A5101567693- Robotics and Sensor-Based Localization
- Inertial Sensor and Navigation
- Robotic Path Planning Algorithms
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Computational Techniques and Applications
- Additive Manufacturing and 3D Printing Technologies
- Geochemistry and Geologic Mapping
- Indoor and Outdoor Localization Technologies
- Underwater Vehicles and Communication Systems
- Advanced Algorithms and Applications
- Infrared Target Detection Methodologies
- Remote-Sensing Image Classification
- Advanced Vision and Imaging
- Anomaly Detection Techniques and Applications
- Information Retrieval and Search Behavior
- Advanced Text Analysis Techniques
- Advanced Measurement and Detection Methods
- Radar Systems and Signal Processing
- Innovations in Concrete and Construction Materials
- Air Traffic Management and Optimization
- Power Systems and Technologies
- Maritime Navigation and Safety
- Mineral Processing and Grinding
- Analog and Mixed-Signal Circuit Design
- Advanced Data Storage Technologies
Chinese University of Hong Kong
2025
Tsinghua University
2025
Huazhong University of Science and Technology
2012-2024
East China Normal University
2024
Ministry of Natural Resources
2021-2024
Beijing Institute of Technology
2014-2024
China University of Geosciences (Beijing)
2021-2024
Beijing Electronic Science and Technology Institute
2024
Liaocheng University
2023-2024
Tianjin University of Science and Technology
2024
The unstructured nature of clinical notes within electronic health records often conceals vital patient-related information, making it challenging to access or interpret. To uncover this hidden specialized Natural Language Processing (NLP) models are required. However, training these necessitates large amounts labeled data, a process that is both time-consuming and costly when relying solely on human experts for annotation. In paper, we propose an approach combines Large Models (LLMs) with...
An engineered artificial lateral-line system has been recently developed, consisting of a 16-element array finely spaced MEMS hot-wire flow sensors. This represents new class underwater sensing instruments and necessitates the development rapid, efficient, robust signal processing algorithms. In this paper, we report on implementation set algorithms that assist in localization tracking vibrational dipole sources underwater. Using these algorithms, accurate trajectory moving source...
In this paper, we present a new method of power management for Plug-in Hybrid Electric Vehicles (PHEVs) using Reinforcement Learning technique combined with trip information. Our control strategy uses the remaining travel distance, which can be easily obtained from today's Global Positioning System (GPS), energy optimization PHEVs. For given trip, distance is highly correlated to future consumption, quantity our controller tries learn and optimize continuously. The simulation results confirm...
As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by algorithms. In this paper, we perform first systematic study of poisoning attacks their countermeasures linear regression models. attacks, deliberately influence training data a predictive model. We propose theoretically-grounded optimization framework specifically designed demonstrate its effectiveness on range datasets also introduce fast...
In the age of big data, prediction and evaluation geological mineral resources have gradually entered a new stage, intelligent prospecting. This review briefly summarizes research development textual data mining spatial mining. It is considered that current on resource has integrated logical reasoning, theoretical models, computational simulations, other scientific advanced toward model. type model tried to mine unknown effective knowledge from by analysis methods. However, many challenges...
Purpose To determine the precision of toric intraocular lens (IOL) formulas used by online calculator European Society Cataract and Refractive Surgeons (ESCRS). Methods This retrospective study included patients undergoing phacoemulsification with IOL implantation from July 2021 to June 2023 in Shanghai Sixth People's Hospital, Jiao Tong University School Medicine. The mean absolute prediction error (PE), standard deviation PE, proportion eyes a PE within ±0.25, ±0.50, ±0.75, ±1.00 diopters...
For the next-generation energy-storage devices, high power density supercapacitors can be used as complementary supplies.
The advent of the big data era has gradually brought about a new demand for integration geological text in three-dimensional (3D) mineral prospectivity mapping (3DMPM). Here, we report novel workflow suitable application natural language processing 3DMPM. Our study area is Xiyu kimberlite-type diamond deposit Shandong, China, which significant prospecting potential its deep portion. In this study, exploration criteria served as bridge connecting and 3DMPM, were constructed employing mining...
ABSTRACT This study aims to examine users' knowledge change characteristics and process, examined factors that may influence process. A user search experiment was conducted, in which participants were asked for two learning‐related tasks use a mind‐map organize their thoughts during the Pre‐ post‐search questionnaires distributed collect self‐assessed topic familiarity task difficulty. Besides overall process by all users, we identified four types of styles using hierarchical clustering...
Unmanned aerial vehicle (UAV) has been used to assist agricultural production. Precision landing control of UAV is critical for application it in some specific areas such as greenhouses or livestock/poultry houses. For controlling on a fixed mobile apron/platform accurately, this study proposed an automatic method and tested under three scenarios: (1) at high operating altitude based the GPS signal apron; (2) low image recognition (3) progress device detection achieve stable action. To...
In the big data era, mineral explorations need to accommodate for growth in spatial dimensions and dimensions, as well volume correlation between data. Aiming overcome problems of limited scattered sources, chaotic types, questionable quality, asymmetric information, small sample sizes current prospecting data, this paper improved traditional 3D prediction methods based on characteristics actual needs relevant First, regions with incomplete a new method transfer learning was proposed....
Summary This paper documents an application of model checking to formally verify interrupt‐driven Slats and Flaps Control Unit software programmed in C, one component a certain type Chinese aircraft. Our objective was identify errors rather than prove correctness. We focused on the correctness algorithms used buffer operations, which are very common important aircraft software. In verification, total four flawed code fragments identified, including minor efficiency issue. According...
Visual servoing has been around for decades, but time delay is still one of the most troublesome problems to achieve target tracking. To circumvent problem, in this paper, Kalman filter employed estimate future position object. In order introduce filter, accurate delays, which include processing lag and motion lag, need be obtained. Thus, delays visual control systems are discussed a generic timing model system provided. Then, we present current statistical moving target. A fuzzy adaptive...
For the vector attitude determination, traditional optimal algorithms which are based on quaternion estimator (QUEST) measurement noise model complicated for just two observations. In our application, magnetometer and accelerometer not comparable kinds of sensors both small field-of-view as well. So in this paper a new unit is derived. According to Wahba problem, weights each obtained by error variance researches. Then an improved Gauss–Newton method presented adopted acquire attitude....
With the era of big data, prediction and evaluation geological mineral resources have gradually entered into a new stage from digital prospecting to intelligent prospecting. The theoretical method data mining can contribute deep resource evaluation. This paper extracts ore-causing ore-caused anomaly information based on text technology, constructs regional conceptual model data. First, we set up corpus discovery preprocessing technology. Second, used CNN multiple scale classification...
Effective fault classification of rolling element bearings provides an important basis for ensuring safe operation rotating machinery. In this paper, a novel vibration sensor-based diagnosis method using Ellipsoid-ARTMAP network (EAM) and differential evolution (DE) algorithm is proposed. The original features are firstly extracted from signals based on wavelet packet decomposition. Then, minimum-redundancy maximum-relevancy introduced to select the most prominent so as decrease feature...