Distributed Memetic Algorithm for Outsourced Database Fragmentation

Ge, Yong-Feng; Yu, Wei; Cao, Jun; Wang, Hua; Zhan, Zhi-Hui; Zhang, Yanchun; Zhang, Jun

doi:10.1109/tcyb.2020.3027962

Cited by 56 publications

(19 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, how to evolve the network depth and topology of CNNs is worthy of further research. Also, more efficient optimization paradigms can be considered for CNN optimization in different scenarios, where potential optimization paradigms include data-driven optimization [61], large-scale optimization [62], dynamic optimization [63], many-objective optimization [64], multi-modal optimization [65], expensive optimization [66], and parallel [67] and distributed optimization [68]. In addition, the SHEDA is potential for solving more challenging learning tasks in complex real-world applications, such as healthcare application [69] and autonomous robot application [70], which will be further explored and studied.…”

Section: J Further Discussionmentioning

confidence: 99%

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

Zhan

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

The performance of a convolutional neural network (CNN) heavily depends on its hyperparameters. However, finding a suitable hyperparameters configuration is difficult, challenging, and computationally expensive due to three issues, which are 1) the mixed-variable problem of different types of hyperparameters; 2) the large-scale search space of finding optimal hyperparameters; and 3) the expensive computational cost for evaluating candidate hyperparameters configuration. Therefore, this article focuses on these three issues and proposes a novel estimation of distribution algorithm (EDA) for efficient hyperparameters optimization, with three major contributions in the algorithm design. First, a hybrid-model EDA is proposed to efficiently deal with the mixed-variable difficulty. The proposed algorithm uses a mixed-variable encoding scheme to encode the mixed-variable hyperparameters and adopts an adaptive hybrid-model learning (AHL) strategy to efficiently optimize the mixed-variables. Second, an orthogonal initialization (OI) strategy is proposed to efficiently deal with the challenge of large-scale search space. Third, a surrogate-assisted multi-level evaluation (SME) method is proposed to reduce the expensive computational cost. Based on the above, the proposed algorithm is named surrogateassisted hybrid-model EDA (SHEDA). For experimental studies,

show abstract

Section: J Further Discussionmentioning

confidence: 99%

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

Zhan

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Generally, privacy and utility [ 31 , 32 ] are two significant metrics to measure privacy pretection technology. In this section, we implement experiments on a real-world dataset to evaluate the performance of our scheme in terms of the privacy and the utility.…”

Section: Evaluation Setupmentioning

confidence: 99%

“…For the other hand, a review for a POI indicates that the owner has visited this POI. The attacker can obtain the historical trajectory of the target user by collecting (such as cyber attack [ 4 ], information sharing [ 5 ], etc.) and analyzing the historical review data of the target user.…”

Section: Introductionmentioning

confidence: 99%

Exchanging registered users’ submitting reviews towards trajectory privacy preservation for review services in Location-Based Social Networks

Wang

Xin

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

In Location-Based Social Networks (LBSNs), registered users submit their reviews for visited point-of-interests (POIs) to the system providers (SPs). The SPs anonymously publish submitted reviews to build reputations for POIs. Unfortunately, the user profile and trajectory contained in reviews can be easily obtained by adversaries who SPs has compromised with. Even worse, existing techniques, such as cryptography and generalization, etc., are infeasible due to the necessity of public publication of reviews and the facticity of reviews. Inspired by pseudonym techniques, we propose an approach to exchanging reviews before users submit reviews to SPs. In our approach, we introduce two attacks, namely review-based location correlation attack (RLCA) and semantic-based long-term statistical attack (SLSA). RLCA can be exploited to link the real user by reconstructing the trajectory, and SLSA can be launched to establish a connection between locations and users through the difference of semantic frequency. To resist RLCA, we design a method named User Selection to Resist RLCA (USR-RLCA) to exchange reviews. We propose a metric to measure the correlation between a user and a trajectory. Based on the metric, USR-RLCA can select reviews resisting RLCA to exchange by suppressing the number of locations on each reconstructed trajectory below the correlation. However, USR-RLCA fails to resist SLSA because of ignoring the essential semantics. Hence, we design an enhanced USR-RLCA named User Selection to Resist SLSA (USR-SLSA). We first propose a metric to measure the indistinguishability of locations concerning the difference of semantic frequency in a long term. Then, USR-SLSA can select reviews resisting SLSA to exchange by allowing two reviews whose indistinguishability is below the probability difference after the exchange to be exchanged. Evaluation results verify the effectiveness of our approach in terms of privacy and utility.

show abstract

“…This considers a logically outrageous issue with the devices since they are alive anyway, identifying inaccurately. Therefore, services fail at the application level either due to middleware erroror the physical layer [6]. Therefore, failures in such dynamic and interactive systems can result in user displeasure.…”

Section: Figure 1 Architecture Of Sensor Network Applicationmentioning

confidence: 99%

Fault Detection in Wireless Sensor Network Based on Deep Learning Algorithms

Regin¹,

Rajest

Singh

2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

This paper is about Fault detection over a wireless sensor network in a fully distributed manner. First, we proposed the Convex hull algorithm to calculate a set of extreme points with the neighbouring nodes and the duration of the message remains restricted as the number of nodes increases. Second, we proposed a Naïve Bayes classifier and convolution neural network (CNN) to improve the convergence performance and find the node faults. Finally, we analyze convex hull, Naïve bayes and CNN algorithms using real-world datasets to identify and organize the faults. Simulation and experimental outcomes retain feasibility and efficiency and show that the CNN algorithm has better-identified faults than the convex hull algorithm based on performance metrics.

show abstract

Distributed Memetic Algorithm for Outsourced Database Fragmentation

Cited by 56 publications

References 53 publications

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

Exchanging registered users’ submitting reviews towards trajectory privacy preservation for review services in Location-Based Social Networks

Fault Detection in Wireless Sensor Network Based on Deep Learning Algorithms

Contact Info

Product

Resources

About