[1]胡康,何思宇,左敏,等.基于CNN-BLSTM的化妆品违法违规行为分类模型[J].智能系统学报,2021,16(6):1151-1157.[doi:10.11992/tis.202104001]
 HU Kang,HE Siyu,ZUO Min,et al.Classification model for judging illegal and irregular behavior for cosmetics based on CNN-BLSTM[J].CAAI Transactions on Intelligent Systems,2021,16(6):1151-1157.[doi:10.11992/tis.202104001]
点击复制

基于CNN-BLSTM的化妆品违法违规行为分类模型(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年6期
页码:
1151-1157
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2021-11-05

文章信息/Info

Title:
Classification model for judging illegal and irregular behavior for cosmetics based on CNN-BLSTM
作者:
胡康1 何思宇2 左敏2 葛伟2
1. 中国食品药品检定研究院 信息中心, 北京 102629;
2. 北京工商大学 农产品质量安全追溯技术及应用国家工程实验室, 北京 100048
Author(s):
HU Kang1 HE Siyu2 ZUO Min2 GE Wei2
1. Information Center, China National Institute for Food and Drug Control, Beijing 102629, China;
2. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China
关键词:
化妆品双维度模型自然语言处理位置感知注意力机制卷积神经网络双向长短时记忆网络
Keywords:
cosmeticsdouble-dimensional modelnatural language processinglocation awarenessattention mechanismCNNBLSTM
分类号:
TP391
DOI:
10.11992/tis.202104001
摘要:
针对化妆品安全监管部门抽样检测所含违法违规行为自动识别且分类困难的问题,建立语义分类自动识别模型,辅助有关部门构建智能化管理体系,依靠数据实现科学决策及有效监管。本文分别使用中文词向量及字向量作为双路模型输入,采用CNN(convolutional neural network)网络模型训练字向量, BLSTM(bidirectional long short-term memory)网络模型训练词向量,并在BLSTM中引入位置注意力机制,构建基于CNN-BLSTM的字词双维度化妆品违法违规行为分类模型。在染发类化妆品抽样检测数据集上进行的对比实验结果表明,CNN-BLSTM 模型准确率比常用的几种深度神经网络模型均有明显提高,验证了其合理性和有效性。
Abstract:
Aiming at the difficulties in the automatic recognition and classification of illegal and irregular behaviors of cosmetic supervision departments in sampling inspection, an automatic semantic classification model is established to assist relevant departments in building an intelligent management system so as to realize scientific decision-making and effective supervision with data. In this study, a Chinese word vector and character vector are used as two-way model input. The convolutional neural network (CNN) model is used to train the character vector, and the bidirectional long short-term memory (BLSTM) network model is used to train the word vector. Then, the positional attention mechanism is introduced to BLSTM to construct a character–word double-dimensional classification model for illegal and irregular behaviors in cosmetic sampling inspection based on CNN-BLSTM. The results of the comparative experiments on the sampling inspection dataset of hair dye cosmetics show that the accuracy of the CNN-BLSTM model is significantly higher than that of several commonly used deep neural network models, which verifies this model’s rationality and effectiveness.

参考文献/References:

[1] RASCHKA S. Naive Bayes and text classification i-introduction and theory [EB/OL]. (2014-02-14) [2021-05-01]https://arxiv.org/abs/1410.5329.
[2] JOACHIMS T. Text categorization with support vector machines: learning with many relevant features[M]//NéDELLEC C, ROUVEIROL C. Machine Learning: ECML-98. Berlin: Springer, 1998: 137-142.
[3] 毛明毅, 吴晨, 钟义信, 等. 加入自注意力机制的BERT命名实体识别模型[J]. 智能系统学报, 2020, 15(4): 772-779
MAO Mingyi, WU Chen, ZHONG Yixin, et al. BERT named entity recognition model with self-attention mechanism[J]. CAAI transactions on intelligent systems, 2020, 15(4): 772-779
[4] 王一成, 万福成, 马宁. 融合多层次特征的中文语义角色标注[J]. 智能系统学报, 2020, 15(1): 107-113
WANG Yicheng, WAN Fucheng, MA Ning. Chinese semantic role labeling with multi-level linguistic features[J]. CAAI transactions on intelligent systems, 2020, 15(1): 107-113
[5] ZHAO Rui, YAN Ruqiang, CHEN Zhenghua, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical systems and signal processing, 2019, 115: 213-237.
[6] AL-SAREM M, BOULILA W, AL-HARBY M, et al. Deep learning-based rumor detection on microblogging platforms: a systematic review[J]. IEEE access, 2019, 7: 152788-152812.
[7] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar, 2014: 1746-1751.
[8] MIKOLOV T, SUTSKEVER I, CHEN Kai, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe, USA, 2013, 26: 3111-3119.
[9] SOCHER R, HUANG E H, PENNINGTON J, et al. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection[C]//Proceedings of the 24th International Conference on Neural Information Processing Systems. Granada, Spain, 2012: 801-809.
[10] SOCHER R, PERELYGIN A, WU J, et al. Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Seattle, USA, 2013: 1631-1642.
[11] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[12] LIU Pengfei, QIU Xipeng, HUANG Xuanjing. Recurrent neural network for text classification with multi-task learning[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence. New York, USA, 2016: 2873-2879.
[13] ALKHODAIR S A, DING S H H, FUNG B C M, et al. Detecting breaking news rumors of emerging topics in social media[J]. Information processing & management, 2020, 57(2): 102018.
[14] BAHDANAU D, CHO K H, BENGIO Y. Neural machine translation by jointly learning to align and translate[C]//3rd International Conference on Learning Representations. San Diego, United States, 2014.
[15] YIN Wenpeng, SCHüTZE H, XIANG Bing, et al. Attention-based convolutional neural network for modeling sentence Pairs[J]. Transactions of the association for computational linguistics, 2016, 4: 259-272.
[16] ZHOU Peng, SHI Wei, TIAN Jun, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Berlin, Germany, 2016: 207-212.
[17] GAO Yuhan. English semantic recognition based on abstract meaning representation and vector space model[J]. Journal of physics: conference series, 2018, 1087(5): 052017.
[18] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space [EB/OL]. (2013-09-07) [2021-05-01]https://arxiv.org/abs/1301.3781.
[19] PENNINGTON J, SOCHER R, MANNING C. Glove: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar, 2014: 1532-1543.
[20] KIM Y, JERNITE Y, SONTAG D, et al. Character-aware neural language models[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix, Arizona, 2016: 2741-2749.
[21] 刘龙飞, 杨亮, 张绍武, 等. 基于卷积神经网络的微博情感倾向性分析[J]. 中文信息学报, 2015, 29(6): 159-165
LIU Longfei, YANG Liang, ZHANG Shaowu, et al. Convolutional neural networks for Chinese micro-blog sentiment analysis[J]. Journal of Chinese information processing, 2015, 29(6): 159-165

备注/Memo

备注/Memo:
收稿日期:2021-04-01。
基金项目:国家自然科学基金项目(61873027);教育部人文社会科学研究青年基金项目(20YJCZH229);北京市自然科学基金项目(4202014);北京市教委科研计划项目(KM202010011011)
作者简介:胡康,高级工程师,主要研究方向为食品、药品、化妆品、医疗器械监管检验方面的人工智能和大数据研究。参与国家、省重点研发计划等项目;2017年获得吴文俊人工智能三等奖等。发表学术论文13篇;何思宇,硕士研究生,主要研究方向为自然语言处理、大数据;左敏,教授,博士生导师,主要研究方向为化妆品安全大数据、化妆品安全追溯。主持国家重点研发计划课题、承担中国工程院战略研究课题多项。2009年被评为“北京市中青年骨干教师”,2012年被推荐为“北京市教委青年拔尖人才”计划,2017年获得吴文俊人工智能三等奖。发表学术论文40余篇
通讯作者:左敏.E-mail:zuomin12345@126.com
更新日期/Last Update: 2021-12-25