Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099491
R. Jamadar, Anoop Sharma
With the advent of deep learning algorithms research work in object recognitions has produced high quality algorithms that outperforms classical image processing techniques. In this work we are proposing a novel approach which employs semantic segmentation to estimate the severity of the leaf disease. For semantic segmentation we have used a light weight deep learning architecture SegNet. Primarily the SegNet removes the background noise and in its subsequent phase it locates the necrotic scars/lesions caused due to leaf diseases and performs semantic segmentation. The estimation of amount of damage caused to the leaf depends on the diseased region/part of the leaf. Through SegNet the proposed work identifies the healthy region and diseased region of the leaf and pixel-level labeling is done. When compared SegNet with other deep learning based semantic segmentation architectures like FPN, Unet and DeepLabv3, SegNet proves to be memory efficient as it stores only the max-pooling indices of the feature-maps. Further this works extends the architecture for classification problem using ResNet. Moreover in the proposed work the accuracy levels of the disease severity obtained are very close to the manual methods and satisfactory.
{"title":"Semantic Segmentation Based Leaf Disease Severity Estimation Using Deep Learning Algorithms","authors":"R. Jamadar, Anoop Sharma","doi":"10.1109/ESCI56872.2023.10099491","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099491","url":null,"abstract":"With the advent of deep learning algorithms research work in object recognitions has produced high quality algorithms that outperforms classical image processing techniques. In this work we are proposing a novel approach which employs semantic segmentation to estimate the severity of the leaf disease. For semantic segmentation we have used a light weight deep learning architecture SegNet. Primarily the SegNet removes the background noise and in its subsequent phase it locates the necrotic scars/lesions caused due to leaf diseases and performs semantic segmentation. The estimation of amount of damage caused to the leaf depends on the diseased region/part of the leaf. Through SegNet the proposed work identifies the healthy region and diseased region of the leaf and pixel-level labeling is done. When compared SegNet with other deep learning based semantic segmentation architectures like FPN, Unet and DeepLabv3, SegNet proves to be memory efficient as it stores only the max-pooling indices of the feature-maps. Further this works extends the architecture for classification problem using ResNet. Moreover in the proposed work the accuracy levels of the disease severity obtained are very close to the manual methods and satisfactory.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114257217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099538
Kamurthi Ravi Teja, Chuan-Ming Liu, Shakti Raj Chopra
The main objective of this study was to determine the surface water and soil moisture available on Earth, and to test water quality using geospatial and machine learning (ML) tools. Java and Python scripts were developed to design the model. This study presents a smart approach for collecting and assessing water bodies present on Earth. In this study, we identified the surface water and soil moisture sites on Earth and subsequently identified the surface water and soil moisture sites in Taiwan. To test the quality of the water, we designed an ML model. Up on experiment, the random forest model obtained training and test accuracy scores of 100% and 68%, respectively. To improve the test accuracy score further, we used the auto-ML technique and obtained a test accuracy score of 69%. Therefore, based on the accuracy scores, we concluded that the auto-ML model was the best.
{"title":"Water Assessment Using Geospatial and Data Science Tools","authors":"Kamurthi Ravi Teja, Chuan-Ming Liu, Shakti Raj Chopra","doi":"10.1109/ESCI56872.2023.10099538","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099538","url":null,"abstract":"The main objective of this study was to determine the surface water and soil moisture available on Earth, and to test water quality using geospatial and machine learning (ML) tools. Java and Python scripts were developed to design the model. This study presents a smart approach for collecting and assessing water bodies present on Earth. In this study, we identified the surface water and soil moisture sites on Earth and subsequently identified the surface water and soil moisture sites in Taiwan. To test the quality of the water, we designed an ML model. Up on experiment, the random forest model obtained training and test accuracy scores of 100% and 68%, respectively. To improve the test accuracy score further, we used the auto-ML technique and obtained a test accuracy score of 69%. Therefore, based on the accuracy scores, we concluded that the auto-ML model was the best.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123358370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099495
MD. Khairul Islam, Syeda Jannatul Boshra, Mahfuzur Rahman, MD. Mominul Islam Jony, Imtiaz Ahmed Rahat
An appointment system is going to be popular nowadays. The necessity of these types of systems is increasing day by day specially in education sector. Worldwide COVID-19 pandemic provoke the demand of these types of application. In this research paper, an Android-based appointment is built for booking an appointment and communicating with the teacher. To use this system both student and teacher have to an android device with connection of the internet. A single android application will be used for both types of users. Students can get the information of all teachers and book an appointment with teachers and teachers can accept or decline this appointment. Java programming language is used for this system and Google's Firebase is used for the database. In addition, the modern coding Architecture pattern MVVM (Model- View-View Model) followed to build this system. Hopefully, this system saves valuable time and makes the teacher-student interaction journey easier.
{"title":"Android Based Smart Appointment System (SAS) for Booking and Interacting with Teacher for Counselling","authors":"MD. Khairul Islam, Syeda Jannatul Boshra, Mahfuzur Rahman, MD. Mominul Islam Jony, Imtiaz Ahmed Rahat","doi":"10.1109/ESCI56872.2023.10099495","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099495","url":null,"abstract":"An appointment system is going to be popular nowadays. The necessity of these types of systems is increasing day by day specially in education sector. Worldwide COVID-19 pandemic provoke the demand of these types of application. In this research paper, an Android-based appointment is built for booking an appointment and communicating with the teacher. To use this system both student and teacher have to an android device with connection of the internet. A single android application will be used for both types of users. Students can get the information of all teachers and book an appointment with teachers and teachers can accept or decline this appointment. Java programming language is used for this system and Google's Firebase is used for the database. In addition, the modern coding Architecture pattern MVVM (Model- View-View Model) followed to build this system. Hopefully, this system saves valuable time and makes the teacher-student interaction journey easier.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114061323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099614
Rakesh Ahuja, Y. Kumar, S. Goyal, Sarakshi Kaur, Ravi Kumar Sachdeva, Vikas Solanki
Stock Market Prediction is affordable access to find the future scope of company stock or any financial exchange. The successful prediction of the stock will maximize the profit of the investors that are associated with the company. This research paper proposed algorithms based on knowledge engineering to envisage the stock price of a brand's dataset. Three most prominent regression techniques namely Support Vector(SVR), Random Forest(RFR) and Linear Regression have been used for predicting the stock price. The model proposed in this paper is based on the historical data of the company. These machine-learning algorithms are very popular and efficient for finding accurate results. This model does the prediction and compares its accuracy through the mean squared error(MSE), Mean Absolute Error(MAE), and Root Mean Squared Error(RMSE) to classify the better result.
{"title":"Stock Price Prediction By Applying Machine Learning Techniques","authors":"Rakesh Ahuja, Y. Kumar, S. Goyal, Sarakshi Kaur, Ravi Kumar Sachdeva, Vikas Solanki","doi":"10.1109/ESCI56872.2023.10099614","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099614","url":null,"abstract":"Stock Market Prediction is affordable access to find the future scope of company stock or any financial exchange. The successful prediction of the stock will maximize the profit of the investors that are associated with the company. This research paper proposed algorithms based on knowledge engineering to envisage the stock price of a brand's dataset. Three most prominent regression techniques namely Support Vector(SVR), Random Forest(RFR) and Linear Regression have been used for predicting the stock price. The model proposed in this paper is based on the historical data of the company. These machine-learning algorithms are very popular and efficient for finding accurate results. This model does the prediction and compares its accuracy through the mean squared error(MSE), Mean Absolute Error(MAE), and Root Mean Squared Error(RMSE) to classify the better result.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131937566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099636
Santosh Lavate, P. K. Srivastava
The growth of Internet of Things devices and technologies has given rise to a challenging new threat in the form of user data traffic flow. When there is insufficient channel allocation and network traffic measures in place, large volumes of sensitive data are at danger, and the transmission of data around the world can be slowed down by unwanted data. Cybercriminals have the potential to take use of this for evil ends. As a consequence of this, sophisticated mechanisms for assigning network channels and classifying network traffic are required. These mechanisms must be able to analyze and assign carriers to Internet of Things (IoT) network traffic in real time. We present a novel strategy based on machine learning for assigning channels in IoT networks and identifying data that is safe to use in order to get around this problem. The classification of Internet of Things (IoT) traffic networks and the allotment of channels for harmless data in huge network traffic could both benefit greatly from the application of this technology. The suggested approach makes use of deep learning technologies to perform operations at the network level, which results in a significant reduction in the amount of time spent on network classification and allocation of appropriate transmission medium for Benign traffic while also producing encouraging outcomes.
{"title":"An Analytical Review on Classification of IoT Traffic and Channel Allocation Using Machine Learning Technique","authors":"Santosh Lavate, P. K. Srivastava","doi":"10.1109/ESCI56872.2023.10099636","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099636","url":null,"abstract":"The growth of Internet of Things devices and technologies has given rise to a challenging new threat in the form of user data traffic flow. When there is insufficient channel allocation and network traffic measures in place, large volumes of sensitive data are at danger, and the transmission of data around the world can be slowed down by unwanted data. Cybercriminals have the potential to take use of this for evil ends. As a consequence of this, sophisticated mechanisms for assigning network channels and classifying network traffic are required. These mechanisms must be able to analyze and assign carriers to Internet of Things (IoT) network traffic in real time. We present a novel strategy based on machine learning for assigning channels in IoT networks and identifying data that is safe to use in order to get around this problem. The classification of Internet of Things (IoT) traffic networks and the allotment of channels for harmless data in huge network traffic could both benefit greatly from the application of this technology. The suggested approach makes use of deep learning technologies to perform operations at the network level, which results in a significant reduction in the amount of time spent on network classification and allocation of appropriate transmission medium for Benign traffic while also producing encouraging outcomes.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126825278","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 rate of industrialization and urbanization has accelerated substantially since the Industrial Revolution. The majority of industrial applications cause air pollution, which is hazardous to people's health. Vehicle emissions are also a major factor to these issues. The majority of developing countries suffer from severe air pollution. According to recent reports, more than ten Indian cities are ranked first. Air quality is an important component in determining air quality. As a result, in order to make a city smart and livable, the air quality index must be regularly monitored. This study aims to use IOT in conjunction with the cloud to make services real-time and faster. The system's primary goal is to access and visualize air quality based on real-time sensor data. At regular intervals, the level of each hazardous pollutant is measured. The Air Quality Index (AQI) for the measured pollutants is calculated, and public awareness is raised via a web application that shows the air quality index in that specific place. Further, ML model is developed which can predict future AQI index value based on the collected data which in order can helps in making precautions arrangements in the case of worst AQI index in concern of public health.
{"title":"AQI Monitoring and Predicting System","authors":"Shital Pawar, Swadesh Kelkar, Neeraja Khire, Tejas Khairnar, Maithili Kharabe","doi":"10.1109/ESCI56872.2023.10099645","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099645","url":null,"abstract":"The rate of industrialization and urbanization has accelerated substantially since the Industrial Revolution. The majority of industrial applications cause air pollution, which is hazardous to people's health. Vehicle emissions are also a major factor to these issues. The majority of developing countries suffer from severe air pollution. According to recent reports, more than ten Indian cities are ranked first. Air quality is an important component in determining air quality. As a result, in order to make a city smart and livable, the air quality index must be regularly monitored. This study aims to use IOT in conjunction with the cloud to make services real-time and faster. The system's primary goal is to access and visualize air quality based on real-time sensor data. At regular intervals, the level of each hazardous pollutant is measured. The Air Quality Index (AQI) for the measured pollutants is calculated, and public awareness is raised via a web application that shows the air quality index in that specific place. Further, ML model is developed which can predict future AQI index value based on the collected data which in order can helps in making precautions arrangements in the case of worst AQI index in concern of public health.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126621732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100285
Kamurthi Ravi Teja, Chuan-Ming Liu, Shakti Raj Chopra
The main aim of this study was to analyze patient health using Machine Learning (ML). To do this, we used the Extreme Gradient Boost (XGBoost) classifier and auto-ML-Pycaret techniques. The sequential procedure we followed for the XGBoost model is data analysis, feature engineering, and model building, which are discussed in this paper. For these tasks, we used data science tools such as the Jupyter notebook and Google Colab (GC). Subsequently, we discuss the auto-ML-Pycaret model, which is an excellent tool for ML tasks. Finally, a performance comparison is performed between the two models based on their accuracy levels. The accuracy rate for the first ML model was 87%, and for the auto ML Pycaret model, we achieved 88% accuracy. Based on the accuracy percentages and time factor, we observed that the auto-ML Pycaret model performed better than the XGBoost model.
{"title":"Patients' Health Analysis using Machine Learning","authors":"Kamurthi Ravi Teja, Chuan-Ming Liu, Shakti Raj Chopra","doi":"10.1109/ESCI56872.2023.10100285","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100285","url":null,"abstract":"The main aim of this study was to analyze patient health using Machine Learning (ML). To do this, we used the Extreme Gradient Boost (XGBoost) classifier and auto-ML-Pycaret techniques. The sequential procedure we followed for the XGBoost model is data analysis, feature engineering, and model building, which are discussed in this paper. For these tasks, we used data science tools such as the Jupyter notebook and Google Colab (GC). Subsequently, we discuss the auto-ML-Pycaret model, which is an excellent tool for ML tasks. Finally, a performance comparison is performed between the two models based on their accuracy levels. The accuracy rate for the first ML model was 87%, and for the auto ML Pycaret model, we achieved 88% accuracy. Based on the accuracy percentages and time factor, we observed that the auto-ML Pycaret model performed better than the XGBoost model.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114213143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10099898
Sabahat Naaz Peerzade, S. Mudda
An asymmetric coplanar strip (ACS)-based compact antenna for multiband applications is presented in this paper. Antennas are miniaturized using ACS methods. The antenna is dimension is 14×25×1.6 mm3, making it exceedingly small. The suggested antenna is made of FR4 material with a $mathbf{epsilon} mathbf{r}=mathbf{4.4}$ and a thickness of 1.6. To achieve multiband features, the monopole antenna is modified by including semi-circle and 5-shaped pieces in the radiating structure. The WLAN band (2.30-2.71 GHz), Wi-MAX (3.37-3.97 GHz), and Wi-Fi (5.17 -6.40 GHz) bands are all applicable to the proposed antenna. At 2.5GHz, 3.6GHz, and 5.4GHz, the antenna's bandwidth is receiving at 410 MHz, 600 MHz, and 1230 MHz. All three bands have VSWR values below 1.4.
{"title":"A Compact Asymmetric Coplanar Strip (ACS) Antenna for WLAN and Wi-Fi Applications","authors":"Sabahat Naaz Peerzade, S. Mudda","doi":"10.1109/ESCI56872.2023.10099898","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10099898","url":null,"abstract":"An asymmetric coplanar strip (ACS)-based compact antenna for multiband applications is presented in this paper. Antennas are miniaturized using ACS methods. The antenna is dimension is 14×25×1.6 mm3, making it exceedingly small. The suggested antenna is made of FR4 material with a $mathbf{epsilon} mathbf{r}=mathbf{4.4}$ and a thickness of 1.6. To achieve multiband features, the monopole antenna is modified by including semi-circle and 5-shaped pieces in the radiating structure. The WLAN band (2.30-2.71 GHz), Wi-MAX (3.37-3.97 GHz), and Wi-Fi (5.17 -6.40 GHz) bands are all applicable to the proposed antenna. At 2.5GHz, 3.6GHz, and 5.4GHz, the antenna's bandwidth is receiving at 410 MHz, 600 MHz, and 1230 MHz. All three bands have VSWR values below 1.4.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"68 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114114161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100002
Kalingarani G, P. Selvaraj
The Internet is overwhelmed with innovative IoT -assisted devices. It is predicted that the number of online-connected devices will be more than 50 billion in 2030. Such IoT devices would need support from enabling technologies to consume less memory and lower the computation cost. The cloud-based services might further increase point-to-point latency. The unprecedentedly high volumes of real-time data generated by IoT devices may suffer from this delay issue. This work proposes a novel cognitive Fog computing-based data processing approach that manages the data influx caused by the sensor devices at the edge router. The proposed cognitive Fog based architecture has empowered edge devices, with the features such as Location awareness, low latency, portability, proximity to end users, diversity, and real-time response. A scalable resource allocation with a dynamic queuing technique was proposed. The simulation results have shown that the proposed architecture boosts the performance of the IoT Fog-based applications more than the existing approaches.
{"title":"Self-Aware Fog Layer toward Scalable Resource Allocation and Dynamic Queuing","authors":"Kalingarani G, P. Selvaraj","doi":"10.1109/ESCI56872.2023.10100002","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100002","url":null,"abstract":"The Internet is overwhelmed with innovative IoT -assisted devices. It is predicted that the number of online-connected devices will be more than 50 billion in 2030. Such IoT devices would need support from enabling technologies to consume less memory and lower the computation cost. The cloud-based services might further increase point-to-point latency. The unprecedentedly high volumes of real-time data generated by IoT devices may suffer from this delay issue. This work proposes a novel cognitive Fog computing-based data processing approach that manages the data influx caused by the sensor devices at the edge router. The proposed cognitive Fog based architecture has empowered edge devices, with the features such as Location awareness, low latency, portability, proximity to end users, diversity, and real-time response. A scalable resource allocation with a dynamic queuing technique was proposed. The simulation results have shown that the proposed architecture boosts the performance of the IoT Fog-based applications more than the existing approaches.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124333483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ESCI56872.2023.10100063
Ayush Gala, Chinmay Borgaonkar, V. Kulkarni, M. Wakode, G. Kale
The IoT represents a great opportunity for tourism and hospitality to increase customer satisfaction while simulta-neously reducing operational costs. Smart tourism involves using smart technology and practices to boost resource management and the sustainability of tourism, while growing the overall competitiveness. Travel and tourism companies will depend on IoT technology to create an array of benefits both in internal and external environments. Through our study, we explore BLE beacon based proximity detection and information delivery, and its various use cases to overcome the complications of the travel and tourism industry. As the key technology, Bluetooth Low Energy (BLE) beacons are deployed at the core of our model along with a front-end application that interacts with the beacons to personalize and satisfy the tourists' demands. By combining smartphone capabilities with beacon technology, messages can be sent to tourists at the point they are most relevant, based on their proximity to the beacon. This would be especially effective on walking tours around a city. When tourists walk past a site of historical or ideological importance, an ancient ruin for example, they can be sent prompts or messages which describe what they are seeing and what it means in terms of the destination's history or culture. Our implementation emulates a tourist scenario enabled by BLE beacons and cloud resources using our experimental model. Moreover, we examine the practical implications about the role and use of IoT in tourism which should enable the industry to keep up with global tourism trends and put them on an equal footing with other participants in the online tourism and travel market.
{"title":"Contextual Flow of Information in Tourism using BLE Proximity Detection to Enhance the Tourism Experience","authors":"Ayush Gala, Chinmay Borgaonkar, V. Kulkarni, M. Wakode, G. Kale","doi":"10.1109/ESCI56872.2023.10100063","DOIUrl":"https://doi.org/10.1109/ESCI56872.2023.10100063","url":null,"abstract":"The IoT represents a great opportunity for tourism and hospitality to increase customer satisfaction while simulta-neously reducing operational costs. Smart tourism involves using smart technology and practices to boost resource management and the sustainability of tourism, while growing the overall competitiveness. Travel and tourism companies will depend on IoT technology to create an array of benefits both in internal and external environments. Through our study, we explore BLE beacon based proximity detection and information delivery, and its various use cases to overcome the complications of the travel and tourism industry. As the key technology, Bluetooth Low Energy (BLE) beacons are deployed at the core of our model along with a front-end application that interacts with the beacons to personalize and satisfy the tourists' demands. By combining smartphone capabilities with beacon technology, messages can be sent to tourists at the point they are most relevant, based on their proximity to the beacon. This would be especially effective on walking tours around a city. When tourists walk past a site of historical or ideological importance, an ancient ruin for example, they can be sent prompts or messages which describe what they are seeing and what it means in terms of the destination's history or culture. Our implementation emulates a tourist scenario enabled by BLE beacons and cloud resources using our experimental model. Moreover, we examine the practical implications about the role and use of IoT in tourism which should enable the industry to keep up with global tourism trends and put them on an equal footing with other participants in the online tourism and travel market.","PeriodicalId":441215,"journal":{"name":"2023 International Conference on Emerging Smart Computing and Informatics (ESCI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117254793","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：