Conference Papers

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

Browse

Subject: search.filters.subject.neural networks

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    System identification for helicopter longitudinal dynamics model - Best practices
    (Institute of Electrical and Electronics Engineers Inc., 2015) Kamble, S.B.; Desai, V.; Jeppu, Y.V.; Prajna
    For estimation of mathematical model and parameters of a system, the system identification has been widely applied in various domains such as the automatic control, aviation, spaceflight, civil and mechanical engineering, medicine, biology, chemical processes, marine ecology, geology etc. The main aim of this work is to perform preliminary studies to design a control law for helicopter model making it as autopilot. X-plane flight simulator will be used with Matlab wherein the estimated model is imported and simulated for its practical behavior. A longitudinal state-space model of the Puma, SA330 research helicopter is used as a reference model. First, the model is described and with standard reference input test signals, output data set is generated, then this input-output dataset is used for system identification purpose. Both traditional methods such as subspace & prediction-error minimization (PEM) method along with modern ways of identification methods such as neural networks are used. A practical comparison between used identification methods and best suitable type of input for estimation is discussed. © 2015 IEEE.
  • No Thumbnail Available
    Item
    FedPruNet: Federated Learning Using Pruning Neural Network
    (Institute of Electrical and Electronics Engineers Inc., 2022) Gowtham, L.; Annappa, A.; Sachin, D.N.
    Federated Learning (FL) is a distributed form of training the machine learning and deep learning models on the data spread over heterogeneous edge devices. The global model at the server learns by aggregating local models sent by the edge devices, maintaining data privacy, and lowering communication costs by just communicating model updates. The edge devices on which the model gets trained usually will have limitations towards power resource, storage, computations to train the model. This paper address the computation overhead issue on the edge devices by presenting a new method named FedPruNet, which trains the model in edge devices using the neural network model pruning method. The proposed method successfully reduced the computation overhead on edge devices by pruning the model. Experimental results show that for the fixed number of communication rounds, the model parameters are pruned up to 41.35% and 65% on MNIST and CIFAR-10 datasets, respectively, without compromising the accuracy compared to training FL edge devices without pruning. © 2022 IEEE.
  • No Thumbnail Available
    Item
    A Study on Depth Estimation from Single Image Using Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2022) Shree, R.; Madagaonkar, S.B.; Singh, M.; Chandra, M.T.A.; Rathnamma, M.V.; Venkataramana, V.; Chandrasekaran, K.
    Depth estimation is fundamental in upcoming technology advancements like scene understanding, robot vision, intelligent driver assistance systems, and many new technologies. Estimating the depth of objects from a viewport can be achieved using various mathematical, geometrical, and stereo concepts, but the process is unaffordable and erroneous. Depth estimation from a single can be accurately done using neural networks. Although this is a challenging task, researchers around the globe have published various works. The works include different neural network standards like CNN, GANs, Encoder-Decoder. The paper analyses and examines famous works in this field of study. Later in the paper, a comparative survey of depth estimation approaches using neural networks is done. © 2022 IEEE.