Theses and Dissertations

Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/1

Browse

Subject: search.filters.subject.Pattern recognition

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    ItemOpen Access
    Desertification characterization using predictive soil modelling and pattern recognition
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2023) Dave, Viral A.; Ghosh, Ranendu
    This thesis presents a hierarchical methodology for land degradation mapping,land use land cover classification, degradation process identification and map-ping using multispectral LISS-3 images. The study aims to demonstrate the im-portance of remote-sensing images for various applications, both social and en-vironmental. The study compares the results of different algorithms for differentterrains, demonstrating that Simple Linear Iterative Clustering (SLIC) segmenta-tion with the random forest(RF) method outperforms CNN and pixel-based Sup-port Vector Machine (SVM) with an accuracy of 85% for level 1 land cover clas-sification. Vegetation degradation in forest areas is assessed in central parts ofGujarat, India, and land degradation in agricultural areas due to soil salinity isstudied, particularly in southeastern parts of Gujarat, India. ML algorithms likesupport vector machine(SVM) and RF was applied to different features to identifythe degradation process. Temporal data were used to find the severity of deserti-fication using the change in degraded areas.Further, it discusses soil degradation causing desertification and severely re-ducing potential soil productivity. The study uses machine learning algorithmsand an ANN-based model to predict soil properties like EC, pH, and OC, whichare important indicators of soil degradation. Environmental parameters are takenas covariates in prediction models, including vegetation indices, terrain indices,soil parameters, spatial attributes, and meteorological parameters of the study re-gion. Field soil sampling data of the study region obtained from Soil Health Card(SHC) for the year 2014 is incorporated in training the model. The SHC data isdivided into different ratios for training and testing the model. The SCORPANmodel is considered the base approach for the development of the ANN-basedprediction model. Moreover, the thesis also discusses the mapping of vulnera-ble areas to desertification. The study combines remote sensing and geographicinformation system (GIS) to map sensitive areas. Two different approaches wereused for vulnerability assessment: Mediterranean Desertification and Land Use(MEDALUS) approach and the fuzzy logic (FL) method. Soil, climate, land uti-lization, geography, and vegetation contribute to the land degradation of anyarea. However, man�s intervention leads to significant changes in the environ-ment, making socio-economic factors a considerable input to assess desertificationvulnerability. Indices related to these factors are generated, and both methods areused to find the severity level of the desertification vulnerability in the Panchma-hal district.Lastly, the role of climate in the process of desertification is discussed. Thestudy uses the aridity index (AI), which incorporates most of the weather datalike temperature, rainfall, humidity, wind, and solar radiation, to identify the de-sertification hot-spot using AI over the Gujarat state. The study uses weatherdata from more than 18 locations all over Gujarat for the past 20 years to calcu-late AI, and the FAO Penman-Monteith method was used to calculate PET. Thestudy generates an annual AI map for the whole of Gujarat using these valuesand compares it with a globally published AI map. It also compares the changein climate with the change in vegetation over the years using the vegetation in-dex for Gujarat. In summary, this thesis provides a comprehensive approach toland degradation mapping using degradation process identification, soil predic-tion, and climate variable using geospatial technology and machine learning. Thestudy demonstrates the importance of remote sensing images in various applica-tions, including social and environmental. The study employs different machinelearning algorithms and approaches to achieve high accuracy and identify vul-nerable areas to desertification. The study also highlights the importance of soilproperties and climate in the process of desertification.
  • Thumbnail Image
    ItemOpen Access
    Imbalanced bioassay data classification for drug discovery
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2018) Shah, Jeni Snehal; Joshi, Manjunath V.
    All the methods developed for pattern recognition will show inferior performance if the dataset presented to it is imbalanced, i.e. if the samples belonging to one class are much more in number compared to the samples from the other class/es. Due to this, imbalanced dataset classification has been an active area of research in machine learning. In this thesis, a novel approach to classifying imbalanced bioassay data is presented. Bioassay data classification is an important task in drug discovery. Bioassay data consists of feature descriptors of various compounds and the corresponding label which denotes its potency as a drug: active or inactive. This data is highly imbalanced, with the percentage of active compounds ranging from 0.1% to 1.4%, leading to inaccuracies in classification for the minority class. An approach for classification in which separate models are trained by using different features derived by training stacked autoencoders (SAE) is proposed. After learning the features using SAEs, feed-forward neural networks (FNN) are used for classification, which are trained to minimize a class sensitive cost function. Before learning the features, data cleaning is performed using Synthetic Minority Oversampling Technique (SMOTE) and removing Tomek links. Different levels of features can be obtained using SAE. While some active samples may not be correctly classified by a trained network on a certain feature space, it is assumed that it can be classified correctly in another feature space. This is the underlying assumption behind learning hierarchical feature vectors and learning separate classifiers for each feature space. vi
  • Thumbnail Image
    ItemOpen Access
    Locality preserving projection: a study and applications
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2012) Shikkenawis, Gitam; Mitra, Suman K
    Locality Preserving Projection (LPP) is a recently proposed approach for dimensionality reduction that preserves the neighbourhood information and obtains a subspace that best detects the essential data manifold structure. Currently it is widely used for finding the intrinsic dimensionality of the data which is usually of high dimension. This characteristic of LPP has made it popular among other available dimensionality reduction approaches such as Principal Component Analysis (PCA). A study on LPP reveals that it tries to preserve the information about nearest neighbours of data points, thus may lead to misclassification in the overlapping regions of two or more classes while performing data analysis. It has also been observed that the dimension reducibility capacity of conventional LPP is much less than that of PCA. A new proposal called Extended LPP (ELPP) which amicably resolves two issues mentioned above is introduced. In particular, a new weighing scheme is designed that pays importance to the data points which are at a moderate distance, in addition to the nearest points. This helps to resolve the ambiguity occurring at the overlapping regions as well as increase the reducibility capacity. LPP is used for a variety of applications for reducing the dimensions one of which is Face Recognition. Face Recognition is one of the most widely used biometric technology for person identification. Face images are represented as highdimensional pixel arrays and due to high correlation between the neighbouring pixel values; they often belong to an intrinsically low dimensional manifold. The distribution of data in a high dimensional space is non-uniform and is generally concentrated around some kind of low dimensional structures. Hence, one of the ways of performing Face Recognition is by reducing the dimensionality of the data and finding the subspace of the manifold in which face images reside. Both LPP and ELPP are used for Face and Expression Recognition tasks. As the aim is to separate the clusters in the embedded space, class membership information may add more discriminating power. With this in mind, the proposal is further extended to the supervised version of LPP (SLPP) that uses the known class labels of data points to enhance the discriminating power along with inheriting the properties of ELPP
  • Thumbnail Image
    ItemOpen Access
    Fingerprint image preprocessing for robust recognition
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2012) Munshi, Paridhi; Mitra, Suman K
    Fingerprint is the oldest and most widely used form of biometric identification. Since they are mainly used in forensic science, accuracy in the fingerprint identification is highly important. This accuracy is dependent on the quality of image. Most of the fingerprint identification systems are based on minutiae matching and a critical step in correct matching of fingerprint minutiae is to reliably extract minutiae from the fingerprint images. However, fingerprint images may not be of good quality. They may be degraded and corrupted due to variations in skin, pressure and impression conditions. Most of the feature extraction algorithms work on binary images instead of the gray scale image and results of the feature extraction depends upon the quality of binary image used. Keeping these points in mind, image preprocessing including enhancement and binarization is proposed in this work. This preprocessing is employed prior to minutiae extraction to obtain a more reliable estimation of minutiae locations and hence to get a robust matching performance. In this dissertation, we give an introduction to the ngerprint structure and identification system . A discussion on the proposed methodology and implementation of technique for fingerprint image enhancement is given. Then a rough-set based method for binarization is proposed followed by the discussion on the methods for minutiae extraction. Experiments are conducted on real fingerprint images to evaluate the performance of the implemented techniques.
  • Thumbnail Image
    ItemOpen Access
    Fractal based approach for image segmentation
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2004) Londhe, Tushar; Banerjee, Asim
    In this thesis, we have proposed an algorithm for image segmentation, using the fractal codes. The basic idea behind this algorithm is to use fractal codes for the image segmentation. This method uses compressed codes instead of the gray levels of the image. Therefore it is cost effective in the sense of storage space and time as no decoding is performed before using the segmentation algorithm. Moreover, the proposed scheme can directly use on the images accessed from the image database where images are kept in fractal-compressed code.