Pub Date : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218552
Ye Wang
Traditional interactive landscape virtual reconstruction methods do not perform feature point matching processing, resulting in low reconstruction efficiency and poor reconstruction effect. Thus, an immersive interactive landscape virtual reconstruction method based was proposed based on digital virtual technology in this study. In the proposed method, an interaction system in virtual reality (VR) was constructed using digital virtual technology using relevant data. In the system, preliminary correction processing was performed on the data. To correct the optics, the scale-invariant feature transform (SIFT) algorithm was adopted to obtain the feature points of the interactive landscape and perform feature point matching processing. With the system, a texture mapping model was established to achieve the virtual reconstruction of immersive interactive landscapes. The simulation results showed that the proposed method had high reconstruction efficiency and reconstruction effect.
{"title":"Research on Reconstruction Simulation of Immersive Interactive Landscape Design Based on Digital Virtual Technology","authors":"Ye Wang","doi":"10.1109/ECBIOS57802.2023.10218552","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218552","url":null,"abstract":"Traditional interactive landscape virtual reconstruction methods do not perform feature point matching processing, resulting in low reconstruction efficiency and poor reconstruction effect. Thus, an immersive interactive landscape virtual reconstruction method based was proposed based on digital virtual technology in this study. In the proposed method, an interaction system in virtual reality (VR) was constructed using digital virtual technology using relevant data. In the system, preliminary correction processing was performed on the data. To correct the optics, the scale-invariant feature transform (SIFT) algorithm was adopted to obtain the feature points of the interactive landscape and perform feature point matching processing. With the system, a texture mapping model was established to achieve the virtual reconstruction of immersive interactive landscapes. The simulation results showed that the proposed method had high reconstruction efficiency and reconstruction effect.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133572275","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 : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218658
J. Yeh, Li-Ching Yuan
Smart agriculture has been researched in these years. With the development of artificial intelligence (AI) and Unmanned Aerial Vehicles (UAV) technology, AI-based object detection of UAV images helps to develop smart agriculture. Therefore, we propose automatic rice seedling labeling from a UAV image system based on YOLOv4. Many studies have shown great performance in object recognition from images. However, detecting small targets such as rice seedlings in UAV images is more difficult than traditional object recognition. In addition, the small number of data is also a problem to improve performance. Therefore, applying YOLOv4 and using the dataset from the AIdea contest in 2021, the proposed model is trained with the original UAV image data for data augmentation to detect small objects. We also design the user interface to upload the target images and visualization of the result. According to the experiment result, the proposed method showed an F1-score of 0.84 and improved the performance of rice seedling detection.
{"title":"Automatic Labeling of Rice Seedlings in Unmanned Aerial Vehicles Images","authors":"J. Yeh, Li-Ching Yuan","doi":"10.1109/ECBIOS57802.2023.10218658","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218658","url":null,"abstract":"Smart agriculture has been researched in these years. With the development of artificial intelligence (AI) and Unmanned Aerial Vehicles (UAV) technology, AI-based object detection of UAV images helps to develop smart agriculture. Therefore, we propose automatic rice seedling labeling from a UAV image system based on YOLOv4. Many studies have shown great performance in object recognition from images. However, detecting small targets such as rice seedlings in UAV images is more difficult than traditional object recognition. In addition, the small number of data is also a problem to improve performance. Therefore, applying YOLOv4 and using the dataset from the AIdea contest in 2021, the proposed model is trained with the original UAV image data for data augmentation to detect small objects. We also design the user interface to upload the target images and visualization of the result. According to the experiment result, the proposed method showed an F1-score of 0.84 and improved the performance of rice seedling detection.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133658841","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 : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218445
Chengcheng Yuan, Hua Li, Yuanxia Zhang, Daoqing Gong
It is well known that drug development takes a long time as well as cost. Due to the unknown nature of compounds, pharmaceutical researchers need to repeat hundreds or thousands of experiments to obtain relatively accurate results. The advent of artificial intelligence algorithms has provided great convenience for pharmaceutical researchers. Researchers have applied machine learning algorithms with artificial intelligence to the field of drug discovery and development and have achieved fruitful results. For the problem of physicochemical properties of compounds involved in the drug development process, with the FMCGEP(fuzzy multicellular gene expression programming) algorithm, we integrate the classification and regression application of compound toxicity data and compound activity data.
{"title":"Ensemble Application of Fuzzy Multicellular Gene Expression by Programming Algorithm","authors":"Chengcheng Yuan, Hua Li, Yuanxia Zhang, Daoqing Gong","doi":"10.1109/ECBIOS57802.2023.10218445","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218445","url":null,"abstract":"It is well known that drug development takes a long time as well as cost. Due to the unknown nature of compounds, pharmaceutical researchers need to repeat hundreds or thousands of experiments to obtain relatively accurate results. The advent of artificial intelligence algorithms has provided great convenience for pharmaceutical researchers. Researchers have applied machine learning algorithms with artificial intelligence to the field of drug discovery and development and have achieved fruitful results. For the problem of physicochemical properties of compounds involved in the drug development process, with the FMCGEP(fuzzy multicellular gene expression programming) algorithm, we integrate the classification and regression application of compound toxicity data and compound activity data.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122485993","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}
The barrage is an important form for the audience to express their emotions and opinions. It runs through the entire video and feeds back audience's overall evaluation of the plot type, characters, and even actors of the videos. Mining such information from massive barrages not only has important academic value but also provides a reference for relevant business decisions to increase film traffic and revenue. We crawled the bullet screen information of 5 different types of recommended movies in the Bilibili bullet screen network in 2021 and performed statistical analysis on the data in a graphical visualization manner. The user's attention is analyzed through the word cloud map. The distribution of the number of bullet screens was used to reflect the changes in the number of viewers every week and every day, and the degree of attention during the film screening process was analyzed. Sentiment analysis is performed on the obtained bullet screen data based on artificial intelligence algorithms. First, the Word2vec model generated the word vector of the bullet screen text and input it into the machine learning model SVM and the deep learning model TextCNN for classification. The experimental results show that the deep learning model is higher than the traditional model in accuracy.
{"title":"Data Mining and Analysis of Video Barrage By AI Algorithm","authors":"Daoqing Gong, Xinyan Gan, Xiaonian Tang, Hua Li, Xiang Gao","doi":"10.1109/ECBIOS57802.2023.10218597","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218597","url":null,"abstract":"The barrage is an important form for the audience to express their emotions and opinions. It runs through the entire video and feeds back audience's overall evaluation of the plot type, characters, and even actors of the videos. Mining such information from massive barrages not only has important academic value but also provides a reference for relevant business decisions to increase film traffic and revenue. We crawled the bullet screen information of 5 different types of recommended movies in the Bilibili bullet screen network in 2021 and performed statistical analysis on the data in a graphical visualization manner. The user's attention is analyzed through the word cloud map. The distribution of the number of bullet screens was used to reflect the changes in the number of viewers every week and every day, and the degree of attention during the film screening process was analyzed. Sentiment analysis is performed on the obtained bullet screen data based on artificial intelligence algorithms. First, the Word2vec model generated the word vector of the bullet screen text and input it into the machine learning model SVM and the deep learning model TextCNN for classification. The experimental results show that the deep learning model is higher than the traditional model in accuracy.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124703018","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 : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218503
Anh Thu Pham Nguyen, Trung Tin Le, Ngoc Yen Bui Tran, Hoang Nhut Huynh, Anh Hao Huynh Vo, Trung Nghia Tran
Monitoring the level of blood glucose is required for diabetes to be managed. Monitoring one's glucose levels with finger prick blood is uncomfortable, unpleasant, and may cause infection. Regularly sticking one's fingers into sharp objects may result in scarring and calluses, reducing sensitivity and perception. Therefore, a blood glucose self-test that is not intrusive is very necessary. The optical blood glucose detection technique is promising and has opportunities for further improvement. This technology makes use of a variety of wavelengths, ranging from ultraviolet to infrared. The skin may be penetrated by low-energy radiation from light with a wavelength ranging from 450 to 2500 nanometers. Changes in light intensity, brought on by glucose's ability to absorb or scatter light, are used to measure blood glucose levels. Despite the extensive research on non-invasive methods, the commercial device is still under development. We summarize the results of experiments utilizing transmission modeling at 660 nm and 780 nm wavelengths. A measurement gadget has been designed to support the finger surveys conducted by volunteers. The VivaChek Ino is used to determine blood glucose levels, which are combined with other measurements to establish the findings of the measurements. The data from fifty different measurements were used to construct the regression lines. The correlation coefficient, R2, is close to 0.70. The findings of this research indicate that it would be possible to use an optical approach in conjunction with a transmission model. Additionally, it recommends mixing different near-infrared wavelength ranges to get superior outcomes.
{"title":"Investigation Transillumination Mode at 660 and 780 nm for Non-Invasive Blood Glucose Monitoring Device","authors":"Anh Thu Pham Nguyen, Trung Tin Le, Ngoc Yen Bui Tran, Hoang Nhut Huynh, Anh Hao Huynh Vo, Trung Nghia Tran","doi":"10.1109/ECBIOS57802.2023.10218503","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218503","url":null,"abstract":"Monitoring the level of blood glucose is required for diabetes to be managed. Monitoring one's glucose levels with finger prick blood is uncomfortable, unpleasant, and may cause infection. Regularly sticking one's fingers into sharp objects may result in scarring and calluses, reducing sensitivity and perception. Therefore, a blood glucose self-test that is not intrusive is very necessary. The optical blood glucose detection technique is promising and has opportunities for further improvement. This technology makes use of a variety of wavelengths, ranging from ultraviolet to infrared. The skin may be penetrated by low-energy radiation from light with a wavelength ranging from 450 to 2500 nanometers. Changes in light intensity, brought on by glucose's ability to absorb or scatter light, are used to measure blood glucose levels. Despite the extensive research on non-invasive methods, the commercial device is still under development. We summarize the results of experiments utilizing transmission modeling at 660 nm and 780 nm wavelengths. A measurement gadget has been designed to support the finger surveys conducted by volunteers. The VivaChek Ino is used to determine blood glucose levels, which are combined with other measurements to establish the findings of the measurements. The data from fifty different measurements were used to construct the regression lines. The correlation coefficient, R2, is close to 0.70. The findings of this research indicate that it would be possible to use an optical approach in conjunction with a transmission model. Additionally, it recommends mixing different near-infrared wavelength ranges to get superior outcomes.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130546628","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 : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218593
Sheng-Hsien Hsieh, Ming-Yi Lin, Ching-Han Chen
We present a high-accuracy 3D facial reconstruction system with the following features: real-time 3D facial reconstruction using exposure synchronization multi-camera, feature alignment to quantify facial differences, a software system based on a naked eye 3D display, and medical records for a 3D face database. The proposed system is novel and practical, and the algorithm and the hardware/software architecture improve the current non-quantitative communication status in medical aesthetics. The system achieves preoperative expectations, real-time recording and feedback during surgery, and postoperative tracking analysis, thus making doctor-patient communication more efficient. The facial data database records personal and quantitative beauty data and its changes, providing accurate medical and aesthetic treatment analysis for individuals. In addition, the collected data of different genders, ages, injection sites, and dosages contribute to the development of more accurate medical materials. With artificial intelligence and cloud architecture, we provide reliable data for medical aesthetics customers, helping them understand their medical aesthetic needs. Doctors also provide stable medical care quality to consumers through cloud data, and medical aesthetic consultants do not need to exaggerate medical effects excessively. They can inform customers of specific differences before and after surgery through precise data and provide visual communication and customer expansion to improve consultation conversion rates.
{"title":"3D Facial Reconstruction Applied to Medical Cosmetology","authors":"Sheng-Hsien Hsieh, Ming-Yi Lin, Ching-Han Chen","doi":"10.1109/ECBIOS57802.2023.10218593","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218593","url":null,"abstract":"We present a high-accuracy 3D facial reconstruction system with the following features: real-time 3D facial reconstruction using exposure synchronization multi-camera, feature alignment to quantify facial differences, a software system based on a naked eye 3D display, and medical records for a 3D face database. The proposed system is novel and practical, and the algorithm and the hardware/software architecture improve the current non-quantitative communication status in medical aesthetics. The system achieves preoperative expectations, real-time recording and feedback during surgery, and postoperative tracking analysis, thus making doctor-patient communication more efficient. The facial data database records personal and quantitative beauty data and its changes, providing accurate medical and aesthetic treatment analysis for individuals. In addition, the collected data of different genders, ages, injection sites, and dosages contribute to the development of more accurate medical materials. With artificial intelligence and cloud architecture, we provide reliable data for medical aesthetics customers, helping them understand their medical aesthetic needs. Doctors also provide stable medical care quality to consumers through cloud data, and medical aesthetic consultants do not need to exaggerate medical effects excessively. They can inform customers of specific differences before and after surgery through precise data and provide visual communication and customer expansion to improve consultation conversion rates.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126784914","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 : 2023-06-02DOI: 10.1109/ECBIOS57802.2023.10218677
Xicai Yue, J. Kiely, Keith Errey
Contactless electrodes have the ability of long- term wearable physiological recording to meet the massive data requirements in digital health. Active electrodes have been used to avoid noise induced by the high-impedance contactless electrodes for better data quality. However, the settling time of the active contactless electrodes is relatively long (e.g., several seconds), restricting the use of contactless electrodes in frequent power on-off operations to save power which is usually supplied by a battery. We develop a low-power active contactless electrode circuit based on the AC-coupled amplifier with a speed-up settling property. Simulation results demonstrated that the ECG baseline drifted during the settling period after power on was eliminated. The proposed electrode is suitable for power-saving operations in long-term wearable ECG applications.
{"title":"Speed Settling of AC-Coupled Amplifier for Active Contactless ECG Electrode","authors":"Xicai Yue, J. Kiely, Keith Errey","doi":"10.1109/ECBIOS57802.2023.10218677","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218677","url":null,"abstract":"Contactless electrodes have the ability of long- term wearable physiological recording to meet the massive data requirements in digital health. Active electrodes have been used to avoid noise induced by the high-impedance contactless electrodes for better data quality. However, the settling time of the active contactless electrodes is relatively long (e.g., several seconds), restricting the use of contactless electrodes in frequent power on-off operations to save power which is usually supplied by a battery. We develop a low-power active contactless electrode circuit based on the AC-coupled amplifier with a speed-up settling property. Simulation results demonstrated that the ECG baseline drifted during the settling period after power on was eliminated. The proposed electrode is suitable for power-saving operations in long-term wearable ECG applications.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852578","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：