Batch linear least squares-based learning algorithm for MLMVN with soft margins

Aizenberg, Evgeni; Aizenberg, Igor

doi:10.1109/cidm.2014.7008147

Cited by 11 publications

(19 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second advantage is derivative free learning, which does not suffer from the local minima phenomenon [29]. The third advantage is the ability of MLMVN to employ a batch learning algorithm [30,34], which adjusts the weights not moving from one learning sample to another, but for the entire learning set after the errors were calculated for all learning samples. Specifically, to improve generalization capability when solving classification problems, a soft margin technique was introduced for MLMVN in [28].…”

Section: Multilayer Neural Network With Multi-valued Neurons (Mlmvn) mentioning

confidence: 99%

See 1 more Smart Citation

A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, we present a new method designed to recognize single parametric faults in analog circuits. The technique follows a rigorous approach constituted by three sequential steps: calculating the testability and extracting the ambiguity groups of the circuit under test (CUT); localizing the failure and putting it in the correct fault class (FC) via multi-frequency measurements or simulations; and (optional) estimating the value of the faulty component. The fabrication tolerances of the healthy components are taken into account in every step of the procedure. The work combines machine learning techniques, used for classification and approximation, with testability analysis procedures for analog circuits.

show abstract

Section: Multilayer Neural Network With Multi-valued Neurons (Mlmvn) mentioning

confidence: 99%

“…Then, some modifications were made in this algorithm and it was generalized for any number of output neurons and hidden layers. Moreover, soft margins introduced for MLMVN in [28] were incorporated in the batch algorithm [34]. We used this algorithm exactly as it was presented in [34].…”

Section: Multilayer Neural Network With Multi-valued Neurons (Mlmvn) mentioning

confidence: 99%

A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The used intelligent classifier is a complex neural network, that presents excellent performances compared to other machinelearning techniques. It is based on a feedforward multilayer neural network with multi-valued neurons (MLMVN), characterized by a derivative free learning algorithm [25], an alternative algorithm based on the linear least square (LLS) methods [26] to reduce the high computational cost of the original backpropagation procedure, a soft margin method [27,28] in order to make the network a good classifier. Further details will be given later in the application description.…”

Section: Neural Network Trainingmentioning

confidence: 99%

Neural Network-Based Fault Diagnosis of Joints in High Voltage Electrical Lines

Bindi¹,

Aizenberg²,

Belardi³

et al. 2020

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

In this paper a classification system based on a complex-valued neural network is used to evaluate the health state of joints in high voltage overhead transmission lines. The aim of this method is to prevent breakages on the joints through the frequency response measurements obtained at the initial point of the network. The specific advantage of this kind of measure is to be non-intrusive and therefore safer than other approaches, also considering the high voltage nature of the lines. A feedforward multi-layer neural network with multi-valued neurons is used to achieve the goal. The results obtained for power lines characterized by three and four junction regions show that the system is able to identify the health state of each joint, with an accuracy level greater than 90%.

show abstract

“…This learning rule allows the correction of the weights for each sample of the dataset s (s = 1, • • • , N s ). As shown in [37,38] the correction of the weights can be obtained through a derivative free learning rule and this is one of the most important advantages of using a complex neural network over other classifiers. This procedure can be applied step by step for each layer and each sample or through an algorithm based on the linear least square (LLS) method reducing the computational cost [39].…”

Section: Complex Neural Networkmentioning

confidence: 99%

“…where ∆W k,m i is the correction for the i-th weight of the k-th neuron belonging to the layer m, α k,m is the corresponding learning rate, n m−1 is the number of the inputs equal to the number of the outputs of the previous layer, z s k,m is the magnitude of the weighted sum, δ s k,m is the output error obtained through the backpropagation method and Y s i,m−1 is the conjugate-transposed of the input. In this way, it is possible to organize a very efficient batch learning algorithm based on the LLS method [37]. When using this algorithm, the output error is calculated for each neuron and each sample and saved in a specific matrix at the end of every training epoch.…”

Section: Complex Neural Networkmentioning

confidence: 99%

Failure Prevention and Malfunction Localization in Underground Medium Voltage Cables

et al. 2020

Self Cite

View full text Add to dashboard Cite

A smart monitoring system capable of detecting and classifying the health conditions of MV (Medium Voltage) underground cables is presented in this work. Using the analysis technique proposed here, it is possible to prevent the occurrence of catastrophic failures in medium voltage underground lines, for which it is generally difficult to realize maintenance operations and carry out punctual inspections. This prognostic method is based on Frequency Response Analysis (FRA) and can be used online during normal network operation, resulting in a minimally invasive tool. In order to obtain the good results shown in the simulation section, it is necessary to develop a lamped equivalent circuit of the network branch under consideration. The standard π-model is used in this paper to analyse sections of a medium voltage cable and the parameter variations with temperature are used to classify the state of health of the line. In fact, the variation of the electrical parameters produces a corresponding variation in the frequency response. The proposed system is based on the use of a complex neural network with feedforward architecture. It processes the frequency response, allowing the classification of the cable conditions with an accuracy higher than 90%.

show abstract

Batch linear least squares-based learning algorithm for MLMVN with soft margins

Cited by 11 publications

References 20 publications

A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

Neural Network-Based Fault Diagnosis of Joints in High Voltage Electrical Lines

Failure Prevention and Malfunction Localization in Underground Medium Voltage Cables

Contact Info

Product

Resources

About