Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618764
Natrisha Francis, Aziz Ong, Hazwani Suhaimi, P. E. Abas
Ankle sprains are amongst the most prevalent musculoskeletal system injuries, impacting athletes of all ages and all sporting activities, with most ankle sprains resulting from stress during inversion, plantar flexion, or supination of the foot. One method of simulating ankle sprain motion is through sub-injury trials using a platform that can force the foot to invert, simulating an ankle sprain motion repeatedly on human participants without causing actual injury. This study aims to design and fabricate a tilting platform that uses a DC motor to enable such research to be performed. The tilting platform, which is capable of inverting the foot to the desired angle of inversion to simulate ankle sprain motion, has been constructed, and a total of 20 sets of data have been collected from four participants to ensure that the platform is able to simulate ankle sprain motion. The design, material, structure, and mechanism of the tilting platform was made to ensure the participants’ safety and not cause real injury to the participants. Comparison of sub-injury trial using the platform and kinematic data from OpenSim has shown that the tilting platform is capable of simulating real-life ankle sprain motion for data analysis, which paves the way forward for further studies on ankle sprain.
{"title":"A Tilting Platform as a Sub-injury Motion for Ankle Sprain Studies","authors":"Natrisha Francis, Aziz Ong, Hazwani Suhaimi, P. E. Abas","doi":"10.1109/nbec53282.2021.9618764","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618764","url":null,"abstract":"Ankle sprains are amongst the most prevalent musculoskeletal system injuries, impacting athletes of all ages and all sporting activities, with most ankle sprains resulting from stress during inversion, plantar flexion, or supination of the foot. One method of simulating ankle sprain motion is through sub-injury trials using a platform that can force the foot to invert, simulating an ankle sprain motion repeatedly on human participants without causing actual injury. This study aims to design and fabricate a tilting platform that uses a DC motor to enable such research to be performed. The tilting platform, which is capable of inverting the foot to the desired angle of inversion to simulate ankle sprain motion, has been constructed, and a total of 20 sets of data have been collected from four participants to ensure that the platform is able to simulate ankle sprain motion. The design, material, structure, and mechanism of the tilting platform was made to ensure the participants’ safety and not cause real injury to the participants. Comparison of sub-injury trial using the platform and kinematic data from OpenSim has shown that the tilting platform is capable of simulating real-life ankle sprain motion for data analysis, which paves the way forward for further studies on ankle sprain.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121944714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618759
Muhammad Adham Aziz, S. A. Jalil, Sharifah Alwiah Syed Abdul Rahaman, H. Abdullah, S. H. Ismail, S. A. M. Aris, N. Noor, Mohd Azmarul A Aziz
Aphasia is a difficulty in communication due to the loss of linguistic abilities caused by brain injuries. People with aphasia can recover their lost abilities through training with language therapy where it trains the ability to read, write, comprehends, and produce speech. With the booming advance in technology, telerehabilitation with the use of IoT opens up possibilities for improvement for providing a better life for people with aphasia. Smartphones being mobile and pocketsized can provide a big improvement for people with aphasia. Mobile applications can be designed and developed based on people’s needs including healthcare. This study will focus on mobile application development for Malay-speaking people with aphasia. Stroke cases in Malaysia have been up to 14396 cases between the year 2012 to 2019 and a median of 34% of post-stroke patients obtained aphasia. In this study, speech therapy mobile apps with a monitoring system will be developed. The mobile app is designed and developed using the Flutter Software development kit as the tool for mobile apps development and IoT as a connection between devices. The monitoring system will be tested to collect the data from users that completed the task and can be accessed by the patient’s caregiver and the patient’s Speech-Language Therapist.
{"title":"Development of Speech Therapy Mobile Application for Aphasia Patients","authors":"Muhammad Adham Aziz, S. A. Jalil, Sharifah Alwiah Syed Abdul Rahaman, H. Abdullah, S. H. Ismail, S. A. M. Aris, N. Noor, Mohd Azmarul A Aziz","doi":"10.1109/nbec53282.2021.9618759","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618759","url":null,"abstract":"Aphasia is a difficulty in communication due to the loss of linguistic abilities caused by brain injuries. People with aphasia can recover their lost abilities through training with language therapy where it trains the ability to read, write, comprehends, and produce speech. With the booming advance in technology, telerehabilitation with the use of IoT opens up possibilities for improvement for providing a better life for people with aphasia. Smartphones being mobile and pocketsized can provide a big improvement for people with aphasia. Mobile applications can be designed and developed based on people’s needs including healthcare. This study will focus on mobile application development for Malay-speaking people with aphasia. Stroke cases in Malaysia have been up to 14396 cases between the year 2012 to 2019 and a median of 34% of post-stroke patients obtained aphasia. In this study, speech therapy mobile apps with a monitoring system will be developed. The mobile app is designed and developed using the Flutter Software development kit as the tool for mobile apps development and IoT as a connection between devices. The monitoring system will be tested to collect the data from users that completed the task and can be accessed by the patient’s caregiver and the patient’s Speech-Language Therapist.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618755
M. Masrom, N. Noor, A. I. Kamaruddin, M. A. A. Aziz
Mobile applications have become substantial and practical for speech therapy services for people with aphasia (PWA) in this advancing technology era. Cultural and linguistic features consideration play a vital role in mobile applications utilization in speech therapy sessions. PWA in the Malaysian population mostly uses the Malay language as their lingua franca. The objective of this study is to 1) review mobile apps available for aphasia and 2) identify instructional features (speech therapy components) and functional features (nonlinguistic components and technology components) of speech therapy mobile applications for the PWA population in Malaysia. Preliminary search and selection process using Preferred Reporting Items for Systematic reviews and Meta Analyses (PRISMA) has identified 1797 apps with 161 apps eligible to be included for reviewing. This study enables documentation and review of the aphasia speech therapy apps compatible with iOS and Android mobile phones. It shall also identify the features and recommendations for the incorporation of users’ needs and perspective in mobile apps development for PWA, particularly in the Malaysian population. This study will help with the review of the speech therapy apps features and propose the framework for future development of speech therapy apps for PWA in the Malay language.
{"title":"Speech Therapy Mobile Applications for People with Aphasia: PRISMA review and features analysis","authors":"M. Masrom, N. Noor, A. I. Kamaruddin, M. A. A. Aziz","doi":"10.1109/nbec53282.2021.9618755","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618755","url":null,"abstract":"Mobile applications have become substantial and practical for speech therapy services for people with aphasia (PWA) in this advancing technology era. Cultural and linguistic features consideration play a vital role in mobile applications utilization in speech therapy sessions. PWA in the Malaysian population mostly uses the Malay language as their lingua franca. The objective of this study is to 1) review mobile apps available for aphasia and 2) identify instructional features (speech therapy components) and functional features (nonlinguistic components and technology components) of speech therapy mobile applications for the PWA population in Malaysia. Preliminary search and selection process using Preferred Reporting Items for Systematic reviews and Meta Analyses (PRISMA) has identified 1797 apps with 161 apps eligible to be included for reviewing. This study enables documentation and review of the aphasia speech therapy apps compatible with iOS and Android mobile phones. It shall also identify the features and recommendations for the incorporation of users’ needs and perspective in mobile apps development for PWA, particularly in the Malaysian population. This study will help with the review of the speech therapy apps features and propose the framework for future development of speech therapy apps for PWA in the Malay language.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131833605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618714
Nur Husna Shahimi, Choon-Hian Goh, M. Tan, E. Lim
Falls among older adults have become a global concern. Autonomic nervous system (ANS) function, which is implicated, can be noninvasively evaluated with heart rate variability (HRV) and blood pressure variability (BPV). The present study evaluated relationship between physical activity, physical performance and autonomic function in 92 older individuals. Continuous non-invasive cardiovascular autonomic reflexes were monitored over 5 minutes supine rest and 3 minutes standing upright. Our findings suggest that elderly fallers had poorer autonomic function, lower hand-grip strength (p< 0.001), poorer walking ability (TUG: p=0.004), greater dependence in instrumental activities of daily living (Lawton IADL: p< 0.001) and lower physical activity level (PASE: p< 0.001). Overall, Lawton IADL, PASE and Time-up and Go were significantly associated with autonomic function indices (LF-nu, HF-nu, LF/HF) and could be served as pre-screening tools to identify patients with autonomic dysfunction. Identification of specific autonomic function risk factors can be useful in the early prevention and diagnosis of recurrent falls and cardiovascular risk.
{"title":"Association between Physical Performance and Autonomic Nervous System in Elderly Fallers","authors":"Nur Husna Shahimi, Choon-Hian Goh, M. Tan, E. Lim","doi":"10.1109/nbec53282.2021.9618714","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618714","url":null,"abstract":"Falls among older adults have become a global concern. Autonomic nervous system (ANS) function, which is implicated, can be noninvasively evaluated with heart rate variability (HRV) and blood pressure variability (BPV). The present study evaluated relationship between physical activity, physical performance and autonomic function in 92 older individuals. Continuous non-invasive cardiovascular autonomic reflexes were monitored over 5 minutes supine rest and 3 minutes standing upright. Our findings suggest that elderly fallers had poorer autonomic function, lower hand-grip strength (p< 0.001), poorer walking ability (TUG: p=0.004), greater dependence in instrumental activities of daily living (Lawton IADL: p< 0.001) and lower physical activity level (PASE: p< 0.001). Overall, Lawton IADL, PASE and Time-up and Go were significantly associated with autonomic function indices (LF-nu, HF-nu, LF/HF) and could be served as pre-screening tools to identify patients with autonomic dysfunction. Identification of specific autonomic function risk factors can be useful in the early prevention and diagnosis of recurrent falls and cardiovascular risk.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114975183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618744
Krishani Murugiah, Mohammad Iliya Zakaria, Hazwani Suhaimi, W. Caesarendra, N. S. Sambudi
Hydroxyapatite (HAp) is a bioceramic material having numerous applications in orthopaedic and dental applications. It can be chemically synthesised from materials that are rich in calcium carbonate (CaCO3). Asiatic Hard Clam (Meretrix meretrix) and Blood Cockle Clam (Anadara granosa) are the commercial species in Southeast Asia, resulting in the discharge of abundant waste shells, which further leads to microbial growth, odour and an unhygienic environment. Moreover, shells are the global source of CaCO3. In order to convert the waste into a valuable product, this study aims to synthesise and characterise HAp from Asiatic Hard Clam and Blood Cockle Clam via a wet precipitation process. These clamshells were characterised by X-Ray fluorescence (XRF), and the result revealed that Asiatic Hard Clam contains 97.4 wt% of CaCO3 and Blood Cockle Clam of about 98.8 wt% of CaCO3. Fourier-transform infrared spectroscopy (FTIR) confirmed the presence of $-left(mathrm{PO}_{4}right)_{3}^{2-},-mathrm{CO}_{3}^{2-}$ and -OH functional groups in the synthesised HAp. The X-Ray powder diffraction (XRD) patterns of this powdered HAp showed sharper peaks which indicates better crystallinity. Moreover, the morphology of the HAp before and after sintering was characterised with the help of scanning electron microscope (SEM), which clearly showed the crystalline structure and coalescence of HAp particles. Results have revealed that HAp derived from both natural clamshells using the wet precipitation method displayed similar crystallinity, morphology and chemical characteristics of pure HAp.
{"title":"Synthesis and Characterisation of Hydroxyapatite (HAp) from Asiatic Hard Clam (Meretrix meretrix) and Blood Cockle Clam (Anadara granosa) Using Wet Precipitation Process","authors":"Krishani Murugiah, Mohammad Iliya Zakaria, Hazwani Suhaimi, W. Caesarendra, N. S. Sambudi","doi":"10.1109/nbec53282.2021.9618744","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618744","url":null,"abstract":"Hydroxyapatite (HAp) is a bioceramic material having numerous applications in orthopaedic and dental applications. It can be chemically synthesised from materials that are rich in calcium carbonate (CaCO3). Asiatic Hard Clam (Meretrix meretrix) and Blood Cockle Clam (Anadara granosa) are the commercial species in Southeast Asia, resulting in the discharge of abundant waste shells, which further leads to microbial growth, odour and an unhygienic environment. Moreover, shells are the global source of CaCO3. In order to convert the waste into a valuable product, this study aims to synthesise and characterise HAp from Asiatic Hard Clam and Blood Cockle Clam via a wet precipitation process. These clamshells were characterised by X-Ray fluorescence (XRF), and the result revealed that Asiatic Hard Clam contains 97.4 wt% of CaCO3 and Blood Cockle Clam of about 98.8 wt% of CaCO3. Fourier-transform infrared spectroscopy (FTIR) confirmed the presence of $-left(mathrm{PO}_{4}right)_{3}^{2-},-mathrm{CO}_{3}^{2-}$ and -OH functional groups in the synthesised HAp. The X-Ray powder diffraction (XRD) patterns of this powdered HAp showed sharper peaks which indicates better crystallinity. Moreover, the morphology of the HAp before and after sintering was characterised with the help of scanning electron microscope (SEM), which clearly showed the crystalline structure and coalescence of HAp particles. Results have revealed that HAp derived from both natural clamshells using the wet precipitation method displayed similar crystallinity, morphology and chemical characteristics of pure HAp.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129937385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618753
Herold Sylvestro Sipail, N. Ahmad, N. Noor
Heart disease is the leading cause of death in the developed world. Early detection of the heart disease can prevent death, as well as other disease that is related to it such as dementia. Therefore, studies in preventing the risks of having a stroke or heart attack required. Using machine learning techniques, the aim of this study is to evaluate the accuracy of supervised learning techniques in predicting heart disease based on the dataset obtained from University of California Irvine data repository. The result from this study shows that Naïve Bayes and Bayesian Network has better estimated accuracy in Weka for the data set, while both Bayesian Network and J48 may give useful insight with Weka generated visualization.
{"title":"Heart Disease Prediction Using Machine Learning Techniques","authors":"Herold Sylvestro Sipail, N. Ahmad, N. Noor","doi":"10.1109/nbec53282.2021.9618753","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618753","url":null,"abstract":"Heart disease is the leading cause of death in the developed world. Early detection of the heart disease can prevent death, as well as other disease that is related to it such as dementia. Therefore, studies in preventing the risks of having a stroke or heart attack required. Using machine learning techniques, the aim of this study is to evaluate the accuracy of supervised learning techniques in predicting heart disease based on the dataset obtained from University of California Irvine data repository. The result from this study shows that Naïve Bayes and Bayesian Network has better estimated accuracy in Weka for the data set, while both Bayesian Network and J48 may give useful insight with Weka generated visualization.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116688055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618758
Muhammad Faris Harun, S. H. Ismail, N. A. Raman, H. Abdullah
One of the industries that make a huge return in Malaysia’s economy is the oil and gas industry, but it is also one of the highest risk industries. This study was conducted to assess the daily risk associated with the ergonomics hazards often encountered by general workers and engineers on board and its contribution to the health of the employees. The study specified food and provision loading activities on the deck area. Data was collected and analyzed using the Rapid Entire Body Assessment (REBA) standard method and Recommended Weight Limit (RWL) calculations by the National Institute of Occupational Safety and Health (NIOSH) Malaysia. The risk obtained were compared by using the Cornell Musculoskeletal Discomfort Questionnaire (CMDQ). The result shows that the most affected body area was the crew’s upper body part. These were due to the crews’ distance at least 30 meters with loads from lorry to galley. A recommendation was made to mitigate the risk.
{"title":"Ergonomics Risk Factors and Musculoskeletal Discomfort among Offshore Support Vessel Deck and Engine Crews","authors":"Muhammad Faris Harun, S. H. Ismail, N. A. Raman, H. Abdullah","doi":"10.1109/nbec53282.2021.9618758","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618758","url":null,"abstract":"One of the industries that make a huge return in Malaysia’s economy is the oil and gas industry, but it is also one of the highest risk industries. This study was conducted to assess the daily risk associated with the ergonomics hazards often encountered by general workers and engineers on board and its contribution to the health of the employees. The study specified food and provision loading activities on the deck area. Data was collected and analyzed using the Rapid Entire Body Assessment (REBA) standard method and Recommended Weight Limit (RWL) calculations by the National Institute of Occupational Safety and Health (NIOSH) Malaysia. The risk obtained were compared by using the Cornell Musculoskeletal Discomfort Questionnaire (CMDQ). The result shows that the most affected body area was the crew’s upper body part. These were due to the crews’ distance at least 30 meters with loads from lorry to galley. A recommendation was made to mitigate the risk.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122381877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618763
H. Hasri, S. A. M. Aris, R. Ahmad
Coronavirus disease 2019 is a fatal viral disease presently sweeping the globe. COVID-19 is a novel coronavirus that produces an infectious illness. Thus, COVID-19 detection in the general population may be helpful. The involvement of machine learning in combating COVID-19 had rapidly increased because of its efficiency to scale up, faster processing capacity, and more dependable than humans in some healthcare activities. This paper will focus on two models which are Linear Regression (LR) model and Holt’s Winter model. The COVID-19 dataset was taken from the Ministry of Health for Malaysia’s website. Daily confirmed cases were recorded from 24th of January 2020 to 31st July 2021 and stored in Microsoft Excel. Waikato Environment for Knowledge Analysis (WEKA) software was utilized to perform the prediction of daily cases in the next 14-days and the quality of forecasting models is evaluated by two performance metrics, Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The best model is selected by the lowest value of performance metrics. The comparison shows that the forecasting result of Holt’s Winter is more accurate than the LR model. The developed prediction model can help public health officials make better decisions and manage resources to decrease COVID-19 pandemic morbidity and mortality. Therefore, preparation and control procedures can be established.
2019冠状病毒病是目前席卷全球的致命病毒性疾病。COVID-19是一种产生传染病的新型冠状病毒。因此，在普通人群中检测COVID-19可能会有所帮助。机器学习在抗击COVID-19中的参与度迅速增加，因为它的规模扩展效率更高，处理能力更快，在某些医疗保健活动中比人类更可靠。本文将重点研究线性回归(LR)模型和Holt 's Winter模型。COVID-19数据集取自马来西亚卫生部的网站。从2020年1月24日至2021年7月31日，每天记录确诊病例，并存储在Microsoft Excel中。使用Waikato Environment for Knowledge Analysis (WEKA)软件对未来14天的每日病例进行预测，并通过平均绝对偏差(MAD)和平均绝对百分比误差(MAPE)两个性能指标评估预测模型的质量。最佳模型由性能指标的最低值选择。对比表明，Holt’s Winter的预测结果比LR模型更准确。开发的预测模型可以帮助公共卫生官员做出更好的决策并管理资源，以降低COVID-19大流行的发病率和死亡率。因此，可以建立准备和控制程序。
{"title":"Linear Regression and Holt’s Winter Algorithm in Forecasting Daily Coronavirus Disease 2019 Cases in Malaysia: Preliminary Study","authors":"H. Hasri, S. A. M. Aris, R. Ahmad","doi":"10.1109/nbec53282.2021.9618763","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618763","url":null,"abstract":"Coronavirus disease 2019 is a fatal viral disease presently sweeping the globe. COVID-19 is a novel coronavirus that produces an infectious illness. Thus, COVID-19 detection in the general population may be helpful. The involvement of machine learning in combating COVID-19 had rapidly increased because of its efficiency to scale up, faster processing capacity, and more dependable than humans in some healthcare activities. This paper will focus on two models which are Linear Regression (LR) model and Holt’s Winter model. The COVID-19 dataset was taken from the Ministry of Health for Malaysia’s website. Daily confirmed cases were recorded from 24th of January 2020 to 31st July 2021 and stored in Microsoft Excel. Waikato Environment for Knowledge Analysis (WEKA) software was utilized to perform the prediction of daily cases in the next 14-days and the quality of forecasting models is evaluated by two performance metrics, Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The best model is selected by the lowest value of performance metrics. The comparison shows that the forecasting result of Holt’s Winter is more accurate than the LR model. The developed prediction model can help public health officials make better decisions and manage resources to decrease COVID-19 pandemic morbidity and mortality. Therefore, preparation and control procedures can be established.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"485 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123889400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-09DOI: 10.1109/nbec53282.2021.9618751
J. Than, P. L. Thon, O. M. Rijal, R. M. Kassim, A. Yunus, N. Noor, P. Then
COVID-19 and lung diseases have been the major focus of research currently due to the pandemic’s reach and effect. Deep Learning (DL) is playing a large role today in various fields from disease classification to drug response identification. The conventional DL method used for images is the Convolutional Neural Network (CNN). A potential method that will replace the usage of CNNs is Transformer specifically Vision Transformers (ViT). This study is a preliminary exploration to determine the performance of using ViT on diseased lungs, COVID-19 infected lungs, and normal lungs. This study was performed on two datasets. The first dataset was a publicly accessible dataset from Iran that has a large cohort of patients. The second dataset was a Malaysian dataset. These images were utilized to verify the usage of ViT and its effectiveness. Images were segregated into several sized patches (16x16, 32x32, 64x64, 128x128, 256x256) pixels. To determine the performance of ViT method, performance metrics of accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and F1-score. From the results of this study, ViT is a promising method with a peak accuracy of 95.36%.
{"title":"Preliminary Study on Patch Sizes in Vision Transformers (ViT) for COVID-19 and Diseased Lungs Classification","authors":"J. Than, P. L. Thon, O. M. Rijal, R. M. Kassim, A. Yunus, N. Noor, P. Then","doi":"10.1109/nbec53282.2021.9618751","DOIUrl":"https://doi.org/10.1109/nbec53282.2021.9618751","url":null,"abstract":"COVID-19 and lung diseases have been the major focus of research currently due to the pandemic’s reach and effect. Deep Learning (DL) is playing a large role today in various fields from disease classification to drug response identification. The conventional DL method used for images is the Convolutional Neural Network (CNN). A potential method that will replace the usage of CNNs is Transformer specifically Vision Transformers (ViT). This study is a preliminary exploration to determine the performance of using ViT on diseased lungs, COVID-19 infected lungs, and normal lungs. This study was performed on two datasets. The first dataset was a publicly accessible dataset from Iran that has a large cohort of patients. The second dataset was a Malaysian dataset. These images were utilized to verify the usage of ViT and its effectiveness. Images were segregated into several sized patches (16x16, 32x32, 64x64, 128x128, 256x256) pixels. To determine the performance of ViT method, performance metrics of accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and F1-score. From the results of this study, ViT is a promising method with a peak accuracy of 95.36%.","PeriodicalId":297399,"journal":{"name":"2021 IEEE National Biomedical Engineering Conference (NBEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128602931","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：