FedNaWi: Selecting the Befitting Clients for Robust Federated Learning in IoT Applications

Federated Learning (FL) is an important privacy-preserving learning paradigm that is expected to play an essential role in the future Intelligent Internet of Things (IoT). However, model training in FL is vulnerable to noise and the statistical heterogeneity of local data across IoT clients. In this paper, we propose FedNaWi, a “Go Narrow, Then...

AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Persons

Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary...

Tunable visible emission and persistent luminescence of BaGa₂O₄:Cu²⁺

In the field of solid-state luminescence, Cu²⁺ has long been widely acknowledged for its capacity to emit infrared light. However, the occurrence of visible emission from Cu²⁺ ions had been infrequently observed and reported. In this study, we made an intriguing discovery by examining the behavior of Cu²⁺...

System-Wide Effects of Local Bed Disturbance on the Morphological Evolution of a Bifurcating Channel Network

Deltaic channel networks are important conduits for water and material supplies to the fluvial and coastal communities. However, increasing human interventions in river deltas have altered the topology and geometry of channel networks as well as their long-term evolution. While the morphological evolution of a single channel has received...

Centimeter-Level Indoor Visible Light Positioning

Visible light positioning (VLP) based on the received signal strength (RSS) can leverage a dense deployment of LEDs in future lighting infrastructure to provide accurate and energy-efficient indoor positioning. However, its positioning accuracy heavily depends on the density of collected fingerprints, which is labor-intensive. In this work,...

Towards Cross-Modal Point Cloud Retrieval for Indoor Scenes

Cross-modal retrieval, as an important emerging foundational information retrieval task, benefits from recent advances in multimodal technologies. However, current cross-modal retrieval methods mainly focus on the interaction between textual information and 2D images, lacking research on 3D data, especially point clouds at scene level,...

MRHF: Multi-stage Retrieval and Hierarchical Fusion for Textbook Question Answering

Textbook question answering is challenging as it aims to automatically answer various questions on textbook lessons with long text and complex diagrams, requiring reasoning across modalities. In this work, we propose MRHF, a novel framework that incorporates dense passage re-ranking and the mixture-of-experts architecture for TQA. MRHF...

Sub-seasonal soil moisture anomaly forecasting using combinations of deep learning, based on the reanalysis soil moisture records

Sub-seasonal drought forecasting is crucial for early warning in estimating agricultural production and optimizing irrigation management, as forecasting skills are relatively weak during this period. Soil moisture exhibits stronger persistence compared to other climate system quantities, which makes it especially influential in shaping land...

Reliability improvement of the dredging perception system: A sensor fault-tolerant strategy

In the dredging industry, the automation and accuracy of the Dredging Perception System (DPS) are vital for operational efficiency and environmental safety. Current DPS implementations face challenges with sensor fault tolerance, leading to system unreliability and increased false alarm rates that can disrupt dredging operations. We propose a...

Designing digital patient experiences: The digital health design framework

Background Digital health (DH) brings considerable benefits, but it comes with potential risks. Human Factors (HF) play a critical role in providing high-quality and acceptable DH solutions. Consultation with designers is crucial for reflecting on and improving current DH design practices. Objectives We investigated the general DH design...

Building Understanding of Experience Design in Digital Health: Preliminary Results Based on Semi-Structured Interviews

Design is expanding its influence on shaping future healthcare. Ideally, designers apply human-centered design and human factors that introduce theory, principles, and methods to design to optimize people’s healthcare experiences in both digital and non-digital environments. To discuss and implement experience design in healthcare, consensus...

PointeNet: A lightweight framework for effective and efficient point cloud analysis

The conventional wisdom in point cloud analysis predominantly explores 3D geometries. It is often achieved through the introduction of intricate learnable geometric extractors in the encoder or by deepening networks with repeated blocks. However, these methods contain a significant number of learnable parameters, resulting in substantial...