Pub Date : 2021-06-26DOI: 10.1109/I2CACIS52118.2021.9495870
Marl D. Barroquillo, Patrick Stephen L. Duque, Eugene S. Bellosillo, Jazer Mesha V. Espanola, Sherwin S. Magon, M. Manuel, Jennifer C. Dela Cruz, Marvin S. Verdadero
Mapúa University's woodworking shop, metalworking shop, and the Universal Testing Machine (UTM) laboratory are facilities that help engineering students, particularly the School of Mechanical and Manufacturing Engineering (SMME), in learning the parts, operations, and safety precautions of different machines and tools. With the use of a 360° camera and a virtual tour building platform, an interactive virtual walkthrough of the facilities was developed as an informational guide for students enrolled in ME136P, ME123L, and ME137L. The researchers conducted an assessment to see the effectiveness of the virtual walkthrough and a survey to get insights from students who are finished with the courses. The analyzed data from the assessment showed that the virtual walkthrough is an effective informational guide since students who used it had a significantly higher scores compared to those that did not. Most of the students who took the survey thought that the virtual walkthrough really assisted in providing necessary information about the machines and tools used in the shop and laboratory courses.
{"title":"Developing an Interactive 360 Walkthrough of MME Shop and Laboratory for ME136P, ME123L, and ME137L","authors":"Marl D. Barroquillo, Patrick Stephen L. Duque, Eugene S. Bellosillo, Jazer Mesha V. Espanola, Sherwin S. Magon, M. Manuel, Jennifer C. Dela Cruz, Marvin S. Verdadero","doi":"10.1109/I2CACIS52118.2021.9495870","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495870","url":null,"abstract":"Mapúa University's woodworking shop, metalworking shop, and the Universal Testing Machine (UTM) laboratory are facilities that help engineering students, particularly the School of Mechanical and Manufacturing Engineering (SMME), in learning the parts, operations, and safety precautions of different machines and tools. With the use of a 360° camera and a virtual tour building platform, an interactive virtual walkthrough of the facilities was developed as an informational guide for students enrolled in ME136P, ME123L, and ME137L. The researchers conducted an assessment to see the effectiveness of the virtual walkthrough and a survey to get insights from students who are finished with the courses. The analyzed data from the assessment showed that the virtual walkthrough is an effective informational guide since students who used it had a significantly higher scores compared to those that did not. Most of the students who took the survey thought that the virtual walkthrough really assisted in providing necessary information about the machines and tools used in the shop and laboratory courses.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127848871","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/I2CACIS52118.2021.9495912
Amjad Iqbal, Mau-Luen Tham, Yoong Choon Chang
Cloud radio access network (CRAN) has gained considerable attention for the upcoming cellular network that can offload the mobile data traffic and reduce energy consumption by deploying intelligent distributed multiple remote radio units (RRHs). However, it is still very challenging to achieve an optimal global strategy to maximize the performance of energy efficiency (EE) and spectral efficiency (SE) simultaneously due to non-convex and combinatorial features. Deep reinforcement learning (DRL)-based framework becomes an imperative solution to jointly maximize the EE-SE performance and guarantee the user quality of service (QoS) demands in downlink CRAN. Furthermore, in order to deal with the large state-action space problem, we leverage dueling double deep Q-network (D3QN) to achieve the nearly optimal control strategy. In the end, extensive simulation results demonstrate the effectiveness of the proposed D3QN method over the conventional-DRL methods.
{"title":"Energy- and Spectral- Efficient Optimization in Cloud RAN based on Dueling Double Deep Q-Network","authors":"Amjad Iqbal, Mau-Luen Tham, Yoong Choon Chang","doi":"10.1109/I2CACIS52118.2021.9495912","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495912","url":null,"abstract":"Cloud radio access network (CRAN) has gained considerable attention for the upcoming cellular network that can offload the mobile data traffic and reduce energy consumption by deploying intelligent distributed multiple remote radio units (RRHs). However, it is still very challenging to achieve an optimal global strategy to maximize the performance of energy efficiency (EE) and spectral efficiency (SE) simultaneously due to non-convex and combinatorial features. Deep reinforcement learning (DRL)-based framework becomes an imperative solution to jointly maximize the EE-SE performance and guarantee the user quality of service (QoS) demands in downlink CRAN. Furthermore, in order to deal with the large state-action space problem, we leverage dueling double deep Q-network (D3QN) to achieve the nearly optimal control strategy. In the end, extensive simulation results demonstrate the effectiveness of the proposed D3QN method over the conventional-DRL methods.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126485815","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/I2CACIS52118.2021.9495896
Jessie R. Balbin, Edward James A. Joves, Mico C. Parreno, E. Chua, Daniel R. Ranque
In the recent years, obtaining a sustainable form of energy to power various autonomous wireless and portable devices is increasingly becoming a matter of concern & various alternate sources of energy have been explored. Energy harvesting technology may be considered as the ultimate solution to replace batteries and provide a long-term power supply for portable devices. The aim of this project is to design and construct a ramp that harvests the kinetic energy from vehicular impacts. The design consists of six stages which include gear mechanism, dc generator, boost converter, transistor circuit, battery level indicator and inverter. The designed prototype is functional, durable, economical, and feasible using affordable components that are readily available in the market.
{"title":"Design and Development of Energy Harvesting Ramp Through Brushed DC Generator Using Gear System","authors":"Jessie R. Balbin, Edward James A. Joves, Mico C. Parreno, E. Chua, Daniel R. Ranque","doi":"10.1109/I2CACIS52118.2021.9495896","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495896","url":null,"abstract":"In the recent years, obtaining a sustainable form of energy to power various autonomous wireless and portable devices is increasingly becoming a matter of concern & various alternate sources of energy have been explored. Energy harvesting technology may be considered as the ultimate solution to replace batteries and provide a long-term power supply for portable devices. The aim of this project is to design and construct a ramp that harvests the kinetic energy from vehicular impacts. The design consists of six stages which include gear mechanism, dc generator, boost converter, transistor circuit, battery level indicator and inverter. The designed prototype is functional, durable, economical, and feasible using affordable components that are readily available in the market.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126669097","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/I2CACIS52118.2021.9495857
Tan Hong, Fazida Hanim Hashim, Thinal Raj, A. B. Huddin
Oil extraction rate (OER) and quality of oil palm can be improved by precisely and accurately classifying the ripeness of oil palm before harvesting. This paper focuses on the development of an artificial neural network (ANN) model for classification of oil palm fruit ripeness using Raman spectra features. In this study, the oil palm fruitlets are from the dura x pisifera (DxP) progenies, harvested from the oil palm plantation of National University of Malaysia (UKM) managed by Khazanah-UKM. A total of 50 samples from unripe, over ripe and ripe fruitlets were collected according to the standard of Malaysia Palm Oil Board (MPOB). Raman spectra for each sample are collected from benchtop Confocal Raman spectrometer. The spectral features for each sample are extracted using pre-processing techniques and used as predictors to train the ANN model. Samples are divided into training set and test set using 50:50 holdout method. The developed model achieves 95.48% prediction accuracy. The accuracy and robustness of the neural network can be improved by increasing the number of samples used in the training.
在采收前对油棕的成熟度进行精确、准确的分级，可以提高油棕的提取率和品质。研究了基于拉曼光谱特征的油棕果实成熟度分类的人工神经网络模型。在本研究中，油棕果实来自马来西亚国立大学(UKM)由Khazanah-UKM管理的油棕种植园收获的dura x pisifera (DxP)后代。根据马来西亚棕榈油委员会(MPOB)的标准，共采集了50个未成熟、过熟和成熟的水果样本。每个样品的拉曼光谱均由台式共聚焦拉曼光谱仪采集。使用预处理技术提取每个样本的光谱特征，并将其用作预测因子来训练人工神经网络模型。采用50:50保留法将样本分为训练集和测试集。所建立的模型预测准确率达到95.48%。通过增加训练中使用的样本数量可以提高神经网络的准确性和鲁棒性。
{"title":"Classification of Oil Palm Fruit Ripeness Using Artificial Neural Network","authors":"Tan Hong, Fazida Hanim Hashim, Thinal Raj, A. B. Huddin","doi":"10.1109/I2CACIS52118.2021.9495857","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495857","url":null,"abstract":"Oil extraction rate (OER) and quality of oil palm can be improved by precisely and accurately classifying the ripeness of oil palm before harvesting. This paper focuses on the development of an artificial neural network (ANN) model for classification of oil palm fruit ripeness using Raman spectra features. In this study, the oil palm fruitlets are from the dura x pisifera (DxP) progenies, harvested from the oil palm plantation of National University of Malaysia (UKM) managed by Khazanah-UKM. A total of 50 samples from unripe, over ripe and ripe fruitlets were collected according to the standard of Malaysia Palm Oil Board (MPOB). Raman spectra for each sample are collected from benchtop Confocal Raman spectrometer. The spectral features for each sample are extracted using pre-processing techniques and used as predictors to train the ANN model. Samples are divided into training set and test set using 50:50 holdout method. The developed model achieves 95.48% prediction accuracy. The accuracy and robustness of the neural network can be improved by increasing the number of samples used in the training.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"134 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131030515","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/I2CACIS52118.2021.9495874
H. Shariff, Mohd Hezri Fazalul Rahiman, R. Adnan, Mohd Hezri Marzaki, M. Tajjudin, M. H. A. Jalil
The steam distillation technique is the earliest technique to extract the essential oil from botanical raw material. Until today, the technique are still relevant and popular among the industrial practitioners due to low manufacturing cost, green environment and higher yield produced. In order to extract the oils, the botanical raw material placed inside the distillation tank which is above the water level. The steam are produced by boiling the water inside the distillation tank. Then, the botanical raw material is heated by the steam and breaking the gland. In order to produce the best quality of essential oils, the con-trolling of steam temperature is important. The disclosure of extracted raw material to the high degree of steam temperature is expose to risk which degradation of essential oils produced. To ensure the process is able to produce the high quality of essential oils; the process dynamic must be regulated by capable controller. In addition, the controller also need to have capability to capture and control dynamic behavior of the system. In this studies, the Small-Medium Scale Steam Distillation System is developed and controlled by PID controller to regulate the temperature at desired setpoint. The development of PID are tuned by the Cohen-Coon, Chchen-Reswicks and Hrones and AMIGO which the controller performance are evaluated based on step test, set point change test and error matrices.
{"title":"Comparative Study of PID Controllers for Time-Varying of Steam Distillation Process","authors":"H. Shariff, Mohd Hezri Fazalul Rahiman, R. Adnan, Mohd Hezri Marzaki, M. Tajjudin, M. H. A. Jalil","doi":"10.1109/I2CACIS52118.2021.9495874","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495874","url":null,"abstract":"The steam distillation technique is the earliest technique to extract the essential oil from botanical raw material. Until today, the technique are still relevant and popular among the industrial practitioners due to low manufacturing cost, green environment and higher yield produced. In order to extract the oils, the botanical raw material placed inside the distillation tank which is above the water level. The steam are produced by boiling the water inside the distillation tank. Then, the botanical raw material is heated by the steam and breaking the gland. In order to produce the best quality of essential oils, the con-trolling of steam temperature is important. The disclosure of extracted raw material to the high degree of steam temperature is expose to risk which degradation of essential oils produced. To ensure the process is able to produce the high quality of essential oils; the process dynamic must be regulated by capable controller. In addition, the controller also need to have capability to capture and control dynamic behavior of the system. In this studies, the Small-Medium Scale Steam Distillation System is developed and controlled by PID controller to regulate the temperature at desired setpoint. The development of PID are tuned by the Cohen-Coon, Chchen-Reswicks and Hrones and AMIGO which the controller performance are evaluated based on step test, set point change test and error matrices.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126049982","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/I2CACIS52118.2021.9495913
Jessie R. Balbin, Aldwin Ian T. Yap, Benedict D. Calicdan, Lester Allan M. Bernabe
Heart rhythm problems, more commonly known as heart arrhythmias, is the phenomenon in which heartbeats don’t work properly due to electrical impulses. This causes the heart to irregularly, sometimes too slow, or too fast, depending on the condition. Fluttering and racing heart are the most common arrhythmia symptoms, which is most of the time harmless. Sometimes heart arrhythmias can even be life-threatening and may manifest several alarming signs and symptoms. This paper is about the acquisition and analysis of heart activity. Using the AD8232 module, the heart’s electrical activity is captured using the principles of Electrocardiography (ECG). For the acoustic activity of the heart, a stethoscope and an electret microphone are used to convert the acoustic energy to electrical energy. The signal from each practice is passed through an ADC to translate the signal to a digital signal to allow further operation. Upon acquiring the data, it is then analyzed whether the subject has arrhythmia, murmur, or is normal using a Deep Learning algorithm. The said algorithm is provided using a Convolutional Neural Network (ConvNet/CNN). Remote communities where medical assistance is scarce will benefit from this research as it can be operated with no medical experience. The study was able to successfully acquire ECGs and PCGs and analyze the heart condition of the data source. The researchers successfully integrated preprocessing techniques to better analyze the gathered data from human subjects. Lastly, the tuned CNN model correctly classified human subjects based on 4 classes which are normal, abnormal, others, and noisy. The classification accuracy shows that 80% of the 20 subjects were correctly classified based on their current medical condition. The performance sensitivity of the study is 100%, while performance specificity is 77.78%. The detection of error rate is at 20%. All values for conformance testing were deemed acceptable considering the testing restrictions due to the ongoing COVID-19 pandemic.
{"title":"Arrhythmia Detection using Electrocardiogram and Phonocardiogram Pattern using Integrated Signal Processing Algorithms with the Aid of Convolutional Neural Networks","authors":"Jessie R. Balbin, Aldwin Ian T. Yap, Benedict D. Calicdan, Lester Allan M. Bernabe","doi":"10.1109/I2CACIS52118.2021.9495913","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495913","url":null,"abstract":"Heart rhythm problems, more commonly known as heart arrhythmias, is the phenomenon in which heartbeats don’t work properly due to electrical impulses. This causes the heart to irregularly, sometimes too slow, or too fast, depending on the condition. Fluttering and racing heart are the most common arrhythmia symptoms, which is most of the time harmless. Sometimes heart arrhythmias can even be life-threatening and may manifest several alarming signs and symptoms. This paper is about the acquisition and analysis of heart activity. Using the AD8232 module, the heart’s electrical activity is captured using the principles of Electrocardiography (ECG). For the acoustic activity of the heart, a stethoscope and an electret microphone are used to convert the acoustic energy to electrical energy. The signal from each practice is passed through an ADC to translate the signal to a digital signal to allow further operation. Upon acquiring the data, it is then analyzed whether the subject has arrhythmia, murmur, or is normal using a Deep Learning algorithm. The said algorithm is provided using a Convolutional Neural Network (ConvNet/CNN). Remote communities where medical assistance is scarce will benefit from this research as it can be operated with no medical experience. The study was able to successfully acquire ECGs and PCGs and analyze the heart condition of the data source. The researchers successfully integrated preprocessing techniques to better analyze the gathered data from human subjects. Lastly, the tuned CNN model correctly classified human subjects based on 4 classes which are normal, abnormal, others, and noisy. The classification accuracy shows that 80% of the 20 subjects were correctly classified based on their current medical condition. The performance sensitivity of the study is 100%, while performance specificity is 77.78%. The detection of error rate is at 20%. All values for conformance testing were deemed acceptable considering the testing restrictions due to the ongoing COVID-19 pandemic.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114259521","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/I2CACIS52118.2021.9495901
Aaron Kyle Monton, Vanessa Larioza, M. Pacis
Obtaining a good Phasor Measurement Unit (PMU) placement equates with having to deal with less power system demands. It allows the monitoring and maintenance of the network at high precision. In this paper, the researchers formed an algorithm wherein an output of where the PMU should be placed to obtain a complete observable network along with the ranking and screening of all N-1 Contingency is obtained through presenting different cases of IEEE buses largely for IEEE-6, IEEE-9, IEEE-14, and IEEE-30 bus system. This allows that evaluation of the severity of each outage that might occur on a given network. Also, the researchers made use of Gauss-Seidel Method for the algorithm’s load flow and Voltage-Reactive Performance Index in determining the severity of each outage while, the utilization of Integer Linear Programming was used on determining the proper PMU Placement.
{"title":"An Optimal Phasor Measurement Unit (PMU) Placement Algorithm with (N-1) Contingency Using Integer Linear Programming (ILP)","authors":"Aaron Kyle Monton, Vanessa Larioza, M. Pacis","doi":"10.1109/I2CACIS52118.2021.9495901","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495901","url":null,"abstract":"Obtaining a good Phasor Measurement Unit (PMU) placement equates with having to deal with less power system demands. It allows the monitoring and maintenance of the network at high precision. In this paper, the researchers formed an algorithm wherein an output of where the PMU should be placed to obtain a complete observable network along with the ranking and screening of all N-1 Contingency is obtained through presenting different cases of IEEE buses largely for IEEE-6, IEEE-9, IEEE-14, and IEEE-30 bus system. This allows that evaluation of the severity of each outage that might occur on a given network. Also, the researchers made use of Gauss-Seidel Method for the algorithm’s load flow and Voltage-Reactive Performance Index in determining the severity of each outage while, the utilization of Integer Linear Programming was used on determining the proper PMU Placement.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124658159","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/I2CACIS52118.2021.9495862
D. M. Ahmed, A. Abdulazeez, D. Zeebaree, F. Y. Ahmed
Machine learning algorithms have been used in many fields, like economics, medicine, etc. Education data mining is one of the areas concerned with exploring patterns of data in an educational environment. One of the most important uses is to predict students' performance to improve the existing educational situation. It can be considered as one of the data mining sciences. The ability to predict in advance in many areas has many benefits. In the case of learning, it enables us to know students' levels in advance and identify students who need special attention. This paper proposes using the algorithm (GBDT) which is a machine learning technology used for regression, classification, and ranking tasks, and is part of the Boosting method family to predict university students' performance in final exams. It compares the proposed system's performance with selected machine learning algorithms (Support vector machine, Logistic Regression, Naive Bayes, Gradient Boosted Trees).
{"title":"Predicting University's Students Performance Based on Machine Learning Techniques","authors":"D. M. Ahmed, A. Abdulazeez, D. Zeebaree, F. Y. Ahmed","doi":"10.1109/I2CACIS52118.2021.9495862","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495862","url":null,"abstract":"Machine learning algorithms have been used in many fields, like economics, medicine, etc. Education data mining is one of the areas concerned with exploring patterns of data in an educational environment. One of the most important uses is to predict students' performance to improve the existing educational situation. It can be considered as one of the data mining sciences. The ability to predict in advance in many areas has many benefits. In the case of learning, it enables us to know students' levels in advance and identify students who need special attention. This paper proposes using the algorithm (GBDT) which is a machine learning technology used for regression, classification, and ranking tasks, and is part of the Boosting method family to predict university students' performance in final exams. It compares the proposed system's performance with selected machine learning algorithms (Support vector machine, Logistic Regression, Naive Bayes, Gradient Boosted Trees).","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123340604","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/I2CACIS52118.2021.9495906
Marison C. Angeles, Bonaobra Paolo Luis V. Bonaobra, Dave Carlo S. Matibag, Marc Daniel N. Molina, Ricky D. Umali, M. Manuel, Jennifer C. Dela Cruz, Roderick C. Tud
A problem that the world faces, especially third world countries is the scarcity and expensiveness of electricity specifically the use of fossil fuel and its surging price. The world faces an era that is slowly degrading its atmosphere and where the carbon emissions are at its all-time high. The solution with renewable energy is not getting cheap to be able to apply these sources into poor rural areas. Icewind turbine is an example of how effective it is but the cost is too high. The focus of the study is to make a design that is cost efficient, can be installed anywhere, and able to supply power to rural roads and areas for adequate lighting. Icewind turbines are types of Vertical Axis Wind Turbines (VAWT) whose blades utilize a Savonius VAWT design. Icewind turbines are already applied in the country Iceland for telecom towers and residential applications such as homes, cabins, and farms. It is also applied in a bus stop located in Reykjavik Iceland as a power hub for Wi-Fi and charging. According to researchers, Icewind turbine is 28.4% more efficient than the typical Savonius Vertical Axis Wind turbine. This research aims to compare the effects of an Icewind Turbine using different materials namely; aluminum, 3D printer filament; Polyethylene terephthalate Glycol (PETG), and stainless steel by fabricating the blades. Using these materials, the researchers gathered data that will determine the best suitable material to fabricate the turbine design that will yield the best performance output and efficiency under the same conditions in three different situations. The materials gave different interpretation in regard to the situation they are under; stiffness and weight made a huge difference on its outcome. The results depended on what type of situation the turbine is. Nevertheless, aluminum blades are the most suitable and most ideal on any given environment.
{"title":"Evaluation of the Effects of Using Different Blade Material in the Performance of an Icewind Turbine","authors":"Marison C. Angeles, Bonaobra Paolo Luis V. Bonaobra, Dave Carlo S. Matibag, Marc Daniel N. Molina, Ricky D. Umali, M. Manuel, Jennifer C. Dela Cruz, Roderick C. Tud","doi":"10.1109/I2CACIS52118.2021.9495906","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495906","url":null,"abstract":"A problem that the world faces, especially third world countries is the scarcity and expensiveness of electricity specifically the use of fossil fuel and its surging price. The world faces an era that is slowly degrading its atmosphere and where the carbon emissions are at its all-time high. The solution with renewable energy is not getting cheap to be able to apply these sources into poor rural areas. Icewind turbine is an example of how effective it is but the cost is too high. The focus of the study is to make a design that is cost efficient, can be installed anywhere, and able to supply power to rural roads and areas for adequate lighting. Icewind turbines are types of Vertical Axis Wind Turbines (VAWT) whose blades utilize a Savonius VAWT design. Icewind turbines are already applied in the country Iceland for telecom towers and residential applications such as homes, cabins, and farms. It is also applied in a bus stop located in Reykjavik Iceland as a power hub for Wi-Fi and charging. According to researchers, Icewind turbine is 28.4% more efficient than the typical Savonius Vertical Axis Wind turbine. This research aims to compare the effects of an Icewind Turbine using different materials namely; aluminum, 3D printer filament; Polyethylene terephthalate Glycol (PETG), and stainless steel by fabricating the blades. Using these materials, the researchers gathered data that will determine the best suitable material to fabricate the turbine design that will yield the best performance output and efficiency under the same conditions in three different situations. The materials gave different interpretation in regard to the situation they are under; stiffness and weight made a huge difference on its outcome. The results depended on what type of situation the turbine is. Nevertheless, aluminum blades are the most suitable and most ideal on any given environment.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129302966","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/I2CACIS52118.2021.9495904
J. P. Félix, K. G. Gonong, E. J. Macadaeg, M. Pacis, G. Magwili, K. K. Quiao
Protective relays on any power system network must always operate correctly with minimum operating time to clear a fault. Until now, manual computations and curve-fitting techniques are still being used to coordinate relays on complex electrical grids. To eliminate these methods, this paper provides a time-efficient algorithm that can determine the optimal directional overcurrent relay settings of any power system network by automating the formulation of its Interval Coordination Matrix. The algorithm was first tested by validating the optimal relay settings of the 3 cases of the IEEE 14 Bus System from a previous study. The proposed algorithm reduced the time of simulation by 77.399%. Then, the researchers were also able to acquire the optimal relay settings on all the 642 fault cases of the 46-Bus Sub-Transmission Network. The result of this study provides a proof of time-efficient algorithm that can replace the manual methods in evaluating the settings of protection relays.
{"title":"Optimal Directional Overcurrent Relay Settings Using Automated Interval Coordination Matrix Algorithm","authors":"J. P. Félix, K. G. Gonong, E. J. Macadaeg, M. Pacis, G. Magwili, K. K. Quiao","doi":"10.1109/I2CACIS52118.2021.9495904","DOIUrl":"https://doi.org/10.1109/I2CACIS52118.2021.9495904","url":null,"abstract":"Protective relays on any power system network must always operate correctly with minimum operating time to clear a fault. Until now, manual computations and curve-fitting techniques are still being used to coordinate relays on complex electrical grids. To eliminate these methods, this paper provides a time-efficient algorithm that can determine the optimal directional overcurrent relay settings of any power system network by automating the formulation of its Interval Coordination Matrix. The algorithm was first tested by validating the optimal relay settings of the 3 cases of the IEEE 14 Bus System from a previous study. The proposed algorithm reduced the time of simulation by 77.399%. Then, the researchers were also able to acquire the optimal relay settings on all the 642 fault cases of the 46-Bus Sub-Transmission Network. The result of this study provides a proof of time-efficient algorithm that can replace the manual methods in evaluating the settings of protection relays.","PeriodicalId":210770,"journal":{"name":"2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115388468","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：