Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks105 from public data
- A Differential Evolution-Based Routing Algorithm for Environmental Monitoring Wireless Sensor Networks57
Simulation results show that the proposed new LEACH routing algorithm has better performance, effectively extends the working lifetime of the system, and improves the quality of the wireless sensor networks.
- Real-Time Detection of River Surface Floating Object Based on Improved RefineDet40
This work proposes a real-time detection method of surface floating objects based on improved RefineDet model, which includes three modules: the anchor refinement module, the transfer connection block and the object detection module, and introduces focal loss function to solve the foreground-background class imbalance.
- Region-specialized underwater image restoration in inhomogeneous optical environments39
A region-specialized method for underwater image restoration, where region-varied changes in the ambient light are taken into consideration for dehazing and color compensation and the highest score of no-reference perceptual quality assessment is obtained.
- Fast and robust image segmentation with active contours and Student's-t mixture model27
A novel active contours method, which combines with the Student's-t mixture model via Expectaton-Maximizaton (EM) algorithm, is proposed to segment complicated two-phase images using latent variables and a novel updating of level set function based on probabilistic principles is derived.
- Underwater Object Segmentation Integrating Transmission and Saliency Features19
Novel cues and a suitable model formulation for object segmentation from underwater images are proposed and the special haze effect over underwater images is considered and an informative feature (transmission feature) is extracted from haze condensation to propose a solution that handles the challenging issues in underwater object segmentsation.
- 15
- 15
- 14
- 12
- 12
- 10
- Underwater Object Detection by Combining the Spectral Residual and Three-Frame Algorithm10
A hierarchical system, in which each level is composed by a specialized processor, is proposed to detect objects in underwater videos to assist the underwater monitor system survey operations, specialized to the task of object detection.
- 10
- Improved RRT* For Fast Path Planning in Underwater 3D Environment9
An improved RRT* is proposed, goal-biased Gaussian distribution sampling with variable standard deviation is proposed to controls the randomness of search nodes, and a focused optimal search strategy is introduced to improve the convergence rate.
- Domain Adaptation and Adaptive Information Fusion for Object Detection on Foggy Days9
A novel object detection method that has the ability to exploit the information in the color and depth domains is proposed and the advantages of the multiple-domain adaptation strategy are experimentally demonstrated via comparison with other methods.
- Efficient handover in railway networking via named data9
This paper argues that railway networking can be more effective through named data networking (NDN), rather than using IP addresses, which provides a name-based paradigm that can achieve seamless handover.
- 9
- An Approach for Target Detection and Extraction Based on Biological Vision8
A target detection and extraction method based on insect compound eye and human visual attention mechanism for improving the detection accuracy of interested target and is based on the LEGION (Locally Excitatory Globally Inhibitory Oscillator Networks) selection network model.
- 8
- 7
- 7
- 7
- Fuzzy Integral Based Information Fusion for Water Quality Monitoring Using Remote Sensing Data7
A fusion method based on Choquet Fuzzy Integral (CFI) to estimate the Chl-a concentration of Taihu Lake and an algorithm that fully considers neighbor sampling information is designed to resolve the over-fitting problem caused by a small number of training sets.
- DGA Domain Detection Based on Transformer and Rapid Selective Kernel Network6
A novel multi-scale feature fusion model that integrates the Transformer architecture with the Rapid Selective Kernel Network (R-SKNet) and develops an efficient channel attention (ECA) module is introduced.
- 6
- The Method of Flotation Froth Image Segmentation Based on Threshold Level Set6
The proposed novel flotation froth image segmentation based on threshold level set method has better segmentation results and higher segmentation efficiency on the images with under-segmentation and incorrect segmentation, and it is meaningful for ore dressing industrial.
- 5
- 5
- Optical Prior‐Based Underwater Object Detection with Active Imaging5
An optical prior-based underwater object detection approach that takes advantage of optical principles to identify optical collimation over underwater images, providing valuable guidance for extracting object features.
- Evaluation of path stretch in scalable routing system5
It is concluded that path stretch is greatly affected by collaboration strategy and the tradeoff between the path stretch and collaboration cost is worth considering.
- Spatial–temporal multi-task learning for salient region detection4
A novel multi-task learning based salient region detection method by fusing spatial and temporal features that outperforms previous methods and learns the mapping relationship from various features to salient regions using the unified Bayesian framework.
- Texture image segmentation using statistical active contours4
A texture-based active contours method for two-phase image segmentation in a statistical framework that combines color, texture, and saliency weight to form an augmented image and uses the local probability distribution to obtain a smooth label to reduce the fragmentation in the initialization and evolution of segmentation contours.
- 4
- 4
- 4
- 4
- 4
- 4
- Underwater Structural Multi-Defects Automatic Detection via Hybrid Neural Network3
A novel hybrid neural network to enhance feature representation of underwater structural multi-defects, which in turn improves the accuracy and adaptability of underwater detection, and provides an effective solution for detecting diverse structural defects in complex underwater environments.
- CFDepthNet: Monocular Depth Estimation Introducing Coordinate Attention and Texture Features3
This paper uses a simple yet compact network structure, a unique loss function, and a relatively flexible embedded attention module, which is more effective and easier to arrange in robotic platforms with weak arithmetic power.
- 3
- A Cooperative Dynamic Cluster in Multitasking Mobile Networks3
This work proposes a model for a dynamic cluster motivated by the tasks with dynamic scale and nodal locatio... that combines reinforcement learning and reinforcement learning to solve the challenge of integrating NoSQL data stores to manage distributed systems.
- Data fusion algorithm of multilayer neural network by ZigBee protocol architecture3
The paper has designed a data fusion algorithm of MLP-ZigBee by ZigBee Protocol Architecture to solve above problems and shows that the algorithm can be repeated sent data by reducing redundancy to reduce the network energy consumption and extend the life cycle of WSN.
- 3
- 3
- 3
- 3
- A New Adaptive EDCA Approach to QoS of Wireless Communications3
This paper analyzes the QoS in IEEE 802.11 MAC protocol framework, and proposes a new design of a Differentiation Enhanced Adaptive EDCA (enhanced distribution channel access) approach to reduce the conflict among the data frames, and improve the channel utilization.
- 3
- 3
- 2
- 2
- Face segmentation based on level set and improved DBM prior shape2
A new method of level set image segmentation based on prior shape, which aims to provide a better solution to the challenging segmentation problems that typically occur in images with complex background, intensity inhomogeneity and partially blocked targets is put forward.
- Spectrum Analysis-Based Traffic Video Synopsis2
A spectrum analysis method for traffic video synopsis, including motion detection and tracking, which can provide a synopsis for Big Data of traffic videos.
- Multiphase Image Segmentation Based on Improved LBF Model2
The proposed model replaces the Gauss kernel function in the original LBF model with the new kernel function to improve the time efficiency and accuracy and is further integrated into the variational level set of multi-phase image segmentation strategy.
- An Opportunistic Routing Protocol Based on Link Correlation for Wireless Mesh Networks2
The results show that LCOR can achieve opportunistic routing in WMNs whose nodes are limited and evenly distributed and the overhead of the protocol is smaller than ExOR when the number of candidates in each forwarding candidates set is less than 5.
- 2
- 2
- An information fusion method for sensor data rectification2
An improved Back Propagation neural network is used to perform data fusion on the hardware platform of a stantion unit, which takes Field-Programmable Gate Array (FPGA) as the core component and results show that this method can recitify random errors as well as gross errors significantly.
- 2
- 2
- 2
- 2
- Authentication and Key Establishment Scheme Based on Token for Mobile Commerce2
Two novel sampling approaches are proposed to obtain a random sample of exact streaming window join result and a windowed aggregate over the exact join results can be unbiasedly and accurately estimated.
- 1
- 1
- 1
- 1
- 1
- 1
- An Adaptive Gradient Enhanced Texture Based Tracking Algorithm for Video Monitoring Applications1
An adaptive gradient enhanced texture based tracking algorithm for traffic monitoring applications that builds a joint histogram template of color and texture for targeting, which solves the problems of tracking targets losing when the color of the object is similar to thecolor of the background.
- 1
- 1
- A local dynamic cluster self-organization algorithm in wireless sensor networks for rainfall monitoring1
A Local Dynamic Cluster Self-organization algorithm (LDCS) is proposed for the large-scale regional and moving target monitoring in RM-WSNs, which can relieve the problem of “too frequent leader switches” in IDSQ and make full use of the history monitoring information of target and continuous monitoring of sensor nodes that failed in DCS.
- –
- –
- –
- AuthPLC: Authenticating PLC Communication Using ST-based Extended Cryptographic Library–
AuthPLC is proposed, an authentication framework for PLC communications that enhances both security and integrity and develops a lightweight authentication and key-exchange protocol that provides anonymity and resists multiple attacks.
- –
- –
- –
- A Sparse-denoising Auto-encoder with Generalization Ability on Sub-network–
By adding noise to the network, the new auto-encoder increases the robustness of the sub-network and improves the generalization ability of sub-learning and improvesThe generalization of the entire network at last.
- The Research on Level Set Segmentation Method Based on Kernel Principal Component Analysis Prior Shape–
A new face segmentation method based on level set prior shape that uses the kernel principal component analysis algorithm to reduce the dimension of the samples, extracts the principal component as the prior shape to guide the image segmentation, and does morphological processing on the mean shape.
- –
- –
- Study on the relationship between prefix caching and path stretch ratio–
This note studies the relationship between prefix caching and path stretch ratio, and presents quantitive results.
- –
- Moving object detection based on background image set and sparse analysis–
The simulation results indicate that when the background illumination mutates, the proposed method can effectively eliminate the impact of environment noise and reduce the false detection rate of target detection.
- A Regularity-Based Connectivity Analysis of Three-Dimensional Wireless Sensor Networks–
The region regularity is introduced into the wireless sensor network model for connectivity analysis by analyzing and simulating the link probability, the average node degree and the node density of networks, and the influence of region regularities on network connectivity is summarized.
- –
- A Novel Sensor Node Management Approach Based on Particle Filtering Prediction–
Compared with the traditional selective trigger mechanism based on prediction and the famous probing environment and collaborating adaptive sleeping node scheduling mechanism, the proposed algorithm can not only achieve much better tracking quality, but also activate only a fewer number of nodes for final tracking, which will finally reduce the whole WSN system’s power consumption.
- –
- –
- –
- –
- –
- –
- Analysis of Authentication Header Protocol–
The components, authentication algorithm, and security of AH protocol are analyzed, including methods and suggestions for improvement, and the weaknesses and flaws of AH are pointed out.
- Study on Data Acquisition and Data Integration Model of Information Integration System in Water-Resource Management–
The characteristics of the system of data acquisition and data integration in water resources information system and a data integration plan based on the multi-agent technology are analyzed and an analysis of the plan's systematic structure and features is made.
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.