A5041611973- Scheduling and Optimization Algorithms
- Cloud Computing and Resource Management
- Advanced Manufacturing and Logistics Optimization
- Distributed and Parallel Computing Systems
- IoT and Edge/Fog Computing
- Assembly Line Balancing Optimization
- Hydraulic Fracturing and Reservoir Analysis
- Optimization and Search Problems
- Plasma Diagnostics and Applications
- Reservoir Engineering and Simulation Methods
- Metaheuristic Optimization Algorithms Research
- Advanced Computational Techniques and Applications
- Mobile Agent-Based Network Management
- Image and Signal Denoising Methods
- Drilling and Well Engineering
- Optimization and Packing Problems
- Oil and Gas Production Techniques
- Advanced Control Systems Optimization
- Service-Oriented Architecture and Web Services
- Neural Networks and Applications
- Collaboration in agile enterprises
- Vehicle License Plate Recognition
- Blockchain Technology Applications and Security
- Advanced Algorithms and Applications
- Advanced Image and Video Retrieval Techniques
Guangdong University of Technology
2024-2025
Inner Mongolia University
2023-2024
Beijing Institute of Technology
2004-2024
Xidian University
2014-2024
Southeast University
2015-2024
Southwest University of Science and Technology
2021-2024
Shenzhen University
2024
Xi'an Jiaotong University
2014-2024
Guangxi University of Science and Technology
2007-2024
Chongqing University
2011-2024
An automatic electroencephalogram (EEG) artifact removal method is presented in this paper. Compared to past methods, it has two unique features: 1) a weighted version of support vector machine formulation that handles the inherent unbalanced nature component classification and 2) ability accommodate structural information typically found classification. The advantages proposed are demonstrated on real-life EEG recordings with comparisons made several benchmark methods. Results show...
Feature selection is important in both machine learning and pattern recognition. Successfully selecting informative features can significantly increase accuracy improve result comprehensibility. Various methods have been proposed to identify from high-dimensional data by removing redundant irrelevant classification accuracy. In this article, we systematically survey existing sparse models for feature the perspectives of individual group selection, analyze differences connections among...
Feature selection (FS) for classification is crucial large-scale images and bio-microarray data using machine learning. It challenging to select informative features from high-dimensional which generally contains many irrelevant redundant features. These often impede classifier performance misdirect tasks. In this article, we present an efficient FS algorithm improve accuracy by taking into account both the relevance of pairwise correlation in regard class labels. Based on conditional mutual...
Abstract 2D second‐order topological insulators (SOTIs) have sparked significant interest, but currently, the proposed realistic materials for SOTIs are limited to nonmagnetic systems. In this study, first time, a single layer of chalcogenide CrSiTe 3 —an experimentally realized transition metal trichalcogenide is with structure—as ferromagnetic (FM) SOTI. Based on first‐principles calculations, study confirms that monolayer exhibits nontrivial gapped bulk state in spin‐up channel and...
To overcome some drawbacks of the plasma stealth technology in real-life application, a practical multilayer structure composed enclosed slab and radar absorbing material (RAM) is presented this paper. Based on technique referred to as transmission line analogy method, reflection coefficients perpendicularly polarized wave, parallel circularly wave obliquely incident upon are determined, respectively. The effects angle, kinds RAMs, parameters including electron density, collision frequency,...
In XaaS clouds, resources as services (e.g., infrastructure, platform and software a service) are sold to applications such scientific big data analysis workflows. Candidate with various configurations (CPU type, memory size, number of machines so on) for the same task may have different execution time cost. Further, some priced rented by intervals that be shared among tasks workflow save service rental Establishing task-mode (service) mapping (to get balance between cost) tabling on...
Electricity prices differ during different time periods and change from place to place. Cloud workflow applications often require geo-distributed data which is transmitted among heterogeneous servers in intra- inter- centers. Such varying electricity transmission bring great challenges when optimizing the energy cost for scheduling tasks cloud In this article, we minimize total a deadline constrained energy-aware problem with being geographically distributed across A algorithm proposed....
Assessing the performance of Pareto front (PF) approximations is a key issue in field evolutionary multi/many-objective optimization. Inverted generational distance (IGD) has been widely accepted as indicator for evaluating comprehensive quality PF approximation. However, IGD usually becomes infeasible when facing real-world optimization problem it needs to know true priori. In addition, time complexity grows quadratically with size solution/reference set. To address aforementioned issues,...
This paper presents a new wrapper-based feature selection method for multilayer perceptron (MLP) neural networks. It uses ranking criterion to measure the importance of by computing aggregate difference, over space, probabilistic outputs MLP with and without feature. Thus, score respect every can be provided using this criterion. Based on numerical experiments several artificial real-world data sets, proposed performs, in general, better than selected methods MLP, particularly when set is...
We consider a special workflow scheduling problem in hybrid-cloud-based management system which tasks are linearly dependent, compute-intensive, stochastic, deadline-constrained and executed on elastic distributed cloud resources. This kind of problems closely resemble many real-time workflow-based applications. Three optimization objectives explored: number, usage time utilization rented VMs. An iterated heuristic framework is presented to schedule jobs event by mainly consists job...