Abstract: Systems and methods for digital tokenization. A method includes issuing a token to a user based on an investment made by the user by recording a first transaction on a decentralized ledger indicating ownership of the token. The decentralized ledger is distributed across nodes among a decentralized network such that at least one portion of code is stored across the nodes, where the portions of code are encoded based on project parameters of an impact project. A third transaction is recorded on the decentralized ledger by generating a transaction specifying progress on the impact project and broadcasting the generated transaction to the decentralized network. A second transaction is recorded on the decentralized ledger via the portions of code based on the project parameters and the third transaction recorded on the decentralized ledger, where the second transaction includes a respective transfer via the token issued to the user.

Abstract: A method and system for image-based region detection. Transformation matrices are computed by performing image registration between a target image and each of one or more reference images. Each transformation matrix is for transforming each of the reference images into a coordinate system of the target image. An optimal reference image is selected from among the reference images based on similarity measures between the target image and each reference image. The transformation matrix of the selected reference image is applied to a reference map associated with the reference image in order to generate a target map for the target image. The target map includes region labels indicating regions shown in the target image.

Abstract: Systems and methods for building digital twins and navigating using digital twins. Reference signal and identifier data sent via antennas is obtained. Timing advance parameters for signals sent to the antennas are received. One or more machine learning models are applied to the reference signal data and timing advance parameters. Each machine learning model is trained to output antenna positions, antenna configurations, or both, and may be trained using training antenna configurations in the form of reference models representing different potential antenna configurations. Based on the outputs of the machine learning models, potential interference for devices occupying various locations within the network are determined. Navigation decisions, gaps in network coverage, or both, are determined based on the potential interference. As a result, interference by one or more devices moving within the network is reduced, thereby improving signal quality.

Abstract: Systems and methods for tokenization of social good. A disclosed method includes encoding a smart contract based on a plurality of project parameters for a social impact project, wherein the smart contract includes at least one self-executing code; and issuing a token to a user based on an investment made by the user, wherein issuing the token to the user further comprises recording a first transaction on a blockchain indicating that the user owns the token, wherein each of the at least one self-executing code is configured to record a second transaction on the blockchain based on the plurality of project parameters and data related to progress of the social impact project, wherein each second transaction includes a respective transfer of funds via the token issued to the user.

Abstract: Techniques for optimizing connection stability via communications with base stations in wireless communication networks. A current actual signal-to-distortion measurement value is determined for signals received by a device from a base station in a wireless communication network. A target base station configuration is determined based on the actual signal-to-distortion measurement value and known relationships between signal-to-distortion measurements and reliability metrics corresponding to different base station configurations. Deceptive signal quality transmissions are sent to the base station until the base station selects the target base station configuration. The deceptive signal quality transmissions may include deceptive signal-to-distortion measurements or deceptive binary values indicating poor signal quality.

Abstract: A system and method for improving connection reliability while navigating in cellular networks. Historical received by vehicles navigating within a cellular network are analyzed in order to create a signal propagation model. The cellular network is distributed across a geographic area including multiple cells, where each cell is a subdivision of the geographic area. The historical signals are received from transceivers deployed the cellular network. Based on the signal propagation model and an expected navigation path of the vehicle, a subset of transceivers within the cellular network is determined. The subset of transceivers is used for making selections about which transceivers the vehicle should communicate with, for example by transmitting the subset of transceivers to a system responsible for selecting which transceiver communicates with a given vehicle such that the system selects which transceiver to use from among the subset of transceivers.

Abstract: Systems and methods for mitigating moving targets using frequency signature mapping. A method includes mapping a plurality of electronic signatures of a target to a three-dimensional (3D) model into an electronic signature mapping, wherein the 3D model includes 3D features representing a plurality of historical frequency signatures; classifying a movement behavior of the target into at least one classification based on the electronic signature mapping and a plurality of learned behaviors for respective classifications of historical movement behavior; and performing at least one mitigation action to interfere with the classified behavior, wherein the at least one mitigation action is determined based on the at least one classification.

Abstract: Techniques for generating recommendations using machine learning with respect to semantic concepts defined in a knowledge graph. A hair profile is determined for a user based on inputs related to the user. Determining the hair profile includes extracting attributes of the user from the inputs using natural language processing, computer vision, or both, and identifying respective nodes for the extracted attributes in the knowledge graph. The knowledge graph is created via machine learning using population data including hair-related data in order to identify relationships between semantic concepts represented by nodes of the knowledge graph. The nodes include discrete properties such as individual hair attributes, ingredients of products, or otherwise discrete characteristics of factors that may affect a user's hair or related health conditions. A generalized recommendation is generated based on the hair profile.

Abstract: Methods and systems for three-dimensional asset modeling. A method includes: initializing a georeferenced data structure for each of a plurality of discrete sub-regions of an asset based on a model representing the asset, wherein the model includes a plurality of points representing features of the asset, wherein each georeferenced data structure includes a subset of the plurality of points representing features of a respective sub-region of the plurality of sub-regions; and populating each georeferenced data structure with input data including three-dimensional (3D) modeling data and nonspatial data, wherein each portion of the input data for a georeferenced data structure is used to populate a respective portion of the georeferenced data structure, wherein the nonspatial data used to populate each georeferenced data structure is organized with respect to geometry of the georeferenced data structure and with respect to time of recording of the nonspatial data.

Abstract: A system and method for providing graphical user interfaces based on computational algorithms described in printed publications. The method includes indexing a first output generated by a container; caching the indexed output in a cache memory; analyzing the printed publication to determine algorithm-indicating information of the computational algorithm; identifying, in the algorithm-indicating information, at least one input and at least one second output; generating at least one GUI element, wherein generating the at least one GUI element includes identifying an association between the printed publication and the container, wherein generating the at least one GUI element further comprises retrieving the first output from the cache memory, wherein the at least one GUI element is generated based on the retrieved first output; and generating executable code, wherein the executable code includes instructions for causing a display of the GUI including the at least one GUI element.

Abstract: A system and method for improved occupancy simulations. A method includes executing a scheduler algorithm based on input data in order to output a plurality of synthetic schedules, wherein the input data includes space data, persona data, and work pattern data, wherein the scheduler algorithm includes a plurality of sub-algorithms executed according to an order of priority, wherein at least an output of one of the plurality of sub-algorithms is input to another of the plurality of sub-algorithms; and inputting the plurality of synthetic schedules to a simulation engine, wherein the simulation engine runs a plurality of simulations using the plurality of synthetic schedules.

Abstract: Techniques for processing images to be used for more accurate measurement of biological processes such as cell migration, as well as techniques for measuring cell migration. A method for processing microscopic images includes generating a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background; generating a high pass filter image by dividing the raw image by the smoothed image; and transforming the high pass filter image into a transformed image by augmenting the spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background.

Abstract: A method and system for preprocessing microscopic images. A method includes identifying a plurality of microglial cells shown in microglial cell channel images, wherein identifying the plurality of microglial cells further comprises quantizing the microglial cell channel microscopic images and filtering a plurality of objects in the quantized microglial cell channel microscopic images; identifying a soma and at least one projection for each of the plurality of microglial cells, wherein identifying the soma and the at least one projection for each microglial cell further includes iteratively removing pixels on the microglial cell as shown in one of the microglial cell channel images, wherein each soma and each projection has a respective size; and determining an activation state of each microglial cell based on the size of the soma and a total size of the at least one projection identified for the microglial cell.

Abstract: The present invention relates to the use of next generation technologies coupled with viability and pathogenicity profiles to determine the threat of microbes in the environment. The invention relates to methods for identifying a pathogenicity and viability profile of microbes from collected samples.

Abstract: Methods and systems for three-dimensional asset modeling. A method includes: initializing a georeferenced data structure for each of a plurality of discrete sub-regions of an asset based on a model representing the asset, wherein the model includes a plurality of points representing features of the asset, wherein each georeferenced data structure includes a subset of the plurality of points representing features of a respective sub-region of the plurality of sub-regions; and populating each georeferenced data structure with input data including three-dimensional (3D) modeling data and nonspatial data, wherein each portion of the input data for a georeferenced data structure is used to populate a respective portion of the georeferenced data structure, wherein the nonspatial data used to populate each georeferenced data structure is organized with respect to geometry of the georeferenced data structure and with respect to time of recording of the nonspatial data.

Abstract: A system and method for developing a treatment plan using multi-stage machine learning. A method includes identifying at least one cognitive distortion of a user by applying a first machine learning model to a first portion of features extracted from data related to the user, wherein the first machine learning model is a cognitive distortions model trained using training user-created content; determining a plurality of digital therapeutics exercise tasks for the user based on the at least one cognitive distortion by applying a second machine learning model to a second portion of the features extracted from the data related to the user and to the output of the first machine learning model, wherein the second machine learning model is a task recommender model trained using training cognitive distortions and the training user-created content; and generating a treatment plan including the plurality of digital therapeutics exercise tasks for the user.

Abstract: A system and method for developing a treatment plan using multi-stage machine learning. A method includes determining a treatment plan for a patient based on at least one mental health disorder of a patient, wherein the treatment plan includes a plurality of digital therapeutics exercise tasks, wherein each digital therapeutics exercise task is selected from among a category of digital therapeutics exercise tasks corresponding to a type of mental health disorder of the at least one mental health disorder of the patient; and administering treatment to the patient by prescribing the treatment plan to the patient and causing data for administering the treatment plan to a user device of the patient.

Abstract: A system and method for identifying hazardous site conditions. The method includes training a classifier using a labeled training set, wherein the classifier is trained to classify site conditions based on features extracted from enhanced floor plans, wherein the labeled training set includes a plurality of training features and a plurality of training labels, wherein the plurality of training features are extracted from a plurality of training enhanced floor plans, wherein the plurality of training labels are a plurality of hazardous site condition identification labels; and identifying at least one hazardous site condition of a test enhanced floor plan by applying the classifier to a plurality of test features extracted from the test enhanced floor plan, wherein the classifier outputs at least one site condition classification when applied to the plurality of test features, wherein the at least one hazardous site condition is identified based on the at least one site condition classification.

Abstract: A system and method for microscopic image processing. The method includes cleaning leaks shown in images to create cleaned images, each of the images having a neuron signal intensity, wherein the images include at least one neuron channel image and at least one oligodendrocyte channel image, wherein cleaning the images further includes applying a filtering function to each of the images and adjusting the neuron signal intensity of each of the images based on an output of the filtering function; detecting oligodendrocytes in the cleaned images, wherein each detected oligodendrocyte is a region of the images including an object for which the neuron signal intensity is within a range of neuron signal intensities; and identifying high-intensity sub-regions within each detected oligodendrocyte, wherein each high-intensity sub-region includes at least one high-intensity object, wherein each high-intensity object is an object for which the neuron signal intensity is above a threshold.

Abstract: A system and method for creating an electronic document chronology. The method includes applying a machine learning model to an application data set to determine a plurality of connecting events representing a plurality of electronic document changes, wherein each connecting event is between a first entity and a second entity of a plurality of entities, wherein the first entity of each connecting event is an electronic document, wherein the application data set includes first electronic document change data and a plurality of first entity identifiers of the plurality of entities; and creating a document chronology graph based on the plurality of connecting events, wherein the document chronology graph includes a plurality of nodes and a plurality of edges, wherein each node represents one of the plurality of entities, wherein each edge represents one of the plurality of connecting events.