Abstract: An example operation may include one or more of generating a data frame storing content of a simulation, compressing the simulation content within the data frame based on previous simulation content stored in another data frame to generate a compressed data frame, and transmitting the compressed data frame via a blockchain request to one or more endorsing peer nodes of a blockchain network for inclusion of the compressed data frame within a hash-linked chain of blocks of the blockchain network.

Abstract: Techniques that facilitate time series analysis using machine learning are provided. In one example, a system includes a matrix generation component, a matrix factorization component and a machine learning component. The matrix generation component converts at least a first stream of time series data and a second stream of time series data (e.g., raw time series data) into a data matrix (e.g., a partially-observed similarity matrix) that comprises void data and numerical data associated with the first stream of time series data and the second stream of time series data. The matrix factorization component factorizes the data matrix into a first factorization data matrix and a second factorization data matrix. The machine learning component processes a machine learning model based on first matrix data associated with the first factorization data matrix and second matrix data associated with the second factorization data matrix.

Abstract: Techniques that facilitate time series analysis using machine learning are provided. In one example, a system includes a matrix generation component, a matrix factorization component and a machine learning component. The matrix generation component converts at least a first stream of time series data and a second stream of time series data (e.g., raw time series data) into a data matrix (e.g., a partially-observed similarity matrix) that comprises void data and numerical data associated with the first stream of time series data and the second stream of time series data. The matrix factorization component factorizes the data matrix into a first factorization data matrix and a second factorization data matrix. The machine learning component processes a machine learning model based on first matrix data associated with the first factorization data matrix and second matrix data associated with the second factorization data matrix.

Abstract: Aspects of the present disclosure describe techniques for detecting anomalous data in an encrypted data set. An example method generally includes receiving a data set of encrypted data points. A tree data structure having a number of levels is generated for the data set. Each level of the tree data structure generally corresponds to a feature of the encrypted plurality of features, and each node in the tree data structure at a given level represents a probability distribution of a likelihood that each data point is less than or greater than a split value determined for a given feature. An encrypted data point is received for analysis, and anomaly score is calculated based on a probability identified for each of the plurality of encrypted features. Based on determining that the calculated anomaly score exceeds a threshold value, the encrypted data point is identified as potentially anomalous.

Abstract: A blockchain of transactions may be referenced for various purposes and may be later accessed by interested parties for ledger verification and information retrieval. One example method of operation may include identifying a number of data parameters to extract from a blockchain based on a request for analytic data, creating one or more queries based on the data parameters, executing the one or more queries and retrieving the data parameters from the blockchain, identifying one or more permissions of a user account associated with the request for analytic data, and populating an interface with analytic figures based on the data parameters retrieved from the blockchain.

Abstract: An example operation may include one or more of generating a data frame storing content of a simulation, compressing the simulation content within the data frame based on previous simulation content stored in another data frame to generate a compressed data frame, and transmitting the compressed data frame via a blockchain request to one or more endorsing peer nodes of a blockchain network for inclusion of the compressed data frame within a hash-linked chain of blocks of the blockchain network.

Abstract: This disclosure provides a method, apparatus and computer program product to create a full homomorphic encryption (FHE)-friendly machine learning model. The approach herein leverages a knowledge distillation framework wherein the FHE-friendly (student) ML model closely mimics the predictions of a more complex (teacher) model, wherein the teacher model is one that, relative to the student model, is more complex and that is pre-trained on large datasets. In the approach herein, the distillation framework uses the more complex teacher model to facilitate training of the FHE-friendly model, but using synthetically-generated training data in lieu of the original datasets used to train the teacher.

Abstract: A method verifies an authenticity, integrity, and provenance of outputs from steps in a process flow. One or more processor(s) validate one or more inputs to each step in a process flow by verifying at least one of a hash and a digital signature of each of the one or more inputs. The processor(s) then generate digital signatures that cover outputs of each step and the one or more inputs to each step, such that the digital signatures result in a chain of digital signatures that are used to verify an authenticity, an integrity and a provenance of outputs of the one or more steps in the process flow.

Abstract: A technique for computationally-efficient privacy-preserving homomorphic inferencing against a decision tree. Inferencing is carried out by a server against encrypted data points provided by a client. Fully homomorphic computation is enabled with respect to the decision tree by intelligently configuring the tree and the real number-valued features that are applied to the tree. To that end, and to the extent the decision tree is unbalanced, the server first balances the tree. A cryptographic packing scheme is then applied to the balanced decision tree and, in particular, to one or more entries in at least one of: an encrypted feature set, and a threshold data set, that are to be used during the decision tree evaluation process. Upon receipt of an encrypted data point, homomorphic inferencing on the configured decision tree is performed using a highly-accurate approximation comparator, which implements a “soft” membership recursive computation on real numbers, all in an oblivious manner.

Abstract: A fixed-wing aircraft advertisement method, system, and non-transitory computer readable medium for a fixed-wing aircraft, include advertising from samples of speech heard by the fixed-wing aircraft at a given location.

Abstract: A blockchain of transactions may be referenced for various purposes and may be later accessed by interested parties for ledger verification and information retrieval. One example method of operation may include identifying a number of data parameters to extract from a blockchain based on a request for analytic data, creating one or more queries based on the data parameters, executing the one or more queries and retrieving the data parameters from the blockchain, identifying one or more permissions of a user account associated with the request for analytic data, and populating an interface with analytic figures based on the data parameters retrieved from the blockchain.

Abstract: A method, apparatus and computer program product for homomorphic inference on a decision tree (DT) model. In lieu of HE-based inferencing on the decision tree, the inferencing instead is performed on a neural network (NN), which acts as a surrogate. To this end, the neural network is trained to learn DT decision boundaries, preferably without using the original DT model data training points. During training, a random data set is applied to the DT, and expected outputs are recorded. This random data set and the expected outputs are then used to train the neural network such that the outputs of the neural network match the outputs expected from applying the original data set to the DT. Preferably, the neural network has low depth, just a few layers. HE-based inferencing on the decision tree is done using HE inferencing on the shallow neural network. The latter is computationally-efficient and is carried without the need for bootstrapping.

Abstract: An approach is provided that detect a section of a document that is currently being read by a user on a display device as well as the user's current emotional state. In response to determining, based on the detected current emotional state, that reading assistance would be helpful to the user, the approach identifies terminology within the section of the document that is currently being read by the user, retrieves assistive texts related to the identified terminology, and provides the assistive texts to the user at the display screen.

Abstract: An example operation includes one or more of computing, by a data owner node, updated gradients on a loss function based on a batch of private data and previous parameters of a machine learning model associated with a blockchain, encrypting, by the data owner node, update information, recording, by the data owner, the encrypted update information as a new transaction on the blockchain, and providing the update information for an audit.

Abstract: An apparatus and method for A/B testing including a storage device storing a set of data, an input device receiving input from a sensor according to a review of composed set of data, a processor receiving an input signal from the input device, the input signal including a plurality of criteria noted according to a time of the composed set of data, the processor processing the first set of data according to a feedback of the input signal. The processor analyzes the input signal and extracts the plurality of criteria from the input signal as extracted information.

Abstract: A system and method utilizing a mass user gaze fixation behavior with respect to products and product racks (using a camera-based inputs and gaze-tracking algorithms) and a financial profitability of each product/product type; generates gaze-based heat maps for indicating blind spots and eye gaze points at different positions of the racks/shelves and indicating product placement positions on the heat map; and advises product placement in the retail store for optimizing financial profitability by performing an iterative refinement of product placements over a period for the product/similar products. The system translates mass eye gaze of retail store customers into financial profitability via product placement optimization, and iteratively runs a method to optimize product placements, and generate gaze-based heat maps and perform blind spot analysis for avoiding product placements at certain locations and placing products at other locations, e.g., by running a decision module on consumer gaze pattern data.

Abstract: An example operation may include one or more of receiving, via a network, tag data that is read from a tag associated with a physical object and signed with a key assigned to the tag, determining, via a blockchain peer, that the signed tag data is validly signed based on a corresponding key pair of the tag which is accessible to the blockchain peer, determining, via the blockchain peer, whether the tag data satisfies of one or more predefined conditions of the physical object, and storing the determination via a blockchain database.

Abstract: An example operation may include one or more of obtaining data of a simulation, identifying checkpoints within the simulation data, generating a plurality of sequential data structures based on the identified checkpoints, where each data structure identifies an evolving state of the simulation with respect to a previous data structure among the sequential data structures, and transmitting the generated sequential data structures to nodes of a blockchain network for inclusion in one or more data blocks within a hash-linked chain of data blocks.

Abstract: A method, system, and non-transitory computer readable medium for an advertisement distribution system, include calculating an interest for each advertisement of an advertisement group, assigning each advertisement a user engagement value based on the interest, conducting an auction to determine winning advertisements based on advertiser parameters received from a database and the user engagement value of each of the plurality of advertisements, and dynamically populating an unviewed portion of the web page with the advertisement group of the winning advertisements.

Abstract: A resume remarketing method, system, and computer program product, including creating a remarketing cookie based on an interest factor of a first user in a first type of resume, matching the first user with a second user based on a similarity between a role of the first and second users, and transferring the remarketing cookie from the first user to the second user to remarket the first type of resume to the second user.