A5080652607- Software Engineering Research
- Advanced Malware Detection Techniques
- Chinese history and philosophy
- Network Security and Intrusion Detection
- Software Reliability and Analysis Research
- Software System Performance and Reliability
- Information and Cyber Security
- Software Testing and Debugging Techniques
- Advanced Decision-Making Techniques
- Complex Network Analysis Techniques
- Railway Engineering and Dynamics
- Structural Engineering and Vibration Analysis
- Anomaly Detection Techniques and Applications
- Nonlinear Waves and Solitons
- Nonlinear Photonic Systems
- Internet Traffic Analysis and Secure E-voting
- Civil and Geotechnical Engineering Research
- Advanced Computational Techniques and Applications
- Web Application Security Vulnerabilities
- Medieval and Classical Philosophy
- Religious Studies and Spiritual Practices
- Heat Transfer and Optimization
- Advanced Software Engineering Methodologies
- Orbital Angular Momentum in Optics
- Digital and Cyber Forensics
China Pharmaceutical University
2014-2024
Guangdong Polytechnic Normal University
2016-2024
Beijing Institute of Technology
2014-2024
Institute of Software
2016-2017
National Center for Drug Screening
2014
Southwest Jiaotong University
2012-2013
Hunan City University
2013
China University of Political Science and Law
2006-2012
Tianjin University
2010-2012
Institute of Philosophy
2005
In recent years, advanced threat attacks are increasing, but the traditional network intrusion detection system based on feature filtering has some drawbacks which make it difficult to find new in time. This paper takes NSL-KDD data set as research object, analyses latest progress and existing problems field of technology, proposes an adaptive ensemble learning model. By adjusting proportion training setting up multiple decision trees, we construct a MultiTree algorithm. order improve...
Due to the rapid rise of automated tools, number malware variants has increased dramatically, which poses a tremendous threat security Internet. Recently, some methods for quick analysis have been proposed, but these usually require large computational overhead and cannot classify samples accurately large-scale complex data set. Therefore, in this paper, we propose new visualization method characterizing globally locally achieve fast effective fine-grained classification. We take approach...
Under the present study, we focus on developing some exact solutions of (3 + 1)-dimensional generalized Kudryashov-Sinelshchikov equation (KSE) for liquid with gas bubbles. First, resonant soliton molecules different planes are extracted via imposing velocity resonance condition N-soliton that constructed Hirota bilinear method. Besides, asymmetric solitons also derived by choosing appropriate parameters. In end, diverse kinds travelling wave including bright wave, dark singular and periodic...
Malware threats and privacy protection are two of the biggest challenges in cloud computing environment. Many studies have focused on accuracy malware detection, but they did not sufficiently take into account tenants. This paper proposes a novel detection model, based semi-supervised transfer learning (SSTL) for cloud, that consists prediction, components. To protect tenants public byte classifier recurrent neural network (RNN) its component is designed to detect malware. However, because...
The advent of unmanned aerial vehicle (UAV) swarm technology brings possibilities to help humans complete tasks in no man's land, such as deserts and rainforests. However, UAV network faces many cyber threats, where attackers can impersonate legitimate entities or tamper with task data. For identity security, most the existing methods use centralized authentication schemes, which have a single point failure problem. data only secure ground system, ignoring security air network. Therefore,...
The nanofluids (including MWCNT based nanofluid and SWCNT nanofluid) liquid metal Ga68In20Sn12 are proposed to replace the conventional water as cooling of micro-channel for enhancing heat transfer performance three-dimensional integrated circuits (3-D ICs) in this paper. An equivalent thermal model 3-D ICs with is established investigate performances using different liquids. results show that steady-state temperature nanofluid, liquids can be reduced over 25.698%, 28.771% 35.735% than...
This paper proposed a new heat dissipation structure with embedded both through silicon vias (TSVs) and micro-channels to solve the complex problems of three-dimensional integrated circuits (3D-ICs). The COMSOL simulation model is established investigate characteristics steady-state response for defined four cases. results show that our (i.e., case 4: 3D-ICs TSVs micro-channels) can reduce temperature over 43.546%, 18.440% 12.338% in comparison 1 without structure), 2 only inserted TSVs) 3...
Defect distribution prediction is a meaningful topic because software defects are the fundamental cause of many attacks and data loss. Building accurate models can help developers find bugs prioritize their testing efforts. Previous researches focus on exploring different machine learning algorithms based features that encode characteristics programs. The problem redundancy exists in defect set, which has great influence effect. We propose model (Deep belief network model, DBNPM), system for...
A recent study namely software defect prediction model based on Local Linear Embedding and Support Vector Machines (LLE-SVM) has indicated that Regression (SVR) an interesting potential in the field of prediction. However, parameters optimization LLE-SVM is computationally expensive by using grid search algorithm, resulting a lower efficiency model; it ignores imbalance data sets when SVM classier to differentiate defective class non-defective class. Thus accuracy. To solve these problems...
During the prediction of software defect distribution, data redundancy caused by multi-dimensional measurement will lead to decrease accuracy. In order solve this problem, paper proposed a novel model based on neighborhood preserving embedded support vector machine (NPE-SVM) algorithm. The uses SVM as basic classifier distribution model, and NPE algorithm is combined keep local geometric structure unchanged in process dimensionality reduction. problem precision reduction loss after attribute...
Software defect prediction technology mainly relies on machine learning algorithm to learn the measurement data of existing software. There is some redundant in element software defect, which will reduce accuracy algorithm. This paper proposes a model based KPCA-SVM.First, dimension reduction pretreatment sets carried out.Then, using support vector machines for classification.The can be improved by keeping global features selection algorithm.Therefore, kernel principal component analysis...
Cloud native application is especially susceptible to layer DDoS attack. This attributes the internal service calls, by which microservices cooperate and communicate with each other, amplifying effect of Since different services have varying degrees sensitivity an attack, a sophisticated attacker can take advantage those expensive API calls produce serious damage availability applications ease. To better analyze severity mitigate attacks in cloud applications, we propose novel method...
Aiming at the test data generation, which is one of key issues in network protocol fuzzing, this paper presents a new method on basis classification tree and heuristic operator. The firstly builds up divided into 4 layers: target protocol, fields, attributes belonging to all attribute values. In order reduce scale fuzz testing data, operators are defined remove useless items from value sets attributes. And then for each field was obtained by doing Cartesian product between finally generated...
Enzalutamide (ENZ) is a second-generation androgen receptor (AR) antagonist used for the treatment of castration-resistant prostate cancer (CRPC) and reportedly prolongs survival time within year starting therapy. However, CRPC patients can develop ENZ resistance (ENZR), mainly driven by abnormal reactivation AR signaling, involving increased expression full-length (ARfl) or dominantly active splice variant 7 (ARv7) ARfl/ARv7 heterodimers. There currently no efficient ENZR in CRPC. Herein,...