Department of Computer Science and Information Systems

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928

Browse

Start date: 2010Subject: search.filters.subject.Neural networks

Search Results

Now showing 1 - 10 of 23
  • 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
    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
  • No Thumbnail Available
    Item
    Impact of Transformer-Based Models and User Clustering in Early Fake News Detection in Social Media
    (Scitepress, 2023) Sharma, Yashvardhan; Chauhan, Gajendra Singh
    People are now consuming news on social media platforms rather than through traditional sources as a result of easy access to the internet. This has allowed for the recent rise in the online dissemination of false information. The spread of false information seriously damages people’s reputations and the public’s trust in them. The research community has recently given fake news identification a great deal of attention, and prior studies have mainly concentrated on finding hints in news content or diffusion graphs. The older models, on the other hand, didn’t have the key features needed to spot fake news quickly. We focus on finding fake news by using features that are available when it is just starting to spread. The current work suggests a new framework made up of content-based features taken from news articles and social-context features taken from user characteristics and responses at the sentence level. In addition, we extend our approach to Transformer-based models and leverage user clustering to demonstrate a considerable performance gain over the original model.
  • No Thumbnail Available
    Item
    Steno AI at SemEval-2023 Task 6: Rhetorical Role Labelling of Legal Documents using Transformers and Graph Neural Networks
    (Association for Computational Linguistics, 2023) Sharma, Yashvardhan
    A legal document is usually long and dense requiring human effort to parse it. It also contains significant amounts of jargon which make deriving insights from it using existing models a poor approach. This paper presents the approaches undertaken to perform the task of rhetorical role labelling on Indian Court Judgements as part of SemEval Task 6: understanding legal texts, shared subtask A (Modi et al., 2023). We experiment with graph based approaches like Graph Convolutional Networks and Label Propagation Algorithm, and transformer-based approaches including variants of BERT to improve accuracy scores on text classification of complex legal documents.
  • No Thumbnail Available
    Item
    Novel Image Compression and Deblocking Approach Using BPN and Deep Neural Network Architecture
    (Springer, 2021-04) Viswanathan, Sangeetha
    Medical imaging is an important source of digital information to diagnose the illness of a patient. The digital information generated consists of different modalities that occupy more disk space, and the distribution of the data occupies more bandwidth. A digital image compression technique that can reduce an image's size without losing much of its important information is challenging. In this paper, a novel image compression technique based on BPN and Arithmetic coders is proposed. The high non-linearity and unpredictiveness of the interrelationship between the pixels present in the image to be compressed is handled by BPN. An efficient coding technique called Arithmetic coding is used to produce an image with a better compression ratio and lower redundancy. A deep CNN based image deblocker is used as a post-processing step to remove the artefacts present in the reconstructed image to improve the quality of the reconstructed image. The effectiveness of the proposed methodology is validated in terms of PSNR. The proposed method is able to achieve about a 3% improvement in PSNR compared with the existing methods.
  • No Thumbnail Available
    Item
    Classifying DNS over HTTPS Malicious/Benign Traffic Using Deep Learning Models
    (IEEE, 2023) Viswanathan, Sangeetha
    As we live in an era where privacy over the Internet has become rudimentary, protocols like DNS over HTTPS (DoH) and DNS over TLS (DoT), which promote encryption, have become popular. While these protocols were introduced to overcome the drawbacks of DNS protocol, even DoH has some security issues that need to be tackled to prevent any misuse. Herein, we implemented deep learning models to classify DNS over HTTPS traffic and found the most efficient method in regard to time-required complexity and computational requirements. Previous studies have used a variety of features from datasets to identify malicious activities. Although machine learning and deep learning models are commonly used, they require more human intervention. These models are also more computationally complex, as one is required to tune the model and its parameters for accurate results. In comparison, some deep learning models are more efficient as they work well without any human intervention and are capable of parameter tuning by themselves. In this work, we used the CIRA-CIC-DoHBrw-2020 dataset and performed data imbalance handling, one hot encoding, and feature selection to create a model that can be used for a more generalized environment. We implemented long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and gated recurrent unit (GRU) models to classify DoH traffic with high accuracy. Although the mentioned models produced good accuracy, the BiLSTM model performs better than the LSTM model in the time taken for prediction and accuracy; the GRU model outperformed both LSTM and BiLSTM models in terms of accuracy, computation time, and computation complexity. Hence, it is more efficient than both LSTM and BiLSTM models.
  • No Thumbnail Available
    Item
    Deep Neural Networks Fused with Textures for Image Classification
    (Springer, 2023-08) Bera, Asish
    Fine-grained image classification (FGIC) is a challenging task due to small visual differences among inter-subcategories, but large intra-class variations. In this paper, we propose a fusion approach to address FGIC by combining global texture with local patch-based information. The first pipeline extracts deep features from various fixed-size non-overlapping patches and encodes features by sequential modeling using the long short-term memory (LSTM). Another path computes image-level textures at multiple scales using the local binary patterns (LBP). The advantages of both streams are integrated to represent an efficient feature vector for classification. The method is tested on six datasets (e.g., human faces, food-dishes, etc.) using four backbone CNNs. Our method has attained better classification accuracy over existing methods with notable margins
  • No Thumbnail Available
    Item
    Your Tribe Decides Your Vibe: Analyzing Local Popularity in the US Patent Citation Network
    (ARXIV, 2021-06) Narang, Nishit
    In many networks, the indegree of a vertex is a measure of its popularity. Past research has studied indegree distributions treating the network as a whole. In the US Patent citation network (USPCN), patents are classified into categories and subcategories. A natural question arises: How do patents gather their popularity from various (sub)categories? We analyse local indegree distributions to answer this question. The citation (indegree) of a patent within the same category indicates its internal popularity, while a cross-category citation indicates its external popularity. We analyze the internal and external indegree distributions at each level of USPCN hierarchy to learn how the internal and external popularity of patents varies across (sub)categories. We find that all (sub)categories have local preferences that decide internal and external patents' popularities. Different patents are popular in different groups: Groups C1, C2 and C3 may not agree on popular patents in C1. In general, patent popularity appears to be a highly local phenomenon with subcategories (not even categories) deciding their own popular patents independent of the other (sub)categories