edge computing

guv-calcs v0.7.3: An open-source Python library for modeling germicidal UV in indoor environments

guv-calcs is an open-source Python scientific computing library for physically based modeling of germicidal ultraviolet (GUV) light in indoor environments, with a focus on far-UVC (200–235 nm) applications. The library provides core numerical tools for representing lamps, spatial geometry, calculation planes and volume...

Privacy-Preserving Fraud Intelligence for Kenya's Account-to-Account Payment Ecosystem

This whitepaper proposes a privacy-preserving federated graph intelligence architecture for fraud detection across Kenya’s account-to-account payment ecosystem, using PesaLink as the principal infrastructure context. The research addresses a structural limitation of institution-level fraud detection: fraudulent activit...

Privacy-Preserving Fraud Intelligence for Kenya's Account-to-Account Payment Ecosystem

This whitepaper proposes a privacy-preserving federated graph intelligence architecture for fraud detection across Kenya’s account-to-account payment ecosystem, using PesaLink as the principal infrastructure context. The research addresses a structural limitation of institution-level fraud detection: fraudulent activit...

An Intelligent a IoT Framework for Automated Checkout and Real-Time Inventory Management in Smart Retail

The Smart Cart is an AI-and IoT-based intelligent shopping system designed to transform the conventional retail shopping experience by enabling automated billing, real-time inventory monitoring, and personalized customer assistance.Traditional shopping carts and manual checkout processes often result in long queues, in...

Photonic accelerators for AI across cloud and edge platforms

RTMDet-AS: an improved real-time instance segmentation model for tomato harvesting based on attention mechanism and SIoU loss

RTMDet-AS is presented, a robust instance segmentation network tailored to address the challenges of cluttered backgrounds, dense fruit clusters, and the strict efficiencyaccuracy trade-off required for edge computing in unstructured greenhouses with a 96.7 FPS inference rate and fewer computational efforts.

Edge AI Doctrine: Ten Critical Considerations for Edge AI, With Architectural Ramifications, Consequences, and Governance

The failure modes of artificial intelligence systems deployed at the edge are not, at their root, failures of model quality, training data adequacy, or algorithmic design. They are failures of architectural composition: the failure to design for the constraints that edge environments impose as boundary conditions rathe...

(Short Paper19) The Eyeball Organ as a Privileged I/O Port in the In Vivo QPU Paradigm: Visual System Edge Computing and Fail-Safe Mechanisms Associated with Sleep Deprivation

In conventional neuroscience, the visual organ—the eyeball—has been treated as a “passive sensor that converts external photon information into electrical signals at the retina and transmits them to the cerebral visual cortex.” However, within the framework of the in vivo quantum processing unit (Bio-QPU) theory, the c...

Research on an intelligent rice crop monitoring system based on UAV optical remote sensing and AI

According to the study designed and impIemented an intelligent rice crop monitoring system based on unmanned aerial vehicle (UAV) optical remote sensing, and artificial intelligence (AI) technology. A multirotor UAV platform, multispectral imaging sensors, edge computing modules and a cloud-based AI analysis platform a...

Communication-Aware Decentralized FMMC Optimization via Edge-Local ADMM and Chebyshev Polynomial Filtering

Extended version of a paper on decentralized fastest mixing Markov chain (FMMC) optimization. The method represents the transition matrix through O(|E|) edge variables, splits the graph-feasibility and spectral-box constraints by ADMM, computes the graph projection with an exact distributed consensus ADMM, and computes...

From detection to prediction: rethinking foodborne pathogen intelligence in the age of AI

This perspective argues that the more consequential shift is genuine predictive capability: forecasting contamination before it manifests, enabling proactive intervention rather than reactive damage control.

Supporting data: reaction–demixing coupling and Cu(II) uptake at ionisable acidic sites in Jatropha-oil-derived precursor/polyethersulfone membranes

Supporting data for the article “Reactive aqueous NIPS of a Jatropha-oil-derived NCO-terminated precursor with polyethersulfone: reaction–demixing coupling, urethane–urea network formation and Cu(II) uptake at ionisable acidic sites” (Journal of Membrane Science). The record holds the structured numerical records under...