检索结果-内蒙古大学图书馆

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Wang, Jingjing Huang, Minhuan Nie, Yuanping Li, Jin National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9780738131702

With the rapid increase of practical problem complexity and code scale, the threat of software security is increasingly serious. Consequently, it is crucial to pay attention to the analysis of software source code vulnerability in the development stage and take efficient measures to detect the vulnerability as soon as possible. Machine learning techniques have made remarkable achievements in various fields. However, the application of machine learning in the domain of vulnerability static analysis is still in its infancy and the characteristics and performance of diverse methods are quite different. In this survey, we focus on a source code-oriented static vulnerability analysis method using machine learning techniques. We review the studies on source code vulnerability analysis based on machine learning in the past decade. We systematically summarize the development trends and different technical characteristics in this field from the perspectives of the intermediate representation of source code and vulnerability prediction model and put forward several feasible research directions in the future according to the limitations of the current approaches. © 2021 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Detecting Adversarial Samples in Neural Network with Statistical Metrics: A Practical Approach 6

Detecting Adversarial Samples in Neural Network with Statist...

引用

6th IEEE International Conference on Data science in Cyberspace, DSC 2021

作者： Kong, Wei Cao, Huayang Tian, Jianwen Kuang, Xiaohui National Key Laboratory Of Science And Technology On Information System Security Beijing China

ISBN: (纸本)9781665418157

The inherent vulnerability of deep learning systems, which is subject to adversarial attacks, limits its application in the safety-critical domain such as automatic driving, military application and so on. More seriously, the implementations of adversarial perturbation in the physical world are proved feasible by a considerable body of works. Hence, it is crucial to develop the capability of defense that matches adversarial attacks. In this paper, we firstly investigate various defensive methodologies and find that the detection-only approach shows its superiority in terms of robustness and efficiency when facing strong attack strategies. Next, detection approaches with different statistical metrics are presented, such as Kernel Density Estimation(KDE), Local Intrinsic Dimensionality (LID) and Neural Network Invariant Checking (NIC), to prove the hypothesis that adversarial examples can be totally detected if choose the reasonable statistical metrics. Hence, we believe that the research on finding more proper metrics is a promising and practical direction. Moreover, given the absence of a systematic evaluation framework, we proposed a threat model and evaluation criteria as the first step for evaluating various defense measures. Finally, it also remains a huge challenge and needs further researches to accomplish a trade-off between security and efficiency in this area. © 2021 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Synthesis Optimization of SSZ-13 Zeolite Membranes by Dual Templates for N_(2)/NO_(2) Separation

引用

Chemical Research in Chinese Universities 2022年第1期38卷 250-256页

作者： LI Jun RONG Huazhen CHEN Cong LI Ziyi ZUO Jiayu WANG Wenjian LIU Xinjian GUAN Yixing YANG Xiong LIU Yingshu ZOU Xiaoqin ZHU Guangshan School of Energy and Environmental Engineering University of Science and Technology BeijingBeijing 100083P.R.China Faculty of Chemistry Northeast Normal UniversityChangchun 130024P.R.China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of ChinaChengdu 610213P.R.China

High-silica SSZ-13 zeolite membranes are promising in industrial separations of light gases and continuous membranes are highly demanded for better separation performances. Herein, pure-phase, continuous and thin SSZ-13 zeolite membranes were synthesized using dual templates of N,N,N-trimethtyl-1-adamantammonium hydroxide(TMAdaOH) and tetraethylammonium hydroxide(TEAOH). systematical investigations of TMAdaOH/TEAOH ratios and their concentrations show that TMAdaOH acts as the main structure-directing agent in the formation of the SSZ-13 zeolite. TMAdaOH cooperatively plays with TEAOH in promoting the SSZ-13 crystal intergrowth to form a continuous polycrystalline membrane. Additionally, appropriate introduction of TEAOH is able to adjust the membrane thickness to the crystal-comparable size of ca. 2.0 μm. The SSZ-13 membranes are further applied for N2/NO2separation, which is firstly reported on zeolite membranes. The gas permeation results show that the SSZ-13 membrane synthesized by the dual-template approach exhibits selective separation of N2 over NO2 with N2/NO2 separation factor of 7.6 and N2 permeance of 1.66×10-8 mol·m-2·s-1·Pa-1.

关键词： Zeolite membrane Dual template SSZ-13 Gas separation Nitrogen dioxide

来源：评论

学校读者我要写书评

暂无评论

Robust Video Object Segmentation with Restricted Attention 48

Robust Video Object Segmentation with Restricted Attention

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Huaizheng Guo, Pinxue Le, Zhongwen Zhang, Wenqiang Shanghai Key Laboratory of Intelligent Information Processing China Fudan University School of Computer Science Shanghai China Fudan University Academy for Engineering and Technology Shanghai China

ISBN: (纸本)9781728163277

This paper focuses on the two problems of the similar objects distraction and the lack of robustness for unseen object categories in semi-supervised video object segmentation task. Existing methods have achieved great results on the benchmark dataset, but these two problems still have not been completely solved. We propose the Robust Video Object Segmentation With Restricted Attention (RVOSR), which can suppress the effects caused by similar objects and filter out noise confusion from other irrelevant regions. Meanwhile augmenting the semantic information of features, which makes the features more suitable for video object segmentation task. Extensive experiments demonstrate the effectiveness of our approach and achieve the state-of-the-art performance on the widely-used VOS benchmarks including DAVIS-2016 (92.1% J& F), DAVIS-2017 (86.8% J& F) and YouTubeVOS-2019 (84.8%). © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Transcranial direct current stimulation inhibits epileptic activity propagation in a large-scale brain network model

引用

science China(Technological sciences) 2023年第12期66卷 3628-3638页

作者： YU Ying FAN YuBo HAN Fang LUAN GuoMing WANG QingYun School of Engineering Medicine Beihang UniversityBeijing 100191China Beihang University Beijing Advanced Innovation Center for Biomedical EngineeringSchool of Biological Science and Medical EngineeringKey Laboratory Biomechanics&MechanobiologyMinistry of EducationBeijing 100191China College of Information Science and Technology Donghua UniversityShanghai 201620China Beijing Key Laboratory of Epilepsy Sanbo Brain HospitalCapital Medical UniversityBeijing 100069China Department of Dynamics and Control Beihang UniversityBeijing 100191China Beijing Institute of Brain Disorders Capital Medical UniversityBeijing 100069China

Transcranial direct current stimulation(tDCS)is a noninvasive technique that uses constant,low-intensity direct current to regulate brain *** studies have shown that cathode-tDCS(c-tDCS)is effective in reducing seizure frequency in patients with *** to the heterogeneity and patient specificity of seizures,patient-specific epilepsy networks are increasingly important in exploring the regulatory role of *** this study,we first set the left hippocampus,parahippocampus,and amygdala as the epileptogenic zone(EZ),and the left inferior temporal cortex and ventral temporal cortex as the initial propagation zone(PZ)to establish a large-scale epilepsy network *** we set tDCS cathode locations according to the maximum average energy of the simulated EEG signals and systematically study c-tDCS inhibitory effects on the propagation of epileptic *** results show that c-tDCS is effective in suppressing the propagation of epileptic ***,to consider the patient specificity,we set specific EZ and PZ according to the clinical diagnosis of 6 patients and establish patient-specific epileptic *** find that c-tDCS can suppress the propagation of abnormal activity in most patient-specific epileptic ***,when the PZ is widely distributed in both hemispheres,the treatment effect of c-tDCS is not ***,we propose dual-cathode *** epilepsy models with a wide distribution of PZ,it can inhibit the propagation of epileptiform activity in other nodes except EZ and PZ without increasing the tDCS current *** results provide theoretical support for the treatment of epilepsy with tDCS.

关键词： epilepsy large-scale brain network modeling transcranial direct current stimulation neural mass model

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using Bayesian Learning from a Multi-Label Data Corpus

Emotion Recognition Using Bayesian Learning from a Multi-Lab...

引用

2022 International Conference on Computing, Networking, Telecommunications and engineering sciences Applications, CoNTESA 2022

作者： Swathi, Bandi Kumar, Madapuri Rudra Riyaz Belgaum, Mohammad Alansari, Zainab G. Pulla Reddy Engineering College Computer Science and Engineering Kurnool India G Pullaiah College of Engineering and Technology Computer Science and Engineering Kurnool India Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia University of Malaya Computer System and Information Technology Kuala Lumpur Malaysia Information Technology Muscat Oman

ISBN: (纸本)9798350398014

In the digital era of information systems, emotion detection from audio signals is crucial for forensic services and operator or driver emotion monitoring in large-scale companies' safety and security. Speech is a uniquely human trait used to express and communicate one's point of view to others. Emotion recognition from speech audio signals is obtaining a presenter's emotions from the presenter's audio signal. Machine learning is used to develop emotion recognition systems, a critical research goal in current engineering research. The three main stages in speech emotion recognition are extraction of features, feature engineering, and classification. Even though powerful machine learning-based emotion identification algorithms for speech audio signals exist, the detection rate with maximum specificity and sensitivity is not scalable using most modern methods. A significant research objective is feature optimization for emotion recognition from speech audio signals. This article introduced a unique technique called Supervised Bayes Learning on Digital Features (SBL-DF). To scale its performance, the trials compared the suggested approach's performance to an earlier model depicted against a similar goal. Experiment results indicate that the proposed method for optimizing features could be used on a large scale. The reference classifiers' performance in making accurate detections with few false positives. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Study on the effect of self-heating effect of bulk acoustic wave filter on the interpolation loss in the band

引用

International Journal of Nanomanufacturing 2023年第3-4期18卷 178-188页

作者： Ruan, Bin Liu, Tingting Yang, Shaohua Huang, Qinwen Wu, Ming Shao, Weiheng School of Information Engineering Southwest University of Science and Technology No. 59 Qinglong Road Sichuan Province Mianyang621010 China Science and Technology on Reliability Physics and Application Technology of Electronic Component Laboratory China Electronic Product Reliability Environmental Testing Research Institute Guangdong Province Guangzhou510610 China Pandhus Microsystem Co. Ltd. Innovation Centre Phase 2 Room 301 Building 3 Science and Technology Business Park Sichuan Mianyang China

The self-heating effect occurs when the bulk acoustic wave filter is loaded with power, leading to the deterioration of the insertion loss. In this paper, the self-heating effect of bulk acoustic wave filters at high frequency power is investigated. A test system is built to obtain the maximum surface temperature and the insertion loss of the bulk acoustic wave filter at different power levels. The test results show that the self-heating effect causes the internal temperature of the bulk acoustic wave filter to increase further after increasing the power, resulting in the increase of the insertion loss. The test system and analysis method in this paper verify the relationship between the self-heating effect and the insertion loss, and can provide guidance for the construction of the relevant reliability test system of the bulk acoustic wave filter. Copyright © The Author(s) 2023. Published by Inderscience Publishers Ltd.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

高电容性能MXene电极对插层修饰离子的选择性

引用

science China Materials 2023年第3期66卷 974-981页

作者：胡敏敏代君陈丽红孟阿兰王磊李桂村谢海姣李镇江 School of Materials Science and Engineering Qingdao University of Science and TechnologyQingdao 266042China College of Electromechanical Engineering Qingdao University of Science and TechnologyQingdao 266042China State Key Laboratory Base of Eco-chemical Engineering College of Chemistry and Molecular EngineeringQingdao University of Science and TechnologyQingdao 266042China Hangzhou Yanqu Information Technology Co. Ltd.Hangzhou 310003China

离子插层是提高Ti_(3)C_(2)TxMXene电化学性能的有效方法之一.然而,不同的插层离子对MXene的结构和电化学性能的影响是否相同这一问题尚不清楚.本文系统研究了Li+、Na+、K+、Cs+、Zn2+、Mg2+、SO_(4)2-和OH-等一系列离子插层后的MXene... 详细信息

离子插层是提高Ti_(3)C_(2)TxMXene电化学性能的有效方法之一.然而,不同的插层离子对MXene的结构和电化学性能的影响是否相同这一问题尚不清楚.本文系统研究了Li+、Na+、K+、Cs+、Zn2+、Mg2+、SO_(4)2-和OH-等一系列离子插层后的MXene的结构特征和电化学性能.研究结果表明,插层离子的半径、电荷数和化学特性对插层效果都会产生影响.在所研究的插层剂中,由离子半径最大的一价阳离子Cs+和具有强碱性的阴离子OH-组成的插层剂CsOH对MXene具有较好的插层效果.插层后的MXene层间距增大,层间容纳了大量游离水,Ti的价态升高,片层表面有利于氧化还原反应的含O官能团增多,这都大大促进了电解液离子H+的扩散与存储.由此制备的电极的质量比电容大幅度提高,为原始MXene电极的7倍多,而且经过20,000次充放电循环后电容保持率未发生下降.本文为具有高电容性能的MXene和MXene基复合电极的合理设计和制备提供了指导.

关键词：电容性能充放电循环质量比电容电化学性能氧化还原反应离子半径复合电极电荷数

来源：评论

学校读者我要写书评

暂无评论

Color-tunable circularly polarized electroluminescence from a helical chiral multiple resonance emitter with B–N bonds

引用

science China Chemistry 2023年第9期66卷 2612-2620页

作者： Li Yuan Zhen-Long Tu Jun-Wei Xu Hua-Xiu Ni Zhi-Ping Mao Wen-Ye Xu You-Xuan Zheng State Key Laboratory of Coordination Chemistry Collaborative Innovation Center of Advanced MicrostructuresJiangsu Key Laboratory of Advanced Organic MaterialsSchool of Chemistry and Chemical EngineeringNanjing UniversityNanjing 210023China Shenzhen Institute of Information Technology Shenzhen 518172China School of Materials and Energy University of Electronic Science and Technology of ChinaChengdu 611731China Guangzhou Research&Creativity Biotechnology Co.Ltd. Guangzhou 510700China

Chiral B,N-doped polycyclic aromatic hydrocarbons with circularly polarized luminescence(CPL) and small full-width at halfmaxima(FWHM) are promising multiple resonance(MR) emitters for CP organic light-emitting diodes(CP-OLEDs).This work presents a pair of chiral MR enantiomers,P/M-o[B-N]_(2)N_(2),featuring B–N bonds incorporated within a[7]-helicene *** enantiomers exhibit narrow 0-0 and 0-1 electronic transition bands,whose relative intensity can be fine-tuned by increasing doping concentrations,resulting in redshifts of the emission peak from 542 to 592 *** enantiomers show mirrorsymmetric CPL spectra with an asymmetry factor(|g_(PL)|) of 1.0×10^(-3).The hyperfluorescent CP-OLEDs with double-sensitized emitting layers display a FWHM of 33 nm,an external quantum efficiency of 25.1%,and a|g_(EL)|factor of 7.7×10^(-4).Notably,the CP-OLEDs realize color-tunable CP electroluminescence peak from 553 to 613 nm by regulating the vibrational *** work provides a novel concept for the design of helical CP-MR materials and CP-OLEDs,highlighting their potential for future applications in advanced optoelectronic devices.

关键词： chiral multiple resonance material helical chirality circularly polarized luminescence narrowband emission color-tunable circularly polarized electroluminescence

来源：评论

学校读者我要写书评

暂无评论

Study on enrichment characteristics of Chinese herbal medicine based on LIBS technology

引用

Optoelectronics Letters 2023年第2期19卷 88-94页

作者： WANG Chun LI Honglian SUN Jiaxing LüHeshuai WANG Fan ZHANG Rongxiang School of Quality and Technology Supervision Hebei UniversityBaoding 071000China National&Local Joint Engineering Research Center of Metrology Instrument and System Baoding 071002China Hebei Key Laboratory of Energy Metering and Safety Testing Technology Hebei UniversityBaoding 071002China College of Physics Science and Technology Hebei UniversityBaoding 071002China

To improve the accuracy of laser induced breakdown spectroscopy(LIBS) measurement and investigate the enrichment characteristics of trace elements in different parts of Chinese herbal medicine, the original spectral data of different Chinese herbal medicines were preprocessed by combining median absolute deviation(MAD), segmented feature extraction, and wavelet denoising, and the enrichment laws of trace elements in different parts of Chinese herbal medicine were studied based on the calibration free laser induced breakdown spectroscopy(CF-LIBS). For these experimental samples, the contents of K, Ca, Mg, and Fe in chrysanthemum and its roots, stems, and leaves, Iris lactea roots and leaves, Salvia miltiorrhiza and corresponding planting soil were obtained by CF-LIBS. By calculating the element enrichment coefficient, it was found that chrysanthemum had strong enrichment ability of K element, and the enrichment ability of K element was flower > leaf > stem > root. The roots and leaves of Iris lactea showed strong enrichment of Ca and Mg. The enrichment ability for Ca is leaf > root, and for Mg is leaf > root. The enrichment coefficient of Ca and Mg in Salvia miltiorrhiza is higher. The results show that the combination of multiple data preprocessing methods can effectively improve the accuracy of LIBS measurement results. The calculation method of trace element enrichment law in different parts of Chinese herbal medicines provides guidance for the cultivation and fertilization of Chinese herbal medicines and the identification of high-quality Chinese herbal medicines.

关键词： enrichment characteristics of Chinese herbal medicine LIBS technology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：