A5100331862- Target Tracking and Data Fusion in Sensor Networks
- Speech and Audio Processing
- Music and Audio Processing
- Speech Recognition and Synthesis
- Gaussian Processes and Bayesian Inference
- Indoor and Outdoor Localization Technologies
- Anomaly Detection Techniques and Applications
- Water Systems and Optimization
- Microwave Imaging and Scattering Analysis
- Air Quality Monitoring and Forecasting
- Advanced Computational Techniques and Applications
- Animal Vocal Communication and Behavior
- Oral microbiology and periodontitis research
- Neural Networks and Applications
- Digital Marketing and Social Media
- Advanced MIMO Systems Optimization
- Advanced Neural Network Applications
- Data Stream Mining Techniques
- Topic Modeling
- Mobile Crowdsensing and Crowdsourcing
- Fault Detection and Control Systems
- Advanced Control Systems Optimization
- Network Security and Intrusion Detection
- Geological Modeling and Analysis
- Advanced Sensor and Control Systems
Harbin Institute of Technology
2004-2025
Institute of Information Engineering
2023-2025
Chinese Academy of Sciences
2017-2025
Criminal Investigation Police University of China
2025
Shandong Provincial QianFoShan Hospital
2025
University of Surrey
2002-2024
Dalian University of Technology
2003-2024
Henan University of Traditional Chinese Medicine
2024
Yangzhou University
2024
Suzhou University of Science and Technology
2022-2024
In this paper, two different backstepping neural network (NN) control approaches are presented for a class of affine nonlinear systems in the strict-feedback form with unknown nonlinearities. By special design scheme, controller singularity problem is avoided perfectly both approaches. Furthermore, closed loop signals guaranteed to be semiglobally uniformly ultimately bounded and outputs system proved converge small neighborhood desired trajectory. The performances closed-loop can shaped as...
Radio-frequency (RF) tomography is the method of tracking targets using received signal-strength (RSS) measurements for RF transmissions between multiple sensor nodes. When are near line-of-sight path two nodes, they more likely to cause substantial attenuation or amplification signal. In this paper, we develop a measurement model multitarget in indoor environments and apply it successfully up three targets. We compare several algorithms examine performance scenarios when number 1) known...
The Gaoligong Mountains lie at the intersection of three global biodiversity hotspots. In recent years, with continuous deepening fieldwork in region, studies have increasingly indicated that amphibian diversity this region remains poorly understood. During herpetological surveys 2023, a series Amolops specimens were collected from Yunnan Province, China. integrated results morphological and molecular phylogenetic analyses indicate presence separate previously unknown lineage A....
We propose a working set based approximate sub gradient descent algorithm to minimize the margin-sensitive hinge loss arising from soft constraints in max-margin learning frameworks, such as structured SVM. focus on setting of general graphical models, loopy MRFs and CRFs commonly used image segmentation, where exact inference is intractable most violated can only be approximated, voiding optimality guarantees SVM's cutting plane well reducing robustness existing methods. show that proposed...
Many real-world time series analysis problems are characterized by low signal-to-noise ratios and compounded scarce data. Solutions to these types of often rely on handcrafted features extracted in the or frequency domain. Recent high-profile advances deep learning have improved performance across many application domains; however, they typically large data sets that may not always be available. This paper presents an for acoustic event detection a challenging, data-scarce, problem. We show...
A key challenge when designing particle filters in high-dimensional state spaces is the construction of a proposal distribution that close to posterior distribution. Recent advances flow provide promising avenue avoid weight degeneracy; particles drawn from prior are migrated space by solving partial differential equations. Numerous have been proposed based on different assumptions concerning dynamics. Approximations needed implementation all these filters; as result, do not exactly match...
Purpose Drawing on anthropomorphism and the stereotype content model, this study aims to explore impacts of robot hotel guests’ word mouth continuous usage intention through perceived warmth competence. This also investigates moderating effects expertise. Design/methodology/approach A total 524 valid data was collected with Chinese guest an online survey. Data were analyzed by using structural equation modeling. Findings The results indicate that positively affects Perceived intention, while...
The ovary plays a crucial role in the reproductive system of female animals. Ovarian problems such as ovarian insufficiency, premature aging, polycystic syndrome, and cysts may lead to ovulation disorders, abnormal hormone secretion, or luteal dysfunction, thereby increasing risk infertility abortion. Only when function other organs remain healthy work normally can animals be ensured carry out activities regularly, improve pregnancy rate litter size, promote development fetus, then their...
Presents results of the face verification contest that was organized in conjunction with International Conference on Pattern Recognition 2000. Participants had to use identical data sets from a large, publicly available multimodal database XM2VTSDB. Training and evaluation carried out according an priori known protocol. Verification all tested algorithms have been collected made public XM2VTSDB website, facilitating large scale experiments classifier combination fusion. Tested methods...
In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling from 8kHz to 16kHz while restoring high content level almost indistinguishable ground truth. The architecture is based on SEANet (Sound EnhAncement Network), wave-to-wave fully convolutional model, which uses combination feature losses and adversarial reconstruct an enhanced version input speech. addition, variant that can be deployed on-device in streaming mode,...
Radio Frequency (RF) tomographic tracking is the process of moving targets by analyzing changes attenuation in wireless transmissions. This paper presents a novel sequential Monte Carlo (SMC) method for RF single target using sensor network. The algorithm incorporates on-line Expectation Maximization (EM) to estimate model parameters. Based on experimental measurements, we introduce new measurement caused target. We assess performance through numerical simulation and demonstrate that it...