A5067133312- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Fault Detection and Control Systems
- Control Systems and Identification
- Advanced Control Systems Optimization
- Blind Source Separation Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Structural Health Monitoring Techniques
- Advanced Algorithms and Applications
- Robotic Path Planning Algorithms
- Adaptive Control of Nonlinear Systems
- Advanced Computational Techniques and Applications
- Gait Recognition and Analysis
- Chemical Synthesis and Analysis
- Face and Expression Recognition
- Spectroscopy and Chemometric Analyses
- Industrial Technology and Control Systems
- Autonomous Vehicle Technology and Safety
- Advanced Adaptive Filtering Techniques
- AI-based Problem Solving and Planning
- Phenothiazines and Benzothiazines Synthesis and Activities
- Synthesis and Biological Evaluation
- Stability and Control of Uncertain Systems
- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
University of Southampton
2014-2024
Ocean University of China
2024
Clinical Research Institute
2022
University of Newcastle Australia
2007-2022
Newcastle University
2008-2022
University of Cambridge
2019-2021
University of Birmingham
2021
College of Staten Island
2021
City University of New York
2021
Google (United States)
2019-2020
Currently there exist two commonly used measurement fusion methods for Kalman-filter-based multisensor data fusion. The first (Method I) simply merges the through observation vector of Kalman filter, whereas second II) combines based on a minimum-mean-square-error criterion. This paper, an analysis fused state estimate covariances methods, shows that are functionally equivalent if sensors fusion, with different and independent noise characteristics, have identical matrices. Also presented...
Abstract Lithium–sulfur batteries are currently being explored as promising advanced energy storage systems due to the high theoretical specific capacity of sulfur. However, achieving a scalable synthesis for sulfur electrode material whilst maintaining volumetric density remains serious challenge. Here, continuous ball‐milling route is devised synthesizing multifunctional FeS 2 /FeS/S composites use tap electrodes. These demonstrate maximum reversible 1044.7 mAh g −1 and peak 2131.1 Ah L...
Many industrial processes contain both linear and nonlinear parts, kernel principal component analysis (KPCA), widely used in process monitoring, may not offer the most effective means for dealing with these processes. This paper proposes a new hybrid linear-nonlinear statistical modeling approach monitoring by closely integrating (PCA) KPCA using serial model structure, which we refer to as PCA (SPCA). Specifically, is first applied extract PCs features, decompose data into PC subspace...
The paper introduces an efficient construction algorithm for obtaining sparse linear-in-the-weights regression models based on approach of directly optimizing model generalization capability. This is achieved by utilizing the delete-1 cross validation concept and associated leave-one-out test error also known as predicted residual sums squares (PRESS) statistic, without resorting to any other data set evaluation in process. Computational efficiency ensured using orthogonal forward...
Many kernel classifier construction algorithms adopt classification accuracy as performance metrics in model evaluation. Moreover, equal weighting is often applied to each data sample parameter estimation. These modeling practices become problematic if the sets are imbalanced. We present a algorithm using orthogonal forward selection (OFS) order optimize generalization for imbalanced two-class sets. This identification based on new regularized weighted least squares (ROWLS) estimator and...
Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need manually engineering or prior a perception system. However, data RL is collected via running an agent in desired environment, and applications robotics, robot real world may be extremely costly time consuming. Simulated training offers appealing alternative, but ensuring that policies trained simulation transfer effectively...
In order to deeply exploit intrinsic data feature information hidden among the process data, an improved kernel principal component analysis (KPCA) method is proposed, which referred as deep (DePCA). Specifically, motivated by learning strategy, we design a hierarchical statistical model structure extract multilayer features, including both linear and nonlinear components. To reduce computation complexity in extraction, feature-samples' selection technique applied build sparse for DePCA....
A system for automatic gait recognition without segmentation of particular body parts is described. Eigenspace transformation (EST) has already proved useful several tasks including face recognition, analysis, etc; it optimal in dimensionality reduction by maximising the total scatter all classes but not class separability. statistical approach that combines EST with canonical space (CST) proposed using temporal templates from a sequence as features. This method can be used to reduce data...
A Fourier transform spectrometer designed to operate at high resolution wavelengths down 170 nm is described. The principal instrumental parameters are: mirror travel, 200 mm; resolving limit, 0.025 cm-1; collimator aperture ratio, f/25; overall dimensions of vacuum tank, 1.5 m*0.25 m. Test results show (i) a signal-to-noise ratio in the transformed spectrum better than 1000:1 for an iron-neon hollow cathode lamp power quarter million, (ii) fully resolved line profiles same source limit 0.03...
407 Background: The role of post nephro-ureterectomy (NU) treatment for UTUC is unclear. POUT (CRUK/11/027; NCT01993979) addresses whether adjuvant chemotherapy improves disease free survival (DFS) pts with histologically confirmed pT2-T4 N0-3 M0 UTUC. Methods: Pts (max n = 345) ≤90 days NU were randomised (1:1) to 4 cycles gemcitabine-cisplatin (gemcitabine-carboplatin if GFR 30-49ml/min) or surveillance subsequent required. had 6 monthly cross sectional imaging and cystoscopy the first 2...
Sodium-ion batteries (SIBs) are promising power sources due to the low cost and abundance of battery-grade sodium resources, while practical SIBs suffer from intrinsically sluggish diffusion kinetics severe volume changes electrode materials. Metal-organic framework (MOFs) derived carbonaceous metal compound offer applications in materials their tailorable composition, nanostructure, chemical physical properties. Here, we fabricated hierarchical MOF-derived nickel selenides with bi-phase...