BITS Faculty Publications

Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867

Browse

Subject: search.filters.subject.Neural networks

Search Results

Now showing 1 - 10 of 60
  • No Thumbnail Available
    Item
    Physics-informed failure prediction in disordered systems sharing a common resource
    (Elsevier, 2026-03) Singh, Navin
    We study the progressive degradation of disordered systems that experience multiple intermediate failures and equilibrations before collapsing while sharing a common resource. The system is modelled using a generalized Fibre Bundle framework, wherein individual elements fail upon exceeding their local thresholds, and their load is redistributed among surviving elements according to a prescribed load-sharing scheme. We employ two classes of disorder distributions: the two-parameter Weibull and a more flexible custom distribution. To predict the ultimate tensile strength (UTS) and critical burst size which characterize system failure in this model—we employ Artificial Neural Networks (ANNs) informed by theoretical expressions rooted in statistical physics. Our investigation shows that the predictive performance of ANNs is significantly improved (from 83% to 99%) by our Physics informed theoretical predictors. This approach reduces the need for large-scale simulations and is a more efficient way to estimate the reliability of such complex disordered systems.
  • No Thumbnail Available
    Item
    A multi-modal smart switching based image transmission using semantic communication
    (IEEE, 2025-02) Tripathi, Sharda; Joshi, Sandeep
    The conventional paradigm of communication primarily concentrates on the transmission of raw data, often disregarding its contextual meaning. However, to tackle the exponential growth in data demands along with the limited availability of transmission bandwidth, there is an increasing need to transition from Shannon’s classical information-theoretic communication to a more advanced framework centered on semantics. This work presents a multi-modal semantic-based communication method for the transmission of high-definition images aimed at optimizing the transmitted data volume while maintaining a high throughput and mean intersection over union score. To this end, two architectural models are explored: a denser ResNet-based and a lightweight U-Net-based. Depending on the required QoS and resource availability, the raw image is either semantically segmented to obtain a fine-grained, pixel-level classification of the image or represented as label semantics, which provides only a higher-level, object-based, or region-based classification prior to its transmission. The experimental results show that such an adaptive semantic image processing approach leads to around 63% reduction in the transmitted data volume without compromising on the quality of image reconstruction.
  • No Thumbnail Available
    Item
    Quantum computing-accelerated kalman filtering for satellite clusters: algorithms and comparative analysis
    (IEEE, 2025-01) Bitragunta, Sainath; Bhatia, Ashutosh; Tiwari, Kamlesh
    The increasing demand for high-precision real-time data processing in satellite clusters requires efficient algorithms to manage inherent uncertainties in space-based systems. We propose an innovative framework that integrates Quantum Neural Network (QNN) architecture into Kalman filtering processes, specifically tailored for Low Earth Orbit satellite clusters. Our quantum computing-based approach achieves a significant improvement in prediction accuracy and a reduction in mean absolute error compared to classical Kalman filtering techniques. These advances significantly improve computational efficiency and error handling, making the method highly scalable under varying noise levels. A comparative analysis demonstrates the superior performance of the Quantum Kalman Filter in processing speed, resource utilization, and prediction accuracy, all evaluated within the constraints of LEO satellite constellations. These findings highlight the potential of quantum computing to optimize data processing strategies for future missions, including deep space explorations.
  • No Thumbnail Available
    Item
    Neutrino interaction vertex reconstruction in dune with pandora deep learning
    (2025) Chauhan, Bhavesh
    The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours.
  • No Thumbnail Available
    Item
    Modelling for working capital efficiency: integrating SBM-DEA and artificial neural networks in Indian manufacturing
    (Emerald, 2024-09) Chadha, Saurabh
    This study aims to present an innovative predictive methodology that transitions from traditional efficiency assessment techniques to a forward-looking strategy for evaluating working capital management(WCM) and its determinants by integrating data envelopment analysis (DEA) with artificial neural networks (ANN).
  • No Thumbnail Available
    Item
    Application of Spiking Neural Networks in Renewable Energy Forecasting
    (Springer, 2024-12) Pasari, Sumanta
    Considering the high consumption rates of the non-renewable energy sources as well as their adverse climatic impacts, renewable energy has become a widespread topic of discussion. Among the available renewable resources, solar and wind are the highest contributors. However, the high influence of atmospheric parameters and higher cost involved in energy production prevent the widespread use of renewable energy among common public. The location identification for optimum energy production is also a crucial step for setting up future energy plants. In this regard, here we propose a novel strategy to compare prediction results in terms of loss made by traditional convolutional neural network (CNN) with that of spiking neural network (SNN). Though the SNNs are popularly used for vision related tasks, here we evaluate their efficacy in analyzing time series data of solar irradiance and wind speed. In summary, we provide a comprehensive discussion on SNN and their significance on energy forecasting.
  • No Thumbnail Available
    Item
    Lightweight convolutional neural network architecture implementation using TensorFlow lite
    (Springer, 2023-06) Asati, Abhijit
    Recently, with the increase in the precision of convolutional neural networks (CNN) on a wide variety of classification and recognition tasks, the demand for their deployment has dramatically increased. Even the focus is on lightweight, faster, and low-power implementations. In this paper, we have implemented a CNN model onto an embedded platform, ‘Raspberry Pi 4-Model B edge computing system (RP4-BECS)’. This CNN model was initially trained and verified in MATLAB and then implemented on the Machine Learning (ML) framework to generate a TensorFlow lite (TF-lite) flat buffer format. This implementation offers a reduced size of models with good prediction accuracy and lesser inference time as compared with the available literature. We attempted three trials for all the digits from 0 to 9 to evaluate average prediction accuracy and average inference time. An average prediction accuracy of 99.32% and average inference time of 22.53 ms is achieved for the Sign Language Digits Database (SLDD). Further, an average prediction accuracy of 99.09% and average inference time of 13.28 ms is achieved for the Modified National Institute of Standards and Technology Database (MNIST). The model sizes implemented using TF-Lite are highly reduced to 1.53 MB for SLDD and 148 KB for the MNIST database. The obtained accuracy, inference time and model sizes are better than published results.
  • No Thumbnail Available
    Item
    Text-Convolutional Neural Networks for Fake News Detection in Tweets
    (Springer, 2020-09) Sharma, Yashvardhan
    With the widespread use of online social networking websites, user-generated stories and social network platform have become critical in news propagation. The Web portals are being used to mislead users for political gains. Unreliable information is being shared without any fact-checking. Therefore, there is a dire need for automatic news verification system which can help journalists and the common users from misleading content. In this work, the task is defined as being able to classify a tweet as real or fake. The complexity of natural language constructs along with variegated languages makes this task very challenging. In this work, a deep learning model to learn semantic word embeddings is proposed to handle this complexity. The evaluations on the benchmark dataset (VMU 2015) show that deep learning methods are superior to traditional natural language processing algorithms
  • No Thumbnail Available
    Item
    Irony Detection in Non-English Tweets
    (IEEE, 2021) Sharma, Yashvardhan
    Sentiment analysis is the interpretation and classification of emotions conveyed by text data. While there have been many attempts to classify the sentiment of a given text, there have been few models that can do the same when provided with non-English data exhibiting sarcasm or irony. This paper aims to compare various techniques of sarcasm detection and decide which method works the best for datasets of different sizes and types. The models have been tested on datasets of three different non-English languages - Arabic, French and a Hindi-English code-mix. None of the presented models are language-specific and can be run on data of any language. A comparison between a sub-word model, the usage of Term Frequency-Inverse Document Frequency (TF-IDF) and neural networks, a Long Short-Term Memory (LSTM) model and machine learning techniques such as Nearest Neighbors, Decision Tree, Random Forest, AdaBoost, Naive Bayes (NB), Support Vector Machine (SVM) Linear, SVM radial basis function (RBF), SVM Sigmoid has been performed. The output for each language and model has been evaluated based on their F1-score, accuracy, precision, and recall.
  • No Thumbnail Available
    Item
    FakeRevealer: A Multimodal Framework for Revealing the Falsity of Online Tweets Using Transformer-Based Architectures
    (Scitepress, 2023) Sharma, Yashvardhan; Chauhan, Gajendra Singh
    As the Internet has evolved, the exposure and widespread adoption of social media concepts have altered the way news is formed and published. With the help of social media, getting news is cheaper, faster, and easier. However, this has also led to an increase in the number of fake news articles, either by manipulating the text or morphing the images. The spread of fake news has become a serious issue all over the world. In one case, at least 20 people were killed just because of false information that was circulated over a social media platform. This makes it clear that social media sites need a system that uses more than one method to spot fake news stories. To solve this problem, we’ve come up with FakeRevealer, a single-configuration fake news detection system that works on transfer learning based techniques. Our multi-modal archutecture understands the textual features using a language transformer model called DistilRoBERTa and image features are extracted using the Vision Transf ormer (ViTs) that is pre-trained on ImageNet 21K. After feature extraction, a cosine similarity measure is used to fuse both the features. The evaluation of our proposed framework is done over publicly available twitter dataset and results shows that it outperforms current state-of-art on twitter dataset with an accuracy of 80.00% which is 2.23%more, that than the current state-of-art on twitter dataset