检索结果-内蒙古大学图书馆

HACAN:a hierarchical answer-aware and context-aware network for question generation

Frontiers of Computer science 2024年第5期18卷 45-55页

作者： Ruijun SUN Hanqin TAO Yanmin CHEN Qi LIU Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei230027China

Question Generation(QG)is the task of generating questions according to the given *** of the existing methods are based on Recurrent Neural Networks(RNNs)for generating questions with passage-level input for providing more details,which seriously suffer from such problems as gradient vanishing and ineffective information *** fact,reasonably extracting useful information from a given context is more in line with our actual needs during questioning especially in the education *** that end,in this paper,we propose a novel Hierarchical Answer-Aware and Context-Aware Network(HACAN)to construct a high-quality passage representation and judge the balance between the sentences and the whole ***,a Hierarchical Passage Encoder(HPE)is proposed to construct an answer-aware and context-aware passage representation,with a strategy of utilizing multi-hop ***,we draw inspiration from the actual human questioning process and design a Hierarchical Passage-aware Decoder(HPD)which determines when to utilize the passage *** conduct extensive experiments on the SQuAD dataset,where the results verify the effectivenesss of our model in comparison with several baselines.

关键词： question generation natural language generation natural language processing sequence to sequence

来源：评论

学校读者我要写书评

暂无评论

Enhanced Privacy-Preserving WiFi Fingerprint Localization from CL Encryption

引用

Chinese Journal of Electronics 2024年第6期33卷 1435-1446页

作者： Zhiwei WANG Qiuchi ZHU Zhenqi ZHANG School of Computer Nanjing University of Posts and Telecommunications State Key Laboratory of Public Big Data Guizhou University Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Engineering Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal University

The WiFi fingerprint-based localization method is considered one of the most popular techniques for indoor localization. In INFOCOM'14, Li et al. proposed a wireless fidelity(WiFi) fingerprint localization system based on Paillier encryption, which is claimed to protect both client C 's location privacy and service provider S's database privacy. However, Yang et al. presented a practical data privacy attack in INFOCOM'18, which allows a polynomial time attacker to obtain S's database. We propose a novel WiFi fingerprint localization system based on CastagnosLaguillaumie(CL) encryption, which has a trustless setup and is efficient due to the excellent properties of CL encryption. To prevent Yang et al.'s attack, the system requires that S selects only the locations from its database that can receive the nonzero signals from all the available access points in C 's nonzero fingerprint in order to determine C's location. Security analysis shows that our scheme is secure under Li et al.'s threat model. Furthermore, to enhance the security level of privacy-preserving WiFi fingerprint localization scheme based on CL encryption, we propose a secure and efficient zero-knowledge proof protocol for the discrete logarithm relations in C's encrypted localization queries.

关键词： Location awareness Threat modeling data privacy Protocols databases Fingerprint recognition Trustless services Encryption Servers Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

A general tail item representation enhancement framework for sequential recommendation

引用

Frontiers of Computer science 2024年第6期18卷 137-148页

作者： Mingyue CHENG Qi LIU Wenyu ZHANG Zhiding LIU Hongke ZHAO Enhong CHEN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China&State Key Laboratory of Cognitive IntelligenceHefei 230026China College of Management and Economics Tianjin UniversityTianjin 300072China

Recently advancements in deep learning models have significantly facilitated the development of sequential recommender systems(SRS).However,the current deep model structures are limited in their ability to learn high-quality embeddings with insufficient ***,highly skewed long-tail distribution is very common in recommender ***,in this paper,we focus on enhancing the representation of tail items to improve sequential recommendation *** empirical studies on benchmarks,we surprisingly observe that both the ranking performance and training procedure are greatly hindered by the poorly optimized tail item *** address this issue,we propose a sequential recommendation framework named TailRec that enables contextual information of tail item well-leveraged and greatly improves its corresponding *** the characteristics of the sequential recommendation task,the surrounding interaction records of each tail item are regarded as contextual information without leveraging any additional side *** approach allows for the mining of contextual information from cross-sequence behaviors to boost the performance of sequential *** a light contextual filtering component is plug-and-play for a series of SRS *** verify the effectiveness of the proposed TailRec,we conduct extensive experiments over several popular benchmark *** experimental results demonstrate that TailRec can greatly improve the recommendation results and speed up the training *** codes of our methods have been available.

关键词： sequential recommendation long-tail distribution training accelerating

来源：评论

学校读者我要写书评

暂无评论

Remarkable average thermoelectric performance of the highly oriented Bi(Te,Se)-based thin films and devices

引用

Journal of Materiomics 2024年第2期10卷 366-376页

作者： Zhiliang Li Xiaoqi Yang Zhi Gao Jingxuan Wang Yuli Xue Jianglong Wang Qian Cao Zhihai Ding Shufang Wang Hebei Key Lab of Optic-Electronic Information and Materials Key Laboratory of High-Precision Computation and Application of Quantum Field Theory of Hebei ProvinceCollege of Physics Science and TechnologyHebei UniversityBaoding071002China Huabei Cooling Device Co. LtdXianghe065400China

Bi(Te,Se)-based compounds have attracted lots of attention for nearly two centuries as one of the most successful commercial thermoelectric(TE)materials due to their high performance at near room *** with 3D bulks,2D thin films are more compatible with modern semiconductor technology and have unique advantages in the construction of micro-and *** device applications,high average TE performance over the entire operating temperature range is ***,highly c-axis-oriented N-type Bi(Te,Se)epitaxial thin films have been successfully prepared using the pulsed laser deposition technology by adjusting the deposition *** film deposited at~260℃demonstrate a remarkable average power factor(PFave)of~24.4 mW·cm^(-1)·K^(-2)over the tem-perature range of 305e470 K,higher than most of the state-of-the-art Bi(Te,Se)-based ***,the estimated average zT value of the film is as high as~*** then constructed thin-film TE devices by using the above oriented Bi(Te,Se)films,and the maximum output power density of the device can reach up to~30.1 W/m^(2)under the temperature difference of 40 ***,the outstanding average TE performance of the highly oriented Bi(Te,Se)thin films will have an excellent panorama of applications in semiconductor cooling and power generation.

关键词： Bismuth telluride Oriented thin film Thermoelectric device Average power factor Output power density

来源：评论

学校读者我要写书评

暂无评论

Current Status of Objectification of Four Diagnostic Methods on Constitution Recognition of Chinese Medicine

引用

Chinese Journal of Integrative Medicine 2022年第12期28卷 1137-1146页

作者： LI Cong-cong YAN Xin-sheng LIU Ming-hao TENG Gui-fa School of Information Science and Technology Hebei Agricultural UniversityBaodingHebei Province 071001China Hebei Key Laboratory of Agricultural Big Data BaodingHebei Province 071001China

Chinese medicine(CM)has thousands of years of experience in prevention of *** for CM,people's constitution is closely related to their health status,thus recognition of CM constitution is the fundamental and core contentof research on constitution *** development of technologies such as sensors,arificial intelligence and big data,objectification of the four diagnostic methods of CM has gradually matured,bringing changes in the mindset and innovations in technical means for recognition of CM *** paper presents a systematic review of the latest research trends in constitution recognition based on objectification of diagnostic methods in CM.

关键词： Chinese medicine constitution recognition four diagnostic methods objectification machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and development of immersive 3D virtual simulation experiment teaching platform for internet of things

引用

Multimedia Tools and applications 2024年 1-15页

作者： Li, Yanan Li, Congcong Wang, Yijin Teng, Guifa College of Information Science & amp Technology Hebei Agricultural University No.289 Lingyusi Street Hebei Province Baoding071001 China Hebei Key Laboratory of Agricultural Big Data No.289 Lingyusi Street Hebei Province Baoding071001 China

The learning content of the Internet of Things (IoT) professional courses is closely related to reality, and has the characteristics of comprehensiveness, intersection and application. In order to solve the limitations of traditional practice teaching methods in time and space, and enhance the interaction of practice teaching, this project took the Internet of Things technology and application in virtual smart city as the research object, combined with advanced information technology, based on Bloom’s teaching objectives, a 3D virtual simulation experiment teaching platform composed of virtual equipment, and integrated data management and analysis services was established. The platform constructs a number of IoT 3D virtual simulation scenarios that emphasize professional technology and reflect the cutting-edge technology to create an immersive teaching environment. In addition, the platform contains multiple comprehensive experimental projects for exploratory research-based professional courses. Through the innovative experimental mode of integrating games, competitions, breakthroughs, explorations and flipped experiments, students’ interest in learning can be enhanced, and the overall quality of students’ practical ability, innovative spirit and learning ability can be improved. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

A keypoint-Based Object Detection Algorithm 7

A Keypoint-Based Object Detection Algorithm

引用

7th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2024

作者： Hou, Xiangdan Chen, Quansong Liu, Hongpu School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Hebei Province Key Laboratory of Big Data Computing Tianjin China

ISBN: (纸本)9798350370782

An improved algorithm is proposed for the omission and re-detection problems in the point cloud object detection method CenterPoint. The algorithm firstly adds Focal sparse convolution module to the feature extraction network to increase the proportion of important information in the features;then redefines the generation function of the detection head heatmap, and the supervisory signal generated by the elliptical Gaussian kernel is more closely matched to the real shape of the object to inhibit the generation of negative samples;finally, the overall regression of the bounding box information is applied to the training, so that the back propagation loss gain of the single dimensional information is regulated by the associated information. The improved algorithm is trained and evaluated on the KITTI 3D object detection dataset, and the overall mean Average Precision (mAP) is improved by 3.29% compared with the base model CenterPoint. The experimental results show that the improved algorithm effectively suppresses the redetection and omission problems of CenterPoint. © 2024 IEEE.

关键词： CenterPoint Focal sparse convolution Gaussian kernel object detection overall regression

来源：评论

学校读者我要写书评

暂无评论

Towards Exploring Large Molecular Space:An Efficient Chemical Genetic Algorithm

引用

Journal of Computer science & Technology 2022年第6期37卷 1464-1477页

作者： Jian-Fu Zhu Zhong-Kai Hao Qi Liu Yu Yin Cheng-Qiang Lu Zhen-Ya Huang En-Hong Chen Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China

Generating molecules with desired properties is an important task in chemistry and *** efficient method may have a positive impact on finding drugs to treat diseases like *** mining and artificial intelligence may be good ways to find an efficient ***,both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule’s ***,existing methods have defects in the experimental evaluation *** methods also need to be improved in efficiency and *** solve these problems,we propose a method named the Chemical Genetic Algorithm for Large Molecular Space(CALM).Specifically,CALM employs a scalable and efficient molecular representation called molecular *** we design corresponding crossover,mutation,and mask operators inspired by domain knowledge and previous *** apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular *** results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods,where the z tests performed on the results of several experiments show that our method is more than 99%likely to be *** the same time,based on the experimental results,we point out the defects in the experimental evaluation standard which affects the fair evaluation of all previous *** these defects helps to objectively evaluate the performance of all work.

关键词： data mining molecular generation genetic algorithm drug discovery artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

W boson mass in NP models with an extra U(1)gauge group

引用

Chinese Physics C 2024年第11期48卷 15-21页

作者： Jin-Lei Yang Zhao-Feng Ge Xiu-Yi Yang Sheng-Kai Cui Tai-Fu Feng Department of Physics Hebei UniversityBaoding 071002China Key Laboratory of High-precision Computation and Application of Quantum Field Theory of Hebei Province Baoding 071002China CAS Key Laboratory of Theoretical Physics School of Physical SciencesUniversity of Chinese Academy of SciencesBeijing 100049China School of Science University of Science and Technology LiaoningAnshan 114051China

The precise measurement of the W boson mass is closely related to the contributions of new physics(NP),which can significantly constrain the parameter space of NP models,particularly those with an additional U(1)local gauge *** inclusion of a new Z'gauge boson and gauge couplings in these models can contribute to the oblique parameters S,T,and U and the W boson mass at tree *** the effects of kinetic mixing,in this study,we calculate and analyze the oblique parameters S,T,and U and the W boson mass in such NP *** find that the kinetic mixing effects can make significant contributions to the W boson mass,and these contributions can be eliminated by redefining the gauge boson fields by removing neutral currents with charged leptons if the leptonic Yukawa couplings are invariant under the extra U(1)local gauge group,even with nonzero kinetic mixing effects.

关键词： extra U(1) oblique parameters kinetic mixing

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Fast Area Optimization Approach for Mixed Polarity Reed-Muller Logic Circuits

引用

Chinese Journal of Electronics 2024年第5期33卷 1165-1180页

作者： Yuhao ZHOU Zhenxue HE Jianhui JIANG Xiaojun ZHAO Fan ZHANG Limin XIAO Xiang WANG School of Software Engineering Tongji University Key Laboratory of Agricultural Big Data of Hebei Province Hebei Agricultural University School of Computer Science and Engineering Beihang University School of Electronic and Information Engineering Beihang University

Area has become one of the main bottlenecks restricting the development of integrated circuits. The area optimization approaches of existing XNOR/OR-based mixed polarity Reed-Muller(MPRM) circuits have poor optimization effect and efficiency. Given that the area optimization of MPRM logic circuits is a combinatorial optimization problem, we propose a whole annealing adaptive bacterial foraging algorithm(WAA-BFA), which includes individual evolution based on Markov chain and Metropolis acceptance criteria, and individual mutation based on adaptive probability. To address the issue of low conversion efficiency in existing polarity conversion approaches, we introduce a fast polarity conversion algorithm(FPCA). Moreover, we present an MPRM circuits area optimization approach that uses the FPCA and WAA-BFA to search for the best polarity corresponding to the minimum circuits area. Experimental results demonstrate that the proposed MPRM circuits area optimization approach is effective and can be used as a promising EDA tool.

关键词： Integrated circuits Microorganisms Annealing Logic circuits Circuits Benchmark testing Delays

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：