A5100338862- Anomaly Detection Techniques and Applications
- Machine Learning and Data Classification
- Face and Expression Recognition
- Data Visualization and Analytics
- Synthesis and Biological Evaluation
- Software Engineering Research
- Natural Language Processing Techniques
- Image Retrieval and Classification Techniques
- Click Chemistry and Applications
- Advanced Statistical Methods and Models
- Water Systems and Optimization
- Wastewater Treatment and Nitrogen Removal
- Distributed Sensor Networks and Detection Algorithms
- Odor and Emission Control Technologies
- Machine Learning and ELM
- Synthesis and Characterization of Pyrroles
- Software Engineering Techniques and Practices
- Theoretical and Computational Physics
- Machine Fault Diagnosis Techniques
- Machine Learning in Healthcare
- Machine Learning and Algorithms
- Graph Theory and Algorithms
- Neural Networks and Applications
- Ion Channels and Receptors
- Multimodal Machine Learning Applications
Zhejiang University
2013-2024
Yanshan University
2024
Dalian University of Technology
2022
Arizona State University
2016
Hangzhou Xixi hospital
2015
Pharmaceutical Biotechnology (Czechia)
2015
China University of Geosciences (Beijing)
2012
National University of Singapore
1998
A simple, multicomponent, and straightforward reaction of vinyl azide, aldehyde, tosylhydrazine affords the construction 3,4,5-trisubstituted 1H-pyrazoles regioselectively in presence base with moderate to excellent yields. range functionality could be tolerated this methodology, a possible mechanism is proposed.
Proper feature selection for unsupervised outlier detection can improve performance but is very challenging due to complex interactions, the mixture of relevant features with noisy/redundant in imbalanced data, and unavailability class labels. Little work has been done on this challenge. This paper proposes a novel Coupled Unsupervised Feature Selection framework (CUFS short) filter out noisy or redundant subsequent categorical data. CUFS quantifies outlierness (or relevance) by learning...
Substrate-controlled reactions have been developed for the synthesis of spirocyclopropylpyrazolones and bicyclic 4,5-dihydropyrazoles from 1,2-diaza-1,3-dienes sulfur ylides. These protocols were carried out under mild reaction conditions without any additives in generally moderate to good yields. Plausible mechanisms transformations proposed.
Bridges play an essential role in transportation and economics. Since the loss is significant event of bridge damage, monitoring structure health important. One important tasks anomaly detection. The detection a challenging problem since real-world data collected by sensors are usually contaminated large non-Gaussian noises. To address this issue, we propose correntropy-induced weighted generative adversarial network (CWGAN) for Specifically, first correntropy-based generator, which has...
GPS-based taxi trajectories contain valuable knowledge about movement patterns for transportation and urban planning. Topic modeling is an effective tool to extract semantic information from trajectory data. However, previous methods generally ignore directions that are important in the analysis of patterns. In this paper, we employ bigram topic model rather than traditional models analyze textualized consider direction trajectories. We further propose a modified Apriori algorithm topical...
A simple and direct synthesis of functionalized imidazoles from α-nitro-epoxides amidines was developed.
Anomaly detection is widely used in many fields to reveal the abnormal process of a system. Typical model-based anomaly methods work well general problems. However, some application-specific scenarios, anomalies interest are "direction-related," that is, only deviation certain directions data space abnormal. Most existing do not these especially when there no information during training. Considering real applications such as medical disease and industrial device faults diagnosis, normal have...
Ordinal regression methods are widely used to predict the ordered labels of data, among which support vector ordinal (SVOR) popular because their good generalization. In many realistic circumstances, data collected by a distributed network. order protect privacy or due some practical constraints, cannot be transmitted center for processing. However, as far we know, existing SVOR all centralized. above situations, centralized inapplicable, and more suitable choices. this paper, propose...
Multilingual neural machine translation aims to translate multiple language pairs in a single model and has shown great success thanks the knowledge transfer across languages with shared parameters. Despite promising, this share-all paradigm suffers from insufficient ability capture language-specific features. Currently, common practice is insert or search networks balance specific However, those two types of features are not sufficient enough complex commonality divergence languages, such...