Classification of Time Signals Using Machine Learning Techniques

被引：0

作者：

Jadoon, Ishfaq Ahmad ^{[1
]}

Logofatu, Doina ^{[1
]}

Islam, Mohammad Nahin ^{[1
]}

机构：

[1] Frankfurt Univ Appl Sci, Frankfurt, Germany

来源：

24TH INTERNATIONAL CONFERENCE ON ENGINEERING APPLICATIONS OF NEURAL NETWORKS, EAAAI/EANN 2023 | 2023年 / 1826卷

关键词：

Machine Learning; Deep Learning; Supervised Learning; Neural Network; Multi-Layer Perceptron (MLP); Hilbert-Huang Transform (HHT); Empirical Mode Decomposition (EMD); Object Classification; EMPIRICAL MODE DECOMPOSITION;

D O I：

10.1007/978-3-031-34204-2_8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This study presents a comprehensive overview of the classification of time signals over a variety of objects. Signals were initially processed using the Hilbert-Huang transform, followed by supervised machine learning and deep learning to classify objects. Multilayer Perceptron (MLP) and Support Vector Machines (SVM) were used for sound discrimination. The result is a program that effectively detects and classifies time signals as "Object 1" or "Not Object 1" (i.e., Object #2 and Object 3).

引用

页码：85 / 96

页数：12

共 18 条

[1]

Abe S, 2010, ADV PATTERN RECOGNIT, P1, DOI 10.1007/978-1-84996-098-4

[2]

Aery M.K., 2017, A Review on Machine Learning: Trends and Future Prospects

[3] Empirical mode decomposition based on Fourier transform and band-pass filter [J].

Chen, Zheng-Shou ;

Rhee, Shin Hyung ;

Liu, Gui-Lin .

INTERNATIONAL JOURNAL OF NAVAL ARCHITECTURE AND OCEAN ENGINEERING, 2019, 11 (02) :939-951

[4]

Frost J., 2020, Statistics By Jim. Overfitting Regression Models: Problems, Detection, and Avoidance, V1, P10

[5]

IBM, Artificial intelligence

[6]

Ju QC, 2022, COMMUN MATH SCI, V20, P1637, DOI 10.4310/CMS.2022.v20.n6.a8

[7]

Leite T.M., 2018, Medium, Neural Networks, Multilayer Perceptron and the Backpropagation Algorithm

[8]

Nicholson C, BEGINNERS GUIDE MULT

[9]

Peltarion, Categorical crossentropy

[10]

SAMUEL AL, 1959, IBM J RES DEV, V3, P211, DOI 10.1147/rd.441.0206

← 1 2 →