http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/1925 2026-04-01T13:40:21Z 2026-04-01T13:40:21Z Joshi, Sandeep http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/19317 2025-09-03T10:19:08Z 2025-04-01T00:00:00Z

Title: Stochastic diffusivity with time-varying trajectory in mobile molecular communication: performance analysis and channel modeling Authors: Joshi, Sandeep Abstract: This work considers a three-dimensional mobile molecular communication (MC) with intra-body disease spread applications. The communicating devices in the considered mobile MC system are point transmitters and passive spherical receiver nano-machines (NMs) with emitted information-carrying molecules following the Gaussian Brownian motion. These NMs can be used to detect the presence of disease spread and for targeted drug delivery. We propose stochastic diffusivity models for both communicating devices and information-carrying molecules. Using the stochastic diffusivity model and considering initial distance as a reference, we derive the probability density function of the relative distance between the communicating devices. We allocate the time-varying trajectory to the information-carrying molecules moving towards receiver NM and obtain its diffusivity distribution. Through the proposed stochastic diffusivity model, we characterize the mobile MC channel by channel impulse response and derive its statistical mean. We consider the discrete-time statistical channel model at a high inter-symbol interference regime and analyze the channel performance in terms of error analysis and receiver operating characteristics. We also derive the channel for the considered system model. We show the degree of accuracy through root mean square error for the Poisson and Gaussian distribution models. Furthermore, the numerical results are verified through particle-based simulations.

2025-04-01T00:00:00Z Joshi, Sandeep http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/19316 2025-09-03T10:14:54Z 2025-03-01T00:00:00Z

Title: Nonlinear anisotropic diffusion-based channel estimation in 5G wireless networks Authors: Joshi, Sandeep Abstract: In the context of the fifth-generation new radio downlink scenario, we introduce an innovative approach for channel estimation in this paper that circumvents the requirement for the prior dataset. We incorporate anisotropic diffusion and bit-plane decomposition to remove the noise in channel estimates. We first pre-process wireless channel coefficients with bit-plane decomposition to partially reduce noise interference and maintain the granularity of the information. In the second stage, anisotropic diffusion is performed based on neighboring coefficients, and the gradient-based denoising takes place without prior training. We assess the mean square error (MSE) across varying noise levels compared to the state-of-the-art method and further explore the impact of key parameters governing anisotropic diffusion. The simulation results indicate that the proposed channel estimation technique achieves a 44.77% reduction in average MSE and a significant reduction in computational complexity compared to the baseline reference technique.

2025-03-01T00:00:00Z Joshi, Sandeep http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/19315 2025-09-03T10:10:33Z 2025-08-01T00:00:00Z

Title: Redefining channel estimation in underwater acoustic OFDM systems with deep neural network Authors: Joshi, Sandeep Abstract: This paper introduces a novel method for channel estimation in underwater acoustic communication in an autonomous underwater vehicular network. The proposed method employs a denoising technique to refine least squares (LS) channel estimates using deep image prior (DIP). By establishing an equivalence between underwater acoustic (UWA) channel estimation and image denoising, we leverage DIP to enhance estimation accuracy. The proposed approach is validated on the Norway continental shelf (NCS1) watermark dataset, demonstrating superior performance with average mean square error reductions of 96.64% and 96.09% compared to LS and the deep denoising convolutional neural network (DnCNN), respectively. Furthermore, the proposed analysis of pilot symbol utilization in the DIP-based estimator shows a 46.47 % error reduction, even when using only 25 % of the pilot symbols. By efficiently utilizing available resources, the proposed method enhances spectral efficiency and enables accurate estimation, even with limited pilot signals.

2025-08-01T00:00:00Z Sambangi, Ramesh http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/19314 2025-09-03T09:29:08Z 2021-11-01T00:00:00Z

Title: LPNet: a DNN based latency prediction technique for application mapping in Network-on-Chip design Authors: Sambangi, Ramesh Abstract: Analytical models used for latency estimation of Network-on-Chip (NoC) are not producing reliable accuracy. This makes these analytical models difficult to use in optimization of design space exploration. In this paper, we propose a learning based model using deep neural network (DNN) for latency predictions. Input features for DNN model are collected from analytical model as well as from Booksim simulator. Then this DNN model has been adopted in mapping optimization loop for predicting the best mapping of given application and NoC parameters combination. Our simulations show that using the proposed DNN model, prediction error is less than 12% for both synthetic and application specific traffic. More than 108 times speedup could be achieved using DPSO with DNN model compared to DPSO using Booksim simulator.

2021-11-01T00:00:00Z