A5100618565- Energy Efficient Wireless Sensor Networks
- Water Quality Monitoring Technologies
- Underwater Vehicles and Communication Systems
- Advanced Computational Techniques and Applications
- Air Quality Monitoring and Forecasting
- Fault Detection and Control Systems
- Risk and Safety Analysis
- Distributed Sensor Networks and Detection Algorithms
- Robotics and Sensor-Based Localization
- Target Tracking and Data Fusion in Sensor Networks
- Machine Learning and ELM
- Image and Signal Denoising Methods
- Water Quality Monitoring and Analysis
- Anomaly Detection Techniques and Applications
- Evacuation and Crowd Dynamics
- Security in Wireless Sensor Networks
- Air Quality and Health Impacts
- Opportunistic and Delay-Tolerant Networks
- Atmospheric Ozone and Climate
- Occupational Health and Safety Research
- Indoor and Outdoor Localization Technologies
- Vehicle Routing Optimization Methods
- Hydrological Forecasting Using AI
- Mobile Ad Hoc Networks
- Vehicle emissions and performance
Hangzhou Normal University
2022-2024
Yiwu Science and Technology Research Institute
2024
Wuhan University of Technology
2022-2023
Guangdong University of Technology
2021
Hangzhou Dianzi University
2008-2020
Zhejiang Lab
2015-2016
Jiangxi Science and Technology Normal University
2016
Beijing University of Technology
2008
Chongqing University of Technology
2005-2008
International Paper (United States)
2008
A water environmental monitoring system based on a wireless sensor network is proposed. It consists of three parts: data nodes, base station and remote center. This suitable for the complex large-scale environment monitoring, such as reservoirs, lakes, rivers, swamps, shallow or deep groundwaters. paper devoted to explanation illustration our new design. The had successfully accomplished online auto-monitoring temperature pH value an artificial lake. system's measurement capacity ranges from...
Wireless sensor networks (WSNs) are an important tool for monitoring distributed remote environments. As one of the key technologies involved in WSNs, node fault detection is indispensable most WSN applications. It well known that (DFD) scheme checks out failed nodes by exchanging data and mutually testing among neighbor this network., but accuracy a DFD would decrease rapidly when number to be diagnosed small node's failure ratio high. In paper, improved proposed defining new criteria....
Various types of sensor data can be collected by the Internet Things (IoT). Each node has spatial attributes and may also associated with a large number measurement that evolve over time; therefore, these high-dimensional are inherently scale. Detecting outliers in large-scale IoT is challenging task. Most existing anomaly detection methods based on vector representation. However, have characteristics make tensor more efficient for extracting information. The vector-based destroy original...
The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has the largest aperture and a 19-beam L-band receiver, making it powerful for investigating neutral hydrogen atomic gas (HI) in universe. We present HiFAST (https://hifast.readthedocs.io), dedicated, modular, self-contained calibration imaging pipeline processing HI data of FAST. consists frequency-dependent noise diode calibration, baseline fitting, standing wave removal using an FFT-based method, flux density stray radiation...
In this paper, a data-driven fault diagnosis model dealing with chemical imbalanced data streams is investigated. Different faults occur varied frequencies by continuous arrival in plants, while issue has been hardly addressed developing model. A novel incremental imbalance modified deep neural network (incremental-IMDNN) proposed to promote the stream. The first step designing incremental-IMDNN employment of an method combined active learning for extraction and generation most valuable...
Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in processes. A deep neural network (DNN) with novel active learning inducing diagnosis is presented this study. It a method using large amount data, combination criterion to target difficulty consecutive diagnosis. DNN architectures, instead shallow ones, could be developed through learn suitable feature representation from raw an unsupervised...
Catastrophic interlocking chemical accidents (CICAs) are the most frequent hazardous events that occur in parks, and they result severe human casualties property losses. Emergency rescue facilities play an important role ensuring safety of as their locations determine efficiency effectiveness emergency management process. This paper proposes a multi-objective location (ERFsL) model for CICAs. Due to special characteristics CICAs, proposed considers not only spatial but also potential risks...
Designing an efficient deployment method to guarantee optimal monitoring quality is one of the key topics in underwater sensor networks. At present, a realistic approach involves adjusting depths nodes water. One typical algorithms used such process self-deployment depth adjustment algorithm (SDDA). This mainly focuses on maximizing network coverage by constantly node reduce overlaps between two neighboring nodes, and thus, achieves good performance. However, connectivity performance SDDA...
Side-scan sonar is widely utilized in the field of underwater exploration. Accurate segmentation side-scan images an essential part image processing. To improve accuracy and reduce occupancy computing resources, a new active contour model for proposed this article. Firstly, we make energy function each pixel determined by itself its neighbors. This article embeds local texture neighborhood region system define structure to against noise object boundary pollution image. Further, introduce...
This paper is concerned with the study of robust distributed average tracking (DAT) algorithms for networked control systems in presence external disturbances or false data injection attacks (FDIAs). To eliminate impacts and FDIAs, technologies disturbance-observer-based (DOBC) active disturbance rejection (ADRC) are introduced into context DAT problems. First, a class known dynamics, we propose an anti-disturbance (AD-DAT) algorithm, where stand-alone observer based on idea DOBC employed to...
Existing node deployment algorithms for underwater sensor networks are nearly unable to improve the network coverage rate under premise of ensuring full connectivity and do not optimize communication move energy consumption during deployment. Hence, a algorithm based on connected dominating set (CDS) is proposed. After randomly sowing nodes in 3D monitoring space, disconnected sink until achieves connectivity. The then performs centralized optimization determine CDS adjusts locations...
Introduction The ocean economy serves as a critical engine for the development of human society and economy, its stable growth is utmost importance. However, frequent unexpected occurrence natural disasters, such submarine poses significant threats to society, especially disasters related wave phenomena like Ekman current, which has particularly prominent impacts. Methods study proposes dynamic routing scheme underwater acoustic sensor networks. It establishes cone-shaped distributed...
Heterogeneous vehicle routing problem with time windows (HVRPTW) aspect of hazardous material (HazMat) transportation is studied in this article. Given the multiobjective nature HazMat transportation, a three-objective optimization model defined for HVRPTW transportation. The objective to determine fleet size and routes so as meet all given constraints well minimize objectives total traveling cost, risk, average redundancy. A load-variant risk assessment considering type waiting presented...
The focus of this article is to address the asynchronous control issue for a class nonlinear Markov jump systems with parameter uncertainties. They are represented by interval type-2 polynomial fuzzy model. A hidden model utilized describe behavior between system mode and controller in quantitative manner. This achieved using joint random process, which presented concise format encompasses both spontaneous simultaneous jumps. Further facilitate design flexibility low implementation burden,...
Water environment monitoring system based on wireless sensor networks (WSNs) consists of three parts: data nodes, date video base station and remote center. For the sake realizing to monitor large range waters such as reservoir, wetland, lake, river ocean etc, has function perception, acquisition, processing transmission for video-information in key areas various water parameters, temperature, PH, turbidity, electric conductivity, dissolved oxygen so on. As gateway between those nodes CDMA...