检索结果-内蒙古大学图书馆

Gas Emission Prediction Based on Secondary Decomposition and MSCSO-WLSSVM

学校读者我要写书评

暂无评论

Journal of Network Intelligence 2024年第3期9卷 1405-1426页

作者： Zhao, Xue-Han An, Wei-Peng Qiao, Wei-Hao Lv, Chang-Zhou School of Computer Science and Technology Henan Polytechnic University Jiaozuo454000 China School of Software Henan Polytechnic University Jiaozuo454000 China

This paper proposes a combined prediction model based on secondary decomposition and MSCSO-WLSSVM to enhance methane gas emission prediction accuracy. Firstly, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is applied to decompose the residual term of variational mode decomposition (VMD). This effectively extracts the important information from the original data. Secondly, the global search ability and local exploitation ability of the sand cat swarm optimization algorithm (SCSO) are enhanced by introducing chaotic sequence and Lévy flight strategy. Then, the modified SCSO (MSCSO) is used to optimize kernel width and regularization parameters of the weighted least squares support vector machines (WLSSVM). Finally, the combined model MSCSO-WLSSVM is used to individually predict each decomposed subsequence, and the predicted results are then superimposed, further enhancing the overall prediction accuracy. The experimental results show this model(VCMW) has significant improvements over the SCSO-WLSSVM model, with reductions of 84.45% in mean square error and 92.31% in average relative variance. Additionally, the coefficient of determination has increased by 26.42%, demonstrating superior performance compared to competing models and highlighting its capability for precise and efficient gas emission prediction. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Support vector machines

Blockchain-based IVPPA Scheme for Pseudonym Privacy Protection in Internet of Vehicles

学校读者我要写书评

暂无评论

Journal of Network Intelligence 2024年第2期9卷 1260-1277页

作者： Wang, Hui Zhang, Fangyu Shen, Zihao Liu, Peiqian Liu, Kun School of Software Henan Polytechnic University Jiaozuo454000 China School of Computer Science and Technology Henan Polytechnic University Jiaozuo454000 China

Existing Vehicular Ad-hoc Networks (VANETs), while enabling vehicles to communicate with each other, share data, and connect to external networks, also face a large number of data security challenges, such as data leakage and hijacking, cyber-attacks, and malware. For the security and privacy of vehicle user data in Internet of Vehicles (IoV), this paper proposes a blockchain-based IVPPA scheme for pseudonym privacy protection in IoV using a blockchain to assist the security of VANETs authentication and key certificate protocols. Firstly, Elliptic Curve Cryptography (ECC) and secure hash functions are introduced in the message signing and authentication scheme technique. Second, the hash operation is performed on the vehicle certificate and the certificate hash value and the certificate are stored on the blockchain, and the mutual authentication between the vehicle and the roadside unit (RSU) is realized by querying the hash value on the blockchain, which improves the effectiveness of the mutual authentication between the entities. Finally, the improved Merkle Patricia Trie (MMPT) is used to store and manage the pseudonyms assigned to the vehicle efficiently, thus avoiding the tracking of the vehicle path and the leakage of the vehicle information. Simulation experiments show that this scheme has significantly lower average latency in computing overhead and byte size in communication overhead than the comparison scheme, in which the communication overhead is only 232 bytes, which is about 50% of the highest overhead of the compared schemes, and has better authentication performance and stronger feasibility in the context of vehicle networking. © 2024, J. Network Intell. All rights reserved.

关键词： Blockchain

WSN Data Fusion Algorithm Based on Radial Cluster and Elephant Swarm Neural Networks

学校读者我要写书评

暂无评论

Journal of Network Intelligence 2024年第4期9卷 2137-2150页

作者： Liu, Jia-Wei An, Wei-Peng School of Computer Science and Technology Henan Polytechnic University Jiaozuo454000 China School of Software Henan Polytechnic University Jiaozuo454000 China

To minimize the propagation of redundant data in wireless sensor networks, conserve energy, and extend network lifespan, we propose an algorithm (R-IEHOBP) that combines radial clustering and an elephant swarm neural network. Initially, we suggest employing the radial clustering routing protocol to address the issue of uneven energy consumption in nodes caused by the majority of current data fusion algorithms based on the LEACH clustering routing protocol. In the radial clustering protocol, we first divide candidate cluster heads into clusters of different sizes, and then we screen the cluster heads based on the number of required cluster head nodes in the sub-cluster, the remaining energy of the candidate nodes, distance from the center of gravity, and the number of nearby one-hop nodes. Secondly, we improve the elephant swarm optimization algorithm by introducing chaotic sequences, elite strategies, adversarial learning, and guided substitution principles. Next, we use the elephant group algorithm to select the initial matrices of weights and thresholds for the neural network to avoid the impact of unsuitable initial parameters on the final convergence speed and output accuracy. Addressing issues in single-stage neural network data fusion, such as incomplete data processing and large errors in the fused data, this paper proposes using a second-stage neural network to fuse the initial data received by the cluster head node and output it to the aggregation node. Finally, we establish a WSN data fusion model based on the radial clustering routing protocol by combining the radial clustering structure of wireless sensor networks with the neural network structure. Simulation experiment results demonstrate that the algorithm exhibits better redundant data rejection ability compared to similar algorithms, with lower energy consumption and higher data fusion accuracy. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Spatio-temporal data

Weighted Attribute Based Conditional Proxy Re-Encryption in the Cloud

学校读者我要写书评

暂无评论

computers, Materials & Continua 2025年第4期83卷 1399-1414页

作者： Xixi Yan Jing Zhang Pengyu Cheng Henan Key Laboratory of Network Cryptography Technology Network Information Security and Cryptography LaboratorySchool of SoftwareHenan Polytechnic UniversityJiaozuo454003China School of Computer Science and Technology Henan Polytechnic UniversityJiaozuo454000China

Conditional proxy re-encryption(CPRE)is an effective cryptographic primitive language that enhances the access control mechanism and makes the delegation of decryption permissions more granular,but most of the attribute-based conditional proxy re-encryption(AB-CPRE)schemes proposed so far do not take into account the importance of user attributes.A weighted attribute-based conditional proxy re-encryption(WAB-CPRE)scheme is thus designed to provide more precise decryption rights *** introducing the concept of weight attributes,the quantity of system attributes managed by the server is reduced *** the same time,a weighted tree structure is constructed to simplify the expression of access structure *** conditional proxy re-encryption,large amounts of data and complex computations are outsourced to cloud servers,so the data owner(DO)can revoke the user’s decryption rights directly with minimal *** scheme proposed achieves security against chosen plaintext attacks(CPA).Experimental simulation results demonstrated that the decryption time is within 6–9 ms,and it has a significant reduction in communication and computation cost on the user side with better functionality compared to other related schemes,which enables users to access cloud data on devices with limited resources.

关键词： Cloud service conditional proxy re-encryption user revocation weighted attribute

A Differential Privacy Budget Allocation Method Combining Privacy Security Level

学校读者我要写书评

暂无评论

Journal of Communications and Information Networks 2023年第1期8卷 90-98页

作者： Zihao Shen Shuhan He Hui Wang Peiqian Liu Kun Liu Fangfang Lian School of Computer Science and Technology Henan Polytechnic UniversityJiaozuo 454000China

Trajectory privacy protection schemes based on suppression strategies rarely take geospatial constraints into account,which is made more likely for an attacker to determine the user’s true sensitive location and *** solve this problem,this paper presents a privacy budget allocation method based on privacy security level(PSL).Firstly,in a custom map,the idea of P-series is contributed to allocate a given total privacy budget reasonably to the initially sensitive ***,the size of privacy security level for sensitive locations is dynamically adjusted by comparing it with the customized initial level threshold parameterµ.Finally,the privacy budget of the initial sensitive location is allocated to its neighbors based on the relationship between distance and degree between *** comparing the PSL algorithm with the traditional allocation methods,the results show that it is more flexible to allocate a privacy budget without compromising location privacy under the same preset conditions.

关键词： location privacy differential privacy privacy budget budget allocation PSL

Enhanced secure medical data sharing with traceable and direct revocation

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2023年第1期30卷 66-79页

作者： Peng Weiping Cui Shuang Song Cheng Han Ning School of Computer Science and Technology Henan Polytechnic UniversityJiaozuo 454003China

Sharing of the electronic medical records among different hospitals raises serious concern of the leakage of individual privacy for the adoption of the semi trustworthiness of the medical cloud *** tracking and revocation of malicious users have become urgent *** solve these problems,this paper proposed a traceable and directly revocable medical data sharing *** the scheme,a unique identity parameter(ID),which was generated and embedded in the private key generation phase by the medical service provider(MSP),is used to identify legal authorized user and trace malicious *** when attributes satisfy the access policy and user’s ID is not in the revocation list can the user calculate the decryption *** user can be tracked and directly revoked by using the revocation *** the assumption of decision bilinear Diffie-Hellman(DBDH),this paper has proved that the scheme is able to achieve security against chosen-plaintext attack(CPA).The performance analysis demonstrates that the sizes of the public key and private key are shorter,and the time overhead is less than other schemes in the public-private key generation,data encryption and data decryption stages.

关键词： medical data sharing electronic medical records tracking and revocation privacy protection

Semisymmetric Graphs of Order 2p^(3)with Valency p^(2)

学校读者我要写书评

暂无评论

Algebra Colloquium 2024年第2期31卷 199-208页

作者： Li Wang Songtao Guo Genghua Fan School of Mathematics and Information Science Henan Polytechnic University JiaozuoHenan 454000China School of Mathematics and Statistics Henan University of Science and Technology LuoyangHenan 471023China 不详

A simple undirected regular graph is said to be semisymmetric if it is edge-transitive but not *** a semisymmetric graphΓof order 2p^(3),p a prime,it is well known thatΓis bipartite with two biparts having equal *** complete classification of such graphs has been given for the full automorphism group Aut(Γ)acting unfaithfully on at least one bipart ofΓ,which shows that there is only one infinite family of such graphs with valency p^(2).The graphs of this kind have been determined when Aut(Γ)acts faithfully and primitively on at least one bipart ofΓ,and thus there is only one remaining case for classifying such graphs of valency p^(2),Aut(Γ)acting faithfully and imprimitively on both biparts ofΓ,which is dealt with in this *** a result,there is only one infinite family of semisymmetric graphs of order 2p^(3)with valency p^(2).

关键词： semisymmetric graph semitransitive graph bi-coset graph

Density Peaking Clustering Algorithm Based on Improved Tuna Swarm Optimization

学校读者我要写书评

暂无评论

Journal of Network Intelligence 2024年第1期9卷 126-141页

作者： Zhang, Hang Liu, Yong-Li Chao, Hao College of Computer Science and Technology Henan Polytechnic University Jiaozuo454000 China

The density peak clustering algorithm shows good clustering performance by rapidly determining each cluster division with a high-density region as the kernel. However, the cut-off distance (dc) as the only parameter of the algorithm usually needs to be specified manually, so it is limited in practical applications. In order to automatically select the optimal value of the cut-off distance parameter, a Density Peak Clustering (DPC) algorithm based on Improved Tuna Swarm Optimization (ITSO) was designed. To begin, the ITSO algorithm introduces multi-strategy chaotic mapping initialization and a self-adaptive factor, which boosts tuna swarm search performance, and conducts simulation experiments on 8 benchmark functions, with the results demonstrating that the ITSO algorithm outperforms other comparison algorithms;then the cut-off distance in the DPC is optimized using the ITSO algorithm, and the objective function is developed based on the accuracy index. In order to evaluate the effectiveness of the ITSO-DPC algorithm, five synthetic datasets and three UCI standard datasets were chosen for experiments. The results of the experiments demonstrate that the proposed algorithm can automatically select a better cut-off distance value and guarantee a higher clustering accuracy. © 2024, J. Network Intell. All rights reserved.

关键词： Clustering algorithms

Location Privacy Desensitization Algorithm Based on Multi-attribute Decision Model

学校读者我要写书评

暂无评论

Journal of Network Intelligence 2023年第4期8卷 1164-1182页

作者： Shen, Zihao Yang, Xin Wang, Hui Liu, Peiqian Liu, Kun School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454000 China School of Software Henan Polytechnic University Jiaozuo 454000 China

Traditional methods of building secure anonymity sets using location privacy desensitization techniques commonly suffer from low dummy location differentiation and vulnerable to background knowledge attacks. To address this problem, this paper proposes a multi-attribute decision model-based location privacy desensitization (MDMLPD) algorithm. Firstly, the construction of the candidate dummy location set is obtained by historical query probability judgment;secondly, data preprocessing is performed on the defined five attribute values and attribute weights are determined using hierarchical analysis;finally, comprehensive decision making is performed to select the optimal dummy location and construct a secure anonymous set to achieve location privacy desensitization. The experimental results show that the MDMLPD algorithm reduces the time overhead by about 9.8% compared with the MMDS algorithm, and the probability of being identified by the semantic attack is reduced by 15.3% and 26.2% compared with the MMDS algorithm and the K-DLS algorithm, respectively, what is feasible and efficient to satisfy user privacy requirements. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Location