A5101497185- Topic Modeling
- Collaboration in agile enterprises
- Language, Metaphor, and Cognition
- Natural Language Processing Techniques
- Energy Efficient Wireless Sensor Networks
- Network Security and Intrusion Detection
- Advanced Text Analysis Techniques
- Semantic Web and Ontologies
- Lightning and Electromagnetic Phenomena
- Industrial Technology and Control Systems
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Software System Performance and Reliability
- Explainable Artificial Intelligence (XAI)
- Vacuum and Plasma Arcs
- Software Engineering Research
- Security in Wireless Sensor Networks
- Advanced Graph Neural Networks
- Fire effects on ecosystems
- Sentiment Analysis and Opinion Mining
- Imbalanced Data Classification Techniques
- Service-Oriented Architecture and Web Services
- Cryptography and Data Security
- Color perception and design
- Biomedical Text Mining and Ontologies
Xinjiang University of Finance and Economics
2023
Ningbo University
2006-2022
First Affiliated Hospital of Hebei Medical University
2022
Ping An (China)
2020-2021
University of Shanghai for Science and Technology
2017-2020
University College Dublin
2008-2019
China Electric Power Research Institute
2012-2014
North China Electric Power University
2012-2014
Korea Advanced Institute of Science and Technology
2013-2014
Central South University
2010
This report summarizes the objectives and evaluation of SemEval 2015 task on sentiment analysis figurative language Twitter (Task 11).This is first wholly dedicated to analyzing Twitter.Specifically, three broad classes are considered: irony, sarcasm metaphor.Gold standard sets 8000 training tweets 4000 test were annotated using workers crowdsourcing platform CrowdFlower.Participating systems required provide a fine-grained score an 11-point scale (-5 +5, including 0 for neutral intent) each...
Adversarial machine learning is a fast growing research area, which considers the scenarios when systems may face potential adversarial attackers, who intentionally synthesize input data to make well-trained model mistake. It always involves defending side, usually classifier, and an attacking side that aims cause incorrect output. The earliest studies on examples for algorithms start from information security much wider varieties of methods. But recent focus popularized by deep community...
Wireless sensor networks (WSNs) have been pushed to the forefront in past decade, owing advert of Internet Things. Our research suggests that reliability and lifetime performance a typical application WSNs depends crucially on set parameters. In this paper, we implemented our experiments nearest closer protocol with J-Sim simulation tool. We then analyze closure relationships among density, lifetime, reveal trade-off them based analysis experiment results. Next, propose five intelligent...
The next-generation network (6G) has more strict requirements for the online learning ability and high interpretability of learned systems. Machine is expected to be essential assist in making networks efficient adaptable, but most promising methods often are treated as "black boxes" due deep structures nonlinearity. Therefore, this article attempts study interpretations machine algorithms make them applicable 6G-enabled Internet things (IoT) networks. Typically, focuses on new model...
Concept taxonomies offer a powerful means for organizing knowledge, but this organization must allow many overlapping and fine-grained perspectives if general-purpose taxonomy is to reflect concepts as they are actually employed reasoned about in everyday usage. We present here of bootstrapping finely-discriminating from variety different starting points, or seeds, that acquired three sources: WordNet, ConceptNet the web at large.
Introspection is a question-led process in which one builds on what already knows to explore possible and plausible. In creative introspection, whether art or science, framing the right question as important finding answer. Presupposition-laden questions are themselves source of knowledge, this paper we show how widely-held beliefs about world can be dynamically acquired by harvesting such from Web. We metaphorical reasoning modeled an introspective process, that harvested Web pose further...
Risk control has always been a major challenge in finance. Overdue repayment is frequently encountered discreditable behavior online lending. Motivated by the powerful capabilities of deep neural networks, we propose fusion learning approach, namely AD-MBLSTM, based on network (DNN), multi-layer bi-directional long short-term memory (LSTM) (BiLSTM) and attention mechanism for overdue forecasting according to historical records. Furthermore, present novel feature derivation selection method...
The age of Internet things gives rise to more challenges various secure demands when designing the protocols, such as object identification and tracking, privacy control. In many current a malicious server may cheat users if it was legal server, making vital verify legality both servers with help trusted third-party, registration center. Li et al. proposed an authentication protocol based on dynamic identity for multi-server environment, which is still susceptible password-guessing attack,...
Twitter is an intriguing source of topical content for tasks involving the detection phenomena such as sarcasm and metaphor. The hashtags that users employ to self-annotate their own micro-texts can often facilitate targeted retrieval texts with desired characteristics. Though tweets tagged #sarcasm are highly likely be sarcastic, lack a topic model sarcastic makes it difficult detect when tags used in expected way, or indeed, retrieve not explicitly this way. In study, we explore how...
According to the working characteristics of over-voltage protective device for series compensation, principle and structure spark switch were introduced in this paper briefly. Special test loop HV fast switch-off designed evaluate performance swich trials. Test data mathematic statistic results revealed that self-breakdown probability obeyed normal distribution cumulative had been less affected by different enviroment temperature. The number trials was restricted insulated gas electrode...