Patents by Inventor Mariswamy Girish Chandra
Mariswamy Girish Chandra has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240288340Abstract: This disclosure relates generally to a field of industrial machine inspection, and, more particularly, to method and system for acoustic based industrial machine inspection using Delay-and-Sum beamforming (DAS-BF) and dictionary learning (DL). The disclosed method presents a two-stage approach for anomaly detection using a multi-channel acoustic mixed signal. In the first stage, separation of a plurality of acoustic signals corresponding to the spatially distributed acoustic sources is performed at a coarser level by using the DAS-BF. Subsequently, dictionaries pre-trained using the plurality of acoustic signals of the individual source machines are utilized for generating a plurality of separated acoustic source signals. The generated plurality of separated acoustic source signals are analyzed for the anomaly detection by comparing them with a corresponding normal machine sound template.Type: ApplicationFiled: December 29, 2023Publication date: August 29, 2024Applicant: Tata Consultancy Services LimitedInventors: Saurabh SAHU, Achanna Anil KUMAR, Mariswamy Girish CHANDRA, Kriti KUMAR, Angshul MAJUMDAR
-
Publication number: 20240151690Abstract: In industrial inspection scenarios, early detection of machine malfunction is extremely essential as it helps in preventing any significant damage and the associated economic losses. Embodiments herein provide a method and system for an acoustic based anomaly detection in industrial machines using a beamforming and a sequential transform learning. Herein, the system employs two-stage multi-channel source separation technique that uses the well-known delay and sum beamforming followed by a recent data-driven sequential transform learning (STL) approach to obtain clean sources. The STL is a solution to linear state-space model where operators/matrices are learnt from data and is used here to model the dynamics of time-varying source signals for source separation. Subsequently, a reference template matching is employed on each separated source to detect an anomaly.Type: ApplicationFiled: September 25, 2023Publication date: May 9, 2024Applicant: Tata Consultancy Services LimitedInventors: Saurabh SAHU, Mariswamy Girish CHANDRA, Kriti KUMAR, Achanna Anil KUMAR, Angshul MAJUMDAR
-
Patent number: 11961028Abstract: Energy consumption modelling requires to consider various factors affecting the energy consumption in buildings, to be able to effectively forecast future consumption. Even though some of the state of the art deep learning based approaches are able to address these requirements to some extent, they are computationally heavy. The disclosure herein generally relates to energy forecasting, and, more particularly, to a method and system for graph signal processing (GSP) based energy modelling and forecasting. The system monitors and collects information on energy consumption in a building and values of associated energy consumption parameters. This input data is further processed using GSP to generate a building energy consumption model, from which a smooth signal is obtained by applying total variation minimization. The system further performs forecasting using the smooth signal.Type: GrantFiled: January 27, 2022Date of Patent: April 16, 2024Assignee: Tata Consultancy Limited ServicesInventors: Naveen Kumar Thokala, Spoorthy Paresh, Vishnu Brindavanam, Mariswamy Girish Chandra
-
Publication number: 20240013081Abstract: Traditional approaches for recommending optimum combination of quantum circuits are experimentation based approaches, and require manual efforts or are cumbersome, effort intensive and iterative processes. Method and system disclosed herein generally relates to quantum experimentation, and, more particularly, for recommending optimum combination of quantum circuits. In this approach, a high-level combination of experiments are initially generated, which are further prioritized using a graph based approach, which then forms a training data. The training data is then used for generating a GNN data model, which is further used for recommending optimum combination of quantum circuits.Type: ApplicationFiled: July 6, 2023Publication date: January 11, 2024Applicant: Tata Consultancy Services LimitedInventors: Aniket Nandkishor KULKARNI, Sukesh Kumar Ranjan, Pathai Viswanathan Venkateswaran, Mariswamy Girish Chandra, Pranav Champaklal Shah, Sayantan Pramanik, Chundi Venkata Sridhar, Vishnu Vaidya, Vidyut Vaman Navelkar, Sudhakara Deva Poojary, Mayank Baranwal
-
Publication number: 20230401428Abstract: This disclosure relates to a method and system for multi-sensor fusion in the presence of missing and noisy labels. Prior methods for multi-sensor fusion do not estimate and correct labels for learning effective models in semi-supervised learning methods. Embodiments of the present disclosure provides a method for learning robust sensor-specific autoencoder based fusion model by utilizing a graph structure to perform label propagation and correction. In the disclosed Graph regularized AutoFuse (GAF) method latent representation for each sensor is learnt using the sensor-specific autoencoders. Further these latent representations are combined and fed to a classifier for multi-class classification. The disclosure presents a joint optimization formulation for multi-sensor fusion where label propagation and correction, sensor-specific learning and classification are executed together.Type: ApplicationFiled: June 8, 2023Publication date: December 14, 2023Applicant: Tata Consultancy Services LimitedInventors: KRITI KUMAR, SAURABH SAHU, ACHANNA ANIL KUMAR, MARISWAMY GIRISH CHANDRA, ANGSHUL MAJUMDAR
-
Publication number: 20230307907Abstract: This disclosure relates generally to methods and systems for determining the power load disaggregation profile of a building. Most of the conventional techniques are algorithmic centric, specific to certain scenarios and does not employ the low-sampling rate data due to the complexity involved. Present disclosure determines the power load disaggregation profile of the building using the low-sampling rate power consumption data accurately. According to the present disclosure, firstly, the background power loads are detected and removed from the low-sampled data samples. Next, a robust event detection mechanism is employed to detect the events when the change in the power consumption occurred, and such events are paired using the iterative pairing technique. Further, a set of event clusters are formed using the density-based clustering technique and lastly, each of the set of event clusters are classified with each appliance type using a rule-based classification technique.Type: ApplicationFiled: February 28, 2023Publication date: September 28, 2023Applicant: Tata Consultancy Services LimitedInventors: NAVEEN KUMAR THOKALA, SPOORTHY PARESH, JOSE IGNACIO MATEOS ALBIACH, ARUP KUMAR DAS, MARISWAMY GIRISH CHANDRA
-
Publication number: 20230013631Abstract: This disclosure relates generally to a method and system for multi-modal image super-resolution. Conventional methods for multi-modal image super-resolution are performed using joint image based filtering, deep learning and dictionary based approaches which require large datasets for training. Embodiments of the present disclosure provide a joint optimization based transform learning framework wherein a high-resolution (HR) image of target modality is reconstructed from a HR image of guidance modality and a low-resolution (LR) image of target modality. A set of parameters, transforms, coefficients and weight matrices are learnt jointly from a training data which includes a HR image of guidance modality, a LR image of target modality and a HR image of target modality. The learnt set of parameters are used for reconstructing a HR image of target modality. The disclosed joint optimization transform learning framework is used in remote sensing, environment monitoring and so on.Type: ApplicationFiled: May 26, 2022Publication date: January 19, 2023Applicant: Tata Consultancy Services LimitedInventors: Andrew GIGIE, Achanna Anil KUMAR, Kriti KUMAR, Mariswamy Girish CHANDRA, Angshul MAJUMDAR
-
Publication number: 20220327263Abstract: Power consumption forecasting plays a key role in the efficient operation of a building energy management system to assess energy demands of building, and at the same time, help electrical utilities in planning their supply operations. However, no state-of-the-arts are available for forecasting medium-term or long-term power consumption of the buildings. This disclosure relates to a method and system for forecasting a power consumption of buildings for a scalable forecast horizon. The system is configured to pre-process to deal with outliers/missing values, followed by synchronization of smart meter data with other sensory data. An energy-temperature correlation is calculated to estimate an energy drift using historical power consumptions. Further, in feature derivation stage, additional features necessary for the forecast are derived. The system is to be employed for modeling the building load consumption that depends on the time horizon of forecasting and the granularity of the data.Type: ApplicationFiled: March 2, 2022Publication date: October 13, 2022Applicant: Tata Consultancy Services LimitedInventors: NAVEEN KUMAR THOKALA, VISHNU BRINDAVANAM, SPOORTHY PARESH, MARISWAMY GIRISH CHANDRA
-
Patent number: 11443136Abstract: This disclosure relates generally to method for signal pre-processing based on a plurality of data driven models and a data dependent model transformation. The method includes (a) receiving, a raw signal as an input; (b) learning, a set of representational basis from the received raw signal, wherein the set of representational basis comprises a plurality of orthonormal vectors; (c) selecting, at least one orthonormal vector from the plurality of orthonormal vectors, (d) determining, a structure of the plurality of dictionary atoms, wherein structure of the plurality of dictionary atoms corresponds to a graph structure represented as a Laplacian matrix (L); (e) integrating, the graph structure as a structure of the set of representational basis to obtain a reconfigured data model; and (f) reconstructing, using the reconfigured data model to obtain a denoised signal, wherein at least one of constraints on a optimization problem corresponds to desired spectral and topological structure.Type: GrantFiled: March 19, 2020Date of Patent: September 13, 2022Assignee: TATA CONSULTANCY SERVICES LIMITEDInventors: Rahul Sinha, Mariswamy Girish Chandra
-
Publication number: 20220284237Abstract: Load disaggregation is useful for both the consumers and producers of energy. The present-day supervised learning models for load disaggregation necessitate the learning of models for every appliance load of interest, which incurs high computational costs. Embodiments of the present disclosure implement a Restricted Boltzmann Machine (RBM) based source-separation model with application to load disaggregation of appliances of interest. Representations of appliance of interest are learnt, between the power aggregate data and the appliance signatures, to output the mapping of data representations on the appliance signatures, for load disaggregation. Discriminative ability for each load/appliance of interest is achieved by adding the free energies of softmax layers of the RBM on other loads/appliance, as a discriminating gradient to the approximate gradients obtained on the load under consideration.Type: ApplicationFiled: November 2, 2021Publication date: September 8, 2022Applicant: Tata Consultancy Services LimitedInventors: Spoorthy Paresh, Naveen Thokala, Vishnu Brindavanam, Mariswamy Girish Chandra
-
Publication number: 20220269961Abstract: Quantum Information Processing (QIP) with the availability of Noisy Intermediate-Scale Quantum (NISQ) device(s) are available to work on quantum algorithms. Different problems, which are hard to solve by classical computation, but can be sped up (significantly in some cases) are also being populated. However, current approaches solve only two cluster max-cut problems. Mining the two cluster Max-Cut problem within the framework of quantum Ising model, embodiments of the present disclosure solve Quadratic Unconstrained D-ary Optimization (QUDO) problems by quantum computing with the identification of an appropriate Hamiltonian. More specifically, the problem is mapped to an Ising model to obtain a d-ray Quantum Ising Hamiltonian. The d-ray Quantum Ising Hamiltonian is then executed on one or more qudit processors, to obtain one or more resultant quantum states which are measured in a qudit computational basis to obtain at least one solution.Type: ApplicationFiled: April 2, 2021Publication date: August 25, 2022Applicant: Tata Consultancy Services LimitedInventors: Sayantan PRAMANIK, Mariswamy Girish CHANDRA
-
Publication number: 20220269940Abstract: Multi-sensor fusion is a technology which effectively utilizes the data from multiple sensors so as to portray a unified picture with improved information and offers significant advantages over existing single sensor-based techniques. This disclosure relates to a method and system for a multi-label classification using a two-stage autoencoder. Herein, the system employs autoencoder based architectures, where either raw sensor data or hand-crafted features extracted from each sensor are used to learn sensor-specific autoencoders. The corresponding latent representations from a plurality of sensors are combined to learn a fusing autoencoder. The latent representation of the fusing autoencoder is used to learn a label consistent classifier for multi-class classification. Further, a joint optimization technique is presented for learning the autoencoders and classifier weights together.Type: ApplicationFiled: February 17, 2022Publication date: August 25, 2022Applicant: Tata Consultancy Services LimitedInventors: KRITI KUMAR, MARISWAMY GIRISH CHANDRA, SAURABH SAHU, ARUP KUMAR DAS, ANGSHUL MAJUMDAR
-
Publication number: 20220237544Abstract: Energy consumption modelling requires to consider various factors affecting the energy consumption in buildings, to be able to effectively forecast future consumption. Even though some of the state of the art deep learning based approaches are able to address these requirements to some extent, they are computationally heavy. The disclosure herein generally relates to energy forecasting, and, more particularly, to a method and system for graph signal processing (GSP) based energy modelling and forecasting. The system monitors and collects information on energy consumption in a building and values of associated energy consumption parameters. This input data is further processed using GSP to generate a building energy consumption model, from which a smooth signal is obtained by applying total variation minimization. The system further performs forecasting using the smooth signal.Type: ApplicationFiled: January 27, 2022Publication date: July 28, 2022Applicant: Tata Consultancy Services LimitedInventors: NAVEEN KUMAR THOKALA, SPOORTHY PARESH, VISHNU BRINDAVANAM, MARISWAMY GIRISH CHANDRA
-
Publication number: 20220101205Abstract: This disclosure relates to multi-sensor fusion using Transform Learning (TL) that provides a compact representation of data in many scenarios as compared to Dictionary Learning (DL) and Deep network models that may be computationally intensive and complex. A two-stage approach for better modeling of sensor data is provided, wherein in the first stage, representation of the individual sensor time series is learnt using dedicated transforms and their associated coefficients and in the second stage, all the representations are fused together using a fusing (common) transform and its associated coefficients to effectively capture correlation between the different sensor representations for deriving an inference. The method and system of the present disclosure can find application in areas employing multiple sensors that are mostly heterogeneous in nature.Type: ApplicationFiled: August 20, 2021Publication date: March 31, 2022Applicant: Tata Consultancy Services LimitedInventors: Mariswamy Girish CHANDRA, Achanna Anil KUMAR, Kriti KUMAR, Angshul MAJUMDAR, Debasish MISHRA, Surjya Kanta PAL
-
Patent number: 11281980Abstract: Systems and methods for extending reasoning capability for data analytics in Internet of Things (IoT) platform(s) are provided. Traditional systems and methods for executing IoT analytics tasks suffer as IoT analytics techniques are generated in different programming language platforms, and this leads to a manual intervention or an asynchronous and sequential analysis of IoT analytics task(s). Embodiments of the method disclosed provide for overcoming the limitations faced by the traditional systems and methods by dynamically creating procedural functions from a plurality of programming languages upon determining an absence of pre-defined procedural functions, and extracting, using the dynamically created procedural functions, one or more semantic rules in a real-time, wherein the one or more semantic rules extend a reasoning capability for executing the one or more data analytics tasks in a plurality of IoT platforms.Type: GrantFiled: September 3, 2019Date of Patent: March 22, 2022Assignee: Tata Consultancy Services LimitedInventors: Snehasis Banerjee, Mariswamy Girish Chandra
-
Patent number: 11270429Abstract: The disclosure herein generally relates to image processing, and, more particularly, to a method and system for impurity detection using multi-modal image processing. This system uses a combination of polarization data, and at least one of a depth data and an RGB image data to perform the impurity material detection. The system uses a graph fusion based approach while processing the captured images to detect presence of the impurity material, and accordingly alert the user.Type: GrantFiled: June 12, 2020Date of Patent: March 8, 2022Assignee: Tata Consultancy Services LimitedInventors: Achanna Anil Kumar, Rishab Khawad, Riddhi Panse, Andrew Gigie, Tapas Chakravarty, Kriti Kumar, Saurabh Sahu, Mariswamy Girish Chandra
-
Patent number: 11119132Abstract: This disclosure relates generally to method and system for low sampling rate electrical load disaggregation. At low sampling rates, disaggregation of energy load is challenging due to unavailability of events and signatures of the constituent loads. The disclosed energy disaggregation technique receives aggregated load data from a utility meter and sequentially obtains training data for determining disaggregated energy load at low sampling rate. Dictionaries are used to characterize the different loads in terms of power values and time of operation. The obtained dictionary coefficients are treated as graph signals and graph smoothness is used for propagating the coefficients from the training phase to the test phase by formulating an optimization model. The derivation of the optimization model identifies the load of interest and estimate their power consumption based on optimization model constraints. This method achieves accuracy greater than 70% for the loads of interest at low sampling rates.Type: GrantFiled: March 10, 2020Date of Patent: September 14, 2021Assignee: Tata Consultancy Services LimitedInventors: Kriti Kumar, Mariswamy Girish Chandra, Achanna Anil Kumar, Naveen Kumar Thokala
-
Publication number: 20210019876Abstract: The disclosure herein generally relates to image processing, and, more particularly, to a method and system for impurity detection using multi-modal image processing. This system uses a combination of polarization data, and at least one of a depth data and an RGB image data to perform the impurity material detection. The system uses a graph fusion based approach while processing the captured images to detect presence of the impurity material, and accordingly alert the user.Type: ApplicationFiled: June 12, 2020Publication date: January 21, 2021Applicant: Tata Consultancy Services LimitedInventors: Achanna Anil KUMAR, Rishab KHAWAD, Riddhi PANSE, Andrew GIGIE, Tapas CHAKRAVARTY, Kriti KUMAR, Saurabh SAHU, Mariswamy Girish CHANDRA
-
Publication number: 20210011062Abstract: This disclosure relates generally to method and system for low sampling rate electrical load disaggregation. At low sampling rates, disaggregation of energy load is challenging due to unavailability of events and signatures of the constituent loads. The disclosed energy disaggregation technique receives aggregated load data from a utility meter and sequentially obtains training data for determining disaggregated energy load at low sampling rate. Dictionaries are used to characterize the different loads in terms of power values and time of operation. The obtained dictionary coefficients are treated as graph signals and graph smoothness is used for propagating the coefficients from the training phase to the test phase by formulating an optimization model. The derivation of the optimization model identifies the load of interest and estimate their power consumption based on optimization model constraints. This method achieves accuracy greater than 70% for the loads of interest at low sampling rates.Type: ApplicationFiled: March 10, 2020Publication date: January 14, 2021Applicant: Tata Consultancy Services LimitedInventors: Kriti Kumar, Mariswamy Girish CHANDRA, Achanna Anil KUMAR, Naveen Kumar THOKALA
-
Publication number: 20200302228Abstract: This disclosure relates generally to method for signal pre-processing based on a plurality of data driven models and a data dependent model transformation. The method includes (a) receiving, a raw signal as an input; (b) learning, a set of representational basis from the received raw signal, wherein the set of representational basis comprises a plurality of orthonormal vectors; (c) selecting, at least one orthonormal vector from the plurality of orthonormal vectors, (d) determining, a structure of the plurality of dictionary atoms, wherein structure of the plurality of dictionary atoms corresponds to a graph structure represented as a Laplacian matrix (L); (e) integrating, the graph structure as a structure of the set of representational basis to obtain a reconfigured data model; and (f) reconstructing, using the reconfigured data model to obtain a denoised signal, wherein at least one of constraints on a optimization problem corresponds to desired spectral and topological structure.Type: ApplicationFiled: March 19, 2020Publication date: September 24, 2020Applicant: Tata Consultancy Services LimitedInventors: Rahul SINHA, Mariswamy Girish CHANDRA