Gaurav Arora, Srujana Merugu, Shreya Jain, Vaibhav Saxena. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti, Gaurav Arora, Srujana Merugu. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The availability of well-curated datasets has driven the success of Machine Learning (ML) models. Despite greater access to earth observation data in agriculture, there is a scarcity of curated and labelled datasets, which limits the potential of its use in training ML models for remote sensing (RS) in agriculture. To this end, we introduce a first-of-its-kind dataset called SICKLE, which constitutes a time-series of multi-resolution imagery from 3 distinct satellites: Landsat-8, Sentinel-1 and Sentinel-2. Our dataset constitutes multi-spectral, thermal and microwave sensors during January 2018 - March 2021 period. We construct each temporal sequence by considering the cropping practices followed by farmers primarily engaged in paddy cultivation in the Cauvery Delta region of Tamil Nadu, India; and annotate the corresponding imagery with key cropping parameters at multiple resolutions (i.e. 3m, 10m and 30m). Our dataset comprises 2, 370 season-wise samples from 388 unique plots, having an average size of 0.38 acres, for classifying 21 crop types across 4 districts in the Delta, which amounts to approximately 209,000 satellite images. Out of the 2,370 samples, 351 paddy samples from 145 plots are annotated with multiple crop parameters; such as the variety of paddy, its growing season and productivity in terms of per-acre yields. Ours is also one among the first studies that consider the growing season activities pertinent to crop phenology (spans sowing, transplanting and harvesting dates) as parameters of interest. We benchmark SICKLE on three tasks: crop type, crop phenology (sowing, transplanting, harvesting), and yield prediction.

Remote sensing through satellite imagery is applied widely for environmental control, urban planning and land cover classification. To this end, supervised deep learning models can fully exploit the potential of satellite images. However, such models require large annotated datasets. Therefore, through this study we present two novel labelled satellite image datasets, namely In-Sat1, based on Sentinel-2 Satellite Imagery and Google Earth Imagery covering Indian subcontinent regions. We provide benchmarks and detailed analysis for these datasets using state-of-the-art and our improved remote sensing deep learning models which achieve 91% and 81% overall accuracy in region-wise split setting and 98% and 94% overall accuracy in class-wise split setting for Sentinel-2 data and Google Earth data respectively. We also demonstrate the application of our system for change detection.

Awareness information in shared-workspace groupware is often ephemeral, and when users are interrupted or look away from the system, they can miss important information about others' activities. These attentional disconnections are brief (generally less than ten seconds), are frequent in many work environments, and can occur for many reasons. In this paper, we provide visualization techniques that can help groupware users recover from these short absences. First, we provide a simple attention monitor that informs groupware systems whether a user is looking at the screen and whether the workspace is visible. Second, we provide a framework of catch-up techniques for visualizing missed activity -- including highlighting, motion traces, and replay. We implemented these techniques in three applications that cover different communication methods and interaction speeds, and explored the use of the effects in three studies. Participants clearly saw the value of catch-up techniques, and although different techniques were preferred in different situations, nearly all users strongly preferred the catch-up techniques. Our work shows that helping users deal with periods of attentional disconnection can substantially improve the usability of real-time groupware systems.

This paper describes a computer-aided software engineering (CASE) tool that helps designers analyze and fine-tune the timing properties of their embedded real-time software. Existing CASE tools focus on the software specification and design of embedded systems. However, they provide little, if any, support after the software has been implemented. Even if the developer used a CASE tool to design the system, their system most likely does not meet the specifications on the first try. This paper includes guidelines for implementing analyzable code, profiling a real-time system, filtering and extracting measured data, analyzing the data, and interactively predicting the effect of changes to the real-time system. The tool is a necessary first step towards automating the debugging and fine tuning of an embedded system's temporal properties.

A dynamically reconfigurable real-time software (DRRTS) paradigm can be used effectively in the design of embedded systems to provide many major advantages over conventional software development techniques. The benefits include rapid development which reduces development time and cost, ability to easily upgrade and maintain embedded software, and both analytic and practical tools for automated analysis and systematic fine tuning of the embedded system. Our current research is founded upon the Chimera Methodology, which demonstrated the feasibility of using dynamically reconfigurable software to control robots. However, there are still many design challenges in order to use it in an embedded system, which has less flexibility, severe limits on memory and CPU bandwidth, and more rigid timing constraints and reliability specifications. We have several ongoing projects which address some of the issues, in a strive towards the overall objective of creating a software infrastructure for developing dynamically reconfigurable embedded software.