Morphology of Convolutional Neural Network with Diagonalized Pooling

Peleshchak, Roman; Lytvyn, Vasyl; Mediakov, Oleksandr; Peleshchak, Ivan

doi:10.1007/978-3-031-27034-5_11

Cited by 4 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper [12] presents the structure of a convolutional neural network with diagonalised pooling (DiagPooling), which is symmetrical with respect to the main diagonal of the diagonalised pooling matrix. This symmetrical diagonalised pooling increases the model's performance when compared to CNNs that use classical pooling by 4%.…”

Section: Related Workmentioning

confidence: 99%

“…where y i -element of the output vector of probabilities of the object belonging to each class of mines; f softmax -softmax activation function; w ij -the element of the weight matrix between the first and second tacked layer; w jk -element of the weighting matrix between the input layer and the first hidden layer; and x k -element of the input vector of mine characteristics [12]. The size of the input layer is 3, the size of the first hidden layer is 7 and has the relu activation function, the second hidden layer has the same characteristics as the first, and the output layer has a size of 5 and the softmax activation function.…”

Section: Soil Typementioning

confidence: 99%

Section: Soil Typementioning

confidence: 99%

“…where yi-element of the output vector of probabilities of the object belonging to each class of mines; fsoftmax-softmax activation function; frelu-relu activation function; wli-an element of the weighting matrix between the second hidden layer and the original layer; wij-element of the weighting matrix between the first and second hidden layer; wjk-element of the weighting matrix between the input layer and the first hidden layer; and xkelement of the input vector of mine characteristics [12]. Thus, the main flow chart that describes the algorithm for classifying mines from different materials using the FLC-100 magnetic field sensor, depending on the types of soil and the height at which the sensor is located, is shown in Figure 3.…”

Section: 𝑖 ∈ {1; 5} ̅̅̅̅̅̅mentioning

confidence: 99%

See 3 more Smart Citations

Influence of the Symmetry Neural Network Morphology on the Mine Detection Metric

Peleshchak,

Lytvyn,

Nazarkevych

et al. 2024

Symmetry

View full text Add to dashboard Cite

Presently, active detectors are widely used to detect mines, providing high accuracy. However, the principle of the operation of active detectors can lead to the explosion of hidden mines. The novelty of this work is the development of the morphology of a neural network for the classification of mines made of different materials (metallic, semi-metallic, plastic) with high accuracy (99.23%), based on a vector of input features with the following components: the value of the output voltage of the FLC-100 magnetic field sensor, which measures magnetic field anomalies in the vicinity of mines with an accuracy of 10−10–10−4 Tesla; six different soil types, depending on the humidity; and the height at which the magnetic field sensor is located above the mine. Due to the fact that mines, when made of different materials (metallic, semi-metallic, plastic), have different magnetic properties, the neural network method of mine classification, based on the sensor data regarding anomalies of the magnetic field in the vicinity of mines, allows the classification of mines made of different materials. The accuracy of mine classification was assessed with two-layer and three-layer neural networks on various metrics (confusion matrix, ROC curves, accuracy–loss curves), using ADAM, RMSprop, and SGD optimisers, and analyses and comparisons were then carried out. The impact of asymmetry in the neuron number and the types of activation functions in the first and second hidden layers on the values of the accuracy and loss metrics was studied. In particular, it was established that the asymmetry of the number of neurons in the first and second hidden layers relative to the plane of symmetry between the hidden layers has a significant effect on the accuracy of the model (decrease in accuracy by 25%), while the loss function, when the symmetry of the neurons number in the hidden layers is violated, increases to a maximum of 50%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Soil Typementioning

confidence: 99%

Section: Soil Typementioning

confidence: 99%

Section: 𝑖 ∈ {1; 5} ̅̅̅̅̅̅mentioning

confidence: 99%

See 2 more Smart Citations

Influence of the Symmetry Neural Network Morphology on the Mine Detection Metric

Peleshchak,

Lytvyn,

Nazarkevych

et al. 2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…Data obtained using ultra-wideband radar, an MLP filter, and an oscillatory neural network are used for the detection of subsurface objects (Peleshchak, 2023). An important measure of mine action is educating the population about the dangers of explosive ordnance .…”

Section: Literature Reviewmentioning

confidence: 99%

Integrating Humanitarian Demining with Remote Control Tech in Educational Process

Dziuba,

Neroba,

Chukanov

et al. 2023

RDLUZ

View full text Add to dashboard Cite

The aim of the work is to investigate the possibility of introducing the system of humanitarian demining into the educational process of higher education institutions (HEIs) of Ukraine. The introduction of modern equipment against improvised explosive devices explosive items, for example remotely controlled ones, was also studied. Methods used: content analysis, semi-structured interviews, and self-assessment of the sapper’s competence. The conducted research for the first to describe the results of the possibility of introducing a system of humanitarian demining in HEIs of Ukraine, where it has not yet been introduced. It was found that educational institutions for military training in various fields have sufficient material and technical resources for professional training of demining personnel. It is also proposed to renew or renovate the demining equipment, as well as introduce a project activity on the development of remotely controlled mechanisms against explosive items into the educational process. The results can be useful to researchers and teachers who are working on updating the content of education in accordance with the current security needs. Further research should be conducted on the monitoring of new demining equipment.

show abstract

Neural Network Technology of Mine Recognition Based on Data From Magnetic Field Sensors

Peleshchak,

Lytvyn,

Peleshchak

et al. 2023

2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applicat

View full text Add to dashboard Cite

Morphology of Convolutional Neural Network with Diagonalized Pooling

Cited by 4 publications

References 11 publications

Influence of the Symmetry Neural Network Morphology on the Mine Detection Metric

Influence of the Symmetry Neural Network Morphology on the Mine Detection Metric

Integrating Humanitarian Demining with Remote Control Tech in Educational Process

Neural Network Technology of Mine Recognition Based on Data From Magnetic Field Sensors

Contact Info

Product

Resources

About