A5100333975- Advanced Computational Techniques and Applications
- Complexity and Algorithms in Graphs
- Natural Language Processing Techniques
- Topic Modeling
- Algorithms and Data Compression
- Data Management and Algorithms
- Lexicography and Language Studies
- Dyeing and Modifying Textile Fibers
- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Advanced Database Systems and Queries
- Digital Media and Visual Art
- Data Quality and Management
- Safety and Risk Management
- Machine Learning in Healthcare
- Advanced Steganography and Watermarking Techniques
- Bayesian Methods and Mixture Models
- Sustainable Urban and Rural Development
- Text and Document Classification Technologies
- Artificial Intelligence in Games
- Graph Theory and Algorithms
- Machine Learning and Algorithms
- Machine Learning and ELM
- Data Mining Algorithms and Applications
- Metaheuristic Optimization Algorithms Research
Dalian University of Technology
2023
Shanghai Micro Satellite Engineering Center
2023
Northeast Forestry University
2022
Wuhan University
2009-2014
Beijing University of Posts and Telecommunications
2011-2013
Yuxi Normal University
2007-2010
Xi'an University of Science and Technology
2010
Taishan Medical University
2010
Wuhan University of Technology
2009
Neijiang Normal University
2007
Dynamic searchable symmetric encryption (DSSE) allows efficient searches over encrypted databases and also supports clients in their updating of the data, such as those stored a remote cloud server. However, recent attacks suggest risk leakage during updates, which consequently impacts on privacy queries. In addition, existing DSSE schemes that support forward generally rely honest-but-curious server only single-keyword retrieval, limits application scenarios. this paper, we present design...
This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.
Knowledge of the medical decision process, which can be modeled as trees (MDTs), is critical to build clinical support systems. However, current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, explore automatic extraction MDTs from texts such guidelines textbooks. We normalize form create an annotated Text-to-MDT dataset in Chinese with participation experts. investigate two different for Text2MDT...
Based on differential evolution algorithm and the concept of multi-objective optimization, a for constrained optimization problem based constraint handling is proposed in this paper. This can achieve global search local effectively by using algorithm. For problems, paper presents new comparison mechanism Pareto optimal solution. The grades solutions, feasible solutions infeasible are prescribed enable them to be selected at different probabilities during evolutionary process, which lead...
Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches been proposed address this problem. Among them, one solution is diversify training distributions vanilla by modifying the data environment, yet accessing environment information complex. Besides, another promising approach involves rationalization, extracting invariant rationales for...
Knowledge modeling, acquisition, and proper use are crucial for successful computer playing of the game GO. This paper presents a systematic approach knowledge representations GO-playing in which meaning move is defined as contextual pattern with respect to local contexts surroundings move. representation allows large amounts patterns, along their usage statistics, be acquired efficiently from records. Contextual patterns that appear jointly may form collocation, its significance measured by...
For resolving the vehicle routing problem with time windows (VRPTW), a decision support model based on hybrid algorithm of particle swarm optimization (PSO) and ant colony (ACO) developed to minimize transportation costs for product delivery is discussed in this paper. We discuss adaptation VRPTW provide group experiments show effectiveness algorithm. Experiment results indicate that new can effectively quickly get optimal resolution.
High performance analysis and processing technology of load data is an important basic situation awareness in the context power Internet things. Under this background, a high deep learning classification method for massive class imbalanced presented. Firstly, mogrifier long short-term memory (Mogrifier-LSTM) network presented as algorithm to solve deficiency information interaction between input layer hidden traditional LSTM. In addition, attention mechanism bidirectional feature fusion are...
We investigate the approximation for computing sum $a_1+...+a_n$ with an input of a list nonnegative elements $a_1,..., a_n$. If all are in range $[0,1]$, there is randomized algorithm that can compute $(1+\epsilon)$-approximation problem time ${O({n(\log\log n)\over\sum_{i=1}^n a_i})}$, where $\epsilon$ constant $(0,1)$. Our based on uniform random sampling, which selects one element equal probability from each time. also prove lower bound $\Omega({n\over \sum_{i=1}^n a_i})$, almost matches...