A5101508112- Insect-Plant Interactions and Control
- Energy Efficient Wireless Sensor Networks
- Phytoplasmas and Hemiptera pathogens
- Oceanographic and Atmospheric Processes
- Lepidoptera: Biology and Taxonomy
- Underwater Vehicles and Communication Systems
- Advanced Computational Techniques and Applications
- Marine and fisheries research
- Maritime Navigation and Safety
- Advanced Neural Network Applications
- Plant and animal studies
- Indoor and Outdoor Localization Technologies
- Cocoa and Sweet Potato Agronomy
- Evaluation and Optimization Models
- Mobile Ad Hoc Networks
- Caching and Content Delivery
- Service-Oriented Architecture and Web Services
- Arctic and Antarctic ice dynamics
- Video Surveillance and Tracking Methods
- Hydrological Forecasting Using AI
- Cloud Computing and Resource Management
- Advanced Image and Video Retrieval Techniques
- Power Systems and Technologies
- Cooperative Communication and Network Coding
- Advanced Wireless Network Optimization
Ocean University of China
2015-2025
Duke University
2024
Shenzhen Institutes of Advanced Technology
2024
Chinese Academy of Sciences
2008-2024
Shanghai Stomatological Hospital
2023
Tongji University
2014-2023
Guangxi University
2023
China Academy Of Machinery Science & Technology (China)
2023
Dalian Maritime University
2023
Chongqing Three Gorges University
2023
The integration of artificial intelligence (AI) in healthcare has led to the development intelligent auxiliary diagnosis systems, enhancing diagnostic capabilities across various medical domains. These AI-assisted systems leverage deep learning algorithms aid professionals disease screening, localization focal areas, and treatment plan selection. With policies emphasizing innovation AI technology, particularly China, have emerged as valuable tools improving accuracy efficiency. categorized...
This paper proposes a convolutional neural network (CNN) method to estimate subsurface temperature (ST) in the Pacific Ocean from suite of satellite remote sensing measurements. These include sea surface temperature(SST), height (SSH), and salinity (SSS). We propose using multisource parameters establish monthly CNN model reconstruct ocean use Argo data for accurate validation. The results show that can accurately ST by model. trained 12 months. most prominent months are January, April,...
Existing localization approaches are divided into two groups: 1) range based and 2) free. The range-free schemes often suffer from poor accuracy low scalability, whereas the range-based heavily depend on extra hardware capabilities or absolute received signal strength indicator (RSSI) values, which is far practical. In this paper, we propose a mobile-assisted scheme called Perpendicular Intersection (PI), setting up delicate tradeoff between approaches. Instead of directly mapping RSSI...
Underwater acoustic sensor networks (UWA-SNs) are envisioned to perform monitoring tasks over the large portion of world covered by oceans. Due economics and area ocean, UWA-SNs mainly sparsely deployed nowadays. The limited battery resources is a big challenge for deployment such long-term networks. Unbalanced energy consumption will lead early depletion nodes, which partitions whole impairs integrity datasets or even results in collapse entire On contrary, balanced dissipation nodes can...
Indian Ocean Dipole (IOD) is a large-scale physical ocean phenomenon in the that plays an important role predicting El Nino Southern Oscillation tropical Pacific. Predicting occurrence of IOD great significance to study climate change and other marine phenomena. Generally, index calculated judge whether occurs. In this paper, convolutional LSTM (convLSTM) neural network used build deep learning model predict sea surface temperature next seven months calculate index. Through analysis...
Mesoscale air–sea interaction, which is active in Western Boundary Currents (WBCs), has a non-negligible effect on mid-latitude climate variability. The analysis and prediction of the mesoscale interaction rely high-resolution observation datasets mesoscale-resolving models, often require long processing times to estimate future changes have several limitations. Therefore, this study, we used newly developed iTransformer model, integrates sea surface temperature anomaly (SSTa) latent heat...
It is typical for cloud providers to operate a number of geographically distributed data centers, where inter-data center traffic constitutes large portion provider's demand over the Internet. Though such incurs substantial operational costs that are charged by ISPs, it varies significantly across different overlay links, raising opportunity optimize both routing and scheduling minimize costs. As being transmitted multiple sources their respective destinations, an intermediate also able...
User authentication is important to protect sensitive and private information for smartphone users. We propose Waving Authentication (WA) which a motion gesture system based on accelerometer. WA utilizes eight distinguishing features hiding in the acceleration traces of gestures exploits one-class Support Vector Machine classification. It insusceptible shoulder surfing attacks. In interactivity, we first provide two exhibitors' phones audiences try intruding by all kinds waving. And present...
High accurate indoor localization and tracking of smart phones is critical to pervasive applications. Most radio-based solutions either exploit some error prone power-distance models or require labor-intensive process site survey construct RSS fingerprint database. This study offers a new perspective readings by their contrast relationship rather than absolute values, leading three observations functions called turn verifying, room distinguishing entrance discovering. On this basis, we...
Microorganisms play a central role in sustaining soil ecosystems and agriculture, these functions are usually associated with their complex life history. Yet, the regulation evolution of history have remained enigmatic poorly understood, especially protozoa, third most abundant group organisms soil. Here, we explore cosmopolitan species-
Impacted by global warming, the sea surface temperature (SST) has increased, exerting profound effects on local climate and marine ecosystems. So far, investigators have focused short-term forecast of a small or medium-sized area ocean. It is still an important challenge to obtain accurate large-scale long-term SST predictions. In this study, we used reanalysis data sets provided National Centers for Environmental Prediction based Internet Things technology temporal convolutional network...
Motion sensors may impose the danger of hand-writing leakage if smartwatch installs a malicious app. By presenting proof-of-concept system: MotionHacker, we show usage app to record motions and extract handwriting-specific features for machine learning based analysis. MotionHacker is targeted on user-independent handwriting recognition word-level estimation content victim's handwriting, where only limit that follows print style. Furthermore, lowercase letters, which are more difficult than...
With the rapid development of marine IoT (Internet Things), ocean MDTN (Mobile Delay Tolerant Network) has become a research hot spot. Long-term trajectory prediction is key issue in MDTN. There are no long-term fine-grained methods proposed for vessels because vessel’s mobility pattern lacks map topology support and can be easily influenced by fish moratorium, sunshine duration, etc. A traditional on-land algorithm cannot directly utilized this field characteristics far different from that...
Different from terrestrial wireless networks that use radio channel, underwater utilize acoustic which poses great research challenges in medium access control (MAC) protocol design due to its low available bandwidth and high propagation delay characteristics. In addition, the bit-error, transmission energy cost, complex multi-path effects environment make it even harder. this paper, a suitable MAC protocol, named C-MAC (cellular MAC) for sensor (UWANs) is proposed. TDMA-based divides into...
Short-term prediction of fishing effort distributions will guide fishery management in a dynamic way. However, it meets two unique challenges: the randomness fishers' behaviors and diversity marine meteorology such as sea storms short period. This study proposes short-term system distribution by mining new kind knowledge: chronology among trawlers. We first define, quantify, dig out chronological relations trawlers based on VMS dataset. Then extracts optimal early bird set from relations,...
Existing localization approaches are divided into two groups: range-based and range-free. The range-free schemes often suffer from poor accuracy low scalability, while the heavily depend on extra hardware capabilities or rely absolute RSSI (received signal strength indicator) values, far practical. In this work, we propose a mobile-assisted scheme called perpendicular intersection (PI), setting dedicate tradeoff between approaches. Instead of directly mapping values physical distances, by...
In this project, we explore the possibility of deploying networked sensors on Ocean's surface, to monitor depth and temperature, as well other valuable environmental parameters. Sea monitoring is a critical task ensure safe operation harbors. Traditional schemes largely rely labor-intensive work expensive hardware. We present new solution for measuring sea with Restricted Floating Sensors. To address problem node localization changeable environment, propose Perpendicular Intersection (PI),...