检索结果-内蒙古大学图书馆

Privacy Preserving Blockchain with Optimal Deep Learning Model for Smart Cities

computers, Materials & Continua 2022年第12期73卷 5299-5314页

作者： K.Pradeep Mohan Kumar Jenifer Mahilraj D.Swathi R.Rajavarman Subhi R.M.Zeebaree Rizgar RZebari Zryan Najat Rashid Ahmed Alkhayyat Department of Computing Technologies SRM Institute of Science and TechnologyKattankulathurChennai603203India Department of Computer Science and Information Technology School of Engineering and TechnologyKebridehar UniversityKebridehar250Ethiopia Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTiruchirappalli621112India Energy Department Technical College of EngineeringDuhok Polytechnic UniversityDuhokIraq Computer Science Department College of ScienceNawroz UniversityDuhokIraq Computer Network Department Technical College of InformaticsSulaimani Polytechnic UniversitySulaimaniIraq College of Technical Engineering The Islamic UniversityNajafIraq

Recently,smart cities have emerged as an effective approach to deliver high-quality services to the people through adaptive optimization of the available *** the advantages of smart cities,security remains a huge challenge to be ***,Intrusion Detection System(IDS)is the most proficient tool to accomplish security in this ***,blockchain exhibits significance in promoting smart city designing,due to its effective characteristics like immutability,transparency,and *** order to address the security problems in smart cities,the current study designs a Privacy Preserving Secure Framework using Blockchain with Optimal Deep Learning(PPSF-BODL)*** proposed PPSFBODL model includes the collection of primary data using sensing ***,z-score normalization is also utilized to transform the actual data into useful ***,Chameleon Swarm Optimization(CSO)with Attention Based Bidirectional Long Short TermMemory(ABiLSTM)model is employed for detection and classification of *** is employed for optimal hyperparameter tuning of ABiLSTM *** the same time,Blockchain(BC)is utilized for secure transmission of the data to cloud *** cloud server is a decentralized,distributed,and open digital ledger that is employed to store the transactions in different methods.A detailed experimentation of the proposed PPSF-BODL model was conducted on benchmark dataset and the outcomes established the supremacy of the proposed PPSFBODL model over recent approaches with a maximum accuracy of 97.46%.

关键词： Blockchain smart city security intrusion detection system chameleon swarm optimization deep learning parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Study on an Enhanced Stream Cipher Algorithm Based on Random Hashing

Study on an Enhanced Stream Cipher Algorithm Based on Random...

引用

2024 8th International Conference on Electrical, Mechanical and computer engineering (ICEMCE)

作者： Guanghui Feng Xibin Sun Jianhua Jiang Wei Li Yifang Tang Computer Engineering Technical College Guangdong Polytechnic of Science and Technology Zhuhai China

ISBN: (数字)9798331506230

ISBN: (纸本)9798331506247

In response to the issues of traditional stream cipher mechanisms based on exclusive-OR (XOR) operation, which has a single encryption and decryption method and whose security entirely relies on the key stream, this paper proposes a stream cipher algorithm based on random hashing. Firstly, we utilize Nonlinear Feedback Shift Registers (NLFSRs) to generate high-security pseudorandom sequences, enhancing resistance against correlation and algebraic attacks. Secondly, a specific XOR operation for designated plaintext positions, combined with a random hashing algorithm inspired by N -way merging, is designed to replace the traditional XOR operation in stream ciphers, effectively preventing Many-Time-Pad (MTP) attacks. Finally, this algorithm maintains the same time and space complexity as traditional XOR operation-based stream cipher algorithms. Still, experimental results show that when the pseudorandom sequence is short, this algorithm exhibits higher code uniformity and is particularly effective for encrypting short information.

关键词： Resistance Ciphers Correlation Merging Shift registers Robustness Encoding Encryption Time complexity Random sequences

来源：评论

学校读者我要写书评

暂无评论

Adaptive Incremental Broad Learning System Based on Interval Type-2 Fuzzy Set with Automatic Determination of Hyperparameters

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1713-1725页

作者： Wu, Haijie Lin, Weiwei Chen, Yuehong Shi, Fang Shen, Wangbo Chen, C. L. Philip South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Shenzhen518066 China Guangdong Polytechnic Normal University School of Mathematics and Systems Science Guangzhou510665 China South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China South China University of Technology School of Computer Science and Engineering Guangzhou511442 China

The fuzzy broad learning system (FBLS) has received increasing attention due to its ability to quickly train from broad learning systems (BLS) and interpretability with fuzzy inference. However, the randomness of BLS brings instability to the training performance of the model, so the hyperparameters of the model are crucial for its performance. Currently, many FBLS use grid search to determine hyperparameters. However, grid search brings longer search time and the parameters obtained have randomness, which may not necessarily be the optimal hyperparameters. In response to these challenges, this paper proposes a fuzzy broad learning system with automatic determination of hyperparameters (ADHFBLS). We construct a novel FBLS based on the interval type-2 fuzzy set and design an incremental learning algorithm for rules and enhancement nodes to support rapid model expansion. Meanwhile, a heuristic hyperparameter automatic optimization algorithm is designed to overcome the randomness and long optimization time of grid search. Experiments have shown that ADHFBLS has higher accuracy and shorter model tuning time compared to some state-of-the-art models based on FBLS. © 1993-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Graph-based Group Division Network for Referring Expression Comprehension

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 6170-6183页

作者： Ke, Jingcheng Wang, Jia Wong, Waikeung Toomey, Anne Wen, Jie Guangdong University of Technology School of Computer Science and Technology GuangZhou China Guangdong Pharmaceutical University College of Medical Information Engineering GDPU Guangdong Guangzhou China The Hong Kong Polytechnic University School of Fashion and Textiles Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong Hong Kong The Royal College of Art Kensington Gore School of Design London South KensingtonSW7 2EU United Kingdom Harbin Institute of Technology School of Computer Science and Technology Shenzhen China

Referring expression comprehension (REC) aims at locating the target object described by an expression. We observe that most of the graph-based REC methods only focus on establishing relations between all objects in an image and the given expression during the graph construction while ignoring the relationships between objects in the same category. As a result, these methods are sub-optimal in locating the target object described by the expression, particularly when the target object is surrounded by objects of similar categories. Meanwhile, during reasoning, numerous irrelevant objects are considered for expression, which will introduce significant harmful noise. To address these issues, this paper proposes a new graph-based group division network (GBGDN). Different from the existing works, our work partitions the constructed graphs into several sub-graphs based on the categories of objects and expressions. In each sub-graph, the common visual features of objects will be strengthened through a feature enhancement strategy. Subsequently, the enhanced sub-graphs and expressions undergo joint processing via a filtering-based reasoning module designed to reduce the influence of unrelated nodes in each subgraph, facilitating more accurate reasoning and matching. Experimental results across various datasets, including RefCOCO /+/g, Flickr30K Entities, RefClef, and Ref-reasoning, showcase the superiority of our proposed method over existing approaches. Most importantly, our method does not need pre-training. © 1991-2012 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

computer-Simulated Performance Comparison of T-type and Π-type Network based Microwave Angular Displacement Sensors

Computer-Simulated Performance Comparison of T-type and Π-t...

引用

2025 2nd International Conference on Algorithms, Software engineering and Network Security (ASENS)

作者： Hongxu Zhu Zhongming Yang Computer Engineering Technical College (Artificial Intelligence College) Guangdong Polytechnic of Science and Technology Zhuhai China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

In this paper, the T-type and Π-type network based microwave angular displacement sensors are compared and analyzed. By incorporating neural networks, one can optimize the design parameters of microwave sensors, enhance the evaluation of critical sensor performance indicators, including frequency response, linearity, sensitivity, bandwidth, and stability.

关键词： Sensitivity Neural networks Software algorithms Linearity Bandwidth Network security Microwave sensors Stability analysis Sensors Software engineering

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent network OBE teaching evaluation system based on Mixed algorithm 23

Design of intelligent network OBE teaching evaluation system...

引用

Proceedings of the 2023 International Conference on Information Education and Artificial Intelligence

作者： Meng Xia Yaping Chang Yongjun He Computer Engineering Technical College (Artificial Intelligence College) Guangdong Polytechnic of Science and Technology China

ISBN: (纸本)9798400716157

Teacher evaluation in teaching departments is one of the most important components of the evaluation of teaching quality. With the acceleration of the education informatization process, the use of modern information processing techniques can provide extremely favorable conditions and means for the evaluation of teachers' teaching quality in traditional teaching. At the same time, in a certain network environment, the use of teaching evaluation-assisted decision-making systems can further promote the rationality and fairness of teaching evaluation. Based on this background, this paper designs an intelligent network OBE (Outcome-Based Education) teaching evaluation system based on the Mixed algorithm. Firstly, the evaluation results of the teaching model are obtained based on the Mixed algorithm and neural network algorithm. Then, the OBE concept is integrated into teaching evaluation. Finally, the entire teaching evaluation system is designed in a unified manner. The results show that the system designed in this paper provides objective and reasonable evaluation results for teaching quality and can provide reference for the evaluation and decision-making of teaching quality in colleges and universities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Typhoon Track Image Prediction Using a Comprehensive LSTM Attention Model in Deep Learning 4

Typhoon Track Image Prediction Using a Comprehensive LSTM At...

引用

4th International Conference on Neural Networks, Information and Communication engineering, NNICE 2024

作者： Jiang, Yiping Yu, Yi Ma, Yuelong Zhuang, Jiahao Ye, Xianze Yuan, Yifeng Su, Guanpeng Guangdong University of Science and Technology School of Computer Science Guangdong Dongguan China University of Macau Faculty of Science and Technology Fst China South China Normal University School of Information and Optoelectronic Science and Engineering Guangdong Guangzhou China Macao Polytechnic University Faculty of Applied Sciences China Zhuhai College of Science and Technology School of Computer Guangdong Zhuhai China

ISBN: (纸本)9798350394375

Typhoons are exceptionally destructive tropical cyclones that possess the capacity to inflict significant harm upon society. For institutions engaged in risk assessment and disaster mitigation, accurately forecasting typhoon paths and trajectories is of paramount importance. In this study, we propose a Typhoon Track Image Prediction model based on a Comprehensive Long Short-Term Memory (LSTM) Attention Model in the field of Deep Learning. This model significantly improves the accuracy of typhoon track prediction. To assess its performance, we utilize typhoon data from the China Typhoon Network spanning from 1949 to 2022. The Comprehensive LSTM Attention Model is compared against other popular models such as Temporal Convolutional Networks (TCN), traditional LSTM, and Seq2Seq models for forecasting the typhoon track over a 12-hour period. The results demonstrate the superiority of our proposed model, showcasing its effectiveness in terms of superior accuracy in typhoon track prediction. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Implementation of brain computer interface technology based on artificial intelligence in intelligent wearable devices 24

Implementation of brain computer interface technology based ...

引用

2024 guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Li, Jianzhong Wan, Qiang Wu, Meiping School of Entrepreneurship Guangdong Innovative Technical College Guangdong Dongguan523000 China School of computer science and engineering South china university of technology Guangdong Guangzhou510641 China School of Stomatology Guangzhou Health Science College Guangdong Guangzhou510999 China

ISBN: (纸本)9798400717147

The smart wearable device industry is growing fast, with devices being used more in healthcare, sports, and entertainment. These devices use micro-sensors to collect data, which is sent to the Internet for analysis and display. This study looks at how artificial intelligence is used in brain-computer interface (BCI) research for smart wearables and found:1. For better accuracy in short time periods, the right stimulation method is key. An AR-BCI system using SSVEP was developed, which resulted in an average online recognition rate of 88.67% with 1 second of data and 98.6% with 2 seconds.2. Monitoring brain activity relies on capturing action potentials outside neurons, with EEG being captured at 2048 Hz for better accuracy and reduced data processing.3. The EEG shows high quality signals, needing minimal preprocessing for high classification accuracy. The MSCNN-SVN model shows an analysis efficiency of 10.2, with the MSCNN model at 12.3, and the SVM model at 35.2. The MSCNN-SVN model has low error rates and high efficiency. © 2024 ACM.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Empirical Likelihood for PLSIM with Missing Response Variables and Error-Prone Covariates 2nd

Empirical Likelihood for PLSIM with Missing Response Varia...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Qi, Xin Chen, Hongling Liu, Qin Guangdong Polytechnic of Science and Technology Zhuhai519090 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

ISBN: (纸本)9789819902712

A variety of data can be obtained through the Internet, but some data involves privacy and cannot be fully acquired. Privacy information hiding or missing problems frequently occur in many fields. In this paper, we consider some privacy missing data models and analysis problems. The empirical likelihood method is applied to study a partially linear single-index model that has the covariate X measured error and the response Y missing. The bias-corrected empirical log-likelihood ratio with asymptotic chi-square is derived, and the confidence regions are constructed. A few simulation experiments and an application to a real data set, in which some personal privacy information is hidden or missing, are conducted to illustrate our proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis of extrapolated relaxed Hermitian and skewHermitian splitting iteration methods for large sparse linear complementarity problems 7

Convergence analysis of extrapolated relaxed Hermitian and s...

引用

2022 7th International Conference on Information science, computer technology and Transportation, ISCTT 2022

作者： Duan, Banxiang Computer Engineering Technical College Guangdong Institute of Science and Technology Guangdong519090 China

ISBN: (纸本)9783800760565

We investigate the problem of solving large sparse linear complementarity problems. First, we propose an extrapolated relaxation Hermitian and skew-Hermitian splitting iteration method for solving large sparse linear complementarity problems. Then, the convergence theory of thematods is established when the coefficient matrix is a positive or an H ‐ matrix. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Matrix algebra

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：