Patents by Inventor Snehasis Banerjee
Snehasis Banerjee 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: 20190138806Abstract: Development of sensor data based descriptive and prescriptive system involves machine learning tasks like classification and regression. Any such system development requires the involvement of different stake-holders for obtaining features. Such features typically obtained are not interpretable for 1-D sensor signals. Embodiments of the present disclosure provide systems and methods that perform signal analysis for features extraction and interpretation thereof wherein input is raw signal data where origin of a feature is traced to signal data, and mapped to domain/application knowledge. Feature(s) are extracted using deep learning network(s) and machine learning (ML) model(s) are implemented for sensor data analysis to perform causality analysis for prognostics. Layer(s) (say last layer) of Deep Network(s) contains the automatically derived features that can be used for ML tasks.Type: ApplicationFiled: February 21, 2018Publication date: May 9, 2019Applicant: Tata Consultancy Services LimitedInventors: Snehasis BANERJEE, Tanushyam CHATTOPADHYAY, Ayan MUKHERJEE
-
Patent number: 10277682Abstract: A method and system has been provided for recommending features for developing an IoT analytics application. The method follows a deep like architecture. It comprises of three distinct layers. First layer is for input signal processing and other two layers are for feature reduction. The time domain, frequency domain and time-frequency domain features are extracted from the input signal. The invention uses multiple feature selection methods so that the union of the recommended features by these feature selection methods is significantly lesser than the initial set of features. The best feature combination is recommended using an exhaustive search.Type: GrantFiled: November 20, 2017Date of Patent: April 30, 2019Assignee: Tata Consultancy Services LimitedInventors: Swagata Biswas, Tanushyam Chattopadhyay, Arpan Pal, Snehasis Banerjee, Utpal Garin
-
Publication number: 20190026551Abstract: Signal analysis is applied in various industries and medical field. In signal analysis, wavelet analysis plays an important role. The wavelet analysis needs to identify a mother wavelet associated with an input signal. However, identifying the mother wavelet associated with the input signal in an automatic way is challenging. Systems and methods of the present disclosure provides signal analysis with automatic selection of wavelets associated with the input signal. The method provided in the present disclosure receives the input signal and a set of parameters associated with the signal. Further, the input signal is analyzed converted into waveform. The waveforms are analyzed to provide image units. Further, the image units are processed by a plurality of deep architectures. The deep architectures provides a set of comparison scores and a matching wavelet family is determined by utilizing the set of comparison scores.Type: ApplicationFiled: February 22, 2018Publication date: January 24, 2019Applicant: Tata Consultancy Services LimitedInventors: Snehasis BANERJEE, Swarnava DEY, Arijit MUKHERJEE, Swagata BISWAS
-
Patent number: 10074052Abstract: Disclosed is a method and system for dynamically generating a customized, personalized and contextual alert for a user based upon personalized, contextual and background knowledge associated with the profile of the user. The system comprises a profile updater module configured to update the profile data of the user extracted either from the social web or from the user. Further, a reasoning module is configured to derive refined background knowledge in context with the updated profile data of the user. A monitoring module is configured to monitor the events sensed by a sensing module. A context extractor module is configured for extracting the context of the events and the context of the user. A knowledge converter module is configured to convert the extracted context into structured format. Finally, the refined background knowledge is steam reasoned to determine whether the events received are relevant to the user and accordingly transmitted.Type: GrantFiled: December 5, 2013Date of Patent: September 11, 2018Assignee: TATA CONSULTANCY SERVICES LIMITEDInventors: Snehasis Banerjee, Debnath Mukherjee, Prateep Misra
-
Patent number: 9990403Abstract: Disclosed is a method and a system for stream reasoning a plurality of data streams. The system comprises a processor and a memory coupled to the processor. The processor is capable of executing a plurality of modules embodied on the memory. The plurality of modules comprises an event module and a application managed window module. The event module is configured to receive a data stream associated with an event from a stream reasoner application. The data stream provides factual information about the event. Further, the data stream comprises a request. The request may be an add request or a delete request. The application managed window module is configured to insert the request associated with the event or delete a prior request associated with the event from the memory based upon a type of the request.Type: GrantFiled: April 12, 2013Date of Patent: June 5, 2018Assignee: Tata Consultancy Services LimitedInventors: Debnath Mukherjee, Prateep Misra, Snehasis Banerjee
-
Publication number: 20180146047Abstract: A method and system has been provided for recommending features for developing an IoT analytics application. The method follows a deep like architecture. It comprises of three distinct layers. First layer is for input signal processing and other two layers are for feature reduction. The time domain, frequency domain and time-frequency domain features are extracted from the input signal. The invention uses multiple feature selection methods so that the union of the recommended features by these feature selection methods is significantly lesser than the initial set of features. The best feature combination is recommended using an exhaustive search.Type: ApplicationFiled: November 20, 2017Publication date: May 24, 2018Applicant: Tata Consultancy Services LimitedInventors: Swagata BISWAS, Tanushyam CHATTOPADHYAY, Arpan Pal, Snehasis Banerjee, Utpal GARIN
-
Patent number: 9898502Abstract: The present disclosure provides system and method for executing SPARQL query on a SPARQL engine. For executing the SPARQL query, a function may be instantly integrated with the SPARQL query which leads to extension of the SPARQL query. The extension may be achieved through a user friendly interface which may allow transparent integration of code (i.e., the function) in any language such as JAVA, C, C++ and the like, supporting a particular functionality. The system may integrate the code by addition of newly added code to the SPARQL library after validation. Further, the system may analyze the functionality associated with the code to optimize decision making of a user. The system may further support auto compilation and rating of the functions based on the user feedback and re-usability of the code working in a collaborative environment. Further the system may enable also enable to integrate external tools and web services.Type: GrantFiled: July 7, 2015Date of Patent: February 20, 2018Assignee: Tata Consultancy Services LimitedInventors: Snehasis Banerjee, Debnath Mukherjee
-
Patent number: 9510050Abstract: A context aware recommendation system and method for recommending at least one program to the user responsive to dynamically varying user preferences, learned user behavior and contextual information is described. The recommended program is a television program, radio program or music file. The system and method further alert the user about change in user's preferences and guides the user to change stated preferences.Type: GrantFiled: June 20, 2012Date of Patent: November 29, 2016Assignee: TATA CONSULTANCY SERVICES LIMITEDInventors: Debnath Mukherjee, Snehasis Banerjee, Siddharth Bhattacharya, Prateep Misra
-
Publication number: 20160246845Abstract: Disclosed is a system and method for providing data required for resolving a query. A data receiving module may receive a dataset captured by a plurality of sensors. A logic manager module may create a space for storing the dataset in a window of a plurality of windows. The logic manager module may further receive the query from a user. In one aspect, the query may either be registered query or an ad-hoc query. A window manager module may determine the data based upon the query. The window manager module may further resize the window when the query is the registered query. A learning module may select a maximum size window having a maximum size amongst the plurality of windows when the query is the ad-hoc query. A data facilitating module may provide the data in order to resolve the query.Type: ApplicationFiled: October 15, 2014Publication date: August 25, 2016Applicant: Tata Consultancy Services LimitedInventors: Snehasis BANERJEE, Debnath MUKHERJEE
-
Publication number: 20160026680Abstract: The present disclosure provides system and method for executing SPARQL query on a SPARQL engine. For executing the SPARQL query, a function may be instantly integrated with the SPARQL query which leads to extension of the SPARQL query. The extension may be achieved through a user friendly interface which may allow transparent integration of code (i.e., the function) in any language such as JAVA, C, C++ and the like, supporting a particular functionality. The system may integrate the code by addition of newly added code to the SPARQL library after validation. Further, the system may analyze the functionality associated with the code to optimize decision making of a user. The system may further support auto compilation and rating of the functions based on the user feedback and re-usability of the code working in a collaborative environment. Further the system may enable also enable to integrate external tools and web services.Type: ApplicationFiled: July 7, 2015Publication date: January 28, 2016Inventors: Snehasis Banerjee, Debnath Mukherjee
-
Publication number: 20150363694Abstract: Disclosed is a method and system for dynamically generating a customized, personalized and contextual alert for a user based with the profile of the user. The system comprises a profile updater module configured to update the profile data of the user extracted either from the social web or from the user. Further, a reasoning module is configured to derive refined background knowledge in context with the updated profile data of the user. A monitoring module is configured to monitor the events sensed by a sensing module. A context extractor module is configured for extracting the context of the events and the context of the user. A knowledge converter module is configured to convert the extracted context into structured format. Finally, the refined background knowledge is steam reasoned to determine whether the events received are relevant to the user and accordingly transmitted.Type: ApplicationFiled: December 5, 2013Publication date: December 17, 2015Inventors: Snehasis BANERJEE, Debnath MUKHERJEE, Prateep MISRA
-
Patent number: 9135562Abstract: The system and method of the present invention are described for automatic detection of error in the entry of particular category of individuals, especially referring to gender and age classification either real time while creating a database of such information or on an existing database on the record of individuals by analyzing their biometric characteristics like speech, image or face and other related demographic information like name of the individual in order to accord each individual with a unique identification.Type: GrantFiled: April 12, 2012Date of Patent: September 15, 2015Assignee: TATA CONSULTANCY SERVICES LIMITEDInventors: Aniruddha Sinha, Prateep Misra, Snehasis Banerjee, Arpan Pal
-
Publication number: 20150039648Abstract: Disclosed is a method and a system for stream reasoning a plurality of data streams. The system comprises a processor and a memory coupled to the processor. The processor is capable of executing a plurality of modules embodied on the memory. The plurality of modules comprises an event module and a application managed window module. The event module is configured to receive a data stream associated with an event from a stream reasoner application. The data stream provides factual information about the event. Further, the data stream comprises a request. The request may be an add request or a delete request. The application managed window module is configured to insert the request associated with the event or delete a prior request associated with the event from the memory based upon a type of the request.Type: ApplicationFiled: April 12, 2013Publication date: February 5, 2015Inventors: Debnath Mukherjee, Prateep Misra, Snehasis Banerjee
-
Publication number: 20140123165Abstract: A context aware recommendation system and method for recommending at least one program to the user responsive to dynamically varying user preferences, learned user behavior and contextual information is described. The recommended program is a television program, radio program or music file. The system and method further alert the user about change in user's preferences and guides the user to change stated preferences.Type: ApplicationFiled: June 20, 2012Publication date: May 1, 2014Applicant: Tata Consultancy Services LimitedInventors: Debnath Mukherjee, Snehasis Banerjee, Siddharth Bhattacharya, Prateep Misra
-
Publication number: 20140025624Abstract: The system and method of the present invention are described for automatic detection of error in the entry of particular category of individuals, especially referring to gender and age classification either real time while creating a database of such information or on an existing database on the record of individuals by analyzing their biometric characteristics like speech, image or face and other related demographic information like name of the individual in order to accord each individual with a unique identification.Type: ApplicationFiled: April 12, 2012Publication date: January 23, 2014Applicant: TATA CONSULTANCY SERVICES LIMITEDInventors: Aniruddha Sinha, Prateep Misra, Snehasis Banerjee, Arpan Pal