Pub Date : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535609
Hasan Qayyum Chohan, I. Ahmad
Oil shale retorting process is conversion of kerogen shale particles into oil and gas. Uncertainties present in process variables challenge the plant operation design of oil shale retorting process. In this work, the effect of uncertainties present in various input variables is studied on shale oil yield and flue gases. This study is focused on evaluation of most sensitive input variables that affect the oil yield. Oil shale retorting plant data is generated through interfacing of Aspen Plus, MS Excel 2010 and MATLAB R2018a. Least square boosting (LSBoost) model was used for virtual sensing of generated data and predicted the target outputs. Sensitivity analysis was performed using Sobol and Fourier amplitude sensitivity test to evaluate the effect of individual input variable on target outcomes of the process.
{"title":"Sensitivity Analysis of Oil Shale Retorting Process through Sobol and Fourier Amplitude Sensitivity Test (FAST)","authors":"Hasan Qayyum Chohan, I. Ahmad","doi":"10.1109/EUROCON52738.2021.9535609","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535609","url":null,"abstract":"Oil shale retorting process is conversion of kerogen shale particles into oil and gas. Uncertainties present in process variables challenge the plant operation design of oil shale retorting process. In this work, the effect of uncertainties present in various input variables is studied on shale oil yield and flue gases. This study is focused on evaluation of most sensitive input variables that affect the oil yield. Oil shale retorting plant data is generated through interfacing of Aspen Plus, MS Excel 2010 and MATLAB R2018a. Least square boosting (LSBoost) model was used for virtual sensing of generated data and predicted the target outputs. Sensitivity analysis was performed using Sobol and Fourier amplitude sensitivity test to evaluate the effect of individual input variable on target outcomes of the process.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121143632","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535574
Jasten K. D. Treceñe
In the present time, leaf disease is one of the major problems of Brassicaceae vegetables in the agriculture domain as it affects the quality and quantity of the vegetables. The most common leaf disease of these vegetables is downy mildew, blight leaf disease, and leaf spot. This paper mainly considers identifying the diseased region of the leaves using the image segmentation technique and presents experimentation of the desired number of clusters k. To address the objectives, image acquisition, pre-processing, segmentation, and emphasizing the affected portion of the leaves are all part of the process of the proposed method. The images were transformed into grayscale and removed from the background using Otsu’s thresholding method. K-means clustering algorithm was applied to segment the different regions of the sample images. Finally, the clustered images were then analyzed using a median filter to emphasize the region of interest of the affected leaves. With the different number of clusters k used, k = 4 was successfully segmented the diseased portion, and it was confirmed by the elbow method. Further, the infected area of the sample images was presented in different colors. Also, the proposed method provides a 96.90% accuracy compared to other image segmentation techniques. Image segmentation has become an effective tool in various applications in the agricultural sector.
叶片病害是目前十字花科蔬菜在农业领域面临的主要问题之一，它影响着蔬菜的质量和数量。这些蔬菜最常见的叶病是霜霉病、叶枯病和叶斑病。本文主要考虑使用图像分割技术识别叶片的病变区域，并给出了所需簇数k的实验。为了实现目标，图像采集、预处理、分割和强调叶片的病变部分都是本文提出的方法的一部分。利用Otsu阈值法将图像转换成灰度后从背景中去除。采用K-means聚类算法对样本图像的不同区域进行分割。最后，使用中值滤波器对聚类图像进行分析，以强调受影响叶片的感兴趣区域。使用不同簇数k, k = 4成功分割病变部分，并通过肘部法进行确认。此外，样本图像的感染区域以不同的颜色呈现。与其他图像分割技术相比，该方法的分割准确率为96.90%。图像分割已成为农业领域各种应用的有效工具。
{"title":"Brassicaceae Leaf Disease Detection using Image Segmentation Technique","authors":"Jasten K. D. Treceñe","doi":"10.1109/EUROCON52738.2021.9535574","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535574","url":null,"abstract":"In the present time, leaf disease is one of the major problems of Brassicaceae vegetables in the agriculture domain as it affects the quality and quantity of the vegetables. The most common leaf disease of these vegetables is downy mildew, blight leaf disease, and leaf spot. This paper mainly considers identifying the diseased region of the leaves using the image segmentation technique and presents experimentation of the desired number of clusters k. To address the objectives, image acquisition, pre-processing, segmentation, and emphasizing the affected portion of the leaves are all part of the process of the proposed method. The images were transformed into grayscale and removed from the background using Otsu’s thresholding method. K-means clustering algorithm was applied to segment the different regions of the sample images. Finally, the clustered images were then analyzed using a median filter to emphasize the region of interest of the affected leaves. With the different number of clusters k used, k = 4 was successfully segmented the diseased portion, and it was confirmed by the elbow method. Further, the infected area of the sample images was presented in different colors. Also, the proposed method provides a 96.90% accuracy compared to other image segmentation techniques. Image segmentation has become an effective tool in various applications in the agricultural sector.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116054315","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535592
T. Majoros, S. Oniga
Brain-computer interface (BCI) is widely used in several clinical applications. Motor imagery-based BCI can help patients who have lost their motor functions in communication and rehabilitation. To develop such BCI applications, the accurate classification of motor-imagery based electroencephalography (EEG) is crucial. By processing a publicly available EEG dataset, we obtained information that can be used to train neural networks and efficiently classify activities performed by volunteers. In this paper we used several data pre-processing methods and examined how they affect the classification performance of a feedforward neural network. As the results were not satisfactory with the feedforward network, the data prepared with the best pre-processing method were also used to train a convolutional neural network (CNN). We achieved an accuracy of 91.27% in classifying fists and feet closing activities using data from ten volunteers.
{"title":"Comparison of Motor Imagery EEG Classification using Feedforward and Convolutional Neural Network","authors":"T. Majoros, S. Oniga","doi":"10.1109/EUROCON52738.2021.9535592","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535592","url":null,"abstract":"Brain-computer interface (BCI) is widely used in several clinical applications. Motor imagery-based BCI can help patients who have lost their motor functions in communication and rehabilitation. To develop such BCI applications, the accurate classification of motor-imagery based electroencephalography (EEG) is crucial. By processing a publicly available EEG dataset, we obtained information that can be used to train neural networks and efficiently classify activities performed by volunteers. In this paper we used several data pre-processing methods and examined how they affect the classification performance of a feedforward neural network. As the results were not satisfactory with the feedforward network, the data prepared with the best pre-processing method were also used to train a convolutional neural network (CNN). We achieved an accuracy of 91.27% in classifying fists and feet closing activities using data from ten volunteers.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116213218","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535617
M. Zellagui, N. Belbachir, C. El‐Bayeh
Recently, the installation of Renewable Distributed Generation (RDG) into the Electrical Distribution System (EDS) became one of the best solutions that guarantee the balance between electric energy consumption and production, also show various advantages. In addition to delivering clean energy, they contribute to minimizing power losses, as well as enhancing the voltage profiles. In this paper, the metaheuristic optimization algorithm of the Grey Wolf Optimizer (GWO) is utilized to optimally allocate the RDG based multiple PV and WT units into EDS considering the uncertainty of electrical output energy from the RDGs as well as load demand variation during all seasons. The Multi-Objective Functions (MOF) developed in this paper is considered to minimize simultaneous the indices of the total of Active Power Loss Index (APLI), the Reactive Power Loss Index (RPLI), the Voltage Deviation Index (VDI), the Operation Time Index (OTI) of the overcurrent relay (OCR), and enhance the Coordination Time Interval Index (CTII) of the overcurrent relays installed in the test system which is the IEEE 33-bus EDS.
{"title":"Optimal Allocation of RDG in Distribution System Considering the Seasonal Uncertainties of Load Demand and Solar-Wind Generation Systems","authors":"M. Zellagui, N. Belbachir, C. El‐Bayeh","doi":"10.1109/EUROCON52738.2021.9535617","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535617","url":null,"abstract":"Recently, the installation of Renewable Distributed Generation (RDG) into the Electrical Distribution System (EDS) became one of the best solutions that guarantee the balance between electric energy consumption and production, also show various advantages. In addition to delivering clean energy, they contribute to minimizing power losses, as well as enhancing the voltage profiles. In this paper, the metaheuristic optimization algorithm of the Grey Wolf Optimizer (GWO) is utilized to optimally allocate the RDG based multiple PV and WT units into EDS considering the uncertainty of electrical output energy from the RDGs as well as load demand variation during all seasons. The Multi-Objective Functions (MOF) developed in this paper is considered to minimize simultaneous the indices of the total of Active Power Loss Index (APLI), the Reactive Power Loss Index (RPLI), the Voltage Deviation Index (VDI), the Operation Time Index (OTI) of the overcurrent relay (OCR), and enhance the Coordination Time Interval Index (CTII) of the overcurrent relays installed in the test system which is the IEEE 33-bus EDS.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122854419","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535540
M. Gutnyk, E. Tverytnykova, S. Radohuz, I. Krylenko, Svitlana Tkachenko
The information about the general situation of the Kharkiv city at the end of XIX – at the beginning of the XX century is presented. In particular, it is illustrated which enterprises, railways and institutes were functioned in that time. The information about events preceded to the opening in Kharkiv Practical Technological Institute is pointed. The contribution of the scientists of this institute to the electrification of the Kharkiv city is considered. On the basis of documents from Archives, the existing information about the scientific activities by Oleksandr Pogorelko, Pavlo Kopniaev, Mykola Pilchikov, Mykola Klobukov was supplemented and corrected. The expert activity of these scientists is shown. It is stated that the mentioned scientists were at the origins of the electrotechnical education of Ukraine.
{"title":"The Electrification of Kharkiv City at the End of ХIX – at the Beginning of ХX Century","authors":"M. Gutnyk, E. Tverytnykova, S. Radohuz, I. Krylenko, Svitlana Tkachenko","doi":"10.1109/EUROCON52738.2021.9535540","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535540","url":null,"abstract":"The information about the general situation of the Kharkiv city at the end of XIX – at the beginning of the XX century is presented. In particular, it is illustrated which enterprises, railways and institutes were functioned in that time. The information about events preceded to the opening in Kharkiv Practical Technological Institute is pointed. The contribution of the scientists of this institute to the electrification of the Kharkiv city is considered. On the basis of documents from Archives, the existing information about the scientific activities by Oleksandr Pogorelko, Pavlo Kopniaev, Mykola Pilchikov, Mykola Klobukov was supplemented and corrected. The expert activity of these scientists is shown. It is stated that the mentioned scientists were at the origins of the electrotechnical education of Ukraine.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"602 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123203726","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535577
Osman Rasit Kultur, H. Ş. Bilge
Aircraft have many sensors and modules scattered throughout their fuselage. Due to the ever-increasing sensor load (radar, electronic warfare, radio, camera, etc.), aircraft need more bandwidth and higher broadband communication backbones. Legacy protocols such as ARINC-429 and MIL-STD-1553 used in the communication of these modules are insufficient to meet the increased bandwidth requirements of today’s aircraft. However, these legacy networks are highly reliable and deterministic, as avionics systems require. For this reason, different technologies have been developed without losing their quality of service and suitability for critical systems. Avionics Full-Duplex Switched Ethernet (AFDX) protocol, a special application of ARINC-664 Part 7, patented by Airbus, has come to the fore in recent years. Another prominent solution is the Time-Triggered Ethernet (TTEthernet) protocol, patented by TTTech. This paper compares these two protocols from the avionics perspective with a simulation model in OMNET++ and outlooks the new generation avionics networks.
飞机的机身上散布着许多传感器和模块。由于不断增加的传感器负载(雷达、电子战、无线电、相机等)，飞机需要更多的带宽和更高的宽带通信骨干。这些模块通信中使用的arinc429和MIL-STD-1553等传统协议不足以满足当今飞机日益增加的带宽需求。然而，这些传统网络是高度可靠和确定性的，因为航空电子系统需要。由于这个原因，开发了不同的技术，但不会失去其服务质量和对关键系统的适用性。航空电子全双工交换以太网(AFDX)协议是ARINC-664 Part 7的一种特殊应用，由空客公司申请专利，近年来已经崭露头角。另一个著名的解决方案是Time-Triggered以太网(TTEthernet)协议,由TTTech专利。本文从航电的角度对这两种协议进行了比较，并在omnet++中建立了仿真模型，对新一代航电网络进行了展望。
{"title":"Comparative Analysis of Next Generation Aircraft Data Networks","authors":"Osman Rasit Kultur, H. Ş. Bilge","doi":"10.1109/EUROCON52738.2021.9535577","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535577","url":null,"abstract":"Aircraft have many sensors and modules scattered throughout their fuselage. Due to the ever-increasing sensor load (radar, electronic warfare, radio, camera, etc.), aircraft need more bandwidth and higher broadband communication backbones. Legacy protocols such as ARINC-429 and MIL-STD-1553 used in the communication of these modules are insufficient to meet the increased bandwidth requirements of today’s aircraft. However, these legacy networks are highly reliable and deterministic, as avionics systems require. For this reason, different technologies have been developed without losing their quality of service and suitability for critical systems. Avionics Full-Duplex Switched Ethernet (AFDX) protocol, a special application of ARINC-664 Part 7, patented by Airbus, has come to the fore in recent years. Another prominent solution is the Time-Triggered Ethernet (TTEthernet) protocol, patented by TTTech. This paper compares these two protocols from the avionics perspective with a simulation model in OMNET++ and outlooks the new generation avionics networks.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127505354","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535556
Arturs Kempelis, A. Romānovs, A. Patlins
The use of IoT networks to facilitate agricultural processes has been developing rapidly in recent years, as it makes possible to make these processes more efficient with tools for monitoring and analyzing sensor data and helping farmers to make decisions. However, there are also a number of challenges in implementing IoT networks, like designing, developing, and testing these networks so they are also sufficiently secure. Within this paper, food production processes in agriculture are studied and it is described how various technologies and sensors can be integrated into these processes, which could facilitate the management and execution of these processes. Within this paper, a secure and scalable IoT network is designed, developed, and tested with the help of open-hardware prototyping devices and open-source tools. At the end of the paper, the results are summarized and the benefits of using IoT network in agriculture are formulated to provide recommendations.
{"title":"Design and Implementation of IoT Network Prototype to Facilitate the Food Production Process in Agriculture","authors":"Arturs Kempelis, A. Romānovs, A. Patlins","doi":"10.1109/EUROCON52738.2021.9535556","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535556","url":null,"abstract":"The use of IoT networks to facilitate agricultural processes has been developing rapidly in recent years, as it makes possible to make these processes more efficient with tools for monitoring and analyzing sensor data and helping farmers to make decisions. However, there are also a number of challenges in implementing IoT networks, like designing, developing, and testing these networks so they are also sufficiently secure. Within this paper, food production processes in agriculture are studied and it is described how various technologies and sensors can be integrated into these processes, which could facilitate the management and execution of these processes. Within this paper, a secure and scalable IoT network is designed, developed, and tested with the help of open-hardware prototyping devices and open-source tools. At the end of the paper, the results are summarized and the benefits of using IoT network in agriculture are formulated to provide recommendations.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122253405","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535552
Siddharth Gupta, A. Panwar, Kishor Mishra
Skin is one of the very important and largest organs of the human body that helps in regulating the body temperature and is responsible for sensations such as feel, touch, hot and cold. These days, skin problems are very common in day-to-day life. There may be many reasons for skin diseases: unbalanced and impure diet, several types of pollutions, or maybe family heredity. However, if skin disease after a long treatment does not show any sign of improvement or the skin cells grow abnormally, this may lead to skin cancer. There are many forms of skin cancer. For early and timely diagnosis of skin cancer, an efficient technique is required at utmost importance. Many people across the globe lost their lives due to the late diagnosis. Therefore, a technique that is cost-effective, quicker, and easily accessible needs a higher demand. These days for the classification of images, machine learning, and deep learning techniques proved to be the most efficient approach. In this paper, the dataset of several images of a benign and malignant tumor was taken and pre-processed. Once all the images were pre-processed, they are ready to fed in several CNN models. These models extract the features and pass the images to several machine learning classifiers for the classification of moles as benign or malignant. The results verify by using the classification approach it becomes very much easy for the dermatologist to easily detect the lesions and provide the appropriate treatment to the patient to save the life.
{"title":"Skin Disease Classification using Dermoscopy Images through Deep Feature Learning Models and Machine Learning Classifiers","authors":"Siddharth Gupta, A. Panwar, Kishor Mishra","doi":"10.1109/EUROCON52738.2021.9535552","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535552","url":null,"abstract":"Skin is one of the very important and largest organs of the human body that helps in regulating the body temperature and is responsible for sensations such as feel, touch, hot and cold. These days, skin problems are very common in day-to-day life. There may be many reasons for skin diseases: unbalanced and impure diet, several types of pollutions, or maybe family heredity. However, if skin disease after a long treatment does not show any sign of improvement or the skin cells grow abnormally, this may lead to skin cancer. There are many forms of skin cancer. For early and timely diagnosis of skin cancer, an efficient technique is required at utmost importance. Many people across the globe lost their lives due to the late diagnosis. Therefore, a technique that is cost-effective, quicker, and easily accessible needs a higher demand. These days for the classification of images, machine learning, and deep learning techniques proved to be the most efficient approach. In this paper, the dataset of several images of a benign and malignant tumor was taken and pre-processed. Once all the images were pre-processed, they are ready to fed in several CNN models. These models extract the features and pass the images to several machine learning classifiers for the classification of moles as benign or malignant. The results verify by using the classification approach it becomes very much easy for the dermatologist to easily detect the lesions and provide the appropriate treatment to the patient to save the life.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117193278","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535636
A. Diker
The brain tumor classification and detection are significant problems in computer-assisted diagnosis (CAD) for medical applications. In this study, the performance comparison of pre-trained deep learning models which are AlexNet, GoogleNet ,and ResNet-18 for the classification of brain MRI images was made. The performances of these models are compared with each other. Experimental results show that the AlexNet model achieves the highest accuracy at 96%. It is followed by the GoogleNet and ResNet-18 model with an accuracy of 90.66% and 88% respectively.
{"title":"A Performance Comparison of Pre-trained Deep Learning Models to Classify Brain Tumor","authors":"A. Diker","doi":"10.1109/EUROCON52738.2021.9535636","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535636","url":null,"abstract":"The brain tumor classification and detection are significant problems in computer-assisted diagnosis (CAD) for medical applications. In this study, the performance comparison of pre-trained deep learning models which are AlexNet, GoogleNet ,and ResNet-18 for the classification of brain MRI images was made. The performances of these models are compared with each other. Experimental results show that the AlexNet model achieves the highest accuracy at 96%. It is followed by the GoogleNet and ResNet-18 model with an accuracy of 90.66% and 88% respectively.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134540318","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535564
A. Khan, S. Zubair, Samreen Khan
Detection and prediction of Alzheimer's Disease (AD) conversion from the stage of Mild Cognitive Impairment (MCI) have remained a challenging task. Regression analysis is a method that sorts those essential features/biomarkers that have a strong impact on the overall prediction. This study centres on delivering an individualized regression analysis of cognitively normal and MCI converts over the twenty independent biomarkers that leverage clinical data. Out of the 1713 male and female subjects, 768 female subjects were studied to investigate the prevalence of AD and MCI, those diagnosed with AD and MCI and their associated risk factors. The study data were gathered from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Twenty potential clinical features were included; comprised of a combination of demographic, cerebral spinal fluid, cognitive, diffusion tensor imaging, electroencephalography, genetic, magnetic resonance imaging, and positron emission tomography testing variables. The regression analysis metrics R-squared, F-statistic, Omnibus, Durbin-Watson, Coefficient and Standard error, were used to evaluate the model. Our results showed that cognitive assessment metrics were highly significant among the other testing biomarkers. Additionally, we determined the significance of each clinical variable. Our performed analysis could impact the clinical setting as a means to further develop a machine learning model in predicting the conversion of MCI to AD or to detect principle subjects for clinical trials.
{"title":"An Epidemiological-based Regression Analysis of Alzheimer’s disease and Mild Cognitive Impairment Converts in the Female Population","authors":"A. Khan, S. Zubair, Samreen Khan","doi":"10.1109/EUROCON52738.2021.9535564","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535564","url":null,"abstract":"Detection and prediction of Alzheimer's Disease (AD) conversion from the stage of Mild Cognitive Impairment (MCI) have remained a challenging task. Regression analysis is a method that sorts those essential features/biomarkers that have a strong impact on the overall prediction. This study centres on delivering an individualized regression analysis of cognitively normal and MCI converts over the twenty independent biomarkers that leverage clinical data. Out of the 1713 male and female subjects, 768 female subjects were studied to investigate the prevalence of AD and MCI, those diagnosed with AD and MCI and their associated risk factors. The study data were gathered from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Twenty potential clinical features were included; comprised of a combination of demographic, cerebral spinal fluid, cognitive, diffusion tensor imaging, electroencephalography, genetic, magnetic resonance imaging, and positron emission tomography testing variables. The regression analysis metrics R-squared, F-statistic, Omnibus, Durbin-Watson, Coefficient and Standard error, were used to evaluate the model. Our results showed that cognitive assessment metrics were highly significant among the other testing biomarkers. Additionally, we determined the significance of each clinical variable. Our performed analysis could impact the clinical setting as a means to further develop a machine learning model in predicting the conversion of MCI to AD or to detect principle subjects for clinical trials.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132871637","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：