A Large-Scale UAV Audio Dataset and Audio-Based UAV Classification Using CNN

被引：8

作者：

Wang, Yaqin ^{[1
]}

Chu, Zhiwei ^{[1
]}

Ku, Ilmun ^{[2
]}

Smith, E. Cho ^{[1
]}

Matson, Eric T. ^{[1
]}

机构：

[1] Purdue Univ, W Lafayette, IN 47907 USA

[2] Hankuk Univ Foreign Studies, Seoul, South Korea

来源：

2022 SIXTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING, IRC | 2022年

关键词：

Drone Audio Dataset; UAV Classification; Machine Learning; Convolutional Neural Network; PARAMETRIC REPRESENTATIONS;

D O I：

10.1109/IRC55401.2022.00039

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The increased popularity and accessibility of UAVs may create potential threats. Researchers have been developing UAV detection and classification systems with different methods, including audio-based approach. However, the number of publicly available UAV audio datasets is limited. To fill this gap, we selected 10 different UAVs, ranging from toy hand drones to Class I drones, and recorded a total of 5215 seconds length of audio data generated from the flying UAVs. To the best of our knowledge, the proposed dataset is the largest audio dataset for UAVs so far. We further implemented a convolutional neural network (CNN) model for 10-class UAV classification and trained the model with the collected data. The overall test accuracy of the trained model is 97.7% and the test loss is 0.085.

引用

页码：186 / 189

页数：4

共 50 条

[41] AUDIO-BASED CONDITION MONITORING IN MILLING OF THE WORKPIECE MATERIAL WITH THE HARDNESS VARIATION USING SUPPORT VECTOR MACHINES AND CONVOLUTIONAL NEURAL NETWORKS [J].

Kothuru, Achyuth ;

Nooka, Sai Prasad ;

Liu, Rui .

PROCEEDINGS OF THE ASME 13TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE, 2018, VOL 4, 2018,

[42] Economic Fruit Trees Recognition in Hillsides: A CNN-Based Approach Using Enhanced UAV Imagery [J].

Hooshyar, Maral ;

Li, Yuan-Shuo ;

Chun Tang, Wen ;

Chen, Ling-Wei ;

Huang, Yueh-Min .

IEEE ACCESS, 2024, 12 :61991-62005

[43] UAV-Based Powerline Problem Inspection and Classification using Machine Learning Approaches [J].

Chandaliya, Mahavir ;

Goli, Teja Sree ;

Kotha, Swapna ;

Gao, Jerry .

2024 IEEE 10TH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND MACHINE LEARNING APPLICATIONS, BIGDATASERVICE 2024, 2024, :52-59

[44] Predicting Heart Rate at the Anaerobic Threshold Using a Machine Learning Model Based on a Large-Scale Population Dataset [J].

Nakayama, Atsuko ;

Iwata, Tomoharu ;

Sakuma, Hiroki ;

Kashino, Kunio ;

Tomoike, Hitonobu .

JOURNAL OF CLINICAL MEDICINE, 2025, 14 (01)

[45] Enhancing the Prediction of Episodes of Aggression in Patients with Dementia Using Audio-Based Detection: A Multimodal Late Fusion Approach with a Meta-Classifier [J].

Galanakis, Ioannis ;

Soldatos, Rigas Filippos ;

Karanikolas, Nikitas ;

Voulodimos, Athanasios ;

Voyiatzis, Ioannis ;

Samarakou, Maria .

APPLIED SCIENCES-BASEL, 2025, 15 (10)

[46] An Efficient Deep Representation Based Framework for Large-Scale Terrain Classification [J].

Yan, Yupeng ;

Rangarajan, Anand ;

Ranka, Sanjay .

2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, :940-945

[47] Large-scale optimization-based classification models in medicine and biology [J].

Lee, Eva K. .

ANNALS OF BIOMEDICAL ENGINEERING, 2007, 35 (06) :1095-1109

[48] Large-Scale Optimization-Based Classification Models in Medicine and Biology [J].

Eva K. Lee .

Annals of Biomedical Engineering, 2007, 35 :1095-1109

[49] Sample Dropout for Audio Scene Classification Using Multi-scale Dense Connected Convolutional Neural Network [J].

Feng, Dawei ;

Xu, Kele ;

Mi, Haibo ;

Liao, Feifan ;

Zhou, Yan .

KNOWLEDGE MANAGEMENT AND ACQUISITION FOR INTELLIGENT SYSTEMS (PKAW 2018), 2018, 11016 :114-123

[50] Deep CNN-Based Planthopper Classification Using a High-Density Image Dataset [J].

Ibrahim, Mohd Firdaus ;

Khairunniza-Bejo, Siti ;

Hanafi, Marsyita ;

Jahari, Mahirah ;

Ahmad Saad, Fathinul Syahir ;

Mhd Bookeri, Mohammad Aufa .

AGRICULTURE-BASEL, 2023, 13 (06)

← 1 2 3 4 5 →