Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495878
Soufiane Dangoury, Saad Abouzahir, A. Alali, Mohammed Sadik
During last decade, Artificial Intelligence (AI) has been able to reshape our life daily. Different areas were positively impacted by AI such as Healthcare, Logistic, etc. Medical imaging is one of the fields of healthcare in which AI was introduced to solve and overcome different problems. Challenges including image processing, signal processing, and data acquisition. In this paper, we deeply demonstrate the loss function as one of the main parameters that influence the quality of the ultrasound (US) image. Therefore, we introduce the main components of ultrasound systems form end-to-end perspective such as the data acquisition, the signal processing, and the image interpretation. Then, we present the losses functions as a critical performance metrics for the model validation. Metrics such as the Mean Absolute Error (MAE), Cross-Entropy loss function (CE), Dice Similarity Coefficient (DSC), and the Structural Similarity (SSIM). After that we present the adopted CNN model to generate ultrasound image. The excessive simulation results demonstrate that the selection of the loss function provides significant improvement in terms of image quality (e.g., contrast, CNR and SNR). Choosing simple loss functions such as mean square error helps to faster the convergence of the convolution neural network during the training process. However, for image quality enhancement, we propose the combination of different loss functions such structural similarity (SSIM) with Dice Similarity Coefficient (DSC).
{"title":"Impacts of Losses Functions on the Quality of the Ultrasound Image by Using Machine Learning Algorithms","authors":"Soufiane Dangoury, Saad Abouzahir, A. Alali, Mohammed Sadik","doi":"10.1109/I2CACIS52118.2021.9495878","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495878","url":null,"abstract":"During last decade, Artificial Intelligence (AI) has been able to reshape our life daily. Different areas were positively impacted by AI such as Healthcare, Logistic, etc. Medical imaging is one of the fields of healthcare in which AI was introduced to solve and overcome different problems. Challenges including image processing, signal processing, and data acquisition. In this paper, we deeply demonstrate the loss function as one of the main parameters that influence the quality of the ultrasound (US) image. Therefore, we introduce the main components of ultrasound systems form end-to-end perspective such as the data acquisition, the signal processing, and the image interpretation. Then, we present the losses functions as a critical performance metrics for the model validation. Metrics such as the Mean Absolute Error (MAE), Cross-Entropy loss function (CE), Dice Similarity Coefficient (DSC), and the Structural Similarity (SSIM). After that we present the adopted CNN model to generate ultrasound image. The excessive simulation results demonstrate that the selection of the loss function provides significant improvement in terms of image quality (e.g., contrast, CNR and SNR). Choosing simple loss functions such as mean square error helps to faster the convergence of the convolution neural network during the training process. However, for image quality enhancement, we propose the combination of different loss functions such structural similarity (SSIM) with Dice Similarity Coefficient (DSC).","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117107978","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495876
Anjon S. Hernandez, A. Ballado, Aaron Paulo D. Heredia
Non-intrusive load monitoring is the process of recognizing and identifying electrical devices and its energy consumption on the entire electrical system through "power signatures". In this process, the aggregated load information is obtained from a single point of measurement. Compared with the traditional way of load identification by setting up multiple devices and sensors, the system uses only one energy measurement device, hence making it more efficient and economical. In this study, the focus was on designing a hardware that can obtain all power quality measurements, data analysis, and appliance identifier, which were analyzed by the microcontroller. The general information and introduction to the system, as well as the past and present literatures about the types of NILM System used by the researchers are presented. It was found that the combined unknown loads can be identified. Three different loads were analyzed at the same time from light bulb, electric fan and heater which gave 8-8.2W, 40-42W, and 238-249W respectively, all determined using a small-scale NILM system equipped with energy metering block and microcontroller that extracts and classifies loads with the use of support vector machine. This has a great significance to the industry and understanding of energy management since the demand for energy is growing rapidly.
{"title":"Development of a Non-Intrusive Load Monitoring (NILM) with Unknown Loads using Support Vector Machine","authors":"Anjon S. Hernandez, A. Ballado, Aaron Paulo D. Heredia","doi":"10.1109/I2CACIS52118.2021.9495876","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495876","url":null,"abstract":"Non-intrusive load monitoring is the process of recognizing and identifying electrical devices and its energy consumption on the entire electrical system through \"power signatures\". In this process, the aggregated load information is obtained from a single point of measurement. Compared with the traditional way of load identification by setting up multiple devices and sensors, the system uses only one energy measurement device, hence making it more efficient and economical. In this study, the focus was on designing a hardware that can obtain all power quality measurements, data analysis, and appliance identifier, which were analyzed by the microcontroller. The general information and introduction to the system, as well as the past and present literatures about the types of NILM System used by the researchers are presented. It was found that the combined unknown loads can be identified. Three different loads were analyzed at the same time from light bulb, electric fan and heater which gave 8-8.2W, 40-42W, and 238-249W respectively, all determined using a small-scale NILM system equipped with energy metering block and microcontroller that extracts and classifies loads with the use of support vector machine. This has a great significance to the industry and understanding of energy management since the demand for energy is growing rapidly.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115598126","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495856
M. M. Daud, Hanif Md. Saad, M. Ijab
Industrial workers are vulnerable to hazard and accidents. There could be many factors that contribute for these to occur including human error. Standard operating procedure and safety guideline have been set up to be followed by the workers with manual supervision where total adherence is required in a wide range of operation and hence, often lead to inefficiency. Thus, this work has proposed a preliminary work on safety monitoring within the potentially danger area to make the process to be efficient and reduce the manual supervision burden via deep learning. This work has adopted YOLO network for feature extraction and human detection in several monitoring areas. Then, counting module is executed to retrieve the data of how frequent the monitoring area is being interrupted. Prior to that, a region of interest (ROI) would be set up where human is detected only in the ROI. Lastly, measure the area of intersection between human and ROI to decide whether the subject is in the monitoring area or vice versa. The number of counts indicates the risk of accidents occur in the monitoring area. The higher the counts, the higher the risk in that region. This conceptual design can be extensively used in many ways for safety monitoring as it requires less supervision and becomes a safety measure by enforcing industrial safety in manufacturing sites.
{"title":"Conceptual Design of Human Detection via Deep Learning for Industrial Safety Enforcement in Manufacturing Site","authors":"M. M. Daud, Hanif Md. Saad, M. Ijab","doi":"10.1109/I2CACIS52118.2021.9495856","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495856","url":null,"abstract":"Industrial workers are vulnerable to hazard and accidents. There could be many factors that contribute for these to occur including human error. Standard operating procedure and safety guideline have been set up to be followed by the workers with manual supervision where total adherence is required in a wide range of operation and hence, often lead to inefficiency. Thus, this work has proposed a preliminary work on safety monitoring within the potentially danger area to make the process to be efficient and reduce the manual supervision burden via deep learning. This work has adopted YOLO network for feature extraction and human detection in several monitoring areas. Then, counting module is executed to retrieve the data of how frequent the monitoring area is being interrupted. Prior to that, a region of interest (ROI) would be set up where human is detected only in the ROI. Lastly, measure the area of intersection between human and ROI to decide whether the subject is in the monitoring area or vice versa. The number of counts indicates the risk of accidents occur in the monitoring area. The higher the counts, the higher the risk in that region. This conceptual design can be extensively used in many ways for safety monitoring as it requires less supervision and becomes a safety measure by enforcing industrial safety in manufacturing sites.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128705481","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495889
Alfiyah Shaldzabila Yustin, H. Nugroho, W. Wibowo
Currently CO2 gas emissions from conventional vehicles makes a big impact on global warming. One of the solutions is switch the technology from using the combustion engine into electric motor. Control method is needed to drive the electric motor hence the machine performance meets the design specifications. In this research, the unknown DC motor parameter was estimated using Matlab parameter estimation tools. Furthermore, the cascade PI control method with series connection was applied on DC motor that act as main actuator which regulates motor speed and its acceleration. The gain of two controller was tuned by using Particle Swarm Optimization and Genetic Algorithm. The simulation and experimental results show that the speed response gives good performance and satisfy the design specification.
{"title":"Precise Speed Control of DC Motor by Implementing Cascade PI Controller","authors":"Alfiyah Shaldzabila Yustin, H. Nugroho, W. Wibowo","doi":"10.1109/I2CACIS52118.2021.9495889","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495889","url":null,"abstract":"Currently CO2 gas emissions from conventional vehicles makes a big impact on global warming. One of the solutions is switch the technology from using the combustion engine into electric motor. Control method is needed to drive the electric motor hence the machine performance meets the design specifications. In this research, the unknown DC motor parameter was estimated using Matlab parameter estimation tools. Furthermore, the cascade PI control method with series connection was applied on DC motor that act as main actuator which regulates motor speed and its acceleration. The gain of two controller was tuned by using Particle Swarm Optimization and Genetic Algorithm. The simulation and experimental results show that the speed response gives good performance and satisfy the design specification.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123588397","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495909
Nor Syahira Jak Jailani, Z. Muhammad, Mohd Hezri Fazalul Rahiman, M. Nasir Taib
Currently, the quality and grading of essential oil are done manually which is through sensory evaluation. It was performed based on the essential oil physical properties for example human experience and perception of the oil colour, odour, and long-lasting aroma. The sensory evaluation method is very subjective and may vary from one person to another such as a human sensory organ easily get fatigued to deal with repeatability experiment, the result obtained by trained grader usually is not consistent since it may vary to each other and the process itself is lengthy and high time-consuming. To face this problem, many researchers found that the chemical profile of the oil can be used to grad kaffir lime oil more accurately and save time. This study proposed analyses the chemical compound by gas chromatography-mass spectrometry (GC-MS) and Z-score technique from the 11 samples of kaffir lime oils with different brands in Malaysia. The chemical compounds in these samples were extracted by using GC-MS and being analyzed. The significant compound was identified by the Z-score technique. It was found that six chemical compounds such as Citronellal, Limonene, β-pinene, terpinene-4-ol, E-caryophyllene, and terpinolene were highlighted as significant for kaffir lime oil and can be used as a major compound in classifying the kaffir lime oil.
{"title":"Analysis of Kaffir Lime Oil Chemical Compounds by Gas Chromatography-Mass Spectrometry (GC-MS) and Z-Score Technique","authors":"Nor Syahira Jak Jailani, Z. Muhammad, Mohd Hezri Fazalul Rahiman, M. Nasir Taib","doi":"10.1109/I2CACIS52118.2021.9495909","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495909","url":null,"abstract":"Currently, the quality and grading of essential oil are done manually which is through sensory evaluation. It was performed based on the essential oil physical properties for example human experience and perception of the oil colour, odour, and long-lasting aroma. The sensory evaluation method is very subjective and may vary from one person to another such as a human sensory organ easily get fatigued to deal with repeatability experiment, the result obtained by trained grader usually is not consistent since it may vary to each other and the process itself is lengthy and high time-consuming. To face this problem, many researchers found that the chemical profile of the oil can be used to grad kaffir lime oil more accurately and save time. This study proposed analyses the chemical compound by gas chromatography-mass spectrometry (GC-MS) and Z-score technique from the 11 samples of kaffir lime oils with different brands in Malaysia. The chemical compounds in these samples were extracted by using GC-MS and being analyzed. The significant compound was identified by the Z-score technique. It was found that six chemical compounds such as Citronellal, Limonene, β-pinene, terpinene-4-ol, E-caryophyllene, and terpinolene were highlighted as significant for kaffir lime oil and can be used as a major compound in classifying the kaffir lime oil.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114811292","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495925
Mohd Syahmi Hashim, Jia Ying Yong, V. Ramachandaramurthy, M. Mansor, K. Tan
Electrifying the transportation sector helps reducing carbon emissions. However, the need of electric vehicle to receive charging from the power grid introduces various technical impacts to the grid operation. This paper presents a comprehensive investigation of technical impacts of electric vehicle charging to Malaysian distribution grid. The charging assessment considered different power grid loadings, electric vehicle charger types, electric vehicle charging locations, and electric vehicle charging times. These factors were taken into considerations to ensure the practicality of the study. The technical impact study was implemented in a typical Malaysian distribution grid under four different scenarios with respect to the interconnection schemes outlined in the Technical Guidelines for Interconnection of Electric Vehicle to Distribution System. The studies were performed using Matlab/Simulink software. The results indicated that the charging of electric vehicles in Connection Schemes I, II, and III caused overloading of cables and substation transformer, whereas DC fast charging in Connection Scheme IV caused severe grid voltage violation.
{"title":"Assessment of Technical Impacts of EV Charging to Malaysian Distribution Grid","authors":"Mohd Syahmi Hashim, Jia Ying Yong, V. Ramachandaramurthy, M. Mansor, K. Tan","doi":"10.1109/I2CACIS52118.2021.9495925","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495925","url":null,"abstract":"Electrifying the transportation sector helps reducing carbon emissions. However, the need of electric vehicle to receive charging from the power grid introduces various technical impacts to the grid operation. This paper presents a comprehensive investigation of technical impacts of electric vehicle charging to Malaysian distribution grid. The charging assessment considered different power grid loadings, electric vehicle charger types, electric vehicle charging locations, and electric vehicle charging times. These factors were taken into considerations to ensure the practicality of the study. The technical impact study was implemented in a typical Malaysian distribution grid under four different scenarios with respect to the interconnection schemes outlined in the Technical Guidelines for Interconnection of Electric Vehicle to Distribution System. The studies were performed using Matlab/Simulink software. The results indicated that the charging of electric vehicles in Connection Schemes I, II, and III caused overloading of cables and substation transformer, whereas DC fast charging in Connection Scheme IV caused severe grid voltage violation.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121684925","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495922
S. F. Abulhail, M. Z. Al-Faiz
The non-linearity of Inverse kinematics (IK) equations are complex. A Social Spider Optimization (SSO) and Particle Swarm Optimization (PSO) algorithms are proposed in this paper to solve the IK of Humanoid Robotic Arms (HRA). These optimization algorithms are applied on both right and left arms to find the required angles and desired positions with minimum error. Mathematical model of HRA is simulated depending on Denavit-Hartenberg (D-H) method for each arm in which each arm has five Degree Of Freedom (DOF). Performance of HRA model is tested by many positions to be reach by both arms to obtain which optimization algorithm is better. Comparisons are listed between optimal solution using PSO and SSO algorithms. These optimization algorithms are assessed by calculating the Root Mean Squared Error (RMSE) for the absolute error vector of the positions. Simulations and calculation results showed that RMSE value using SSO is less than RMSE value using PSO. We got the largest RMSE of 0.0864 using PSO algorithm. while the lowest possible error, which is 0.00004 was acquired by SSO algorithm. The Graphical User Interface (GUI) is designed and built for motional characteristics of the HRA model in the Forward Kinematics (FK) and IK.
{"title":"Social Spider Optimization for Solving Inverse Kinematics for Both Humanoid Robotic Arms","authors":"S. F. Abulhail, M. Z. Al-Faiz","doi":"10.1109/I2CACIS52118.2021.9495922","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495922","url":null,"abstract":"The non-linearity of Inverse kinematics (IK) equations are complex. A Social Spider Optimization (SSO) and Particle Swarm Optimization (PSO) algorithms are proposed in this paper to solve the IK of Humanoid Robotic Arms (HRA). These optimization algorithms are applied on both right and left arms to find the required angles and desired positions with minimum error. Mathematical model of HRA is simulated depending on Denavit-Hartenberg (D-H) method for each arm in which each arm has five Degree Of Freedom (DOF). Performance of HRA model is tested by many positions to be reach by both arms to obtain which optimization algorithm is better. Comparisons are listed between optimal solution using PSO and SSO algorithms. These optimization algorithms are assessed by calculating the Root Mean Squared Error (RMSE) for the absolute error vector of the positions. Simulations and calculation results showed that RMSE value using SSO is less than RMSE value using PSO. We got the largest RMSE of 0.0864 using PSO algorithm. while the lowest possible error, which is 0.00004 was acquired by SSO algorithm. The Graphical User Interface (GUI) is designed and built for motional characteristics of the HRA model in the Forward Kinematics (FK) and IK.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115972130","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495882
Angela Ciara R. Buela, Rodolfo Rey M. Torres, Fermin II G. Unisa, P. R. Meris, M. Manuel, Jennifer C. Dela Cruz, Roderick C. Tud
Wind turbines can be a replacement for coal as an energy source. However, the conventional wind turbines are expensive and are very complicated due to many mechanical components translating to high manufacturing and maintenance costs. This study aims to help improve the efficiency and design of bladeless wind power generators through generation of power using vortex induced vibration. A bladeless wind power generator was designed using Autodesk Fusion 360 wherein the prototype was modeled to be approximately 1.35 m x 0.5m x 0.5m (overall height, width, and length). A Nonlinear Static Simulation, using ANSYS®Academic Student MechanicalTM, was performed to determine the effect of two different wind velocities, 4.5 m/s and 6.5 m/s, acting on the mast. The design of the bladeless wind turbine was focused on simplifying its manufacturability by using a helical spring to connect the mast to the base while also attaining maximum vortex shedding at a low velocity. The researchers of this study used a static simulation to simplify the study. The predetermined wind velocities were converted into a pressure value, allowing the researchers to obtain the total deformation, directional deformation, and maximum principal and shear stresses (in the spring). It has been determined that the maximum deformation experienced by the bladeless wind power generator was 131.800 mm and 253.270 mm for wind velocities of 4.5 m/s and 6.5 m/s resulting to a theoretical power output of 9.765W and 29.428W, respectively.
风力涡轮机可以替代煤炭作为一种能源。然而，传统的风力涡轮机价格昂贵且非常复杂，因为许多机械部件转化为高制造和维护成本。本研究旨在通过涡激振动发电来提高无叶片风力发电机的效率和设计。使用Autodesk Fusion 360设计了无叶片风力发电机，其中原型模型约为1.35 m x 0.5m x 0.5m(总高度，宽度和长度)。利用ANSYS®Academic Student MechanicalTM进行了非线性静态仿真，以确定两种不同风速(4.5 m/s和6.5 m/s)对桅杆的影响。无叶片风力涡轮机的设计重点是简化其可制造性，通过使用螺旋弹簧将桅杆连接到基座，同时在低速时实现最大的涡脱落。本研究的研究人员使用静态模拟来简化研究。将预定的风速转换为压力值，使研究人员能够获得总变形，定向变形以及最大主应力和剪应力(在春季)。在风速为4.5 m/s和6.5 m/s时，无叶片风力发电机的最大变形为131.800 mm和253.270 mm，理论输出功率分别为9.765W和29.428W。
{"title":"Design and Nonlinear Static Simulation of a Small–Scale Vortex Bladeless Wind Power Generator","authors":"Angela Ciara R. Buela, Rodolfo Rey M. Torres, Fermin II G. Unisa, P. R. Meris, M. Manuel, Jennifer C. Dela Cruz, Roderick C. Tud","doi":"10.1109/I2CACIS52118.2021.9495882","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495882","url":null,"abstract":"Wind turbines can be a replacement for coal as an energy source. However, the conventional wind turbines are expensive and are very complicated due to many mechanical components translating to high manufacturing and maintenance costs. This study aims to help improve the efficiency and design of bladeless wind power generators through generation of power using vortex induced vibration. A bladeless wind power generator was designed using Autodesk Fusion 360 wherein the prototype was modeled to be approximately 1.35 m x 0.5m x 0.5m (overall height, width, and length). A Nonlinear Static Simulation, using ANSYS®Academic Student MechanicalTM, was performed to determine the effect of two different wind velocities, 4.5 m/s and 6.5 m/s, acting on the mast. The design of the bladeless wind turbine was focused on simplifying its manufacturability by using a helical spring to connect the mast to the base while also attaining maximum vortex shedding at a low velocity. The researchers of this study used a static simulation to simplify the study. The predetermined wind velocities were converted into a pressure value, allowing the researchers to obtain the total deformation, directional deformation, and maximum principal and shear stresses (in the spring). It has been determined that the maximum deformation experienced by the bladeless wind power generator was 131.800 mm and 253.270 mm for wind velocities of 4.5 m/s and 6.5 m/s resulting to a theoretical power output of 9.765W and 29.428W, respectively.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126671592","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495921
Jessie R. Balbin, John Maverick Ramos, Joseph Nathaniel Reyes, C. Santiago
The Manila City Government just recently implemented a city ordinance of strict implantation of curfew for minors. Upon conducting interviews, the researchers found out that the system of implementation of curfew uses manpower and barangay patrol roaming around the barangay. This study aims to develop a curfew monitoring system using Image Processing with notifying features via SMS. LBPH (or Local Binary Pattern Histogram) algorithm is implemented in the study. The system was successful in recognizing faces that are registered to the system. The challenge that the researchers encountered was the range of facial recognition is limited. People that are far away cannot be recognized by the system. Also, that the face should be facing the camera. Having any angle with the camera will make the % confidence of the recognition lower. The system has great recognition with the face facing directly at the camera with 15 degrees tolerance.
{"title":"SMS based Curfew Monitoring System for Detecting Minors from a Facial Database to Aid the Local Government Unit Using Image Processing","authors":"Jessie R. Balbin, John Maverick Ramos, Joseph Nathaniel Reyes, C. Santiago","doi":"10.1109/I2CACIS52118.2021.9495921","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495921","url":null,"abstract":"The Manila City Government just recently implemented a city ordinance of strict implantation of curfew for minors. Upon conducting interviews, the researchers found out that the system of implementation of curfew uses manpower and barangay patrol roaming around the barangay. This study aims to develop a curfew monitoring system using Image Processing with notifying features via SMS. LBPH (or Local Binary Pattern Histogram) algorithm is implemented in the study. The system was successful in recognizing faces that are registered to the system. The challenge that the researchers encountered was the range of facial recognition is limited. People that are far away cannot be recognized by the system. Also, that the face should be facing the camera. Having any angle with the camera will make the % confidence of the recognition lower. The system has great recognition with the face facing directly at the camera with 15 degrees tolerance.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115227486","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 : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495888
Aina Umairah Mazlan, N. A. Sahabudin, Muhammad Akmal bin Remli, N. N. Ismail, M. S. Mohamad, Nor Bakiah Abd Warif
This is models with the ability to detect and classify cancer is important in the industrial of healthcare. The most difficult aspect for such model is the classification of cancer, which can be addressed using machine learning methods. The methods are used to improve classification accuracy between system output and test data. The classification process becomes more difficult due to vast data information. This paper presents an overview on current development of cancer classification techniques using machine learning methods, which have received increasing attention within the area of healthcare. This review will mainly focus on the development of machine learning methods for classification of cancer diseases. Recently, there are various researchers proposed different kinds of methods for cancer classification. The results show that the successful of cancer classification is dependent on the machine learning models. Besides, various types of healthcare data used in the experiments would also be discussed in this paper. The development of many optimization methods for cancer classification has brought a lot of improvement in the healthcare field. There is demand for further improvements in optimization methods to develop better machine learning models for cancer classification.
{"title":"Supervised and Unsupervised Machine Learning for Cancer Classification: Recent Development","authors":"Aina Umairah Mazlan, N. A. Sahabudin, Muhammad Akmal bin Remli, N. N. Ismail, M. S. Mohamad, Nor Bakiah Abd Warif","doi":"10.1109/I2CACIS52118.2021.9495888","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495888","url":null,"abstract":"This is models with the ability to detect and classify cancer is important in the industrial of healthcare. The most difficult aspect for such model is the classification of cancer, which can be addressed using machine learning methods. The methods are used to improve classification accuracy between system output and test data. The classification process becomes more difficult due to vast data information. This paper presents an overview on current development of cancer classification techniques using machine learning methods, which have received increasing attention within the area of healthcare. This review will mainly focus on the development of machine learning methods for classification of cancer diseases. Recently, there are various researchers proposed different kinds of methods for cancer classification. The results show that the successful of cancer classification is dependent on the machine learning models. Besides, various types of healthcare data used in the experiments would also be discussed in this paper. The development of many optimization methods for cancer classification has brought a lot of improvement in the healthcare field. There is demand for further improvements in optimization methods to develop better machine learning models for cancer classification.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115300630","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：