Pub Date : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073849
Siva Prasad Reddy K.V, Archana K.S
Melanoma is considered as a most lethal form of cancer. Design and development of computer-aided intelligent algorithms for early detection of skin cancer is the emerging research area. Despite many conventional mechanisms, a new type of cancer caused by unrepaired Deoxyribonucleic acid (DNA) within the skin cells. Due to its nature of rapid genetic mutations on the skin, it widely affects other body parts if not treated at early stages of intelligent computing evidenced the development of automated medical diagnosis and recommendation systems. It is possible to identify between melanoma and other classification of skin cancer based on the symmetry, color, size, form, and other characteristics of lesions. Numerous efforts are made by many researchers to develop various deep learning and machine learning inspired classification and segmentation algorithms to analyses skin lesion images. In existing the algorithm used for this research was naïve bayes, support vector machine etc. Here, after several methods such as data pre-processing, image segmentation, feature extraction and the feature extraction and the proposed algorithm of adaboost method, which is used to tune the algorithm to predict the skin infection. Finally, the proposed model has achieved 92.5% accuracy when compared with existing work.
{"title":"Basal Cell Carcinoma Prediction in Pigmented Skin Infection using Intelligent Techniques","authors":"Siva Prasad Reddy K.V, Archana K.S","doi":"10.1109/ICAIS56108.2023.10073849","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073849","url":null,"abstract":"Melanoma is considered as a most lethal form of cancer. Design and development of computer-aided intelligent algorithms for early detection of skin cancer is the emerging research area. Despite many conventional mechanisms, a new type of cancer caused by unrepaired Deoxyribonucleic acid (DNA) within the skin cells. Due to its nature of rapid genetic mutations on the skin, it widely affects other body parts if not treated at early stages of intelligent computing evidenced the development of automated medical diagnosis and recommendation systems. It is possible to identify between melanoma and other classification of skin cancer based on the symmetry, color, size, form, and other characteristics of lesions. Numerous efforts are made by many researchers to develop various deep learning and machine learning inspired classification and segmentation algorithms to analyses skin lesion images. In existing the algorithm used for this research was naïve bayes, support vector machine etc. Here, after several methods such as data pre-processing, image segmentation, feature extraction and the feature extraction and the proposed algorithm of adaboost method, which is used to tune the algorithm to predict the skin infection. Finally, the proposed model has achieved 92.5% accuracy when compared with existing work.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130338225","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073708
K. M, Jones Nirmal L, Jenin Prabhu R, S. P
The MPPT controller of a photovoltaic (PV) system fluctuates, increasing solar irradiance, and has complex voltage-current properties. To balance the solar PV system towards the load and design the solar energy system on MPPT, a two-cell interleaved DC-DC boost connected with an inverter is utilized. Using just load voltage statistics, a voltage control technique is created, excluding array current monitoring. When compared to non-coupled pair interleaved conversions, the current conversion design has lower ripple contents from the loads and supply sides, better efficiency, as well as lower switch stress. Consequently, a decreased array capacitance value is enough to stabilize the array voltage output. For maximum power point functioning, analytical formulas for the solar supply and interleaved boost converter are constructed. The power interleaved converter is functioning using the control technique of MPPT, the Perturb and Observe (P&O) algorithm is employed, and the power is supplied to the alternating voltage conversion, and it is connected to the voltage source converter. The modeling and experimental findings are presented here to demonstrate how well suited that particular kind of power converter is for the application. In addition, a comparison of coupled and non-coupled interleaved boost converters for solar applications is performed.
{"title":"Photovoltaic System based Interleaved Converter for Grid System","authors":"K. M, Jones Nirmal L, Jenin Prabhu R, S. P","doi":"10.1109/ICAIS56108.2023.10073708","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073708","url":null,"abstract":"The MPPT controller of a photovoltaic (PV) system fluctuates, increasing solar irradiance, and has complex voltage-current properties. To balance the solar PV system towards the load and design the solar energy system on MPPT, a two-cell interleaved DC-DC boost connected with an inverter is utilized. Using just load voltage statistics, a voltage control technique is created, excluding array current monitoring. When compared to non-coupled pair interleaved conversions, the current conversion design has lower ripple contents from the loads and supply sides, better efficiency, as well as lower switch stress. Consequently, a decreased array capacitance value is enough to stabilize the array voltage output. For maximum power point functioning, analytical formulas for the solar supply and interleaved boost converter are constructed. The power interleaved converter is functioning using the control technique of MPPT, the Perturb and Observe (P&O) algorithm is employed, and the power is supplied to the alternating voltage conversion, and it is connected to the voltage source converter. The modeling and experimental findings are presented here to demonstrate how well suited that particular kind of power converter is for the application. In addition, a comparison of coupled and non-coupled interleaved boost converters for solar applications is performed.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"58 30","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114000136","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073860
M. Karthik, R. Vishnu, M. Vigneshwar, M. Logaeshwar
One of the most important concerns across the globe is energy crisis. The potential solution for this problem is renewable energy. In recent years, solar panels have been employed more frequently to transform solar energy into electrical energy. It is reasonably priced and almost completely safe for the environment. The electromagnetic radiation that is used to produce electricity is released by it. The major goal is to develop a workable autonomous solar tracking system that moves the solar panel so that it remains always perpendicular to the sun. In this system, the sensor will be a photoresistor. The horizontal and the vertical axes on the dual axis solar panel are rotated, so that the efficiency of the device can be increased. Hence, the dual axis provides precise control of planet elevation relative to the sun. This will provide better efficiency of the panel.
{"title":"Arduino based Dual Axis Smart Solar Tracking System","authors":"M. Karthik, R. Vishnu, M. Vigneshwar, M. Logaeshwar","doi":"10.1109/ICAIS56108.2023.10073860","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073860","url":null,"abstract":"One of the most important concerns across the globe is energy crisis. The potential solution for this problem is renewable energy. In recent years, solar panels have been employed more frequently to transform solar energy into electrical energy. It is reasonably priced and almost completely safe for the environment. The electromagnetic radiation that is used to produce electricity is released by it. The major goal is to develop a workable autonomous solar tracking system that moves the solar panel so that it remains always perpendicular to the sun. In this system, the sensor will be a photoresistor. The horizontal and the vertical axes on the dual axis solar panel are rotated, so that the efficiency of the device can be increased. Hence, the dual axis provides precise control of planet elevation relative to the sun. This will provide better efficiency of the panel.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115023362","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073890
Jenyfal Sampson, R. Nandakishore Reddy, M. Venkata Janardhan Reddy, Myla Chandra Narayana, R. Varun Kumar
The purpose of this study is to predict the flood at the dams and alerting the authorities to make them the people who are living their lives in remote areas i.e., near to the dam to the safer place, so that to reduce the mortality rate due to unprecedented flood. This study predicts the flood by using sensor-based networking system. Here, two ultrasonic sensors are connected to determine the level of water; waterflow sensor is used to know the speed of water; rainfall sensor is used to determine the rainfall. After measuring all the factors, the data is processed to the NodeMCU, which will act as a transmitter and it will transfer the data through the wireless communication to the another NodeMCU, which was situated at the office present at the dam and it will act as a receiver. After analyzing all the values, if the values exceed the limit, an alert will be sent to the authorities and then automatically the dam gates will get open.
{"title":"IoT based Early Flood Detection, Destruction Avoidance and Automated Dam Gate Control System","authors":"Jenyfal Sampson, R. Nandakishore Reddy, M. Venkata Janardhan Reddy, Myla Chandra Narayana, R. Varun Kumar","doi":"10.1109/ICAIS56108.2023.10073890","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073890","url":null,"abstract":"The purpose of this study is to predict the flood at the dams and alerting the authorities to make them the people who are living their lives in remote areas i.e., near to the dam to the safer place, so that to reduce the mortality rate due to unprecedented flood. This study predicts the flood by using sensor-based networking system. Here, two ultrasonic sensors are connected to determine the level of water; waterflow sensor is used to know the speed of water; rainfall sensor is used to determine the rainfall. After measuring all the factors, the data is processed to the NodeMCU, which will act as a transmitter and it will transfer the data through the wireless communication to the another NodeMCU, which was situated at the office present at the dam and it will act as a receiver. After analyzing all the values, if the values exceed the limit, an alert will be sent to the authorities and then automatically the dam gates will get open.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114808342","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073810
J. Manju, R. Manjula, Ritesh Dash
In order to maintain a balance between demand and supply, the Internet of Things (IoT) enabled Smart Grid (SG) plays a critical role in establishing a Demand Response (DR) program. It is all about Demand Side Management (DSM) in SG’s system. When IoT gadgets are programmed to turn on and off according to supply and demand, they become an essential part of the smart grid load prediction system and help to balance energy use. This research use Artificial Bee Colony (ABC) optimization model for load prediction in the smart grid environment. To effectively predict the load in the SG, an Efficient Artificial Bee Colony Optimized Model for Load Prediction in Smart Grid (EABCOM-LPSG) model is proposed in this research. The Artificial Bee Colony (ABC) algorithm is as warm-based meta-heuristic technique used for numerical problem optimization. It was inspired by honey bees’ clever foraging behavior. The proposed method’s two-step prediction system, specifically developed to improve forecasting precision as one of its major advantages. A major benefit of the suggested method is that it can statistically examine the effects of several major aspects, which is extremely useful when selecting attribute combinations and deploying on-board sensors for smart grids with large areas, diverse climates, and different social conventions. The proposed model when contrasted with traditional model exhibits better performance levels.
{"title":"An Efficient Artificial Bee Colony based Optimized Model for Load Prediction in IoT Enabled Smart Grid","authors":"J. Manju, R. Manjula, Ritesh Dash","doi":"10.1109/ICAIS56108.2023.10073810","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073810","url":null,"abstract":"In order to maintain a balance between demand and supply, the Internet of Things (IoT) enabled Smart Grid (SG) plays a critical role in establishing a Demand Response (DR) program. It is all about Demand Side Management (DSM) in SG’s system. When IoT gadgets are programmed to turn on and off according to supply and demand, they become an essential part of the smart grid load prediction system and help to balance energy use. This research use Artificial Bee Colony (ABC) optimization model for load prediction in the smart grid environment. To effectively predict the load in the SG, an Efficient Artificial Bee Colony Optimized Model for Load Prediction in Smart Grid (EABCOM-LPSG) model is proposed in this research. The Artificial Bee Colony (ABC) algorithm is as warm-based meta-heuristic technique used for numerical problem optimization. It was inspired by honey bees’ clever foraging behavior. The proposed method’s two-step prediction system, specifically developed to improve forecasting precision as one of its major advantages. A major benefit of the suggested method is that it can statistically examine the effects of several major aspects, which is extremely useful when selecting attribute combinations and deploying on-board sensors for smart grids with large areas, diverse climates, and different social conventions. The proposed model when contrasted with traditional model exhibits better performance levels.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114468079","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073660
Jieqi Li, Shaoqiang Guo, Wei Li
Monitoring the combined structural stability under different scenario is an essential task for the security, hence, this paper designs the novel nighttime monitoring system for combined structural stability based on the infrared image recognition. Firstly, this study discusses the infrared image recognition algorithm considering the different features and methods. Then, the combined structural feature is discussed to further assist the processing of images. Finally, the nighttime monitoring system is implemented with the designed image processing algorithm. The proposed model utilizes the SURF algorithm to select the features. Based on the integral image, the SURF algorithm uses the Hessian operator to detect and obtain feature points. Through the testing, the performance before and after the processing for the original image is presented. And through the analysis on ratio of the number of correctly tested samples, the model is proven to be effective.
{"title":"A Nighttime Monitoring System for Combined Structural Stability based on Infrared Image Recognition","authors":"Jieqi Li, Shaoqiang Guo, Wei Li","doi":"10.1109/ICAIS56108.2023.10073660","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073660","url":null,"abstract":"Monitoring the combined structural stability under different scenario is an essential task for the security, hence, this paper designs the novel nighttime monitoring system for combined structural stability based on the infrared image recognition. Firstly, this study discusses the infrared image recognition algorithm considering the different features and methods. Then, the combined structural feature is discussed to further assist the processing of images. Finally, the nighttime monitoring system is implemented with the designed image processing algorithm. The proposed model utilizes the SURF algorithm to select the features. Based on the integral image, the SURF algorithm uses the Hessian operator to detect and obtain feature points. Through the testing, the performance before and after the processing for the original image is presented. And through the analysis on ratio of the number of correctly tested samples, the model is proven to be effective.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115784508","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}
The capacity to talk smoothly is typically affected by stuttering, a neuro-developmental speech disorder where the flow of speech is disrupted by involuntary pauses and repetition of sounds. Stuttering can be cured by identifying the type of stutter and providing proper speech guidance. Many approaches have been taken to classify stuttered speech via a computer aided process including Deep Learning models. But most of the works rely heavily on a large number of audio features to be extracted manually. Also, many past works use the UCLASS dataset that is much older and lacks in quality. This paper proposes a Deep Learning model using Bidirectional LSTM and Attention to classify five types of stuttering events – Block, Prolongation, Word Repetition, Sound Repetition and Interjection, by utilizing only Mel-spectrogram audio feature. The model is trained and tested on the SEP-28k and latest annotations of the FluencyBank dataset to evaluate the performance and achieves an overall 75% accuracy.
{"title":"An Integrated Usage of Bidirectional LSTM and Computer-based Cognitive Attention to Categorize Speech Stutters","authors":"Krishna Basak, Vineet Sharma, Sarangh Ramesh Kv, Nilamadhab Mishra","doi":"10.1109/ICAIS56108.2023.10073818","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073818","url":null,"abstract":"The capacity to talk smoothly is typically affected by stuttering, a neuro-developmental speech disorder where the flow of speech is disrupted by involuntary pauses and repetition of sounds. Stuttering can be cured by identifying the type of stutter and providing proper speech guidance. Many approaches have been taken to classify stuttered speech via a computer aided process including Deep Learning models. But most of the works rely heavily on a large number of audio features to be extracted manually. Also, many past works use the UCLASS dataset that is much older and lacks in quality. This paper proposes a Deep Learning model using Bidirectional LSTM and Attention to classify five types of stuttering events – Block, Prolongation, Word Repetition, Sound Repetition and Interjection, by utilizing only Mel-spectrogram audio feature. The model is trained and tested on the SEP-28k and latest annotations of the FluencyBank dataset to evaluate the performance and achieves an overall 75% accuracy.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123485512","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073773
B. Gopi, J. Premalatha, R. Kalaivani, D. Ravikumar
Landslides are one of the most devastating natural disasters that can strike a region. They are caused by the movement of large amounts of earth, rock, and other material down a slope. Landslides are caused by rain, snow, and other precipitation that causes soil to become saturated and unable to support the loads that are placed on it. Landslides can also be triggered by earthquakes or human activities such as mining, construction, and quarrying. Internally generated Internet of Things network and system acquisition generation Landslides were detected using humidity sensors, accelerometers, and vibration sensors, as well as GPS and a siren to inform people. You may charge a little price for this sensor, and if the fee surpasses the basic cost, you can approximately watch people in preparation of an imminent landslide, and big losses are avoided. The microcontroller collects and updates statistics from websites using the MQTT protocol. These telemetry flights can assist folks become aware of an oncoming crisis and have a better understanding of the situation.
{"title":"Cloud based Landslide Detection and Alerting Nearby People by using IoT Technology","authors":"B. Gopi, J. Premalatha, R. Kalaivani, D. Ravikumar","doi":"10.1109/ICAIS56108.2023.10073773","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073773","url":null,"abstract":"Landslides are one of the most devastating natural disasters that can strike a region. They are caused by the movement of large amounts of earth, rock, and other material down a slope. Landslides are caused by rain, snow, and other precipitation that causes soil to become saturated and unable to support the loads that are placed on it. Landslides can also be triggered by earthquakes or human activities such as mining, construction, and quarrying. Internally generated Internet of Things network and system acquisition generation Landslides were detected using humidity sensors, accelerometers, and vibration sensors, as well as GPS and a siren to inform people. You may charge a little price for this sensor, and if the fee surpasses the basic cost, you can approximately watch people in preparation of an imminent landslide, and big losses are avoided. The microcontroller collects and updates statistics from websites using the MQTT protocol. These telemetry flights can assist folks become aware of an oncoming crisis and have a better understanding of the situation.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124678135","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073711
S. Gopi, Hari Kishan Kondaveeti
To feed the world’s population of 7.9 billion people, preventing crop failure through early disease detection is essential. Various bacterial, viral, or fungal diseases affect the rice leaf and these diseases drastically lower rice yield. Therefore, identifying rice leaf diseases is essential to meeting the demand for rice from an extensive worldwide population. However, the ability to identify rice leaf disease is constrained by the image backgrounds and the circumstances under which the images were captured. When tested on independent rice leaf diseased data, the performance of deep learning models for automated detection of rice leaf diseases suffers substantially. This stusy examines the results of well-known and widely used transfer learning models to detect the rice leaf disease. This can be done in two ways: frozen layers and fine-tuning. It was observed that the results of the freeze layers, the DenseNet169, achieved a good testing accuracy of 99.66%, and when the results of the fine-tuned transfer learning models were examined, Xception performed well and achieved 99.99% of testing accuracy.
{"title":"Transfer Learning for Rice Leaf Disease Detection","authors":"S. Gopi, Hari Kishan Kondaveeti","doi":"10.1109/ICAIS56108.2023.10073711","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073711","url":null,"abstract":"To feed the world’s population of 7.9 billion people, preventing crop failure through early disease detection is essential. Various bacterial, viral, or fungal diseases affect the rice leaf and these diseases drastically lower rice yield. Therefore, identifying rice leaf diseases is essential to meeting the demand for rice from an extensive worldwide population. However, the ability to identify rice leaf disease is constrained by the image backgrounds and the circumstances under which the images were captured. When tested on independent rice leaf diseased data, the performance of deep learning models for automated detection of rice leaf diseases suffers substantially. This stusy examines the results of well-known and widely used transfer learning models to detect the rice leaf disease. This can be done in two ways: frozen layers and fine-tuning. It was observed that the results of the freeze layers, the DenseNet169, achieved a good testing accuracy of 99.66%, and when the results of the fine-tuned transfer learning models were examined, Xception performed well and achieved 99.99% of testing accuracy.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124865631","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073903
Amanoollah Khurwolah, V. Oree
This paper presents the design and implementation of a dual-axis solar tracker that allows the PV panel on which it is mounted to capture maximum solar energy throughout the day. The device tracks the azimuth and elevation angles of the Sun as it moves across the sky to maintain the PV panel perpendicular to sunlight at all times. Four light sensors are used for this purpose and an Arduino microcontroller processes their signals to actuate driving mechanisms that maintain the orthogonal position of the PV panel with respect to sunlight. The mechanical structure of the solar tracker is designed in such a way as to minimize its inherent energy consumption so that the overall energy performance is optimized. The prototype is tested in the tropical island of Mauritius. Previous studies have shown that the energy performance of solar tracking systems is highly dependent on the climate, with negligible energy gain achieved in very hot regions. Results indicate that improvements of 30.5% and 28.5% in the total energy output of the PV panel are obtained compared to a fixed PV panel on a cloudy and sunny day respectively.
{"title":"Investigating the Performance of a Dual-Axis Solar Tracking System in a Tropical Climate","authors":"Amanoollah Khurwolah, V. Oree","doi":"10.1109/ICAIS56108.2023.10073903","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073903","url":null,"abstract":"This paper presents the design and implementation of a dual-axis solar tracker that allows the PV panel on which it is mounted to capture maximum solar energy throughout the day. The device tracks the azimuth and elevation angles of the Sun as it moves across the sky to maintain the PV panel perpendicular to sunlight at all times. Four light sensors are used for this purpose and an Arduino microcontroller processes their signals to actuate driving mechanisms that maintain the orthogonal position of the PV panel with respect to sunlight. The mechanical structure of the solar tracker is designed in such a way as to minimize its inherent energy consumption so that the overall energy performance is optimized. The prototype is tested in the tropical island of Mauritius. Previous studies have shown that the energy performance of solar tracking systems is highly dependent on the climate, with negligible energy gain achieved in very hot regions. Results indicate that improvements of 30.5% and 28.5% in the total energy output of the PV panel are obtained compared to a fixed PV panel on a cloudy and sunny day respectively.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122760461","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：