arXiv subjects

Anshika Singh

Publications and source records attributed to Anshika Singh.

4 recordsLinked to original sources

arXiv2026

Accelerating Update Broadcasts Over LoRaWAN Downlink via D2D Cooperation

Broadcast distribution of updates (e.g., security patches, machine learning models) from a server to end devices (EDs) is a critical requirement in the Internet of Things (IoT). In this paper, we consider the problem of reliable over-the-air broadcast of updates in Long Range Wide Area Networks (LoRaWANs). Existing broadcast techniques for LoRaWANs suffer from long delivery delays due to low data rates and duty-cycle constraints. We address this problem by proposing a device-level cooperative mechanism, in which updated EDs broadcast a few update fragments to accelerate delivery to their neighbors. We demonstrate large reductions in the delivery time compared to conventional methods. For instance, in a 400-node network spanning 1 km radius and operating at 1% duty-cycle, the proposed scheme reduces the time required to deliver a 10 kilobyte update to an ED at the network's edge from 42 hours to 45 minutes. The proposed solution thus provides a pathway toward improved security and efficient realization of edge intelligence in LoRaWAN IoT.

cs.NI↗

arXiv2025

Federated Learning Over LoRa Networks: Simulator Design and Performance Evaluation

Federated learning (FL) over long-range (LoRa) low-power wide area networks faces unique challenges due to limited bandwidth, interference, and strict duty-cycle constraints. We develop a Python-based simulator that integrates and extends the Flower and LoRaSim frameworks to evaluate centralized FL over LoRa networks. The simulator employs a detailed link-level model for FL update transfer over LoRa channels, capturing LoRa's receiver sensitivity, interference characteristics, block-fading effects, and constraints on the maximum transmission unit. It supports update sparsification, quantization, compression, forward frame-erasure correction (FEC), and duty cycling. Numerical results illustrate the impact of transmission parameters (spreading factor, FEC rate) and interference on FL performance. Demonstrating the critical role of FEC in enabling FL over LoRa networks, we perform an in-depth evaluation of the impact of FEC on FL convergence and device airtime, providing insights for communication protocol design for FL over LoRa networks.

cs.NI↗

arXiv2025

Enhancing Customer Service Chatbots with Context-Aware NLU through Selective Attention and Multi-task Learning

Customer service chatbots are conversational systems aimed at addressing customer queries, often by directing them to automated workflows. A crucial aspect of this process is the classification of the customer's intent. Presently, most intent classification models for customer care utilise only customer query for intent prediction. This may result in low-accuracy models, which cannot handle ambiguous queries. An ambiguous query like "I didn't receive my package" could indicate a delayed order, or an order that was delivered but the customer failed to receive it. Resolution of each of these scenarios requires the execution of very different sequence of steps. Utilizing additional information, such as the customer's order delivery status, in the right manner can help identify the intent for such ambiguous queries. In this paper, we have introduced a context-aware NLU model that incorporates both, the customer query and contextual information from the customer's order status for predicting customer intent. A novel selective attention module is used to extract relevant context features. We have also proposed a multi-task learning paradigm for the effective utilization of different label types available in our training data. Our suggested method, Multi-Task Learning Contextual NLU with Selective Attention Weighted Context (MTL-CNLU-SAWC), yields a 4.8% increase in top 2 accuracy score over the baseline model which only uses user queries, and a 3.5% improvement over existing state-of-the-art models that combine query and context. We have deployed our model to production for Walmart's customer care domain. Accurate intent prediction through MTL-CNLU-SAWC helps to better direct customers to automated workflows, thereby significantly reducing escalations to human agents, leading to almost a million dollars in yearly savings for the company.

cs.LG↗

arXiv2024

Alfvén Pulse Driven Spicule-like Jets in the Presence of Thermal Conduction and Ion-Neutral Collision in Two-Fluid Regime

We present the formation of quasi-periodic cool spicule-like jets in the solar atmosphere using 2.5-D numerical simulation in two-fluid regime (ions+neutrals) under the presence of thermal conduction and ion-neutral collision. The non-linear, impulsive Alfvénic perturbations at the top of the photosphere trigger field aligned magnetoacoustic perturbations due to ponderomotive force. The transport of energy from Alfvén pulse to such vertical velocity perturbations due to ponderomotive force is considered as an initial trigger mechanism. Thereafter, these velocity perturbations steepen into the shocks followed by quasi-periodic rise and fall of the cool jets transporting mass in the overlying corona.

astro-ph.SR↗