《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (1): 175-181.DOI: 10.11772/j.issn.1001-9081.2023010002
所属专题: 人工智能
张雨宁1, 阿布都克力木·阿布力孜1(), 梅悌胜2, 徐春1, 麦尔达娜·买买提热依木3, 哈里旦木·阿布都克里木1, 侯钰涛1
收稿日期:
2023-01-04
修回日期:
2023-04-13
接受日期:
2023-04-13
发布日期:
2023-06-06
出版日期:
2024-01-10
通讯作者:
阿布都克力木·阿布力孜
作者简介:
张雨宁(2000—),女,河北定州人,硕士研究生,CCF学生会员,主要研究方向:人工智能、医学人工智能;基金资助:
Yuning ZHANG1, Abudukelimu ABULIZI1(), Tisheng MEI2, Chun XU1, Maierdana MAIMAITIREYIMU3, Halidanmu ABUDUKELIMU1, Yutao HOU1
Received:
2023-01-04
Revised:
2023-04-13
Accepted:
2023-04-13
Online:
2023-06-06
Published:
2024-01-10
Contact:
Abudukelimu ABULIZI
About author:
ZHANG Yuning, born in 2000, M. S. candidate. Her research interests include artificial intelligence, medical artificial intelligence.Supported by:
摘要:
为探索自监督特征提取方法在骨骼X线影像异常检测方面的可行性,提出了基于自监督特征提取的骨骼X线影像异常检测方法。将自监督学习框架与ViT(Vision Transformer)模型结合用于骨骼异常检测的特征提取,并通过线性分类器进行异常检测分类,在特征提取阶段可有效避免有监督模型对大规模有标注数据的依赖性。在公开的骨骼X线影像数据集上进行实验,采用准确率分别评估预训练的卷积神经网络(CNN)和自监督特征提取的骨骼异常检测模型。实验结果表明,自监督特征提取模型相较于一般的CNN模型效果更优,在7个部位分类结果与有监督的CNN模型ResNet50相差无几,但在肘部、手指、肱骨的异常检测中准确率均取得了最优值,平均准确率提升了5.37个百分点。所提方法易于实现,可以作为放射科医生初步诊断的可视化辅助工具。
中图分类号:
张雨宁, 阿布都克力木·阿布力孜, 梅悌胜, 徐春, 麦尔达娜·买买提热依木, 哈里旦木·阿布都克里木, 侯钰涛. 基于自监督特征提取的骨骼X线影像异常检测方法[J]. 计算机应用, 2024, 44(1): 175-181.
Yuning ZHANG, Abudukelimu ABULIZI, Tisheng MEI, Chun XU, Maierdana MAIMAITIREYIMU, Halidanmu ABUDUKELIMU, Yutao HOU. Anomaly detection method for skeletal X-ray images based on self-supervised feature extraction[J]. Journal of Computer Applications, 2024, 44(1): 175-181.
类型 | 训练集样本数 | 测试集样本数 | 样本总数 | ||
---|---|---|---|---|---|
正常 | 异常 | 正常 | 异常 | ||
合计 | 8 280 | 5 177 | 661 | 537 | 14 656 |
肘部 | 1 094 | 660 | 92 | 66 | 1 912 |
手指 | 1 280 | 655 | 92 | 83 | 2 110 |
手部 | 1 497 | 521 | 101 | 66 | 2 185 |
肱骨 | 321 | 271 | 68 | 67 | 727 |
前臂 | 950 | 287 | 69 | 64 | 1 010 |
肩部 | 1 364 | 1 457 | 99 | 95 | 3 015 |
手腕 | 2 134 | 1 326 | 140 | 97 | 3 697 |
表1 MURA数据集中正常和异常样本分布
Tab. 1 Distribution of normal and abnormal samples in MURA dataset
类型 | 训练集样本数 | 测试集样本数 | 样本总数 | ||
---|---|---|---|---|---|
正常 | 异常 | 正常 | 异常 | ||
合计 | 8 280 | 5 177 | 661 | 537 | 14 656 |
肘部 | 1 094 | 660 | 92 | 66 | 1 912 |
手指 | 1 280 | 655 | 92 | 83 | 2 110 |
手部 | 1 497 | 521 | 101 | 66 | 2 185 |
肱骨 | 321 | 271 | 68 | 67 | 727 |
前臂 | 950 | 287 | 69 | 64 | 1 010 |
肩部 | 1 364 | 1 457 | 99 | 95 | 3 015 |
手腕 | 2 134 | 1 326 | 140 | 97 | 3 697 |
实验参数 | 设置 | 实验参数 | 设置 |
---|---|---|---|
Patch大小 | 16 | 优化器 | AdamW |
ViT模型层数 | 12 | 教师网络优化动量 | 0.996 |
ViT模型注意力头 | 6 | 教师网络温度参数 | 0.04 |
Batch大小 | 16 | Dropout率 | 0.1 |
迭代次数 | 300 |
表2 实验参数设置
Tab. 2 Experiment parameter settings
实验参数 | 设置 | 实验参数 | 设置 |
---|---|---|---|
Patch大小 | 16 | 优化器 | AdamW |
ViT模型层数 | 12 | 教师网络优化动量 | 0.996 |
ViT模型注意力头 | 6 | 教师网络温度参数 | 0.04 |
Batch大小 | 16 | Dropout率 | 0.1 |
迭代次数 | 300 |
模型 | 准确率 | 模型 | 准确率 |
---|---|---|---|
Inception | 94.43 | ResNet152 | 87.86 |
VGG16 | 93.50 | DenseNet121 | 95.44 |
VGG19 | 89.84 | DenseNet169 | 76.35 |
Xception | 95.78 | DenseNet201 | 65.99 |
ResNet50 | 95.07 | DINO(ViT) | 95.50 |
ResNet101 | 94.71 |
表3 不同模型在第一阶段骨骼分类的准确率 ( %)
Tab. 3 Acuracies of skeletal classification at first stage by different models
模型 | 准确率 | 模型 | 准确率 |
---|---|---|---|
Inception | 94.43 | ResNet152 | 87.86 |
VGG16 | 93.50 | DenseNet121 | 95.44 |
VGG19 | 89.84 | DenseNet169 | 76.35 |
Xception | 95.78 | DenseNet201 | 65.99 |
ResNet50 | 95.07 | DINO(ViT) | 95.50 |
ResNet101 | 94.71 |
模型 | 准确率 | 平均准确率 | ||||||
---|---|---|---|---|---|---|---|---|
肩膀 | 肘部 | 手指 | 前臂 | 手部 | 肱骨 | 手腕 | ||
Inception | 79.00 | 82.97 | 60.32 | 65.61 | 88.16 | 80.38 | 71.09 | 75.36 |
VGG16 | 50.00 | 65.00 | 70.00 | 89.00 | 81.36 | 56.94 | 73.93 | 69.46 |
VGG19 | 50.00 | 60.00 | 75.00 | 87.00 | 80.70 | 56.94 | 84.00 | 70.52 |
Xception | 81.00 | 78.45 | 69.74 | 68.58 | 79.61 | 56.60 | 75.00 | 72.71 |
ResNet50 | 79.00 | 69.18 | 64.69 | 78.72 | 85.75 | 77.78 | 74.09 | 75.60 |
ResNet101 | 80.00 | 74.78 | 63.82 | 62.84 | 81.14 | 80.21 | 77.13 | 74.27 |
ResNet152 | 76.00 | 72.84 | 69.52 | 70.72 | 78.07 | 78.82 | 74.70 | 74.31 |
DenseNet121 | 78.00 | 67.03 | 63.60 | 61.82 | 73.03 | 84.00 | 75.91 | 71.91 |
DenseNet169 | 79.00 | 68.10 | 51.97 | 76.35 | 72.81 | 78.47 | 67.84 | 70.65 |
DenseNet201 | 78.00 | 73.92 | 61.18 | 70.61 | 74.12 | 80.90 | 78.35 | 73.87 |
DINO(ResNet50) | 70.52 | 73.33 | 76.10 | 70.10 | 71.30 | 79.86 | 77.24 | 74.06 |
DINO(ViT) | 77.26 | 83.01 | 78.31 | 78.74 | 78.70 | 87.15 | 83.61 | 80.97 |
表4 不同模型在第二阶段异常检测的结果 ( %)
Tab. 4 Results of anomaly detection at second stage by different models
模型 | 准确率 | 平均准确率 | ||||||
---|---|---|---|---|---|---|---|---|
肩膀 | 肘部 | 手指 | 前臂 | 手部 | 肱骨 | 手腕 | ||
Inception | 79.00 | 82.97 | 60.32 | 65.61 | 88.16 | 80.38 | 71.09 | 75.36 |
VGG16 | 50.00 | 65.00 | 70.00 | 89.00 | 81.36 | 56.94 | 73.93 | 69.46 |
VGG19 | 50.00 | 60.00 | 75.00 | 87.00 | 80.70 | 56.94 | 84.00 | 70.52 |
Xception | 81.00 | 78.45 | 69.74 | 68.58 | 79.61 | 56.60 | 75.00 | 72.71 |
ResNet50 | 79.00 | 69.18 | 64.69 | 78.72 | 85.75 | 77.78 | 74.09 | 75.60 |
ResNet101 | 80.00 | 74.78 | 63.82 | 62.84 | 81.14 | 80.21 | 77.13 | 74.27 |
ResNet152 | 76.00 | 72.84 | 69.52 | 70.72 | 78.07 | 78.82 | 74.70 | 74.31 |
DenseNet121 | 78.00 | 67.03 | 63.60 | 61.82 | 73.03 | 84.00 | 75.91 | 71.91 |
DenseNet169 | 79.00 | 68.10 | 51.97 | 76.35 | 72.81 | 78.47 | 67.84 | 70.65 |
DenseNet201 | 78.00 | 73.92 | 61.18 | 70.61 | 74.12 | 80.90 | 78.35 | 73.87 |
DINO(ResNet50) | 70.52 | 73.33 | 76.10 | 70.10 | 71.30 | 79.86 | 77.24 | 74.06 |
DINO(ViT) | 77.26 | 83.01 | 78.31 | 78.74 | 78.70 | 87.15 | 83.61 | 80.97 |
部位 | DINO(ViT) | DINO(ResNet50) | ||
---|---|---|---|---|
灵敏度 | 特异度 | 灵敏度 | 特异度 | |
平均值 | 76.36 | 85.98 | 70.71 | 80.55 |
肩膀 | 74.92 | 80.24 | 67.66 | 74.78 |
肘部 | 81.85 | 82.01 | 68.94 | 80.81 |
手指 | 73.68 | 80.25 | 72.03 | 80.44 |
前臂 | 73.09 | 94.23 | 64.56 | 82.11 |
手部 | 78.03 | 78.71 | 68.93 | 80.65 |
肱骨 | 88.73 | 84.93 | 78.85 | 81.06 |
手腕 | 79.39 | 90.74 | 73.99 | 84.03 |
表5 DINO框架下不同预训练模型的灵敏度和特异度 (%)
Tab. 5 Sensitivity and specificity of different pre-trained models under DINO framework
部位 | DINO(ViT) | DINO(ResNet50) | ||
---|---|---|---|---|
灵敏度 | 特异度 | 灵敏度 | 特异度 | |
平均值 | 76.36 | 85.98 | 70.71 | 80.55 |
肩膀 | 74.92 | 80.24 | 67.66 | 74.78 |
肘部 | 81.85 | 82.01 | 68.94 | 80.81 |
手指 | 73.68 | 80.25 | 72.03 | 80.44 |
前臂 | 73.09 | 94.23 | 64.56 | 82.11 |
手部 | 78.03 | 78.71 | 68.93 | 80.65 |
肱骨 | 88.73 | 84.93 | 78.85 | 81.06 |
手腕 | 79.39 | 90.74 | 73.99 | 84.03 |
1 | MBOI N, SURBAKTI I M, TRIHANDINI I, et al. On the road to universal health care in Indonesia, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016 [J]. Lancet, 2018, 392(10147): 581-591. 10.1016/s0140-6736(18)30595-6 |
2 | AI-AYYOUB M, HMEIDI I, RABABAH H. Detecting hand bone fractures in X-ray images [J]. Journal of Multimedia Processing and Technologies, 2013, 4(3): 155-168. |
3 | ZEELAN BASHA C M A K, MARUTHI PADMAJA T, BALAJI G N. Automatic X-ray image classification system [C]// Proceedings of the First International Conference on Smart Computing and Informatics. Cham: Springer, 2018: 43-52. 10.1007/978-981-10-5547-8_5 |
4 | 林广,张志强.人工智能医学影像在骨关节系统中的应用进展[J].中国医学影像学杂志, 2022, 30(2): 184-187. 10.3969/j.issn.1005-5185.2022.02.017 |
LIN G, ZHANG Z Q. Advances in the application of artificial intelligence in osteoarticular medical imaging [J]. Chinese Journal of Medical Imaging, 2022, 30(2): 184-187. 10.3969/j.issn.1005-5185.2022.02.017 | |
5 | SPAHR A, BOZORGTABAR B, THIRAN J P. Self-taught semi-supervised anomaly detection on upper limb X-rays [C]// Proceedings of the 2021 IEEE 18th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2021: 1632-1636. 10.1109/isbi48211.2021.9433771 |
6 | SCHMARJE L, SANTAROSSA M, SCHRÖDER S M, et al. A survey on semi-, self- and unsupervised techniques in image classification [J]. IEEE Access, 2021, 9: 82146-82168. 10.1109/access.2021.3084358 |
7 | HUANG G, LARADJI I, VÁZQUEZ D, et al. A survey of self-supervised and few-shot object detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(4): 4071-4089. |
8 | CARON M, TOUVRON H, MISRA I, et al. Emerging properties in self-supervised vision transformers [C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9630-9640. 10.1109/iccv48922.2021.00951 |
9 | DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale [EB/OL]. [2023-03-21]. . |
10 | RAJPURKAR P, IRVIN J, BAGUL A, et al. MURA: Large dataset for abnormality detection in musculoskeletal radiographs [EB/OL]. [2023-03-21]. . 10.3390/reports2040026 |
11 | JAISWAL A, BABU A R, ZADEH M Z, et al. A survey on contrastive self-supervised learning [J]. Technologies, 2020, 9(1): No. 2. 10.3390/technologies9010002 |
12 | PATHAK D, KRÄHENBÜHL P, DONAHUE J, et al. Context encoders: feature learning by in painting [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 2536-2544. 10.1109/cvpr.2016.278 |
13 | ZHANG R, ISOLA P, EFROS A A. Colorful image colorization [C]// Proceedings of the 2016 European Conference on Computer Vision. Cham: Springer, 2016: 649-666. 10.1007/978-3-319-46487-9_40 |
14 | GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks [J]. Communications of the ACM, 2020, 63(11): 139-144. 10.1145/3422622 |
15 | ZHU J-Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2242-2251. 10.1109/iccv.2017.244 |
16 | KARRAS T, LAINE S, AILA T. A style-based generator architecture for generative adversarial networks [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 4396-4405. 10.1109/cvpr.2019.00453 |
17 | 李希,刘喜平,李旺才,等.对比学习研究综述[J].小型微型计算机系统, 2023, 44(4): 787-797. |
LI X, LIU X P, LI W C, et al. Survey on contrastive learning research [J]. Journal of Chinese Computer Systems, 2023, 44(4): 787-797. | |
18 | HE K, FAN H, WU Y, et al. Momentum contrast for unsupervised visual representation learning [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9726-9735. 10.1109/cvpr42600.2020.00975 |
19 | CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations [C]// Proceedings of the 37th International Conference on Machine Learning. New York: JMLR.org, 2020: 1597-1607. |
20 | J-B GRILL, STRUB F, ALTCHÉ F, et al. Bootstrap your own latent — a new approach to self-supervised learning [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020, 33: 21271-21284. |
21 | CARON M, MISRA I, MAIRAL J, et al. Unsupervised learning of visual features by contrasting cluster assignments [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 9912-9924. |
22 | FERNANDO T, GAMMULLE H, DENMAN S, et al. Deep learning for medical anomaly detection-a survey [J]. ACM Computing Surveys, 2021, 54(7): No. 141. 10.1145/3464423 |
23 | MAHENDRAN S K, SANTHOSH BABOO S. An enhanced tibia fracture detection tool using image processing and classification fusion techniques in X-ray images [J]. Global Journal of Computer Science and Technology, 2011, 11(14): 23-28. |
24 | CHUNG S W, HAN S S, LEE J W, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm [J]. Acta Orthopaedica, 2018, 89(4): 468-473. 10.1080/17453674.2018.1453714 |
25 | MIAH M B A, AKTER A. Detecting and determining the types of hand bone fracture using K-means clustering [J]. Journal of Computer Science Applications and Information Technology, 2018, 3(3): 1-10. |
26 | BANGA D, WAIGANJO P. Abnormality detection in musculoskeletal radiographs with convolutional neural networks (ensembles) and performance optimization [EB/OL]. [2023-03-21]. . |
27 | TANTAWI M, THABET R, SAYED A M, et al. Bone X-rays classification and abnormality detection [J]. Internet of Things — Applications and Future, 2020, 114: 277-286. 10.1007/978-981-15-3075-3_20 |
28 | El-SAADAWY H, TANTAWI M, SHEDEED H A, et al. A two-stage method for bone X-rays abnormality detection using MobileNet network [C]// Proceedings of the 2020 International Conference on Artificial Intelligence and Computer Vision. Cham: Springer, 2020: 372-380. 10.1007/978-3-030-44289-7_35 |
29 | HE M, WANG X, ZHAO Y. A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs [J]. Scientific Reports, 2021, 11(1): 9097. 10.1038/s41598-021-88578-w |
30 | 王鑫.基于深度神经网络的骨骼异常检测方法研究[D].呼和浩特:内蒙古大学, 2020: 20-35. |
WANG X. Research on skeletal abnormally detection method based on deep neural learning [D]. Hohhot: Inner Mongolia University, 2020: 20-35. | |
31 | 黄彩云,陈德武,何吉福,等.基于改进双路径网络的上肢肌肉骨骼异常检测[J].山东大学学报(工学版), 2022, 52(3): 25-33, 41. |
HUANG C Y, CHEN D W, HE J F, et al. Detection of upper limb musculoskeletal abnormality based on improved dual path network [J]. Journal of Shandong University (Engineering Science), 2022, 52(3): 25-33, 41. | |
32 | YAO J, GUO Z, YU W. Enhanced deep residual network for bone classification and abnormality detection. [J]. Medical Physics, 2022, 49(11): 6914-6929. 10.1002/mp.15966 |
33 | El-SAADAWY H, TANTAWI M, SHEDEED H A, et al. A hybrid two-stage GNG-Modified VGG method for bone X-rays classification and abnormality detection [J]. IEEE Access, 2021, 9: 76649-76661. 10.1109/access.2021.3081915 |
34 | 王浩.人体骨骼医学影像的异常检测方法研究[D].荆州:长江大学, 2022: 1-5. 10.25221/fee.455.2 |
WANG H. Research on anomaly detection method of human bone medical image [D]. Jingzhou: Yangtze University, 2022: 1-5. 10.25221/fee.455.2 | |
35 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010. |
36 | SIMONYAN K, ZISSERMAN A. Very Deep convolutional networks for large-scale image recognition [EB/OL]. [2023-03-21]. . |
37 | SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 2818-2826. 10.1109/cvpr.2016.308 |
38 | CHOLLET F. Xception: Deep learning with depthwise separable convolutions [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1800-1807. 10.1109/cvpr.2017.195 |
39 | HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
40 | HUANG G, LIU Z, VAN DER MAATEN L, 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 |
41 | RAGHU M, UNTERTHINER T, KORNBLITH S, et al. Do vision transformers see like convolutional neural networks? [EB/OL]. (2022-03-03) [2022-06-02]. . 10.1016/s0004-3702(98)00055-1 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 唐廷杰, 黄佳进, 秦进. 基于图辅助学习的会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2711-2718. |
[3] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[4] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[5] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[6] | 陈廷伟, 张嘉诚, 王俊陆. 面向联邦学习的随机验证区块链构建[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2770-2776. |
[7] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[8] | 杨鑫, 陈雪妮, 吴春江, 周世杰. 结合变种残差模型和Transformer的城市公路短时交通流预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2947-2951. |
[9] | 陈虹, 齐兵, 金海波, 武聪, 张立昂. 融合1D-CNN与BiGRU的类不平衡流量异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2493-2499. |
[10] | 付帅, 郭小英, 白茹意, 闫涛, 陈斌. 改进的CloFormer模型与有序回归相结合的年龄评估方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2372-2380. |
[11] | 陈彤, 杨丰玉, 熊宇, 严荭, 邱福星. 基于多尺度频率通道注意力融合的声纹库构建方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2407-2413. |
[12] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. |
[13] | 顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625. |
[14] | 石乾宏, 杨燕, 江永全, 欧阳小草, 范武波, 陈强, 姜涛, 李媛. 面向空气质量预测的多粒度突变拟合网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2643-2650. |
[15] | 吴筝, 程志友, 汪真天, 汪传建, 王胜, 许辉. 基于深度学习的患者麻醉复苏过程中的头部运动幅度分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2258-2263. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||