arXiv subjects

Aman Yadav

Publications and source records attributed to Aman Yadav.

3 recordsLinked to original sources

arXiv2025

Cognitive Inference based Feature Pyramid Network for Sentimental Analysis using EEG Signals

Sentiment analysis using Electroencephalography (EEG) sensor signals provides a deeper behavioral understanding of a person's emotional state, offering insights into real-time mood fluctuations. This approach takes advantage of brain electrical activity, making it a promising tool for various applications, including mental health monitoring, affective computing, and personalised user experiences. An encoder-based model for EEG-to-sentiment analysis, utilizing the ZUCO 2.0 dataset and incorporating a Feature Pyramid Network (FPN), is proposed to enhance this process. FPNs are adapted here for EEG sensor data, enabling multiscale feature extraction to capture local and global sentiment-related patterns. The raw EEG sensor data from the ZUCO 2.0 dataset is pre-processed and passed through the FPN, which extracts hierarchical features. In addition, extracted features are passed to a Gated Recurrent Unit (GRU) to model temporal dependencies, thereby enhancing the accuracy of sentiment classification. The ZUCO 2.0 dataset is utilized for its clear and detailed representation in 128 channels, offering rich spatial and temporal resolution. The experimental metric results show that the proposed architecture achieves a 6.88\% performance gain compared to the existing methods. Furthermore, the proposed framework demonstrated its efficacy on the validation datasets DEAP and SEED.

eess.SP↗

arXiv2024

Tiling Spaces and the Expanding Universe: Bridging Quantum Mechanics and Cosmology

We propose a heuristic model of the universe as a growing quasicrystal projected from a higher-dimensional lattice. This quasicrystalline framework offers a novel perspective on cosmic expansion, where the intrinsic growth dynamics naturally give rise to the observed large-scale expansion of the universe. Motivated by this model, we explore the Schr\"odinger equation for a particle in a box with time-dependent boundaries, representing the expanding underlying space. By introducing a constraint that links microscale quantum phenomena with macroscale cosmological quantities, we derive an equation resembling the Friedmann equation, providing potential insights into the Hubble tension. Our model incorporates phonons and phasons-quasiparticles inherent in quasicrystalline structures-that play critical roles in cosmic-scale dynamics and the universe's expansion. This framework suggests that the necessity for an inflationary period may be obviated. Furthermore, phonons arising from the quasicrystalline structure may serve as dark matter candidates, influencing the dynamics of ordinary matter while remaining largely undetectable through electromagnetic interactions. Drawing parallels with crystalline matter at atomic scales, which is fundamentally quantum in nature, we explore how the notion of tiling space can support continuous symmetry atop a discrete structure. This provides a novel framework for understanding the universe's expansion and underlying structure. Consequently, our approach suggests that further development could enhance our understanding of cosmic expansion and the universe's structure, bridging concepts from quantum mechanics, condensed matter physics, and cosmology.

physics.gen-ph↗

arXiv2023

Natural Language Processing Through Transfer Learning: A Case Study on Sentiment Analysis

Artificial intelligence and machine learning have significantly bolstered the technological world. This paper explores the potential of transfer learning in natural language processing focusing mainly on sentiment analysis. The models trained on the big data can also be used where data are scarce. The claim is that, compared to training models from scratch, transfer learning, using pre-trained BERT models, can increase sentiment classification accuracy. The study adopts a sophisticated experimental design that uses the IMDb dataset of sentimentally labelled movie reviews. Pre-processing includes tokenization and encoding of text data, making it suitable for NLP models. The dataset is used on a BERT based model, measuring its performance using accuracy. The result comes out to be 100 per cent accurate. Although the complete accuracy could appear impressive, it might be the result of overfitting or a lack of generalization. Further analysis is required to ensure the model's ability to handle diverse and unseen data. The findings underscore the effectiveness of transfer learning in NLP, showcasing its potential to excel in sentiment analysis tasks. However, the research calls for a cautious interpretation of perfect accuracy and emphasizes the need for additional measures to validate the model's generalization.

cs.CL↗