Pub Date : 2021-12-17DOI: 10.1109/PIC53636.2021.9687045
B. Zeng, Rui Wang, Chun-hui Yang
The application of optical fiber technology in ships has changed the traditional marine network architecture and improved the reliability and security of the communication of ship equipment. However, current complicated ship equipment and different supporting network standards restrict the sharing and use of information in the ship integrated bridge system. In order to address the problem, an integrated gateway system is designed, meanwhile the protocol conversion method, structure and components and packet scheduling algorithm is studied. Finally, NS3 was used to analyze performance associated with priority and bandwidth.
{"title":"Design of Integrated Gateway System for Marine Communication","authors":"B. Zeng, Rui Wang, Chun-hui Yang","doi":"10.1109/PIC53636.2021.9687045","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687045","url":null,"abstract":"The application of optical fiber technology in ships has changed the traditional marine network architecture and improved the reliability and security of the communication of ship equipment. However, current complicated ship equipment and different supporting network standards restrict the sharing and use of information in the ship integrated bridge system. In order to address the problem, an integrated gateway system is designed, meanwhile the protocol conversion method, structure and components and packet scheduling algorithm is studied. Finally, NS3 was used to analyze performance associated with priority and bandwidth.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130077741","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}
In the field of optimization algorithms, hybrid algorithms are increasingly valued by researchers for their effectiveness in improving algorithmic capabilities.In recent years, a new type of natural meta-heuristic algorithm called whale optimization algorithm has been proposed. The algorithm refers to whales in nature and imitates their three different feeding methods to solve realistic optimization problems. The particle swarm algorithm, on the other hand, is an algorithm proposed by imitating the way a flock of birds transmits information. As population intelligence algorithms, the accuracy of these two algorithms are not high enough in the convergence process. At the same time, they tend to fall into the local optimum. In this paper, a hybrid algorithm based on whale optimization algorithm and particle swarm algorithm is proposed to update the population by a kind of selection iteration. The experimental results confirm that the algorithm has excellent superiority in convergence accuracy and convergence speed.
{"title":"A Hybrid Whale Optimization and Particle Swarm Optimization Algorithm","authors":"Zijing Yuan, Jiayi Li, Haichuan Yang, Baohang Zhang","doi":"10.1109/PIC53636.2021.9687017","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687017","url":null,"abstract":"In the field of optimization algorithms, hybrid algorithms are increasingly valued by researchers for their effectiveness in improving algorithmic capabilities.In recent years, a new type of natural meta-heuristic algorithm called whale optimization algorithm has been proposed. The algorithm refers to whales in nature and imitates their three different feeding methods to solve realistic optimization problems. The particle swarm algorithm, on the other hand, is an algorithm proposed by imitating the way a flock of birds transmits information. As population intelligence algorithms, the accuracy of these two algorithms are not high enough in the convergence process. At the same time, they tend to fall into the local optimum. In this paper, a hybrid algorithm based on whale optimization algorithm and particle swarm algorithm is proposed to update the population by a kind of selection iteration. The experimental results confirm that the algorithm has excellent superiority in convergence accuracy and convergence speed.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131997943","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687081
Rui Xue, Guohu Li, Xiao-ning Ma, Yifei Liu, Min Liu, Yanjun Liu
Networks in real life have been increasingly dependent on each other, and therefore, they have become more complex and intertwined, with consequences of relations that are difficult to identify, understand and represent. Besides, the coupling interactions among layers may vary in different types of complex networks. Thus, it is demanding to focus on this interdependence when the cost of taking inter-layer steps weights more in networks such as transportation. To obtain representative node embeddings in complex networks, we propose a solution collecting coupling relations among layers with contrastive learning. Specifically, we develop a framework, termed TransCL, with encoders in two aspects to embed intra-layer and inter-layer node representations. Besides, we introduce random walk betweenness centrality to the inter-layer embeddings and leverage this measurement to improve contrastive learning. The link prediction as a downstream task is followed to evaluate the embedding performance. We compare this method with other popular embedding models on the public dataset Cora and a real-world industrial dataset. This model outperforms other methods on the industrial dataset and meanwhile shows competitive performance on the public dataset. This work, in sum, allows for obtaining complex network representations with layer interdependence learned in a self-supervised manner.
{"title":"TransCL: Contrastive Learning on Complex Transportation Network","authors":"Rui Xue, Guohu Li, Xiao-ning Ma, Yifei Liu, Min Liu, Yanjun Liu","doi":"10.1109/PIC53636.2021.9687081","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687081","url":null,"abstract":"Networks in real life have been increasingly dependent on each other, and therefore, they have become more complex and intertwined, with consequences of relations that are difficult to identify, understand and represent. Besides, the coupling interactions among layers may vary in different types of complex networks. Thus, it is demanding to focus on this interdependence when the cost of taking inter-layer steps weights more in networks such as transportation. To obtain representative node embeddings in complex networks, we propose a solution collecting coupling relations among layers with contrastive learning. Specifically, we develop a framework, termed TransCL, with encoders in two aspects to embed intra-layer and inter-layer node representations. Besides, we introduce random walk betweenness centrality to the inter-layer embeddings and leverage this measurement to improve contrastive learning. The link prediction as a downstream task is followed to evaluate the embedding performance. We compare this method with other popular embedding models on the public dataset Cora and a real-world industrial dataset. This model outperforms other methods on the industrial dataset and meanwhile shows competitive performance on the public dataset. This work, in sum, allows for obtaining complex network representations with layer interdependence learned in a self-supervised manner.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127945292","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}
Diabetes mellitus (DM) prediction facilitates timely targeted treatment and interventions in the early stages of DM, and is important for reducing the incidence of DM and analyzing risk factors. In this paper, we proposed an integrated learning model GC-Stacking based on Genetic Algorithm (GA) and improved CatBoost method. Firstly, we selected the most optimal set of traits associated with diabetes risk factors based on the global search capability of genetic algorithm (GA); Then, the improved CatBoost method is combined with KNN, SVM and other algorithms with excellent prediction performance as the main learner, and then, the stack ensemble learning strategy is adopted. RF is used as a secondary learner to train this integrated prediction model, which uses the selected features for diabetes prediction. The model was validated on the Qingdao CDC physical examination dataset and the UCI public diabetes dataset. The experimental results showed that the GC-stacking model based on 7-fold cross validation has better predictive performance. It outperforms other algorithms in terms of accuracy, Fl-score and other performance metrics.
{"title":"Integrated Learning Model Based on GC-Stacking for Early Prediction of Diabetes Mellitus","authors":"Xiaoxia Li, Jianjun Zhang, Peishun Liu, Ruichun Tang, Qing Guo, Qinshuo Wang","doi":"10.1109/PIC53636.2021.9687044","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687044","url":null,"abstract":"Diabetes mellitus (DM) prediction facilitates timely targeted treatment and interventions in the early stages of DM, and is important for reducing the incidence of DM and analyzing risk factors. In this paper, we proposed an integrated learning model GC-Stacking based on Genetic Algorithm (GA) and improved CatBoost method. Firstly, we selected the most optimal set of traits associated with diabetes risk factors based on the global search capability of genetic algorithm (GA); Then, the improved CatBoost method is combined with KNN, SVM and other algorithms with excellent prediction performance as the main learner, and then, the stack ensemble learning strategy is adopted. RF is used as a secondary learner to train this integrated prediction model, which uses the selected features for diabetes prediction. The model was validated on the Qingdao CDC physical examination dataset and the UCI public diabetes dataset. The experimental results showed that the GC-stacking model based on 7-fold cross validation has better predictive performance. It outperforms other algorithms in terms of accuracy, Fl-score and other performance metrics.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115326816","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687041
Yuanbo Huang, Zhuo Zhang, Xiaolong Xu
The surface crack of underwater dam is one of the important indexes to evaluate the normal operation of the dam. Complete crack image is an important means to improve the accuracy of evaluation. In view of the limitations of traditional Algorithms in underwater crack image stitching, we propose an underwater dam surface crack image stitching algorithm based on region division(ISA-RD). First of all, an image enhancement algorithm aiming at increasing the number of feature points is used. Secondly, we simplify the process of feature point selection and matching by relying on the features of multiple regions in the local crack image, and improve the matching accuracy by mining the close relationship between the matching of feature points and different regions. Finally, the high matching feature point pairs are used for image fusion. We take the crack image of the real scene as the research object. Compared with the classical image stitching algorithm, the feature point matching algorithm proposed in this paper improves the accuracy of feature point matching. Obviously, the image quality after stitching is improved.
{"title":"Image Stitching Algorithm Based on Region Division for Underwater Dam Crack Image","authors":"Yuanbo Huang, Zhuo Zhang, Xiaolong Xu","doi":"10.1109/PIC53636.2021.9687041","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687041","url":null,"abstract":"The surface crack of underwater dam is one of the important indexes to evaluate the normal operation of the dam. Complete crack image is an important means to improve the accuracy of evaluation. In view of the limitations of traditional Algorithms in underwater crack image stitching, we propose an underwater dam surface crack image stitching algorithm based on region division(ISA-RD). First of all, an image enhancement algorithm aiming at increasing the number of feature points is used. Secondly, we simplify the process of feature point selection and matching by relying on the features of multiple regions in the local crack image, and improve the matching accuracy by mining the close relationship between the matching of feature points and different regions. Finally, the high matching feature point pairs are used for image fusion. We take the crack image of the real scene as the research object. Compared with the classical image stitching algorithm, the feature point matching algorithm proposed in this paper improves the accuracy of feature point matching. Obviously, the image quality after stitching is improved.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"363 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115977437","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687071
Kevin Kollek, M. Aguilar, Marco Braun, A. Kummert
Pruning techniques for neural networks are applied to achieve superior model compression while maintaining accuracy. Common pruning approaches rely on single granularity (e.g., weights, channels, or layers) compression techniques and miss valuable optimization potential. This major limitation results in a sequence of obsolete layers with a small number of channels or highly sparse weights. In this paper, we present a novel pruning approach to address this issue. More precisely, in this work, a Multi-Grain Pruning (MGP) framework is proposed to optimize neural network architectures from coarse to fine in up to four different granularities. Besides the traditional pruning granularities, a new granularity is introduced on so-called blocks, which consist of multiple layers. By combining multiple pruning granularities, models can be optimized even further. We evaluated the proposed framework with VGG-19 on CIFAR-10 and CIFAR-100 as well as ResNet-56 on CIFAR-10 and ResNet-50 on ImageNet. The results show that our technique achieves from 31.9x up to 185.3x model compression rates with an accuracy drop from 0.08% up to 1.73% with VGG-19 on CIFAR-10.
{"title":"Improving Neural Network Architecture Compression by Multi-Grain Pruning","authors":"Kevin Kollek, M. Aguilar, Marco Braun, A. Kummert","doi":"10.1109/PIC53636.2021.9687071","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687071","url":null,"abstract":"Pruning techniques for neural networks are applied to achieve superior model compression while maintaining accuracy. Common pruning approaches rely on single granularity (e.g., weights, channels, or layers) compression techniques and miss valuable optimization potential. This major limitation results in a sequence of obsolete layers with a small number of channels or highly sparse weights. In this paper, we present a novel pruning approach to address this issue. More precisely, in this work, a Multi-Grain Pruning (MGP) framework is proposed to optimize neural network architectures from coarse to fine in up to four different granularities. Besides the traditional pruning granularities, a new granularity is introduced on so-called blocks, which consist of multiple layers. By combining multiple pruning granularities, models can be optimized even further. We evaluated the proposed framework with VGG-19 on CIFAR-10 and CIFAR-100 as well as ResNet-56 on CIFAR-10 and ResNet-50 on ImageNet. The results show that our technique achieves from 31.9x up to 185.3x model compression rates with an accuracy drop from 0.08% up to 1.73% with VGG-19 on CIFAR-10.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"323 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116434853","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687063
Fang Ye, Shunxin Li, Xin Yuan, Longfei Li
Drowsiness detection is a significant problem, most existing non-intrusive methods estimate drowsiness only by single images, without leveraging the temporal information available in the frame sequence. The lack of temporal information leads to the inability of drowsiness detection to indicate consecutive behaviors. To this end, we present a drowsiness detection method, which takes into account both eye and head pose deep feature representation by conducting feature fusion. Then, the fused feature is fed into the LSTM (Long Short-Term Memory) network to enhance the accuracy of the drowsiness detection model through temporal information. The experimental results on the NHTU-DDD dataset and the self-constructed dataset show that the proposed method outperforms six existing advanced approaches.
{"title":"Multi-Level Drowsiness Detection Based on Deep Feature Fusion of Eye and Head Pose","authors":"Fang Ye, Shunxin Li, Xin Yuan, Longfei Li","doi":"10.1109/PIC53636.2021.9687063","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687063","url":null,"abstract":"Drowsiness detection is a significant problem, most existing non-intrusive methods estimate drowsiness only by single images, without leveraging the temporal information available in the frame sequence. The lack of temporal information leads to the inability of drowsiness detection to indicate consecutive behaviors. To this end, we present a drowsiness detection method, which takes into account both eye and head pose deep feature representation by conducting feature fusion. Then, the fused feature is fed into the LSTM (Long Short-Term Memory) network to enhance the accuracy of the drowsiness detection model through temporal information. The experimental results on the NHTU-DDD dataset and the self-constructed dataset show that the proposed method outperforms six existing advanced approaches.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116118648","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687082
Zhihui Feng, Quan Liang, Zicheng Zhang, W. Ji
Aiming at the problems of traditional camera calibration method, such as sensitivity to the initial values of camera model parameters and unstable calibration results. This paper proposes a camera calibration method based on sine cosine algorithm. After obtaining a certain initial value by Zhang's camera calibration method, use the sine cosine algorithm (SCA) to form the initial population in the field near the initial value, and perform iterative optimization. The average error between the actual projection point and the calculated projection point is the accuracy criterion. Using the volatility and periodicity of the sine function and cosine function to search and iterate, so that the solution can be oscillating towards the global optimum and achieve the purpose of optimization. Experiments have proved that the adaptive parameters and randomness parameters in the algorithm better balance the exploration and development capabilities of the algorithm. The improved algorithm has fewer parameters, simple structure, easy implementation, and fast convergence speed. The experiment proves that the camera calibration accuracy is effectively improved.
{"title":"Camera Calibration Method Based on Sine Cosine Algorithm","authors":"Zhihui Feng, Quan Liang, Zicheng Zhang, W. Ji","doi":"10.1109/PIC53636.2021.9687082","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687082","url":null,"abstract":"Aiming at the problems of traditional camera calibration method, such as sensitivity to the initial values of camera model parameters and unstable calibration results. This paper proposes a camera calibration method based on sine cosine algorithm. After obtaining a certain initial value by Zhang's camera calibration method, use the sine cosine algorithm (SCA) to form the initial population in the field near the initial value, and perform iterative optimization. The average error between the actual projection point and the calculated projection point is the accuracy criterion. Using the volatility and periodicity of the sine function and cosine function to search and iterate, so that the solution can be oscillating towards the global optimum and achieve the purpose of optimization. Experiments have proved that the adaptive parameters and randomness parameters in the algorithm better balance the exploration and development capabilities of the algorithm. The improved algorithm has fewer parameters, simple structure, easy implementation, and fast convergence speed. The experiment proves that the camera calibration accuracy is effectively improved.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123311051","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687046
Félix Fernández-Peña, Fernando Ibarra-Torres, Pilar Urrutia-Urrutia, D. Coello-Fiallos
Social media has been influencing almost all areas of human society during the last decade. Nevertheless, the lack of studies on the acceptance of a social storefront business model has been identified as a missing point in this research area. In this scenario, this paper evaluates the technology acceptance of a storefront website and its Facebook business page. The study was carried out with the participation of 520 young students of two Ecuadorian universities from the Coastal and the Andean region. A controlled experiment was designed based on the Technology Acceptance Model. After using the evaluated tools for two weeks, two surveys were conducted and 48 participants were interviewed. The results show that both, the perceived ease of use and the perceived usefulness of the analyzed tools have a positive impact on the behavioral intention of using social media for e-commerce. No significant differences were found but both, the storefront webpage and the Facebook business page, had positive acceptance among participants. Interviewed students sustained that social media play a key role for reinforcing the trustability of e-commerce initiatives in the country.
{"title":"Evaluating the Usability of a Social Storefront Business Model for Ecuadorian Millennials and Centennials","authors":"Félix Fernández-Peña, Fernando Ibarra-Torres, Pilar Urrutia-Urrutia, D. Coello-Fiallos","doi":"10.1109/PIC53636.2021.9687046","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687046","url":null,"abstract":"Social media has been influencing almost all areas of human society during the last decade. Nevertheless, the lack of studies on the acceptance of a social storefront business model has been identified as a missing point in this research area. In this scenario, this paper evaluates the technology acceptance of a storefront website and its Facebook business page. The study was carried out with the participation of 520 young students of two Ecuadorian universities from the Coastal and the Andean region. A controlled experiment was designed based on the Technology Acceptance Model. After using the evaluated tools for two weeks, two surveys were conducted and 48 participants were interviewed. The results show that both, the perceived ease of use and the perceived usefulness of the analyzed tools have a positive impact on the behavioral intention of using social media for e-commerce. No significant differences were found but both, the storefront webpage and the Facebook business page, had positive acceptance among participants. Interviewed students sustained that social media play a key role for reinforcing the trustability of e-commerce initiatives in the country.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116903034","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687083
Shenglan Wang, Junhui Li, Mingying Lan, Li Gao, Xiaolin Gao
Lactate threshold or gas exchange threshold is commonly used to guide exercise intensity, but direct measurement of these two are never easy for general population. Among all physiological indicators, heart rate is very easy to obtain. And the heart rate deflection point is consistent with the lactate threshold during incremental exercise. However, previous studies suffer from expertise or a priori information requirement, computation inefficiency, lack of cohort diversity, etc. Based on prior knowledge, this contribution proposes a computer-aided methods to automatically identity heart rate intersection points by sections, and further optimization. As result, among 200 healthy college student volunteers, only 8 subjects fall beyond the 95% confidence interval in residual analysis. Therefore, a self-consistent, economic, noninvasive method to estimate the lactate threshold with heart rate data only is demonstrated.
{"title":"A Computer-Aided Recognition Method of Heart Rate Deflection Point","authors":"Shenglan Wang, Junhui Li, Mingying Lan, Li Gao, Xiaolin Gao","doi":"10.1109/PIC53636.2021.9687083","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687083","url":null,"abstract":"Lactate threshold or gas exchange threshold is commonly used to guide exercise intensity, but direct measurement of these two are never easy for general population. Among all physiological indicators, heart rate is very easy to obtain. And the heart rate deflection point is consistent with the lactate threshold during incremental exercise. However, previous studies suffer from expertise or a priori information requirement, computation inefficiency, lack of cohort diversity, etc. Based on prior knowledge, this contribution proposes a computer-aided methods to automatically identity heart rate intersection points by sections, and further optimization. As result, among 200 healthy college student volunteers, only 8 subjects fall beyond the 95% confidence interval in residual analysis. Therefore, a self-consistent, economic, noninvasive method to estimate the lactate threshold with heart rate data only is demonstrated.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131565204","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：