The purpose of this study is to address the issue of a shortage of caregivers for the elderly in an aging society. Elderly individuals living alone at home may experience various sudden health issues such as falls and emergencies. However, healthcare professionals may not have access to the individuals at that moment. Having access to real-time data can assist medical professionals in making more informed decisions about the patient's conditions. Thus, using FMCW millimeter-wave radar, we track the vital signs of individuals through a non-contact method in point clouds. Additionally, RGB cameras and the human pose estimation tool, OpenPose, are used to monitor and analyze motions and activities in public spaces, detecting special events such as falls and fainting and issuing alerts for immediate rescue to minimize further harm. This approach facilitates the exchange of information between medical professionals and patients, thereby reducing the likelihood of unfortunate incidents and improving patient outcomes.
{"title":"Integrating FMCW Radar and RGBD Sensor for Vital Sign Detection","authors":"Sheng-Hsien Hsieh, Yuh-Jiuan Tsay, Yu-Wei Chen, Ya-Yun Huang, Yu-Xuan Yu","doi":"10.1109/ECBIOS57802.2023.10218461","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218461","url":null,"abstract":"The purpose of this study is to address the issue of a shortage of caregivers for the elderly in an aging society. Elderly individuals living alone at home may experience various sudden health issues such as falls and emergencies. However, healthcare professionals may not have access to the individuals at that moment. Having access to real-time data can assist medical professionals in making more informed decisions about the patient's conditions. Thus, using FMCW millimeter-wave radar, we track the vital signs of individuals through a non-contact method in point clouds. Additionally, RGB cameras and the human pose estimation tool, OpenPose, are used to monitor and analyze motions and activities in public spaces, detecting special events such as falls and fainting and issuing alerts for immediate rescue to minimize further harm. This approach facilitates the exchange of information between medical professionals and patients, thereby reducing the likelihood of unfortunate incidents and improving patient outcomes.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"470 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":"133406614","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/ECBIOS57802.2023.10218472
W. Heng, N. A. Abdul-Kadir
Deep learning algorithms have been widely used for various healthcare research because it helps eliminate the need for manual feature extraction which requires specialist expertise and is time-consuming. However, deep learning models have low interpretability in their classification results and hence low trust and practical usage in clinical settings. To overcome this reliability issue, explainable machine learning (XAI) can be used to understand the effect of the different networks and the extracted features on the classification results. In this study, multiple convolutional neural networks were trained and tested on hairy scalp images for the detection of hair diseases. In addition to standard performance metrics including accuracy, sensitivity, and specificity, we further investigated the models' interpretability using three XAI techniques including Local Interpretable Model-Agnostic Explanations, Gradient-weighted Class Activation Mapping, and occlusion sensitivity. The result of using XAI techniques revealed that the model's high classification accuracy did not necessarily coincide with its applicability or practicality. The application of XAI techniques in this study provided valuable insights into the contributions made by different groups of pixels to the model's decision-making process. This method helped identify potential model biases, which could then be utilized to facilitate informed adjustments for the improvement of the model's robustness.
{"title":"Deep Learning and Explainable Machine Learning on Hair Disease Detection","authors":"W. Heng, N. A. Abdul-Kadir","doi":"10.1109/ECBIOS57802.2023.10218472","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218472","url":null,"abstract":"Deep learning algorithms have been widely used for various healthcare research because it helps eliminate the need for manual feature extraction which requires specialist expertise and is time-consuming. However, deep learning models have low interpretability in their classification results and hence low trust and practical usage in clinical settings. To overcome this reliability issue, explainable machine learning (XAI) can be used to understand the effect of the different networks and the extracted features on the classification results. In this study, multiple convolutional neural networks were trained and tested on hairy scalp images for the detection of hair diseases. In addition to standard performance metrics including accuracy, sensitivity, and specificity, we further investigated the models' interpretability using three XAI techniques including Local Interpretable Model-Agnostic Explanations, Gradient-weighted Class Activation Mapping, and occlusion sensitivity. The result of using XAI techniques revealed that the model's high classification accuracy did not necessarily coincide with its applicability or practicality. The application of XAI techniques in this study provided valuable insights into the contributions made by different groups of pixels to the model's decision-making process. This method helped identify potential model biases, which could then be utilized to facilitate informed adjustments for the improvement of the model's robustness.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"43 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":"115663715","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/ECBIOS57802.2023.10218590
Chun-Cheng Peng, Bing-Rong Lee
Medical image analysis is crucial in healthcare research. The convolutional neural network (CNN) has great potential in improving the precision and speed of medical diagnosis. In medical diagnostics, CNNs have displayed promising results, indicating their capability to enhance the accuracy and efficiency of the diagnostic process, accurately classifying complex medical images remains challenging. Colorectal cancer, a significant cause of global mortality, emphasizes the need for early detection and diagnosis to ensure successful treatment. We develop a new method combining transfer learning and a ResNet50 CNN model with the Adam optimizer to increase the accuracy in the classification of the histopathology images of colorectal cancer. The experimental results demonstrated outstanding performance with an accuracy of 99.99% in training and an accuracy of 99.77% in validation which were excellent performance on widely recognized evaluation metrics. In conclusion, the proposed method surpasses other related studies using CNN models for histopathology image classification. It provides a practical solution to further improve the classification performance of colorectal cancer histopathology images. The study result shows the efficacy of transfer learning in the analysis of medical images. Moreover, the proposed approach outperforms existing methods in medical image analysis, underscoring its potential to empower medical professionals in enhancing diagnostic capabilities and making more informed clinical decisions for patients.
{"title":"Enhancing Colorectal Cancer Histological Image Classification Using Transfer Learning and ResNet50 CNN Model","authors":"Chun-Cheng Peng, Bing-Rong Lee","doi":"10.1109/ECBIOS57802.2023.10218590","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218590","url":null,"abstract":"Medical image analysis is crucial in healthcare research. The convolutional neural network (CNN) has great potential in improving the precision and speed of medical diagnosis. In medical diagnostics, CNNs have displayed promising results, indicating their capability to enhance the accuracy and efficiency of the diagnostic process, accurately classifying complex medical images remains challenging. Colorectal cancer, a significant cause of global mortality, emphasizes the need for early detection and diagnosis to ensure successful treatment. We develop a new method combining transfer learning and a ResNet50 CNN model with the Adam optimizer to increase the accuracy in the classification of the histopathology images of colorectal cancer. The experimental results demonstrated outstanding performance with an accuracy of 99.99% in training and an accuracy of 99.77% in validation which were excellent performance on widely recognized evaluation metrics. In conclusion, the proposed method surpasses other related studies using CNN models for histopathology image classification. It provides a practical solution to further improve the classification performance of colorectal cancer histopathology images. The study result shows the efficacy of transfer learning in the analysis of medical images. Moreover, the proposed approach outperforms existing methods in medical image analysis, underscoring its potential to empower medical professionals in enhancing diagnostic capabilities and making more informed clinical decisions for patients.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"68 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":"129450332","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/ECBIOS57802.2023.10218557
Dehlela Shabir, S. Kharbech, Jhasketan Padhan, Elias Yaacoub, A. Mohammed, Zhigang Deng, A. Al-Ansari, P. Tsiamyrtzis, N. Navkar
Laparoscopic simulators have emerged as effective tools for surgical training. The virtual environment is used in the simulator for the training of procedure-specific surgical skills. These simulators can be enhanced if an expert can provide guidance on every surgical step of the procedure, as well as provide feedback as each step is performed by the trainee. In pursuit of this objective, this study introduces a telementoring system designed to be seamlessly integrated with surgical simulators, thereby enabling remote training. The system incorporates guidance from an expert located remotely, utilizing audio-visual cues as a means of instruction. The visual cues consist of the virtual laparoscopic instruments, which is remote-controlled by the expert and superimposed onto the operative field displayed on the simulator's visualization screen. The system was evaluated for its technical performance, and a user study was conducted. The technical evaluation showed low latency to enable real-time communication, whereas the user study demonstrated effective transfer of surgical skills.
{"title":"Telementoring System Assessment Integrated with Laparoscopic Surgical Simulators","authors":"Dehlela Shabir, S. Kharbech, Jhasketan Padhan, Elias Yaacoub, A. Mohammed, Zhigang Deng, A. Al-Ansari, P. Tsiamyrtzis, N. Navkar","doi":"10.1109/ECBIOS57802.2023.10218557","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218557","url":null,"abstract":"Laparoscopic simulators have emerged as effective tools for surgical training. The virtual environment is used in the simulator for the training of procedure-specific surgical skills. These simulators can be enhanced if an expert can provide guidance on every surgical step of the procedure, as well as provide feedback as each step is performed by the trainee. In pursuit of this objective, this study introduces a telementoring system designed to be seamlessly integrated with surgical simulators, thereby enabling remote training. The system incorporates guidance from an expert located remotely, utilizing audio-visual cues as a means of instruction. The visual cues consist of the virtual laparoscopic instruments, which is remote-controlled by the expert and superimposed onto the operative field displayed on the simulator's visualization screen. The system was evaluated for its technical performance, and a user study was conducted. The technical evaluation showed low latency to enable real-time communication, whereas the user study demonstrated effective transfer of surgical skills.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"48 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":"122258217","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/ECBIOS57802.2023.10218541
Michelle J. Lin
The emergence of antimicrobial resistance genes in multidrug-resistant gram-negative (MDRGN) bacteria leads to an immense increase in mortality rates and poses a major threat to global health. Current treatment methods and even drugs of last resort (DoLRs) have failed to successfully treat these infections, warranting the need for a new and immediate solution. This study focuses on the synthesis and investigation of an optimal dispersal agent for co-treatment. Previous screening of the genome of Acinetobacter baumannii, a highly virulent nosocomial gram-negative pathogen of ESKAPE, identified the hypothetical gene segment Pase 1 with potential characteristics of bacterial dispersion. Through treatment of various multidrug-resistant gram-negative bacterial biofilms and ESKAPE pathogens, the results indicated that AB-Pase 1 exhibited optimal characteristics as a co-treatment dispersal agent, with higher dispersion percentages and controlled dispersal rates in comparison to E. coli-Pase 1. Therefore, with the expansion of AB-Pase 1 in co-treatment therapy, there is an immense potential for successfully combating multi-resistant bacteria, a crucial breakthrough in the medical field.
{"title":"Combating Multidrug-Resistant Gram-Negative Bacteria Using Biofilm Protein Pase 1 as Novel Dispersal Agent for Co-Treatment Therapy","authors":"Michelle J. Lin","doi":"10.1109/ECBIOS57802.2023.10218541","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218541","url":null,"abstract":"The emergence of antimicrobial resistance genes in multidrug-resistant gram-negative (MDRGN) bacteria leads to an immense increase in mortality rates and poses a major threat to global health. Current treatment methods and even drugs of last resort (DoLRs) have failed to successfully treat these infections, warranting the need for a new and immediate solution. This study focuses on the synthesis and investigation of an optimal dispersal agent for co-treatment. Previous screening of the genome of Acinetobacter baumannii, a highly virulent nosocomial gram-negative pathogen of ESKAPE, identified the hypothetical gene segment Pase 1 with potential characteristics of bacterial dispersion. Through treatment of various multidrug-resistant gram-negative bacterial biofilms and ESKAPE pathogens, the results indicated that AB-Pase 1 exhibited optimal characteristics as a co-treatment dispersal agent, with higher dispersion percentages and controlled dispersal rates in comparison to E. coli-Pase 1. Therefore, with the expansion of AB-Pase 1 in co-treatment therapy, there is an immense potential for successfully combating multi-resistant bacteria, a crucial breakthrough in the medical field.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"25 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":"132543003","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/ECBIOS57802.2023.10218376
Ahmad O. Alokaily
Accurate diagnostic tests rooted in neuropsychology are crucial for the detection of dementia in the elderly. Several studies have reported that detecting dementia at early stages is essential in enhancing the effectiveness of therapeutic intervention and delaying the disorder's progression. However, most neuropsychological studies in clinical practice require competent physicians' involvement. Advancements in technology have enabled the computerizing of screening tools, providing a faster and more convenient way to assess the common symptoms of dementia. However, currently, there is no Arabic computerized dementia screening software. Therefore, this study is carried out to present a computerized Arabic assessment tool that is versatile and easy to use. The proposed screening software was developed using MATLAB and consists of 28 questions with a total possible score of 47 points. A test was performed to evaluate four sensitive cognitive functions (memory, attention, visual and naming, and executive function). The computerized Arabic dementia screening tool was tested on five healthy subjects (4 males and 1 female, ages $61.80pm 6.53$) to assess its practicality and ease of use. All participants were able to complete the tests on their own and reported no technical or linguistic difficulty. The proposed test has the potential in primary healthcare clinics, as it is easy to administer and can be supervised by healthcare providers with minimal training.
{"title":"Development of Arabic Computer-Based Screening Tool for Early Detection of Dementia","authors":"Ahmad O. Alokaily","doi":"10.1109/ECBIOS57802.2023.10218376","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218376","url":null,"abstract":"Accurate diagnostic tests rooted in neuropsychology are crucial for the detection of dementia in the elderly. Several studies have reported that detecting dementia at early stages is essential in enhancing the effectiveness of therapeutic intervention and delaying the disorder's progression. However, most neuropsychological studies in clinical practice require competent physicians' involvement. Advancements in technology have enabled the computerizing of screening tools, providing a faster and more convenient way to assess the common symptoms of dementia. However, currently, there is no Arabic computerized dementia screening software. Therefore, this study is carried out to present a computerized Arabic assessment tool that is versatile and easy to use. The proposed screening software was developed using MATLAB and consists of 28 questions with a total possible score of 47 points. A test was performed to evaluate four sensitive cognitive functions (memory, attention, visual and naming, and executive function). The computerized Arabic dementia screening tool was tested on five healthy subjects (4 males and 1 female, ages $61.80pm 6.53$) to assess its practicality and ease of use. All participants were able to complete the tests on their own and reported no technical or linguistic difficulty. The proposed test has the potential in primary healthcare clinics, as it is easy to administer and can be supervised by healthcare providers with minimal training.","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":"117265142","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/ECBIOS57802.2023.10218477
Jen-Suh Chern, Yu-Chih Mao
The purpose of this study was to examine the effects of immersive virtual reality puzzle-solving videogame (IVRPSVG) training on improving cognition, motor control, and functional behavior in people with Schizophrenia Spectrum Disorder (SSD). This study was carried out with a randomized control and a pre-posttest design. There was a total of 22 participants (12 in the experimental group and 10 in the control group). The experimental group received IVRPSVG training for 12 weeks, three times a week, and 30 to 40 min each time. The control group received work activities intervention. The outcome measures include Color Trails Test one and two (CTT1 &2), Left-hand and Right-hand Box and Block Test (BBTR and BTTL), Timed Up and Go Test (TUG), and Functional Reach Test (FRT). A repeated measured two-way analysis of covariance was used to test whether the training in this study caused significant changes with SPSS 23.0 statistical software package. Statistically significant differences were determined at $p < 0.05$. The statistical analysis results showed that IVRPSVG was effective in (1) shortening the time spent on CTT1 ($p=0.01$), and (2) improving the performance in BBTL and TUG ($p=0.01, p=0.01$). There was no significant difference in functional behavior between the groups. This result indicated that IVRPSVG had a significant effect on the cognitive-motor integration ability (including path-motor skills, perceptual tracking, number sorting, and sustained attention), upper and left-hand gross motor manipulation, and lower-extremity motor control in patients with SSD. In addition, the work activities training also improved the cognition and motor control of the upper and lower extremities. The improvement in cognition and movement obtained by 12 weeks of training was not sufficient to reflect the changes in cognition and motor control in changes of functional behavior.
{"title":"Effects of Immersive Virtual Reality Puzzle Solving Video Games on Cognition, Motor Control, and Functional Behavior in People with Schizophrenia Spectrum Disorders","authors":"Jen-Suh Chern, Yu-Chih Mao","doi":"10.1109/ECBIOS57802.2023.10218477","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218477","url":null,"abstract":"The purpose of this study was to examine the effects of immersive virtual reality puzzle-solving videogame (IVRPSVG) training on improving cognition, motor control, and functional behavior in people with Schizophrenia Spectrum Disorder (SSD). This study was carried out with a randomized control and a pre-posttest design. There was a total of 22 participants (12 in the experimental group and 10 in the control group). The experimental group received IVRPSVG training for 12 weeks, three times a week, and 30 to 40 min each time. The control group received work activities intervention. The outcome measures include Color Trails Test one and two (CTT1 &2), Left-hand and Right-hand Box and Block Test (BBTR and BTTL), Timed Up and Go Test (TUG), and Functional Reach Test (FRT). A repeated measured two-way analysis of covariance was used to test whether the training in this study caused significant changes with SPSS 23.0 statistical software package. Statistically significant differences were determined at $p < 0.05$. The statistical analysis results showed that IVRPSVG was effective in (1) shortening the time spent on CTT1 ($p=0.01$), and (2) improving the performance in BBTL and TUG ($p=0.01, p=0.01$). There was no significant difference in functional behavior between the groups. This result indicated that IVRPSVG had a significant effect on the cognitive-motor integration ability (including path-motor skills, perceptual tracking, number sorting, and sustained attention), upper and left-hand gross motor manipulation, and lower-extremity motor control in patients with SSD. In addition, the work activities training also improved the cognition and motor control of the upper and lower extremities. The improvement in cognition and movement obtained by 12 weeks of training was not sufficient to reflect the changes in cognition and motor control in changes of functional behavior.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"9 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":"134253458","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/ECBIOS57802.2023.10218556
Zhilei Huo, Jiaqi Li, Rui Li, Gang Wang, Zheyan Cheng, Gang Ren
We introduce a novel approach to promoting healthy sitting posture for students during their home study by using a posture-based smart learning environment (PBSLE). The prolonged sitting period in studying imposes negative effects on students' learning outcomes and musculoskeletal health and leads to long-term ailments such as back pain and spinal disorders. It is crucial to solve this problem to ensure the overall well-being and academic performance of students. The PBSLE system leverages cutting-edge sensor technologies and the Internet of Things (IoTs) are adopted to monitor students' sitting postures in real-time and deliver personalized feedback to correct improper postures with active interventions of smart table lamps, height-adjustable tables, and chairs. The system design for interactive applications helps to maintain a proper sitting posture to promote health and learning efficiency. The initial evaluation showed an improvement in sitting behaviors, suggesting that the PBISLE system is an effective tool for a healthy and efficient study with the right postures. We discuss the use of PBSLE in various educational settings such as classrooms and libraries.
{"title":"Promoting Healthy Sitting Posture During Study Sessions with Posture-Based Interaction Smart Learning Environment","authors":"Zhilei Huo, Jiaqi Li, Rui Li, Gang Wang, Zheyan Cheng, Gang Ren","doi":"10.1109/ECBIOS57802.2023.10218556","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218556","url":null,"abstract":"We introduce a novel approach to promoting healthy sitting posture for students during their home study by using a posture-based smart learning environment (PBSLE). The prolonged sitting period in studying imposes negative effects on students' learning outcomes and musculoskeletal health and leads to long-term ailments such as back pain and spinal disorders. It is crucial to solve this problem to ensure the overall well-being and academic performance of students. The PBSLE system leverages cutting-edge sensor technologies and the Internet of Things (IoTs) are adopted to monitor students' sitting postures in real-time and deliver personalized feedback to correct improper postures with active interventions of smart table lamps, height-adjustable tables, and chairs. The system design for interactive applications helps to maintain a proper sitting posture to promote health and learning efficiency. The initial evaluation showed an improvement in sitting behaviors, suggesting that the PBISLE system is an effective tool for a healthy and efficient study with the right postures. We discuss the use of PBSLE in various educational settings such as classrooms and libraries.","PeriodicalId":334600,"journal":{"name":"2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)","volume":"7 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":"133993349","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/ECBIOS57802.2023.10218532
Wang Jiao, Wei Wei
The main endpoint drift, electromyography (EMG) interference signals, step-up transformer interference signals, and large motion artifacts often appear in ambulatory rhythm. In solving the signal problem, the traditional method has caused a great loss. The deep learning neural network model used in this study did not require prior knowledge related to the characteristic waveforms and pathological features. Using supervised or unsupervised learning of various features related to the data and classification, the limitations caused by insufficient prior knowledge were avoided. We proposed the form of pre-reinforcement training with the model. Using a deep neural network, the unsupervised learning of data for ECG examination was achieved. By pre-training and manually adjusting the experimental comparison of multiple databases, the calculation accuracy of the model was effectively improved. The information associated with the extrinsic features of the extracted data was adopted for learning reinforcement training. The fusion of the control mechanisms enhanced the received signal containing the generated noise and contributed to the extraction of useful extrinsic features.
{"title":"Heart Rhythm Abnormal Signal Diagnosis Based on Neural Network Deep Learning","authors":"Wang Jiao, Wei Wei","doi":"10.1109/ECBIOS57802.2023.10218532","DOIUrl":"https://doi.org/10.1109/ECBIOS57802.2023.10218532","url":null,"abstract":"The main endpoint drift, electromyography (EMG) interference signals, step-up transformer interference signals, and large motion artifacts often appear in ambulatory rhythm. In solving the signal problem, the traditional method has caused a great loss. The deep learning neural network model used in this study did not require prior knowledge related to the characteristic waveforms and pathological features. Using supervised or unsupervised learning of various features related to the data and classification, the limitations caused by insufficient prior knowledge were avoided. We proposed the form of pre-reinforcement training with the model. Using a deep neural network, the unsupervised learning of data for ECG examination was achieved. By pre-training and manually adjusting the experimental comparison of multiple databases, the calculation accuracy of the model was effectively improved. The information associated with the extrinsic features of the extracted data was adopted for learning reinforcement training. The fusion of the control mechanisms enhanced the received signal containing the generated noise and contributed to the extraction of useful extrinsic features.","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":"132647114","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：