A5081745865- Forensic Entomology and Diptera Studies
- Diptera species taxonomy and behavior
- Insect behavior and control techniques
- Insect and Pesticide Research
- Coleoptera Taxonomy and Distribution
- Reinforcement Learning in Robotics
- Hymenoptera taxonomy and phylogeny
- Body Image and Dysmorphia Studies
- Animal Ecology and Behavior Studies
- Yersinia bacterium, plague, ectoparasites research
- Artificial Intelligence in Games
- Network Security and Intrusion Detection
- Insect-Plant Interactions and Control
- Insect symbiosis and bacterial influences
- Recommender Systems and Techniques
- Forest Ecology and Biodiversity Studies
- Insect Utilization and Effects
- Bacillus and Francisella bacterial research
- Fossil Insects in Amber
- Hemiptera Insect Studies
- Plant and Fungal Species Descriptions
- Access Control and Trust
- Digital Imaging for Blood Diseases
- Lepidoptera: Biology and Taxonomy
- Nonlinear Dynamics and Pattern Formation
Changzhou University
2023-2024
Shenyang Normal University
2012-2024
Nanyang Technological University
2021-2024
National University of Singapore
2019-2020
Xi'an Jiaotong University
2020
Institute of Entomology
1993-2014
Shenyang Institute of Engineering
2009
Shenyang Center for Disease Control and Prevention
2008
Shenyang University
2002
Advanced Network and Services (United States)
1984-1992
Nine new species of Helina annosa-group from China, namely H. longievecta sp. nov, longisurstyla midmargiseta nigriabdomilis nivimonta setosiannosa shii subfloscula nov. and subnigriabdomilis are described illustrated. Diagnosis this group, a key distributions the also given.http://www.zoobank.org/urn:lsid:zoobank.org:pub:3516C15F-F4AA-4391-B944-84556792CC83
Five new species of Phaonia are described from China, namely P. sunqiia Xue & Du sp. nov., zhangjunyui liujiayui wangpingga nov. and tianmushanensis The available keys to the three species-groups where belong were updated.
Sarcophaga (Hoa) membranijuxta sp. nov. is described from the Chinese provinces Guangxi and Hainan documented with illustrations, photographs scanning electron microscopy images. The habitus male terminalia of basiseta Baranov, 1931 are for first time, circumscription distribution subgenus Hoa Rohdendorf, 1937 updated.
One-shot image classification aims to train classifiers over the dataset with only one per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images class. In this paper, we adopt metric learning problem, which has been applied few- and many-shot by comparing distance between test center each class in feature space. However, one-shot learning, existing approaches would suffer poor performance because single training may not be...
Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading. Especially, intraday is one of the most profitable risky tasks because behaviors financial market that reflect billions rapidly fluctuating capitals. However, a vast majority existing RL methods focus on relatively low frequency scenarios (e.g., day-level) fail to capture fleeting investment opportunities due two major...
The complexity of designing reward functions has been a major obstacle to the wide application deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new paradigm called from human preferences (or preference-based RL) emerged as promising solution, in which are learned preference labels among behavior trajectories. However, existing methods RL limited by need accurate oracle labels. This paper addresses this...
Pursuit-evasion games on graphs model the coordination of police forces chasing a fleeing felon in real-world urban settings, using standard framework imperfect-information extensive-form (EFGs). In recent years, solving EFGs has been largely dominated by Policy-Space Response Oracle (PSRO) methods due to their modularity, scalability, and favorable convergence properties. However, even these quickly reach limits when facing large combinatorial strategy spaces pursuit-evasion games. To...
This paper provides the characters of genus Limnophora (Diptera: Muscidae) and a key to Chinese species Limnophora, six new collected from Hainan Island China, namely, L. brevispatula, n. sp., cothurnosurstyla, dyadocerca, longitarsis, nuditibia, sp. ypocerca, are diagnosed, described illustrated, record in argentifrons (Shinonaga et Kano, 1977), is also included.
The global rising trend of consumer health awareness has increasingly drawn attention towards the development nutrition tracking applications. A key component to enable large scale, low cost and personalized analysis is a food image recognition engine based on convolutional neural network (CNN). While there strong demand for many variants such applications serve different localized needs around world, it remains an ongoing challenge piece together complete solution involving (i) dataset...
Securing networked infrastructures is important in the real world. The problem of deploying security resources to protect against an attacker domains can be modeled as Network Security Games (NSGs). Unfortunately, existing approaches, including deep learning-based are inefficient solve large-scale extensive-form NSGs. In this paper, we propose a novel learning paradigm, NSG-NFSP, NSGs based on Neural Fictitious Self-Play (NFSP). Our main contributions include: i) reforming best response (BR)...
Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that coordination can be greatly improved by allowing communication between agents. Meanwhile, adversarial machine (ML) has shown ML models are vulnerable to attacks. Despite the increasing concern about robustness of algorithms, how achieve robust been largely neglected. In this paper, we systematically explore problem MACRL. Our main contributions threefold. First, propose an effective method...
How resources are deployed to secure critical targets in networks can be modelled by Network Security Games (NSGs). While recent advances deep learning (DL) provide a powerful approach dealing with large-scale NSGs, DL methods such as NSG-NFSP suffer from the problem of data inefficiency. Furthermore, due centralized control, they cannot scale scenarios large number resources. In this paper, we propose novel DL-based method, NSGZero, learn non-exploitable policy NSGs. NSGZero improves...
Long-term engagement is preferred over immediate in sequential recommendation as it directly affects product operational metrics such daily active users (DAUs) and dwell time. Meanwhile, reinforcement learning (RL) widely regarded a promising framework for optimizing long-term recommendation. However, due to expensive online interactions, very difficult RL algorithms perform state-action value estimation, exploration feature extraction when engagement. In this paper, we propose ResAct which...
Abstract This paper deals with the taxonomy of Helina Robineau-Desvoidy, 1830 from China. Three new species, namely H. cynocercata, sp. nov., subhirtisurstyla, nov. and xianggelilaensis, four junior synonyms, i.e., dehiscideleta Xue & Li, 2002, syn. for paomashana Feng, 2000; jianchangensis Ma, 1981, intermedia (Villeneuve, 1899); rariciliata Wu, 1989, annosa (Zetterstedt, 1838); subeiensis Ma Wang, 1992, bohemani Ringdahl, 1916 are established. An original key to identify known 162 Chinese...
Four new species of Mydaeinae, Mydaea franzosternita n. sp., Myospila apicaliciliola maoershanensis and subflavipennis are described illustrated here for the first time. A key to genus Mydaeinae from China keys genera provided.