Pub Date : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9697049
Shreyas V Kuradagi, Kritika Arora, P. Mahalakshmi, S. Balaganapathy, A. Sharmila
Usually movement of goods from one location to another requires human input. This is a tiring job in industries where goods are picked and placed in bulk and the weight of goods to be carried is beyond human potential. Automation industry can play a large role in reducing the human labour and making the process more efficient. In this paper, we put forward a solution to this problem using environment friendly automation technology. We use NodeMCU as the connection between the system and the device through the internet. Our goal is to reduce human interference in hazardous work environment and place with oxygen deficiency through an app controlled 3D printed robotic arm. This arm can be controlled through an android application from anywhere around the globe and can be programmed to perform basic tasks. Furthermore, we are using 3D printing technology so as to eliminate the requirements of production moulds thereby reducing the cost of the arm and making it more feasible. Another objective of this Project was to make the Arm as environmentally safe as possible. Hence, a solar panel will be connected to the Chassis. This ensures that the primary source of power for the Arm is solar energy which is a renewable resource. In addition to this, the plastic which will be used to 3D print the individual parts will be biodegradable and thereby reducing the carbon footprint.
{"title":"App controlled Robotic Arm with Ultrasonic Sensor and Solar Panels","authors":"Shreyas V Kuradagi, Kritika Arora, P. Mahalakshmi, S. Balaganapathy, A. Sharmila","doi":"10.1109/i-PACT52855.2021.9697049","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9697049","url":null,"abstract":"Usually movement of goods from one location to another requires human input. This is a tiring job in industries where goods are picked and placed in bulk and the weight of goods to be carried is beyond human potential. Automation industry can play a large role in reducing the human labour and making the process more efficient. In this paper, we put forward a solution to this problem using environment friendly automation technology. We use NodeMCU as the connection between the system and the device through the internet. Our goal is to reduce human interference in hazardous work environment and place with oxygen deficiency through an app controlled 3D printed robotic arm. This arm can be controlled through an android application from anywhere around the globe and can be programmed to perform basic tasks. Furthermore, we are using 3D printing technology so as to eliminate the requirements of production moulds thereby reducing the cost of the arm and making it more feasible. Another objective of this Project was to make the Arm as environmentally safe as possible. Hence, a solar panel will be connected to the Chassis. This ensures that the primary source of power for the Arm is solar energy which is a renewable resource. In addition to this, the plastic which will be used to 3D print the individual parts will be biodegradable and thereby reducing the carbon footprint.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116619027","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696553
S. Devi, Amirthavarshini D, Anbukani R S, Harini T K
Due to the pandemic by the spread of the COVID virus, there has been a mandatory demand to screen patients. Predominantly RTPCR test is used to detect the virus. The RTPCR test is the most commonly used technique to detect COVID - 19 viruses. The test takes a minimum of 12 hours which is time-consuming and might put a patient's life at stake. This detection method for COVID screening is said to have a false detection rate. CT scans have been used for COVID-19 screening and using CT has several challenges especially since their radiation dose is considerably higher than x-rays. Hence, CXRs are a better choice for the initial assessment. Detection of COVID-19 pneumonia is a fine-grained problem as doctors cannot detect it just by looking at the x-ray images. Moreover, the radiologists visit many patients every day and the diagnosis process take significant time, which may increase errors in screening notably. Therefore, a medical decision support system for screening COVID-19 patients is of utmost importance. Our proposed system is a web application that helps to screen COVID-19 patients effectively.
{"title":"A Medical Decision Support System to Detect Covid-19 Pneumonia Using CNN","authors":"S. Devi, Amirthavarshini D, Anbukani R S, Harini T K","doi":"10.1109/i-PACT52855.2021.9696553","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696553","url":null,"abstract":"Due to the pandemic by the spread of the COVID virus, there has been a mandatory demand to screen patients. Predominantly RTPCR test is used to detect the virus. The RTPCR test is the most commonly used technique to detect COVID - 19 viruses. The test takes a minimum of 12 hours which is time-consuming and might put a patient's life at stake. This detection method for COVID screening is said to have a false detection rate. CT scans have been used for COVID-19 screening and using CT has several challenges especially since their radiation dose is considerably higher than x-rays. Hence, CXRs are a better choice for the initial assessment. Detection of COVID-19 pneumonia is a fine-grained problem as doctors cannot detect it just by looking at the x-ray images. Moreover, the radiologists visit many patients every day and the diagnosis process take significant time, which may increase errors in screening notably. Therefore, a medical decision support system for screening COVID-19 patients is of utmost importance. Our proposed system is a web application that helps to screen COVID-19 patients effectively.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116579923","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696864
Jarapala Siva Naik, R. Thirumalaivasan, M. Janaki
The power system stabilizer (PSS) plays a key role in multi-machine power systems. The main objective of PSS is to provide damping of the rotor oscillations, whenever there is a transient disturbance. In this paper, eigenvalues and participation factor are used to identify the oscillatory modes in a multi-machine system without and with PSS. The transient simulation is carried out to validate the steady state model. The proposed methods runs for N-number of buses and M-number of generators. The study system comprises a 4-generators and 10-buses two area multi-machine system. The results obtained on the study system show that oscillatory response of speed deviation and rotor angle is well damped with PSS.
{"title":"Analysis of Multi-Machine Power System with PSS using Participation Factor Method","authors":"Jarapala Siva Naik, R. Thirumalaivasan, M. Janaki","doi":"10.1109/i-PACT52855.2021.9696864","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696864","url":null,"abstract":"The power system stabilizer (PSS) plays a key role in multi-machine power systems. The main objective of PSS is to provide damping of the rotor oscillations, whenever there is a transient disturbance. In this paper, eigenvalues and participation factor are used to identify the oscillatory modes in a multi-machine system without and with PSS. The transient simulation is carried out to validate the steady state model. The proposed methods runs for N-number of buses and M-number of generators. The study system comprises a 4-generators and 10-buses two area multi-machine system. The results obtained on the study system show that oscillatory response of speed deviation and rotor angle is well damped with PSS.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121747879","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696943
B. M, S. Sahoo, S. Sukchai
A Novel Maximum Power Point Tracking (MPPT) Algorithms has been designed for the Photovoltaic System (PV) to overcome the effect of partial shading condition using Ant Lion Optimizer (ALO) algorithm. The conventional Algorithms has been failed to track the peak point for variable atmospheric conditions. The novelty of this work is the Ant Lion Optimizer (ALO) algorithm has been proposed for MPPT which has the ability to perform under variable atmospheric conditions. The detailed simulation and experimental work has been carried out on ALO algorithm. To validate its performance and to show the supremacy of this method it has been further compared with conventional Perturb and Observe (P&O) and Incremental Conductance (IC) Algorithms. The simulation study has been carried out for various steady state and dynamic operating conditions. The boost converter experimental setup has been developed in the laboratory to test the feasibility of the system. dSPACE DS1103 control interface is for Real Time Implementation (RTI). The experimental results have shown very good agreement with the simulation results.
{"title":"Maximum Power Extraction using Ant Lion Optimization Technique for Photovoltaic System","authors":"B. M, S. Sahoo, S. Sukchai","doi":"10.1109/i-PACT52855.2021.9696943","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696943","url":null,"abstract":"A Novel Maximum Power Point Tracking (MPPT) Algorithms has been designed for the Photovoltaic System (PV) to overcome the effect of partial shading condition using Ant Lion Optimizer (ALO) algorithm. The conventional Algorithms has been failed to track the peak point for variable atmospheric conditions. The novelty of this work is the Ant Lion Optimizer (ALO) algorithm has been proposed for MPPT which has the ability to perform under variable atmospheric conditions. The detailed simulation and experimental work has been carried out on ALO algorithm. To validate its performance and to show the supremacy of this method it has been further compared with conventional Perturb and Observe (P&O) and Incremental Conductance (IC) Algorithms. The simulation study has been carried out for various steady state and dynamic operating conditions. The boost converter experimental setup has been developed in the laboratory to test the feasibility of the system. dSPACE DS1103 control interface is for Real Time Implementation (RTI). The experimental results have shown very good agreement with the simulation results.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124782506","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696619
V. Indragandhi, A. Chitra, Raunak Singhania, Divyansh Garg, V. Subramaniyaswamy
Internet of things (IOT) and Machine Learning (ML) techniques have achieved quite high standards with the availability of high-speed GPU's and wide range of applications in real world. Both of them are shaping the way we live, travel, work and communicate. Medication in India is the core power of the Economy but, it's quite expensive. This paper aims at an attempt to deploy these IOT and ML techniques for Automating Insulin Drug Delivery (AIDD) for comatose patients. The main focus is to replace the existing Insulin Delivery Systems which are costly and limited to only certain hospitals, with a cost friendly and smart system which incorporates IOT and Machine learning with good accuracy and a very affordable price. In this the rotor system is designed and presented which is employed to deliver the required amount of insulin. The rotation of the designed rotor system is controlled by a motor. In order to make the system more flexible, bimodal operation is developed using IOT which enables either manual or automatic mode. To fix the optimal ML technique, the various machine models such as Linear Regression, Decision Tree and Random Forest is employed to predict insulin dose amount that must be given to the patient by examining his/her condition. This method makes it possible to treat a diabetic patient remotely, without the need of a physical person.
{"title":"Bimodal Insulin Delivery System Using Internet of Things and Machine Learning Approach","authors":"V. Indragandhi, A. Chitra, Raunak Singhania, Divyansh Garg, V. Subramaniyaswamy","doi":"10.1109/i-PACT52855.2021.9696619","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696619","url":null,"abstract":"Internet of things (IOT) and Machine Learning (ML) techniques have achieved quite high standards with the availability of high-speed GPU's and wide range of applications in real world. Both of them are shaping the way we live, travel, work and communicate. Medication in India is the core power of the Economy but, it's quite expensive. This paper aims at an attempt to deploy these IOT and ML techniques for Automating Insulin Drug Delivery (AIDD) for comatose patients. The main focus is to replace the existing Insulin Delivery Systems which are costly and limited to only certain hospitals, with a cost friendly and smart system which incorporates IOT and Machine learning with good accuracy and a very affordable price. In this the rotor system is designed and presented which is employed to deliver the required amount of insulin. The rotation of the designed rotor system is controlled by a motor. In order to make the system more flexible, bimodal operation is developed using IOT which enables either manual or automatic mode. To fix the optimal ML technique, the various machine models such as Linear Regression, Decision Tree and Random Forest is employed to predict insulin dose amount that must be given to the patient by examining his/her condition. This method makes it possible to treat a diabetic patient remotely, without the need of a physical person.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124177620","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9697005
P. Deepa, Rashmita Khilar
Voice recognition has been advancing at a fast rate. Many cases involving edited audio clips and incorrect identity claims are reported on a daily basis. Due to the growing importance of information processing technology, it becomes easier and easier to identify people by their voices. Voice recognition consists of detecting a user's identity based on characteristics of their voice. It is a widely applied form of biometric recognition in the world, particularly in fields where security has a high priority. The deep neural networks were used as feature extractor alongside classifiers, but they haven't been completely trained due to the success of deep learning. While such methods are extremely efficient, they still require manual attention. Especially in DNN, interactivity between people and machines is essential. This is where the art of voice recognition comes from. In addition to their application in speech recognition, deep neural networks have demonstrated their potential to be used for voice recognition as well. They provide an efficient implementation of complex nonlinear models for learning unique and invariant data structures. The main contribution of this work is to provide a brief overview of the field of deep neural networks and voice recognition, describing its system, underlying approaches, and challenges.
{"title":"A Report on Voice Recognition System: Techniques, Methodologies and Challenges using Deep Neural Network","authors":"P. Deepa, Rashmita Khilar","doi":"10.1109/i-PACT52855.2021.9697005","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9697005","url":null,"abstract":"Voice recognition has been advancing at a fast rate. Many cases involving edited audio clips and incorrect identity claims are reported on a daily basis. Due to the growing importance of information processing technology, it becomes easier and easier to identify people by their voices. Voice recognition consists of detecting a user's identity based on characteristics of their voice. It is a widely applied form of biometric recognition in the world, particularly in fields where security has a high priority. The deep neural networks were used as feature extractor alongside classifiers, but they haven't been completely trained due to the success of deep learning. While such methods are extremely efficient, they still require manual attention. Especially in DNN, interactivity between people and machines is essential. This is where the art of voice recognition comes from. In addition to their application in speech recognition, deep neural networks have demonstrated their potential to be used for voice recognition as well. They provide an efficient implementation of complex nonlinear models for learning unique and invariant data structures. The main contribution of this work is to provide a brief overview of the field of deep neural networks and voice recognition, describing its system, underlying approaches, and challenges.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128529428","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696801
J. J. Imaculate, Adduri Aishwarya, K. G., S. A. Sampson
Gas sensors have become indispensable, not just in potentially hazardous industries, but also for the everyday lives of ordinary citizens. In this work, Quartz Tuning Forks (QTFs) modified with nanostructured polymer wires were simulated using COMSOL Multiphysics to investigate their feasibility as gas sensors. Different polymers were used to functionalize the QTFs and a study was done to analyze which polymer is best suited for use as potential Volatile Organic Compounds (VOCs) sensors. The suitability of the polymer was reflected in the shift in eigenfrequency of the system. The relationship between properties of the polymer and the frequency response of the polymer functionalized QTF system when the QTF was both mass loaded and spring-loaded with different polymers, was studied.
{"title":"Investigation of Polymer Functionalized QTFs as Potential Gas Sensors Using COMSOL Multiphysics","authors":"J. J. Imaculate, Adduri Aishwarya, K. G., S. A. Sampson","doi":"10.1109/i-PACT52855.2021.9696801","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696801","url":null,"abstract":"Gas sensors have become indispensable, not just in potentially hazardous industries, but also for the everyday lives of ordinary citizens. In this work, Quartz Tuning Forks (QTFs) modified with nanostructured polymer wires were simulated using COMSOL Multiphysics to investigate their feasibility as gas sensors. Different polymers were used to functionalize the QTFs and a study was done to analyze which polymer is best suited for use as potential Volatile Organic Compounds (VOCs) sensors. The suitability of the polymer was reflected in the shift in eigenfrequency of the system. The relationship between properties of the polymer and the frequency response of the polymer functionalized QTF system when the QTF was both mass loaded and spring-loaded with different polymers, was studied.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129890188","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696782
Pretty Mary Tom, J. Edward
One of the vital needs for the distribution systems is the Low-Voltage-Ride-through (LVRT) capability which has to meet the grid code standards. The capability of the distribution system to stay connected even during voltage sag issues is termed as LVRT. A solar-wind-battery based hybrid renewable energy system (HRES) for microgrid applications is considered in this work which enables the use of renewable energy resources effectively, each and every system of HRES is controlled exclusively. The output of PV is boosted with the aid of a LUO converter which is controlled by a closed loop control based on Crow Search Algorithm. The wind energy conversion system utilizes doubly-fed-induction generator (DFIG), the output of which is converted to DC by a PWM rectifier and this is controlled by a PI controller. The battery system uses a bidirectional Buck-Boost converter and the state of charge (SOC) of the battery is monitored by artificial neural network (ANN). The key aspect of this work is the estimation of LVRT and this is accomplished by Signal processing approach based Deep Neural Network (DNN). Notch filter is used for pre-processing by which the noises are removed, Hilbert transform is used for segmentation and SIFT for feature extraction. The trained and test data are classified with DNN classifier from which the LVRT is estimated. The proposed strategy is implemented in MATLAB and the results were attained. The grid current THD is observed as 4.72% and the LVRT is estimated at 2.6sec.
{"title":"Low Voltage Ride Through Estimation in Microgrid using Deep Neural Network","authors":"Pretty Mary Tom, J. Edward","doi":"10.1109/i-PACT52855.2021.9696782","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696782","url":null,"abstract":"One of the vital needs for the distribution systems is the Low-Voltage-Ride-through (LVRT) capability which has to meet the grid code standards. The capability of the distribution system to stay connected even during voltage sag issues is termed as LVRT. A solar-wind-battery based hybrid renewable energy system (HRES) for microgrid applications is considered in this work which enables the use of renewable energy resources effectively, each and every system of HRES is controlled exclusively. The output of PV is boosted with the aid of a LUO converter which is controlled by a closed loop control based on Crow Search Algorithm. The wind energy conversion system utilizes doubly-fed-induction generator (DFIG), the output of which is converted to DC by a PWM rectifier and this is controlled by a PI controller. The battery system uses a bidirectional Buck-Boost converter and the state of charge (SOC) of the battery is monitored by artificial neural network (ANN). The key aspect of this work is the estimation of LVRT and this is accomplished by Signal processing approach based Deep Neural Network (DNN). Notch filter is used for pre-processing by which the noises are removed, Hilbert transform is used for segmentation and SIFT for feature extraction. The trained and test data are classified with DNN classifier from which the LVRT is estimated. The proposed strategy is implemented in MATLAB and the results were attained. The grid current THD is observed as 4.72% and the LVRT is estimated at 2.6sec.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130776804","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696747
Chuanhui Lau, Hungyang Leong, Joonhuang Chuah, N. Kamarudin
The rapid increase in global population significantly drives the hiking demand for transportations. This trend further leads to the increase in the number of road traffic accidents globally. Based on a study, fatigue due to prolonged driving is one of the leading causes for traffic accidents. With a customized Graphical User Interface (GUI), this work aims to develop an eye fatigue recognition system using YOLOv2 model. The proposed method used PERCLOS and blink rate parameters as indicators to determine the alertness of the user. This proposed method achieved a real-time average accuracy of 99.23% in normal lighting conditions and 98.57% in low light conditions.
{"title":"An Eye Fatigue Recognition System using YOLOv2","authors":"Chuanhui Lau, Hungyang Leong, Joonhuang Chuah, N. Kamarudin","doi":"10.1109/i-PACT52855.2021.9696747","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696747","url":null,"abstract":"The rapid increase in global population significantly drives the hiking demand for transportations. This trend further leads to the increase in the number of road traffic accidents globally. Based on a study, fatigue due to prolonged driving is one of the leading causes for traffic accidents. With a customized Graphical User Interface (GUI), this work aims to develop an eye fatigue recognition system using YOLOv2 model. The proposed method used PERCLOS and blink rate parameters as indicators to determine the alertness of the user. This proposed method achieved a real-time average accuracy of 99.23% in normal lighting conditions and 98.57% in low light conditions.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130097751","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9697020
P. Dhal
A practical energy management method for a small-scale hybrid wind-solar-battery power system is proposed in this research. To evaluate the performance of a hybrid micro grid, dc-dc converter and controllers were built together with wind and solar power conversion and energy storage technologies. The hybrid power system is configured to run at unity power factor, and the Maximum Power Point Tracking (MPPT) methodology is used to control the output voltage as the weather shifts. An energy management system maintains the power balance for fluctuations in renewable energy sources power generation as well as load demand fluctuations. However, this proposed system improved reliability; reduce voltage fluctuations due to various irradiations and wind speed combined with the main grid. The battery with a DC-DC converter is incorporated into the main power system by a 3– - inverter and also the battery is used to store the energy in normal condition and deliver the energy when not available from the sources.
{"title":"A Solar and Wind: Hybrid Energy System Connected to the Grid Reduces Voltage Fluctuation and Improve Reliability","authors":"P. Dhal","doi":"10.1109/i-PACT52855.2021.9697020","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9697020","url":null,"abstract":"A practical energy management method for a small-scale hybrid wind-solar-battery power system is proposed in this research. To evaluate the performance of a hybrid micro grid, dc-dc converter and controllers were built together with wind and solar power conversion and energy storage technologies. The hybrid power system is configured to run at unity power factor, and the Maximum Power Point Tracking (MPPT) methodology is used to control the output voltage as the weather shifts. An energy management system maintains the power balance for fluctuations in renewable energy sources power generation as well as load demand fluctuations. However, this proposed system improved reliability; reduce voltage fluctuations due to various irradiations and wind speed combined with the main grid. The battery with a DC-DC converter is incorporated into the main power system by a 3– - inverter and also the battery is used to store the energy in normal condition and deliver the energy when not available from the sources.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130011319","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：