Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815484
S. Z. Ishak, F. Nusa, Roslina Ahmad, Shahriman Shafien
Malaysia launched REIT in 2013 for infrastructure that could leverage the financial stock market in Malaysia. As one of the most developed countries in South East Asia, Malaysia's infrastructure development, mainly the land transportation network such as the railway system, is becoming a nerve of economic growth with rapid rail development comprised of Light Rail Transit (LRT), Mass Rail Transit (MRT), and the Electric Train Service (ETS) under KTMB and Prasarana, respectively. However, discontinuing rail development in the main city could obstruct the Malaysian market and economic growth. The investment regime that has potential for railway development, such as the real estate market, should become more prominent. Thus, the potential of M-REITs and Islamic REITs is to be explored for real estate infrastructure in the Malaysian market. This study aims to understand the REIT infrastructure and its differences from normal REITs and i-REITs on the differences between China REIT (C-REIT) and Japan Infrastructure Fund. The outcome of this study will be compared with M-REIT followed by its potential in the domain of infrastructure investment. The framework of C-REIT and Japan Infrastructure Fund will be done through several categories, starting with the investors, REIT management, project owners, ownership, distribution, and others to be discussed in depth.
{"title":"The Comparison of Malaysian Real Estate Investment Trusts (M-REITs) and Islamic REITs with China-REITs (C-REITs) and Japan Infrastructure Fund for Railway Infrastructure Development in Malaysia: A Review","authors":"S. Z. Ishak, F. Nusa, Roslina Ahmad, Shahriman Shafien","doi":"10.1109/i2cacis54679.2022.9815484","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815484","url":null,"abstract":"Malaysia launched REIT in 2013 for infrastructure that could leverage the financial stock market in Malaysia. As one of the most developed countries in South East Asia, Malaysia's infrastructure development, mainly the land transportation network such as the railway system, is becoming a nerve of economic growth with rapid rail development comprised of Light Rail Transit (LRT), Mass Rail Transit (MRT), and the Electric Train Service (ETS) under KTMB and Prasarana, respectively. However, discontinuing rail development in the main city could obstruct the Malaysian market and economic growth. The investment regime that has potential for railway development, such as the real estate market, should become more prominent. Thus, the potential of M-REITs and Islamic REITs is to be explored for real estate infrastructure in the Malaysian market. This study aims to understand the REIT infrastructure and its differences from normal REITs and i-REITs on the differences between China REIT (C-REIT) and Japan Infrastructure Fund. The outcome of this study will be compared with M-REIT followed by its potential in the domain of infrastructure investment. The framework of C-REIT and Japan Infrastructure Fund will be done through several categories, starting with the investors, REIT management, project owners, ownership, distribution, and others to be discussed in depth.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128424049","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815270
Vince Andrei S. Hu, M. A. Latina, Jaymick Bryan A. Monido
Soil is the core of agriculture, and the quality of the soil often influences which crops the farmers can and cannot cultivate in a particular area. The inaccessibility of modern agricultural equipment, such as those used to detect soil quality, is one of the factors leading to the Philippines' agriculture sector's downfall. Nitrogen (N), phosphorus (P), and potassium (K) are all significant soil quality indicators since they aid in plant growth and development. In this paper, the researchers formed a technique for determining NPK levels in a given soil sample. NPK levels were determined with an optical transducer and compared to lab-acquired values from soil samples. With a Pearson Correlation Coefficient R-value greater than 0.5, the device reading corresponds and correlates with the findings from the recognized soil testing facility in all nutrients Nitrogen (N), Phosphorus (P), and Potassium (K).
{"title":"Use of Fuzzy Logic System for Assessing Optically-Detected NPK Levels","authors":"Vince Andrei S. Hu, M. A. Latina, Jaymick Bryan A. Monido","doi":"10.1109/i2cacis54679.2022.9815270","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815270","url":null,"abstract":"Soil is the core of agriculture, and the quality of the soil often influences which crops the farmers can and cannot cultivate in a particular area. The inaccessibility of modern agricultural equipment, such as those used to detect soil quality, is one of the factors leading to the Philippines' agriculture sector's downfall. Nitrogen (N), phosphorus (P), and potassium (K) are all significant soil quality indicators since they aid in plant growth and development. In this paper, the researchers formed a technique for determining NPK levels in a given soil sample. NPK levels were determined with an optical transducer and compared to lab-acquired values from soil samples. With a Pearson Correlation Coefficient R-value greater than 0.5, the device reading corresponds and correlates with the findings from the recognized soil testing facility in all nutrients Nitrogen (N), Phosphorus (P), and Potassium (K).","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122410821","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 : 2022-06-25DOI: 10.1109/I2CACIS54679.2022.9815463
Turki Khaled Salem, Wai Kit Wong, Thu Soe Min, E. K. Wong
The counterfeit problem with Ringgit become a significant challenge especially with nowadays high definition color printing technology. Hence, watermark-based image processing techniques is crucial to the Ringgit counterfeit detection. This paper presents a Malaysian banknotes counterfeit detection algorithm using fuzzy logic and image processing techniques for ten Ringgit and twenty Ringgit. The algorithm will first identify the currency values of the inserted banknote, perform banknotes position detection and re-adjustment, detect the three watermarks (Watermark Portrait, Perfect See-Through Register, and Color Shifting Security Thread) and uses the Fuzzy IF-THEN conditional statements to inference and make decision whether the inserted banknote is a real ten Ringgit, a real twenty Ringgit or none of them.
{"title":"Malaysian Banknotes Counterfeit Detection Algorithm for Ten Ringgit and Twenty Ringgit","authors":"Turki Khaled Salem, Wai Kit Wong, Thu Soe Min, E. K. Wong","doi":"10.1109/I2CACIS54679.2022.9815463","DOIUrl":"https://doi.org/10.1109/I2CACIS54679.2022.9815463","url":null,"abstract":"The counterfeit problem with Ringgit become a significant challenge especially with nowadays high definition color printing technology. Hence, watermark-based image processing techniques is crucial to the Ringgit counterfeit detection. This paper presents a Malaysian banknotes counterfeit detection algorithm using fuzzy logic and image processing techniques for ten Ringgit and twenty Ringgit. The algorithm will first identify the currency values of the inserted banknote, perform banknotes position detection and re-adjustment, detect the three watermarks (Watermark Portrait, Perfect See-Through Register, and Color Shifting Security Thread) and uses the Fuzzy IF-THEN conditional statements to inference and make decision whether the inserted banknote is a real ten Ringgit, a real twenty Ringgit or none of them.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207953","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815473
Quah Yi Hang, Tan Xiao Jian, Khairul Shakir Ab Rahman, Lu Juei Min, Teoh Leong Hoe, Wong Chung Yee, Oung Qi Wei, Teoh Chai Ling
According to the International Agency for Research on Cancer (IARC), breast cancer has become the most diagnosed cancer in the world. The analysis of breast histopathology images is important. Segmentation of relevant and irrelevant regions is an important pre-processing for the analysis of breast cancer. In the conventional method, the histopathologists need to use the eyeball rolling method to find the tumor regions. The main objective of this paper is to develop an automation segmentation procedure for the relevant regions, which are referred as tumor regions, and irrelevant regions refer as non-tumor regions. The proposed procedure consists of four main stages: (1) color normalization; (2) color model conversion; (3) relevant regions segmentation using FCM, and; (4) masking processing. The proposed procedure was tested using 31 breast histopathology images. The obtained results show that the average accuracy and precision of the relevant region detection are 86.27% (±8.4129) and 84.53% (±10.6636), respectively.
{"title":"Fuzzy Relevant Regions Segmentation in Breast Histopathology Images using FCM","authors":"Quah Yi Hang, Tan Xiao Jian, Khairul Shakir Ab Rahman, Lu Juei Min, Teoh Leong Hoe, Wong Chung Yee, Oung Qi Wei, Teoh Chai Ling","doi":"10.1109/i2cacis54679.2022.9815473","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815473","url":null,"abstract":"According to the International Agency for Research on Cancer (IARC), breast cancer has become the most diagnosed cancer in the world. The analysis of breast histopathology images is important. Segmentation of relevant and irrelevant regions is an important pre-processing for the analysis of breast cancer. In the conventional method, the histopathologists need to use the eyeball rolling method to find the tumor regions. The main objective of this paper is to develop an automation segmentation procedure for the relevant regions, which are referred as tumor regions, and irrelevant regions refer as non-tumor regions. The proposed procedure consists of four main stages: (1) color normalization; (2) color model conversion; (3) relevant regions segmentation using FCM, and; (4) masking processing. The proposed procedure was tested using 31 breast histopathology images. The obtained results show that the average accuracy and precision of the relevant region detection are 86.27% (±8.4129) and 84.53% (±10.6636), respectively.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116209051","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815488
Md. Tanjil Sarker, A. H. Tan, Timothy Tzen Vun Yap
In this paper, iterative system identification is investigated where the amplitude spectra of the perturbation signals are optimised according to the present estimate of the model parameters. The iterative signal design is compared for single-input single-output (SISO) open loop systems grouped into six different categories based on the system order and dynamic characteristic. Three different signal-to-noise ratios (SNRs) are tested. The performance of the iterative signal design is assessed by taking the ratios of the performance measures of the estimated and initial models to the actual model for a single iteration. These performance measures are defined based on errors in the frequency response. It was found that the iterative signal design is very effective in reducing the model error, except for high order lowpass systems.
{"title":"Performance Evaluation of Iterative Signal Design for System Identification","authors":"Md. Tanjil Sarker, A. H. Tan, Timothy Tzen Vun Yap","doi":"10.1109/i2cacis54679.2022.9815488","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815488","url":null,"abstract":"In this paper, iterative system identification is investigated where the amplitude spectra of the perturbation signals are optimised according to the present estimate of the model parameters. The iterative signal design is compared for single-input single-output (SISO) open loop systems grouped into six different categories based on the system order and dynamic characteristic. Three different signal-to-noise ratios (SNRs) are tested. The performance of the iterative signal design is assessed by taking the ratios of the performance measures of the estimated and initial models to the actual model for a single iteration. These performance measures are defined based on errors in the frequency response. It was found that the iterative signal design is very effective in reducing the model error, except for high order lowpass systems.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125847055","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815457
F. A. Thobiani, Esra Elhadad, A. Shamekh, A. Altowati
A Genetic Algorithm (GA) combined with a two-loop PID-PI control structure is utilized to control the temperature of a semi-batch polymerization reactor (SBPR). The Chylla-Haase benchmark model is considered in this work. The GA-based optimization is exploited in single and multi-objective problems to determine the desired controller setting. The study is conducted in the Matlab/Simulink environment with several simulation scenarios. The obtained results reveal that the GA-based PID-PI technique can provide consistent performance that satisfies the system constraints. Moreover, the proposed algorithm does not contain heavy calculation burdens and can be tuned offline.
{"title":"Application of Genetic Algorithm in Semi-batch Polymerization Temperature Control","authors":"F. A. Thobiani, Esra Elhadad, A. Shamekh, A. Altowati","doi":"10.1109/i2cacis54679.2022.9815457","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815457","url":null,"abstract":"A Genetic Algorithm (GA) combined with a two-loop PID-PI control structure is utilized to control the temperature of a semi-batch polymerization reactor (SBPR). The Chylla-Haase benchmark model is considered in this work. The GA-based optimization is exploited in single and multi-objective problems to determine the desired controller setting. The study is conducted in the Matlab/Simulink environment with several simulation scenarios. The obtained results reveal that the GA-based PID-PI technique can provide consistent performance that satisfies the system constraints. Moreover, the proposed algorithm does not contain heavy calculation burdens and can be tuned offline.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125015602","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815479
M. N. Mohammed, Osama Y. M. Al-Rawi, S. Al-Zubaidi, Safinaz Mustapha, M. Abdulrazaq
A smart city incorporates information and communication technology (ICT) to achieve operational excellence, public info sharing, and the integrity of state services and citizen satisfaction. Nowadays, Bahrain has started a drive forward into smart cities, whereby urban areas can be more effective, habitable, and sustainable in the short and long term with the direct involvement of government, citizens, and enterprises. Food service providers should pay attention to consumer concerns regarding food safety since they have the ability to alter the use of their services as a result of the COVID-19 pandemic and state societal distancing regulations. This study intends to build and construct a Smart Restaurant Order System that provides an automated dining experience that eliminates the need for people to wait staff. When the epidemic struck, however, it became not only one of the just methods to purchase, yet indeed one of the safer, as it required little to no human interaction. As a result, both restaurants and people have embraced technology more quickly.
{"title":"Toward Sustainable Smart Cities in the Kingdom of Bahrain: A New Approach of Smart Restaurant Management and Ordering System During Covid-19","authors":"M. N. Mohammed, Osama Y. M. Al-Rawi, S. Al-Zubaidi, Safinaz Mustapha, M. Abdulrazaq","doi":"10.1109/i2cacis54679.2022.9815479","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815479","url":null,"abstract":"A smart city incorporates information and communication technology (ICT) to achieve operational excellence, public info sharing, and the integrity of state services and citizen satisfaction. Nowadays, Bahrain has started a drive forward into smart cities, whereby urban areas can be more effective, habitable, and sustainable in the short and long term with the direct involvement of government, citizens, and enterprises. Food service providers should pay attention to consumer concerns regarding food safety since they have the ability to alter the use of their services as a result of the COVID-19 pandemic and state societal distancing regulations. This study intends to build and construct a Smart Restaurant Order System that provides an automated dining experience that eliminates the need for people to wait staff. When the epidemic struck, however, it became not only one of the just methods to purchase, yet indeed one of the safer, as it required little to no human interaction. As a result, both restaurants and people have embraced technology more quickly.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129599711","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815274
Weiming. Lim, Mohammad Babrdel Bonab, K. Chua
Many wood manufacturers are still relying on manual human eyes inspection for wood defects detection. This approach is tedious, inconsistent, inefficient, and prone to human errors. Machine vision technology can provide a satisfactory solution for wood defects detection and reduce the manpower required. In this paper, a lightweight object detection model is proposed for the detection of four types of wood defects based on the YOLOv4-Tiny architecture. The accuracy of the model is improved by modifying the loss function for YOLOv4-Tiny to incorporate Intersection over Union into its objectness loss. The results showed that the improvement made has successfully enhanced the model’s accuracy and the best model can achieve a mean average precision of 88.32% running at 225.22 frames per second.
{"title":"An Optimized Lightweight Model for Real-Time Wood Defects Detection based on YOLOv4-Tiny","authors":"Weiming. Lim, Mohammad Babrdel Bonab, K. Chua","doi":"10.1109/i2cacis54679.2022.9815274","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815274","url":null,"abstract":"Many wood manufacturers are still relying on manual human eyes inspection for wood defects detection. This approach is tedious, inconsistent, inefficient, and prone to human errors. Machine vision technology can provide a satisfactory solution for wood defects detection and reduce the manpower required. In this paper, a lightweight object detection model is proposed for the detection of four types of wood defects based on the YOLOv4-Tiny architecture. The accuracy of the model is improved by modifying the loss function for YOLOv4-Tiny to incorporate Intersection over Union into its objectness loss. The results showed that the improvement made has successfully enhanced the model’s accuracy and the best model can achieve a mean average precision of 88.32% running at 225.22 frames per second.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132152334","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815469
Henry Sheng Hoong Siew, Y. Alshebly, Marwan Nafea
The health and well-being of a fetus can be conducted by constantly monitoring its cardiac activity while in pregnancy. The cardiac movement of the mother and fetus can be monitored by placing several electrodes at the thoracic and abdominal parts of the mother to examine the heart of both the mother and fetus. However, the cardiac activity of the mother may affect the fetal one. Often, the abdominal data is corrupted by the mother’s heart data, which covers the fetal heartbeat signal. This paper presents a method to extract maternal electrocardiogram (MECG) and fetal ECG (FECG) signals from thoracic and abdominal signals from the Daisy database. The proposed method utilizes a combination of the Butterworth and Savitsky-Golay filters to perform the filtering and windowing processes required to extract the MECG. Savitzky-Golay filtered windows are used to perform the FECG signal extraction. The proposed approach was also used to determine the heart rates of the mother and fetus, which were around 85.5 and 132.5 bpm, respectively. The proposed method shows promising performance in terms of noise filtering and extracting the PQRST complex when compared with previously reported methods. The proposed method can be potentially used to filter and extract different biosignals when adjusted to suit the specific applications.
{"title":"Fetal ECG Extraction Using Savitzky-Golay and Butterworth Filters","authors":"Henry Sheng Hoong Siew, Y. Alshebly, Marwan Nafea","doi":"10.1109/i2cacis54679.2022.9815469","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815469","url":null,"abstract":"The health and well-being of a fetus can be conducted by constantly monitoring its cardiac activity while in pregnancy. The cardiac movement of the mother and fetus can be monitored by placing several electrodes at the thoracic and abdominal parts of the mother to examine the heart of both the mother and fetus. However, the cardiac activity of the mother may affect the fetal one. Often, the abdominal data is corrupted by the mother’s heart data, which covers the fetal heartbeat signal. This paper presents a method to extract maternal electrocardiogram (MECG) and fetal ECG (FECG) signals from thoracic and abdominal signals from the Daisy database. The proposed method utilizes a combination of the Butterworth and Savitsky-Golay filters to perform the filtering and windowing processes required to extract the MECG. Savitzky-Golay filtered windows are used to perform the FECG signal extraction. The proposed approach was also used to determine the heart rates of the mother and fetus, which were around 85.5 and 132.5 bpm, respectively. The proposed method shows promising performance in terms of noise filtering and extracting the PQRST complex when compared with previously reported methods. The proposed method can be potentially used to filter and extract different biosignals when adjusted to suit the specific applications.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121996427","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815467
Teh Xuan Ying, Asma’ Abu-Samah
Intensive care unit patients, especially those who have undergone surgeries or have severe health issues, tend to have a higher risk of developing sepsis due to a weaker immune system. Due to late detection of sepsis, no preventive actions can be taken to treat sepsis patients. Therefore, this research aims to identify, validate, and test suitable machine learning algorithms for the early prediction of sepsis using pre-processed data produced from the Medical Information Mart for Intensive Care III, MIMIC-III database. This research will be designing prediction models for 15 hours before sepsis onset using pre-processed data obtained from MIMIC-III database using Decision Tree, Random Forest, AdaBoost, Gradient Boosted Tree, and Multilayer Perceptron. A 10 cross-validation is used in validating the models. The performance of prediction models is evaluated mainly using ROC-AUC score. In model comparison, an extra set of prediction models using the same algorithms is developed for 10 hours before sepsis onset to compare its performance with the earlier prediction model developed. The result of model comparison shows that for the prediction model of 15 and 10 hours before sepsis onset, ROC-AUC score for Gradient Boosted Tree is the best with 0.777 for 15 hours and 0.769 respectively from 10 hours prediction model. The results can be optimized further using more data and using derived Boosted Trees algoritms.
{"title":"Early Prediction of Sepsis for ICU Patients using Gradient Boosted Tree","authors":"Teh Xuan Ying, Asma’ Abu-Samah","doi":"10.1109/i2cacis54679.2022.9815467","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815467","url":null,"abstract":"Intensive care unit patients, especially those who have undergone surgeries or have severe health issues, tend to have a higher risk of developing sepsis due to a weaker immune system. Due to late detection of sepsis, no preventive actions can be taken to treat sepsis patients. Therefore, this research aims to identify, validate, and test suitable machine learning algorithms for the early prediction of sepsis using pre-processed data produced from the Medical Information Mart for Intensive Care III, MIMIC-III database. This research will be designing prediction models for 15 hours before sepsis onset using pre-processed data obtained from MIMIC-III database using Decision Tree, Random Forest, AdaBoost, Gradient Boosted Tree, and Multilayer Perceptron. A 10 cross-validation is used in validating the models. The performance of prediction models is evaluated mainly using ROC-AUC score. In model comparison, an extra set of prediction models using the same algorithms is developed for 10 hours before sepsis onset to compare its performance with the earlier prediction model developed. The result of model comparison shows that for the prediction model of 15 and 10 hours before sepsis onset, ROC-AUC score for Gradient Boosted Tree is the best with 0.777 for 15 hours and 0.769 respectively from 10 hours prediction model. The results can be optimized further using more data and using derived Boosted Trees algoritms.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127667676","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：