公开(公告)号：US20240096492A1

公开(公告)日：2024-03-21

申请号：US18367546

申请日：2023-09-13

Applicant: Tata Consultancy Services Limited

Inventor： Arijit UKIL ,  Trisrota DEB ,  Ishan SAHU ,  Sai Chander RACHA ,  Sundeep KHANDELWAL ,  Arpan PAL ,  Utpal GARAIN ,  Soumadeep SAHA

IPC: G16H50/20

CPC classification number: G16H50/20

Abstract: The present invention relates to the field of evaluating clinical diagnostic models. Conventional metrics does not consider context dependent clinical principles and is unable to capture critically important features that ought to be present in a diagnostic model. Thus, present disclosure provides a method and system for evaluating clinical efficacy of multi-label multi-class computational diagnostic models. Diagnosis for a given dataset of diagnostic samples is obtained from the diagnostic model which is then classified as wrong, missed, over or right diagnosis, based on which a first penalty is calculated. A second penalty is calculated for each diagnostic sample using a contradiction matrix. The first and second penalties are summed up to compute a pre-score for each diagnostic sample. Finally, the diagnostic model is evaluated using a metric that is based on sum of pre-scores, and scores from a perfect and a null multi-label multi-class computational diagnostic model.

公开(公告)号：US20220284293A1

公开(公告)日：2022-09-08

申请号：US17447625

申请日：2021-09-14

Applicant: Tata Consultancy Services Limited

Inventor： Swarnava DEY ,  Arpan PAL ,  Gitesh KULKARNI ,  Chirabrata BHAUMIK ,  Arijit UKIL ,  Jayeeta MONDAL ,  Ishan SAHU ,  Aakash TYAGI ,  Amit SWAIN ,  Arijit MUKHERJEE

IPC: G06N3/08 ,  G06N3/063 ,  G06F1/3206 ,  G06K9/62

Abstract: Small and compact Deep Learning models are required for embedded Al 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.

公开(公告)号：US20210326765A1

公开(公告)日：2021-10-21

申请号：US17156821

申请日：2021-01-25

Applicant: Tata Consultancy Services Limited

Inventor： Arijit UKIL ,  Arpan PAL ,  Soma BANDYOPADHYAY ,  Ishan SAHU ,  Trisrota DEB

IPC: G06N20/10 ,  G06F17/16 ,  G06K9/62

Abstract: 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.

公开(公告)号：US20200012941A1

公开(公告)日：2020-01-09

申请号：US16506828

申请日：2019-07-09

Applicant: Tata Consultancy Services Limited

Inventor： Arijit UKIL ,  Soma BANDYOPADHYAY ,  Pankaj MALHOTRA ,  Arpan PAL ,  Lovekesh VIG ,  Gautam SHROFF ,  Tulika BOSE ,  Ishan SAHU ,  Ayan MUKHERJEE

IPC: G06N3/08 ,  G06N3/04

Abstract: The disclosure herein describes a method and a system for generating hybrid learning techniques. The hybrid learning technique refers to learning techniques that are a combination a plurality of techniques that include of deep learning, machine learning and signal processing to enable a rich feature space representation and classifier construction. The generation of the hybrid learning techniques also considers influence/impact of domain constraints that include business requirements and computational constraints, while generating hybrid learning techniques. Further from the plurality hybrid learning techniques a single hybrid learning technique is chosen based on performance matrix based on optimization techniques.

公开(公告)号：US20190205778A1

公开(公告)日：2019-07-04

申请号：US16179771

申请日：2018-11-02

Applicant: Tata Consultancy Services Limited

Inventor： Ishan SAHU ,  Snehasis BANERJEE ,  Tanushyam CHATTOPADHYAY ,  Arpan PAL ,  Utpal GARAIN

IPC: G06N7/00 ,  G06N99/00 ,  G06K9/62 ,  G06F17/18

CPC classification number: G06F17/148

Abstract: 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.