Multi-Objective Optimization for Location Prediction of Mobile Devices in Sensor-Based Applications

Peng, Qinglan; Zhou, MengChu; He, Qiang; Xia, Yunni; Wu, Chunrong; Deng, Shuiguang

doi:10.1109/access.2018.2869897

Cited by 39 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In straightforward terms, mutation might be characterized as a little arbitrary change in the chromosome, to get another arrangement. A case of a mutation administrator includes a likelihood that a discretionary piece in a genetic grouping will be transformed from its unique state [7]. A typical strategy for actualizing the mutation administrator includes producing an irregular variable for each piece in an arrangement.…”

Section: Phase 4: Crossovermentioning

confidence: 99%

A Genetic Algorithm based task scheduling procedure for Cost-Efficient Cloud Data Centers

Prabha¹,

Ramesh²,

Geetha³

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

View full text Add to dashboard Cite

In the current situation, Cloud computing cut itself as a developing innovation which empowers the association to use equipment, programming and applications with no forthright expense over the internet space. The main provocation for the cloud provider is the means of providing productively and adequately the hidden computing assets like virtual machines, arrange, capacity units, and transmission capacity and so forth ought to be overseen with the goal that no computing gadget is in under-usage or over-use state in a unique domain. A decent task scheduling method is constantly required for the dynamic assignment of the task to evade such a circumstance. Through this paper we are going to introduce the Genetic Algorithm based task scheduling procedure, which will disperse the heap adequately among the virtual machine so the general reaction time (QoS) ought to be insignificant. An examination of this Genetic Algorithm based task scheduling procedure is performed on CloudSim test system which shows that, this will beat the current strategies like Greedy based, First-Come first-Serve (FCFS) methods.

show abstract

Section: Phase 4: Crossovermentioning

confidence: 99%

A Genetic Algorithm based task scheduling procedure for Cost-Efficient Cloud Data Centers

Prabha¹,

Ramesh²,

Geetha³

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

View full text Add to dashboard Cite

show abstract

“…Details can be found in Section IV-A. 2 Finally, existing similarity computation methods of users' GPS trajectories fail to meet the distance metric axioms. To address the problem, we convert users' distance to an optimal solution of a balanced transportation problem.…”

Section: Definition 3 (Stay Region): a Stay Region Sr Is A Geographicmentioning

confidence: 99%

“…These data contain valuable information for user behavior analysis. For instance, many efforts have been devoted to analyze users' spatiotemporal data to provide location-based services, such as location prediction [1], [2], location recommendation [3], [4], friend recommendation [5], [6], community discovery [7], [8] and link prediction [9]. For the above applications, the user similarity measure is an extremely important step.…”

Section: Introductionmentioning

confidence: 99%

A Semantic User Distance Metric Using GPS Trajectory Data

et al. 2019

View full text Add to dashboard Cite

User similarity measure plays an important role in various location-based services including location prediction and recommendation. However, existing similarity computation methods fail to meet the distance metric axioms. In addition, existing works also suffer from some deficiency when identifying indoor stay regions and representing semantic information. To address these issues, this paper proposes a new method to evaluate user similarity by analyzing the global positioning system (GPS) trajectory data. Specifically, a more accurate algorithm for indoor stay region identification is proposed by taking velocity into account. Word embedding technique is used to compute the semantic distance between two stay regions. After that, stay regions are clustered and the user's GPS trajectories are represented as a multiset of semantic label sequences. Then a distance metric of these multisets satisfying the distance metric axioms is proposed on the basis of the balanced transportation problem. Finally, the effectiveness of the proposed method is evaluated by experiments using both synthetic and real-life datasets.

show abstract

“…Next, we will carry out further convergence analysis on (36), and prove that the weight vector θ (t) can converge to the eigenvector corresponding to the minimum eigenvalue σ m of the autocorrelation matrix. According to (35) and (45), it can be known that for all t ≥ 0, there are…”

Section: Improved Mca Algorithm With Fast Convergencementioning

confidence: 99%

“…As a powerful tool for data analysis, neural networks has been successfully used in many practical applications [4], [5], [7], [9], [10], [12], [14]- [20], [22]- [24], [28], [33], [36], [37], [40], [43]- [45], in which neural network learning algorithms play an essential role. MCA neural network algorithms are usually represented as Stochastic Discrete Time (SDT) systems.…”

Section: Introductionmentioning

confidence: 99%

An Improved Minor Component Analysis Algorithm Based on Convergence Analysis of 5G Multi-Dimensional Signals

Chen

Peng

et al. 2019

IEEE Access

View full text Add to dashboard Cite

With the availability of 5G, multi-dimensional signals' characteristic analysis becomes more challenging. Minor component analysis (MCA) is a useful data analysis approach to estimate the important features of multi-dimensional signals. MCA neural network approaches can extract minor components from real-time data streams not only adaptively but also online. The rapid convergence of MCA neural network approaches is valuable in practical applications. We propose a deterministic discrete time-based method to analyze the convergence performance of MCA neural network algorithms and reveal the effects of initial weight vectors' norm in MCA algorithms on convergence speed. Then, based on the convergence analysis, a new MCA algorithm is proposed to achieve faster convergence than existing MCA algorithms, which are proven by both the theoretical analysis and simulation results.INDEX TERMS 5G, minor component analysis (MCA), neural networks, Eigen value, deterministic discrete time (DDT) method.

show abstract

Multi-Objective Optimization for Location Prediction of Mobile Devices in Sensor-Based Applications

Cited by 39 publications

References 21 publications

A Genetic Algorithm based task scheduling procedure for Cost-Efficient Cloud Data Centers

A Genetic Algorithm based task scheduling procedure for Cost-Efficient Cloud Data Centers

A Semantic User Distance Metric Using GPS Trajectory Data

An Improved Minor Component Analysis Algorithm Based on Convergence Analysis of 5G Multi-Dimensional Signals

Contact Info

Product

Resources

About