HADNet: A Novel Lightweight Approach for Abnormal Sound Detection on Highway Based on 1D Convolutional Neural Network and Multi-Head Self-Attention Mechanism

卷积神经网络 机制(生物学) 主管(地质) 计算机科学 声音(地理) 人工神经网络 人工智能 声学 地质学 物理 量子力学 地貌学
作者
Liang Cong,Qian Chen,Qiran Li,Qingnan Wang,Kang Zhao,Jihui Tu,Ammar Jafaripournimchahi
出处
期刊:Electronics [Multidisciplinary Digital Publishing Institute]
卷期号:13 (21): 4229-4229
标识
DOI:10.3390/electronics13214229
摘要

Video surveillance is an effective tool for traffic management and safety, but it may face challenges in extreme weather, low visibility, areas outside the monitoring field of view, or during nighttime conditions. Therefore, abnormal sound detection is used in traffic management and safety as an auxiliary tool to complement video surveillance. In this paper, a novel lightweight method for abnormal sound detection based on 1D CNN and Multi-Head Self-Attention Mechanism on the embedded system is proposed, which is named HADNet. First, 1D CNN is employed for local feature extraction, which minimizes information loss from the audio signal during time-frequency conversion and reduces computational complexity. Second, the proposed block based on Multi-Head Self-Attention Mechanism not only effectively mitigates the issue of disappearing gradients, but also enhances detection accuracy. Finally, the joint loss function is employed to detect abnormal audio. This choice helps address issues related to unbalanced training data and class overlap, thereby improving model performance on imbalanced datasets. The proposed HADNet method was evaluated on the MIVIA Road Events and UrbanSound8K datasets. The results demonstrate that the proposed method for abnormal audio detection on embedded systems achieves high accuracy of 99.6% and an efficient detection time of 0.06 s. This approach proves to be robust and suitable for practical applications in traffic management and safety. By addressing the challenges posed by traditional video surveillance methods, HADNet offers a valuable and complementary solution for enhancing safety measures in diverse traffic conditions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
岑晓冰完成签到 ,获得积分10
刚刚
啦啦啦完成签到,获得积分10
刚刚
感动的小鸽子完成签到 ,获得积分10
1秒前
lxj完成签到 ,获得积分10
1秒前
无辜的蜗牛完成签到 ,获得积分10
1秒前
xiaojin完成签到,获得积分10
2秒前
程程完成签到,获得积分10
2秒前
duckspy发布了新的文献求助30
2秒前
2秒前
sunyanghu369发布了新的文献求助30
7秒前
hdc12138完成签到,获得积分10
8秒前
飞龙在天完成签到,获得积分0
8秒前
狄淇儿完成签到 ,获得积分10
8秒前
吨吨完成签到,获得积分10
9秒前
小芒果完成签到,获得积分0
13秒前
14秒前
杰克李李完成签到,获得积分10
15秒前
pakiorder完成签到,获得积分20
17秒前
无心的雅霜完成签到,获得积分10
17秒前
1122完成签到,获得积分10
18秒前
王磊完成签到,获得积分10
18秒前
顺心醉蝶完成签到 ,获得积分10
18秒前
量子星尘发布了新的文献求助10
18秒前
zhao完成签到 ,获得积分10
19秒前
yuncong323发布了新的文献求助10
19秒前
gfasdjsjdsjd发布了新的文献求助30
21秒前
pan完成签到,获得积分10
21秒前
22秒前
23秒前
魔幻的妖丽完成签到 ,获得积分10
25秒前
王小凡完成签到 ,获得积分10
25秒前
26秒前
开心薯片发布了新的文献求助10
27秒前
ZXW完成签到,获得积分10
28秒前
莉莉发布了新的文献求助10
28秒前
眼睛大的擎苍完成签到,获得积分10
30秒前
xr完成签到,获得积分10
31秒前
ZORO完成签到,获得积分10
31秒前
32秒前
临时演员完成签到,获得积分10
33秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038235
求助须知:如何正确求助?哪些是违规求助? 3575992
关于积分的说明 11374009
捐赠科研通 3305760
什么是DOI,文献DOI怎么找? 1819276
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022