plaza, J., Martinez, P., P\u00e9rez, R., and Plaza, A. (April, January 31). Nonlinear neural network mixture models for fractional abundance estimation in AVIRIS Hyperspectral Images. Proceedings of the NASA Jet Propulsion Laboratory AVIRIS Airborne Earth Science Workshop, Pasadena, CA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/S0034-4257(99)00027-9","article-title":"A neural network method for mixture estimation for vegetation mapping","volume":"70","author":"Carpenter","year":"1999","journal-title":"Remote Sens. Environ."},{"key":"ref_14","unstructured":"Jensen, J.O., and Th\u00e9riault, J.-M. (2004, January 25\u201328). Analysis of the behaviour of a neural network model in the identification and quantification of hyperspectral signatures applied to the determination of water quality. Chemical and Biological Standoff Detection II, Proceedings of SPIE Optics East Conference, Philadelphia, PA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/36.103288","article-title":"The least-squares mixing models to generate fraction images derived from remote sensing multispectral data","volume":"29","author":"Shimabukuro","year":"1991","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","unstructured":"Liu, W., Gopal, S., and Woodcock, C. (2001, January 7\u201310). ARTMAP Multisensor-resolution framework for land cover characterization. Proceedings 4th Annual Conference information fusion, Montreal, Canada."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1976","DOI":"10.1109\/TGRS.2004.831893","article-title":"ART-MMAP: A neural network approach to subpixel classification","volume":"42","author":"Liu","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1117\/12.366289","article-title":"N-FINDR: An algorithm for fast autonomous spectral end-member determination in hyperspectral data","volume":"Volume 3753","author":"Descour","year":"1999","journal-title":"Proceedings of the SPIE: Imaging Spectrometry V"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TGRS.2004.839543","article-title":"Orthogonal Subspace Projection (OSP) Revisited: A comprehensive study and analysis","volume":"43","author":"Chang","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/36.298007","article-title":"Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection approach","volume":"32","author":"Harsanyi","year":"1994","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","unstructured":"Crippen, R.E., and Bloom, R.G. (1999, January 1\u20133). Unveiling the lithology of vegetated terrains in remotely sensed imagery via forced decorrelation. Proceedings of the Thirteenth International Conference on Applied Geologic Remote Sensing, Vancouver, Canada."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/36.655327","article-title":"A noise subspace projection approach to target signature detection and extraction in an unknown background for hyperspectral images","volume":"36","author":"Tu","year":"1998","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/36.508422","article-title":"On the relationship between spectral unmixing and subspace projection","volume":"34","author":"Settle","year":"1996","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1023\/A:1011181216297","article-title":"Spectral mixture analysis: Linear and semi-parametric full and iterated partial unmixing in multi-and hyperspectral image data","volume":"42","author":"Nielsen","year":"2001","journal-title":"Int. J. Comput. Vis."},{"key":"ref_25","unstructured":"Haykin, S. (1998). Neural Networks: A Comprehensive Foundation, Macmillan."},{"key":"ref_26","unstructured":"Duda, R.O., Hart, P.E., and Stork, D.G. (2000). Pattern Classification, Wiley."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4907","DOI":"10.1080\/0143116031000114851","article-title":"The use of backpropagating artificial neural networks in land cover classification","volume":"24","author":"Kavzoglu","year":"2003","journal-title":"Int. J. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ecss.2003.08.011","article-title":"Mapping land use\/cover in a tropical coastal area using satellite sensor data, GIS and artificial neural networks","volume":"59","author":"Mas","year":"2003","journal-title":"Estuar. Coast. Shelf Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kumar, U., Raja, K.S., Mukhopadhyay, C., and Ramachandra, T.V. (2011, January 14\u201316). A Multi-layer Perceptron based Non-linear Mixture Model to estimate class abundance from mixed pixels. Proceedings of the 2011 IEEE Students\u2019 Proceedings of the 2011 IEEE Students\u2019 Technology Symposium, Indian Institute of Technology, Kharagpur, India.","DOI":"10.1109\/TECHSYM.2011.5783815"},{"key":"ref_31","unstructured":"Jet Propulsion Laboratory (JPL) Homepage. Available online:http:\/\/speclib.jpl.nasa.gov\/."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Plaza, J., Plaza, A., P\u2019erez, R., and Martinez, P. (2007, January 23\u201327). Joint linear\/nonlinear spectral unmixing of hyperspectral image data. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS'07), Barcelona, Spain.","DOI":"10.1109\/IGARSS.2007.4423735"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3032","DOI":"10.1016\/j.patcog.2009.04.008","article-title":"On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral images","volume":"42","author":"Plaza","year":"2009","journal-title":"Pattern Recognition"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/3\/3\/420\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:52:23Z","timestamp":1760219543000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/3\/3\/420"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,9,14]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2012,9]]}},"alternative-id":["info3030420"],"URL":"https:\/\/doi.org\/10.3390\/info3030420","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2012,9,14]]}}}