http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : ( Shengwei Tian ) (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
Complete loss distribution model of GaN HEMTs considering the influence of parasitic parameters
Shengwei Gao,Jinrui Tian,Xiaoyu Fu,Yongxiao Li,Bo Wang,Lixia Zhao 전력전자학회 2024 JOURNAL OF POWER ELECTRONICS Vol.24 No.1
When compared with Si-based devices, Gallium Nitride High Electron Mobility Transistors (GaN HEMTs) possess the advantages of lower junction-to-case thermal resistance, smaller on-state resistance, faster switching velocity, and higher switching frequency. These advantages make them a promising power semiconductor device. However, with the enhancement of switching frequencies, the influence of parasitic parameters on switching ringing and the losses of GaN HEMTs are increasingly severe. Thus, it is necessary to predict the loss distribution by establishing an accurate loss model of the switching process. On the premise of considering parasitic inductance, nonlinear junction capacitance, and reverse transfer characteristics, this article proposes a precise switching loss model of GaN HEMTs to predict the loss distribution in the switching process. In addition, it verifies results based on the double pulse test (DPT) circuit, which validates the accuracy of the proposed model. Ultimately, based on the above-mentioned loss model, this article discussed the influence of parasitic capacitance and inductance on the output capacitance loss (Eqoss), the reverse conduction loss (ESD), the opening V-I overlap loss (Eopen), the closing V-I overlap loss (Eclose), and the total loss (Etotal). Then, this article produces an optimizing method to enhance the conversion efficiency of GaN HEMTs in accordance with laboratory findings.
-
Android malicious code Classification using Deep Belief Network
( Luo Shiqi ),( Tian Shengwei ),( Yu Long ),( Yu Jiong ),( Sun Hua ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.1
This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.
-
MALICIOUS URL RECOGNITION AND DETECTION USING ATTENTION-BASED CNN-LSTM
( Yongfang Peng ),( Shengwei Tian ),( Long Yu ),( Yalong Lv ),( Ruijin Wang ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.11
A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.
-
Robust Visual Tracking Integrating Spatio-Temporal Model
Min Jiang,Jiao Wu,Jun Kong,Chenhua Liu,Shengwei Tian 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.10
Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency. However, the CT extracts samples around the previous target region within a fixed search radius; the searching area is unsuitable when the target undergoes abrupt acceleration change. Meanwhile, the classifier learns the features of the target online without judgment even the target is fully occluded. Thus, the improper searching area and incorrectly updated features lead to a marked drop in precision of tracking. To solve this issue, a robust target tracking method integrating spatio-temporal model to constrain the searching area is proposed in this paper. Different from CT, the proposed method initially constructs the spatio-temporal model to calculate a confidence map between consecutive frames, and the region with high confidence suggests the high possibility that target exists. Thus the samples can be extracted in the high confidence area. Then, the optimal target location can be estimated with a naive Bayes classifier using sparse coding features. Experiments show that the proposed method outperforms several competing methods in efficiency and robustness.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
