Department of Civil Engineering
Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1927
Browse
6 results
Search Results
Item Inception SN: An Inception based Convolutional Neural Network for Hyperspectral Image Classification(IEEE, 2021-10) Gupta, RajivHyperspectral satellite imagery provides a wealth of spatial and spectral information about a given scene of interest. Therefore it is widely used in several applications like pixel-wise classification, vegetation mapping, ocean color monitoring and so on. Many pixel-wise classification algorithms like support vector machine, random forest, parallelopiped classifier, and neural networks are used for this purpose. The advent of convolutional neural networks (CNN) has brought about great development in this field, owing to their unique property of automatic feature extraction. Plain CNN architectures perform only one of pooling/convolution at each stage for feature extraction. This paper describes a new CNN architecture, the Inception SN, which makes use of both pooling and convolution at each stage to effectively extract features. It also makes use of spatial and spectral information in order to carry out classification. The outcome of this is a robust algorithm which performs well even with lower training data.Item Assessment of sustainability index for rural water management using ANN(IWA, 2022) Gupta, Rajiv; Kumar, GauravThe current study proposes a sustainability index (SI) measure based on artificial neural networks (ANN) and globally accepted parameters. Some of the available methods for SI measurement are multi-criteria analysis, external costs, energy analysis, and ecological footprint methods. However, validity remains a concern due to a system's needs, criteria, and requirements. Generally, sustainability is assessed in economic, environmental, and social issues, which varies across regions and countries. Most of the studies accept sub-indices but to a limited extent. Therefore, the proposed study develops an SI evaluation method based on the idea of multi-sustainability incorporating operations, institutions, risks, and climate factors besides economic, environmental, and social issues. All these issues might not be applicable to a single project but may help to develop a complete index when applied. The present study considered different scenarios in building a method to calculate SI using ANN. The results obtained by the ANN model for various input parameters helped to identify the best water conservation strategy. Sensitivity analysis was also performed to determine the uncertainty contribution/significance of the input variables for the water scarcity in the study region. The developed model in the study is tested on a rural water management system.Item Spatiotemporal analysis and prediction of urban evolution patterns using ANN tool(ICE Virtual Library, 2023-11) Gupta, RajivThe precise quantification of land-use land cover plays a vital role in preserving sustainability, which is being affected by growing urbanisation. The study proposes the comprehensive Geographical Information System approach in integration with Artificial Neural Network to analyse the past development patterns of a city for predicting future land transformations. In this study, land transformations over the past three decades (1990–2020) were analysed using classified maps for Jaipur city, India, as a case study, which reveals that the built-up land was increased by 46.55%. Subsequently, the simulated land transformation map for 2030 using the multi-layer perceptron and cellular automata anticipates that the built-up land would be increased by 12.68% by cutting down the barren land and vegetation by 9.44 and 3.24%, respectively. The simulation offers strong evidence that most of the medium-built-up land density municipality wards transform into high-density built-up land density wards during the next decade, which is visualised through the exclusively developed ward-by-ward built-up land density maps. The utilisation of the simulated map in the proposed way helps to prepare comprehensive micro-level urban development planning by incorporating natural resource conservation and land-use planning.Item Low-cost Artificial Intelligence Enhanced Hardware Design for Data Augmentation(IEEE, 2023) Gupta, Rajiv; Gupta, AnuThis paper presents a novel low-cost hardware implementation of data augmentation using artificial neural networks for a low-power, low-cost Water Quality Indexing application. Multilayer Perceptron (MLP) feedforward network with backpropagation learning has been designed to predict the data of DO and EC using pH and ORP as the input vector. This reduces the requirement for costly sensor electrodes, decreasing the design's cost. The design has been implemented on both ASIC and Embedded platforms. The Augmentation ANN predicts DO and EC with a 98% accuracy rate and achieves a 92% reduction in cost. The results have been presented and compared with standard WQI device.Item Removal of COD and color from textile industrial wastewater using wheat straw activated carbon: an application of response surface and artificial neural network modeling(Springer, 2023) Singh, Ajit PratapA novel approach has been undertaken wherein chemically modified wheat straw activated carbon (WSAC) as adsorbent is developed, characterized, and examined for the removal of COD and color from the cotton dyeing industry effluent. Thirty experimental runs are designed for batch reactor study using the central composite method (CCM) for optimizing process parameters, namely biochar dose, time of contact, pH, and temperature, for examining the effect on COD and color-removing efficiency of WSAC. The experimental data have been modeled using the machine learning approaches such as polynomial quadratic regression and artificial neural networks (ANN). The determined optimum conditions are pH: 7.18, time of contact: 85.229 min, adsorbent dose: 2.045 g/l, and temperature: 40.885 °C, at which the COD and color removal efficiency is 90.92 and 94.48%, respectively. The nonlinear pseudo-second order (PSO) kinetic model shows good coefficient of determination (R2 ~ 1) values. The maximum adsorption capacity for COD and color by WSAC is at the pH of 7, the temperature of 40 °C, adsorbent dose of 2 g/l is obtained at the contact time of 80 min is 434.78 mg/g and 331.55 PCU/g, respectively. The COD removal and decolorization is more than 70% in the first 20 min of the experiment. The primary adsorption mechanism involves hydrogen bonding, electrostatic attraction, n-π interactions, and cation exchange. Finally, the adsorbent is environmentally benign and cost-effective, costing 16.66% less than commercially available carbon. The result of the study indicates that WSAC is a prominent solution for treating textile effluent. The study is beneficial in reducing the pollutants from textile effluents and increasing the reuse of treated effluent in the textile industries.Item Performance of the generalized delta rule in structural damage detection(Elsiever, 1995-04) Barai, Sudhir KumarThe paper examines the suitability of the generalized data rule in training artificial neural networks (ANN) for damage identification in structures. Several multilayer perceptron architectures are investigated for a typical bridge truss structure with simulated damage states generated randomly. The training samples have been generated in terms of measurable structural parameters (displacements and strains) at suitable selected locations in the structure. Issues related to the performance of the network with reference to hidden layers and hidden neurons are examined. Some heuristics are proposed for the design of neural networks for damage identification in structures. These are further supported by an investigation conducted on five other bridge truss configurations.