Assured Information Security, Inc.

Other

The State University of New York

Eastman-kodak Company

Triple R Enterprises, LLC

Robert Wright

Ryan Burnham

Robert Dora

Jacob Baldwin

Andrew Meyer

Lei Yu

Steven Loscalzo

Joseph G Guilmette

A system and method for controlling a system, comprising estimating an optimal control policy for the system; receiving data representing sequential states and associated trajectories of the system, comprising off-policy states and associated off-policy trajectories; improving the estimate of the optimal control policy by performing at least one approximate value iteration, comprising: estimating a value of operation of the system dependent on the estimated optimal control policy; using a complex return of the received data, biased by the off-policy states, to determine a bound dependent on at least the off-policy trajectories, and using the bound to improve the estimate of the value of operation of the system according to the estimated optimal control policy; and updating the estimate of the optimimal control policy, dependent on the improved estimate of the value of operation of the system. The control system may produce an output signal to control the system directly, or output the optimized control policy. The system preferably is a reinforcement learning system which continually improves.

Approximate value iteration with complex returns by bounding

Behavioral verification of user identity includes building a deep neural network for keystroke-based behavioral verification of user identity. The building includes receiving recorded keystroke events, each such recorded keystroke event including (i) an indication of whether the recorded keystroke event is a key press or a key release, (ii) a key identifier of the respective key pressed or released, and (iii) a timestamp of the recorded keystroke event. The building further includes performing pre-processing of the recorded keystroke events to provide data structures representing sequential key events for processing by a deep neural network to extract local patterns, and training the deep neural network using the data structures. The method also includes providing the trained deep neural network for keystroke-based behavioral verification of user identity based on determinate vectors output from the trained deep neural network.

Behavioral biometric feature extraction and verification

A control system and method for controlling a system, which employs a data set representing a plurality of states and associated trajectories of an environment of the system; and which iteratively determines an estimate of an optimal control policy for the system. The iterative process performs the substeps, until convergence, of estimating a long term value for operation at a respective state of the environment over a series of predicted future environmental states; using a complex return of the data set to determine a bound to improve the estimated long term value; and producing an updated estimate of an optimal control policy dependent on the improved estimate of the long term value. The control system may produce an output signal to control the system directly, or output the optimized control policy. The system preferably is a reinforcement learning system which continually improves.

A method for keystroke-based behavioral verification of user identity of a subject user of a computer system includes obtaining an enrollment signature corresponding to an identified user and serving as a unique identifier of the identified user, the enrollment signature including an enrollment determinate vector generated based on supplying enrollment keystroke data to a deep neural network for processing. The method further includes obtaining verification determinate vector(s), the verification determinate vector(s) for comparison to the enrollment signature to determine whether the subject user is the identified user. The method compares the verification determinate vector(s) to the enrollment signature and generates a probability indicator indicating a probability that keystroke data from a common user produced, from the deep neural network, the enrollment signature and the verification determinate vector(s), and indicates to the computer system whether, based on the probability indicator, the subject user is verified to be the identified user.

A method for gait-based behavioral verification of user identity of a subject user of a computer system includes obtaining an enrollment signature corresponding to an identified user and serving as a unique identifier of the identified user, the enrollment signature including an enrollment determinate vector generated based on supplying enrollment gait data to a deep neural network for processing. The method further includes obtaining verification determinate vector(s), the verification determinate vector(s) for comparison to the enrollment signature to determine whether the subject user is the identified user. The method compares the verification determinate vector(s) to the enrollment signature and generates a probability indicator indicating a probability that gait data from a common user produced, from the deep neural network, the enrollment signature and the verification determinate vector(s), and indicates to the computer system whether, based on the probability indicator, the subject user is verified to be the identified user.

A method and composition for cleaning and protecting vinyl, rubber and leather surfaces. The composition comprises a water-based emulsion of acrylic copolymer of RHOPLEX.RTM. HA-12, manufactured by Rohm and Haas of Philadelpha, Pa., polyethoxylated alkylphenol, and ammonium hydroxide. The ammonium hydroxide prevents coagulation that otherwise can result from freezing and thawing the composition. Application of the composition to aged and faded vinyl, rubber and leather surfaces cleans and restores the original luster and color without leaving an oily or glossy film.

Vinyl surface cleanser and protectant

A method and apparatus are disclosed for handling a needle to reduce the likelihood of accidental pricking. The apparatus includes cylindrical sleeve for receiving a phalanx of a finger or thumb. The apparatus also includes a pair of planar magnetic surfaces supported on the cylindrical sleeve for removably holding a needle thereon. The surfaces are spaced from and flush with each other. The spacing between the planar surfaces allows the needle to be easily placed on or removed from the surfaces with the aid of a needle grasping tool. The device further includes a shield located to one side of the spaced planar magnetic surfaces to protect the wearer from accidental pricking when the needle is being placed onto, removed from, or held by the magnetic planar surfaces. The method includes placing the cylindrical sleeve on the phalanx of a finger or thumb so that the shield is closer to the proximal end of the phalanx or thumb and the planar surfaces are closer the distal end of the phalanx or thumb, placing the needle on the spaced planar magnetic surfaces, and removing the needle from the spaced planar magnetic surfaces. If worn on a finger, the cylindrical sleeve is preferably rotated so that the planar magnetic surfaces face away from the side of the finger.

Needle holding apparatus and method of use

A customized packaging arrangement, for securely containing rectanguloid articles that vary in size and aspect ratio, comprises a combination of inner and outer packages. The inner package consists of first and second rectangular paperboard sheets that are joined in superposed, transverse relation at their central portions to provide a rectangular double-walled bottom for supporting an article thereon, the two sheets extending perpendicularly therefrom to provide opposite side and end portions, which are first folded against the article sides and ends, respectively, and are then folded and joined in overlapping relation upon the article top. The inner package so formed is then centered on, and secured to, a third paperboard sheet, which includes a rectangular central portion that is larger than the inner-package bottom centered thereon and, extending perpendicularly therefrom, opposite side and end portions which are first folded upwardly into spaced, confronting relation with the inner-package sides and ends, respectively, and are then folded inwardly and joined in overlapping relation upon the inner-package top. The outer package so formed is spaced from the inner package around its sides and ends to provide cushioning against impact. All cutting and scoring of the three sheets thus forming the inner and outer packages may be automated on-line in accordance with given dimensions of the article(s) to be packaged.

Customized packaging

A cold trap system is disclosed for recovering and recycling condensable gas reactants, such as xenon difluoride. Continuous recovery and recycling is achieved through a system including a plurality of cold traps and a storage chamber having a single input/output access pipe.

Growing community of inventors

Sherrill, NY, United States of America

Robert Wright