Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187378
Daniel Dietsche, T. E. Dettling, C. Trefftz, Byron DeVries
While Voronoi diagrams are used in a wide range of applications, leading algorithms (e.g., Fortune's algorithm) are limited to two-dimensional Voronoi diagrams. Problematically, many of the space-dividing applications of Voronoi diagrams exist in three-dimensional spaces rather than two-dimensional spaces. While two-dimensional Voronoi diagrams have been used in cases where three-dimensional space can be simplified to two-dimensional space with an acceptable loss of precision, such simplification is not always feasible. In this paper we extend existing work on divide-and-conquer algorithms for computing two-dimensional discretized Voronoi diagrams by introducing and comparing two novel algorithms for calculating three-dimensional discretized Voronoi diagrams. A comparison of the two algorithms is presented for a range of both space sizes and number of sites.
{"title":"Divide-and-Conquer Algorithms for Computing Three-Dimensional Voronoi Diagrams","authors":"Daniel Dietsche, T. E. Dettling, C. Trefftz, Byron DeVries","doi":"10.1109/eIT57321.2023.10187378","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187378","url":null,"abstract":"While Voronoi diagrams are used in a wide range of applications, leading algorithms (e.g., Fortune's algorithm) are limited to two-dimensional Voronoi diagrams. Problematically, many of the space-dividing applications of Voronoi diagrams exist in three-dimensional spaces rather than two-dimensional spaces. While two-dimensional Voronoi diagrams have been used in cases where three-dimensional space can be simplified to two-dimensional space with an acceptable loss of precision, such simplification is not always feasible. In this paper we extend existing work on divide-and-conquer algorithms for computing two-dimensional discretized Voronoi diagrams by introducing and comparing two novel algorithms for calculating three-dimensional discretized Voronoi diagrams. A comparison of the two algorithms is presented for a range of both space sizes and number of sites.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125799295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187290
Zongguang Liu, Myoungkuk Park, J. Bae
This paper proposes a heuristic that optimizes the task completion time for heterogeneous multi-robot systems operating in various real-world applications such as transportation, surveillance, and monitoring. Focusing on transportation missions in manufacturing or warehouse environments, the heuristic aims to find a tour for each robot that departs from distinctive depots completes all assigned tasks, and returns to the depot while minimizing the last task completion time. Building on previous work, the newly developed algorithm can solve more generalized problems, which involve required minimum payload restrictions on each task. The heterogeneous multi-robot systems consist of robots with different average running speeds and maximum payloads. The proposed heuristic considers workload balancing between the robots to provide a feasible solution satisfying all constraints. To validate the approach, the algorithm is tested repeatedly in simulation, varying problem sizes. The results show that the heuristic produces good-quality solutions within a reasonable computation time, demonstrating the potential for real-time implementation. Performance metrics used for evaluation include the objective function value and computation time.
{"title":"A Heuristic for Multiple Heterogeneous Mobile Robots Task Assignment under Various Loading Conditions considering Workload Balance","authors":"Zongguang Liu, Myoungkuk Park, J. Bae","doi":"10.1109/eIT57321.2023.10187290","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187290","url":null,"abstract":"This paper proposes a heuristic that optimizes the task completion time for heterogeneous multi-robot systems operating in various real-world applications such as transportation, surveillance, and monitoring. Focusing on transportation missions in manufacturing or warehouse environments, the heuristic aims to find a tour for each robot that departs from distinctive depots completes all assigned tasks, and returns to the depot while minimizing the last task completion time. Building on previous work, the newly developed algorithm can solve more generalized problems, which involve required minimum payload restrictions on each task. The heterogeneous multi-robot systems consist of robots with different average running speeds and maximum payloads. The proposed heuristic considers workload balancing between the robots to provide a feasible solution satisfying all constraints. To validate the approach, the algorithm is tested repeatedly in simulation, varying problem sizes. The results show that the heuristic produces good-quality solutions within a reasonable computation time, demonstrating the potential for real-time implementation. Performance metrics used for evaluation include the objective function value and computation time.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123439401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187348
D. Möller, H. Vakilzadian
The increasing number and effectiveness of cyber-attacks and data breaches adversely affect infrastructure systems by exploiting their vulnerabilities. Cyber-attacks on critical infrastructure sometimes undermine safe operations or cause complete shutdowns. Therefore, identifying and evaluating the actual status of infrastructure system processes for critical assets in advance requires analyzing the actual cybersecurity status to protect them from potential cyber-attacks and data breaches. So far, the information deficit about cybersecurity awareness in the infrastructure systems sector exists. International studies are more broadly designed, but not directly focused on gaining detailed knowledge about cybersecurity defense's status quo in the infrastructure system sector. Therefore, strategic steps are required to secure the infrastructure systems against cyber-attacks and vulnerabilities. This includes developing and implementing procedures to improve cyber-attack detection and eliminate system vulnerabilities. In this regard, a maturity level model as a specific analysis method of the actual cybersecurity status of the infrastructure system is introduced to gain knowledge about how to achieve the desired to-be-cybersecurity status against the actual status, as a best practice example is provided for a rail system. This paper describes the cybersecurity risk of digitization in the railway sector as a use case.
{"title":"Cybersecurity Risk in Digitalization of Infrastructure Systems: A Use Case","authors":"D. Möller, H. Vakilzadian","doi":"10.1109/eIT57321.2023.10187348","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187348","url":null,"abstract":"The increasing number and effectiveness of cyber-attacks and data breaches adversely affect infrastructure systems by exploiting their vulnerabilities. Cyber-attacks on critical infrastructure sometimes undermine safe operations or cause complete shutdowns. Therefore, identifying and evaluating the actual status of infrastructure system processes for critical assets in advance requires analyzing the actual cybersecurity status to protect them from potential cyber-attacks and data breaches. So far, the information deficit about cybersecurity awareness in the infrastructure systems sector exists. International studies are more broadly designed, but not directly focused on gaining detailed knowledge about cybersecurity defense's status quo in the infrastructure system sector. Therefore, strategic steps are required to secure the infrastructure systems against cyber-attacks and vulnerabilities. This includes developing and implementing procedures to improve cyber-attack detection and eliminate system vulnerabilities. In this regard, a maturity level model as a specific analysis method of the actual cybersecurity status of the infrastructure system is introduced to gain knowledge about how to achieve the desired to-be-cybersecurity status against the actual status, as a best practice example is provided for a rail system. This paper describes the cybersecurity risk of digitization in the railway sector as a use case.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126284390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187340
Md Shahin Alam, Il-Seop Shin, S. A. Arefifar
Global warming has become a serious issue throughout the entire world. It is mainly caused by environmental pollution from burning fossil fuels. According to the California Air Resources Board, transportation is the state's single largest source of global warming emissions and air pollution. The policymakers proposed a plan that 100% of new cars and light trucks sold in California would be zero-emission vehicles, such as electric vehicles (EVs), by 2035. In this scenario, finding optimal locations of EV charging stations (EVCSs) is highly manifested to support transition to EVs from internal combustion engine vehicles. EV integration into the existing power distribution system will help reduce not only environmental emissions but also operational costs for the utility companies, which leads to financial incentives for the EV owners and general public. This research presents ideas of identifying the optimal locations, finding appropriate charging capacities based on the types of vehicles, and improving operational performance of distribution systems. In addition, EVCSs can work in a hybrid manner where electricity is provided by utilities, solar energy, and energy storage units. By adopting the concept of microgrids, EV owners charge their vehicles during off-peak hours and unload the energy back to the grid during peak hours at higher prices. Utility companies utilize the energy to further reduce their dependency on fossil fuels to provide electricity. The PG&E 69-bus distribution system is used to find the optimal location of charging stations. The operational costs and emissions are evaluated to improve the operational performance.
{"title":"Optimal Allocation of EV Charging Stations to Support Vast Internal Combustion Engine Vehicle Replacement","authors":"Md Shahin Alam, Il-Seop Shin, S. A. Arefifar","doi":"10.1109/eIT57321.2023.10187340","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187340","url":null,"abstract":"Global warming has become a serious issue throughout the entire world. It is mainly caused by environmental pollution from burning fossil fuels. According to the California Air Resources Board, transportation is the state's single largest source of global warming emissions and air pollution. The policymakers proposed a plan that 100% of new cars and light trucks sold in California would be zero-emission vehicles, such as electric vehicles (EVs), by 2035. In this scenario, finding optimal locations of EV charging stations (EVCSs) is highly manifested to support transition to EVs from internal combustion engine vehicles. EV integration into the existing power distribution system will help reduce not only environmental emissions but also operational costs for the utility companies, which leads to financial incentives for the EV owners and general public. This research presents ideas of identifying the optimal locations, finding appropriate charging capacities based on the types of vehicles, and improving operational performance of distribution systems. In addition, EVCSs can work in a hybrid manner where electricity is provided by utilities, solar energy, and energy storage units. By adopting the concept of microgrids, EV owners charge their vehicles during off-peak hours and unload the energy back to the grid during peak hours at higher prices. Utility companies utilize the energy to further reduce their dependency on fossil fuels to provide electricity. The PG&E 69-bus distribution system is used to find the optimal location of charging stations. The operational costs and emissions are evaluated to improve the operational performance.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133785170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187294
B. Morshed, Moriom R. Momota, Tomoko Fujiwara
Electrical energy storage need has evolved to lightweight and portable devices such as electric vehicle, drones, robotics, wearables, etc. Current technology of batteries such as Li-Ion or Li-Poly are not able to meet the requirement for future. We have been developing a new type of supercapacitor for this technological barrier. Our supercapacitors are fabricated with inkjet-printing (IJP) technique that uses very precise MEMS based cartridge to print thin-films on planar substrates. We have previously demonstrated metal-insulator-metal (MIM) capacitor fabrication and simulation, as well as stacked MIM supercapacitor fabrication. In this paper, we present electrical characterization (such as charging-discharging cycles) and scanning electron microscopy image for IJP stacked MIM supercapacitor. The electrical characterization validates the charge storage capability of the supercapacitor. We have tested the samples for up to 20 V charging voltage. The corresponding stored charge can be as high as 40 nC, and the charge density is 17.4 $mathbf{C}/mathbf{m}^{3}$. These solid-state IJP stacked MIM supercapacitors are flexible with high energy-density and safe for prolonged use which can be applicable in electric vehicles, wearables, implantable, drones, and other energy storage applications.
{"title":"Characterization of Inkjet-Printed Stacked MIM Thin-film Solid-State Flexible Super-Capacitor","authors":"B. Morshed, Moriom R. Momota, Tomoko Fujiwara","doi":"10.1109/eIT57321.2023.10187294","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187294","url":null,"abstract":"Electrical energy storage need has evolved to lightweight and portable devices such as electric vehicle, drones, robotics, wearables, etc. Current technology of batteries such as Li-Ion or Li-Poly are not able to meet the requirement for future. We have been developing a new type of supercapacitor for this technological barrier. Our supercapacitors are fabricated with inkjet-printing (IJP) technique that uses very precise MEMS based cartridge to print thin-films on planar substrates. We have previously demonstrated metal-insulator-metal (MIM) capacitor fabrication and simulation, as well as stacked MIM supercapacitor fabrication. In this paper, we present electrical characterization (such as charging-discharging cycles) and scanning electron microscopy image for IJP stacked MIM supercapacitor. The electrical characterization validates the charge storage capability of the supercapacitor. We have tested the samples for up to 20 V charging voltage. The corresponding stored charge can be as high as 40 nC, and the charge density is 17.4 $mathbf{C}/mathbf{m}^{3}$. These solid-state IJP stacked MIM supercapacitors are flexible with high energy-density and safe for prolonged use which can be applicable in electric vehicles, wearables, implantable, drones, and other energy storage applications.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134447943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187383
Iman Yazdansepas, N. Houshangi
The robotics sector is experiencing unprecedented growth, driven by the increasing demand for household and assistive robots. These robots need to navigate autonomously between various rooms in a home. To achieve this, they must construct a map of their surroundings and accurately locate themselves within it. Identifying different rooms can enhance the robot's performance. In this study, Gmapping, a Simultaneous Localization and Mapping (SLAM) technique employing a LiDAR sensor, is utilized to generate an environmental map. This map serves as the training data for a Convolutional Neural Network (CNN) designed for room classification. Both simulation and real-world testing demonstrate the effectiveness of CNN in room classification tasks.
{"title":"Room Categorization utilizing Convolutional Neural Network on 2D map obtained by LiDAR","authors":"Iman Yazdansepas, N. Houshangi","doi":"10.1109/eIT57321.2023.10187383","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187383","url":null,"abstract":"The robotics sector is experiencing unprecedented growth, driven by the increasing demand for household and assistive robots. These robots need to navigate autonomously between various rooms in a home. To achieve this, they must construct a map of their surroundings and accurately locate themselves within it. Identifying different rooms can enhance the robot's performance. In this study, Gmapping, a Simultaneous Localization and Mapping (SLAM) technique employing a LiDAR sensor, is utilized to generate an environmental map. This map serves as the training data for a Convolutional Neural Network (CNN) designed for room classification. Both simulation and real-world testing demonstrate the effectiveness of CNN in room classification tasks.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133401599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187285
A. Ross, M. Das
Coordinated control of various actuators to maintain stability during emergency maneuvers is a major topic of automotive research. This paper discusses a particular approach for controlling and coordinating two electric motors in an electric all wheel drive powertrain (eAWD) during a double lane change maneuver. A two-tiered control scheme is implemented. The upper tier consists of the vehicle level controller which provides target tire forces to the motor controllers, which make up the lower tier. The controllers at the vehicle and motor levels employ a predictive one step ahead concept. The vehicle level controller integrates fuzzy rules to calculate target tire forces for the lower tier controller. This control scheme is implemented and simulated using Simulink and CarSim.
{"title":"Design of an Integrated Weighted One Step Ahead and Fuzzy Yaw Controller for an Electric AWD Powertrain","authors":"A. Ross, M. Das","doi":"10.1109/eIT57321.2023.10187285","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187285","url":null,"abstract":"Coordinated control of various actuators to maintain stability during emergency maneuvers is a major topic of automotive research. This paper discusses a particular approach for controlling and coordinating two electric motors in an electric all wheel drive powertrain (eAWD) during a double lane change maneuver. A two-tiered control scheme is implemented. The upper tier consists of the vehicle level controller which provides target tire forces to the motor controllers, which make up the lower tier. The controllers at the vehicle and motor levels employ a predictive one step ahead concept. The vehicle level controller integrates fuzzy rules to calculate target tire forces for the lower tier controller. This control scheme is implemented and simulated using Simulink and CarSim.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132695802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187387
Papia F. Rozario, E. Ruehmann, T. Pham, Tianqi Sun, Jacob Jensen, Hengrui Jia, Zhongyue Yu, Rahul Gomes
Classification of hyperspectral images is an important step of image interpretation from high spatial resolution imagery. Different studies demonstrate that spatial features can provide complementary information for increasing the accuracy of hyperspectral image classification. In this study, we evaluate different methods of spectral-spatial classification of hyperspectral images that are based on denoising methods using convolutional autoencoders. The resulting high-dimensional vectors of spectral features are classified by supervised algorithms such as support vector machine (SVM), maximum likelihood (ML), and random forest (RF). The experiments are performed on several widely known hyperspectral images that reveal a patch-based 3D convolutional autoencoder is more effective in reducing noise in the dataset and retaining spectral-spatial information. Random Forest classifier provides the highest classification accuracy across all the models.
{"title":"Deep Learning Patch-Based Approach for Hyperspectral Image Classification","authors":"Papia F. Rozario, E. Ruehmann, T. Pham, Tianqi Sun, Jacob Jensen, Hengrui Jia, Zhongyue Yu, Rahul Gomes","doi":"10.1109/eIT57321.2023.10187387","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187387","url":null,"abstract":"Classification of hyperspectral images is an important step of image interpretation from high spatial resolution imagery. Different studies demonstrate that spatial features can provide complementary information for increasing the accuracy of hyperspectral image classification. In this study, we evaluate different methods of spectral-spatial classification of hyperspectral images that are based on denoising methods using convolutional autoencoders. The resulting high-dimensional vectors of spectral features are classified by supervised algorithms such as support vector machine (SVM), maximum likelihood (ML), and random forest (RF). The experiments are performed on several widely known hyperspectral images that reveal a patch-based 3D convolutional autoencoder is more effective in reducing noise in the dataset and retaining spectral-spatial information. Random Forest classifier provides the highest classification accuracy across all the models.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114947325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187311
Todd A. Perkins, M. Das
To meet the ever-increasing emissions and economy standards of the past 50 years, vehicle manufacturers have turned to sophisticated electronic control of all aspects of the powertrain. One of the areas gaining interest during the past 20 years has been torque converter clutch engagement and expanding the conditions when it operates. Slip mode, when the clutch is partially locked, allows the torque converter to transmit power very efficiently through the clutch while allowing a small amount of power through the fluid coupler. Allowing the clutch to slip dampens the engine vibrations from the rest of the drivetrain by allowing the fluid coupler to absorb and dampen the impulse. This paper presents a new disturbance observer based control scheme for the torque converter clutch during slip mode. Also, the performance of the proposed control scheme is demonstrated using simulation studies.
{"title":"Modeling and Control of Torque Converter Clutch Using a Disturbance Observer based Tracking Controller","authors":"Todd A. Perkins, M. Das","doi":"10.1109/eIT57321.2023.10187311","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187311","url":null,"abstract":"To meet the ever-increasing emissions and economy standards of the past 50 years, vehicle manufacturers have turned to sophisticated electronic control of all aspects of the powertrain. One of the areas gaining interest during the past 20 years has been torque converter clutch engagement and expanding the conditions when it operates. Slip mode, when the clutch is partially locked, allows the torque converter to transmit power very efficiently through the clutch while allowing a small amount of power through the fluid coupler. Allowing the clutch to slip dampens the engine vibrations from the rest of the drivetrain by allowing the fluid coupler to absorb and dampen the impulse. This paper presents a new disturbance observer based control scheme for the torque converter clutch during slip mode. Also, the performance of the proposed control scheme is demonstrated using simulation studies.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116052910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187283
Rabia Emhamed Al Mamlook, Ahmad Nasayreh, Hasan Gharaibeh, Sujeet Shrestha
Glioblastoma multiforme (GBM) is a highly ma-lignant type of brain cancer with a bleak prognosis. This study aimed to apply machine learning methods to classify GBM samples from the Cancer Genome Atlas (TCGA) dataset. Several supervised learning algorithms, including Support Vector Machine, Ad boost, Neural Network, and Decision Tree, were employed in the analysis. Our findings indicate that the Decision Tree algorithm was the most effective for this classification task, achieving an impressive 99% accuracy. Our study provides evidence that machine learning can accurately classify GBM samples in large-scale genomic datasets, enabling a deeper understanding of the genomic characteristics of this cancer. This study emphasizes the potential of machine learning approaches for improved cancer diagnosis and treatment through the analysis of large-scale genomic datasets.
{"title":"Classification Of Cancer Genome Atlas Glioblastoma Multiform (TCGA-GBM) Using Machine Learning Method","authors":"Rabia Emhamed Al Mamlook, Ahmad Nasayreh, Hasan Gharaibeh, Sujeet Shrestha","doi":"10.1109/eIT57321.2023.10187283","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187283","url":null,"abstract":"Glioblastoma multiforme (GBM) is a highly ma-lignant type of brain cancer with a bleak prognosis. This study aimed to apply machine learning methods to classify GBM samples from the Cancer Genome Atlas (TCGA) dataset. Several supervised learning algorithms, including Support Vector Machine, Ad boost, Neural Network, and Decision Tree, were employed in the analysis. Our findings indicate that the Decision Tree algorithm was the most effective for this classification task, achieving an impressive 99% accuracy. Our study provides evidence that machine learning can accurately classify GBM samples in large-scale genomic datasets, enabling a deeper understanding of the genomic characteristics of this cancer. This study emphasizes the potential of machine learning approaches for improved cancer diagnosis and treatment through the analysis of large-scale genomic datasets.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130541302","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：