ANAkshay Nambi

Akshay Nambi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Akshay Nambi has a total of 49 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    eARCO: Efficient Automated Root Cause Analysis with Prompt Optimization

    by Drishti Goel, Raghav Magazine, Supriyo Ghosh, Akshay Nambi, Prathamesh Deshpande, Xuchao Zhang, Chetan Bansal, Saravan Rajmohan

    Root cause analysis (RCA) for incidents in large-scale cloud systems is a complex, knowledge-intensive task that often requires significant manual effort from on-call engineers (OCEs). Improving RCA is vital for accelerating the incident resolution process and reducing service downtime and manual efforts. Recent advancements in Large-Language Models (LLMs) have proven to be effective in solving different stages of the incident management lifecycle including RCA. However, existing LLM-based RCA recommendations typically leverage default finetuning or retrieval augmented generation (RAG) methods with static, manually designed prompts, which lead to sub-optimal recommendations. In this work, we leverage 'PromptWizard', a state-of-the-art prompt optimization technique, to automatically identify the best optimized prompt instruction that is combined with semantically similar historical examples for querying underlying LLMs during inference. Moreover, by utilizing more than 180K historical incident data from Microsoft, we developed cost-effective finetuned small language models (SLMs) for RCA recommendation generation and demonstrate the power of prompt optimization on such domain-adapted models. Our extensive experimental results show that prompt optimization can improve the accuracy of RCA recommendations by 21% and 13% on 3K test incidents over RAG-based LLMs and finetuned SLMs, respectively. Lastly, our human evaluation with incident owners have demonstrated the efficacy of prompt optimization on RCA recommendation tasks. These findings underscore the advantages of incorporating prompt optimization into AI for Operations (AIOps) systems, delivering substantial gains without increasing computational overhead.

  • Open Access

    Shiksha Copilot: Teacher-AI Collaboration for Curating and Customizing Lesson Plans in Low-Resource Schools CSCW038

    by Deepak Varuvel Dennison, Bakhtawar Ahtisham, Kavyansh Chourasia, Nirmit Arora, Rahul Singh, René F. Kizilcec, Akshay Nambi, Tanuja Ganu, Aditya Vashistha

    This study investigates Shiksha Copilot, an AI-assisted lesson planning tool deployed in government schools across Karnataka, India. The system combined LLMs and human expertise through a structured process in which English and Kannada lesson plans were co-created by curators and AI; teachers then further customized these curated plans for their classrooms using their own expertise alongside AI support. Drawing on a large-scale mixed-methods study involving 1,043 teachers and 23 curators, we examine how educators collaborate with AI to generate context-sensitive lesson plans, assess the quality of AI-generated content, and analyze shifts in teaching practices within multilingual, low-resource environments. Our findings show that teachers used Shiksha Copilot both to meet administrative documentation needs and to support their teaching. The tool eased bureaucratic workload, reduced lesson planning time, and lowered teaching-related stress, while promoting a shift toward activity-based pedagogy. However, systemic challenges such as staffing shortages and administrative demands constrained broader pedagogical change. We frame these findings through the lenses of teacher-AI collaboration and communities of practice to examine the effective integration of AI tools in teaching. Finally, we propose design directions for future teacher-centered EdTech, particularly in multilingual and Global South contexts.


  • Open Access

    Physics-Based Fault Analysis for Commodity PIR Sensors*

    by Ashish Kashinath, Sibin Mohan, Akshay Nambi, Sumukh Marathe

    Passive Infra-Red (PIR) sensors are ubiquitous and have applications ranging from automatic lighting and heating control in smart buildings, towel dispensers in washrooms, security alarms (for intrusion detection) to human detection robots (for search and rescue). Unfortunately, PIR sensors are prone to failures during deployment due to reasons such as environmental damage, incorrect installation and component degradation among others that can lead to incorrect or faulty data. Currently, such failures are typically detected using either : (a) heavily engineered data-driven, statistical approaches that can have high false positive rates due to unseen data patterns or (b) expensive, unscalable methods that use additional hardware such as video cameras or a golden reference sensor. In this work, we first create a taxonomy for the most common PIR sensor failures and analyze these failures from the perspective of sensor physics. We then present PIRMedic— a physics-driven, edge-based approach to detect and diagnose the failures in a PIR sensor using an intrinsic hardware signal viz., the analog output from the pyroelectric element in the sensor. Using this hardware signal in conjunction with frequency analysis and supervised machine learning methods, we obtain a high accuracy of 98-99% in failure detection and diagnosis. We evaluate our methods using multiple real-world deployments , in four distinct locations, in different environment and usage conditions.

  • Open Access

    TorchSpatial: A Python Package for Spatial Representation Learning and Geo-Aware Model Development

    by Qian Cao, Nemin Wu, Zhangyu Wang, Zeping Liu, Yanlin Qi, Jielu Zhang, Joshua Ni, Xiaobai Yao, Hongxu Ma, Lan Mu, et al.

    Spatial representation learning (SRL) focuses on developing spatial embeddings from various forms of spatial data, such as points, polylines, polygons, graphs, networks, and images without any additional feature engineering or data conversion step. Effective spatial representation is fundamental for a wide range of downstream geospatial applications, including species distribution modeling, satellite image classification, point cloud classification and segementation, trajectory synthesis, building footprint extraction, and cartographic generalization. Despite the widespread use of SRL as a cornerstone for many spatially-aware AI models, there is still no comprehensive package shared across the community that provides ready-made code to support the implementation and reproduction of SRL model development. To fill this void, we present TorchSpatial, a Python package designed to support the encoding of spatial data, starting with location (point) encoding, a fundamental data type in SRL. TorchSpatial includes two key components: 1) We present TorchSpatial, an SRL framework supporting the development of location encoders. TorchSpatial now integrates 15 widely-used encoders and essential encoder components, ensuring scalability and reproducibility for future developments; 2) We establish a ready-to-use workflow that takes the input hyperparameters and outputs the model inference results and evaluation across geo-aware image classification and regression tasks with access to 17 datasets. We believe TorchSpatial will foster future advancement of SRL and spatial fairness in GeoAI research. The TorchSpatial SRL framework and inference models are available at https://github.com/seai-lab/TorchSpatial.


  • Open Access

    PressureML: Modelling Pressure Waves to Generate Large-Scale Water-Usage Insights in Buildings

    by Tanmaey Gupta, Anupam Sobti, Akshay Nambi

    Several studies have indicated that delivering insights and feedback on water usage has been effective in curbing water consumption, making it a pivotal component in achieving long-term sustainability objectives. Despite a significant proportion of water consumption originating from large residential and commercial buildings, there is a scarcity of cost-effective and easy-to-integrate solutions that provide water usage insights at a reasonable spatio-temporal granularity in such structures. Furthermore, existing methods for disaggregating water usage necessitate training data and rely on frequent data sampling to capture patterns, both of which pose challenges when scaling up and adapting to new environments. In this work, we aim to solve these challenges through a novel end-to-end approach which records data from pressure sensors and uses time-series classification by DNN models to determine room-wise water consumption in a building. This consumption data is then fed to a novel water disaggregation algorithm which can suggest a set of water-usage events, and has a flexible requirement of training data and sampling granularity. We conduct experiments using our approach and demonstrate its potential as a promising avenue for in-depth exploration, offering valuable insights into water usage on a large scale.

  • Open Access

    Verified Telemetry: A General, Easy to use, Scalable and Robust Fault Detection SDK for IoT Sensors

    by Tanmaey Gupta, Shubhankar Handa, Akshay Nambi

    With the proliferation of IoT sensors, the reliance on sensor telemetry has never been greater. Today numerous applications from smart agriculture to smart buildings and cities, rely on IoT telemetry to provide insights and to take decisions. However, due to the characteristics of these IoT deployments (in the wild, harsh conditions), sensors are prone to failures, leading to the generation of bad/dirty data. Hitherto, data-centric algorithms were used to determine the quality of the sensed data, which has several limitations and relies on additional contextual information or sensor redundancy. Recently, system-centric approaches based on sensor fingerprinting has shown to detect sensor faults reliably without any additional information. However, the sensor fingerprinting approach is validated only for specific sensors, is not robust to real-world conditions, and cannot scale to large-scale deployments. To this end, we propose a general, easy-to-use, scalable, and robust fault detection SDK called Verified Telemetry (VT) SDK. VT SDK builds on the sensor fingerprinting approach and can work with a wide variety of sensors (both analog and digital) and IoT devices with very minimal changes. We propose improved sensor fingerprinting algorithms that are robust to signal variations, sensor circuitry, and real-world conditions. VT SDK is implemented across numerous devices and we show its usage on several practical applications. Finally, VT SDK is made available for the community to address sensor fault detection in IoT deployments (https://aka.ms/verifiedtelemetry).


  • Open Access

    Driving Lane Detection on Smartphones using Deep Neural Networks

    by Ravi Bhandari, Akshay Uttama Nambi, Venkata N. Padmanabhan, Bhaskaran Raman

    Current smartphone-based navigation applications fail to provide lane-level information due to poor GPS accuracy. Detecting and tracking a vehicle’s lane position on the road assists in lane-level navigation. For instance, it would be important to know whether a vehicle is in the correct lane for safely making a turn, or whether the vehicle’s speed is compliant with a lane-specific speed limit. Recent efforts have used road network information and inertial sensors to estimate lane position. While inertial sensors can detect lane shifts over short windows, it would suffer from error accumulation over time. In this article, we present DeepLane, a system that leverages the back camera of a windshield-mounted smartphone to provide an accurate estimate of the vehicle’s current lane. We employ a deep learning--based technique to classify the vehicle’s lane position. DeepLane does not depend on any infrastructure support such as lane markings and works even when there are no lane markings, a characteristic of many roads in developing regions. We perform extensive evaluation of DeepLane on real-world datasets collected in developed and developing regions. DeepLane can detect a vehicle’s lane position with an accuracy of over 90%, and we have implemented DeepLane as an Android app.


  • Evaluation and Visualization of Driver Inattention Rating From Facial Features

    by Isha Dua, Akshay Uttama Nambi, C. V. Jawahar, Venkata N. Padmanabhan

    In this paper, we present AutoRate, a system that leverages the front camera of a windshield-mounted smartphone to monitor driver’s attention by combining several features. We derive a driver attention rating by fusing spatio-temporal features based on the driver state and behavior such as head pose, eye gaze, eye closure, yawns, use of cellphones, etc. We perform extensive evaluation of AutoRate on real-world driving data and also data from controlled, static vehicle settings with 30 drivers in a large city. We compare AutoRate’s automatically-generated rating with the scores given by 5 human annotators. We compute the agreement between AutoRate’s rating and human annotator rating using kappa coefficient. AutoRate’s automatically-generated rating has an overall agreement of 0.88 with the ratings provided by 5 human annotators. We also propose soft attention mechanism in AutoRate which improves AutoRate’s accuracy by 10%. We use temporal and spatial attention to visualize the key frame and the key action which justify the model’s predicted rating. Further, we observe that personalization in AutoRate can improve driver specific results by a significant amount.


  • Open Access

    Smartphone-based driver license testing

    by Anurag Ghosh, Vijay Lingam, Ishit Mehta, Akshay Uttama Nambi, Venkata N. Padmanabhan, Satish Sangameswaran

  • Open Access

    Sensor Identification and Fault Detection in IoT Systems

    by Tusher Chakraborty, Akshay Uttama Nambi, Ranveer Chandra, Rahul Sharma, Manohar Swaminathan, Zerina Kapetanovic