Pub Date : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061294
Lingxi Chen, Yuan-da Xu, Bin Li, Hongqiang Mo
Diaphragm electromyography (EMGdi) collected by esophageal electrodes can provide important information for the assessment of the respiratory system. But it is vulnerable to electrocardiogram (ECG) interference. It is pointed out that the autocorrelation function of EMGdi is significantly different from that of ECG. And accordingly, a filter based on linear prediction is proposed to suppress the ECG interference. The coefficients of the filter are adjusted on line so as to adapt to different subjects or the slow change of the autocorrelation function of the same subject over time. The filter is applied to clinically acquired signals, and the results demonstrate that it can effectively suppress the ECG interference, and the filtered EMGdi is in a good synchronization with the transdiaphragmatic pressure (Pdi).
{"title":"Adaptive Noise-Reduction Algorithm for Diaphragm Electromyography Based on Linear Prediction","authors":"Lingxi Chen, Yuan-da Xu, Bin Li, Hongqiang Mo","doi":"10.1109/ISBP57705.2023.10061294","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061294","url":null,"abstract":"Diaphragm electromyography (EMGdi) collected by esophageal electrodes can provide important information for the assessment of the respiratory system. But it is vulnerable to electrocardiogram (ECG) interference. It is pointed out that the autocorrelation function of EMGdi is significantly different from that of ECG. And accordingly, a filter based on linear prediction is proposed to suppress the ECG interference. The coefficients of the filter are adjusted on line so as to adapt to different subjects or the slow change of the autocorrelation function of the same subject over time. The filter is applied to clinically acquired signals, and the results demonstrate that it can effectively suppress the ECG interference, and the filtered EMGdi is in a good synchronization with the transdiaphragmatic pressure (Pdi).","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123880423","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}
ECG recognition is of great significance to the diagnosis of heart diseases. Based on the data of the MIT-BIH Arrhythmia Database, a more accurate ECG signal map was extracted using wavelet transform, a BP neural network was constructed for pattern recognition, and five types of arrhythmia-sinus arrhythmia, premature beats, Yibo, sinoatrial block, and atrial block. And compared with the BP network using SVM and K nearest neighbor algorithm, it is found that the BP network performs better.
{"title":"Classification and Processing of MIT-BIH Arrhythmia-Based on BP Algorithm","authors":"Fumin Mi, Baixuan Li, Xiaojie Cheng, Yunjie Zhao, Minyi Li, Jin Jing","doi":"10.1109/ISBP57705.2023.10061303","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061303","url":null,"abstract":"ECG recognition is of great significance to the diagnosis of heart diseases. Based on the data of the MIT-BIH Arrhythmia Database, a more accurate ECG signal map was extracted using wavelet transform, a BP neural network was constructed for pattern recognition, and five types of arrhythmia-sinus arrhythmia, premature beats, Yibo, sinoatrial block, and atrial block. And compared with the BP network using SVM and K nearest neighbor algorithm, it is found that the BP network performs better.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125643619","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061308
Hua-Ru Wang, Yanju Jing
The advent of the era of artificial intelligence (AI) has greatly promoted the integration and development of multi-disciplines, especially in the fields of health care and education. At present, artificial intelligence technology has penetrated into various fields of medicine, through the establishment of data information processing model and its advanced computer software analysis system, to promote the diagnosis of patients, drug discovery and hospital management. To this end, this paper summarizes the technical experimental support of artificial intelligence in drug design, clinical trial design, synthetic biology and tumor, aiming to promote the continuous update and development of AI technology and lead a new era of revolution.
{"title":"Research on the Application of Artificial Intelligence in the Development of Biomedicine and Oncology","authors":"Hua-Ru Wang, Yanju Jing","doi":"10.1109/ISBP57705.2023.10061308","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061308","url":null,"abstract":"The advent of the era of artificial intelligence (AI) has greatly promoted the integration and development of multi-disciplines, especially in the fields of health care and education. At present, artificial intelligence technology has penetrated into various fields of medicine, through the establishment of data information processing model and its advanced computer software analysis system, to promote the diagnosis of patients, drug discovery and hospital management. To this end, this paper summarizes the technical experimental support of artificial intelligence in drug design, clinical trial design, synthetic biology and tumor, aiming to promote the continuous update and development of AI technology and lead a new era of revolution.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129293616","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061317
Yuehua Song
In recent years, the rapid development of artificial intelligence (AI) has accelerated the development of many social industries. In view of the demand for large data collection and effective medical data processing, AI has undoubtedly become an important part of biomedical research. Medical professionals can accurately diagnose and treat a variety of symptoms in patients with the help of AI algorithms. Modern AI technologies, such as traditional neural networks for structured data and natural language processing for unstructured data, can accurately analyze various medical data. The medical industry uses these AI learning techniques for disease diagnosis, drug discovery, and medical image analysis. Against this backdrop, this paper focuses on the application of AI algorithms in biomedicine and examined cases from biomedical research in addition to the introduction of machine learning, deep learning, and transformer models. Last but not least, we briefly introduce the progress of AI in biomedicine and the difficulties it will encounter.
{"title":"Artificial Intelligence Algorithms in Biomedical Application","authors":"Yuehua Song","doi":"10.1109/ISBP57705.2023.10061317","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061317","url":null,"abstract":"In recent years, the rapid development of artificial intelligence (AI) has accelerated the development of many social industries. In view of the demand for large data collection and effective medical data processing, AI has undoubtedly become an important part of biomedical research. Medical professionals can accurately diagnose and treat a variety of symptoms in patients with the help of AI algorithms. Modern AI technologies, such as traditional neural networks for structured data and natural language processing for unstructured data, can accurately analyze various medical data. The medical industry uses these AI learning techniques for disease diagnosis, drug discovery, and medical image analysis. Against this backdrop, this paper focuses on the application of AI algorithms in biomedicine and examined cases from biomedical research in addition to the introduction of machine learning, deep learning, and transformer models. Last but not least, we briefly introduce the progress of AI in biomedicine and the difficulties it will encounter.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126302031","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061320
XiangDong Ma, Jianhua Chen
We propose an efficient referential genome compression algorithm called RCCG. It extends reference genomes by its reverse complementation and uses coprime window sampling to detect the maximum matches (MEMs) between two genome sequences. After the assessment, those selected matches will be united to form mutation-containing matches (MCMs). The average compression ratio of the proposed algorithm is higher than that of the state-of-the-art genome compression algorithms.
{"title":"Improving Genome Compression Performance by Extending Reference Sequences","authors":"XiangDong Ma, Jianhua Chen","doi":"10.1109/ISBP57705.2023.10061320","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061320","url":null,"abstract":"We propose an efficient referential genome compression algorithm called RCCG. It extends reference genomes by its reverse complementation and uses coprime window sampling to detect the maximum matches (MEMs) between two genome sequences. After the assessment, those selected matches will be united to form mutation-containing matches (MCMs). The average compression ratio of the proposed algorithm is higher than that of the state-of-the-art genome compression algorithms.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126100335","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061309
Xiaolong Wu
Modern remote sensing technology has developed rapidly in recent years. The high-resolution remote sensing images brought by new technologies have good application prospects in military and civilian fields, but the information contained in them is also richer, which increases the complexity of remote sensing image analysis and understanding. At present, artificial intelligence technology represented by deep learning has been widely used in the field of image processing. This paper adopts the U-net network model and uses the transfer learning method to train on the remote sensing image dataset published by the French National Institute of Information and Automation (Inria) to verify the effectiveness of the deep learning semantic segmentation method on high-resolution remote sensing images. and stability. Experiments show that the model has an accuracy of 86.86% in extracting buildings from images, a recall rate of 82.54%, and an average intersection ratio of 84.53%, which is effective in semantic segmentation of high-resolution remote sensing images.
{"title":"Building Semantic Segmentation of High-resolution Remote Sensing Image Buildings Based on U-net Network Model Based on Pytorch Framework","authors":"Xiaolong Wu","doi":"10.1109/ISBP57705.2023.10061309","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061309","url":null,"abstract":"Modern remote sensing technology has developed rapidly in recent years. The high-resolution remote sensing images brought by new technologies have good application prospects in military and civilian fields, but the information contained in them is also richer, which increases the complexity of remote sensing image analysis and understanding. At present, artificial intelligence technology represented by deep learning has been widely used in the field of image processing. This paper adopts the U-net network model and uses the transfer learning method to train on the remote sensing image dataset published by the French National Institute of Information and Automation (Inria) to verify the effectiveness of the deep learning semantic segmentation method on high-resolution remote sensing images. and stability. Experiments show that the model has an accuracy of 86.86% in extracting buildings from images, a recall rate of 82.54%, and an average intersection ratio of 84.53%, which is effective in semantic segmentation of high-resolution remote sensing images.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120975544","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061316
Jing Xia
The brain goes through various anatomical changes with age. These alterations are a result of ageing naturally. A more profound comprehension of these typical changes is crucial for separating them from pathogenic ones. In this study, we exhibit the ageing trajectories of cortical morphology by using cortical thickness from 55 to 85 years old. To explore the ageing hierarchical pattern, the whole cortex is divided into different regions with similar ageing trajectories. To construct the similarity matrix, we computed Pearson’s correlation coefficient between the cortical thickness of any paired vertices on the cortical surface. Then, we applied the parcellation method based on the similarity matrix on 490 normal middle-aged and old adults from 55 to 85 years old, and achieved meaningful hierarchical parcellation ageing maps based on cortical ageing trajectory. We then fit the ageing trajectory of the cortical thickness in each cluster. The results indicate that the rapid thinning regions in clusters are related to the temporal cortex and prefrontal cortices, while slowly thinning regions in clusters are related to the insula and medial occipital cortices. Importantly, our generated parcellation ageing maps indicate the hierarchical ageing patterns of normal middle-age and old adults, which is essential in disease diagnosing related to neurodegeneration and can help understand the ageing process.
{"title":"Pacellation method based on brain cortical morphological aging trajectory in normal cohorts","authors":"Jing Xia","doi":"10.1109/ISBP57705.2023.10061316","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061316","url":null,"abstract":"The brain goes through various anatomical changes with age. These alterations are a result of ageing naturally. A more profound comprehension of these typical changes is crucial for separating them from pathogenic ones. In this study, we exhibit the ageing trajectories of cortical morphology by using cortical thickness from 55 to 85 years old. To explore the ageing hierarchical pattern, the whole cortex is divided into different regions with similar ageing trajectories. To construct the similarity matrix, we computed Pearson’s correlation coefficient between the cortical thickness of any paired vertices on the cortical surface. Then, we applied the parcellation method based on the similarity matrix on 490 normal middle-aged and old adults from 55 to 85 years old, and achieved meaningful hierarchical parcellation ageing maps based on cortical ageing trajectory. We then fit the ageing trajectory of the cortical thickness in each cluster. The results indicate that the rapid thinning regions in clusters are related to the temporal cortex and prefrontal cortices, while slowly thinning regions in clusters are related to the insula and medial occipital cortices. Importantly, our generated parcellation ageing maps indicate the hierarchical ageing patterns of normal middle-age and old adults, which is essential in disease diagnosing related to neurodegeneration and can help understand the ageing process.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125290635","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061315
Chunhui Zhu, Xiaowei Niu, Lu Zuo, Ziwei Liu
In view of the slightly low accuracy of the existing overall segmentation algorithm of retinal vessels, a fused residual attention dense convolution double-U network, LSCD-UNet (Laddernet network based on scSE-Residual and CBAM and dense cavity convolution) was proposed.. Laddernet, a form of UNet, was introduced into the network. On this basis, the residual module with shared weights was upgraded and replaced with the scSE-Residual module of shared weights to facilitate feature enhancement extraction. A multi-module was introduced at the bottom of this network, consisting of the Convolutional Attention Mechanism Module (CBAM) and Dense Cavity Convolution Module (DAC) in series to expand the field of view and capture more subtle vascular features. Hybrid loss function was used to accelerate the network convergence. The LSCD-UNet algorithm was validated on the public datasets, DRIVE and STARE,. The results showed that the LSCD-UNet algorithm had an accuracy of 97.35% and 97.28%, a sensitivity of 81.80% and 86.23%, an AUC of 98.82% and 99.02%, and an F1 value of 84.89% and 84.97%, respectively, outperforming UNet and Laddernet and other retinal vessel segmentation algorithms.
{"title":"Fused Residual Attention Dense Double-U Network Retinal Vessel Segmentation Algorithm","authors":"Chunhui Zhu, Xiaowei Niu, Lu Zuo, Ziwei Liu","doi":"10.1109/ISBP57705.2023.10061315","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061315","url":null,"abstract":"In view of the slightly low accuracy of the existing overall segmentation algorithm of retinal vessels, a fused residual attention dense convolution double-U network, LSCD-UNet (Laddernet network based on scSE-Residual and CBAM and dense cavity convolution) was proposed.. Laddernet, a form of UNet, was introduced into the network. On this basis, the residual module with shared weights was upgraded and replaced with the scSE-Residual module of shared weights to facilitate feature enhancement extraction. A multi-module was introduced at the bottom of this network, consisting of the Convolutional Attention Mechanism Module (CBAM) and Dense Cavity Convolution Module (DAC) in series to expand the field of view and capture more subtle vascular features. Hybrid loss function was used to accelerate the network convergence. The LSCD-UNet algorithm was validated on the public datasets, DRIVE and STARE,. The results showed that the LSCD-UNet algorithm had an accuracy of 97.35% and 97.28%, a sensitivity of 81.80% and 86.23%, an AUC of 98.82% and 99.02%, and an F1 value of 84.89% and 84.97%, respectively, outperforming UNet and Laddernet and other retinal vessel segmentation algorithms.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121642392","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061301
Ming Liu, Jianqiang Du, Zhiqing Li, Jigen Luo, Bin Nie, Mengting Zhang
The experimental data on traditional Chinese medicine efficacy has many irrelevant and redundant features, and different feature combinations have different effects. Therefore, we propose a hybrid multistage feature selection algorithm based on approximate Markov blanket and improved black widow algorithm. The first stage remove irrelevant features by the maximum information coefficient. The second stage delete redundant features from clustered searched by approximate Markov blanket by Lasso algorithm to avoid information loss. The third stage search the optimal feature subset by improved black widow algorithm that used the fast reproduction strategy, the child eating mother strategy and the population restriction strategy. The proposed approach is tested on the basic material data of traditional Chinese medicine and 9 UCI datasets, and compared with other feature selection algorithms. The experimental results show that the algorithm can obtain a small number of feature subsets with high accuracy, and has good time performance.
{"title":"Hybrid Multistage Feature Selection Method and its Application in Chinese Medicine","authors":"Ming Liu, Jianqiang Du, Zhiqing Li, Jigen Luo, Bin Nie, Mengting Zhang","doi":"10.1109/ISBP57705.2023.10061301","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061301","url":null,"abstract":"The experimental data on traditional Chinese medicine efficacy has many irrelevant and redundant features, and different feature combinations have different effects. Therefore, we propose a hybrid multistage feature selection algorithm based on approximate Markov blanket and improved black widow algorithm. The first stage remove irrelevant features by the maximum information coefficient. The second stage delete redundant features from clustered searched by approximate Markov blanket by Lasso algorithm to avoid information loss. The third stage search the optimal feature subset by improved black widow algorithm that used the fast reproduction strategy, the child eating mother strategy and the population restriction strategy. The proposed approach is tested on the basic material data of traditional Chinese medicine and 9 UCI datasets, and compared with other feature selection algorithms. The experimental results show that the algorithm can obtain a small number of feature subsets with high accuracy, and has good time performance.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121144914","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 : 2023-01-06DOI: 10.1109/ISBP57705.2023.10061295
Yilin Zhang
An advanced convolutional neural network architecture for forecasting blood glucose is proposed in this paper. Four different measures are introduced in this essay, including Glucose, Meal, Insulin, and Time of the day, which are denoted as G, M, I, and T for short. Past 2-hour historical data of individuals are exploited to predict the future glucose level in 30 minutes with high accuracy. To verify the effectiveness of the blood glucose prediction model, three major methods have been displayed and compared. To be more specific, Recurrent Neural Network (RNN) was the better model for forecasting blood glucose, compared with Neural Network Predictive Glucose (NNPG) and Support Vector Regression (SVM). The metrics of evaluation are Root-Mean-Square deviation (RMSE) and Mean Absolute Relative Difference (MARD). The average of the best RMSE is 7.75, which is largely better than those of the other two models. This result shows the superior performance of RNN in accurate glucose prediction.
提出了一种用于血糖预测的卷积神经网络结构。本文介绍了四种不同的测量方法，包括葡萄糖，膳食，胰岛素和一天中的时间，简称为G, M, I和T。利用个体过去2小时的历史数据预测未来30分钟内的血糖水平，准确度高。为了验证血糖预测模型的有效性，展示并比较了三种主要方法。更具体地说，与神经网络预测血糖(NNPG)和支持向量回归(SVM)相比，递归神经网络(RNN)是更好的血糖预测模型。评价指标为均方根偏差(RMSE)和平均绝对相对差(MARD)。最佳RMSE的平均值为7.75，大大优于其他两个模型。这一结果显示了RNN在准确预测血糖方面的优越性能。
{"title":"Glucose Prediction Based on the Recurrent Neural Network Model","authors":"Yilin Zhang","doi":"10.1109/ISBP57705.2023.10061295","DOIUrl":"https://doi.org/10.1109/ISBP57705.2023.10061295","url":null,"abstract":"An advanced convolutional neural network architecture for forecasting blood glucose is proposed in this paper. Four different measures are introduced in this essay, including Glucose, Meal, Insulin, and Time of the day, which are denoted as G, M, I, and T for short. Past 2-hour historical data of individuals are exploited to predict the future glucose level in 30 minutes with high accuracy. To verify the effectiveness of the blood glucose prediction model, three major methods have been displayed and compared. To be more specific, Recurrent Neural Network (RNN) was the better model for forecasting blood glucose, compared with Neural Network Predictive Glucose (NNPG) and Support Vector Regression (SVM). The metrics of evaluation are Root-Mean-Square deviation (RMSE) and Mean Absolute Relative Difference (MARD). The average of the best RMSE is 7.75, which is largely better than those of the other two models. This result shows the superior performance of RNN in accurate glucose prediction.","PeriodicalId":309634,"journal":{"name":"2023 International Conference on Intelligent Supercomputing and BioPharma (ISBP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126033481","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：