arXiv subjects

Akash Pandey

Publications and source records attributed to Akash Pandey.

10 recordsLinked to original sources

arXiv2026

TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification

Identifying the extent to which every temporal segment influences a model's predictions is essential for explaining model decisions and increasing transparency. While post-hoc explainable methods based on gradients and feature-based attributions have been popular, they suffer from reference state sensitivity and struggle to generalize across time-series datasets, as they treat time points independently and ignore sequential dependencies. Another perspective on explainable time-series classification is through interpretable components of the model, for instance, leveraging self-attention mechanisms to estimate temporal attribution; however, recent findings indicate that these attention weights often fail to provide faithful measures of temporal importance. In this work, we advance this perspective and present a novel explainability-driven deep learning framework, TimeSliver, which jointly utilizes raw time-series data and its symbolic abstraction to construct a representation that maintains the original temporal structure. Each element in this representation linearly encodes the contribution of each temporal segment to the final prediction, allowing us to assign a meaningful importance score to every time point. For time-series classification, TimeSliver outperforms other temporal attribution methods by 11% on 7 distinct synthetic and real-world multivariate time-series datasets. TimeSliver also achieves predictive performance within 2% of state-of-the-art baselines across 26 UEA benchmark datasets, positioning it as a strong and explainable framework for general time-series classification.

cs.LG↗

arXiv2025

Design, simulation and performance of the resistive-anode PICOSEC Micromegas detector

The PICOSEC Micromegas detector is a Micro-Pattern Gaseous Detector concept developed to achieve tens of picosecond timing resolution for charged particle detection by combining a Cherenkov radiator with a two-stage Micromegas amplification structure. To improve operational robustness, a resistive anode has been implemented using a DLC layer deposited on a Kapton substrate. While this design enhances detector stability, the resistive layer may influence rate capability, signal formation, and detector capacitance, altering timing performance. This work presents a comprehensive study of a resistive design, including an analytical model and finite-element simulations to quantify rate-dependent gain reduction due to ohmic voltage drop on the resistive layer. An analytical solution for the voltage across a finite-size resistive layer is derived, and a numerical model is developed to evaluate gain suppression under intense particle fluxes. The impact of the resistive layer on signal formation is investigated using time-dependent weighting fields and the Garfield++ simulation framework. The contribution of signal components induced by the resistive layer is quantified, and preservation of the signal leading edge is found for surface resistivities above 100 kohm per square. Single-channel resistive-anode prototypes were designed, constructed, and experimentally characterized. Laboratory measurements using single photoelectrons and power spectral density analysis show the predicted reduction in signal amplitude while preserving the leading edge. Muon beam tests with CsI and DLC photocathodes demonstrate a time resolution of 11.5 ps for CsI, comparable to 11.9 ps for the metallic-anode device, showing the suitability of the resistive design for precision timing applications.

physics.ins-det↗

arXiv2025

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

From clinical healthcare to daily living, continuous sensor monitoring across multiple modalities has shown great promise for real-world intelligent decision-making but also faces various challenges. In this work, we introduce MAESTRO, a novel framework that overcomes key limitations of existing multimodal learning approaches: (1) reliance on a single primary modality for alignment, (2) pairwise modeling of modalities, and (3) assumption of complete modality observations. These limitations hinder the applicability of these approaches in real-world multimodal time-series settings, where primary modality priors are often unclear, the number of modalities can be large (making pairwise modeling impractical), and sensor failures often result in arbitrary missing observations. At its core, MAESTRO facilitates dynamic intra- and cross-modal interactions based on task relevance, and leverages symbolic tokenization and adaptive attention budgeting to construct long multimodal sequences, which are processed via sparse cross-modal attention. The resulting cross-modal tokens are routed through a sparse Mixture-of-Experts (MoE) mechanism, enabling black-box specialization under varying modality combinations. We evaluate MAESTRO against 10 baselines on four diverse datasets spanning three applications, and observe average relative improvements of 4% and 8% over the best existing multimodal and multivariate approaches, respectively, under complete observations. Under partial observations -- with up to 40% of missing modalities -- MAESTRO achieves an average 9% improvement. Further analysis also demonstrates the robustness and efficiency of MAESTRO's sparse, modality-aware design for learning from dynamic time series.

cs.LG↗

arXiv2025

Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs

Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech. However, most prior methods rely on paired voiced and unvoiced EMG signals, along with speech data, for EMG-to-text conversion, which is not practical for such individuals. Given the rise of large language models (LLMs) in speech recognition, we explore their potential to understand unvoiced speech. To this end, we address the challenge of learning from unvoiced EMG alone and propose a novel EMG adaptor module that maps EMG features into an LLM's input space, achieving an average word error rate (WER) of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. Even with a conservative data availability of just six minutes, our approach improves performance over specialized models by nearly 20%. While LLMs have been shown to be extendable to new language modalities -- such as audio -- understanding articulatory biosignals like unvoiced EMG remains more challenging. This work takes a crucial first step toward enabling LLMs to comprehend unvoiced speech using surface EMG.

cs.CL↗

arXiv2025

COLOR: A compositional linear operation-based representation of protein sequences for identification of monomer contributions to properties

The properties of biological materials like proteins and nucleic acids are largely determined by their primary sequence. While certain segments in the sequence strongly influence specific functions, identifying these segments, or so-called motifs, is challenging due to the complexity of sequential data. While deep learning (DL) models can accurately capture sequence-property relationships, the degree of nonlinearity in these models limits the assessment of monomer contributions to a property - a critical step in identifying key motifs. Recent advances in explainable AI (XAI) offer attention and gradient-based methods for estimating monomeric contributions. However, these methods are primarily applied to classification tasks, such as binding site identification, where they achieve limited accuracy (40-45%) and rely on qualitative evaluations. To address these limitations, we introduce a DL model with interpretable steps, enabling direct tracing of monomeric contributions. We also propose a metric ($\mathcal{I}$), inspired by the masking technique in the field of image analysis and natural language processing, for quantitative analysis on datasets mainly containing distinct properties of anti-cancer peptides (ACP), antimicrobial peptides (AMP), and collagen. Our model exhibits 22% higher explainability, pinpoints critical motifs (RRR, RRI, and RSS) that significantly destabilize ACPs, and identifies motifs in AMPs that are 50% more effective in converting non-AMPs to AMPs. These findings highlight the potential of our model in guiding mutation strategies for designing protein-based biomaterials.

q-bio.BM↗

arXiv2024

Phenomenological study of the charged particles production in pPb collisions at $\sqrt{s_{\rm{NN}}}$ = 5.02 TeV

We have studied transverse momentum ($p_{\rm{T}}$) spectra of charged hadrons in various pseudo-rapidity ranges for p-Pb collisions at $\sqrt{s_{\rm{NN}}}$ = 5.02 TeV. The medium effects such as collective flow and energy loss resulting from heavy-ion collisions have also been investigated using modified Tsallis distribution function over a wide range of $p_{\rm{T}}$ that indicates the transverse collective flow at low and intermediate $p_{\rm{T}}$ range and in-medium energy loss in high $p_{\rm{T}}$ range.

hep-ph↗

arXiv2023

Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks

Human emotion understanding is pivotal in making conversational technology mainstream. We view speech emotion understanding as a perception task which is a more realistic setting. With varying contexts (languages, demographics, etc.) different share of people perceive the same speech segment as a non-unanimous emotion. As part of the ACM Multimedia 2023 Computational Paralinguistics ChallengE (ComParE) in the EMotion Share track, we leverage their rich dataset of multilingual speakers and multi-label regression target of 'emotion share' or perception of that emotion. We demonstrate that the training scheme of different foundation models dictates their effectiveness for tasks beyond speech recognition, especially for non-semantic speech tasks like emotion understanding. This is a very complex task due to multilingual speakers, variability in the target labels, and inherent imbalance in the regression dataset. Our results show that HuBERT-Large with a self-attention-based light-weight sequence model provides 4.6% improvement over the reported baseline.

cs.AI↗

arXiv2021

Pulse shape simulation of p-type Point Contact Germanium Detector for The MAJORONA DEMONSTRATOR Experiment

In the rare physics events search, liquid and solid detector plays an important role. Its analysis is based on the detection of excess events over the expected background or on the detection of an annual event rate modulation. Germanium detectors sensitivities have been demonstrated as efficient means to probe Weakly Interacting Massive Particles (WIMPs). Germanium detectors having sensitivity less than 100 eV opens new platform for the investigation of neutrinos and dark matter physics. There are various working configuration available for germanium detectors such as semi-coaxial, true coaxial and point contact. The point contact germanium detectors have been widely used for dark matter and low energy neutrino searches because of their sub KeV energy threshold and low electronic noise. Pulse shape of P-type point contact (P-PC) germanium detector has been simulated in the present work and compared to the pulse shape of Majorana Demonstrator(MJD).

physics.ins-det↗

arXiv2018

Required sensitivity to search the neutrinoless double beta decay in $^{124}Sn$

\textbf{T}he \textbf{IN}dia's \textbf{TIN} (TIN.TIN) detector is under development in the search for neutrinoless double-$\beta$ decay (0$\nu\beta\beta$) using 90\% enriched $^{124}$Sn isotope as the target mass. This detector will be housed in the upcoming underground facility of the \textbf{I}ndia based \textbf{N}eutrino \textbf{O}bservatory. We present the most important experimental parameters that would be used in the study of required sensitivity for the TIN.TIN experiment to probe the neutrino mass hierarchy. The sensitivity of the TIN.TIN detector in the presence of sole two neutrino double-$\beta$ decay (2$\nu\beta\beta$) decay background is studied at various energy resolutions. The most optimistic and pessimistic scenario to probe the neutrino mass hierarchy at 3$\sigma$ sensitivity level and 90\% C.L. is also discussed.

hep-ph↗

arXiv2010

Cloud Computing: Exploring the scope

Cloud computing refers to a paradigm shift to overall IT solutions while raising the accessibility, scalability and effectiveness through its enabling technologies. However, migrated cloud platforms and services cost benefits as well as performances are neither clear nor summarized. Globalization and the recessionary economic times have not only raised the bar of a better IT delivery models but also have given access to technology enabled services via internet. Cloud computing has vast potential in terms of lean Retail methodologies that can minimize the operational cost by using the third party based IT capabilities, as a service. It will not only increase the ROI but will also help in lowering the total cost of ownership. In this paper we have tried to compare the cloud computing cost benefits with the actual premise cost which an organization incurs normally. However, in spite of the cost benefits, many IT professional believe that the latest model i.e. "cloud computing" has risks and security concerns. This report demonstrates how to answer the following questions: (1) Idea behind cloud computing. (2) Monetary cost benefits of using cloud with respect to traditional premise computing. (3) What are the various security issues? We have tried to find out the cost benefit by comparing the Microsoft Azure cloud cost with the prevalent premise cost.

cs.DC↗