Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Towards a Task-agnostic Distillation Methodology for Creating Edge Foundation Models
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 10–15https://doi.org/10.1145/3662006.3662061In recent years, AI has undergone significant changes. Firstly, there is a growing recognition of the need to deploy inference models based on Deep Neural Networks (DNNs) on edge devices. Secondly, there is an increasing demand for low-energy inferencing ...
- ArticleDecember 2023
Spatiotemporal Co-occurrence Index Using Spatiotemporal Variability Signals
Pattern Recognition and Machine IntelligenceDec 2023, Pages 699–707https://doi.org/10.1007/978-3-031-45170-6_73AbstractSpatiotemporal climatic variables like temperature, precipitation, humidity vary in a co-occurring fashion across different geographical zones. It is intuitive to believe that the co-occurrence is higher for signals sampled from nearby locations ...
- short-paperApril 2024
Demo Abstract: Lightweight Attention Network for Time Series Classification on Edge
SenSys '23: Proceedings of the 21st ACM Conference on Embedded Networked Sensor SystemsNovember 2023, Pages 484–485https://doi.org/10.1145/3625687.3628393In this work, we present a lightweight attention network to perform Time Series Classification on Edge devices. We evaluate the merit of our system on a Human Activity Recognition dataset and show the demonstration with the help of a Wearable device (...
- demonstrationMay 2024
Supervised Vision-based Anomaly Detection
AIMLSystems '23: Proceedings of the Third International Conference on AI-ML SystemsOctober 2023, Article No.: 61, Pages 1–3https://doi.org/10.1145/3639856.3639920In the following paper associated with a demonstration, we describe an in- house designed, developed and deployed versatile anomaly detection model called SCNet. The model is based on state-of-the-art deep learning techniques, and is targeted for ...
- research-articleMay 2024
Physics Guided Generative Learning for Domain Adaptable Data Synthesis : Progressive Fault Synthesization for Predictive Machine Maintenance
AIMLSystems '23: Proceedings of the Third International Conference on AI-ML SystemsOctober 2023, Article No.: 29, Pages 1–7https://doi.org/10.1145/3639856.3639885In this work, we perform Physics guided data synthesis. Proposed method uses seed data from the observed source state / domain for data generation of unobserved target state / domain. Our method adapts the variation of features with respect to the ...
-
- research-articleOctober 2023
GSR Based Generic Stress Prediction System
UbiComp/ISWC '23 Adjunct: Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable ComputingOctober 2023, Pages 433–438https://doi.org/10.1145/3594739.3610734Stress detection is important for ensuring overall mental well-being of an individual. Literature suggests several approaches for prediction or classification of stress. However, the performance of these approaches varies a lot across subjects and ...
- research-articleJuly 2023
A critical review on applications of artificial intelligence in manufacturing
Artificial Intelligence Review (ARTR), Volume 56, Issue Suppl 1Oct 2023, Pages 661–768https://doi.org/10.1007/s10462-023-10535-yAbstractThe fourth industrial revolution, Industry 4.0, has brought internet, artificial intelligence (AI), and machine learning (ML) concepts into manufacturing. There is an immediate need to understand the capabilities of AI and ML and how they can be ...
- research-articleJune 2023
Assessment of Mental Workloads using Differential Dermal Potentials Recorded from in and around Ear
- Dibyanshu Jaiswal,
- Debatri Chatterjee,
- Arindam Sarkar,
- Meghana S,
- Ramesh Kumar Ramakrishnan,
- Arpan Pal,
- Ratna Ghosh
BodySys '23: Proceedings of the 8th Workshop on Body-Centric Computing SystemsJune 2023, Pages 1–6https://doi.org/10.1145/3597061.3597257Differential dermal potentials is a non-invasive bio-potential signal acquired from the skin surface is a relatively new mode for human activity and behavior monitoring. Literature suggests acquiring differential dermal potentials from either hand or ...
- research-articleMay 2023
A Few-shot approach to MRI-based Knee Disorder Diagnosis using Fuzzy Layers
- Mohana Singh,
- K Ram Prabhakar,
- Viswanath Pamulakanty Sudarshan,
- Murali Poduval,
- Arpan Pal,
- Jayavardhana Gubbi
ICVGIP '22: Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image ProcessingDecember 2022, Article No.: 52, Pages 1–9https://doi.org/10.1145/3571600.3571654Magnetic Resonance Imaging (MRI) has a long-standing acceptance as the de facto technology for obtaining high-resolution three-dimensional images of soft tissue pathologies of the knee. However, the volume and amount of information in MRI sequences ...
- research-articleJanuary 2023
Intelligent Continuous Monitoring to Handle Data Distributional Changes for IoT Systems
SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor SystemsNovember 2022, Pages 1189–1195https://doi.org/10.1145/3560905.3568438Intelligent continuous monitoring of an IoT system to identify the operational changes, encompassing both normal and abnormal scenarios, with drift in sensing device is a challenging problem. It demands capability of learning continuously with multiple ...
- research-articleJanuary 2023
CycleGAN Based Unsupervised Domain Adaptation for Machine Fault Diagnosis
- Naibedya Pattnaik,
- Uday Sai Vemula,
- Kriti Kumar,
- A. Anil Kumar,
- Angshul Majumdar,
- M. Girish Chandra,
- Arpan Pal
SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor SystemsNovember 2022, Pages 973–979https://doi.org/10.1145/3560905.3568303Fault diagnosis plays a vital role in ensuring the normal operation of the machine and safe production. In recent years, data-driven techniques have gained a lot of popularity for machine fault diagnosis. But most of these techniques assume the training ...
- research-articleMay 2023
Acceleration-aware, Retraining-free Evolutionary Pruning for Automated Fitment of Deep Learning Models on Edge Devices
AIMLSystems '22: Proceedings of the Second International Conference on AI-ML SystemsOctober 2022, Article No.: 10, Pages 1–10https://doi.org/10.1145/3564121.3564133Deep Learning architectures used in computer vision, natural language and speech processing, unsupervised clustering, etc. have become highly complex and application-specific in recent times. Despite existing automated feature engineering techniques, ...
- ArticleSeptember 2022
Uncertainty-Informed Bayesian PET Image Reconstruction Using a Deep Image Prior
Machine Learning for Medical Image ReconstructionSep 2022, Pages 145–155https://doi.org/10.1007/978-3-031-17247-2_15AbstractModel-based image reconstruction (MBIR) methods using convolutional neural networks (CNNs) as priors have demonstrated superior image quality and robustness compared to conventional methods. Studies have explored MBIR combined with supervised and ...
- research-articleApril 2023
Designing and evaluating a system for studying EarEEG signals
UbiComp/ISWC '22 Adjunct: Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable ComputersSeptember 2022, Pages 225–228https://doi.org/10.1145/3544793.3563417Electroencephalography (EEG) allows the study of the brain in humans with applications in areas of Psychology, Brain-Computer Interfaces, and Neuromarketing. The conventional systems limit the applications of EEG to lab environments, but recent ...
- ArticleJuly 2024
Spatial-SMOTE: An Approach for Handling Class Imbalance in Spatial Time Series Data
Pattern Recognition and Machine IntelligenceDec 2021, Pages 488–497https://doi.org/10.1007/978-3-031-12700-7_50AbstractData imbalance handling is important to have unbiased learning during model training of classification tasks. Synthetic minority over-sampling technique (SMOTE) is primarily used for data imbalance handling. Conventional SMOTE algorithm and its ...
- research-articleJune 2021
I know it's still you: A study of using the PPG sensor to support zero re-authentications
- Tanushree Banerjee,
- Kartik Muralidharan,
- Dibyanshu Jaiswal,
- Mithun Basaralu Sheshachala,
- Ramesh Kumar Ramakrishnan,
- Arpan Pal
BodySys'21: Proceedings of the Workshop on Body-Centric Computing SystemsJune 2021, Pages 24–29https://doi.org/10.1145/3469260.3469669The Photoplethysmogram (PPG) sensor is found in most smart wearables and fitness trackers to support the physical wellness monitoring of it's user. The popularity of this sensor has encouraged the exploration of it's use in other domains particularly in ...
- research-articleJune 2021
Heart Rate Monitoring Using Capacitive Touchscreen Sensing
BodySys'21: Proceedings of the Workshop on Body-Centric Computing SystemsJune 2021, Pages 13–17https://doi.org/10.1145/3469260.3469667According to World Health Organization (WHO) cardiovascular diseases (CVDs) are the number one cause of global deaths annually. More than 17 million people die each year from CVDs. To diagnose CVDs some clinical tests are required which are invasive and ...
- research-articleJune 2021
Effective Assessment of Cognitive Load in Real-World Scenarios using Wrist-worn Sensor Data
BodySys'21: Proceedings of the Workshop on Body-Centric Computing SystemsJune 2021, Pages 7–12https://doi.org/10.1145/3469260.3469666The ability to assess cognitive load of an user in real time, is an integral part of effective human-computer interactions. Several approaches are used in literature for assessing cognitive load of an user in labs, however, assessment in real world ...
- research-articleFebruary 2021
A self-adaptive network for multi-robot warehouse communication
Computing (CMPT), Volume 103, Issue 2Feb 2021, Pages 333–356https://doi.org/10.1007/s00607-020-00852-3AbstractWith the growing popularity of e-commerce, warehouse communication needs to operate in a dynamic environment with multiple robots in the system. Such multi-robot systems have many practical issues in reality. Among the major issues, end-to-end ...
- research-articleSeptember 2020
Action recognition using spatially distributed radar setup through microdoppler signature
UbiComp/ISWC '20 Adjunct: Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable ComputersSeptember 2020, Pages 278–253https://doi.org/10.1145/3410530.3414362Small form factor off-the shelf radar sensor nodes are being investigated for various privacy preserving non-contact sensing applications. This paper, presents a novel method, based on a system of spatially distributed radar setup(panel radar), for real ...