Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Subject: search.filters.subject.Autoencoders

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Extending Denoising AutoEncoders for Feature Recognition
    (Institute of Electrical and Electronics Engineers Inc., 2018) Jeppu, N.; Chandrasekaran, K.
    Image rendering techniques involve the addition of noise on the rendered samples. The characteristics of Monte Carlo rendered noisy images makes it difficult to denoise using conventional methods. The noise induced in this case is spatially sparse. Using traditional methods of denoising and feature recognition is time consuming for such images as they use the entire image space as their search space. This results in unnecessary calculations that can be avoided and therefore reduce the processing time significantly. A recurrent convolutional neural network that operates on varying spatial resolutions, also known as the auto encoder decoder structure perform very well on these rendered images. The partitioning into encoder and decoder phases lets the network operate on continuously decreasing and increasing spatial domains respectively. This can be coupled with classification techniques to incorporate feature recognition of noisy images. In this paper the pretrained autoencoder layers are supported with additional softmax and sigmoid layers to enable feature recognition capabilities. © 2018 IEEE.
  • No Thumbnail Available
    Item
    Quality assessment of dimensionality reduction techniques on hyperspectral data: A neural network based approach
    (International Society for Photogrammetry and Remote Sensing, 2020) C, C.; Shetty, A.; Narasimhadhan, A.V.
    Dimensionality reduction of hyperspectral images plays a vital role in remote sensing data analysis. The rapid advances in hyperspectral remote sensing has brought in a lot of opportunities to researchers to come up with advanced algorithms to analyse such voluminous data to better explore earth surface features. Modern machine learning algorithms can be applied to explore the underlying structure of high dimensional hyperspectral data and reduce the redundant information through feature extraction techniques. Limited studies have been carried out on dimensionality reduction for mineral exploration. The current study mainly focuses on the application of autoencoders for dimensionality reduction and provides a qualitative (visual) analysis of the obtained representations. The performance of autoencoders are investigated on Cuprite scene. Coranking matrix is used as evaluation criteria. From the obtained results it is evident that, deep autoencoders provide better results compared to single layer autoencoders. An increase in the number of hidden layers provides a better embedding. The neighborhood size K ≥ 40 of deep autoencoders provides a better transformation compared to autoencoders which shows an improved embedding only after K ≥ 80. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.
  • No Thumbnail Available
    Item
    Clustering Enhanced Encoder–Decoder Approach to Dimensionality Reduction and Encryption
    (Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Mukesh, B.R.; Madhumitha, N.; Aditya, N.P.; Vivek, S.; Anand Kumar, M.
    Dimensionality reduction refers to reducing the number of attributes that are being considered, by producing a set of principal variables. It can be divided into feature selection and feature extraction. Dimensionality reduction serves as one of the preliminary challenges in storage management and is useful for effective transmission over the Internet. In this paper, we propose a deep learning approach using encoder–decoder networks for effective (almost-lossless) compression and encryption. The neural network essentially encrypts data into an encoded format which can only be decrypted using the corresponding decoders. Clustering is essential to reduce the variation in the dataset to ensure overfit. Using clustering resulted in a net gain of 1% over the standard encoder architecture over three MNIST datasets. The compression ratio achieved was 24.6:1. The usage of image datasets is for visualization only and the proposed pipeline could be applied for textual and visual data as well. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Comparative Analysis of Intrusion Detection System using ML and DL Techniques
    (Springer Science and Business Media Deutschland GmbH, 2023) Sunil, C.K.; Reddy, S.; Kanber, S.G.; Vuddanti, V.R.; Patil, N.
    Intrusion detection system (IDS) protects the network from suspicious and harmful activities. It scans the network for harmful activity and any potential breaching. Even in the presence of the so many network intrusion APIs there are still problems in detecting the intrusion. These problems can be handled through the normalization of whole dataset, and ranking of feature on benchmark dataset before training the classification models. In this paper, used NSL-KDD dataset for the analysation of various features and test the efficiency of the various algorithms. For each value of k, then, trained each model separately and evaluated the feature selection approach with the algorithms. This work, make use of feature selection techniques like Information gain, SelectKBest, Pearson coefficient and Random forest. And also iterate over the number of features to pick the best values in order to train the dataset.The selected features then tested on different machine and deep learning approach. This work make use of stacked ensemble learning technique for classification. This stacked ensemble learner contains model which makes un-correlated error there by making the model more robust. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.