A5076925423- Voice and Speech Disorders
- Phonetics and Phonology Research
- Speech Recognition and Synthesis
- IoT-based Smart Home Systems
- Dysphagia Assessment and Management
- Autopsy Techniques and Outcomes
- Water Quality Monitoring Technologies
- Safety Systems Engineering in Autonomy
- Prostate Cancer Diagnosis and Treatment
- Smart Grid Security and Resilience
- Indoor and Outdoor Localization Technologies
- Assistive Technology in Communication and Mobility
- Speech and Audio Processing
- Speech and dialogue systems
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Underwater Acoustics Research
- Geophysical Methods and Applications
- UAV Applications and Optimization
- Risk and Safety Analysis
- Water Systems and Optimization
- Nuclear and radioactivity studies
- AI in cancer detection
- Global Trade and Competitiveness
Hengyang Academy of Agricultural Sciences
2023-2024
Google (United States)
2020-2024
University of South China
2020-2024
<h3>Importance</h3> Expert-level artificial intelligence (AI) algorithms for prostate biopsy grading have recently been developed. However, the potential impact of integrating such into pathologist workflows remains largely unexplored. <h3>Objective</h3> To evaluate an expert-level AI-based assistive tool when used by pathologists biopsies. <h3>Design, Setting, and Participants</h3> This diagnostic study a fully crossed multiple-reader, multiple-case design to grading. Retrospective core...
This study examines the effectiveness of automatic speech recognition (ASR) for individuals with disorders, addressing gap in performance between read and conversational ASR. We analyze factors influencing this disparity effect mode-specific training on ASR accuracy.
Interest in anti-UAV detection systems has increased due to growing concerns about the security and privacy issues associated with unmanned aerial vehicles (UAVs). Achieving real-time high accuracy, while accommodating limited resources of edge-computing devices poses a significant challenge for detection. Existing deep learning-based models often cannot balance processing speed, model size, computational efficiency. To address these limitations, lightweight efficient model, DRBD-YOLOv8, is...
We developed dysarthric speech intelligibility classifiers on 551,176 disordered samples contributed by a diverse set of 468 speakers, with range self-reported speaking disorders and rated for their overall five-point scale. trained three models following different deep learning approaches evaluated them ~ 94K utterances from 100 speakers. further found the to generalize well (without training) TORGO database[1] (100% accuracy), UASpeech[2] (0.93 correlation), ALS-TDI PMP[3] (0.81 AUC)...
Although personalized automatic speech recognition (ASR) models have recently been improved to recognize even severely impaired speech, model performance may degrade over time for persons with degenerating speech. The aims of this study were (1) analyze the change ASR in individuals degrading and (2) explore mitigation strategies optimize throughout disease progression. Speech was recorded by four due amyotrophic lateral sclerosis (ALS). Word error rates (WER) across recording sessions...
The quality and quantity of water supplied by high-level tank directly affect people's daily life. Most traditional tanks use manual detection, which has high detection cost low data accuracy. In order to ensure the safety continuity supply, this paper designs a set monitoring system based on Internet things. adopts TDS sensor ultrasonic monitor level respectively, transmits back center for real-time through ZigBee -a wireless communication protocol. can control automatically alarm when is...
For loss and theft in the transport of radioactive materials by a single vehicle, this article summarizes characteristics “illegal movement” establishes security system that senses its inter-relationship responds though group network relationship. The reminds vehicle crew through on-site response linkage response. A failure detection method for is proposed, is, push model used first, when measurement results are suspected, pull to further confirm failure. adopts model. According different...
The loss and theft of radioactive material in transport can be attributed to the illegal movement. In order distinguish it from movement caused by turbulence transportation vehicle, this paper proposes criterion “illegal movement” as materials outside compartment. Since interior compartment is generally a metal environment, wireless signal strength data sensing method. filtered converted into distance data. We construct spatial triangle perpendicular top sides based on When inside...
The rapid expansion of nuclear technology across various sectors due to global economic growth has led a substantial rise in the transportation radioactive materials. International Atomic Energy Agency (IAEA) estimates that approximately 20 million shipments materials occur annually. In this context, ensuring safety and security material is significant importance. IAEA’s “Security Radioactive Materials Transport” (Nuclear Security Series No. 9-G) mandates an effective transport system should...