Homologous spectrogram feature fusion with self-attention mechanism for bird sound classification

doi:10.11772/j.issn.1001-9081.2021071258

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (4): 1260-1268.DOI: 10.11772/j.issn.1001-9081.2021071258

Special Issue: CCF第36届中国计算机应用大会 (CCF NCCA 2021)

• The 36 CCF National Conference of Computer Applications (CCF NCCA 2020) • Previous Articles Next Articles

Homologous spectrogram feature fusion with self-attention mechanism for bird sound classification

Zhihua LIU¹^,², Wenjie CHEN¹^,², Aibin CHEN¹^,²()

^1.College of Computer and Information Engineering，Central South University of Forestry and Technology，Changsha Hunan 410004，China
^2.Institute of Applied Artificial Intelligence，Central South University of Forestry and Technology，Changsha Hunan 410004，China

Received:2021-07-16 Revised:2021-08-26 Accepted:2021-08-30 Online:2021-08-26 Published:2022-04-10
Contact: Aibin CHEN
About author:LIU Zhihua， born in 1996， M. S. candidate. His research interests include deep learning， audio classification.
CHEN Wenjie， born in 1996， M. S. candidate. Her research interests include deep learning， image detection and classification.
Supported by:
Hunan Key Laboratory of Intelligent Logistics Technology(2019TP1015)

基于自注意力机制时频谱同源特征融合的鸟鸣声分类

刘志华¹^,², 陈文洁¹^,², 陈爱斌¹^,²()

^1.中南林业科技大学计算机与信息工程学院，长沙 410004
^2.中南林业科技大学人工智能应用研究所，长沙 410004

通讯作者: 陈爱斌
作者简介:刘志华（1996—），男，湖南邵阳人，硕士研究生，主要研究方向：深度学习、音频分类
陈文洁（1996—），女，湖南株洲人，硕士研究生，主要研究方向：深度学习、图像检测与分类
基金资助:
智慧物流技术湖南省重点实验室资助项目(2019TP1015)

Abstract

Abstract:

At present， most deep learning models are difficult to deal with the classification of bird sound under complex background noise. Because bird sound has the continuity characteristic in time domain and high-low characteristic in frequency domain， a fusion model of homologous spectrogram features was proposed for bird sound classification under complex background noise. Firstly， Convolutional Neural Network （CNN） was used to extract Mel-spectrogram features of bird sound. Then， the time domain and frequency domain dimensions of the same Mel-spectrogram feature were compressed to 1 by specific convolution and down-sampling operations， so that frequency domain feature with only high-low characteristics and the time domain feature with only continuous characteristics were obtained. Based on the above operation to extract frequency domain and time domain features， the features of Mel-spectrogram were extracted both in time domain and frequency domain， the time-frequency domain features with continuity and high-low characteristics were obtained. Then the self-attention mechanism was applied to the obtained time domain， frequency domain and time-frequency domain features， strengthening their own characteristics. Finally， the results of these three homologous spectrogram features after decision fusion were used for bird sound classification. The proposed model was used for audio classification of 8 bird species on Xeno-canto website， achieved the better result in the comparison experiment with the Mean Average Precision （MAP） of 0.939. The experimental results show that the proposed model can deal with the problem of the poor classification effect of bird sound under complex background noise.

Key words: deep learning, bird sound classification, Convolutional Neural Network (CNN), self-attention mechanism, homologous spectrogram feature fusion

摘要：

目前深度学习模型大都难以应对复杂背景噪声下的鸟鸣声分类问题。考虑到鸟鸣声具有时域连续性、频域高低性特点，提出了一种利用同源谱图特征进行融合的模型用于复杂背景噪声下的鸟鸣声分类。首先，使用卷积神经网络（CNN）提取鸟鸣声梅尔时频谱特征；然后，使用特定的卷积以及下采样操作，将同一梅尔时频谱特征的时域和频域维度分别压缩至1，得到仅包含鸟鸣声高低特性的频域特征以及连续特性的时域特征。基于上述提取频域以及时域特征的操作，在时域和频域维度上同时对梅尔时频谱特征进行提取，得到具有连续性以及高低特性的时频域特征。然后，将自注意力机制分别用于得到的时域、频域、时频域特征以加强其各自拥有的特性。最后，将这三类同源谱图特征决策融合后的结果用于鸟鸣声分类。所提模型用于Xeno-canto网站的8种鸟类音频分类，并在分类对比实验中取得了平均精确率（MAP）为0.939的较好结果。实验结果表明该模型能应对复杂背景噪声下的鸟鸣声分类效果较差的问题。

关键词: 深度学习, 鸟鸣声分类, 卷积神经网络, 自注意力机制, 同源谱图特征融合

CLC Number:

TP183

Zhihua LIU, Wenjie CHEN, Aibin CHEN. Homologous spectrogram feature fusion with self-attention mechanism for bird sound classification[J]. Journal of Computer Applications, 2022, 42(4): 1260-1268.

刘志华, 陈文洁, 陈爱斌. 基于自注意力机制时频谱同源特征融合的鸟鸣声分类[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1260-1268.

Figures/Tables 13

References 47

1	李朝洪，赵晓红.黑龙江省森工国有林区生态建设与经济转型协调发展研究［J］.南京林业大学学报（自然科学版），2019，43（2）：144-152. 10.3969/j.issn.1000-2006.201804022
	LI C H， ZHAO X H. Study on the coordinated development of ecological construction and economic transformation in state-owned forest region of forest industry in Heilongjiang Province［J］. Journal of Nanjing Forestry University （Natural Sciences Edition）， 2019， 43（2）： 144-152. 10.3969/j.issn.1000-2006.201804022
2	QIAO Y， QIAN K， ZHAO Z P. Learning higher representations from bioacoustics： a sequence-to-sequence deep learning approach for bird sound classification［C］// Proceedings of the 2020 International Conference on Neural Information Processing. Cham： Springer， 2020： 130-138. 10.1007/978-3-030-63823-8_16
3	LEE C H， CHOU C H， HAN C C， et al. Automatic recognition of animal vocalizations using averaged MFCC and linear discriminant analysis［J］. Pattern Recognition Letters， 2006， 27（2）： 93-101. 10.1016/j.patrec.2005.07.004
4	DONG X Y， JIA J P. Advances in automatic bird species recognition from environmental audio［C］// Proceedings of the 5th International Conference on Intelligent Computing and Signal Proceeding. Suzhou： Journal of Physics： Conference Series， 2020： 012110. 10.1088/1742-6596/1544/1/012110
5	LENG Y R， TRAN H D. Multi-label bird classification using an ensemble classifier with simple features［C］// Proceedings of the 2014 Signal and Information Processing Association Annual Summit and Conference. Piscataway： IEEE， 2014： 1-5. 10.1109/apsipa.2014.7041649
6	CHEN Z X， MAHER R C. Semi-automatic classification of bird vocalizations using spectral peak tracks［J］. The Journal of the Acoustical Society of America， 2006， 120（5）： 2974-2984. 10.1121/1.2345831
7	FAGERLUND S. Bird species recognition using support vector machines［J］. EURASIP Journal on Advances in Signal Processing， 2007， 2007： 38637.1-38637.8. 10.1155/2007/38637
8	QIAN K， GUO J， ISHIDA K， et al. Fast recognition of bird sounds using extreme learning machines［J］. IEEJ Transactions on Electrical and Electronic Engineering， 2017， 12（2）： 294-296. 10.1002/tee.22378
9	TAN L N， ALWAN A. Dynamic time warping and sparse representation classification for birdsong phrase classification using limited training data［J］. The Journal of the Acoustical Society of America， 2015， 137（3）： 1069-1080. 10.1121/1.4906168
10	阙鑫华，乔倩，蒋慧，等.基于改进DTW算法的海岛水鸟鸣声识别应用研究［J］.农村经济与科技，2021，32（11）：320-322. 10.3969/j.issn.1007-7103.2021.11.117
	QUE X H， QIAO Q， JIANG H， et al. Application research of island waterbird song recognition based on improved DTW algorithm［J］. Rural Economy and Science-Technology， 2021， 32（11）： 320-322. 10.3969/j.issn.1007-7103.2021.11.117
11	JANČOVIČ P， KÖKÜER M， RUSSELL M. Bird species recognition from field recordings using HMM-based modelling of frequency tracks［C］// Proceedings of the 2014 International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2014： 8252-8256. 10.1109/icassp.2014.6855210
12	WIELGAT R， POTEMPA T， ŚWIETOJAŃSKI P， et al. On using prefiltration in HMM-based bird species recognition［C］// Proceedings of the 2012 International Conference on Signals and Electronic Systems. Piscataway： IEEE， 2012： 1-5. 10.1109/icses.2012.6382258
13	SPRINGER J， DUAN Z， PARDO B. Approaches to multiple concurrent species bird song recognition［C］// Proceedings of the 2nd International Workshop on Machine Listening in Multisource Environments. Piscataway： IEEE， 2013： 85-86.
14	ACEVEDO M A， CORRADA-BRAVO C J， CORRADA-BRAVO H， et al. Automated classification of bird and amphibian calls using machine learning： a comparison of methods［J］. Ecological Informatics， 2009， 4（4）： 206-214. 10.1016/j.ecoinf.2009.06.005
15	张赛花，赵兆，许志勇，等.基于Mel子带参数化特征的自动鸟鸣识别［J］.计算机应用，2017，37（4）：1111-1115. 10.11772/j.issn.1001-9081.2017.04.1111
	ZHANG S H， ZHAO Z， XU Z Y， et al. Automatic bird vocalization identification based on Mel-subband parameterized feature［J］. Journal of Computer Applications， 2017， 37（4）： 1111-1115. 10.11772/j.issn.1001-9081.2017.04.1111
16	LEE C H， HSU S B， SHIH J L， et al. Continuous birdsong recognition using Gaussian mixture modeling of image shape features［J］. IEEE Transactions on Multimedia， 2012， 15（2）： 454-464. 10.1109/tmm.2012.2229969
17	HINTON G， DENG L， YU D， et al. Deep neural networks for acoustic modeling in speech recognition： the shared views of four research groups［J］. IEEE Signal Processing Magazine， 2012， 29（6）： 82-97. 10.1109/msp.2012.2205597
18	ZHANG H， MCLOUGHLIN I， SONG Y. Robust sound event recognition using convolutional neural networks［C］// Proceedings of the 2015 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2015： 559-563. 10.1109/icassp.2015.7178031
19	ZHANG X， CHEN A B， ZHOU G X， et al. Spectrogram-frame linear network and continuous frame sequence for bird sound classification［J］. Ecological Informatics， 2019， 54： 101009. 10.1016/j.ecoinf.2019.101009
20	SPRENGEL E， JAGGI M， KILCHER Y， et al. Audio based bird species identification using deep learning techniques［C］// Proceedings of the 2016 Conference and Labs of the Evaluation Forum. Cham： Springer， 2016： 547-559.
21	KOOPS H V， BALEN J V， WIERING F. A deep neural network approach to the LifeCLEF 2014 bird task［J］. CLEF2014 Working Notes， 2014， 1180： 634.
22	SANKUPELLAY M， KONOVALOV D. Bird call recognition using deep convolutional neural network， ResNet-50［C］// Proceedings of the 2018 International Conference on ACOUSTICS. New York： Curran Associates Inc.， 2018， 7： 1-8.
23	HUANG G， LIU Z， MAATEN L V D， et al. Densely connected convolutional networks［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 2261-2269. 10.1109/cvpr.2017.243
24	TAKAHASH N， GYGLI M， GOOL L VAN. AENet： Learning deep audio features for video analysis［J］. IEEE Transactions on Multimedia， 2018， 20（3）： 513-524. 10.1109/tmm.2017.2751969
25	NARANCHIMEG B， ZHANG C， AKASHI T. Cross-domain deep feature combination for bird species classification with audio-visual data［J］. IEICE Transactions on Information and Systems， 2019， 102（10）： 2033-2042. 10.1587/transinf.2018edp7383
26	XIE J， HU K， ZHU M Y， et al. Investigation of different CNN-based models for improved bird sound classification［J］. IEEE Access， 2019， 7： 175353-175361. 10.1109/access.2019.2957572
27	谢将剑，杨俊，邢照亮，等.多特征融合的鸟类物种识别方法［J］.应用声学，2020，39（2）：199-206. 10.11684/j.issn.1000-310X.2020.02.005
	XIE J J， YANG J， XING Z L， et al. Bird species recognition method based on multi-feature fusion［J］. Journal of Applied Acoustics， 2020， 39（2）： 199-206. 10.11684/j.issn.1000-310X.2020.02.005
28	GRAVES A， MOHAMED A， HINTON G. Speech recognition with deep recurrent neural networks［C］// Proceedings of the 2013 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2013： 6645-6649. 10.1109/icassp.2013.6638947
29	MÜLLER L， MARTÍ M. Bird sound classification using a bidirectional LSTM［C］// CLEF 2018：Proceedings of the 2018 Conference on Bird Conference and Labs of the Evaluation Forum. Cham： Sprinter， 2018： 134.1-134.13.
30	邢照亮，吴伟银，张正晓，等.基于C-LSTM的鸟鸣声识别方法［J］.科技创新与应用，2021，11（15）：15-18.
	XING Z L， WU W Y， ZHANG Z X， et al. Birdsong recognition method based on C-LSTM［J］. Technological Innovation and Application， 2021， 11（15）： 15-18.
31	HIMAWAN I， TOWSEY M， ROE P. 3D convolution recurrent neural networks for bird sound detection［C］// Proceedings of the 3rd Workshop on Detection and Classification of Acoustic Scenes and Events. Västra Finlands län： Tampere University of Technology， 2018： 108-112.
32	PEI S C， DING J J. Relations between Gabor transforms and fractional Fourier transforms and their applications for signal processing［J］. IEEE Transactions on Signal Processing， 2007， 55（10）： 4839-4850. 10.1109/tsp.2007.896271
33	NEAL L， BRIGGS F， RAICH R， et al. Time-frequency segmentation of bird song in noisy acoustic environments［C］// Proceedings of the 2011 IEEE International Conference on Acoustics， Speech and Signal Processing， Piscataway： IEEE， 2011： 2012-2015. 10.1109/icassp.2011.5946906
34	WANG W， YANG N， WEI F， et al. Gated self-matching networks for reading comprehension and question answering［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： Association for Computational Linguistics， 2017： 189-198. 10.18653/v1/p17-1018
35	NUTTALL A. Some windows with very good sidelobe behavior［J］. IEEE Transactions on Acoustics， Speech， and Signal Processing， 1981， 29（1）： 84-91. 10.1109/tassp.1981.1163506
36	LEE C H， HAN C C， CHUANG C C. Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients［J］. IEEE Transactions on Audio， Speech， and Language Processing， 2008， 16（8）： 1541-1550. 10.1109/tasl.2008.2005345
37	MCFEE B， RAFFEL C， LIANG D， et al. Librosa： audio and music signal analysis in python［EB/OL］.［2021-05-30］.. 10.25080/majora-7b98e3ed-003
38	STEVENS S S， VOLKMANN J， NEWMAN E B. A scale for the measurement of the psychological magnitude pitch［J］. The Journal of the Acoustical Society of America， 1937， 8（3）： 185-190. 10.1121/1.1915893
39	LAVANYA S， LAVANYA D， NELATURI N. Random forest algorithm for recognition of bird species using audio recordings ［J］. International Journal of Technology Management， 2018， 8（11），90-94.
40	BAI S J， KOLTER J Z， KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling ［EB/OL］. ［2018-04-19］. .
41	KAHL S， WILHELM-STEIN T， KLINCK H， et al. Recognizing birds from sound-the 2018 BirdCLEF baseline system ［EB/OL］. ［2018-04-19］. .
42	KOOPS H， BALEN J VAN， WIERING F. A deep neural network approach to the lifeclef 2014 bird task［J］. Conference and Labs of the Evaluation Forum 2014 Working Notes， 2014， 1180： 634-642.
43	GUO J X， XU N， LI L J， et al. Attention based CLDNNs for short-duration acoustic scene classification［C］// Proceedings of the 2017 Conference on Interspeech. Stockholm： International Speech Communication Association， 2017： 469-473.
44	TIELEMAN T， HINTON G. Lecture 6.5—RMSprop： Divide the gradient by a running average of its recent magnitude［J］. COURSERA： Neural Networks for Machine Learning， 2012， 4（2）： 26-31.
45	CHEN X， ZHOU G X， CHEN A B， et al. Identification of tomato leaf diseases based on combination of ABCK-BWTR and B-ARNet［J］. Computers and Electronics in Agriculture， 2020， 178： 105730. 10.1016/j.compag.2020.105730
46	YI J Z， CHEN A B， CAI Z X， et al. Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation［J］. Applied Soft Computing， 2019， 82： 105540. 10.1016/j.asoc.2019.105540
47	刘伟波，曾庆宁，卜玉婷，等. 基于双微阵列与卷积神经网络的语音识别方法［J］.计算机应用，2019，39（11）：3268-3273.
	LIU W B， ZENG Q N， BU Y T， et al. Automatic bird vocalization identification based on mel-subband parameterized feature［J］. Journal of Computer Applications， 2019，39（11）：3268-3273.

网络层	输入大小	输出大小	滤波器数量	滤波器大小	步长
1	80×600	8×79×600	8	［2，1］	［1，1］
2	8×79×600	8×39×600	―	［3，1］	［2，1］
3	8×39×600	8×19×600	8	［3，1］	［2，1］
4	8×19×600	8×9×600	―	［3，1］	［2，1］
5	8×9×600	8×4×600	8	［3，1］	［2，1］
6	8×4×600	8×2×600	―	［2，1］	［2，1］
7	8×2×600	8×1×600	―	［2，1］	［2，1］

网络层	输入大小	输出大小	滤波器数量	滤波器大小	步长
1	80×600	8×79×600	8	［2，1］	［1，1］
2	8×79×600	8×39×600	―	［3，1］	［2，1］
3	8×39×600	8×19×600	8	［3，1］	［2，1］
4	8×19×600	8×9×600	―	［3，1］	［2，1］
5	8×9×600	8×4×600	8	［3，1］	［2，1］
6	8×4×600	8×2×600	―	［2，1］	［2，1］
7	8×2×600	8×1×600	―	［2，1］	［2，1］

网络层	输入大小	输出大小	滤波器数量	滤波器大小	步长
1	80×600	8×80×300	8	［1，2］	［1，2］
2	8×80×300	8×80×150	―	［1，2］	［1，2］
3	8×80×150	8×80×50	8	［1，3］	［1，3］
4	8×80×50	8×80×25	―	［1，2］	［1，2］
5	8×80×25	8×80×8	8	［1，4］	［1，3］
6	8×80×8	8×80×2	―	［1，4］	［1，4］
7	8×80×2	8×80×1	―	［1，2］	［1，2］

网络层	输入大小	输出大小	滤波器数量	滤波器大小	步长
1	80×600	8×80×300	8	［1，2］	［1，2］
2	8×80×300	8×80×150	―	［1，2］	［1，2］
3	8×80×150	8×80×50	8	［1，3］	［1，3］
4	8×80×50	8×80×25	―	［1，2］	［1，2］
5	8×80×25	8×80×8	8	［1，4］	［1，3］
6	8×80×8	8×80×2	―	［1，4］	［1，4］
7	8×80×2	8×80×1	―	［1，2］	［1，2］

网络层	输入大小	输出大小	滤波器数量	滤波器大小	步长
1	80×600	8×79×300	8	［2，2］	［1，2］
2	8×79×300	8×39×150	―	［3，2］	［2，2］
3	8×39×150	8×19×50	8	［3，3］	［2，3］
4	8×19×50	8×9×25	―	［3，2］	［2，2］

Homologous spectrogram feature fusion with self-attention mechanism for bird sound classification

基于自注意力机制时频谱同源特征融合的鸟鸣声分类

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 47

Related Articles 15

Recommended Articles

Metrics

种类	原始音频数量	最终实验样本数量	种类	原始音频数量	最终实验样本数量
灰雁	330	2 244	叽喳柳莺	837	3 569
普通鵟	395	3 104	欧柳莺	512	2 650
金黄鹂	539	3 784	喜鹊	450	2 673
大山雀	927	2 525	乌鸫	512	3 012

实验序号	方法	输入类型	输入大小	准确率
1	2DCNN+FC+FC（p）	Image	80×600	0.896
2	2DCNN+GRU+GRU（t）	Image	80×600	0.804
3	2DCNN+FC+FC（pt）	Image	80×600	0.872
4	Experiment（1+2+3）+Decision-fusion	Image	80×600	0.923
5	Experiment（1+2+3）+Self-attention+Decision-fusion	Image	80×600	0.939

Types	Precision	Recall	F1-score	数据数量
灰雁	0.962	0.922	0.941	689
普通鵟	0.924	0.918	0.921	955
金黄鹂	0.885	0.945	0.914	1 162
大山雀	0.992	0.950	0.970	743
叽喳柳莺	0.982	0.971	0.977	1 038
欧柳莺	0.912	0.966	0.938	754
喜鹊	0.952	0.949	0.950	819
乌鸫	0.924	0.882	0.903	908
Micro average	0.942	0.938	0.938	7 068
Macro average	0.942	0.938	0.939	7 068
Weighted average	0.939	0.938	0.938	7 068

实验序号	模型	输入类型	输入大小	准确率
1	2DCNN+FC	Image	80×600	0.872
2	LSTM+FC	Image	80×600	0.868
3	SPFN	Continuous frame sequence	150×80×6	0.932
4	本文模型	Image	80×600	0.939

[1]	Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969.
[2]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[3]	Yun LI, Fuyou WANG, Peiguang JING, Su WANG, Ao XIAO. Uncertainty-based frame associated short video event detection method [J]. Journal of Computer Applications, 2024, 44(9): 2903-2910.
[4]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[5]	Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918.
[6]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[7]	Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703.
[8]	Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499.
[9]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[10]	Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.
[11]	Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650.
[12]	Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318.
[13]	Yangyi GAO, Tao LEI, Xiaogang DU, Suiyong LI, Yingbo WANG, Chongdan MIN. Crowd counting and locating method based on pixel distance map and four-dimensional dynamic convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2233-2242.
[14]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[15]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.