Pub Date : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079698
Han Xiang Lim, Y. Z. Chong, Yin Qing Tan, V. Sundar, Y. Selva, S. Chan
Running is one of the low-cost exercises to improve general well-being but repetitive loading at lower extremities can lead to high occurrence of running injuries. Running shoe cushioning characteristic is postulated can enhance running performance and reduce the potential risk of running related injuries. The soft and hard cushioning footwear will affect the running gait especially after shoe aging. Several studies have investigated the link between running shoe cushioning and running biomechanics. However, there were generally inconsistent finding being reported. So, the purpose of this study is to perform a biomechanical analysis if running shoe cushioning properties can have positive effect on distance running. 10 amateur runners participated in this study and completed 80 km running distance within timeline. They were divided into two groups who run with soft cushioning and hard cushioning shoes respectively. The lower extremities joint flexion range of motion and vertical ground reaction force were accessed at baseline, after 40 km and 80 km of running. The result showed that hardness of cushioning was increased if the running distance increased. Greater range of motion was observed for both hard and soft cushioning condition when the running distance was accumulated to 80 km. Hard cushioning running had significantly higher range of motion and ground reaction force if compared to soft cushioning running. In conclusion soft cushioning running produces less impact load may result in better protection on running injury.
{"title":"Effect Of Shoe Cushioning Hardness to Running Biomechanics","authors":"Han Xiang Lim, Y. Z. Chong, Yin Qing Tan, V. Sundar, Y. Selva, S. Chan","doi":"10.1109/IECBES54088.2022.10079698","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079698","url":null,"abstract":"Running is one of the low-cost exercises to improve general well-being but repetitive loading at lower extremities can lead to high occurrence of running injuries. Running shoe cushioning characteristic is postulated can enhance running performance and reduce the potential risk of running related injuries. The soft and hard cushioning footwear will affect the running gait especially after shoe aging. Several studies have investigated the link between running shoe cushioning and running biomechanics. However, there were generally inconsistent finding being reported. So, the purpose of this study is to perform a biomechanical analysis if running shoe cushioning properties can have positive effect on distance running. 10 amateur runners participated in this study and completed 80 km running distance within timeline. They were divided into two groups who run with soft cushioning and hard cushioning shoes respectively. The lower extremities joint flexion range of motion and vertical ground reaction force were accessed at baseline, after 40 km and 80 km of running. The result showed that hardness of cushioning was increased if the running distance increased. Greater range of motion was observed for both hard and soft cushioning condition when the running distance was accumulated to 80 km. Hard cushioning running had significantly higher range of motion and ground reaction force if compared to soft cushioning running. In conclusion soft cushioning running produces less impact load may result in better protection on running injury.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115462737","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079697
Tatiana N. Gribinichenko, M. Uspenskaya, Petr P. Snetkov, R. Olekhnovich
Currently, the perforations of the nasal septum and tympanic membrane is a relevant problem in modern ENT (Ear, Nose, and Throat) surgery. In this regard, the development of universal materials is an extremely urgent and topical task for bioengineering and biomedicine. Hyaluronic acid, having a unique set of physicochemical, chemical, rheological, and biological properties, is an optimal biopolymer for the creation of such materials. Films based on hyaluronic acid assuredly have the necessary levels of biocompatibility and biodegradability, as well as promote wound healing process. In this research, films based on sodium hyaluronate with a molecular weight equal to 1.29 MDa and chitosan with a molecular weight equal to 0.5 MDa and 0.9 MDa for the potential treatment of nasal septum/tympanic membrane perforations were obtained and characterized. Films were fabricated from polymer solutions by layer-by-layer technique with the subsequent cross-linking and removal of the soluble phase. The optimal component composition resulting in materials with desired properties was determined. It was shown that the obtained polymer films have high porosity, roughness, and high adhesive ability. Further research related to the technology of such polymeric materials will promote the development of modern regenerative materials for nasal septum / tympanic membrane pathologies treatment.
{"title":"Bi-Layered Films based on Sodium Hyaluronate and Chitosan as Materials for ENT Surgery","authors":"Tatiana N. Gribinichenko, M. Uspenskaya, Petr P. Snetkov, R. Olekhnovich","doi":"10.1109/IECBES54088.2022.10079697","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079697","url":null,"abstract":"Currently, the perforations of the nasal septum and tympanic membrane is a relevant problem in modern ENT (Ear, Nose, and Throat) surgery. In this regard, the development of universal materials is an extremely urgent and topical task for bioengineering and biomedicine. Hyaluronic acid, having a unique set of physicochemical, chemical, rheological, and biological properties, is an optimal biopolymer for the creation of such materials. Films based on hyaluronic acid assuredly have the necessary levels of biocompatibility and biodegradability, as well as promote wound healing process. In this research, films based on sodium hyaluronate with a molecular weight equal to 1.29 MDa and chitosan with a molecular weight equal to 0.5 MDa and 0.9 MDa for the potential treatment of nasal septum/tympanic membrane perforations were obtained and characterized. Films were fabricated from polymer solutions by layer-by-layer technique with the subsequent cross-linking and removal of the soluble phase. The optimal component composition resulting in materials with desired properties was determined. It was shown that the obtained polymer films have high porosity, roughness, and high adhesive ability. Further research related to the technology of such polymeric materials will promote the development of modern regenerative materials for nasal septum / tympanic membrane pathologies treatment.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123706106","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079534
S. Jantan, Siti Anom Ahmad, A. C. Soh, A. J. Ishak, Raja Nurzatul Efah Raja Adnan
Electroencephalographic (EEG) technology's non-invasive, inexpensive, and potable qualities have recently increased interest in EEG-based driving fatigue detection. EEG signals have been one of the most accurate and reliable markers of driver fatigue. Despite this, extracting valuable features from cluttered EEG signals still difficult to detect driving fatigue. This study aims to create a novel real-time methodology for detecting driving fatigue based on EEG signals. The study utilizes the Discrete Wavelet Transform (DWT) to obtain different EEG bands and compute power spectrum density (PSD) and other statistical features over each DWT band for the online detection of mental fatigue. Deep learning, particularly convolutional neural networks (CNN), has demonstrated impressive results in recent years as a method to extract features from EEG signals among various analysis techniques successfully. Although automatic feature extraction and accurate classification are advantages of deep learning, designing the network structure can be challenging and requires a vast amount of prior knowledge. Therefore, we used these features as input to CNN instead of using raw EEG data directly. Classification results of multiple machine learning models such as Support Vector Machine (SVM), k-nearest neighbor (kNN), Linear discriminant analysis (LDA), Decision Tree (DT), and Naive Bayes (NB) classifiers are also explored to obtain an optimum solution of the driver's fatigue evaluation. Two driving fatigue EEG datasets were used as testbeds to denote the effectiveness of five conventional classifiers and CNN. The proposed method reached more than 99% classification accuracy using a kNN and CNN in both datasets. The outcomes confirmed the efficacy of the suggested approach.
{"title":"A Multi-Model Analysis for Driving Fatigue Detection using EEG Signals","authors":"S. Jantan, Siti Anom Ahmad, A. C. Soh, A. J. Ishak, Raja Nurzatul Efah Raja Adnan","doi":"10.1109/IECBES54088.2022.10079534","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079534","url":null,"abstract":"Electroencephalographic (EEG) technology's non-invasive, inexpensive, and potable qualities have recently increased interest in EEG-based driving fatigue detection. EEG signals have been one of the most accurate and reliable markers of driver fatigue. Despite this, extracting valuable features from cluttered EEG signals still difficult to detect driving fatigue. This study aims to create a novel real-time methodology for detecting driving fatigue based on EEG signals. The study utilizes the Discrete Wavelet Transform (DWT) to obtain different EEG bands and compute power spectrum density (PSD) and other statistical features over each DWT band for the online detection of mental fatigue. Deep learning, particularly convolutional neural networks (CNN), has demonstrated impressive results in recent years as a method to extract features from EEG signals among various analysis techniques successfully. Although automatic feature extraction and accurate classification are advantages of deep learning, designing the network structure can be challenging and requires a vast amount of prior knowledge. Therefore, we used these features as input to CNN instead of using raw EEG data directly. Classification results of multiple machine learning models such as Support Vector Machine (SVM), k-nearest neighbor (kNN), Linear discriminant analysis (LDA), Decision Tree (DT), and Naive Bayes (NB) classifiers are also explored to obtain an optimum solution of the driver's fatigue evaluation. Two driving fatigue EEG datasets were used as testbeds to denote the effectiveness of five conventional classifiers and CNN. The proposed method reached more than 99% classification accuracy using a kNN and CNN in both datasets. The outcomes confirmed the efficacy of the suggested approach.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121923076","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079640
Choon-Hian Goh, Chee Hong Koh, Y. Z. Chong, Wei Yin Lim
Gait analysis is essential for diagnosis, assessment, monitoring purpose, and prediction of gait disorder. However, the objective analysis method is less feasible in hospital environments for treatment purposes due to limited coverage of sources. Thus, this study aims to develop a classification algorithm that can effectively classify subjects with relatively simplified temporal spatial gait data. This study employed several datasets acquired from PhysioNet containing subjects’ gait data of three classes. The training dataset contains a total of 48,318 instances of three target classes (young healthy adults, old healthy adults, and Parkinson’s disease patients). Two classification algorithms were developed: Support Vector Machine (SVM) classification algorithm and Artificial Neural Network (ANN). Preprocessing was performed to the original dataset which includes data cleaning, data normalization and new features generation. Next, fine-tuning on the manipulating hyperparameters was performed, and 10-fold cross validation was applied. The optimum configuration of SVM model can generate an accuracy of 93.01% and F1 score of 0.92 with 43 minutes of computational time. On the contrary, the optimum configuration ANN classifier generates an accuracy of 90.56% and F1 score of 0.89 with 112 minutes computational time. Conclusion: In conclusion, comparing both of the proposed classification algorithms, the SVM classifier is more effectively than ANN classifier as overall for the gait dataset used in this study. In addition, after compared with other state-of-the-arts of gait classification algorithms, our proposed classification algorithm produced comparable results with other state-of-arts using a smaller dataset with fewer training features. Clinical Relevance– This establishes the potential of apply machine learning algorithm on basic gait data obtained from the objective gait analysis method in classification of healthy adults, older adults, and Parkinson’s patient.
{"title":"Gait Classification of Parkinson’s Disease with Supervised Machine Learning Approach","authors":"Choon-Hian Goh, Chee Hong Koh, Y. Z. Chong, Wei Yin Lim","doi":"10.1109/IECBES54088.2022.10079640","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079640","url":null,"abstract":"Gait analysis is essential for diagnosis, assessment, monitoring purpose, and prediction of gait disorder. However, the objective analysis method is less feasible in hospital environments for treatment purposes due to limited coverage of sources. Thus, this study aims to develop a classification algorithm that can effectively classify subjects with relatively simplified temporal spatial gait data. This study employed several datasets acquired from PhysioNet containing subjects’ gait data of three classes. The training dataset contains a total of 48,318 instances of three target classes (young healthy adults, old healthy adults, and Parkinson’s disease patients). Two classification algorithms were developed: Support Vector Machine (SVM) classification algorithm and Artificial Neural Network (ANN). Preprocessing was performed to the original dataset which includes data cleaning, data normalization and new features generation. Next, fine-tuning on the manipulating hyperparameters was performed, and 10-fold cross validation was applied. The optimum configuration of SVM model can generate an accuracy of 93.01% and F1 score of 0.92 with 43 minutes of computational time. On the contrary, the optimum configuration ANN classifier generates an accuracy of 90.56% and F1 score of 0.89 with 112 minutes computational time. Conclusion: In conclusion, comparing both of the proposed classification algorithms, the SVM classifier is more effectively than ANN classifier as overall for the gait dataset used in this study. In addition, after compared with other state-of-the-arts of gait classification algorithms, our proposed classification algorithm produced comparable results with other state-of-arts using a smaller dataset with fewer training features. Clinical Relevance– This establishes the potential of apply machine learning algorithm on basic gait data obtained from the objective gait analysis method in classification of healthy adults, older adults, and Parkinson’s patient.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130449114","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079362
S. Marcadent, J. Hêches, J. Favre, D. Desseauve, J. Thiran
In this pilot study, we present a new engineering approach to reconstruct a patient-specific model of the fetal head near term. Indeed, 3D visualization of the fetus prominent skull could help the obstetricians in decision-making to overcome dystocia, a delivery complication which results in labour obstruction. The full reconstruction pipeline is based on the recording of a small set of tracked 2D ultrasound images around the transthalamic brain plane. The use of 2D ultrasound images tracked in 3D space would allow to superimpose the fetal head model to other reconstructed organs. The fetal head is large at late pregnancy stages which causes occlusions in the ultrasound images. Moreover, fetal motion may affect the consistency of ultrasound images, in particular if many frames are needed. Therefore, we propose to extrapolate the full fetal head surface from 10 focused frames only. The reconstruction performance was evaluated in simulation based on a MRI dataset of 7 patients at 34-36 weeks of pregnancy; our best method achieves 1.6 mm of average reconstruction error.
{"title":"Reconstruction of Fetal Head Surface from Few 2D Ultrasound Images Tracked in 3D Space","authors":"S. Marcadent, J. Hêches, J. Favre, D. Desseauve, J. Thiran","doi":"10.1109/IECBES54088.2022.10079362","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079362","url":null,"abstract":"In this pilot study, we present a new engineering approach to reconstruct a patient-specific model of the fetal head near term. Indeed, 3D visualization of the fetus prominent skull could help the obstetricians in decision-making to overcome dystocia, a delivery complication which results in labour obstruction. The full reconstruction pipeline is based on the recording of a small set of tracked 2D ultrasound images around the transthalamic brain plane. The use of 2D ultrasound images tracked in 3D space would allow to superimpose the fetal head model to other reconstructed organs. The fetal head is large at late pregnancy stages which causes occlusions in the ultrasound images. Moreover, fetal motion may affect the consistency of ultrasound images, in particular if many frames are needed. Therefore, we propose to extrapolate the full fetal head surface from 10 focused frames only. The reconstruction performance was evaluated in simulation based on a MRI dataset of 7 patients at 34-36 weeks of pregnancy; our best method achieves 1.6 mm of average reconstruction error.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132980735","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079536
Himani Jha, Rina Weaver, Darshan Mundewadi, B. Bellannagari, S. Zaidi
Non-thermal dielectric barrier discharge plasma finds its application in medicine, where it is used to inactivate bacteria on wound surfaces. In this paper, a dielectric barrier discharge plasma sheet generator was designed to replace the traditional plasma jet. The sheet generator is able to scan large surfaces as compared to a plasma jet. High purity helium was used as the working gas (~30-60 slpm), and the plasma was generated using an AC power supply (5-10kv, 10-30 kHz). The input plasma power was measured to be around a few Watts (~10-25W) depending on the operating conditions of the torch. An automated 2D traversing system was designed and used to scan the plasma sheet and measure plasma gas temperatures along the plasma sheet. Experimental results show that the temperature varies across the plasma sheet for up to 16 percent, and temperatures are more uniform near the exit of the plasma torch. The effectiveness of the plasma torch was determined by running it over agar plates in which E. coli K-12 bacteria was grown. An apparent reduction in the bacterial colonies (up to 44%) was observed as the plasma sheet was scanned along the petri dish for five minutes. The plasma sheet traverses a larger area, which is beneficial because it reduces the time taken by the plasma jet to cover the same area on the petri dish.
{"title":"Surface Bacteria Inactivation by a DBD Plasma Sheet Generator","authors":"Himani Jha, Rina Weaver, Darshan Mundewadi, B. Bellannagari, S. Zaidi","doi":"10.1109/IECBES54088.2022.10079536","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079536","url":null,"abstract":"Non-thermal dielectric barrier discharge plasma finds its application in medicine, where it is used to inactivate bacteria on wound surfaces. In this paper, a dielectric barrier discharge plasma sheet generator was designed to replace the traditional plasma jet. The sheet generator is able to scan large surfaces as compared to a plasma jet. High purity helium was used as the working gas (~30-60 slpm), and the plasma was generated using an AC power supply (5-10kv, 10-30 kHz). The input plasma power was measured to be around a few Watts (~10-25W) depending on the operating conditions of the torch. An automated 2D traversing system was designed and used to scan the plasma sheet and measure plasma gas temperatures along the plasma sheet. Experimental results show that the temperature varies across the plasma sheet for up to 16 percent, and temperatures are more uniform near the exit of the plasma torch. The effectiveness of the plasma torch was determined by running it over agar plates in which E. coli K-12 bacteria was grown. An apparent reduction in the bacterial colonies (up to 44%) was observed as the plasma sheet was scanned along the petri dish for five minutes. The plasma sheet traverses a larger area, which is beneficial because it reduces the time taken by the plasma jet to cover the same area on the petri dish.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128707165","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079451
Nurul Izzati Darul Zaman, Y. Hau, R. Al-ashwal, M. Leong
Monitoring of vital sign parameters is crucial in identifying clinical deterioration. Therefore, these parameters must be measured regularly to monitor acute and chronic diseases. However, most of the existing vital sign monitors are designed mainly for hospital clinical settings. These devices are generally bulky, with complex user interfaces and no integration of mobile applications, as well as auto fever-type classification algorithms for potential disease screening. As a result, this paper presents a 2-in-1 home-based vital sign monitor based on an Arduino Nano microcontroller, a DS18B20 temperature sensor to measure body temperature from the fingertip, and an MPX5050DP pressure sensor to acquire blood pressure based on the oscillometric method. An Android mobile application is also developed and integrated with the device through wireless Bluetooth to display vital sign measurement results, analyze fever patterns and symptoms for early detection of potential diseases, and send an alert notification message if abnormalities are detected. Google Firebase Authentication is also deployed for user authentication. The results show that the system provides an accurate vital sign measurement of 98.75% and 99.94% for blood pressure and body temperature, respectively. The mobile application was also successfully deployed with a fever classification algorithm as a clinical decision support system.Clinical Relevance— The vital signs and fever classification result can be used as part of a clinical decision support system by clinicians for infectious disease screening.
{"title":"A 2-in-1 Vital Sign Monitor with Smart Fever Type Classification for Home-Care Services","authors":"Nurul Izzati Darul Zaman, Y. Hau, R. Al-ashwal, M. Leong","doi":"10.1109/IECBES54088.2022.10079451","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079451","url":null,"abstract":"Monitoring of vital sign parameters is crucial in identifying clinical deterioration. Therefore, these parameters must be measured regularly to monitor acute and chronic diseases. However, most of the existing vital sign monitors are designed mainly for hospital clinical settings. These devices are generally bulky, with complex user interfaces and no integration of mobile applications, as well as auto fever-type classification algorithms for potential disease screening. As a result, this paper presents a 2-in-1 home-based vital sign monitor based on an Arduino Nano microcontroller, a DS18B20 temperature sensor to measure body temperature from the fingertip, and an MPX5050DP pressure sensor to acquire blood pressure based on the oscillometric method. An Android mobile application is also developed and integrated with the device through wireless Bluetooth to display vital sign measurement results, analyze fever patterns and symptoms for early detection of potential diseases, and send an alert notification message if abnormalities are detected. Google Firebase Authentication is also deployed for user authentication. The results show that the system provides an accurate vital sign measurement of 98.75% and 99.94% for blood pressure and body temperature, respectively. The mobile application was also successfully deployed with a fever classification algorithm as a clinical decision support system.Clinical Relevance— The vital signs and fever classification result can be used as part of a clinical decision support system by clinicians for infectious disease screening.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125738896","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079589
Y. Sano, A. Obata, Kazuyuki Yanase, Futoshi Yamamoto, Shingo Omata, M. Ichikawa, T. Tagawa
This study examined the effects of three exercise support apps (walking (WA)/fast walking (FW)/indoor exercise (IE) apps) and a communication (CO) support app on mental stress with the aim of realizing corporate health management. Six groups were set up with a combination of the three exercise support apps and with and without the CO app. Thirty employees in each group continuously used their assigned apps for 10 weeks. In the group using the WA app, frustration significantly decreased (-22%). In the group using the IE app, total mental stress (-14%), frustration (-19%), fatigue (-21%), anxiety (-23%), and depression (-22%) decreased. In the group using the WA and CO apps together, fatigue decreased (-20%). In the group using the FW and CO apps, total mental stress (15%), fatigue (-23%), and anxiety (-34%) decreased. These results indicate that negative emotions (frustration, fatigue, anxiety, and depression) can be alleviated by our apps, but positive emotions (liveliness) and physical sensations (physical complaints) are not affected. A two-way analysis of variance (ANOVA) was applied to these mental stress reduction effects. There were no main effects for all indicators, but simple main effects were calculated for those that had interactions: fatigue under the WA app condition $(mathrm{p}lt 0.05)$ and anxiety under the FW app condition $(mathrm{p}lt 0.01)$ decreased more when the CO app was used. However, frustration decreased more under the IE app condition when the CO app was not used $(mathrm{p}lt 0.05)$. These results indicate that the combination of an exercise support app and a communication support app has different effects on mental stress reduction. In the future, the proposed apps are expected to help prevent mental illness and realize corporate health management.
{"title":"Verification of Mental Stress Reduction Effects of Exercise Support Apps and Communication Support App for Corporate Health Management","authors":"Y. Sano, A. Obata, Kazuyuki Yanase, Futoshi Yamamoto, Shingo Omata, M. Ichikawa, T. Tagawa","doi":"10.1109/IECBES54088.2022.10079589","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079589","url":null,"abstract":"This study examined the effects of three exercise support apps (walking (WA)/fast walking (FW)/indoor exercise (IE) apps) and a communication (CO) support app on mental stress with the aim of realizing corporate health management. Six groups were set up with a combination of the three exercise support apps and with and without the CO app. Thirty employees in each group continuously used their assigned apps for 10 weeks. In the group using the WA app, frustration significantly decreased (-22%). In the group using the IE app, total mental stress (-14%), frustration (-19%), fatigue (-21%), anxiety (-23%), and depression (-22%) decreased. In the group using the WA and CO apps together, fatigue decreased (-20%). In the group using the FW and CO apps, total mental stress (15%), fatigue (-23%), and anxiety (-34%) decreased. These results indicate that negative emotions (frustration, fatigue, anxiety, and depression) can be alleviated by our apps, but positive emotions (liveliness) and physical sensations (physical complaints) are not affected. A two-way analysis of variance (ANOVA) was applied to these mental stress reduction effects. There were no main effects for all indicators, but simple main effects were calculated for those that had interactions: fatigue under the WA app condition $(mathrm{p}lt 0.05)$ and anxiety under the FW app condition $(mathrm{p}lt 0.01)$ decreased more when the CO app was used. However, frustration decreased more under the IE app condition when the CO app was not used $(mathrm{p}lt 0.05)$. These results indicate that the combination of an exercise support app and a communication support app has different effects on mental stress reduction. In the future, the proposed apps are expected to help prevent mental illness and realize corporate health management.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125316276","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079623
Asaad Anaam, M. A. Al-antari, A. Gofuku
The Indirect Immunofluorescence (IIF) on Human Epithelial (HEp-2) cells is considered the hallmark protocol of the Anti-Nuclear Antibodies (ANAs) testing for diagnosing autoimmune diseases. The usual practice of visual slide inspection under the fluorescence microscope suffers from low throughput and high labor-subjectivity. Therefore, developing an efficient framework for automatic HEp-2 cell image classification is necessary for overcoming such manual protocol shortcomings. In this paper, a novel HEp-2 cell image classification framework is proposed based on ensemble deep learning with generative adversarial networks (GANs). An efficient Info-WGANGP approach is adopted for data augmentation by generating new HEp-2 cell images and enlarging the size of the training set. Meanwhile, an ensemble deep learning strategy is implemented to build a backbone network obtaining a potent combination of the deep features using three well-known deep convolutional networks, i.e., DCRNet, DSRNet, and HEpNet. The evaluation experiments on the publicly available I3A dataset demonstrate promising classification results in terms of average classification accuracy (ACA) with 98.82% and mean class accuracy (MCA) with 98.91% outperforming the latest deep learning approaches. The proposed classification framework seems to be applicable for supporting human experts in making accurate and rapid diagnosis decisions of the HEp-2 cell patterns.
{"title":"A Hybrid Ensemble Learning with Generative Adversarial Networks for HEp-2 Cell Image Classification","authors":"Asaad Anaam, M. A. Al-antari, A. Gofuku","doi":"10.1109/IECBES54088.2022.10079623","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079623","url":null,"abstract":"The Indirect Immunofluorescence (IIF) on Human Epithelial (HEp-2) cells is considered the hallmark protocol of the Anti-Nuclear Antibodies (ANAs) testing for diagnosing autoimmune diseases. The usual practice of visual slide inspection under the fluorescence microscope suffers from low throughput and high labor-subjectivity. Therefore, developing an efficient framework for automatic HEp-2 cell image classification is necessary for overcoming such manual protocol shortcomings. In this paper, a novel HEp-2 cell image classification framework is proposed based on ensemble deep learning with generative adversarial networks (GANs). An efficient Info-WGANGP approach is adopted for data augmentation by generating new HEp-2 cell images and enlarging the size of the training set. Meanwhile, an ensemble deep learning strategy is implemented to build a backbone network obtaining a potent combination of the deep features using three well-known deep convolutional networks, i.e., DCRNet, DSRNet, and HEpNet. The evaluation experiments on the publicly available I3A dataset demonstrate promising classification results in terms of average classification accuracy (ACA) with 98.82% and mean class accuracy (MCA) with 98.91% outperforming the latest deep learning approaches. The proposed classification framework seems to be applicable for supporting human experts in making accurate and rapid diagnosis decisions of the HEp-2 cell patterns.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127907689","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079504
Eric Yao, Rory Liao, M. Shalaginov, TingyingHelen Zeng
The global outbreak of COVID-19 has resulted in a surge in patients in hospitals and intensive care units. This unprecedented demand for medical resources has severely burdened healthcare systems. Chest X-Ray (CXR) images can be used by hospitals and small clinics to predict COVID-19 severity to maximize efficiency and allot medical resources to patients with severe COVID-19. This research compares the accuracies of four convolutional neural network models in predicting COVID-19 severity using chest X-Rays images. The CNN models include VGG-16, ResNet 50, Xception, and a custom CNN model. Through the comparison, VGG-16 had the highest COVID-19 severity prediction accuracy of all four models, with 95.56% testing accuracy and 88.33% validation accuracy. Using a machine learning method, disease progression can be tracked more accurately and help prioritize patients to ensure effective and timely treatment.
{"title":"Comparison of Different Models in Predicting COVID-19 Severity Based on Chest X-Ray Scans","authors":"Eric Yao, Rory Liao, M. Shalaginov, TingyingHelen Zeng","doi":"10.1109/IECBES54088.2022.10079504","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079504","url":null,"abstract":"The global outbreak of COVID-19 has resulted in a surge in patients in hospitals and intensive care units. This unprecedented demand for medical resources has severely burdened healthcare systems. Chest X-Ray (CXR) images can be used by hospitals and small clinics to predict COVID-19 severity to maximize efficiency and allot medical resources to patients with severe COVID-19. This research compares the accuracies of four convolutional neural network models in predicting COVID-19 severity using chest X-Rays images. The CNN models include VGG-16, ResNet 50, Xception, and a custom CNN model. Through the comparison, VGG-16 had the highest COVID-19 severity prediction accuracy of all four models, with 95.56% testing accuracy and 88.33% validation accuracy. Using a machine learning method, disease progression can be tracked more accurately and help prioritize patients to ensure effective and timely treatment.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128018946","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：