Tata Consultancy Services Limited

Ishan Sahu

Arpan Pal

Arijit Ukil

Soma Bandyopadhyay

Arijit Mukherjee

Chirabrata Bhaumik

Tanushyam Chattopadhyay

Rohan Banerjee

Snehasis Banerjee

Swarnava Dey

Chetanya Puri

Rituraj Singh

Amit Swain

Ayan Mukherjee

Utpal Garain

Jayeeta Mondal

Gitesh Kulkarni

Trisrota Deb

Aakash Tyagi

This disclosure relates generally to method and system for an adaptive filter based learning model for time series sensor signal classification on edge devices. The adaptive filter based learning model for time series sensor signal classification enables automated-computationally lightweight learning (significant reduction in computational resources) and inferring/classification in real-time or near-real-time on CPU/memory/battery life constrained edge devices. The disclosed techniques for time series sensor signal classification on edge devices characterizes the intrinsic signal processing properties of the input time series sensor signals using linear adaptive filtering and derivative spectrum to efficiently construct the adaptive filter based learning model based on standard classification algorithms for time series sensor signal classification.

Adaptive filter based learning model for time series sensor signal classification on edge devices

Small and compact Deep Learning models are required for embedded AI in several domains. In many industrial use-cases, there are requirements to transform already trained models to ensemble embedded systems or re-train those for a given deployment scenario, with limited data for transfer learning. Moreover, the hardware platforms used in embedded application include FPGAs, AI hardware accelerators, System-on-Chips and on-premises computing elements (Fog/Network Edge). These are interconnected through heterogenous bus/network with different capacities. Method of the present disclosure finds how to automatically partition a given DNN into ensemble devices, considering the effect of accuracy—latency power—tradeoff, due to intermediate compression and effect of quantization due to conversion to AI accelerator SDKs. Method of the present disclosure is an iterative approach to obtain a set of partitions by repeatedly refining the partitions and generating a cascaded model for inference and training on ensemble hardware.

Combining compression, partitioning and quantization of DL models for fitment in hardware processors

A method and system for a feature subset-classifier pair for a classification task. The classification task corresponds to automatically classifying data associated with a subject(s) or object(s) of interest into an appropriate class based on a feature subset selected among a plurality of features extracted from the data and a classifier selected from a set of classifier types. The method proposed includes simultaneously determining the feature subset-classifier pair based on a relax-greedy {feature subset, classifier} approach utilizing sub-greedy search process based on a patience function, wherein the feature subset-classifier pair provides an optimal combination for more accurate classification. The automatic joint selection is time efficient solution, effectively speeding up the classification task.

Method and system for joint selection of a feature subset-classifier pair for a classification task

Systems and methods for obtaining optimal mother wavelets for facilitating machine learning tasks. The traditional systems and methods provide for selecting a mother wavelet and signal classification using some traditional techniques and methods but none them provide for selecting an optimal mother wavelet to facilitate machine learning tasks. Embodiments of the present disclosure provide for obtaining an optimal mother wavelet to facilitate machine learning tasks by computing values of energy and entropy based upon labelled datasets and a probable set of mother wavelets, computing values of centroids and standard deviations based upon the values of energy and entropy, computing a set of distance values and normalizing the set of distance values and obtaining the optimal mother wavelet based upon the set of distance values for performing a wavelet transform and further facilitating machine learning tasks by classifying or regressing, a new set of signal classes, corresponding to a new set of signals.

Systems and methods for obtaining optimal mother wavelets for facilitating machine learning tasks

Growing community of inventors

Kolkata, India

Ishan Sahu