Digital Commons Network^™

Augmenting Tornado Detection And Tracking With Crowdsourced Media, Mel Bass, Daniel V. Klein

Defensive Publications Series

Tornados that impact a location have multiple different effects, not all of which are captured by video footage or other data sources. This disclosure describes techniques to obtain data from additional sources (including consumer devices, with user permission) for the purposes of tornado detection and/or tracking the activity and path of a tornado. Such media can include video footage (or screenshots) from storm chases, vehicle cameras, outdoor cameras, etc. obtained from devices where the users permit use of the video footage for storm detection. Additionally, data from lightning activity, pressure sensors, power grid anomalies, etc. can also be obtained and …

Automatic Generation Of Interactive Maps From Travel Videos, Paula Marques

Defensive Publications Series

This disclosure describes techniques for enhancing travel videos with an interactive map overlay that shows the viewer the geographic locations corresponding to various video frames. With user permission, location data obtained during video capture or determined by analysis of the video content is leveraged to align specific locations with specific frames. When a video is made available for playback via a video streaming service, an interactive route map is automatically generated and displayed alongside the video, enabling users to navigate through the video by clicking on the map. The described techniques eliminate the need for the video creator to provide …

Dynamic User Personalization Using Artificial Intelligence And Machine Learning, Roger William Graves

Defensive Publications Series

This document describes a framework for a personalization engine to suggest custom configuration parameters to each user, by creating a ‘digital twin’ of the user. The proposed framework implements artificial intelligence and/or machine learning principles to predict the preferred user experience and probable behavior of the user and observe actual behavior. The model is designed to be self-improving by comparing the model output (predicted behavior) to ground-truth (actual behavior). As the machine learning model is trained on the user’s preferences, historical behavior and digital actions, the model then provides real-time, custom-tailored personalization suggestions to the user. The model is either …

Subsea Last Mile Protection, N/A

Defensive Publications Series

Power and network communications can be rapidly restored for undersea cable systems. A switch system in cable infrastructure between a beach manhole and cable landing station, known as fronthaul, provides for actuating portions of the fronthaul to be connected and disconnected with terrestrial infrastructure. Specifically, in instances where multiple fronthaul cables are utilized, the cable providing power or optical data can be alternated. This is beneficial in instances where one of the plurality of fronthaul cables is damaged and needs to be repaired.

Novel Process For The Preparation Of 6-Hydroxy-2-Methylbenzofuran-3-Carboxylic Acid, Msn Laboratories Private Limited, R&D Center; Hyderabad, India; Srinivasan Thirumalai Rajan; Gade Srinivas Reddy & Surigilla Venkateshwarlu

Defensive Publications Series

The present disclosure relates to a novel process for the preparation of 6-hydroxy-2-methylbenzofuran-3-carboxylic acid of formula-2 which is a key intermediate used in the preparation of Fruquintinib.

Formula-2.

Smart Fov Tiling For Waveguide Design, Kellie Shaw

Defensive Publications Series

An optical assembly includes an optical waveguide and a first projection system disposed at a first location proximate to the optical waveguide. The first projection system is configured to emit red, green, and blue image light. Red image light coupled into the optical waveguide from the first projection system is outcoupled into a first field of view and blue image light coupled into the optical waveguide from the first projection system is outcoupled into a second field of view that is separate from the first field of view.

System And Method For Performing Secure Offline Payment Transactions Using A Sim Card, Alok Roy

Defensive Publications Series

The present disclosure provides a method and a system for performing secure offline payment transactions using a SIM card embedded in a user device. The method comprises receiving, at a secure element of the SIM card, an offline credit dynamically allocated by a financial institution and provisioned via a mobile application. The offline credit is securely stored in a partition of the secure element. During an offline transaction, the user is authenticated using the stored credentials, and the transaction amount is validated against the available offline credit and applicable policies. Upon successful validation, the secure element deducts the amount and …

A Digital Pixel Sensor Having Decreased Pixel Size

Defensive Publications Series

A pixel array includes a photodiode array and an ADC-memory array underlying the photodiode array, where the photodiode array includes a plurality of photodiode groups, and each photodiode group shares a common ADC element from within the ADC-memory array.

Hybrid Image Sensor For Contextual Artificial Intelligence

Defensive Publications Series

A hybrid image sensor is configured to operate in each of a high-resolution RGB mode, a QVGA mono CV mode, and a SVGA RGB CAI mode. Such an image sensor may include a high-resolution pixel array, a configurable signal binning circuit, and a configurable read-out circuit.

Inkjet Printed 3d Magnetic And Dielectric Polymer Composites With Tailored Properties, Hp Inc

Defensive Publications Series

The use of multi jet fusion (MJF) 3D-printing technology with magnetic nanoparticle inks and a novel pore-producing ink together with voxel-scale engineering techniques and predictive modeling provides an approach for designing and printing novel polymer nanocomposites and metamaterials with tailored physical and functional properties.

Augmented Reality Projected Interfaces On Real-World Objects Via Wearable Devices, Manasa Babu, Ramprasad Sedouram, Sanika Barve, Puneetha Pai Brahmavar Pattanshet

Defensive Publications Series

Interacting with a digital surface currently relies on a device with a touchscreen, where digital objects are displayed and can be manipulated via gestures. Augmented reality wearable devices can display virtual objects together with the real world. This disclosure describes the use of augmented reality wearable devices to turn everyday physical objects into projection surfaces onto which user interfaces are displayed for user interaction. Per the techniques, bounding boxes are determined for real-world objects and used to map objects to UI features of one or more apps. Upon user activation of projection, the selected app UI is projected onto the …

Execution Of Commands Using An Ai Engine, Nixon Aw, Bryson Lee, Yufeng Zhuang, Anita Wan

Defensive Publications Series

One embodiment includes a method comprising: training an artificial intelligence (AI) engine with successfully executed prior action data; receiving, by the AI engine, a request to perform an action; identifying, by the AI engine, one or more attributes to execute the action; obtaining, by the AI engine, a confirmation of the one or more attributes; identifying, by the AI engine, a plurality of APIs to perform the action as defined by the one or more attributes; identifying, by the AI engine, a sequence of execution for the plurality of APIs to perform the action; and executing, by the AI engine, …

Techniques To Facilitate Fast Link Protection Switch Convergence For Routed Passive Optical Networking (Pon) Networks, Manoj Kumar, G T Nadiyan Selvam

Defensive Publications Series

Proposed herein are techniques that enable the propagation of an event from a passive optical networking (PON) segment to an Ethernet segment through the use of a link level protocol (e.g., Link Layer Discovery Protocol (LLDP)). During operation for a PON deployment, when a PON Media Access Control (MAC) layer component takes over a PON link as a new active link, an event can be sent to the far end provider edge (PE) of the Ethernet overlay circuit to enable a path switch from an earlier active path to the protect path. Thus, the proposed techniques may enable fast end-to-end …

Proactive Readiness & Safety System For Autonomous Vehicles, Sudeep Chauhan, Pranav Bolar

Defensive Publications Series

This document describes techniques that enable a mobile computing device (e.g., a smartphone, smart watch, wearable device, augmented reality glasses, etc.) to share a user’s health and/or readiness data with a vehicle (e.g., self-driving cars, airplanes, heavy machinery, etc.) in order to proactively determine driver and/or passenger readiness and improve safety systems. This document further describes techniques that enable the vehicle to perform various actions based on the shared data. The mobile computing device may be able to continuously monitor the user’s vital signs (e.g., heart rate, heart rate variability, blood oxygen levels, body temperature, etc.) and/or behavioral indicators (e.g. …

Neurolink-X: Ai-Powered Adaptive Brain-Spinal Fusion Interface For Total Neural Restoration And Full-Body Integration, George Karelias, George Karelias

Defensive Publications Series

NeuroLink-X represents a pioneering leap in the convergence of artificial intelligence and neurobiology. This invention details an implantable brain-spinal interface capable of reestablishing functional motor-sensory connectivity between the cerebral cortex and a non-native spinal system. Originally envisioned for cephalosomatic transplantation, the device has transformative implications in treating paralysis, spinal cord injuries, neurodegenerative conditions, and interfacing with artificial bodies.

Systems And Methods For Binaural Audio Reproduction, Kellie Shaw

Defensive Publications Series

A computer-implemented method for binaural audio reproduction may include (i) retrieving binaural audio data captured by a device that comprises at least one microphone and at least one camera, (ii) isolating a subset of the binaural audio data that represents audio captured from objects within a field of view of the at least one camera, and (iii) balancing audio levels for the binaural audio data such that the subset of the binaural audio data is more clearly audible than data that is not within the subset and spatial cues for the binaural audio data are preserved. Various other methods, systems, …

Improving Multilingual Llm Language Adherence Via Language Signals And Fine-Tuning, Kandarp Joshi, Clint Kim, Petar Aleksic, Lillian Zhou

Defensive Publications Series

Multilingual large language models (LLMs) are capable of delivering responses to user queries/ prompts, including spoken queries (where the language of the audio may be ambiguous), in various languages. In many contexts, it is important that the response from the multilingual LLM adhere to a pre-configured/ specified language. This disclosure describes three approaches to improve the language adherence of an LLM - zero shot prompting, supervised fine-tuning, and chain-of-thought reasoning. In zero short prompting, a language hint that specifies the languages known to the user is provided to the LLM along with the input audio. In supervised fine-tuning, a training …

Automatic Determination Of Interactive Actions For Different Portions Of Digital Media, Manasa Babu

Defensive Publications Series

Media files lack interactive functionality, requiring users to manually perform actions related to the information displayed. This disclosure describes techniques to provide enhanced media interactivity by enabling context-aware selection and actions with reference to different portions of media content. Per the techniques, media content is analyzed to determine interactive actions that can be taken with reference to different portions of the media. The analysis includes determining the boundaries of the selection. The context of selection such as type of media and the overall content can also be taken into account. The selection mechanism can also adapt to user input. A …

Mastering Technology Audit Quality Assurance: A Framework For Auditors, Ramkumar Bharathan

Defensive Publications Series

Ramkumar's document presents a comprehensive framework (COBIT, NIST, FFIEC CAT, FFIEC IT Handbook) for establishing, implementing, and maturing a robust Technology Quality Assurance Review (QAR) program within internal audit, emphasizing its strategic imperative in today's complex digital landscape. Driven by escalating technology risks (cybersecurity, cloud, AI), evolving regulatory demands (FFIEC, COBIT, NIST CSF, GLBA, SOX, NYDFS, State Privacy Laws), and the need for reliable assurance, the framework details a systematic approach grounded in IIA Global Internal Audit Standards (specifically the QAIP) and integrated with key governance and control frameworks like COBIT and NIST CSF. It outlines core QAR principles, a …

Context-Aware Dynamic Diagram Generation For Enhanced Whiteboarding Sessions In An Online Meeting, Ram Mohan R, Rajarshee Dhar, Deepesh Arora

Defensive Publications Series

Proposed herein are techniques that provide for the ability to derive context for an online meeting from various contextual sources. During operation, the system proposed herein can predict a user's diagramming intent and then dynamically populate a whiteboarding palette with relevant diagrams based on the context of the online meeting.

“Innovative Methodology For Full Human Head Transplantation: A Multidisciplinary Surgical And Neurological Approach”, George Karelias

Defensive Publications Series

This disclosure introduces an innovative concept for an implantable artificial intelligence (AI) neural interface designed to restore functional connectivity between a transplanted human head (or brain) and the recipient body by bridging the severed spinal cord. The system features a bi-directional neural implant equipped with AI-driven signal decoding, encoding, and adaptive learning capabilities, enabling both motor control and sensory feedback across the disconnection. Core components include neural sensor arrays, a machine-learning processor, stimulation modules, and optional regenerative and drug delivery systems. This approach addresses the longstanding barrier of neural reconnection in full head transplantation and holds promise for applications in …

Cache Efficient Assignment Of Serving Tasks, N/A

Defensive Publications Series

This disclosure describes techniques for cache efficient assignment of serving tasks (workers) to client requests. Per techniques of this disclosure, a distributed computing system is configured such that a particular client can connect only to a subset of workers of the distributed computing system. To further ensure cache efficiency, the selection of a particular worker of an assigned subset of workers for a client request is based on a hash value of a key generated from a worker identifier. In some implementations, worker selection may be performed based on a consistent hash, wherein the worker (service task) name or identifier, …

Saving Idle Power And Engineering Hours By Powering Off/On Idle Ai Accelerators, N/A

Defensive Publications Series

The technology described in this paper relates to an artificial intelligence (AI) accelerator chip's application-specific integrated circuits (ASICs)’ power down for idle power reduction, and low-latency peripheral component interconnect express (PCIe) relink made on AI accelerator chips. Complete turning on or off of the AI accelerator chips may be accomplished by leveraging various software and/or hardware components in the AI accelerator systems. The specialized software and/or hardware may be configured to turn off the entirety or only certain components of each AI accelerator chip, such as application-specific integrated circuits (ASICs) embedded in the AI accelerator chip, and remove individual PCIe …

Generating Content Recommendations For User Groups Using A Large Language Model, Sathya Anurag Siruguppa

Defensive Publications Series

The large number of available content options from streaming audio and video service providers poses a challenge for providing useful recommendations to users, especially when a group of users with diverse viewing interests want to collectively engage with content. This disclosure describes techniques that leverage a large language model to generate a feature dataset based on user-permitted metadata for individual users of a group of users and content metadata for available content. A composite rating for individual pieces of content is determined and suitable content for the group is identified.

Enhanced Text Entry Assistance On Smart Devices Using Generative Artificial Intelligence, Yuanbo Zhang, Yuqing Zhong, Yang Lu, Xu Liu, Shumin Zhai, Renjie Liu, Lan Wei, James Su, Haoyue Tong, Haicheng Sun, Fan Yang

Defensive Publications Series

Users entering text on smart devices can receive artificial intelligence (AI) assistance for spelling and grammar corrections, content generation, content refinement, exploration, etc. However, providing a coherent user interface (UI) for AI assistance across different applications and device form factors can be challenging. The disclosure describes techniques of text input assisted by generative AI that enable frictionless content creation, revision, and exploration using a software keyboard-based user interface that is consistent across applications and devices. A user experience (UX) flow that is cognizant of the ambiguity inherent in content creation and open-ended content revision enables human-AI interactivity. A suitable large …

Adaptive Multimodal Speech Compression With Generative Priors, Roger William Graves

Defensive Publications Series

This disclosure describes techniques that leverage generative artificial intelligence to efficiently compress and accurately synthesize speech. Speech compression is achieved with personalized adaptation and with low perceptual loss. Per the techniques, a raw audio recording of a user is transcribed to text and is also used by a generative artificial intelligence (AI) speech synthesis model to create a fine-tuned personalized model of the user’s speech. A low-fidelity quantized representation is generated of information such as prosody, amplitude, inflection, etc. The transcript, the quantized audio data, and the personalized, fine-tuned model are compressed and saved. The compressed data is provided to …

Personalizing Ai Models Using Low-Rank Adaptation And Direct Preference Optimization, Saravanan Ganesh, Yi Li, Yunfei Hu, Krystal Kallarackal, Kelvin Nguyen, Chu-Cheng Lin

Defensive Publications Series

Aligning a large language model (LLM) to individual preferences is difficult to perform at scale. This disclosure describes techniques that leverage direct preference optimization (DPO) and low-rank adaptation (LoRA) to enable scalable alignment of artificial intelligence (AI) models. With user permission, user’s edits to suggestions from the model are obtained. The context of the user’s written data or interaction with the LLM is obtained. The user’s edits serve as training data to contextually fine-tune the model using LoRA and DPO. Training data is created as a side product of the user's tasks assisted by the LLM. The training data is …

Enhanced Deixis In Video Conferencing With Floating Video And Synthesized Gestures, Xun Qian, David Kim, Ruofei Du

Defensive Publications Series

In traditional video conferencing with screensharing, presenters struggle to reference specific on-screen elements effectively due to the limitations of small video feeds and basic pointer tools. This disclosure describes video conferencing (VC) techniques for enhancing the ability to point (deixis) in a videoconference using synthesized hand gestures. The video feed of the presenter is integrated into the shared screen, while synthesized hand gestures are overlaid to align with speech and pointer movements. With user permission, a multimodal machine learning pipeline accepts as input shared screen content, pointer/controller data, and ongoing speech to generate gestures and to determine optimal video placement. …

Federated Ai Learning In Healthcare: Comprehensive Framework For Managing Urgent Care Denials, Kush Sharma

Defensive Publications Series

Federated learning (FL) represents a paradigm shift in artificial intelligence (AI) by enabling collaborative model training across decentralized entities—such as hospitals, insurance providers, and clinics—without requiring the exchange of raw patient data. This approach is particularly transformative in healthcare, where data privacy regulations like the Health Insurance Portability and Accountability Act (HIPAA) in the U.S. and impose strict limitations on data sharing. In the context of urgent care denials—such as rejected pre-authorizations, triage prioritization errors, or resource allocation decisions—FL offers a way to improve AI-driven decision-making while preserving patient confidentiality.

This elaborates on a federated AI framework designed to address …

Machine Learning System And Method For Predicting Risk Of Drilling Component Failure, Baker Hughes Company

Defensive Publications Series

The invention addresses the problem of drilling tool failure risk assessment in the oil and gas industry. Tool failure in drilling operations can lead to significant financial losses, downtime, and safety risks. The invention aims to provide a solution for predicting and preventing these failures, which is crucial for maintaining safe and efficient drilling operations.

The invention proposes a solution by combining data-driven techniques with expert knowledge. It begins with data collection, including historical data on tool performance, and involves data cleaning and pre-processing. Relevant features are identified, and a predictive model is developed using machine learning techniques. The model …