Pub Date : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140259
R. Kavitha, K. Akshatha
This Printed circuit board(PCBs) flaws are identified and detected using artificial intelligence. The necessity for effective and precise inspection procedures in the production of electronic devices is a result of the rising demand for high-quality electronic products. The suggested technique makes use of a deep learning model that was trained on digital microscope pictures of PCBs. The AI model can reliably recognize different components on the PCB and find any flaws, including broken trace lines, missing components, and improper component placement. With an average precision of 99.6% for component identification and an average precision of 98.7% for defect detection, the results demonstrate that the AI model performs with a high degree of accuracy. The effectiveness and dependability of PCB inspection and quality control processes can be greatly increased by putting this strategy into practice
{"title":"Component Identification and Defect Detection of Printed Circuit Board using Artificial Intelligence","authors":"R. Kavitha, K. Akshatha","doi":"10.1109/ICAAIC56838.2023.10140259","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140259","url":null,"abstract":"This Printed circuit board(PCBs) flaws are identified and detected using artificial intelligence. The necessity for effective and precise inspection procedures in the production of electronic devices is a result of the rising demand for high-quality electronic products. The suggested technique makes use of a deep learning model that was trained on digital microscope pictures of PCBs. The AI model can reliably recognize different components on the PCB and find any flaws, including broken trace lines, missing components, and improper component placement. With an average precision of 99.6% for component identification and an average precision of 98.7% for defect detection, the results demonstrate that the AI model performs with a high degree of accuracy. The effectiveness and dependability of PCB inspection and quality control processes can be greatly increased by putting this strategy into practice","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133614357","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140421
Angelin Jael E, Lalith V S, M. M S, R. Sundar
Disabled people face many problems in their daily life especially in communication with others. Since for many learning sign languages is not feasible or easy so this study looks into a method that will help dumb, deaf and partially paralyzed people to communicate with others without learning sign language. This study designs a device that help disabled people to communicate. The main questions are that how can device should always be within the reach of the patient. This research focuses on improving the lifestyle of disabled people. This topic is important to address because to bring equality for people from all walks of life. they must feel it. The most important task in this situation is to express themselves. This study looks for ways to make the existing devices more comfortable for the patients to use and to modify the technologies that are unsuitable. This study uses flex sensors that are stitched to a pair of gloves. The flex sensor signals are sent to LabVIEW via Arduino UNO, and the appropriate message for the finger bend is either displayed or heard. The use of Wi-Fi for transition is a huge boost in the area for transmission of the signals when compared to Bluetooth. This makes the gloves easier to use. The uses of Wi-Fi instead of increases the area of reception when compared to Bluetooth. Wi-Fi is faster as well as it has more coverage when it comes to range of transmission.
{"title":"Implementation of LabVIEW based Smart Assistive Gloves for Deaf and Dumb People","authors":"Angelin Jael E, Lalith V S, M. M S, R. Sundar","doi":"10.1109/ICAAIC56838.2023.10140421","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140421","url":null,"abstract":"Disabled people face many problems in their daily life especially in communication with others. Since for many learning sign languages is not feasible or easy so this study looks into a method that will help dumb, deaf and partially paralyzed people to communicate with others without learning sign language. This study designs a device that help disabled people to communicate. The main questions are that how can device should always be within the reach of the patient. This research focuses on improving the lifestyle of disabled people. This topic is important to address because to bring equality for people from all walks of life. they must feel it. The most important task in this situation is to express themselves. This study looks for ways to make the existing devices more comfortable for the patients to use and to modify the technologies that are unsuitable. This study uses flex sensors that are stitched to a pair of gloves. The flex sensor signals are sent to LabVIEW via Arduino UNO, and the appropriate message for the finger bend is either displayed or heard. The use of Wi-Fi for transition is a huge boost in the area for transmission of the signals when compared to Bluetooth. This makes the gloves easier to use. The uses of Wi-Fi instead of increases the area of reception when compared to Bluetooth. Wi-Fi is faster as well as it has more coverage when it comes to range of transmission.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128882383","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141027
Sakthi Kuhan, L. Grace
Tracking student data and complaints is critical to track student performance in the classroom even while studying. This research study aims to address the grievances of the students and presents the website as a portal built using Javascript, HTML, Python, and MySQL, where students may file concerns, and the department handling the case is notified. The student has complete access to the complaint's history and may see if it has been examined, investigated, sent, rejected, or handled. The proposed technique is totally transparent, and if a complaint remains unanswered for several days, the system will automatically transmit it to the person specified further up the hierarchy. Any correctional system should be concerned about language quality since it may be used to spread incorrect information by making comments about people's gender, color, or religion. Employing the state-of-the-art technologies like deep learning and machine learning helps to detect hate speech. After training 11,325 tweets and analyzing the outcomes using evaluation metrics including F1 score, recall, and precision. Bi-LSTM, LSTM, and SVM models are utilized. By reaching the metrics values of 0.884, 0.84, and 0.86, the LSTM model outscores the other models.
{"title":"Design and Implementation of Students Grievance and Database","authors":"Sakthi Kuhan, L. Grace","doi":"10.1109/ICAAIC56838.2023.10141027","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141027","url":null,"abstract":"Tracking student data and complaints is critical to track student performance in the classroom even while studying. This research study aims to address the grievances of the students and presents the website as a portal built using Javascript, HTML, Python, and MySQL, where students may file concerns, and the department handling the case is notified. The student has complete access to the complaint's history and may see if it has been examined, investigated, sent, rejected, or handled. The proposed technique is totally transparent, and if a complaint remains unanswered for several days, the system will automatically transmit it to the person specified further up the hierarchy. Any correctional system should be concerned about language quality since it may be used to spread incorrect information by making comments about people's gender, color, or religion. Employing the state-of-the-art technologies like deep learning and machine learning helps to detect hate speech. After training 11,325 tweets and analyzing the outcomes using evaluation metrics including F1 score, recall, and precision. Bi-LSTM, LSTM, and SVM models are utilized. By reaching the metrics values of 0.884, 0.84, and 0.86, the LSTM model outscores the other models.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134507422","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141283
J. Jayaudhaya, S. Supriya, Vijay Anand Kandaswamy, Samuthira Pandi V, S. Kamatchi, C. P. Priya
The Industrial Internet of Things (IIoT) requires the real-time transmission of critical data to ensure functionality and prevent hazardous situations. However, current data transmission scheduling methods in 6TiSCH networks do not efficiently handle heterogeneous traffic based on its criticality and performance requirements, potentially leading to violations of timing limits. To address this issue, this paper proposes ACoCo, an Adaptive Congestion Control approach for CoAP that uses reinforcement learning techniques to dynamically adapt congestion control parameters based on real-time network conditions, node behaviors, and traffic patterns. Simulation results demonstrate ACoCo's effectiveness in reducing end-to-end transaction delay and improving transaction delivery ratio under congested network conditions, providing valuable insights for IoT network optimization and design. ACoCo operates effectively within the 6TiSCH network architecture, taking into account the scheduling function and communication requirements of the network.
{"title":"ACoCo: An Adaptive Congestion Control Approach for Enhancing CoAP Performance in IoT Network","authors":"J. Jayaudhaya, S. Supriya, Vijay Anand Kandaswamy, Samuthira Pandi V, S. Kamatchi, C. P. Priya","doi":"10.1109/ICAAIC56838.2023.10141283","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141283","url":null,"abstract":"The Industrial Internet of Things (IIoT) requires the real-time transmission of critical data to ensure functionality and prevent hazardous situations. However, current data transmission scheduling methods in 6TiSCH networks do not efficiently handle heterogeneous traffic based on its criticality and performance requirements, potentially leading to violations of timing limits. To address this issue, this paper proposes ACoCo, an Adaptive Congestion Control approach for CoAP that uses reinforcement learning techniques to dynamically adapt congestion control parameters based on real-time network conditions, node behaviors, and traffic patterns. Simulation results demonstrate ACoCo's effectiveness in reducing end-to-end transaction delay and improving transaction delivery ratio under congested network conditions, providing valuable insights for IoT network optimization and design. ACoCo operates effectively within the 6TiSCH network architecture, taking into account the scheduling function and communication requirements of the network.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115724995","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140361
Kalai Priya V, Avinash Kumar, B. Muthuraj, S. Joshi, Bhushan Kumar, Nikhil Garg, A. Prasad
In the bifacial PERT base p solar cells (SCs) with floating junction in the boron backscatter field, it was found that the efficiency decreased with the increase of the sheet resistance of the boron BSF, when the devices were illuminated on the emitter. It was also found that the formation of the floating junction did not improve the SCs. The form factor was practically unaffected by the floating junction, however the S-C current density and the O-C voltage decreased. By analyzing the external quantum efficiency, it was found that the floating junction did not affect the passivation of the surface with the BSF, regardless of doping.
{"title":"Floating Junction Analysis in Bifacial Pert Solar Cells","authors":"Kalai Priya V, Avinash Kumar, B. Muthuraj, S. Joshi, Bhushan Kumar, Nikhil Garg, A. Prasad","doi":"10.1109/ICAAIC56838.2023.10140361","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140361","url":null,"abstract":"In the bifacial PERT base p solar cells (SCs) with floating junction in the boron backscatter field, it was found that the efficiency decreased with the increase of the sheet resistance of the boron BSF, when the devices were illuminated on the emitter. It was also found that the formation of the floating junction did not improve the SCs. The form factor was practically unaffected by the floating junction, however the S-C current density and the O-C voltage decreased. By analyzing the external quantum efficiency, it was found that the floating junction did not affect the passivation of the surface with the BSF, regardless of doping.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115778962","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140805
S. S, A. G, D. B. Radkar, Sachin Gee Paul, S. Abinandhan, K. Karthikeyan
Farming has an influence on the environment, so smart agriculture uses the most recent technology to maximise agricultural production. LoRaWAn is one such technology that is used in agriculture to automate soil moisture and temperature sensors, resulting in more effective agricultural techniques. The data is then wirelessly relayed from these sensors to a Lora WAN gateway, which sends it to a cloud-based platform for analysis. Farmers may make data-driven decisions about irrigation, fertiliser, and other farming operations by having access to this data through an intuitive interface. While there are many advantages to adopting Lora WAN technology in agriculture, one of them is that it is a more effective alternative to conventional methods because it lowers the cost and time required for data gathering and analysis. Also, it makes it possible to monitor crop conditions in real-time, allowing farmers to react swiftly to changes in the weather or other elements that can affect crop output. Also, because Lora WAN sensors consume so little power, they may stay out in the field for longer periods of time without needing to be frequently recharged By enabling real-time crop monitoring and optimization, the use of Lora WAN technology in agriculture offers the potential to increase agricultural yields and encourage more environmentally friendly farming methods.
{"title":"Strategy for Smart Growth in Agriculture based on LoRaWAN's Autonomous Tractors and Combines","authors":"S. S, A. G, D. B. Radkar, Sachin Gee Paul, S. Abinandhan, K. Karthikeyan","doi":"10.1109/ICAAIC56838.2023.10140805","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140805","url":null,"abstract":"Farming has an influence on the environment, so smart agriculture uses the most recent technology to maximise agricultural production. LoRaWAn is one such technology that is used in agriculture to automate soil moisture and temperature sensors, resulting in more effective agricultural techniques. The data is then wirelessly relayed from these sensors to a Lora WAN gateway, which sends it to a cloud-based platform for analysis. Farmers may make data-driven decisions about irrigation, fertiliser, and other farming operations by having access to this data through an intuitive interface. While there are many advantages to adopting Lora WAN technology in agriculture, one of them is that it is a more effective alternative to conventional methods because it lowers the cost and time required for data gathering and analysis. Also, it makes it possible to monitor crop conditions in real-time, allowing farmers to react swiftly to changes in the weather or other elements that can affect crop output. Also, because Lora WAN sensors consume so little power, they may stay out in the field for longer periods of time without needing to be frequently recharged By enabling real-time crop monitoring and optimization, the use of Lora WAN technology in agriculture offers the potential to increase agricultural yields and encourage more environmentally friendly farming methods.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114530477","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140305
P. Pravalika, P.Komal Kumar, A. Srisaila
The detection of bridges played a significant role in providing construction status. In general, satellite images contain information about geographical capabilities such as bridges, which are extremely useful to both military and civilian personnel. The detection of bridges in major infrastructure projects is critical for providing data about the fame of those structures and guiding feasible decision-making processes. There are traditional methods for inspecting and identifying bridges that use IOT sensors and lasers, but these can only be identified if the object is within a medium range of distance. Convolutional neural networks and Deep learning techniques can be used to perform this identification. In addition, the Geographic Information System aids in the analysis, collection, capture, and management of geographical features. For tracking bridge health, GIS is used to control and combine disparate assets of spatial and characteristic records. The proposed method makes use of YOLOv5's advanced features, such as improved architecture and training methods, to achieve greater accuracy in detecting bridges. On the bridge dataset, transfer learning is used to fine-tune the pre-trained models of YOLOv5 and YOLOv3. The experiments are carried out on a large dataset of satellite images containing a variety of bridge types. In terms of accuracy and mean average precision (mAP) of loss, the results show that YOLOv5 outperforms YOLOv3. YOLOv5 has a mean average precision of 0.92, while YOLOv3 has a mean average precision of 0.54. This approach can be applied to a variety of infrastructure detection tasks and can help to improve the efficiency and accuracy of bridge inspections.
{"title":"Bridge Detection using Satellite Images","authors":"P. Pravalika, P.Komal Kumar, A. Srisaila","doi":"10.1109/ICAAIC56838.2023.10140305","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140305","url":null,"abstract":"The detection of bridges played a significant role in providing construction status. In general, satellite images contain information about geographical capabilities such as bridges, which are extremely useful to both military and civilian personnel. The detection of bridges in major infrastructure projects is critical for providing data about the fame of those structures and guiding feasible decision-making processes. There are traditional methods for inspecting and identifying bridges that use IOT sensors and lasers, but these can only be identified if the object is within a medium range of distance. Convolutional neural networks and Deep learning techniques can be used to perform this identification. In addition, the Geographic Information System aids in the analysis, collection, capture, and management of geographical features. For tracking bridge health, GIS is used to control and combine disparate assets of spatial and characteristic records. The proposed method makes use of YOLOv5's advanced features, such as improved architecture and training methods, to achieve greater accuracy in detecting bridges. On the bridge dataset, transfer learning is used to fine-tune the pre-trained models of YOLOv5 and YOLOv3. The experiments are carried out on a large dataset of satellite images containing a variety of bridge types. In terms of accuracy and mean average precision (mAP) of loss, the results show that YOLOv5 outperforms YOLOv3. YOLOv5 has a mean average precision of 0.92, while YOLOv3 has a mean average precision of 0.54. This approach can be applied to a variety of infrastructure detection tasks and can help to improve the efficiency and accuracy of bridge inspections.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125854289","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10141083
Jaspreet Singh, Gurpreet Singh, Shradha Negi
There will be a billion smart devices with processing, sensing, and actuation capabilities that can be connected to the Internet under the IoT paradigm. The level of convenience, effectiveness, and automation for consumers is expected to rise owing to promising IoT applications. Privacy is a significant concern in IoT systems, and it is essential to provide users with full awareness and control over the data collected by these systems. The use of privacy-enhancing technologies can help to minimise the risks associated with data collection and processing and ensure that user privacy is protected. Lack of standards for devices with limited resources and heterogeneous technologies intensifies the security issue. There are various emerging and existing technologies that can help to address the security risks in the IoT sector and achieve a high degree of trust in IoT applications. By implementing these technologies and countermeasures, it is possible to improve the security and reliability of IoT systems, ensuring that they can be used safely and effectively in a wide range of applications. This article's intent is to provide a comprehensive investigation of the threats and risks in the IoT industry and to examine some potential countermeasures.
{"title":"Evaluating Security Principals and Technologies to Overcome Security Threats in IoT World","authors":"Jaspreet Singh, Gurpreet Singh, Shradha Negi","doi":"10.1109/ICAAIC56838.2023.10141083","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10141083","url":null,"abstract":"There will be a billion smart devices with processing, sensing, and actuation capabilities that can be connected to the Internet under the IoT paradigm. The level of convenience, effectiveness, and automation for consumers is expected to rise owing to promising IoT applications. Privacy is a significant concern in IoT systems, and it is essential to provide users with full awareness and control over the data collected by these systems. The use of privacy-enhancing technologies can help to minimise the risks associated with data collection and processing and ensure that user privacy is protected. Lack of standards for devices with limited resources and heterogeneous technologies intensifies the security issue. There are various emerging and existing technologies that can help to address the security risks in the IoT sector and achieve a high degree of trust in IoT applications. By implementing these technologies and countermeasures, it is possible to improve the security and reliability of IoT systems, ensuring that they can be used safely and effectively in a wide range of applications. This article's intent is to provide a comprehensive investigation of the threats and risks in the IoT industry and to examine some potential countermeasures.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126045656","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140942
X. Shiny, D. Ravikumar, A. Chinnasamy, S. Hemavathi
Regular cities can be transformed into intelligent structures by leveraging information and communication technologies. Innovative city development could be significantly impacted by the Internet of Things paradigm, commonly called cloud computing. All urban locations have a lot of traffic. In this study, Internet-of- Things (IoT) based system is proposed for health care services to organize and to establish the traffic signaling and pick up a route under which road congestion can be administrated. Vehicle accident contraventions are identified by the traffic officers using an online service that is hierarchically carefully monitored or constrained. However, the suggested approach is generic and may be utilized in any major metropolis without losing its generality. Traffic lights linked to cameras in metropolitan areas can be upgraded by connecting to IoT. During a pandemic, this approach is precious. The police can easily regulate traffic from their homes using their cell phones and identify defaulters. The suggested technique aids in the separation of ambulance and rescue engines from ordinary traffic.
{"title":"Cloud Computing based Smart Traffic Management System with Priority Switching for Health Care Services","authors":"X. Shiny, D. Ravikumar, A. Chinnasamy, S. Hemavathi","doi":"10.1109/ICAAIC56838.2023.10140942","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140942","url":null,"abstract":"Regular cities can be transformed into intelligent structures by leveraging information and communication technologies. Innovative city development could be significantly impacted by the Internet of Things paradigm, commonly called cloud computing. All urban locations have a lot of traffic. In this study, Internet-of- Things (IoT) based system is proposed for health care services to organize and to establish the traffic signaling and pick up a route under which road congestion can be administrated. Vehicle accident contraventions are identified by the traffic officers using an online service that is hierarchically carefully monitored or constrained. However, the suggested approach is generic and may be utilized in any major metropolis without losing its generality. Traffic lights linked to cameras in metropolitan areas can be upgraded by connecting to IoT. During a pandemic, this approach is precious. The police can easily regulate traffic from their homes using their cell phones and identify defaulters. The suggested technique aids in the separation of ambulance and rescue engines from ordinary traffic.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128155298","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 : 2023-05-04DOI: 10.1109/ICAAIC56838.2023.10140969
Poonam Shourie, Vatsala Anand, Sheifali Gupta
The flower classification problem involves identifying the species of a given flower image. There were several challenges faced by existing technologies for flower classification like overfitting, computational complexity, limited accuracy, and parameter tuning. In this research, a deep learning model based on Xception architecture is proposed to solve this problem. The proposed model consists of multiple Xception blocks, each of which has a convolutional layer followed by a residual connection and a series of other operations. The output of the final Xception block is fed into a fully connected layer to obtain the final classification. The model was trained on a large dataset of flower images and achieved high accuracy on the test set. The proposed model also conducted experiments to evaluate the performance of the model under various conditions, such as different input resolutions and different amounts of training data. The results show that the proposed model outperforms state-of-the-art methods on the flower classification task. It demonstrates the accuracy of 99.48% and the effectiveness of using the xception architecture in deep learning for image classification tasks and highlights the importance of proper data pre-processing and augmentation techniques in achieving good performance.
{"title":"Flower Classification using a Transfer-based Model","authors":"Poonam Shourie, Vatsala Anand, Sheifali Gupta","doi":"10.1109/ICAAIC56838.2023.10140969","DOIUrl":"https://doi.org/10.1109/ICAAIC56838.2023.10140969","url":null,"abstract":"The flower classification problem involves identifying the species of a given flower image. There were several challenges faced by existing technologies for flower classification like overfitting, computational complexity, limited accuracy, and parameter tuning. In this research, a deep learning model based on Xception architecture is proposed to solve this problem. The proposed model consists of multiple Xception blocks, each of which has a convolutional layer followed by a residual connection and a series of other operations. The output of the final Xception block is fed into a fully connected layer to obtain the final classification. The model was trained on a large dataset of flower images and achieved high accuracy on the test set. The proposed model also conducted experiments to evaluate the performance of the model under various conditions, such as different input resolutions and different amounts of training data. The results show that the proposed model outperforms state-of-the-art methods on the flower classification task. It demonstrates the accuracy of 99.48% and the effectiveness of using the xception architecture in deep learning for image classification tasks and highlights the importance of proper data pre-processing and augmentation techniques in achieving good performance.","PeriodicalId":267906,"journal":{"name":"2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127121363","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：