Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085237
N. Kalpana
Artificial Bee Colony (ABC) method is explored in this paper to solve optimum power flow (OPF) problems in power systems by using a static VAR compensator (SVC). With the usage of ABC the system can reduces the overall generating cost of a power system by employing SVC devices; in addition to that it also maintains Voltage stability. The ABC is developed which is influenced by honey bees' browsing behavior in the discovery of the appropriate nectars. It is a newly developed optimization algorithm in power systems. The suggested ABC method was compared to existing optimization algorithms on IEEE 11-bus & IEEE 30-bus systems to examine how effectively it functioned. Result shows that to handle nonlinear problems in power systems, ABC can be strongly accepted it is widely used in power systems.
{"title":"A Novel Technique for Evaluating Optimal Power Flow and SVC Performance using the ABC Algorithm","authors":"N. Kalpana","doi":"10.1109/ICEARS56392.2023.10085237","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085237","url":null,"abstract":"Artificial Bee Colony (ABC) method is explored in this paper to solve optimum power flow (OPF) problems in power systems by using a static VAR compensator (SVC). With the usage of ABC the system can reduces the overall generating cost of a power system by employing SVC devices; in addition to that it also maintains Voltage stability. The ABC is developed which is influenced by honey bees' browsing behavior in the discovery of the appropriate nectars. It is a newly developed optimization algorithm in power systems. The suggested ABC method was compared to existing optimization algorithms on IEEE 11-bus & IEEE 30-bus systems to examine how effectively it functioned. Result shows that to handle nonlinear problems in power systems, ABC can be strongly accepted it is widely used in power systems.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121116061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085006
V.P Premkkumar, C. Gayathri, P. Priyadharshini, G. Praveenkumar
The fish industry is currently thriving on the market. Their farmers are in need of increasing fish production. Fish are grown in contaminated lakes, ponds, and tanks. This environment affects the fish’s health and results in unhygienic fish growth. Water quality is salient to aquaculture and its ability to lead to a favorable outcome. There are many factors that affect water quality, like sedimentation, runoff, erosion, temperature, pH, and decayed fish. Water quality is dependent on various physical-chemical and biological factors that affect it and, as a result, its aptness for fish and other aquatic animals are produced and distributed. The many factors, such as fish density, feed quality, and feeding intervals, have an impact on aquaculture. Automated water quality monitoring tests are used in the aquaculture sector to evaluate the ponds water quality. The test, which is expensive, can only be performed by trained personnel. This study is based on cutting-edge technology. Innovations in fish farming are being made possible by the Internet of Things (IoT) by using Thingspeak platform, Artificial intelligence (AI), and Blockchain technology. This method presents a smart aquaculture system that uses AI and IoT will enhance fish farming. IoT is a highly used technology in aquaculture because it helps with monitoring and traceable water quality. Sensors were integrated to measure real-time data to analyse the pH level, dissolve oxygen, temperature, turbidity, and total solid dissolution. Save time and reduce fish mortality by using this system. This intention aided in the classification of two types of fish illnesses. There are two: Epizootic Ulcerative Syndrome (EUS) and Ichthyophthirus (Ich). This system uses a motion sensor to inspect the movement of fish and stores the data in an Arduino cloud application. An Android phone is used as a terminal device to alert them when it reaches unhygienic environmental conditions, and they can also monitor their pond whenever needed. The aquaponics system of the future will become more intelligent, intensive, precise, and efficient as a result of this technological advancement.
{"title":"AI & IoT based Control and Traceable Aquaculture with Secured Data using Blockchain Technology","authors":"V.P Premkkumar, C. Gayathri, P. Priyadharshini, G. Praveenkumar","doi":"10.1109/ICEARS56392.2023.10085006","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085006","url":null,"abstract":"The fish industry is currently thriving on the market. Their farmers are in need of increasing fish production. Fish are grown in contaminated lakes, ponds, and tanks. This environment affects the fish’s health and results in unhygienic fish growth. Water quality is salient to aquaculture and its ability to lead to a favorable outcome. There are many factors that affect water quality, like sedimentation, runoff, erosion, temperature, pH, and decayed fish. Water quality is dependent on various physical-chemical and biological factors that affect it and, as a result, its aptness for fish and other aquatic animals are produced and distributed. The many factors, such as fish density, feed quality, and feeding intervals, have an impact on aquaculture. Automated water quality monitoring tests are used in the aquaculture sector to evaluate the ponds water quality. The test, which is expensive, can only be performed by trained personnel. This study is based on cutting-edge technology. Innovations in fish farming are being made possible by the Internet of Things (IoT) by using Thingspeak platform, Artificial intelligence (AI), and Blockchain technology. This method presents a smart aquaculture system that uses AI and IoT will enhance fish farming. IoT is a highly used technology in aquaculture because it helps with monitoring and traceable water quality. Sensors were integrated to measure real-time data to analyse the pH level, dissolve oxygen, temperature, turbidity, and total solid dissolution. Save time and reduce fish mortality by using this system. This intention aided in the classification of two types of fish illnesses. There are two: Epizootic Ulcerative Syndrome (EUS) and Ichthyophthirus (Ich). This system uses a motion sensor to inspect the movement of fish and stores the data in an Arduino cloud application. An Android phone is used as a terminal device to alert them when it reaches unhygienic environmental conditions, and they can also monitor their pond whenever needed. The aquaponics system of the future will become more intelligent, intensive, precise, and efficient as a result of this technological advancement.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114956140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085297
C. Mythili, M. Yazhini Nivethitha
This paper makes a fundamental advancement in the field of Very Large Scale Integration by proposing an autonomous and evolutionary method for building diverse LOD and LOPD circuits (VLSI). Furthermore, there are a few efficient methods for constructing higher-order LODs and LOPDs from the evolved lower-order circuits. As a result, performance has been proven to increase with gate-level rise in LOD and LOPD circuits. The synthesis findings also show that, as a result of the optimized architecture, our system has the lowest latency. In future, the power consumption and the number of transistor will be further reduced to reduce the area.
{"title":"Design and Methodology of LOD and LOPD using Evolutionary Algorithm","authors":"C. Mythili, M. Yazhini Nivethitha","doi":"10.1109/ICEARS56392.2023.10085297","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085297","url":null,"abstract":"This paper makes a fundamental advancement in the field of Very Large Scale Integration by proposing an autonomous and evolutionary method for building diverse LOD and LOPD circuits (VLSI). Furthermore, there are a few efficient methods for constructing higher-order LODs and LOPDs from the evolved lower-order circuits. As a result, performance has been proven to increase with gate-level rise in LOD and LOPD circuits. The synthesis findings also show that, as a result of the optimized architecture, our system has the lowest latency. In future, the power consumption and the number of transistor will be further reduced to reduce the area.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"2009 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123772762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085115
Ramprabu J, Dharan Babu E, Rithika J C, Thavamuthu P S
To suggest a hybrid AC/DC source that would eliminate the need for numerous dc-ac-dc or ac-dc-ac conversions in a single ac or dc grid. In the modern era, the population of people is more. Employment has increased. The number of industries and factories set up in India has increased in recent days. Also, there is lots of work to be done and therefore the need for energy consumption is being increased. In upcoming days, the electricity production in India might be privatized. Cost of production may increase. Hence, there might be a chance of demand in production. The occurrence of power cuts has increased due to this. In order to correct this issue, if moved to renewable energy resources, it will be a better solution to manage and use power in a more efficient way. A hybrid renewable energy source combines one or more renewable energy sources, such solar and wind, to increase system efficiency and improve energy supply reliability to some extent. The interleaved landsman converter will produce steady output voltage and current for the load from the sources linked to it. In the simulation test, the interleaved landsman converter stabilizes the renewable resource energy; if the primary hybrid source fails, the secondary battery source, which is charged by the solar panel, negates it. Wind and solar energy are combined and used as hybrid energy sources. The proposed model is implemented in MATLAB simulation.
建议采用混合AC/DC电源，以消除在单个交流或直流电网中进行大量DC - AC - DC或AC - DC - AC转换的需要。在现代，人口越来越多。就业增加。最近几天，在印度设立的工业和工厂数量有所增加。此外，还有很多工作要做，因此对能源消耗的需求正在增加。在未来的日子里，印度的电力生产可能会私有化。生产成本可能会增加。因此，生产中可能会有需求。因此，停电事件也随之增加。为了纠正这个问题，如果转移到可再生能源，它将是一个更好的解决方案，以更有效的方式管理和使用电力。混合可再生能源将太阳能、风能等一种或多种可再生能源组合在一起，在一定程度上提高系统效率，提高能源供应的可靠性。交错的landsman变换器将产生稳定的输出电压和电流从连接到它的源负载。在仿真试验中，交错式陆人变换器稳定了可再生能源;如果主混合电源发生故障，由太阳能电池板充电的二次电池电源就会使其失效。风能和太阳能被结合起来作为混合能源使用。在MATLAB仿真中实现了该模型。
{"title":"Energy Management System based on Interleaved Landsman Converter using Hybrid Energy Sources","authors":"Ramprabu J, Dharan Babu E, Rithika J C, Thavamuthu P S","doi":"10.1109/ICEARS56392.2023.10085115","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085115","url":null,"abstract":"To suggest a hybrid AC/DC source that would eliminate the need for numerous dc-ac-dc or ac-dc-ac conversions in a single ac or dc grid. In the modern era, the population of people is more. Employment has increased. The number of industries and factories set up in India has increased in recent days. Also, there is lots of work to be done and therefore the need for energy consumption is being increased. In upcoming days, the electricity production in India might be privatized. Cost of production may increase. Hence, there might be a chance of demand in production. The occurrence of power cuts has increased due to this. In order to correct this issue, if moved to renewable energy resources, it will be a better solution to manage and use power in a more efficient way. A hybrid renewable energy source combines one or more renewable energy sources, such solar and wind, to increase system efficiency and improve energy supply reliability to some extent. The interleaved landsman converter will produce steady output voltage and current for the load from the sources linked to it. In the simulation test, the interleaved landsman converter stabilizes the renewable resource energy; if the primary hybrid source fails, the secondary battery source, which is charged by the solar panel, negates it. Wind and solar energy are combined and used as hybrid energy sources. The proposed model is implemented in MATLAB simulation.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114607321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085245
Dharanaesh M, V. Pushpalatha, Yughendaran P, Janarthanan S, Dinesh A
Fatigue or drowsiness is a significant factor that contributes to the occurrence of terrible road accidents. Every day, the number of fatal injuries increases day by day. The paper introduces a novel experimental model that aims to reduce the frequency of accidents by detecting driver drowsiness while also recommending songs based on facial emotions. The existing models use more hardware than necessary, leading to more cost and also do not provide as much accuracy. The proposed system aims to enhance the overall experience by reducing both the computational time required to obtain results and the overall cost of the system. For that, this study has developed a real-time information processing system that captures the video from the car dash camera. Then, an object detection algorithm will be employed to extract multiple facial parts from each frame using a pre-trained deep learning model from image processing libraries like OpenCV. Then, there is MobileNetV2, a lightweight convolutional neural network model that performs transfer learning by freezing feature extraction layers and creating custom dense layers for facial emotion classification, with output labels of happiness, sadness, fear, anger, surprise, disgust, sleepiness, and neutral. The driver's face will be identified using directional analysis from multiple facial parts in a single frame to carry out drowsiness detection to avoid accidents. Then, according to the emotion predicted by multiple users, the application will fetch a playlist of songs from Spotify through a Spotify wrapper and recommend the songs by displaying them on the car's dash screen. Finally, the model will be optimized using various optimization techniques to run on low-latency embedded devices.
{"title":"Video based Facial Emotion Recognition System using Deep Learning","authors":"Dharanaesh M, V. Pushpalatha, Yughendaran P, Janarthanan S, Dinesh A","doi":"10.1109/ICEARS56392.2023.10085245","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085245","url":null,"abstract":"Fatigue or drowsiness is a significant factor that contributes to the occurrence of terrible road accidents. Every day, the number of fatal injuries increases day by day. The paper introduces a novel experimental model that aims to reduce the frequency of accidents by detecting driver drowsiness while also recommending songs based on facial emotions. The existing models use more hardware than necessary, leading to more cost and also do not provide as much accuracy. The proposed system aims to enhance the overall experience by reducing both the computational time required to obtain results and the overall cost of the system. For that, this study has developed a real-time information processing system that captures the video from the car dash camera. Then, an object detection algorithm will be employed to extract multiple facial parts from each frame using a pre-trained deep learning model from image processing libraries like OpenCV. Then, there is MobileNetV2, a lightweight convolutional neural network model that performs transfer learning by freezing feature extraction layers and creating custom dense layers for facial emotion classification, with output labels of happiness, sadness, fear, anger, surprise, disgust, sleepiness, and neutral. The driver's face will be identified using directional analysis from multiple facial parts in a single frame to carry out drowsiness detection to avoid accidents. Then, according to the emotion predicted by multiple users, the application will fetch a playlist of songs from Spotify through a Spotify wrapper and recommend the songs by displaying them on the car's dash screen. Finally, the model will be optimized using various optimization techniques to run on low-latency embedded devices.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123889716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085310
Vishwas Dehankar, Pranjali M. Jumle, S. Tadse
The goal of this study is to demonstrate a non- invasive method for assessing driver tiredness and yawning utilising behavioural and vehicle-based methodologies. Today's traffic accidents occur as the result of driver negligence. The drivers gross recklessness and intoxicated behaviour were on display. On this problem many research works was going on to overcome such accidents, which depends on abnormal behaviour of drivers, drunken driver detections, and many more. The driver tiredness and yawning detection system is one of the research work on the same domain which employs a Raspberry Pi microcontroller to focus on the driver's unusual behaviour. The suggested method uses computer vision techniques to provide a non- intrusive driver drowsiness and yawning monitoring system. The system can detect driver fatigue in two to three seconds, irrespective of whether driver is wearing spectacles or the inside of the vehicle is dark.
{"title":"Design of Drowsiness and Yawning Detection System","authors":"Vishwas Dehankar, Pranjali M. Jumle, S. Tadse","doi":"10.1109/ICEARS56392.2023.10085310","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085310","url":null,"abstract":"The goal of this study is to demonstrate a non- invasive method for assessing driver tiredness and yawning utilising behavioural and vehicle-based methodologies. Today's traffic accidents occur as the result of driver negligence. The drivers gross recklessness and intoxicated behaviour were on display. On this problem many research works was going on to overcome such accidents, which depends on abnormal behaviour of drivers, drunken driver detections, and many more. The driver tiredness and yawning detection system is one of the research work on the same domain which employs a Raspberry Pi microcontroller to focus on the driver's unusual behaviour. The suggested method uses computer vision techniques to provide a non- intrusive driver drowsiness and yawning monitoring system. The system can detect driver fatigue in two to three seconds, irrespective of whether driver is wearing spectacles or the inside of the vehicle is dark.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122346160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085187
M. Shunmathi, S. Fusic, V. Jayshree, K.J.V. Aishwarya, G. Sharanya
A high gain Z-Source converter including an active switching capacitor is used in the solar system's front-end power conversion stage to produce the required DC bus voltage. A Z-source DC-DC converter with a high step-up capabilities and few device voltage stress is shown in the study. The converter is operating in discontinuous conduction mode (DCM). In comparison to a conventional converter, the model that was designed can increase voltage gain at the same duty ratio while decreasing voltage stress on the switch and diode at the same output condition. The structure of the converter is simple and the voltage stress on the extra capacitor and diode are lesser. The simulation findings validate the study and the converter's boost capacity.
{"title":"Solar PV based High Gain Converter for Microgrid Applications","authors":"M. Shunmathi, S. Fusic, V. Jayshree, K.J.V. Aishwarya, G. Sharanya","doi":"10.1109/ICEARS56392.2023.10085187","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085187","url":null,"abstract":"A high gain Z-Source converter including an active switching capacitor is used in the solar system's front-end power conversion stage to produce the required DC bus voltage. A Z-source DC-DC converter with a high step-up capabilities and few device voltage stress is shown in the study. The converter is operating in discontinuous conduction mode (DCM). In comparison to a conventional converter, the model that was designed can increase voltage gain at the same duty ratio while decreasing voltage stress on the switch and diode at the same output condition. The structure of the converter is simple and the voltage stress on the extra capacitor and diode are lesser. The simulation findings validate the study and the converter's boost capacity.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128874633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10084970
Akshali Jain, Mehul Jain, Mayank Patel, N. Rathore
To solve the problems that occur during the training of coal mining, this study has developed a VR-based user interactive solution with which immersive virtual training will be provided to the miners before going into real fieldwork, and workers can get the in-handed experience of safety and precautions in coal mines. VR solutions for underground coal mining training can help the workers to skill up their workforce, especially for the young miners and better life-saving training. Maximum of the present VR-based education structures are lacking in a learning enjoy. But these structures adopt training and mastering functions via player interatcion with the assist of 3D coal mine VR schooling models. The system can be efficiently implemented in a laboratory environment. The proposed model provides four types of training - Coal digging and Loading, Fire rescue operation, Disaster scenario, and mechanical operations. In all these operations, after wearing the VR headset instructions will be provided to the users step by step on what they must do accordingly. With the help of this solution, miners can be trained to save their lives and handle the disastrous situation in coal mines. This will be a complete training for new miners.
{"title":"An Enhanced and Interactive Training Model for Underground Coal Mines Using Virtual Reality","authors":"Akshali Jain, Mehul Jain, Mayank Patel, N. Rathore","doi":"10.1109/ICEARS56392.2023.10084970","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10084970","url":null,"abstract":"To solve the problems that occur during the training of coal mining, this study has developed a VR-based user interactive solution with which immersive virtual training will be provided to the miners before going into real fieldwork, and workers can get the in-handed experience of safety and precautions in coal mines. VR solutions for underground coal mining training can help the workers to skill up their workforce, especially for the young miners and better life-saving training. Maximum of the present VR-based education structures are lacking in a learning enjoy. But these structures adopt training and mastering functions via player interatcion with the assist of 3D coal mine VR schooling models. The system can be efficiently implemented in a laboratory environment. The proposed model provides four types of training - Coal digging and Loading, Fire rescue operation, Disaster scenario, and mechanical operations. In all these operations, after wearing the VR headset instructions will be provided to the users step by step on what they must do accordingly. With the help of this solution, miners can be trained to save their lives and handle the disastrous situation in coal mines. This will be a complete training for new miners.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124763654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085032
Ravi Mohan, S. Chalasani, S. Suma Christal Mary, Amit Chauhan, S. Parte, S. Anusuya
In the field of accident avoidance systems, figuring out how to keep drivers from getting sleepy is a major challenge. The only way to prevent dozing off behind the wheel is to have a system in place that can accurately detect when a driver's attention has drifted and then alert and revive them. This paper presents a method for detection that makes use of image processing software to examine video camera stills of the driver's face. Driver inattention is measured by how much the eyes are open or closed. This paper introduces Regularized Extreme Learning Machine, a novel approach based on the structural risk reduction principle and weighted least squares, which is applied following preprocessing, binarization, and noise removal. Generalization performance was significantly improved in most cases using the proposed algorithm without requiring additional training time. This approach outperforms both the CNN and ELM models, with an accuracy of around 99% being achieved.
{"title":"Identification of Driver Drowsiness Detection using a Regularized Extreme Learning Machine","authors":"Ravi Mohan, S. Chalasani, S. Suma Christal Mary, Amit Chauhan, S. Parte, S. Anusuya","doi":"10.1109/ICEARS56392.2023.10085032","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085032","url":null,"abstract":"In the field of accident avoidance systems, figuring out how to keep drivers from getting sleepy is a major challenge. The only way to prevent dozing off behind the wheel is to have a system in place that can accurately detect when a driver's attention has drifted and then alert and revive them. This paper presents a method for detection that makes use of image processing software to examine video camera stills of the driver's face. Driver inattention is measured by how much the eyes are open or closed. This paper introduces Regularized Extreme Learning Machine, a novel approach based on the structural risk reduction principle and weighted least squares, which is applied following preprocessing, binarization, and noise removal. Generalization performance was significantly improved in most cases using the proposed algorithm without requiring additional training time. This approach outperforms both the CNN and ELM models, with an accuracy of around 99% being achieved.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125689108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-02DOI: 10.1109/ICEARS56392.2023.10085676
Mohammad Qamar, Hamnah Rao, Sheikh Afaan Farooq, Ajatray Swagat Bhuyan
The practice of finding emotion embedded in textual data is known as sentiment analysis, sometimes known as opinion mining. Various sentiment analysis algorithms, including classic Machine Learning models and Deep Learning models, have been suggested up until now. Some Machine Learning-based models, such as Naive Bayes, Decision Tree, SVM, and others, have demonstrated exceptional performance in sentiment categorization. Although Machine Learning algorithms have demonstrated high performance, they are constrained by the quantity of the dataset employed and include feature extraction tasks, which are time demanding. As a result, this study considers Deep Learning (DL)-based models, which include automated feature extraction and can handle massive amounts of data. One of the major issues with existing sentiment analysis models is that they are domain-dependent; hence, if there is a dataset available from a domain on which the model was not trained on, its accuracy is significantly reduced. To make the model domain agnostic, it is trained on datasets from three distinct domains: Twitter US Airline Review dataset, the IMDb Movie Review dataset, and the US Presidential Election dataset. The suggested sentiment analysis model is trained on five different deep learning models: CNN-GRU, CNN-LSTM, CNN, LSTM and GRU. The model's performance was evaluated using test data from three datasets on which the model was trained, as well as a fresh book review dataset scraped from the Amazon website.
{"title":"Sentiment Analysis using Deep Learning: A Domain Independent Approach","authors":"Mohammad Qamar, Hamnah Rao, Sheikh Afaan Farooq, Ajatray Swagat Bhuyan","doi":"10.1109/ICEARS56392.2023.10085676","DOIUrl":"https://doi.org/10.1109/ICEARS56392.2023.10085676","url":null,"abstract":"The practice of finding emotion embedded in textual data is known as sentiment analysis, sometimes known as opinion mining. Various sentiment analysis algorithms, including classic Machine Learning models and Deep Learning models, have been suggested up until now. Some Machine Learning-based models, such as Naive Bayes, Decision Tree, SVM, and others, have demonstrated exceptional performance in sentiment categorization. Although Machine Learning algorithms have demonstrated high performance, they are constrained by the quantity of the dataset employed and include feature extraction tasks, which are time demanding. As a result, this study considers Deep Learning (DL)-based models, which include automated feature extraction and can handle massive amounts of data. One of the major issues with existing sentiment analysis models is that they are domain-dependent; hence, if there is a dataset available from a domain on which the model was not trained on, its accuracy is significantly reduced. To make the model domain agnostic, it is trained on datasets from three distinct domains: Twitter US Airline Review dataset, the IMDb Movie Review dataset, and the US Presidential Election dataset. The suggested sentiment analysis model is trained on five different deep learning models: CNN-GRU, CNN-LSTM, CNN, LSTM and GRU. The model's performance was evaluated using test data from three datasets on which the model was trained, as well as a fresh book review dataset scraped from the Amazon website.","PeriodicalId":338611,"journal":{"name":"2023 Second International Conference on Electronics and Renewable Systems (ICEARS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126049043","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：