Pub Date : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987296
D. Josephine, R. Shyam Sunder, S. Sharanesh, C. B. Nithin Ram, G. Hari Prasath
Covid-19 is an extremely communicable disease. It becomes extremely hard to control once it begins to spread. One of the most important and effective steps to break the chain and keep healthy people from getting infected is social isolation/distancing. When an infected person comes into contact with a healthy person, that person becomes infected as well, and the chain reaction continues. To curb this, COVID alert system using geo-fencing is developed. This system uses a GPS module to create a Geo Fence around the infected area and the healthy area. The live/current GPS location/coordinate is compared with the hotspot co-ordinates. The GSM module with Sim800L will send an alert to healthy people when they come into contact with virus-infected areas. The device comes with a GPS, GSM module with Sim800L and an OLED which displays the alert message. The device can be fit into any public or private transport, so that the healthy person will be prevented from entering the hotspot zones unnecessarily, thereby blocking the virus spread.
{"title":"COVID Hotspot Alert System using Geo-Fencing Technique","authors":"D. Josephine, R. Shyam Sunder, S. Sharanesh, C. B. Nithin Ram, G. Hari Prasath","doi":"10.1109/I-SMAC55078.2022.9987296","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987296","url":null,"abstract":"Covid-19 is an extremely communicable disease. It becomes extremely hard to control once it begins to spread. One of the most important and effective steps to break the chain and keep healthy people from getting infected is social isolation/distancing. When an infected person comes into contact with a healthy person, that person becomes infected as well, and the chain reaction continues. To curb this, COVID alert system using geo-fencing is developed. This system uses a GPS module to create a Geo Fence around the infected area and the healthy area. The live/current GPS location/coordinate is compared with the hotspot co-ordinates. The GSM module with Sim800L will send an alert to healthy people when they come into contact with virus-infected areas. The device comes with a GPS, GSM module with Sim800L and an OLED which displays the alert message. The device can be fit into any public or private transport, so that the healthy person will be prevented from entering the hotspot zones unnecessarily, thereby blocking the virus spread.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124151876","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987391
R. Prabu, G. Anitha, V. Mohanavel, M. Tamilselvi, G. Ramkumar
The impartiality and reliability of evaluation, as well as the high time and expense demands, make it impossible to conduct a manual examination of infrastructure issues such as building fractures. For airborne images of damage, use unmanned aerial vehicles. Artificial intelligence and machine learning methods may help overcome the limits of many computer vision-based approaches to crack detection. But these hybrid approaches have their own limitations that can be solved. Images with damage may be more accurately detected using modified convolutional neural networks (MCNNs), which are less affected by picture noise. For fracture identification and damage assessment in civil infrastructures, a Modified Deep CNN Model (MDCNN) has been deployed. The 16-layer convolutional architecture and the Support Vector Machine are used in this design. The last layer of the CNN networks is replaced with SVM. Rather of relying on a single layer, we suggest a multi-layered network instead. Their abilities in identifying objects and putting them into categories are quite reliable. A further great benefit of MDCNNs is their ability to share the burden. When compared to a standard neural network, proposed method use significantly less processing power.
{"title":"Automated Crack and Damage Identification in Premises using Aerial Images based on Machine Learning Techniques","authors":"R. Prabu, G. Anitha, V. Mohanavel, M. Tamilselvi, G. Ramkumar","doi":"10.1109/I-SMAC55078.2022.9987391","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987391","url":null,"abstract":"The impartiality and reliability of evaluation, as well as the high time and expense demands, make it impossible to conduct a manual examination of infrastructure issues such as building fractures. For airborne images of damage, use unmanned aerial vehicles. Artificial intelligence and machine learning methods may help overcome the limits of many computer vision-based approaches to crack detection. But these hybrid approaches have their own limitations that can be solved. Images with damage may be more accurately detected using modified convolutional neural networks (MCNNs), which are less affected by picture noise. For fracture identification and damage assessment in civil infrastructures, a Modified Deep CNN Model (MDCNN) has been deployed. The 16-layer convolutional architecture and the Support Vector Machine are used in this design. The last layer of the CNN networks is replaced with SVM. Rather of relying on a single layer, we suggest a multi-layered network instead. Their abilities in identifying objects and putting them into categories are quite reliable. A further great benefit of MDCNNs is their ability to share the burden. When compared to a standard neural network, proposed method use significantly less processing power.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131984723","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987363
N. Radha, R. Swathika, P. Shreya
Fish have been around for about 450 million years, making them the oldest living organisms. There are about thirty different types of fish. Fish play a crucial role in the marine ecosystem as a source of nutrients. The economic well-being of humanity depends on fish. This paper aim is to find fish in underwater recordings and determine what kind of fish they are (based on species). In this study, 1200 photos of the 12 species represented in the LCF-15 dataset are considered. While the remaining 240 photos are used for testing, 960 are used for training. Different models of YOLOv5 (YOLOv5S, YOLOv5M, and YOLOv5L) are used to train and test our collected dataset. The proposed models are evaluated with F1 score. The YOLOv5S, YOLOv5M, YOLOv5L algorithms achieve a F1 Score of 92.5%, 94.9%, and 94.4% and mAP values of 94.9%, 95.6%, and 96.4% respectively. The findings of the best model show that YOLOv5M provides improved detection accuracy when compared to other methods.
{"title":"Automatic Fish Detection in Underwater Videos using Machine Learning","authors":"N. Radha, R. Swathika, P. Shreya","doi":"10.1109/I-SMAC55078.2022.9987363","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987363","url":null,"abstract":"Fish have been around for about 450 million years, making them the oldest living organisms. There are about thirty different types of fish. Fish play a crucial role in the marine ecosystem as a source of nutrients. The economic well-being of humanity depends on fish. This paper aim is to find fish in underwater recordings and determine what kind of fish they are (based on species). In this study, 1200 photos of the 12 species represented in the LCF-15 dataset are considered. While the remaining 240 photos are used for testing, 960 are used for training. Different models of YOLOv5 (YOLOv5S, YOLOv5M, and YOLOv5L) are used to train and test our collected dataset. The proposed models are evaluated with F1 score. The YOLOv5S, YOLOv5M, YOLOv5L algorithms achieve a F1 Score of 92.5%, 94.9%, and 94.4% and mAP values of 94.9%, 95.6%, and 96.4% respectively. The findings of the best model show that YOLOv5M provides improved detection accuracy when compared to other methods.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131594619","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987328
D. Karunkuzhali, D. Geetha, G. Manikandan, J. Manikandan, V. Kavitha
In this study, wireless technology is used to provide a bridge security checking framework based on IoT. The robotized continuous scaffold wellness checking framework was developed with the assistance of breakthroughs in sensor technology. This method will help CEOs plan for and recover from disasters. The Wireless Technology is employed in the development of an IOT-based bridge security checking framework. Remote sensor hubs can collect several forms of data, such as vibration, water level, and bridge weight. These particulars would also be relevant for verification and observation. The primary purpose of this research is to develop a system that can detect and avoid flyover and extension mistakes, as well as underlying disasters. This study provides an overview of the various techniques used to screen the states of the scaffolds and proposes a framework for assessing constant designs as well as a water level sensor for monitoring the water level in the stream in order to keep traffic away from flood situations using AI calculations. If a crisis occurs, the Bridge’s doors will close as a result. The collected data is delivered to the server and data set, allowing managers to monitor the extension situation using portable telecom devices.
{"title":"Artificial Intelligence and Advanced Technology based Bridge Safety Monitoring System","authors":"D. Karunkuzhali, D. Geetha, G. Manikandan, J. Manikandan, V. Kavitha","doi":"10.1109/I-SMAC55078.2022.9987328","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987328","url":null,"abstract":"In this study, wireless technology is used to provide a bridge security checking framework based on IoT. The robotized continuous scaffold wellness checking framework was developed with the assistance of breakthroughs in sensor technology. This method will help CEOs plan for and recover from disasters. The Wireless Technology is employed in the development of an IOT-based bridge security checking framework. Remote sensor hubs can collect several forms of data, such as vibration, water level, and bridge weight. These particulars would also be relevant for verification and observation. The primary purpose of this research is to develop a system that can detect and avoid flyover and extension mistakes, as well as underlying disasters. This study provides an overview of the various techniques used to screen the states of the scaffolds and proposes a framework for assessing constant designs as well as a water level sensor for monitoring the water level in the stream in order to keep traffic away from flood situations using AI calculations. If a crisis occurs, the Bridge’s doors will close as a result. The collected data is delivered to the server and data set, allowing managers to monitor the extension situation using portable telecom devices.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131607368","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987339
Sandeep Shekhawat
Electronic Shelf Labels (ESL) are the new way of displaying pricing in the stores. Going digital helps in improving store employee productivity and accuracy in pricing displayed in the stores. However not all retailers can invest in setting up expensive infrastructure for custom shelf labels at scale. This paper discusses about different ways to use low-cost mobile devices to overcome expensive shelf label infrastructure setup. In addition to that the paper proposes a way to overcome reliability of the low-cost mobile devices to display consistent pricing in the stores. With patchy network connectivity in stores devices can easily go out of sync and end up showing different pricing for the same items. The proposed solution uses an iBeacon/BLE based solution to make sure the mobile devices-based ESLs can build a consensus and show consistent pricing for the merchandise in the store.
{"title":"Decentralized Pricing on Mobile Phone-based ESLs","authors":"Sandeep Shekhawat","doi":"10.1109/I-SMAC55078.2022.9987339","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987339","url":null,"abstract":"Electronic Shelf Labels (ESL) are the new way of displaying pricing in the stores. Going digital helps in improving store employee productivity and accuracy in pricing displayed in the stores. However not all retailers can invest in setting up expensive infrastructure for custom shelf labels at scale. This paper discusses about different ways to use low-cost mobile devices to overcome expensive shelf label infrastructure setup. In addition to that the paper proposes a way to overcome reliability of the low-cost mobile devices to display consistent pricing in the stores. With patchy network connectivity in stores devices can easily go out of sync and end up showing different pricing for the same items. The proposed solution uses an iBeacon/BLE based solution to make sure the mobile devices-based ESLs can build a consensus and show consistent pricing for the merchandise in the store.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131851199","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987412
Chun Luo, Xianyong Wu, Zhicong Wu
In this study, the brand of the live broadcast platform is used to create value together. The personal brand plays the role of brand value link, effectively linking all parties, and the information flow and logistics play an important supporting role. 154 cultural resource points are extracted, based on the ArcGIS platform, using Spatial analysis methods such as Nearest Neighbor Index (ANN), Kernel Density (KDE) and Standard Deviation Ellipse analyze the spatial distribution characteristics of resource points, and construct a rural cultural tourism space from four aspects: cultural resources, topography, natural ecology and transportation construction. pattern, and discussed the development model of rural cultural tourism.
{"title":"Construction of Large-Scale Communication Network based on Abstract Extraction Algorithm","authors":"Chun Luo, Xianyong Wu, Zhicong Wu","doi":"10.1109/I-SMAC55078.2022.9987412","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987412","url":null,"abstract":"In this study, the brand of the live broadcast platform is used to create value together. The personal brand plays the role of brand value link, effectively linking all parties, and the information flow and logistics play an important supporting role. 154 cultural resource points are extracted, based on the ArcGIS platform, using Spatial analysis methods such as Nearest Neighbor Index (ANN), Kernel Density (KDE) and Standard Deviation Ellipse analyze the spatial distribution characteristics of resource points, and construct a rural cultural tourism space from four aspects: cultural resources, topography, natural ecology and transportation construction. pattern, and discussed the development model of rural cultural tourism.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133061115","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987416
J. Jacob, V. P. Devassia
Dense captioning is a fast emerging area in video processing in natural language, that construe semantic contents present in an input video and. A traditional deep learning algorithm faces more challenges in solving this problem because it requires optimizing not just one set of values, but two sets, namely (1) event proposals, which are the timestamps for detecting an activity in a particular temporal region, and (2) natural language annotations for the detected proposals. Bidirectional LS TMs are used to predict event proposals based on information from the past and future of the event. Captions for detected events are also generated based on the past and future information associated with the event. The context vectors are augmented with original C3D video features in the decoder network in order to optimize the encoder network for proposals instead of captions. In this way, all the information necessary for the decoding network is provided. A local attention mechanism is added to the model so that it can focus on the relevant parts of the data to improve its performance. As a final step, captions will be generated with deep LSTMs. In order to verify the effectiveness of proposed model, a rigorous experiments have been conducted on the suggested innovations and demonstrated that it is remarkably effective at dense captioning events in videos with significant gains across a variety of metrics when it uses Feature Context Integrated (FC1) Deep LS TM with local attention.
{"title":"Dense Captioning of Videos using Feature Context Integrated Deep LSTM with Local Attention","authors":"J. Jacob, V. P. Devassia","doi":"10.1109/I-SMAC55078.2022.9987416","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987416","url":null,"abstract":"Dense captioning is a fast emerging area in video processing in natural language, that construe semantic contents present in an input video and. A traditional deep learning algorithm faces more challenges in solving this problem because it requires optimizing not just one set of values, but two sets, namely (1) event proposals, which are the timestamps for detecting an activity in a particular temporal region, and (2) natural language annotations for the detected proposals. Bidirectional LS TMs are used to predict event proposals based on information from the past and future of the event. Captions for detected events are also generated based on the past and future information associated with the event. The context vectors are augmented with original C3D video features in the decoder network in order to optimize the encoder network for proposals instead of captions. In this way, all the information necessary for the decoding network is provided. A local attention mechanism is added to the model so that it can focus on the relevant parts of the data to improve its performance. As a final step, captions will be generated with deep LSTMs. In order to verify the effectiveness of proposed model, a rigorous experiments have been conducted on the suggested innovations and demonstrated that it is remarkably effective at dense captioning events in videos with significant gains across a variety of metrics when it uses Feature Context Integrated (FC1) Deep LS TM with local attention.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133581001","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987411
V. Catherine, A. S. Nargunam
In this paper, an efficient retrievable attribute with Ciphertext-policy attribute-based signcryption with accountable and verifiable outsourced designcryption (CP-ABSc-AVODs) was proposed towards enable sharing of data in cloud in a secure manner. The cloud provides accurate control on data access, encryption and authenticity to data for granting confidentiality and integrity to personal messages. This protocol enables signing of message, depending on the access privileges given in tree structure mentioned embedded with the message. Users will be able to decrypt to get plaintext if and only if they have the necessary properties satisfying the structure specified for data access. In addition, CP-ABSc-AVODs provide access policy update functionality to decrypt unsigned or signed cloud storage server messages and redistribute user secret keys. The feature of access policy update in CP-ABSc-AVODs has no effect on the number of messages or its size received at the client site and hence there is a reduction in bandwidth and memory usage. The proposed protocol includes general attack resistance, message detection, data protection and fraud prevention. In addition, the proposed method’s performance is evaluated by comparing with other methods with respect to size of the key, functionality and time required for computation.
本文提出了一种有效的可检索属性、基于密文策略属性的签名加密和可问责和可验证的外包设计加密(cp - ab - avods)，以实现云数据的安全共享。云提供对数据访问、加密和数据真实性的精确控制，以授予个人信息的机密性和完整性。该协议支持对消息进行签名，具体取决于消息中嵌入的树结构中给定的访问权限。当且仅当用户具有满足为数据访问指定的结构的必要属性时，用户才能够解密以获得明文。此外，cp - ab - avod还提供访问策略更新功能，以解密未签名或签名的云存储服务器消息，并重新分发用户秘密密钥。cp - ab - avod中的访问策略更新特性对客户端站点接收的消息的数量或大小没有影响，因此减少了带宽和内存使用。该协议包括抗一般攻击、消息检测、数据保护和防欺诈。此外，通过与其他方法在密钥大小、功能和计算时间方面的比较，对所提出方法的性能进行了评估。
{"title":"An Efficient and Secure Data Sharing Scheme for Ciphertext-Policy Attribute-based Signcryption for Cloud Storage Services","authors":"V. Catherine, A. S. Nargunam","doi":"10.1109/I-SMAC55078.2022.9987411","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987411","url":null,"abstract":"In this paper, an efficient retrievable attribute with Ciphertext-policy attribute-based signcryption with accountable and verifiable outsourced designcryption (CP-ABSc-AVODs) was proposed towards enable sharing of data in cloud in a secure manner. The cloud provides accurate control on data access, encryption and authenticity to data for granting confidentiality and integrity to personal messages. This protocol enables signing of message, depending on the access privileges given in tree structure mentioned embedded with the message. Users will be able to decrypt to get plaintext if and only if they have the necessary properties satisfying the structure specified for data access. In addition, CP-ABSc-AVODs provide access policy update functionality to decrypt unsigned or signed cloud storage server messages and redistribute user secret keys. The feature of access policy update in CP-ABSc-AVODs has no effect on the number of messages or its size received at the client site and hence there is a reduction in bandwidth and memory usage. The proposed protocol includes general attack resistance, message detection, data protection and fraud prevention. In addition, the proposed method’s performance is evaluated by comparing with other methods with respect to size of the key, functionality and time required for computation.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133185160","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987424
Sai Likhith Panuganti, Naseer Hussain Gajula, Prasanthi Rathnala, M.S. Pradeep Kumar Patnaik, Srinivasa Rao Sura
This research study proposes an embedded color segregation system using the multi-rate sensor data and color identification. There are plenty of applications for color segregation. The most prominent uses are for waste management and fruit and veg packing. In waste management, clutter is identified based on its size, shape and color. Sensor enabled color segregation helps to segregate the unwanted items with ease of use. Another application is segregating the available fruit and veg from the agricultural produce. One of best approaches to achieve this is based on its color, which is the most economical and fast method. The idea of this color segregation is to extend the work further to develop an autonomous waste management system. The proposed prototype segregates color category based on sensor measurements collected from RGB sensor, TCS34725. Segregating color is very simple to human eyes, but there are a lot of background tasks for a sensor to detect the actual given color. TCS34725 detects the color and makes human life easier by providing the exact RGB values, which cannot be identified by the naked eye. A test methodology has been followed to validate the proposed segregation approach. To perform this, a real time prototype has been developed and measured around 10k samples under different conditions. Results indicate that the proposed approach has achieved significant benefits, i.e., accuracy is above 95%, response time less than 3ms.
{"title":"Embedded Color Segregation using Arduino","authors":"Sai Likhith Panuganti, Naseer Hussain Gajula, Prasanthi Rathnala, M.S. Pradeep Kumar Patnaik, Srinivasa Rao Sura","doi":"10.1109/I-SMAC55078.2022.9987424","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987424","url":null,"abstract":"This research study proposes an embedded color segregation system using the multi-rate sensor data and color identification. There are plenty of applications for color segregation. The most prominent uses are for waste management and fruit and veg packing. In waste management, clutter is identified based on its size, shape and color. Sensor enabled color segregation helps to segregate the unwanted items with ease of use. Another application is segregating the available fruit and veg from the agricultural produce. One of best approaches to achieve this is based on its color, which is the most economical and fast method. The idea of this color segregation is to extend the work further to develop an autonomous waste management system. The proposed prototype segregates color category based on sensor measurements collected from RGB sensor, TCS34725. Segregating color is very simple to human eyes, but there are a lot of background tasks for a sensor to detect the actual given color. TCS34725 detects the color and makes human life easier by providing the exact RGB values, which cannot be identified by the naked eye. A test methodology has been followed to validate the proposed segregation approach. To perform this, a real time prototype has been developed and measured around 10k samples under different conditions. Results indicate that the proposed approach has achieved significant benefits, i.e., accuracy is above 95%, response time less than 3ms.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115994996","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987364
Shannmukha Naga Raju Vonteddu, P. Nunna, P. Subramanian, V. Gopu, M. Nagarajan, G. Diwakar
In electric vehicles (EV), one or more electric motors are operated by energy stored in rechargeable batteries. In response to the increased interest in EVs, research into their modelling and simulation has operational variables alter depending on driving conditions, making it difficult to retain control. In the MATLAB/Simulink environment, the transfer function model of the EV is used for design and analysis purposes. In this work, the advanced Back Propagation Neural Network-based Proportional Integral Derivative (BPNN-PID) controller is designed to control the speed of the EV. To identify the effectiveness of the BPNN-PID controller the two conventional controllers fuzzy and PID are used. The error metrics are used to analyse the controller performance. The error metrics employed in this work are Integral Square Error (ISE), Integral Absolute Error (IAE), and Integral Time Absolute Frror (ITAE).
{"title":"PID Controller based on BP Neural Network for Speed Control of Electric Vehicle","authors":"Shannmukha Naga Raju Vonteddu, P. Nunna, P. Subramanian, V. Gopu, M. Nagarajan, G. Diwakar","doi":"10.1109/I-SMAC55078.2022.9987364","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987364","url":null,"abstract":"In electric vehicles (EV), one or more electric motors are operated by energy stored in rechargeable batteries. In response to the increased interest in EVs, research into their modelling and simulation has operational variables alter depending on driving conditions, making it difficult to retain control. In the MATLAB/Simulink environment, the transfer function model of the EV is used for design and analysis purposes. In this work, the advanced Back Propagation Neural Network-based Proportional Integral Derivative (BPNN-PID) controller is designed to control the speed of the EV. To identify the effectiveness of the BPNN-PID controller the two conventional controllers fuzzy and PID are used. The error metrics are used to analyse the controller performance. The error metrics employed in this work are Integral Square Error (ISE), Integral Absolute Error (IAE), and Integral Time Absolute Frror (ITAE).","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129498433","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：