A new method of data missing estimation with FNN-based tensor heterogeneous ensemble learning for internet of vehicle

Zhang, Ting; Zhang, Degan; Yan, Haoran; Qiu, Jianning; Gao, Jin-xin

doi:10.1016/j.neucom.2020.09.042

Cited by 135 publications

(82 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, many scholars at home and abroad have studied the coverage optimization of WSNs. [5][6][7][8][9][10] The main purpose of the topology control and optimal coverage is to improve the efficiency of the network, balance the energy consumption, and increase the coverage of the network. The commonly used methods include the power control and the hierarchical topology design to optimize the communication link to reduce the energy consumption and improve the performance of WSNs.…”

Section: Related Workmentioning

confidence: 99%

A novel topology optimization of coverage-oriented strategy for wireless sensor networks

Wang

You

Yue

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Aiming at the key optimization problems of wireless sensor networks in complex industrial application environments, such as the optimum coverage and the reliability of the network, a novel topology optimization of coverage-oriented strategy for wireless sensor networks based on the wolf pack algorithm is proposed. Combining the characteristics of topology structure of wireless sensor networks and the optimization idea of the wolf pack algorithm redefines the group’s wandering and surprise behavior. A novel head wolf mutation strategy is proposed, which increases the neighborhood search range of the optimal solution, enhances the uniformity of wolf pack distribution and the ergodicity ability of the wolf pack search, and greatly improves the calculation speed and the accuracy of the wolf pack algorithm. With the same probability, the cluster heads are randomly selected periodically, and the overall energy consumption of wireless sensor networks is evenly distributed to the sensor node to realize the balanced distribution of the data of the member nodes in the cluster and complete the design of the topology optimization of wireless sensor networks. Through algorithm simulation and result analysis, compared with the particle swarm optimization algorithm and artificial fish swarm algorithm, the wolf swarm algorithm shows its advantages in terms of the residual energy of the sensor node, the average transmission delay, the average packet delivery rate, and the coverage of the network. Among them, compared with the particle swarm optimization algorithm and artificial fish swarm algorithm, the remaining energy of nodes has increased by 9.5% and 15.5% and the average coverage of the network has increased by 10.5% and 5.6%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

A novel topology optimization of coverage-oriented strategy for wireless sensor networks

Wang

You

Yue

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Finally, a hybrid meta‐heuristic process with Hybrid Ant Colony and Artificial Bee Colony Optimization Algorithm 18 is used to select the efficient CH. The Artificial Bee Colony (ABC) avoids the intensification of Ant Colony Optimization (ACO) and takes care of constraints associated with exploration and delayed convergence through exploitation.…”

Section: Related Workmentioning

confidence: 99%

“…The techniques in Zhang 18 and Shankar et al 19 address the problem with exploitation and exploration; however, they fail to address the issues related to the solution failing within optimal solution, i.e., premature convergence. This leads to the poor selection of optimal CH and hence the energy efficiency associated with premature convergence fails.…”

Section: Related Workmentioning

confidence: 99%

Balanced wireless sensor networks with energy efficient bees swarm–harmony Search–Hill Climbing mechanism

Kavitha¹,

Singaravel²

2021

Int J Communication

View full text Add to dashboard Cite

Summary Wireless sensor networks (WSNs) are widely employed in various sectors, which include health care, military, automotive, and manufacturing sectors. Most of these applications use WSN with certain limitations in terms of its computational power, storage capability, and energy supply. Among this, energy supply is considered to be a major limitation for these sectors. Therefore, prolonging the lifetime of the network by improving the energy efficiency in WSN is a common objective in many types of research. In this research, the WSN energy efficiency is improved using the data aggregation clustering technique by balancing the energy consumption among the sensor nodes. To balance the energy consumption, an efficient selection of cluster heads is required with faster convergence and an improved search pattern. In accomplishing this, a hybrid architecture that combines Bees Swarm Optimization (BSO) with Harmony Search Algorithm (HSA) is used. The combination of both BSO and HSA tends to achieve premature convergence that leads to poor selection of cluster head. Hence, to increase the optimal and faster convergence, the proposed system uses the Hill Climbing algorithm to reach the optimal solution with faster convergence in a shorter computational time. The experiments are conducted with various node densities between the proposed and existing methods. The result shows that the proposed method is active in improving the search capability in effectively finding the cluster heads for improved routing paths.

show abstract

“…Effective communication 16 in a secured way, distributed sensing, and high computation with the collaboration of SNs are part of WSN. The communication between both shared information and two remote nodes is enabled via WSN networking.…”

Section: Introductionmentioning

confidence: 99%

Improved hybrid cuckoo black widow optimization with interval type 2 fuzzy logic system for energy‐efficient clustering protocol

Sheriba

Rajesh

2021

Int J Communication

View full text Add to dashboard Cite

Summary Recently, due to its excellent performance with the limited resources the wireless sensor network (WSN) is a challenging research area. The WSN consists of the number of nodes and power resources with limited energy parameters, but it comprises few difficulties. The energy‐efficient distributed clustering (HEED) is an efficient routing protocol in recent years. This paper proposes IHCBW with interval type 2 fuzzy logic system‐based HEED (IIT2FLS‐HEED) method. We used the combination of cuckoo search (CS) and improved black widow optimization (IBWO) algorithms (IHCBW) for the selection of optimal residual energy selection. The optimal cluster heads (CHs) are chosen with the help of the interval type 2 fuzzy logic system (IT2FLS). Experimentally, the NS2 software handles the entire proposed work and its performance is evaluated with different kinds of performance evaluation. Moreover, 20 benchmark functions are used to validate the performance of the IHCBW algorithm. Finally, the proposed IIT2FLS‐HEED demonstrates better performance results in terms of homogenous, second, and third stage heterogeneous WSN.

show abstract

A new method of data missing estimation with FNN-based tensor heterogeneous ensemble learning for internet of vehicle

Cited by 135 publications

References 38 publications

A novel topology optimization of coverage-oriented strategy for wireless sensor networks

A novel topology optimization of coverage-oriented strategy for wireless sensor networks

Balanced wireless sensor networks with energy efficient bees swarm–harmony Search–Hill Climbing mechanism

Improved hybrid cuckoo black widow optimization with interval type 2 fuzzy logic system for energy‐efficient clustering protocol

Contact Info

Product

Resources

About