A5101868199- Indoor and Outdoor Localization Technologies
- Underwater Vehicles and Communication Systems
- Retinal Imaging and Analysis
- Speech and Audio Processing
- Image and Signal Denoising Methods
- Scheduling and Optimization Algorithms
- Robotics and Sensor-Based Localization
- Advanced Measurement and Detection Methods
- Security in Wireless Sensor Networks
- Advanced Image and Video Retrieval Techniques
- Distributed systems and fault tolerance
- Fault Detection and Control Systems
- Distributed and Parallel Computing Systems
- Medical Image Segmentation Techniques
- Advanced Image Fusion Techniques
- Simulation Techniques and Applications
- Cervical Cancer and HPV Research
- AI in cancer detection
- Advanced Mathematical Physics Problems
- Assembly Line Balancing Optimization
- Food Quality and Safety Studies
- Ginseng Biological Effects and Applications
- Security and Verification in Computing
- Insect Resistance and Genetics
- Video Surveillance and Tracking Methods
Tulane University
2025
Shanghai Institute of Materia Medica
2025
Chinese Academy of Sciences
2025
University of Electronic Science and Technology of China
2010-2024
Northeastern University
2024
State Key Laboratory of Synthetical Automation for Process Industries
2024
Xi'an Jiaotong University
2021-2024
Nanjing University of Aeronautics and Astronautics
2014-2024
Shenzhen University
2022
Inner Mongolia University
2018
In this paper, a novel indoor localization system with channel state information (CSI) fingerprints is proposed, which learns the spatial and frequency features of CSI in fifth-generation (5G) cellular network by Siamese convolution neural network. particular, considering that continuously collected moving target possesses implicit association, we locate successive data gathered within time interval can be regarded as an subspace fingerprint database. Therefore, modeled matching problem...
The WiFi-based fingerprint indoor-positioning system has attracted increasing interest from industry and academia, benefiting the widespread deployment of wireless local area network (WLAN) infrastructure. However, with expansion application scenarios, this suffers labor-intensive work for received signal strength (RSS) construction. In article, we propose a crowdsourcing-based radio map construction method trajectory matching algorithm to solve time-consuming preliminary data collection in...
Currently, WiFi (or IEEE 802.11) enabled infrastructures and devices have become ubiquitous, which makes it promising to provide indoor positioning services via signals. However, most existing studies on its performance are carried out based simulations experiments, is still challenging mathematically characterize the localization error. Therefore, in this paper, Cramer-Rao lower bound (CRLB) for error by using signals established enables us carry a theoretical analysis fundamentals of...
WiFi positioning technology has attracted considerable attention in recent decades due to its widespread deployment and cost-effectiveness. The multipath effect can lead different local variations signals, diminishing both localization accuracy robustness. In this paper, we present an innovative framework that employs multi-scale spatial temporal features for localization, which takes the Received Signal Strength (RSS) sequence as input. First, propose a feature extraction network capture...
Indoor location-based services (LBS) are critical for enhancing social and commercial activities that require accurate efficient localization techniques. Existing deep-learning-based indoor methods mainly focus on pre-defined global features to learn local discriminative representations, which increases learning difficulty is not or robust scenarios with small variations. To address the above issues, we propose a novel Fine-grained Temporal based Localization (FT-Loc) framework utilizes...
The wavelet-domain Hidden Markov Tree Model can properly describe the dependence and correlation of fundus angiographic images' wavelet coefficients among scales. Based on construction images Models Gaussian Mixture Models, this paper applied expectation-maximum algorithm to estimate original Bayesian estimation achieve goal denoising. As is shown in experimental result, compared with other algorithms as mean filter median filter, method effectively improved peak signal noise ratio after...
In present paper we prove the local well-posedness for Von Neumann-Landau wave equation by T
Carrying out science popularization education is of great significance to broaden the knowledge young people, improve scientific literacy, enhance awareness and promote social progress. Combining dissemination advantages youth under background new media professional characteristics higher vocational colleges, this paper analyzes existing problems, strengthens development by constructing a general integration system; establishes service teaching staff, jointly develops high-quality courses;...
In order to realize load balance or fulfill the business logic efficiently, it is very common that a process has be migrated in environment of open network. this case, how protect recipient's platform from malicious code and at same time, attest trustworthiness by recipient are both typical problems. Utilizing trusted computing technology, transmission protocol designed can solve aforementioned problems efficiently. The AVISPA toolset also used verify results verification demonstrate does...
In order to realize the reliable operation of multi-equipment production line, it is necessary monitor overall health status line system avoid large-scale shutdowns equipment. The has characteristics equipment and complex structure, which bring difficulties assessment entire system. Existing research on at level lacks establishment a multilevel evaluation from level. Therefore, this article proposes index calculation method based importance data dynamically set weights for lines. This...
With the increasing popularity of mass customization, most manufacturing companies begin to assemble and manufacture products in a mixed-flow production model. To solve problem global complete kit extending start time order, complexity materials is getting higher higher, no correlation between learning forgetting effects, MOGA algorithm convergent speed slow manufacturer company, classified method put forward first. Then, an improved effect model that factor associated with parameter...
\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and robustness defense algorithms. Recent CNN generator-based approaches can synthesize unrestricted semantically meaningful entities the image, which is shown be transferable robust. However, such methods images by either synthesizing local adversarial entities, are only suitable for attacking specific contents or performing global attacks, applicable a scale. In this...
The time synchronization among simulation federates could be realized through logical by traditional management of distributed simulation. There are two types popular based on time, conservative advance mechanism and optimistic mechanism. Conservative restricted the causal relationship between might lead to poor efficiency deadlock while difficulty in rollback exist Based vector an managing was put forward, updating algorithm introduced control researched. application intelligent detection...