Wyniki wyszukiwania - BazTech

1

Convolutional neural networks in the SSI analysis for mine-induced vibrations

Zając Maciej, Kuźniar Krystyna

Computer Assisted Methods in Engineering and Science

|

2024

|

Vol. 31, no. 1

3--28

EN

Deep neural networks (DNNs) have recently become one of the most often used softcomputational tools for numerical analysis. The huge success of DNNs in the field of imageprocessing is associated with the use of convolutional neural networks (CNNs). CNNs,thanks to their characteristic structure, allow for the effective extraction of multi-layerfeatures. In this paper, the application of CNNs to one of the important soil-structureinteraction (SSI) problems, i.e., the analysis of vibrations transmission from the free-field next to a building to the building foundation, is presented in the case of mine-induced vibrations. To achieve this, the dataset from in-situ experimental measurements,containing 1D ground acceleration records, was converted into 2D spectrogram imagesusing either Fourier transform or continuous wavelet transform. Next, these images wereused as input for a pre-trained CNN. The output is a ratio of maximal vibration valuesrecorded simultaneously on the building foundation and on the ground. Therefore, the lastlayer of the CNN had to be changed from a classification to a regression one. The obtainedresults indicate the suitability of CNN for the analyzed problem.

2

Application of visual classification algorithms for identification of underwater audio signals

Gnyś Piotr, Szczęsna Gabriela, Dominguez-Brito Antonio C., Cabrera-Gámez Jorge

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

|

2022

|

Vol. 26, No 4

1-22

EN

An audio processing and classification pipeline is presented in this work. The main focus is on the classification of sounds in a marine acoustic environment, however, the presented approach can be applied to other audio data. Audio samples from heterogeneous sources automatically spliced, normalized and transformed into spectrogram based visual representation are tagged on the pipeline input. The said representation is then used to train a convolutional neural network that can identify the presented categories in future recordings.

3

Deep networks for image super-resolution using hierarchical features

Yang Xin, Zhang Yifan, Zhou Dake

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 1

art. no. e139616

EN

To better extract feature maps from low-resolution (LR) images and recover high-frequency information in the high-resolution (HR) images in image super-resolution (SR), we propose in this paper a new SR algorithm based on a deep convolutional neural network (CNN). The network structure is composed of the feature extraction part and the reconstruction part. The extraction network extracts the feature maps of LR images and uses the sub-pixel convolutional neural network as the up-sampling operator. Skip connection, densely connected neural networks and feature map fusion are used to extract information from hierarchical feature maps at the end of the network, which can effectively reduce the dimension of the feature maps. In the reconstruction network, we add a 3×3 convolution layer based on the original sub-pixel convolution layer, which can allow the reconstruction network to have better nonlinear mapping ability. The experiments show that the algorithm results in a significant improvement in PSNR, SSIM, and human visual effects as compared with some state-of-the-art algorithms based on deep learning.

4

Vibration-based identification of engine valve clearance using a convolutional neural network

Tabaszewski Maciej, Szymański Grzegorz M., Nowakowski Tomasz

Archives of Transport

|

2022

|

Vol. 61, iss. 1

117--131

EN

Contemporary operation-related requirements for combustion engines force the necessity of ongoing assessment of their in operation technical condition (e.g. marine engines). The engine efficiency and durability depend on a variety of parameters. One of them is valve clearance. As has been proven in the paper, the assessment of the valve clearance can be based on vibration signals, which is not a problem in terms of signal measurement and processing and is not invasive into the engine structure. The authors described the experimental research aiming at providing information necessary to develop and validate the proposed method. Active experiments were used with the task of valve clearance and registration of vibrations using a three-axis transducer placed on the engine cylinder head. The tests were carried out during various operating conditions of the engine set by 5 rotational speeds and 5 load conditions. In order to extract the training examples, fragments of the signal related to the closing of individual valves were divided into 11 shorter portions. From each of them, an effective value of the signal was determined. Obtained total 32054 training vectors for each valve related to 4 classes of valve clearance including very sensitive clearance above 0.8 mm associated with high dynamic interactions in cylinder head. In the paper, the authors propose to use a convolutional network CNN to assess the correct engine valve clearance. The obtained results were compared with other methods of machine learning (pattern recognition network, random forest). Finally, using CNN the valve clearance class identification error was less than 1% for the intake valve and less than 3.5% for the exhaust valve. Developed method replaces the existing standard methods based on FFT and STFT combined with regression calculation where approximation error is up to 10%. Such results are more useful for further studies related not only to classification, but also to the prediction of the valve clearance condition in real engine operations.

5

A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network

Kołodziej Marcin, Majkowski Andrzej, Tarnowski Paweł, Rak Remigiusz Jan, Rysz Andrzej

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e136921

EN

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

6

Plant classification based on leaf edges and leaf morphological veins using wavelet convolutional neural network

Dewi Wulan, Utomo Wiranto Herry

Applied Computer Science

|

2021

|

Vol. 17, no 1

81--89

EN

The leaf is one of the plant organs, contains chlorophyll, and functions as a catcher of energy from sunlight which is used for photosynthesis. Perfect leaves are composed of three parts, namely midrib, stalk, and leaf blade. The way to identify the type of plant is to look at the shape of the leaf edges. The shape, color, and texture of a plant's leaf margins may influence its leaf veins, which in this vein morphology carry information useful for plant classification when shape, color, and texture are not noticeable. Humans, on the other hand, may fail to recognize this feature because they prefer to see plants solely based on leaf form rather than leaf margins and veins. This research uses the Wavelet method to denoise existing images in the dataset and the Convolutional Neural Network classifies through images. The results obtained using the Wavelet Convolutional Neural Network method are equal to 97.13%.

7

Endoscopy image retrieval by Mixer Multi-Layer Perceptron

Trinh Quoc-Huy, Nguyen Minh-Van

Annals of Computer Science and Information Systems

|

2021

|

Vol. 26

223--226

EN

In Computer Vision, the Image Retrieval task is one of the interests of researchers, particularly medical image retrieval and endoscopy images. With the development of the Convolution Neural Network and Vision Transformer Technique, there are many proposals for using these techniques to make Image Retrieval Task and achieve a competitive result. In this paper, we propose a method that using Mixer Multi-Layer Perceptron architecture (Mixer-MLP) to build an Image Retrieval System with Medical images, particularly Endoscopic Images. This System base on the Classification process of Mixer-MLP architecture to generate vector representation for similarity cal- culation. The research result achieves competitively with efficient training time.

8

Robot sensor failure detection system based on convolutional neural networks for calculation of Euler angles

Świetlicka A., Kolanowski K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2020

|

Vol. 68, nr 6

1525--1533

EN

In this work, we present a failure detection system in sensors of any robot. It is based on the k-fold cross-validation approach and built from N neural networks, where N is the number of signals read from sensors. Our tests were carried out using an unmanned aerial vehicle (UAV, quadrocopter), where signals were read from three sensors: accelerometer, magnetometer and gyroscope. Artificial neural network was used to determine Euler angles, based on signals from these sensors. The presented system is an extension of the system that we proposed in one of our previous papers. The improvement shown in this work took place on two levels. The first one was related to improvement of a neural network՚s reproduction quality – we have replaced a recurrent neural network with a convolutional one. The second level was associated with the improvement of the validation process, i.e. with adding some new criteria to check the values of Euler՚s angles determined by the convolutional neural network in subsequent time steps. To highlight the proposed system improvement we present a number of indicators such as RMSE, NRMSE and NDR (Normalized Detection Ratio).

9

REGA: Real-Time Emotion, Gender, Age Detection Using CNN - A Review

Sharma Dibya Jyoti, Dutta Sachin, Bora Dibya Jyoti

Annals of Computer Science and Information Systems

|

2020

|

Vol. 24

115--118

EN

In this paper we describe a methodology and an algorithm to estimate the real-time age, gender, and emotion of a human by analyzing of face images on a webcam. Here we discuss the CNN based architecture to design a real-time model. Emotion, gender and age detection of facial images in webcam play an important role in many applications like forensics, security control, data analysis,video observation and human-computer interaction. In this paper we present some method \& techniques such as PCA,LBP, SVM, VIOLA-JONES, HOG which will directly or indirectly used to recognize human emotion, gender and age detection in various conditions.

10

Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

Kucharski Dariusz, Kajor Marcin, Grochala Dominik, Iwaniec Marek, Iwaniec Joanna

Advances in Science and Technology. Research Journal

|

2019

|

Vol. 13, no 2

112--118

EN

The auscultation technique has been widely used in medicine as a screening examination for ages. Nowadays, advanced electronics and effective computational methods aim to support the healthcare sector by providing dedicated solutions which help physicians and support diagnostic process. In this paper, we propose a machine learning approach for the analysis of heart sounds. We used the spectral analysis of acoustic signal to calculate feature vectors and tested a set of machine learning approaches to provide the most effective detection of cardiac disorders. Finally, we achieved 91% of sensitivity and 99% of positive predictivity for a designed algorithm based on convolutional neural network.