检索结果-内蒙古大学图书馆

2023 IEEE/MTT-S International Microwave Symposium, IMS 2023

作者： Xu, Zhihong Li, Jin Chen, Sicheng Yuan, Tao Guangdong Prov. Mobile Terminal Microwave and Millimeter-Wave Antenna Engineering Research Center College of Electronics and Information Engineering Shenzhen University China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China State Key Laboratory of Millimeter Waves China Shenzhen University ATR National Key Laboratory of Defense Technology College of Electronics and Information Engineering China

ISBN: (纸本)9798350347647

This paper reports on a geometrical-shaping-based resonator design approach for in-line wideband rectangular waveguide bandpass filters (BPFs) aiming to improve the spurious suppression. The rectangular resonator is shaped with capacitive and inductive irises and the shaped resonator features irregular boundaries with the first spurious mode spectrally over an octave away from the fundamental mode. X-band 13%-fractional-bandwidth five-pole BPFs composed of uniform capacitive-iris-loaded resonators (filter I) and non-uniform hybrid-iris-loaded resonators (filter II) are developed. The shaping and non-uniform configuration of the resonators contribute to significantly improved stopband performance of the filter. The filter prototypes are manufactured additively and monolithically by incorporating Polyjet 3-D printing and electroless copper plating processes. The 3-D printed filters demonstrate excellent passband performance with the measured return loss and insertion loss of over 20 dB and lower than 0.3 dB, respectively. The first spurious passband appears at over 1.1× and 1.5× octaves away from the fundamental-mode passband for the filter I and filter II, respectively. © 2023 IEEE.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fast Cell Association Scheme Based on Deep Q-Learning in Ultra-Dense Cellular Networks

引用

china Communications 2021年第2期18卷 259-270页

作者： Jinhua Pan Lusheng Wang Hai Lin Zhiheng Zha Caihong Kai Key Laboratory of Knowledge Engineering with Big Data Ministry of Education.School of Computer Science and Information EngineeringHefei University of TechnologyHefei 230601China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei 230601China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education.School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

To support dramatically increased traffic loads,communication networks become *** cell association(CA)schemes are timeconsuming,forcing researchers to seek fast *** paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is *** the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until *** the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user *** demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional ***,performance metrics,such as capacity and fairness,can be guaranteed.

关键词： ultra-dense cellular networks(UDCN) cell association(CA) deep Q-learning proportional fairness Q-learning

来源：评论

学校读者我要写书评

暂无评论

Fast Multivariate Time Series Anomaly Detection Based on Matrix Completion

Fast Multivariate Time Series Anomaly Detection Based on Mat...

引用

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： He, Shiming Yi, Tongzhijian Yang, Bo Guo, Chenxi Changsha University of Science & Technology School of Computer and Communication Engineering The Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China

ISBN: (纸本)9798350301113

Increasingly complex systems contain large numbers of devices that generate great number of multivariate time series that are monitored and recorded. For anomaly detection of these complex time series, deep learning technology is often used to build a learning model for anomaly detection. The method based on deep learning usually takes a long time to train data in practice, and the online service system is deployed or changed very frequently, which makes the online service system need to frequently spend a lot of time updating the anomaly detection model. To overcome this challenge, this paper proposes a fast multivariate time series anomaly detection (FMAD) approach based on matrix completion. After sampling the primitive low-rank matrix, FMAD uses matrix completion to reconstruct the original low-rank matrix to detect anomalies in multivariate time series. We conducted related experimental analysis and discussion. The experimental results on three real data sets show that FMAD has improved the problem of too long model training time and improved the detection efficiency. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

LogADCH: Hyperspheric-Based Log Message Anomaly Detection And Classification

LogADCH: Hyperspheric-Based Log Message Anomaly Detection An...

引用

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： He, Shiming Xiao, Jinpan Chen, Bowen Lei, Ying Changsha University of Science & Technology School of Computer and Communication Engineering The Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China

ISBN: (纸本)9798350301113

Web services have been integrated with all walks of life in society. Abnormalities in the network and services seriously affect user experience and company revenue. The system log records various information of the system, and the information-rich log messages usually show different anomalies. It is particularly important to accurately and timely identify the anomalies of the log messages and classify the anomalies. In addition, most of the current existing work only detects anomalies and does not classify them, and a few existing works require anomaly labels to classify anomalies. Based on these potential challenges, we propose an unsupervised hypersphere-based log message anomaly detection and classification method, LogADCH. We use the hypersphere loss function to let the BERT model learn compact representations of log messages and perform anomaly detection. Finally, K-Means clustering is performed on the semantic feature vectors detected as anomalies to form clusters of different types of anomalies. Compared with other works, LogADCH further classifies the abnormal types after detecting the abnormal logs, helping the operation and maintenance personnel to quickly locate the fault. We compare our method with other methods on two public datasets, and the experimental results show that LogADCH has superior performance in anomaly detection as well as anomaly classification. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Measurement of the ^(232)Th(n,f)cross section in the 1-200 MeV range at the CSNS Back-n

引用

Nuclear Science and Techniques 2023年第8期34卷 142-153页

作者： Zhi-Zhou Ren Yi-Wei Yang Yong-Hao Chen Rong Liu Bang-Jiao Ye Jie Wen Hai-Rui Guo Zi-Jie Han Qi-Ping Chen Zhong-Wei Wen Wei-Li Sun Han Yi Xing-Yan Liu Tao Ye Jiang-Bo Bai Qi An Jie Bao Yu Bao Ping Cao Hao-Lei Chen Zhen Chen Zeng-Qi Cui Rui-Rui Fan Chang-Qing Feng Ke-Qing Gao Xiao-Long Gao Min-Hao Gu Chang-Cai Han Guo-Zhu He Yong-Cheng He Yang Hong Yi-Wei Hu Han-Xiong Huang Xi-Ru Huang Hao-Yu Jiang Wei Jiang Zhi-Jie Jiang Han-Tao Jing Ling Kang Bo Li Chao Li Jia-Wen Li Qiang Li Xiao Li Yang Li Jie Liu Shu-Bin Liu Ze Long Guang-Yuan Luan Chang-Jun Ning Meng-Chen Niu Bin-Bin Qi Jie Ren Xi-Chao Ruan Zhao-Hui Song Kang Sun Zhi-Jia Sun Zhi-Xin Tan Jing-Yu Tang Xin-Yi Tang Bin-Bin Tian Li-Jiao Wang Peng-Cheng Wang Zhao-Hui Wang Xiao-Guang Wu Xuan Wu Li-Kun Xie Xiao-Yun Yang Li Yu Tao Yu Yong-Ji Yu Guo-Hui Zhang Lin-Hao Zhang Qi-Wei Zhang Xian-Peng Zhang Yu-Liang Zhang Zhi-Yong Zhang Lu-Ping Zhou Zhi-Hao Zhou Ke-Jun Zhu Department of Modern Physics University of Science and Technology of ChinaHefei 230026China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900China Institute of High Energy Physics Chinese Academy of Sciences(CAS)Beijing 100049China Spallation Neutron Source Science Center Dongguan 523803China Institute of Applied Physics and Computational Mathematics Beijing 100088China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230027China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230027China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China State Key Laboratory of Particle Detection and Electronics Institute of High Energy PhysicsChinese Academy of SciencesBeijingChina Northwest Institute of Nuclear Technology Xi’an 710024China University of Chinese Academy of Sciences Beijing 100049China Department of Engineering and Applied Physics University of Science and Technology of ChinaHefei 230026China

The ^(232)Th(n,f)cross section is very important in basic nuclear physics and applications based on the Th/U fuel *** the time-of-flight method and a multi-cell fast-fission ionization chamber,a novel measurement of the^(232)Th(n,f)cross sec-tion relative to^(235)U in the 1–200 MeV range was performed at the china Spallation Neutron Source Back-n white neutron source(Back-n).The fission event-neutron energy spectra of^(232)Th and^(235)U fission cells were measured in the single-bunch *** 232Th/235U fission cross-sectional ratios were obtained,and the measurement uncertainties were 2.5–3.7%for energies in the 2–20 MeV range and 3.6–6.2%for energies in the 20–200 MeV ***^(232)Th(n,f)cross section was obtained by introducing the standard cross section of^(235)U(n,f).The results were compared with those of previous theoreti-cal calculations,measurements,and *** measured 232Th fission cross section agreed with the main evaluation results in terms of the experimental uncertainty,and 232Th fission resonances were observed in the 1–3 MeV *** present results provide^(232)Th(n,f)cross-sectional data for the evaluation and design of Th/U cycle nuclear systems.

关键词： 232Th(n f)cross section Fast-fission ionization chamber Back-n white neutron source

来源：评论

学校读者我要写书评

暂无评论

Mathematical model for predicting fungal growth and decomposition rates based on improved Logistic equations

引用

International Journal of Agricultural and Biological engineering 2023年第1期16卷 60-65页

作者： Jiayong Pan Wenxin Le Zi’ao Wang Jian Chen College of Engineering China Agricultural UniversityBeijing 100083China Shenzhen Key Laboratory of Intelligent Microsatellite Constellation Shenzhen 518107GuangdongChina Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities MNRShanghai 200063China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen 518000GuangdongChina Jiangsu Province and Education Ministry Co-sponsored Synergistic Innovation Center of Modern Agricultural Equipment Jiangsu UniversityZhenjiang 212013China Key Laboratory of Smart Agricultural Technology in Tropical South China Ministry of Agriculture and Rural AffairsGuangzhou 510642China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China State Key Laboratory of Clean Energy Utilization Zhejiang UniversityHangzhou 310013China

As the function of the decomposition of fungi has been clearly researched in the global carbon cycle,it is obviously of value to explore the decomposition rate of fungal *** study analyzed the relationship between environmental factors and biodiversity step by *** order to explore the interaction between the fungi and the relationship between the decomposition rate of fungi with time,the model based on the Logistic model was built and the Lotka-Volterra model was employed in the condition of two kinds of fungi existing in an environment with limited *** changing trend of population number and decomposition rate of several fungi under different environmental conditions can be predicted through the *** illustrate the applicability of the model,Laetiporus conifericola and Hyphoderma setigerum were applied as *** results showed that the higher the degree of population diversity,the greater the decomposition rate,and the higher the decomposition efficiency of the *** rich species diversity is conducive to accelerating the decomposition of litter,lignocellulose,and the circulation of the entire *** on the above model and using the data from measuring the mycelial elongation rate of each isolate at 10℃,16℃,and 22℃ under standardized laboratory conditions,the growth patterns of the five fungi combinations were *** results revealed a general increase in growth rate with increasing temperature,which verifies the accuracy of the ***,it also revealed that the total decomposition rate after fungal incorporation was negatively correlated with the decomposition rate of a fungal single *** on the above model,predictions can be made for fungal growth in different environments,and suitable environments for fungal growth can be *** the future,the model can be further optimized,and lignin and cellulose decomposition factors can be added to fit the decomposition of *** application

关键词： Logistic equations fungal decomposition mathematical model

来源：评论

学校读者我要写书评

暂无评论

Cross-modal image text retrieval based on Cross-optimization and Joint strategy

Cross-modal image text retrieval based on Cross-optimization...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Zheng, Wei Han, Na Hu, Yan Kang, Peipei Zhang, Yue Yang, Aqing Zhang, Lei School of Computer Science Guangdong Polytechnic Normal University China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data China School of Computer Science and Technology Guangdong University of Technology China School of Information Engineering East University of Heilongjiang China

ISBN: (纸本)9781510680425

In the fields of computer vision and natural language processing, cross-modal retrieval is of great importance that cannot be ignored. In existing multi-granularity alignment methods, significant progress has been made by globally aligning images and sentences or locally aligning regions and words. However, most of these methods rely on attention mechanisms, which may be affected by noise and cannot balance the differences between modalities, resulting in suboptimal image-text alignment. In addition, training with attention mechanisms consumes a lot of computational resources, and the retrieval process is time-consuming. To address these challenges, we develop a novel multigranularity image-text alignment model, which we call DFVLM. First, we independently train the intra-modal encoder and cross-modal encoder to reduce interference between different modal encoders and better learn intra-modal and inter-modal information. Then, we propose a joint strategy to combine the intra-modal and inter-modal information to better capture the information between image and text. In addition, we introduce a hard negative pair-based method to train the performance of the intra-modal multi-granularity encoder without using attention mechanisms. Unlike existing methods, We treat image and text retrieval as a two-way process and delve into the intrinsic connections between the two matrices. We propose a cross-validation method to optimize the retrieval result based on common image-to-text alignment scenarios in daily life, i.e., during the image-to-text retrieval process, a text-to-image reverse verification is performed on the retrieved corresponding text. Through extensive qualitative experiments and analysis, our approach performs well on both Flickr30K and MSCOCO datasets and also significantly reduces the time required for testing. © 2024 SPIE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Steel Defect Detection Algorithm Based on Multiobjective ENAS Sharing Strategy 24

Steel Defect Detection Algorithm Based on Multiobjective ENA...

引用

2nd International Conference on Frontiers of Intelligent Manufacturing and Automation, CFIMA 2024

作者： Zhao, Tianchen Dong, Zhiming Wang, Xianpeng National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Ministry of Education Shenyang China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang China Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Northeastern University Shenyang China

ISBN: (纸本)9798400710681

When employing the network architecture search approach for designing a steel surface defect detector, there are issues with conflicting evaluation metrics and limited computational resources. To address this challenge, we propose a multiobjective evolutionary sharing strategy-based network architecture search method (MESNAS). MESNAS defines network architecture search as a bi-level multiobjective optimization problem combined with a weight sharing acceleration strategy designed to quickly and simultaneously optimize the accuracy and complexity of classification models. A refined search space suitable for different image classification and detection tasks is designed. Using the MOEA/D algorithm, which incorporates a variable-length encoding scheme, the search space is co-utilized and explored through targeted improvements to the crossover and mutation operators in the offspring generation process. The optimal network architecture obtained from the search is tested on the concrete surface defect classification task, and the steel continuous casting slab surface defect detection task. The experimental results show that the proposed algorithm has good model performance and portability in image classification as well as defect detection tasks with different data complexities and different categories. © 2024 Copyright held by the owner/author(s).

关键词： Continuous casting

来源：评论

学校读者我要写书评

暂无评论

Multifactor prediction of carbon price based on principal component analysis and long short-term memory 3

Multifactor prediction of carbon price based on principal co...

引用

3rd International Conference on Electronic Information engineering, Big data, and Computer Technology, EIBDCT 2024

作者： Wang, Yuanling Wen, Hao Deng, Shuyun Xia, Xin Chongqing Key Laboratory of Public Big Data Security Technology Chongqing College of Mobile Communication Chongqing401527 China School of Management Science and Engineering Chongqing Technology and Business University Chongqing400067 China

ISBN: (纸本)9781510680449

In recent years, the development of the carbon trading market has become an important policy for china to achieve its "dual carbon"goals at an early date and to take on the role of a major international player in reducing emissions. Since the opening of the carbon market in 2013, there are now eight mature carbon trading pilot cities in china. Considering that carbon prices are susceptible to influences from factors such as the natural environment and financial policies, this paper introduces eight influencing factors from the energy, economic, financial, and natural environment levels for analysis. This paper selects the carbon trading market in Hubei, with the highest carbon trading volume, and the carbon trading market in Fujian, with the lowest carbon trading volume, as research objects. Firstly, the PCA model is applied to extract the main factors that influence carbon prices from the eight influential factors. Then, the LSTM model is used to establish a multifactor prediction model, and the GRU, RNN, and CNN models are used as comparative models. Finally, the predicted fitting graph is drawn, and the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are calculated. The research results show that the multi-factor prediction model based on LSTM performs the best in terms of price prediction accuracy. Through an in-depth exploration of various models, this study has made a significant contribution to the progress of carbon market research. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Carbon

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：