Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00086
Zhiming Lin, Jiawen Lin, Li Li
Meibomian gland dysfunction (MGD) is the most common cause of dry eye disease. Ophthalmologists conduct qualitative evaluation of meibomian glands(MGs) of patients by observing infrared meibomian gland images. But it is subjective to make a diagnosis only with the naked eye. Automatic segmentation of MGs could be challenging and play a key role in MGD morphology analysis and diagnosis. In this paper, an automatic gland segmentation method based on UNet++ and a meibography image dataset are proposed. Data augmentation is used to expand training samples. Infrared meibomian gland images are fed into the preserved model for accurate segmentation. The experiments including comparison with the latest methods show that the presented method effectively segment the MGs and outperform other methods with an average accuracy of 94.28%.
{"title":"Automatic segmentation of glands in infrared meibomian gland image","authors":"Zhiming Lin, Jiawen Lin, Li Li","doi":"10.1109/ITME53901.2021.00086","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00086","url":null,"abstract":"Meibomian gland dysfunction (MGD) is the most common cause of dry eye disease. Ophthalmologists conduct qualitative evaluation of meibomian glands(MGs) of patients by observing infrared meibomian gland images. But it is subjective to make a diagnosis only with the naked eye. Automatic segmentation of MGs could be challenging and play a key role in MGD morphology analysis and diagnosis. In this paper, an automatic gland segmentation method based on UNet++ and a meibography image dataset are proposed. Data augmentation is used to expand training samples. Infrared meibomian gland images are fed into the preserved model for accurate segmentation. The experiments including comparison with the latest methods show that the presented method effectively segment the MGs and outperform other methods with an average accuracy of 94.28%.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"128 1","pages":"399-403"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74205902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of cyberspace, cyber security incidents are increasing, and the means and types of network attacks are becoming more and more complex and refined, which brings greater challenges to security risk control. First, the knowledge graph technology is used to construct a cyber security knowledge graph based on ontology to realize multi-source heterogeneous security big data fusion calculation, and accurately express the complex correlation between different security entities. Furthermore, for cyber security risk control, a key node assessment method for security risk diffusion is proposed. From the perspectives of node communication correlation and topological level, the calculation method of node communication importance based on improved PageRank Algorithm and based on the improved K-shell Algorithm calculates the importance of node topology are studied, and then organically combine the two calculation methods to calculate the importance of different nodes in security risk defense. Experiments show that this method can evaluate the importance of nodes more accurately than the PageRank algorithm and the K-shell algorithm.
{"title":"Node Importance Evaluation Method for Cyberspace Security Risk Control","authors":"Jiaxin Yao, Bihai Lin, Ruiqi Huang, Junyi Fan, Biqiong Chen, Yanhua Liu","doi":"10.1109/ITME53901.2021.00036","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00036","url":null,"abstract":"With the rapid development of cyberspace, cyber security incidents are increasing, and the means and types of network attacks are becoming more and more complex and refined, which brings greater challenges to security risk control. First, the knowledge graph technology is used to construct a cyber security knowledge graph based on ontology to realize multi-source heterogeneous security big data fusion calculation, and accurately express the complex correlation between different security entities. Furthermore, for cyber security risk control, a key node assessment method for security risk diffusion is proposed. From the perspectives of node communication correlation and topological level, the calculation method of node communication importance based on improved PageRank Algorithm and based on the improved K-shell Algorithm calculates the importance of node topology are studied, and then organically combine the two calculation methods to calculate the importance of different nodes in security risk defense. Experiments show that this method can evaluate the importance of nodes more accurately than the PageRank algorithm and the K-shell algorithm.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"62 1","pages":"127-131"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75389046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00031
Wang Linlong, Zhang Huaiqing, Yang Tingdong, Zhang Jing, Cui Zeyu, Zhu Nianfu, Liu Yang, Zuo Yuanqing, Zhang Huacong
In our study, we have explored the influence of panoramic images and ordinary images on the performance of Siberian crane detection, and compared the detection accuracy under different networks based on YOLOv5, to get fine and high-quality datasets and select the proper model for Serbian crane detection. The results show that (i) Training datasets from the internet and ordinary field photos can achieve a better detection performance than other training datasets, and Training datasets from panoramic images only show low accuracy due to Siberian crane's alertness and mosaic data enhancement method adopted in YOLOv5, which reduced the size of a small target. (ii) when the iteration times reach 40000, the YOLOv5 model can completely converge, and the mAP value reached 81.4%, total loss value 0.0357; (iii) With increasing the width and depth of layer in YOLOv5, the value of mAP show a growth trend, however the FPS show an opposite trend; (iv) through verification, we found that the model can also have an effectively performance of detection in the complex environments, such as multi-objective small objects and occlusions, the color similarity between target and background, different dynamic activities including flying, falling, foraging, playing, etc.
{"title":"Optimized Detection Method for Siberian crane (Grus leucogeranus) Based on Yolov5","authors":"Wang Linlong, Zhang Huaiqing, Yang Tingdong, Zhang Jing, Cui Zeyu, Zhu Nianfu, Liu Yang, Zuo Yuanqing, Zhang Huacong","doi":"10.1109/ITME53901.2021.00031","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00031","url":null,"abstract":"In our study, we have explored the influence of panoramic images and ordinary images on the performance of Siberian crane detection, and compared the detection accuracy under different networks based on YOLOv5, to get fine and high-quality datasets and select the proper model for Serbian crane detection. The results show that (i) Training datasets from the internet and ordinary field photos can achieve a better detection performance than other training datasets, and Training datasets from panoramic images only show low accuracy due to Siberian crane's alertness and mosaic data enhancement method adopted in YOLOv5, which reduced the size of a small target. (ii) when the iteration times reach 40000, the YOLOv5 model can completely converge, and the mAP value reached 81.4%, total loss value 0.0357; (iii) With increasing the width and depth of layer in YOLOv5, the value of mAP show a growth trend, however the FPS show an opposite trend; (iv) through verification, we found that the model can also have an effectively performance of detection in the complex environments, such as multi-objective small objects and occlusions, the color similarity between target and background, different dynamic activities including flying, falling, foraging, playing, etc.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"10 1","pages":"01-06"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74287532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00065
Chuanjie Xu, Feng Yuan, Shouqiang Chen
Traditional Chinese medicine (TCM) auxiliary diagnosis is a systematic diagnosis platform that uses computer modeling technology to assist TCM doctors in recording diseases, providing on time diagnoses, writing prescriptions, performing tele-medicine, and supporting medical teaching. This study proposes a Bidirectional Encoder Representations from Transformers TCM auxiliary diagnosis model using 20,000 items of TCM records. These records were collected from the outpatient clinic of the Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine. Specifically, our model aims to predict final diagnosis while taking TCM symptoms as inputs; for example, when we input relief of chest tightness but persistent tiredness and sluggishness, the model provides a diagnosis of chest paralysis. An experiment was conducted on these real-world Chinese medical data. Results show that our model achieves state-of-the-art performance. Hence, our proposed model can effectively use the information from the four diagnostic procedures in the TCM text.
{"title":"Research on Assistant Diagnostic Method of TCM Based on BERT","authors":"Chuanjie Xu, Feng Yuan, Shouqiang Chen","doi":"10.1109/ITME53901.2021.00065","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00065","url":null,"abstract":"Traditional Chinese medicine (TCM) auxiliary diagnosis is a systematic diagnosis platform that uses computer modeling technology to assist TCM doctors in recording diseases, providing on time diagnoses, writing prescriptions, performing tele-medicine, and supporting medical teaching. This study proposes a Bidirectional Encoder Representations from Transformers TCM auxiliary diagnosis model using 20,000 items of TCM records. These records were collected from the outpatient clinic of the Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine. Specifically, our model aims to predict final diagnosis while taking TCM symptoms as inputs; for example, when we input relief of chest tightness but persistent tiredness and sluggishness, the model provides a diagnosis of chest paralysis. An experiment was conducted on these real-world Chinese medical data. Results show that our model achieves state-of-the-art performance. Hence, our proposed model can effectively use the information from the four diagnostic procedures in the TCM text.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"51 1","pages":"282-286"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72556630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00081
Zhaohong Huang, Jiajia Liao, Jun Wei, Guorong Cai, Guowei Zhang
Over the past decade, medical image segmentation has become a necessary prerequisite for disease diagnosis and treatment planning. The deep convolutional neural networks (CNN) have been widely adopted in medical image segmentation which achieves promising performance. However, due to the intrinsic locality of convolution operations, CNN demonstrates limitations in explicitly modeling long-range dependency. Recently proposed hybrid CNN-Transformer architectures that combine the global perception capability of local feature and the local details of global reppresentations. However, the serial structure of CNN and transformer will increase the computational complexity, and then the redundant information generated by convolution operation may leads to the failure of long-range modeling. To this end, this paper proposes a double encoder framework including global encoder and local encoder, TransDE for short, to medical image segmentation. The global encoder takes transformer that designed for sequence-to-sequence prediction, while the local encoder adopts VGG-19 combined with the atrous spatial pyramid pooling (ASPP) to bring about local feature extraction. The experimental results of enteroscopy dataset and dermoscopy dataset show the superiority of our TransDE achieving around 1.97% improvement on CVC-ClinicDB in terms of DSC and 1.6% improvement on Lesion Boundary Segmentation challenge.
{"title":"TransDE: A Transformer and Double Encoder Network for Medical Image Segmentation","authors":"Zhaohong Huang, Jiajia Liao, Jun Wei, Guorong Cai, Guowei Zhang","doi":"10.1109/ITME53901.2021.00081","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00081","url":null,"abstract":"Over the past decade, medical image segmentation has become a necessary prerequisite for disease diagnosis and treatment planning. The deep convolutional neural networks (CNN) have been widely adopted in medical image segmentation which achieves promising performance. However, due to the intrinsic locality of convolution operations, CNN demonstrates limitations in explicitly modeling long-range dependency. Recently proposed hybrid CNN-Transformer architectures that combine the global perception capability of local feature and the local details of global reppresentations. However, the serial structure of CNN and transformer will increase the computational complexity, and then the redundant information generated by convolution operation may leads to the failure of long-range modeling. To this end, this paper proposes a double encoder framework including global encoder and local encoder, TransDE for short, to medical image segmentation. The global encoder takes transformer that designed for sequence-to-sequence prediction, while the local encoder adopts VGG-19 combined with the atrous spatial pyramid pooling (ASPP) to bring about local feature extraction. The experimental results of enteroscopy dataset and dermoscopy dataset show the superiority of our TransDE achieving around 1.97% improvement on CVC-ClinicDB in terms of DSC and 1.6% improvement on Lesion Boundary Segmentation challenge.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"142 1","pages":"374-378"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77360605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00120
Lisha Hu, Chunyu Hu
“Algorithm Design and Analysis” is a professional compulsory course for computer undergraduates. A solid grasp of the content of the course is of great importance for students to engage in relevant positions after graduation such as algorithm engineers or to further study. Nowadays, a large number of application problems need to be solved by machine learning algorithms. In fact, the underlying implementation details of many machine learning algorithms are also derived from these basic algorithms. However, there are few descriptions related to machine learning algorithms in current algorithm courses. In the process of teaching basic algorithms, if automatic association with machine learning algorithms can be realized, knowledge will root in the core knowledge base of students, thereby realizing continuous extension of knowledge. Based on this, this paper effectively associates divide and conquer and greedy algorithms with the machine learning representative --- decision tree algorithm, so as to improve the students' analogy of relevant contents and knowledge and draw inferences from one instance.
{"title":"Fusion of Machine Learning for Teaching Case Research on Algorithm Course","authors":"Lisha Hu, Chunyu Hu","doi":"10.1109/ITME53901.2021.00120","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00120","url":null,"abstract":"“Algorithm Design and Analysis” is a professional compulsory course for computer undergraduates. A solid grasp of the content of the course is of great importance for students to engage in relevant positions after graduation such as algorithm engineers or to further study. Nowadays, a large number of application problems need to be solved by machine learning algorithms. In fact, the underlying implementation details of many machine learning algorithms are also derived from these basic algorithms. However, there are few descriptions related to machine learning algorithms in current algorithm courses. In the process of teaching basic algorithms, if automatic association with machine learning algorithms can be realized, knowledge will root in the core knowledge base of students, thereby realizing continuous extension of knowledge. Based on this, this paper effectively associates divide and conquer and greedy algorithms with the machine learning representative --- decision tree algorithm, so as to improve the students' analogy of relevant contents and knowledge and draw inferences from one instance.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"56 1","pages":"569-572"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79452880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00113
Xiaoyan Liu, Yang Xu
Taking the creative design professional group of the Art College of Dalian University of technology as an example, based on the background of the integration of industry and education, according to the group logic of the professional group docking with the industrial cluster, this paper discusses the construction path of the talent training mode of “two pairs, 335 stages studio system” of the professional group, expounds the effectiveness of the reform of the talent training mode, and Teaching reform provides theoretical reference and practical guidance for future development.
{"title":"Exploration and practice of “studio system” talent training mode of design specialty under the background of integration of industry and education","authors":"Xiaoyan Liu, Yang Xu","doi":"10.1109/ITME53901.2021.00113","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00113","url":null,"abstract":"Taking the creative design professional group of the Art College of Dalian University of technology as an example, based on the background of the integration of industry and education, according to the group logic of the professional group docking with the industrial cluster, this paper discusses the construction path of the talent training mode of “two pairs, 335 stages studio system” of the professional group, expounds the effectiveness of the reform of the talent training mode, and Teaching reform provides theoretical reference and practical guidance for future development.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"100 1","pages":"533-536"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79499260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00088
Shejuan Liu, Zhimin Tao
Objective: To analyze the role of psychopsychological factors in the onset of irritable bowel syndrome (IBS). Methods: Using 60 IBS patients (observation group) and 60 healthy college students (control group), Both groups were investigated using the Hamilton Depression Scale (HAMD), the Hamilton Anxiety Scale (HAMA), and Symptions Check List 90 (SCL-90). Results: Group IBS was HAMD, The HAMA scores were higher than the control group (P <0.05); the IBS group in interpersonal relationship, depression, terror, anxiety, somatization, paranoia, forced factors and SCL-90 scores were higher than the control group (P <0.05). Conclusion: The IBS patients had different levels of anxiety, depression and psychological abnormalities, Note that psychopsychological factors play an important role in the onset of IBS, Failure to receive psychotherapy in IBS patients will make the condition repeated and more serious, Form a vicious circle.
{"title":"Analysis of psychological factors in irritable bowel syndrome","authors":"Shejuan Liu, Zhimin Tao","doi":"10.1109/ITME53901.2021.00088","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00088","url":null,"abstract":"Objective: To analyze the role of psychopsychological factors in the onset of irritable bowel syndrome (IBS). Methods: Using 60 IBS patients (observation group) and 60 healthy college students (control group), Both groups were investigated using the Hamilton Depression Scale (HAMD), the Hamilton Anxiety Scale (HAMA), and Symptions Check List 90 (SCL-90). Results: Group IBS was HAMD, The HAMA scores were higher than the control group (P <0.05); the IBS group in interpersonal relationship, depression, terror, anxiety, somatization, paranoia, forced factors and SCL-90 scores were higher than the control group (P <0.05). Conclusion: The IBS patients had different levels of anxiety, depression and psychological abnormalities, Note that psychopsychological factors play an important role in the onset of IBS, Failure to receive psychotherapy in IBS patients will make the condition repeated and more serious, Form a vicious circle.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"73 1","pages":"409-411"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85214114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00131
Lin Jinjiao, Zhao Yanze, Wen Yuhua, Gao Tianqi
This paper studies learning engagement measurement in SPOC. Based on the existing literature and the analysis of SPOC learning engagement process, a learning engagement evaluation index system is proposed that integrates offline and online data. It realizes the quantitative study of learning engagement based on data.
{"title":"The Evaluation System of SPOC Learning Engagement","authors":"Lin Jinjiao, Zhao Yanze, Wen Yuhua, Gao Tianqi","doi":"10.1109/ITME53901.2021.00131","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00131","url":null,"abstract":"This paper studies learning engagement measurement in SPOC. Based on the existing literature and the analysis of SPOC learning engagement process, a learning engagement evaluation index system is proposed that integrates offline and online data. It realizes the quantitative study of learning engagement based on data.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"121 1","pages":"618-622"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85863266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00082
Zhongmin Liu, Zhiming Luo, Jiajun Xu, Shaozi Li
Extracting and standardizing symptoms from traditional Chinese medical records plays an important role in intelligent diagnosis. Recently, abundant word vector models have been developed and used in natural language processing tasks due to their powerful performance. However, simply using a word vector model as core to analysis text is hard to satisfy both time and precision requirements. To improve this situation, we introduce an improved word vector-based symptom extraction method for traditional Chinese medicine which can extract and standardize symptoms in original medical texts written in Chinese. We design this method into three parts, Word Segmentation, Word Vector Generation, and Term Substitution. Experimental results on our dataset show that our method has a good effect in extracting medical symptoms and discarding redundant words. Compared to other baseline models of word vector representation, our method performs well in general performance of efficiency and accuracy.
{"title":"An Improved Word Vector-Based Symptom Extraction Method for Traditional Chinese Medical Record Analysis","authors":"Zhongmin Liu, Zhiming Luo, Jiajun Xu, Shaozi Li","doi":"10.1109/ITME53901.2021.00082","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00082","url":null,"abstract":"Extracting and standardizing symptoms from traditional Chinese medical records plays an important role in intelligent diagnosis. Recently, abundant word vector models have been developed and used in natural language processing tasks due to their powerful performance. However, simply using a word vector model as core to analysis text is hard to satisfy both time and precision requirements. To improve this situation, we introduce an improved word vector-based symptom extraction method for traditional Chinese medicine which can extract and standardize symptoms in original medical texts written in Chinese. We design this method into three parts, Word Segmentation, Word Vector Generation, and Term Substitution. Experimental results on our dataset show that our method has a good effect in extracting medical symptoms and discarding redundant words. Compared to other baseline models of word vector representation, our method performs well in general performance of efficiency and accuracy.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"17 1","pages":"379-384"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84776801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：