Patents by Inventor Rajarathnam Chandramouli

Rajarathnam Chandramouli 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).

  • Patent number: 10593336
    Abstract: A machine learning multi-dimensional acoustic feature vector authentication system, according to an example of the present disclosure, builds and trains multiple multi-dimensional acoustic feature vector machine learning classifiers to determine a probability of spoofing of a voice. The system may extract an acoustic feature from a voice sample of a user. The system may convert the acoustic feature into multi-dimensional acoustic feature vectors and apply the multi-dimensional acoustic feature vectors to the multi-dimensional acoustic feature vector machine learning classifiers to detect spoofing and determine whether to authenticate a user.
    Type: Grant
    Filed: July 26, 2018
    Date of Patent: March 17, 2020
    Assignees: ACCENTURE GLOBAL SOLUTIONS LIMITED, MISRAM LLC
    Inventors: Constantine T. Boyadjiev, Rajarathnam Chandramouli, Koduvayur Subbalakshmi, Zongru Shao
  • Publication number: 20200035247
    Abstract: A machine learning multi-dimensional acoustic feature vector authentication system, according to an example of the present disclosure, builds and trains multiple multi-dimensional acoustic feature vector machine learning classifiers to determine a probability of spoofing of a voice. The system may extract an acoustic feature from a voice sample of a user. The system may convert the acoustic feature into multi-dimensional acoustic feature vectors and apply the multi-dimensional acoustic feature vectors to the multi-dimensional acoustic feature vector machine learning classifiers to detect spoofing and determine whether to authenticate a user.
    Type: Application
    Filed: July 26, 2018
    Publication date: January 30, 2020
    Applicants: MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam Chandramouli, Koduvayur Subbalakshmi, Zongru Shao
  • Patent number: 10548021
    Abstract: Various embodiments of systems, architecture, and/or methods are described for negotiating accesses to wireless spectrum of heterogeneous networks (e.g., Wifi, cellular 3G, cellular LTE, cellular 5G etc.) among multiple users, service providers, and services. As such, a software defined architecture is disclosed. In some embodiments, the disclosed software defined architecture can include establishing a (dedicated) logical control path from a central controller remotely located from an end device of a user. Such a logical control path is agnostic to the type and/or number of underlying wireless networks and is supplemental to conventionally known data paths, i.e., paths for exchanging data.
    Type: Grant
    Filed: May 21, 2018
    Date of Patent: January 28, 2020
    Assignee: MISRAM LLC
    Inventors: Vidya Sagar, Rajarathnam Chandramouli, Koduvayur P. Subbalakshmi
  • Patent number: 10516701
    Abstract: According to an embodiment, a natural language processing artificial intelligence network and data security system determines an emotions model for one or more users from electronic natural language interactions of the users. The system includes a natural language processing decoder to determine textual features from the electronic natural language interactions that may be indicative of emotional states of the users. They system includes an emotions model encoder that generates an emotions model based on the emotional states of the users in the electronic natural language interactions retrieved from the data storage. The system also includes an artificial intelligence network and data security subsystem.
    Type: Grant
    Filed: October 5, 2017
    Date of Patent: December 24, 2019
    Assignees: ACCENTURE GLOBAL SOLUTIONS LIMITED, MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam Chandramouli, Zongru Shao, Koduvayur Subbalakshmi
  • Publication number: 20190109878
    Abstract: According to an embodiment, a natural language processing artificial intelligence network and data security system determines an emotions model for one or more users from electronic natural language interactions of the users. The system includes a natural language processing decoder to determine textual features from the electronic natural language interactions that may be indicative of emotional states of the users. They system includes an emotions model encoder that generates an emotions model based on the emotional states of the users in the electronic natural language interactions retrieved from the data storage. The system also includes an artificial intelligence network and data security subsystem.
    Type: Application
    Filed: October 5, 2017
    Publication date: April 11, 2019
    Applicants: MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam CHANDRAMOULI, Zongru SHAO, Koduvayur SUBBALAKSHMI
  • Publication number: 20180338247
    Abstract: Various embodiments of systems, architecture, and/or methods are described for negotiating accesses to wireless spectrum of heterogeneous networks (e.g., Wifi, cellular 3G, cellular LTE, cellular 5G etc.) among multiple users, service providers, and services. As such, a software defined architecture is disclosed. In some embodiments, the disclosed software defined architecture can include establishing a (dedicated) logical control path from a central controller remotely located from an end device of a user. Such a logical control path is agnostic to the type and/or number of underlying wireless networks and is supplemental to conventionally known data paths, i.e., paths for exchanging data.
    Type: Application
    Filed: May 21, 2018
    Publication date: November 22, 2018
    Inventors: Vidya SAGAR, Rajarathnam CHANDRAMOULI, Koduvayur P. SUBBALAKSHMI
  • Patent number: 9292493
    Abstract: An apparatus and method for determining whether text is deceptive has a computer programmed with software that automatically analyzes text in digital form by at least one of statistical analysis of psycho-linguistic cues, IP geo-location, gender analysis, authorship analysis, and analysis to detect coded/camouflaged messages. The computer has truth data against which the text message can be compared and a graphical user interface. The computer may be connectable to the Internet and may obtain the text automatically. Speech-to-text software may be used to convert verbal messages to text for analysis. The system may be made available on a webpage, web service, on a computer or by a wireless device. The text may be emails, website content, tweets. In one embodiment, the system detects coded messages.
    Type: Grant
    Filed: April 26, 2011
    Date of Patent: March 22, 2016
    Assignee: The Trustees of The Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Koduvayur P. Subbalakshmi, Rohan Perera
  • Publication number: 20150254566
    Abstract: A method and apparatus for automatically identifying harmful electronic messages, such as those presented in emails, on Craigslist or on Twitter, Facebook and other social media websites, features methodology for discriminating unwanted garbage communications (spam) and unwanted deceptive messages (scam) from wanted, truthful communications based upon patterns discernable from samples of each type of electronic communication. Methods are proposed that enable discrimination of wanted from unwanted communications in short electronic messages, such as on Twitter and for multilingual application.
    Type: Application
    Filed: May 4, 2015
    Publication date: September 10, 2015
    Applicant: THE TRUSTEES OF THE STEVENS INSTITUTE OF TECHNOLOGY
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Kodovayr P. Subbalakshmi, Peng Hao, Na Cheng, Rohan Perera
  • Patent number: 9116877
    Abstract: An apparatus and method for determining whether a text is deceptive may comprise analyzing a body of textual content known to be one of text containing true content and text containing deceptive content; identifying psycho-linguistic cues that are indicative of a text being deceptive; statistically analyzing, via a computing device, a given text based upon the psycho-linguistic cues to determine if the text is deceptive. The apparatus and method may further comprise weighting the psycho-linguistic cues and statistically analyzing based on the weighted psycho-linguistic cues. The statistically analyzing step may be performed using one of a cue matching analysis, a weighted cue matching analysis, a Markov chain analysis, and a sequential probability ratio testing binary hypothesis analysis. The psycho-linguistic cues may be separated into categories, including increasing trend cues and decreasing trend cues and analyzed according to presence in a category from within the categories.
    Type: Grant
    Filed: January 6, 2011
    Date of Patent: August 25, 2015
    Assignee: The Trustees of the Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Koduvayur P. Subbalakshmi
  • Patent number: 8873580
    Abstract: Apparatus and methods are disclosed for improving wireless and other network communications, e.g., through improving resource utilization, which may comprise the steps of accumulating channel modeling information relating to channel performance; calculating a channel parameter threshold based on the accumulated channel modeling information, whereby the channel parameter, as measured, being above the threshold indicates the channel is a good channel; adjusting traffic over a selected good channel to improve performance of the network or a network resource. The network resource may comprises battery life for devices operating on the network, data rate for devices operating on the network, constituting or reconstituting ad hoc networks comprising nodes separated by multiple hops, continuity of connectivity within a single communication link over the network, etc.
    Type: Grant
    Filed: September 15, 2010
    Date of Patent: October 28, 2014
    Assignee: The Trustees of the Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Shamik Sengupta, Kai Hong
  • Publication number: 20140192656
    Abstract: Methods and apparatus are provided for the efficient use of cognitive radios in the performance of dynamic spectrum access. This includes spectrum sensing algorithms, adaptive optimized sensing of parameters based on changing radio environments, and identifying vacant channels. Protocols for switching communication links to different channels, and synchronizing communicating nodes in order to maintain reliable connectively while maximizing spectrum usage are also provided.
    Type: Application
    Filed: March 11, 2014
    Publication date: July 10, 2014
    Applicant: The Trustees of the Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Shamik Sengupta, Kai Hong
  • Patent number: 8699430
    Abstract: Methods and apparatus are provided for the efficient use of cognitive radios in the performance of dynamic spectrum access. This includes spectrum sensing algorithms, adaptive optimized sensing of parameters based on changing radio environments, and identifying vacant channels. Protocols for switching communication links to different channels, and synchronizing communicating nodes in order to maintain reliable connectively while maximizing spectrum usage are also provided.
    Type: Grant
    Filed: October 9, 2009
    Date of Patent: April 15, 2014
    Assignee: The Trustees of the Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Shamik Sengupta, Kai Hong
  • Patent number: 8555052
    Abstract: A steganographic message/advertisement embedding method is presented that can be used for contextual and targeted advertising supporting unobtrusive and on-demand message/advertisement delivery. The present invention presents over two client devices, the method includes receiving, on a first client device, a primary multimedia presentation with a plurality of steganographic codes embedded therein; whereby the steganographic code is not perceivable during a rendering of the multimedia presentation and the steganographic code is associated with at least one secondary multimedia presentation. Next; the primary multimedia presentation is rendered on the first client device. The first client device receives a user selection to select at least one of the steganographic codes.
    Type: Grant
    Filed: August 21, 2007
    Date of Patent: October 8, 2013
    Assignee: The Trustees of The Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Koduvayur P. Subbalakshmi, Helena S. Wisniewski
  • Publication number: 20130138428
    Abstract: An apparatus and method for determining whether text is deceptive has a computer programmed with software that automatically analyzes text in digital form by at least one of statistical analysis of psycho-linguistic cues, IP geo-location, gender analysis, authorship analysis, and analysis to detect coded/camouflaged messages. The computer has truth data against which the text message can be compared and a graphical user interface. The computer may be connectable to the Internet and may obtain the text automatically. Speech-to-text software may be used to convert verbal messages to text for analysis. The system may be made available on a webpage, web service, on a computer or by a wireless device. The text may be emails, website content, tweets. In one embodiment, the system detects coded messages (FIG. 19).
    Type: Application
    Filed: April 26, 2011
    Publication date: May 30, 2013
    Applicant: The Trustees of the Stevens Institute of Technology
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Koduvayur P. Subbalakshmi, Rohan Perera
  • Publication number: 20130046531
    Abstract: An apparatus and method for determining whether a text is deceptive may comprise analyzing a body of textual content known to be one of text containing true content and text containing deceptive content; identifying psycho-linguistic cues that are indicative of a text being deceptive; statistically analyzing, via a computing device, a given text based upon the psycho-linguistic cues to determine if the text is deceptive. The apparatus and method may further comprise weighting the psycho-linguistic cues and statistically analyzing based on the weighted psycho-linguistic cues. The statistically analyzing step may be performed using one of a cue matching analysis, a weighted cue matching analysis, a Markov chain analysis, and a sequential probability ratio testing binary hypothesis analysis. The psycho-linguistic cues may be separated into categories, including increasing trend cues and decreasing trend cues and analyzed according to presence in a category from within the categories.
    Type: Application
    Filed: January 6, 2011
    Publication date: February 21, 2013
    Applicant: THE TRUSTEES OF THE STEVENS INSTITUTE OF TECHNOLOGY
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Koduvayur P. Subbalakshmi
  • Publication number: 20120254333
    Abstract: A method and apparatus for automatically identifying harmful electronic messages, such as those presented in emails, on Craigslist or on Twitter, Facebook and other social media websites, features methodology for discriminating unwanted garbage communications (spam) and unwanted deceptive messages (scam) from wanted, truthful communications based upon patterns discernable from samples of each type of electronic communication. Methods are proposed that enable discrimination of wanted from unwanted communications in short electronic messages, such as on Twitter and for multilingual application.
    Type: Application
    Filed: April 25, 2012
    Publication date: October 4, 2012
    Inventors: Rajarathnam Chandramouli, Xiaoling Chen, Koduvayur P. Subbalakshmi, Peng Hao, Na Cheng, Rohan Perera
  • Publication number: 20110090853
    Abstract: Apparatus and methods are disclosed for improving wireless and other network communications, e.g., through improving resource utilization, which may comprise the steps of accumulating channel modeling information relating to channel performance; calculating a channel parameter threshold based on the accumulated channel modeling information, whereby the channel parameter, as measured, being above the threshold indicates the channel is a good channel; adjusting traffic over a selected good channel to improve performance of the network or a network resource. The network resource may comprises battery life for devices operating on the network, data rate for devices operating on the network, constituting or reconstituting ad hoc networks comprising nodes separated by multiple hops, continuity of connectivity within a single communication link over the network, etc.
    Type: Application
    Filed: September 15, 2010
    Publication date: April 21, 2011
    Inventors: Rajarathnam Chandramouli, Shamik Sengupta, Kai Hong
  • Publication number: 20100325413
    Abstract: A steganographic message/advertisement embedding method is presented that can be used for contextual and targeted advertising supporting unobtrusive and on-demand message/advertisement delivery. The present invention presents over two client devices, the method includes receiving, on a first client device, a primary multimedia presentation with a plurality of steganographic codes embedded therein; whereby the steganographic code is not perceivable during a rendering of the multimedia presentation and the steganographic code is associated with at least one secondary multimedia presentation. Next; the primary multimedia presentation is rendered on the first client device. The first client device receives a user selection to select at least one of the steganographic codes.
    Type: Application
    Filed: August 21, 2007
    Publication date: December 23, 2010
    Inventors: Rajarathnam Chandramouli, Koduvayur P. Subbalakshmi, Helena S. Wisniewski
  • Publication number: 20100135226
    Abstract: Methods and apparatus are provided for the efficient use of cognitive radios in the performance of dynamic spectrum access. This includes spectrum sensing algorithms, adaptive optimized sensing of parameters based on changing radio environments, and identifying vacant channels. Protocols for switching communication links to different channels, and synchronizing communicating nodes in order to maintain reliable connectively while maximizing spectrum usage are also provided.
    Type: Application
    Filed: October 9, 2009
    Publication date: June 3, 2010
    Inventors: Rajarathnam Chandramouli, Shamik Sengupta, Kai Hong
  • Publication number: 20100067687
    Abstract: A method is disclosed for modifying an iterated block cipher by controlling the operations and transformations that cause diffusion. In one embodiment which is applicable to any iterated block cipher (12), a diffusion function (10), during encryption, is selected based on a parameter which measures the order of permutation of the diffusion function (10) and applies the diffusion function (10) to the encryption routine (12). The user chooses the required amount of diffusion for a given block of plaintext (11). The plaintext (11) is then encrypted using the modified diffusion function (10) to produce a ciphertext (14) which is then sent over a communications channel (16) which may be noisy. At the receiving end (18) of the communications channel (16), the received ciphertext (20), which now may be corrupted by bit errors, is passed through an iterated block cipher decryption routine (22) using the same diffusion function (10) selected earlier during encryption.
    Type: Application
    Filed: December 1, 2005
    Publication date: March 18, 2010
    Applicant: THE TRUSTEES OF THE STEVENS INSTITUTE OF TECHNOLOGY
    Inventors: Rajarathnam Chandramouli, Chetan Nanjunda Mathur