scholarly journals Improved Two Hidden Layers Extreme Learning Machines for Node Localization in Range Free Wireless Sensor Networks

2021 ◽  
pp. 528-534
Author(s):  
Oumaima Liouane ◽  
◽  
Smain Femmam ◽  
Toufik Bakir ◽  
Abdessalem Ben Abdelali
Keyword(s):  
Extreme Learning Machine ◽  
Wireless Sensor ◽  
Isotropic Case ◽  
Localization Algorithm ◽  
Node Localization ◽  
Practical Applications ◽  
Learning Machines ◽  
Learning Machine ◽  
Hidden Layer ◽  
Range Free

Wireless Sensor Network (WSN) architectures are widely used in a variety of practical applications. In most cases of application, the event information transmitted by a sensor node via the network has no significance without the knowledge of its accurate geographical localization. In this paper, a method based on Machine Learning Technique (MLT) is proposed to improve node accuracy localization in WSN. We propose a Single Hidden Layer Extreme Learning Machine (SHL-ELM) and a Two Hidden Layer Extreme Learning Machine (THL-ELM) based methods for nodes localization in WSN. The suggested methods are applied in different Multi-hop WSN deployment cases. We focused on range-free localization algorithm in isotropic case and irregular environments. Simulation results demonstrate that the proposed THL-ELM algorithm greatly minimizes the average localization errors when compared to the Single Hidden Layer Extreme Learning Machine and the Distance Vector Hop (DV- Hop) algorithm.

scholarly journals Online Regularized and Kernelized Extreme Learning Machines with Forgetting Mechanism

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Xinran Zhou ◽  
Zijian Liu ◽  
Congxu Zhu
Keyword(s):  
Extreme Learning Machine ◽  
Feedforward Neural Networks ◽  
Matrix Inversion ◽  
Time Varying ◽  
Extreme Learning Machines ◽  
Learning Machines ◽  
Matrix Expansion ◽  
Learning Machine ◽  
Hidden Layer ◽  
Forgetting Mechanism

To apply the single hidden-layer feedforward neural networks (SLFN) to identify time-varying system, online regularized extreme learning machine (ELM) with forgetting mechanism (FORELM) and online kernelized ELM with forgetting mechanism (FOKELM) are presented in this paper. The FORELM updates the output weights of SLFN recursively by using Sherman-Morrison formula, and it combines advantages of online sequential ELM with forgetting mechanism (FOS-ELM) and regularized online sequential ELM (ReOS-ELM); that is, it can capture the latest properties of identified system by studying a certain number of the newest samples and also can avoid issue of ill-conditioned matrix inversion by regularization. The FOKELM tackles the problem of matrix expansion of kernel based incremental ELM (KB-IELM) by deleting the oldest sample according to the block matrix inverse formula when samples occur continually. The experimental results show that the proposed FORELM and FOKELM have better stability than FOS-ELM and have higher accuracy than ReOS-ELM in nonstationary environments; moreover, FORELM and FOKELM have time efficiencies superiority over dynamic regression extreme learning machine (DR-ELM) under certain conditions.

An Improved DV-HOP Localization Algorithm Based on Simulation Curve Fitting

2013 ◽  
Vol 684 ◽  
pp. 390-393 ◽  
Author(s):  
Lin Chen ◽  
Zhi Yi Fang ◽  
Wei Lv ◽  
Zhuang Liu
Keyword(s):  
Wireless Sensor Network ◽  
Curve Fitting ◽  
Wireless Sensor ◽  
Localization Algorithm ◽  
Node Localization ◽  
Centroid Algorithm ◽  
Key Technologies ◽  
Accurate Position ◽  
Beacon Node ◽  
Range Free

Localization technology is one of the key technologies in Wireless Sensor Network (WSN). The Centroid algorithm, DV-HOP algorithm, APIT algorithm and Amorphous are the classic algorithms which are based on Range-free localization algorithm. This paper is improved on the basis of the DV-HOP and Weighted DV-HOP node localization algorithm, proposed an improved DV-HOP and weighted DV-HOP of WSN localization algorithm based on Simulation Curve Fitting (SCF). The SCF algorithm makes the process more refined during selecting the beacon node and the selected beacon node can be closer to the accurate position.

scholarly journals Elliot and Symmetric Elliot Extreme Learning Machines for Gaussian Noisy Industrial Thermal Modelling

Energies ◽  
2018 ◽  
Vol 12 (1) ◽  
pp. 90 ◽  
Author(s):  
Jose Salmeron ◽  
Antonio Ruiz-Celma
Keyword(s):  
Extreme Learning Machine ◽  
Support Vector ◽  
Thermal Processes ◽  
Drying Process ◽  
Machine Model ◽  
Learning Machines ◽  
Nearest Neighbours ◽  
Thermal Drying ◽  
Learning Machine ◽  
Hidden Layer

This research proposes an Elliot-based Extreme Learning Machine approach for industrial thermal processes regression. The main contribution of this paper is to propose an Extreme Learning Machine model with Elliot and Symmetric Elliot activation functions that will look for the fittest number of neurons in the hidden layer. The methodological proposal is tested on an industrial thermal drying process. The thermal drying process is relevant in many industrial processes such as the food industry, biofuels production, detergents and dyes in powder production, pharmaceutical industry, reprography applications, textile industries and others. The methodological proposal of this paper outperforms the following techniques: Linear Regression, k-Nearest Neighbours regression, Regression Trees, Random Forest and Support Vector Regression. In addition, all the experiments have been benchmarked using four error measurements (MAE, MSE, MEADE, R 2 ).

Improved DV-Hop Algorithm for Enhancing Localization Accuracy in WSN

2014 ◽  
Vol 543-547 ◽  
pp. 3256-3259 ◽  
Author(s):  
Da Peng Man ◽  
Guo Dong Qin ◽  
Wu Yang ◽  
Wei Wang ◽  
Shi Chang Xuan
Keyword(s):  
Sensor Nodes ◽  
Wireless Sensor ◽  
Localization Error ◽  
Localization Algorithm ◽  
Node Localization ◽  
Localization Accuracy ◽  
Global Average ◽  
Key Technologies ◽  
Simulation Results ◽  
Range Free

Node Localization technology is one of key technologies in wireless sensor network. DV-Hop localization algorithm is a kind of range-free algorithm. In this paper, an improved DV-Hop algorithm aiming to enhance localization accuracy is proposed. To enhance localization accuracy, average per-hop distance is replaced by corrected value of global average per-hop distance and global average per-hop error. When calculating hop distance, unknown nodes use corresponding average per-hop distance expression according to different hop value. Comparison with DV-Hop algorithm, simulation results show that the improved DV-Hop algorithm can reduce the localization error and enhance the accuracy of sensor nodes localization more effectively.

scholarly journals A Hybrid Model of Extreme Learning Machine Based on Bat and Cuckoo Search Algorithm for Regression and Multiclass Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Qinwei Fan ◽  
Tongke Fan
Keyword(s):  
Extreme Learning Machine ◽  
Learning Algorithm ◽  
Search Algorithm ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Classification Problems ◽  
Neural Network Learning ◽  
Practical Applications ◽  
Learning Machine ◽  
Hidden Layer

Extreme learning machine (ELM), as a new simple feedforward neural network learning algorithm, has been extensively used in practical applications because of its good generalization performance and fast learning speed. However, the standard ELM requires more hidden nodes in the application due to the random assignment of hidden layer parameters, which in turn has disadvantages such as poorly hidden layer sparsity, low adjustment ability, and complex network structure. In this paper, we propose a hybrid ELM algorithm based on the bat and cuckoo search algorithm to optimize the input weight and threshold of the ELM algorithm. We test the numerical experimental performance of function approximation and classification problems under a few benchmark datasets; simulation results show that the proposed algorithm can obtain significantly better prediction accuracy compared to similar algorithms.

scholarly journals Toward deep neural networks: Mirror extreme learning machines for pattern classification

Filomat ◽  
2020 ◽  
Vol 34 (15) ◽  
pp. 4985-4996
Author(s):  
Bolin Liao ◽  
Chuan Ma ◽  
Meiling Liao ◽  
Shuai Li ◽  
Zhiguan Huang
Keyword(s):  
Neural Network ◽  
Extreme Learning Machine ◽  
Pattern Classification ◽  
Simple Structure ◽  
Layer Structure ◽  
Feed Forward Neural Network ◽  
Learning Machines ◽  
S Parameter ◽  
Learning Machine ◽  
Hidden Layer

In this paper, a novel type of feed-forward neural network with a simple structure is proposed and investigated for pattern classification. Because the novel type of forward neural network?s parameter setting is mirrored with those of the Extreme Learning Machine (ELM), it is termed the mirror extreme learning machine (MELM). For the MELM, the input weights are determined by the pseudoinverse method analytically, while the output weights are generated randomly, which are completely different from the conventional ELM. Besides, a growing method is adopted to obtain the optimal hidden-layer structure. Finally, to evaluate the performance of the proposed MELM, abundant comparative experiments based on different real-world classification datasets are performed. Experimental results validate the high classification accuracy and good generalization performance of the proposed neural network with a simple structure in pattern classification.

scholarly journals A Node Localization Algorithm for Wireless Sensor Networks Based on Virtual Partition and Distance Correction

Information ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 330
Author(s):  
Yinghui Meng ◽  
Qianying Zhi ◽  
Minghao Dong ◽  
Weiwei Zhang
Keyword(s):  
Search Algorithm ◽  
Optimal Path ◽  
Distance Estimation ◽  
Wireless Sensor ◽  
Localization Algorithm ◽  
Node Localization ◽  
Path Search ◽  
Communication Path ◽  
Range Free ◽  
Distance Correction

The coordinates of nodes are very important in the application of wireless sensor networks (WSN). The range-free localization algorithm is the best method to obtain the coordinates of sensor nodes at present. Range-free localization algorithm can be divided into two stages: distance estimation and coordinate calculation. For reduce the error in the distance estimation stage, a node localization algorithm for WSN based on virtual partition and distance correction (VP-DC) is proposed in this paper. In the distance estimation stage, firstly, the distance of each hop on the shortest communication path between the unknown node and the beacon node is calculated with the employment of virtual partition algorithm; then, the length of the shortest communication path is obtained by summing the distance of each hop; finally, the unknown distance between nodes is obtained according to the optimal path search algorithm and the distance correction formula. This paper innovative proposes the virtual partition algorithm and the optimal path search algorithm, which effectively avoids the distance estimation error caused by hop number and hop distance, and improves the localization accuracy of unknown nodes.

Sign in / Sign up

Export Citation Format

Share Document