Back propagation neural network with adaptive differential evolution algorithm for time series forecasting

Wang, Lin; Zeng, Yi; Chen, Tao

doi:10.1016/j.eswa.2014.08.018

Cited by 527 publications

(232 citation statements)

References 45 publications

Supporting

Mentioning

226

Contrasting

Unclassified

Order By: Relevance

“…SVM is a training approach that is widely used in classification and regression analysis; it has an efficient capacity of generalization [60]. BPNN is one of the most popular algorithms in the neural network, which has potential for estimating forest biomass, as it can deal with complex linear or nonlinear relationships of reflectivity data and vegetation parameters [61]. Typically, the KNN method is frequently applied to a model when the number of samples is small, and given that the redundancy of the result is low, it is suitable for forest biomass estimation at a regional scale [62].…”

Section: Statistical Analysis and Modelingmentioning

confidence: 99%

Integrating Airborne LiDAR and Optical Data to Estimate Forest Aboveground Biomass in Arid and Semi-Arid Regions of China

Luodan

Pan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Forest Aboveground Biomass (AGB) is a key parameter for assessing forest productivity and global carbon content. In previous studies, AGB has been estimated using various prediction methods and types of remote sensing data. Increasingly, there is a trend towards integrating various data sources such as Light Detection and Ranging (LiDAR) and optical data. In this study, we constructed and compared the accuracies of five models for estimating AGB of forests in the upper Heihe River Basin in Northwest China. The five models were constructed using field and remotely-sensed data (optical and LiDAR) and algorithms including Random Forest (RF), Support Vector Machines (SVM), Back Propagation Neural Networks (BPNN), K-Nearest Neighbor (KNN) and the Generalized Linear Mixed Model (GLMM). Models based on the RF algorithm emerged as being the best among the five algorithms irrespective of the datasets used. The Random Forest AGB model, using only LiDAR data (R 2 = 0.899, RMSE = 14.0 t/ha) as the input data, was more effective than the one using optical data (R 2 = 0.835, RMSE = 22.724 t/ha). Compared to LiDAR or optical data alone, the AGB model (R 2 = 0.913, RMSE = 13.352 t/ha) that used the RF algorithm and integrated LiDAR and optical data was found to be optimal. Incorporation of terrain variables with optical data resulted in only slight improvements in accuracy. The models developed in this study could be useful for using integrated airborne LiDAR and passive optical data to accurately estimate forest biomass.

show abstract

Section: Statistical Analysis and Modelingmentioning

confidence: 99%

Integrating Airborne LiDAR and Optical Data to Estimate Forest Aboveground Biomass in Arid and Semi-Arid Regions of China

Luodan

Pan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Similarly, This network finds optimal values of weight matrix (i.e., ∈ × ) and bias vector (i.e., 3 ∈ ×1 ) too, while polling the output close to the label value, which indicates the real DDoS type. Before this model is able to classify any record collected from DDoS traffic, each layer needs to be trained with backpropagation algorithm [36], separately. Then, they are stacked together and finetuned to improve the performance of the entire model.…”

Section: Autoencoder-based Attack Classificationmentioning

confidence: 99%

OverWatch: A Cross-Plane DDoS Attack Defense Framework with Collaborative Intelligence in SDN

Han

Yang

Sun

et al. 2018

Security and Communication Networks

View full text Add to dashboard Cite

Distributed Denial of Service (DDoS) attacks are one of the biggest concerns for security professionals. Traditional middle-box based DDoS attack defense is lack of network-wide monitoring flexibility. With the development of software-defined networking (SDN), it becomes prevalent to exploit centralized controllers to defend against DDoS attacks. However, current solutions suffer with serious southbound communication overhead and detection delay. In this paper, we propose a cross-plane DDoS attack defense framework in SDN, called OverWatch, which exploits collaborative intelligence between data plane and control plane with high defense efficiency. Attack detection and reaction are two key procedures of the proposed framework. We develop a collaborative DDoS attack detection mechanism, which consists of a coarse-grained flow monitoring algorithm on the data plane and a finegrained machine learning based attack classification algorithm on the control plane. We propose a novel defense strategy offloading mechanism to dynamically deploy defense applications across the controller and switches, by which rapid attack reaction and accurate botnet location can be achieved. We conduct extensive experiments on a real-world SDN network. Experimental results validate the efficiency of our proposed OverWatch framework with high detection accuracy and real-time DDoS attack reaction, as well as reduced communication overhead on SDN southbound interface.

show abstract

“…Incorrectly selected values may lead to a sub-optimal results where the optimisation algorithm selects local optima rather than global optima. Wang et al (2015) propose the use of an adaptive differential evolution algorithm to select appropriate initial connection weights and thresholds. Kocadaǧlı and Aşıkgil (2014) use a Bayesian inference approach to train a ANN.…”

Section: Time Series Analysismentioning

confidence: 99%

A unified model for context-based behavioural modelling and classification

Dabrowski

Villiers

2015

Expert Systems with Applications

View full text Add to dashboard Cite

A unified Bayesian model that simultaneously performs behavioural modelling, information fusion and classification is presented. The model is expressed in the form of a dynamic Bayesian network (DBN). Behavioural modelling is performed by tracking the continuous dynamics of a entity and incorporating various contextual elements that influence behaviour. The entity is classified according to its behaviour. Classification is expressed as a conditional probability of the entity class given its tracked trajectory and the contextual elements. Inference in the DBN is performed using a derived Gaussian sum filter. The model is applied to classify vessels, according to their behaviour, in a maritime piracy situation. The novel aspects of this work include the unified approach to behaviour modelling and classification, the way in which contextual information is fused, the unique approach to classification according to behaviour and the associated derived Gaussian sum filter inference algorithm.

show abstract

Back propagation neural network with adaptive differential evolution algorithm for time series forecasting

Cited by 527 publications

References 45 publications

Integrating Airborne LiDAR and Optical Data to Estimate Forest Aboveground Biomass in Arid and Semi-Arid Regions of China

Integrating Airborne LiDAR and Optical Data to Estimate Forest Aboveground Biomass in Arid and Semi-Arid Regions of China

OverWatch: A Cross-Plane DDoS Attack Defense Framework with Collaborative Intelligence in SDN

A unified model for context-based behavioural modelling and classification

Contact Info

Product

Resources

About