Pub Date : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935633
S. Riyadi, Tety Dwi Septiari, Cahya Damarjati, S. Ramli
The SARS-Cov-2 strain caused COVID-19, inflicting mild to moderate respiratory problems. The spread of COVID-19 is extremely fast which has resulted in the number of victims who have been declared dead to date, up to 2,587,225. There are several ways to reduce the spread of COVID-19, one of which is early detection. Currently, there are alternative methods used for early detection, one of which is the neural network method. Deep learning is one type of artificial neural network that is often used for the detection of several kinds of diseases. In this study, we classify CT-Scan images of the lungs based on two classes, namely CT_COVID and CT-NonCOVID, using two models, Inception-v3 and Inception-v4. The total CT-Scan image data used is 2038 and comes from the Kaggle.com website. Results obtained were then compared with standard performance metrics and then analyzed between the best models among the models used in the COVID-19 classification. From the results of the study, the Inception-v3 model obtained an average accuracy value of 93.96%, a precision value of 90.57%, a recall value of 95.65%, a specificity value of 92.81% and an f-score value of 92.51% and The Inception-v4 model obtained an average accuracy value of 86.41%, a precision value of 77.01%, a recall value of 91.18%, a specificity value of 83.77% and an f-score value of 83.38%. Based on the research results, the method with the best performance in COVID-19 classification is the Inception-v3 model because the Inception-v3 model has more layers, with a total of 48 layers and utilizes the idea of factorization that is more suitable for CT-Scan image classification which has low contrast visualization.
SARS-Cov-2毒株导致COVID-19，造成轻度至中度呼吸问题。COVID-19的传播速度非常快，迄今为止已宣布死亡的受害者人数高达2,587,225人。有几种方法可以减少COVID-19的传播，其中之一是早期发现。目前，有一些替代方法用于早期检测，其中一种方法是神经网络方法。深度学习是一种人工神经网络，通常用于检测几种疾病。在本研究中，我们使用Inception-v3和Inception-v4两种模型，基于CT_COVID和ct - non - covid两类对肺部ct扫描图像进行分类。使用的ct扫描图像数据总数为2038，来自Kaggle.com网站。然后将所得结果与标准性能指标进行比较，然后在COVID-19分类中使用的模型中对最佳模型进行分析。从研究结果来看，Inception-v3模型的平均准确率为93.96%，准确率为90.57%，召回率为95.65%，特异性值为92.81%，f-score值为92.51%;Inception-v4模型的平均准确率为86.41%，准确率为77.01%，召回率为91.18%，特异性值为83.77%，f-score值为83.38%。根据研究结果，在COVID-19分类中表现最好的方法是Inception-v3模型，因为Inception-v3模型的层数更多，总共有48层，并且利用了分解的思想，更适合对比度可视化较低的ct扫描图像分类。
{"title":"Covid-19 Detection Based-On CT-Scan Images Using Inception Deep Learning","authors":"S. Riyadi, Tety Dwi Septiari, Cahya Damarjati, S. Ramli","doi":"10.1109/ICCSCE54767.2022.9935633","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935633","url":null,"abstract":"The SARS-Cov-2 strain caused COVID-19, inflicting mild to moderate respiratory problems. The spread of COVID-19 is extremely fast which has resulted in the number of victims who have been declared dead to date, up to 2,587,225. There are several ways to reduce the spread of COVID-19, one of which is early detection. Currently, there are alternative methods used for early detection, one of which is the neural network method. Deep learning is one type of artificial neural network that is often used for the detection of several kinds of diseases. In this study, we classify CT-Scan images of the lungs based on two classes, namely CT_COVID and CT-NonCOVID, using two models, Inception-v3 and Inception-v4. The total CT-Scan image data used is 2038 and comes from the Kaggle.com website. Results obtained were then compared with standard performance metrics and then analyzed between the best models among the models used in the COVID-19 classification. From the results of the study, the Inception-v3 model obtained an average accuracy value of 93.96%, a precision value of 90.57%, a recall value of 95.65%, a specificity value of 92.81% and an f-score value of 92.51% and The Inception-v4 model obtained an average accuracy value of 86.41%, a precision value of 77.01%, a recall value of 91.18%, a specificity value of 83.77% and an f-score value of 83.38%. Based on the research results, the method with the best performance in COVID-19 classification is the Inception-v3 model because the Inception-v3 model has more layers, with a total of 48 layers and utilizes the idea of factorization that is more suitable for CT-Scan image classification which has low contrast visualization.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117170688","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935583
Syahrull Hi-Fi Syam Ahmad Jamil, Abdul Rashid Alias, Mohamad Taufik A. Rahman, F.R. Hashim, S. Shaharuddin, Mohd. Sabri
Regardless of gender, age, or ethnicity, anyone can get cardiac illness. However, the likelihood of intermediate heart failure is very well predicted by family history. Cardiovascular abnormalities, which rarely show early symptoms, cause patients to die suddenly. The electrical activity or surge that makes up the heartbeat is usually erratic. The Multilayer Perceptron (MLP) network is used in this study as an early detection method for cardiac issues. Using a number of training techniques using Logsig as the MLP network's activation function, the cardiac anomaly dataset from the MIT-BIH database is used to train the chosen MLP network. According to the study, the MLP network's BR training strategy outperformed other strategies with mean square errors (MSE) of 0.0212 and regression performance of 0.9867.
{"title":"Cardiac Abnormality Prediction using Logsig-Based MLP Network","authors":"Syahrull Hi-Fi Syam Ahmad Jamil, Abdul Rashid Alias, Mohamad Taufik A. Rahman, F.R. Hashim, S. Shaharuddin, Mohd. Sabri","doi":"10.1109/ICCSCE54767.2022.9935583","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935583","url":null,"abstract":"Regardless of gender, age, or ethnicity, anyone can get cardiac illness. However, the likelihood of intermediate heart failure is very well predicted by family history. Cardiovascular abnormalities, which rarely show early symptoms, cause patients to die suddenly. The electrical activity or surge that makes up the heartbeat is usually erratic. The Multilayer Perceptron (MLP) network is used in this study as an early detection method for cardiac issues. Using a number of training techniques using Logsig as the MLP network's activation function, the cardiac anomaly dataset from the MIT-BIH database is used to train the chosen MLP network. According to the study, the MLP network's BR training strategy outperformed other strategies with mean square errors (MSE) of 0.0212 and regression performance of 0.9867.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126748780","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935648
Roslan Seman, Asyraf Bin Dzulkipli, Zuraidi Saad
Due to the majority population of the earth is now connected online, our healthcare technology needs to keep on track with it. But the things that keep blocking our way to achieving better healthcare technology are connectivity, speed, and continuous monitoring from the doctors. The objective of this study is to develop a system for continuously recording and monitoring patient health parameters. The concerned doctor and the medical assistant can receive the information via the Internet. The patient's heart rate and movement are measured in this paper. ECG, 3D-Accelerometer, and GPS sensors are employed. The information can be uploaded to the cloud for additional review and recording. Another option is to implement a system that notifies the physician or medical assistant. To facilitate remote health monitoring via the Internet, remote health monitoring systems could be developed to gather data that can be analyzed by doctors who are in charge of monitoring the patient in case of a fall/collapse incident. It was suggested to use an IoT system to develop a Smart Wearable System (SWS) for tracking health. To provide a connection for the monitoring process, a WIFI shield is fixed to it. The outcome of this study can have a significant impact on the healthcare sector because it demonstrates the ability to prevent a critical incident in real time.
{"title":"Smart Health Monitoring using ECG, 3D-Accelerometer, GPS and IoT","authors":"Roslan Seman, Asyraf Bin Dzulkipli, Zuraidi Saad","doi":"10.1109/ICCSCE54767.2022.9935648","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935648","url":null,"abstract":"Due to the majority population of the earth is now connected online, our healthcare technology needs to keep on track with it. But the things that keep blocking our way to achieving better healthcare technology are connectivity, speed, and continuous monitoring from the doctors. The objective of this study is to develop a system for continuously recording and monitoring patient health parameters. The concerned doctor and the medical assistant can receive the information via the Internet. The patient's heart rate and movement are measured in this paper. ECG, 3D-Accelerometer, and GPS sensors are employed. The information can be uploaded to the cloud for additional review and recording. Another option is to implement a system that notifies the physician or medical assistant. To facilitate remote health monitoring via the Internet, remote health monitoring systems could be developed to gather data that can be analyzed by doctors who are in charge of monitoring the patient in case of a fall/collapse incident. It was suggested to use an IoT system to develop a Smart Wearable System (SWS) for tracking health. To provide a connection for the monitoring process, a WIFI shield is fixed to it. The outcome of this study can have a significant impact on the healthcare sector because it demonstrates the ability to prevent a critical incident in real time.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130773420","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935630
Mohamad Haizan Othman, Belinda Chong Chiew Meng, N. S. Damanhuri, M. Aziz, N. A. Othman
Osteosarcoma is the common type of bone cancer in children and adolescents. A magnetic resonance imaging (MRI) is one of the medical imaging techniques used by specialist to diagnose the medical conditions of Osteosarcoma patient. A radiofrequency pulse and gradient sequence known as MRI sequence produces a set of pictures with a specific appearance. In clinical, radiologists need to interpret MRI images and correlating them from various sequences for medical image findings. The process requires a lot of human input and therefore it is subjective, time-consuming, and non-reproducible. Image segmentation can be used to automate MR images into different segments. In image processing, various algorithms used to segment the medical images into region. However, due to the overlap of grayscale pixel values make the segmentation process becomes very difficult and challenging. The purpose of this study is to extract tumor on MRI Osteosarcoma based on three MRI thigh sequences namely T1, T2 and T1_FSE+GADO. The area and perimeter of the extracted tumor are then compared with the ground truth. In this study, two algorithms namely OTSU Thresholding (OT) and Fuzzy C-Means (FCM) were used to perform the segmentation on the MRI Osteosarcoma images. The performance of these two algorithms on segmenting the MRI Osteosarcoma from three MRI sequences are compared and discuss. The result shows that FCM could discriminate the abnormal region better in T1_FSE+GADO sequence. The average percentage error for area in T1_FSE+GADO sequence is 6.20% and average percentage error for perimeter is 6.74% compared to T2 sequence which is 7.18% and 7.71%.
{"title":"MRI Thigh Sequences in Determining the Tumor Size Using Fuzzy C-Means for Patients with Osteosarcoma","authors":"Mohamad Haizan Othman, Belinda Chong Chiew Meng, N. S. Damanhuri, M. Aziz, N. A. Othman","doi":"10.1109/ICCSCE54767.2022.9935630","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935630","url":null,"abstract":"Osteosarcoma is the common type of bone cancer in children and adolescents. A magnetic resonance imaging (MRI) is one of the medical imaging techniques used by specialist to diagnose the medical conditions of Osteosarcoma patient. A radiofrequency pulse and gradient sequence known as MRI sequence produces a set of pictures with a specific appearance. In clinical, radiologists need to interpret MRI images and correlating them from various sequences for medical image findings. The process requires a lot of human input and therefore it is subjective, time-consuming, and non-reproducible. Image segmentation can be used to automate MR images into different segments. In image processing, various algorithms used to segment the medical images into region. However, due to the overlap of grayscale pixel values make the segmentation process becomes very difficult and challenging. The purpose of this study is to extract tumor on MRI Osteosarcoma based on three MRI thigh sequences namely T1, T2 and T1_FSE+GADO. The area and perimeter of the extracted tumor are then compared with the ground truth. In this study, two algorithms namely OTSU Thresholding (OT) and Fuzzy C-Means (FCM) were used to perform the segmentation on the MRI Osteosarcoma images. The performance of these two algorithms on segmenting the MRI Osteosarcoma from three MRI sequences are compared and discuss. The result shows that FCM could discriminate the abnormal region better in T1_FSE+GADO sequence. The average percentage error for area in T1_FSE+GADO sequence is 6.20% and average percentage error for perimeter is 6.74% compared to T2 sequence which is 7.18% and 7.71%.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116337687","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935650
Muhammad Junaid Rabbani, A. Memon
A novel output feedback posture stabilization of wheeled mobile robot (WMR) is presented to overcome the challenges faced by posture stabilization of WMR. A generalized normal form of WMR is developed by a suitable change of coordinates via input-output feedback linearization approach, with the restriction of nonzero initial condition of orientation angle. The internal dynamics is in a strict feedback form that provides an ease to implement a regular integral backstepping control technique. The control law achieves asymptotic stabilization of both the internal and external dynamics of mobile robot. The control design of state feedback is further enhanced to output feedback control utilizing a full order high gain observer. It is shown that estimated states converge to true states rapidly with good transient behavior. Stability analysis of the overall system is proved using Lyapunov method.
{"title":"Output Feedback Stabilization of Nonholonomic Wheeled Mobile Robot Using Backstepping Control","authors":"Muhammad Junaid Rabbani, A. Memon","doi":"10.1109/ICCSCE54767.2022.9935650","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935650","url":null,"abstract":"A novel output feedback posture stabilization of wheeled mobile robot (WMR) is presented to overcome the challenges faced by posture stabilization of WMR. A generalized normal form of WMR is developed by a suitable change of coordinates via input-output feedback linearization approach, with the restriction of nonzero initial condition of orientation angle. The internal dynamics is in a strict feedback form that provides an ease to implement a regular integral backstepping control technique. The control law achieves asymptotic stabilization of both the internal and external dynamics of mobile robot. The control design of state feedback is further enhanced to output feedback control utilizing a full order high gain observer. It is shown that estimated states converge to true states rapidly with good transient behavior. Stability analysis of the overall system is proved using Lyapunov method.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122076732","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935665
Edgar Irwin Michael Pawing, K. A. Ahmad, S. Setumin, A. I. C. Ani, M. A. Idin, A. Ahmad, M. K. Osman, R. Boudville
Nowadays, the increasing intention in the research community on small sized electrical energy generators due to the wide use of wireless sensor networks and the drawbacks of conventional chemical batteries, such as their limited lifespan and large physical dimensions. Therefore, the principle of harvesting energy from solar power, electromagnetic fields, wind and the human body have been introduced as alternatives. Among these energy resources, wind energy is clean, renewable and can be easily turned into mechanical vibrations that can be used to generate electrical energy via vibration-to-electrical energy conversion mechanisms using electromagnetic, electrostatic and piezoelectric transducers. From these transducers, piezoelectric materials have received the most attention because of their higher conversion efficiency. Therefore, flexible piezoelectric cantilever was tested for characterized cantilever in vibration energy harvesting. The parameters of the cantilever such as length, width and thickness were varied and investigated for energy conversion and performance. The piezoelectric cantilever was designed and simulated using COMSOL Multiphysics 5.5 tool. The simulation result and performance of each design was compared. Performances were plot based on generated voltage vs applied vibration frequency. Result shows that generated voltage of 4.3V at applied vibration frequency of 155Hz was the most optimal result compared to the rest of the design for a piezoelectric cantilever with the width, length and height of 30mm, 20mm and 0.2mm respectively. This was ideal as most of the devices nowadays uses 5V supply and the small design allows the piezoelectric cantilever to be portable or even easily installed in projects that utilizes it.
{"title":"Characterization of Flexible Piezoelectric Cantilever in Vibration Energy Harvesting","authors":"Edgar Irwin Michael Pawing, K. A. Ahmad, S. Setumin, A. I. C. Ani, M. A. Idin, A. Ahmad, M. K. Osman, R. Boudville","doi":"10.1109/ICCSCE54767.2022.9935665","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935665","url":null,"abstract":"Nowadays, the increasing intention in the research community on small sized electrical energy generators due to the wide use of wireless sensor networks and the drawbacks of conventional chemical batteries, such as their limited lifespan and large physical dimensions. Therefore, the principle of harvesting energy from solar power, electromagnetic fields, wind and the human body have been introduced as alternatives. Among these energy resources, wind energy is clean, renewable and can be easily turned into mechanical vibrations that can be used to generate electrical energy via vibration-to-electrical energy conversion mechanisms using electromagnetic, electrostatic and piezoelectric transducers. From these transducers, piezoelectric materials have received the most attention because of their higher conversion efficiency. Therefore, flexible piezoelectric cantilever was tested for characterized cantilever in vibration energy harvesting. The parameters of the cantilever such as length, width and thickness were varied and investigated for energy conversion and performance. The piezoelectric cantilever was designed and simulated using COMSOL Multiphysics 5.5 tool. The simulation result and performance of each design was compared. Performances were plot based on generated voltage vs applied vibration frequency. Result shows that generated voltage of 4.3V at applied vibration frequency of 155Hz was the most optimal result compared to the rest of the design for a piezoelectric cantilever with the width, length and height of 30mm, 20mm and 0.2mm respectively. This was ideal as most of the devices nowadays uses 5V supply and the small design allows the piezoelectric cantilever to be portable or even easily installed in projects that utilizes it.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124095562","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935639
Muhammad Faiz Ahmad Sobri, Z. Hussain, S. Z. Yahaya, R. Boudville, Noraiza Aqilah Abdul Aziz
Tetraplegia is a type of paralysis that affects upper and lower limbs due to damage of spinal cord or brain. This condition causes difficulty to move and most of the time caretaker is needed to help the patients. This project proposed the design and implementation of an image processing technique in capturing and categorizing different facial gesture and use it as control instructions for electric wheelchair. The aim was to reduce the dependency to caretaker especially for mobility oftetraplegia patient. The deep learning Haar Cascade Classifier identify the expression of a face through image processing in livevideo capture. The Open Computer Vision (OpenCV) in Python was used to detect, recognize, and analyze the facial expression. Convolution Neural Network (CNN), a deep learning operation will act as trainer that analyze an open-source data to create a model as reference for the facial expression recognition. In orderto make the system operated as a standalone system, the Raspberry Pi module that connects with Pi Camera was used as the platform to capture the live video, perform processing, and produce the output control that give instructions to move such as forward, right, left and stop. Based on the analysis of the system performance, the system was capable to produce high accuracyof detection and correctly produce the electric wheelchair controlinstruction according to the facial expressions.
{"title":"Facial Expression Electric Wheelchair Control Instruction Using Image Processing","authors":"Muhammad Faiz Ahmad Sobri, Z. Hussain, S. Z. Yahaya, R. Boudville, Noraiza Aqilah Abdul Aziz","doi":"10.1109/ICCSCE54767.2022.9935639","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935639","url":null,"abstract":"Tetraplegia is a type of paralysis that affects upper and lower limbs due to damage of spinal cord or brain. This condition causes difficulty to move and most of the time caretaker is needed to help the patients. This project proposed the design and implementation of an image processing technique in capturing and categorizing different facial gesture and use it as control instructions for electric wheelchair. The aim was to reduce the dependency to caretaker especially for mobility oftetraplegia patient. The deep learning Haar Cascade Classifier identify the expression of a face through image processing in livevideo capture. The Open Computer Vision (OpenCV) in Python was used to detect, recognize, and analyze the facial expression. Convolution Neural Network (CNN), a deep learning operation will act as trainer that analyze an open-source data to create a model as reference for the facial expression recognition. In orderto make the system operated as a standalone system, the Raspberry Pi module that connects with Pi Camera was used as the platform to capture the live video, perform processing, and produce the output control that give instructions to move such as forward, right, left and stop. Based on the analysis of the system performance, the system was capable to produce high accuracyof detection and correctly produce the electric wheelchair controlinstruction according to the facial expressions.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126474862","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935636
Adelisa Sirco, A. Almisreb, N. Tahir, Jamil Bakri
It is known that the sixth most common cancer worldwide is liver cancer and CT scans are commonly used to diagnose liver cancer. Hence in this study, deep learning techniques specifically the ResNet models are used to extract the liver and tumour from the CT scans. Here, four liver segmentation methods are used based on 130 CT datasets namely the ResNet-18, ResNet-34, ResNet-50, and ResNet-101. Each model is evaluated and validated based on their training and testing accuracy, number of epochs, valid loss and train loss. Initial results showed that the highest accuracy is contributed by ResNet-34 with 99.2% accuracy and next is ResNet-50. Additionally, ResNet-101 is the most efficient network model whilst ResNet-18 is the most rapid. These findings proved that the deep learning can be used for segmentation of liver tumour based on the CT scan images.
{"title":"Liver Tumour Segmentation based on ResNet Technique","authors":"Adelisa Sirco, A. Almisreb, N. Tahir, Jamil Bakri","doi":"10.1109/ICCSCE54767.2022.9935636","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935636","url":null,"abstract":"It is known that the sixth most common cancer worldwide is liver cancer and CT scans are commonly used to diagnose liver cancer. Hence in this study, deep learning techniques specifically the ResNet models are used to extract the liver and tumour from the CT scans. Here, four liver segmentation methods are used based on 130 CT datasets namely the ResNet-18, ResNet-34, ResNet-50, and ResNet-101. Each model is evaluated and validated based on their training and testing accuracy, number of epochs, valid loss and train loss. Initial results showed that the highest accuracy is contributed by ResNet-34 with 99.2% accuracy and next is ResNet-50. Additionally, ResNet-101 is the most efficient network model whilst ResNet-18 is the most rapid. These findings proved that the deep learning can be used for segmentation of liver tumour based on the CT scan images.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128934852","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935625
Amirul Hakim Ramli, N. A. M. Leh, Shabinar Abdul Hamid, Z. Muhammad
The increased demand for electricity has pushed the electrical grid closer to its stability limit. Due to many methods used to enhance the power system, voltage instability and line overloading have become a difficulty. The creation, transmission, and consumption of reactive power can all be used to investigate the nature of voltage stability. Reactive power unbalancing, which happens when the power system is strained, is one of the key reasons of voltage instability. Flexible AC transmission system (FACTS) devices are vital for enhancing the performance of a power system, but they are also quite expensive, thus they must be placed optimally in the power system. Static var compensator (SVC), a FACTS device, can be used to minimise flows in densely laden lines, resulting in minimal system loss and enhanced voltage stability. A method is proposed based on the index of line stability and overall system of VAR power losses was used to select the best position for the SVC device. Using VSI calculation on the power flow system, the weakest bus will be determined and will be assign as the optimal location for SVC. Also, along with this paper an observation on a power flow system with and without SVC are compared. Therefore, the finding of this research paper will show that SVC can stabilize the voltage profile of a power flow system.
{"title":"Improvement of Voltage Stability in Power System using SVC","authors":"Amirul Hakim Ramli, N. A. M. Leh, Shabinar Abdul Hamid, Z. Muhammad","doi":"10.1109/ICCSCE54767.2022.9935625","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935625","url":null,"abstract":"The increased demand for electricity has pushed the electrical grid closer to its stability limit. Due to many methods used to enhance the power system, voltage instability and line overloading have become a difficulty. The creation, transmission, and consumption of reactive power can all be used to investigate the nature of voltage stability. Reactive power unbalancing, which happens when the power system is strained, is one of the key reasons of voltage instability. Flexible AC transmission system (FACTS) devices are vital for enhancing the performance of a power system, but they are also quite expensive, thus they must be placed optimally in the power system. Static var compensator (SVC), a FACTS device, can be used to minimise flows in densely laden lines, resulting in minimal system loss and enhanced voltage stability. A method is proposed based on the index of line stability and overall system of VAR power losses was used to select the best position for the SVC device. Using VSI calculation on the power flow system, the weakest bus will be determined and will be assign as the optimal location for SVC. Also, along with this paper an observation on a power flow system with and without SVC are compared. Therefore, the finding of this research paper will show that SVC can stabilize the voltage profile of a power flow system.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129340634","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 : 2022-10-21DOI: 10.1109/ICCSCE54767.2022.9935644
A. I. Tajudin, Muhammad Affi Daneal Izani, A. Samat, S. Omar, M. A. Idin
The project purpose to implement Artificial Bee Colony (ABC) algorithm optimization technique for controlling the speed of the DC motor. The separately excited DC motor had been used to analyze the performance of the proposed technique. The boost converter has been selected to supply the required voltage to the terminal voltage of the DC motor. The PID controller was selected to control the desired performance of the converter. The determination of the best parameter is the main issue for this controller. The ABC algorithm was implemented to enhance the system performance by optimizing the PID gains. The objective function of error which is Integral-weight Time Absolute Error (ITAE) was used to minimize the index speed error of the motor. The proposed technique shows its capability to improve the speed response of the DC motor. Simulation model was developed using MATLAB/Simulink.
{"title":"Design a Speed Control for DC Motor Using an Optimal PID Controller Implementation of ABC Algorithm","authors":"A. I. Tajudin, Muhammad Affi Daneal Izani, A. Samat, S. Omar, M. A. Idin","doi":"10.1109/ICCSCE54767.2022.9935644","DOIUrl":"https://doi.org/10.1109/ICCSCE54767.2022.9935644","url":null,"abstract":"The project purpose to implement Artificial Bee Colony (ABC) algorithm optimization technique for controlling the speed of the DC motor. The separately excited DC motor had been used to analyze the performance of the proposed technique. The boost converter has been selected to supply the required voltage to the terminal voltage of the DC motor. The PID controller was selected to control the desired performance of the converter. The determination of the best parameter is the main issue for this controller. The ABC algorithm was implemented to enhance the system performance by optimizing the PID gains. The objective function of error which is Integral-weight Time Absolute Error (ITAE) was used to minimize the index speed error of the motor. The proposed technique shows its capability to improve the speed response of the DC motor. Simulation model was developed using MATLAB/Simulink.","PeriodicalId":346014,"journal":{"name":"2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131062849","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：