Pub Date : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10084957
Raman Singh, Sean Sturley, B. Sharma, I. Dhaou
The Internet of Things (IoT) is the network of multiple devices known as “things” which includes sensors, security cameras, smart lights, smart TV, traffic lights etc. in the smart home or industrial environment. In many applications, these IoT devices are installed in open areas for example traffic lights/ security cameras in a smart city. Strong authentication and authorisation for these devices need to be deployed to ensure trust among IoT networks. IoT devices produce and forward security-sensitive data and hence confidentiality, authentication and proper authorisation should be the primary priority of an IoT system. Implementing Certificate Authority-based digital certificate solutions is costly because of the number of devices involved in IoT networks. Blockchain is a decentralized ledger-based technology which can help to provide seamless yet cost-effective solutions for confidentiality, authentication, and authorisation for IoT environments. A blockchain-based system for device registration, authentication, authorisation, and data confidentiality is proposed. The paper shows the methodological and procedural details of the proposed security scheme.
{"title":"Blockchain-enabled Device Authentication and Authorisation for Internet of Things","authors":"Raman Singh, Sean Sturley, B. Sharma, I. Dhaou","doi":"10.1109/ICAISC56366.2023.10084957","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10084957","url":null,"abstract":"The Internet of Things (IoT) is the network of multiple devices known as “things” which includes sensors, security cameras, smart lights, smart TV, traffic lights etc. in the smart home or industrial environment. In many applications, these IoT devices are installed in open areas for example traffic lights/ security cameras in a smart city. Strong authentication and authorisation for these devices need to be deployed to ensure trust among IoT networks. IoT devices produce and forward security-sensitive data and hence confidentiality, authentication and proper authorisation should be the primary priority of an IoT system. Implementing Certificate Authority-based digital certificate solutions is costly because of the number of devices involved in IoT networks. Blockchain is a decentralized ledger-based technology which can help to provide seamless yet cost-effective solutions for confidentiality, authentication, and authorisation for IoT environments. A blockchain-based system for device registration, authentication, authorisation, and data confidentiality is proposed. The paper shows the methodological and procedural details of the proposed security scheme.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115109367","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085583
K. Saleem, Azam Adel Alajroosh, R. Ouni, W. Mansoor, A. Gawanmeh
This paper proposes a secure internet of things (IoT) based smart radiation detection and measurement system. The Waspmote platform is utilized to build an intelligent IoT station that communicates over 3rd Generation (3G) cellular communication for transferring data to the cloud without redundancy. The IoT radiations monitoring station is enabled with an advanced encryption standard (AES) 256-bit algorithm for onboard data encryption and transfer of the message securely. The message is then stored in the same encrypted form over the cloud to ensure security and privacy. Moreover, the website is developed to decrypt and display as per user input, whether real-time or historical. The experimental results clearly demonstrate the efficiency of the radiation monitoring system with end-to-end data security.
{"title":"Smart and Secure IoT based Remote Real-Time Radiation Detection and Measurement System","authors":"K. Saleem, Azam Adel Alajroosh, R. Ouni, W. Mansoor, A. Gawanmeh","doi":"10.1109/ICAISC56366.2023.10085583","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085583","url":null,"abstract":"This paper proposes a secure internet of things (IoT) based smart radiation detection and measurement system. The Waspmote platform is utilized to build an intelligent IoT station that communicates over 3rd Generation (3G) cellular communication for transferring data to the cloud without redundancy. The IoT radiations monitoring station is enabled with an advanced encryption standard (AES) 256-bit algorithm for onboard data encryption and transfer of the message securely. The message is then stored in the same encrypted form over the cloud to ensure security and privacy. Moreover, the website is developed to decrypt and display as per user input, whether real-time or historical. The experimental results clearly demonstrate the efficiency of the radiation monitoring system with end-to-end data security.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124391954","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085349
Aisha Al Obaidli, Deema Mansour, S. Abdulhamid, Nadhir Ben Halima, A. Al-Ghushami
Internet of Things (IoT) devices have a dark side could be used against the users or threaten the user by hackers and intruders. In addition, IoT devices have some security issues because the devices are basically connected to the internet and are more likely to get mishandled by hackers using anomaly attacks. In this paper, we proposed the application machine algorithms to detect anomaly attacks in IoT devices. The selected algorithms include are the Support Vector Machine (SVM) and Random Forest (RF). The SVM and RF are powerful supervised learning method that was utilized for both detection and feature selection. A standard anomaly dataset called the NSL-KDD dataset was used for the experimentation in arff format. The results shows an accuracy of approximately 99.9% and 97.9% with RF and SVM respectively, while a false positive rate of 0.1% was achieved in all scenarios for classification of anomaly attacks in IoT devices. This shows that the proposed method RF has higher accuracy than previous literatures, which is very promising. The RF and SVM posted a very encouraging recall and precision as well.
{"title":"Machine Learning Approach to Anomaly Detection Attacks Classification in IoT Devices","authors":"Aisha Al Obaidli, Deema Mansour, S. Abdulhamid, Nadhir Ben Halima, A. Al-Ghushami","doi":"10.1109/ICAISC56366.2023.10085349","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085349","url":null,"abstract":"Internet of Things (IoT) devices have a dark side could be used against the users or threaten the user by hackers and intruders. In addition, IoT devices have some security issues because the devices are basically connected to the internet and are more likely to get mishandled by hackers using anomaly attacks. In this paper, we proposed the application machine algorithms to detect anomaly attacks in IoT devices. The selected algorithms include are the Support Vector Machine (SVM) and Random Forest (RF). The SVM and RF are powerful supervised learning method that was utilized for both detection and feature selection. A standard anomaly dataset called the NSL-KDD dataset was used for the experimentation in arff format. The results shows an accuracy of approximately 99.9% and 97.9% with RF and SVM respectively, while a false positive rate of 0.1% was achieved in all scenarios for classification of anomaly attacks in IoT devices. This shows that the proposed method RF has higher accuracy than previous literatures, which is very promising. The RF and SVM posted a very encouraging recall and precision as well.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123496525","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085644
Sobia Arshad, Rida Zanib, Adeel Akram, Talha Saeed
For Network Intrusion Detection and Prevention Systems (NIDPS), Deep Packet Inspection (DPI) requires matching the payload against regular expressions and fixed strings to identify attack signatures. Such attack strings can span more than one IP fragment or TCP segment. This issue can lead to false results because strings cannot be identified this way. Therefore, to accurately identify such attack strings we need to reassemble traffic packets before string matching. Although various hardware-based solutions are provided for improvements at the TCP layer that includes reassembly too. The requirements of reassembly architectures which are suited to particular requirements of DPI systems, are reordering of segments or fragments and tracking of streams in bulk numbers. Along with this, it has to deal with ambiguities that might be present in IP fragmentation or TCP segmentation which can be done by traffic normalization or target-based reassembly. Therefore, in this paper, we present a short review of these TCP reassembly efforts. Then, we suggest solutions and approaches implement TCP reassembly for High-Speed Networks.
{"title":"A Short Review on Faster and More Reliable TCP Reassembly for High-Speed Networks in Deep Packet Inspection","authors":"Sobia Arshad, Rida Zanib, Adeel Akram, Talha Saeed","doi":"10.1109/ICAISC56366.2023.10085644","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085644","url":null,"abstract":"For Network Intrusion Detection and Prevention Systems (NIDPS), Deep Packet Inspection (DPI) requires matching the payload against regular expressions and fixed strings to identify attack signatures. Such attack strings can span more than one IP fragment or TCP segment. This issue can lead to false results because strings cannot be identified this way. Therefore, to accurately identify such attack strings we need to reassemble traffic packets before string matching. Although various hardware-based solutions are provided for improvements at the TCP layer that includes reassembly too. The requirements of reassembly architectures which are suited to particular requirements of DPI systems, are reordering of segments or fragments and tracking of streams in bulk numbers. Along with this, it has to deal with ambiguities that might be present in IP fragmentation or TCP segmentation which can be done by traffic normalization or target-based reassembly. Therefore, in this paper, we present a short review of these TCP reassembly efforts. Then, we suggest solutions and approaches implement TCP reassembly for High-Speed Networks.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123239316","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085552
Sikandar Ali, Abdullah, Ali Athar, Maisam Ali, Ali Hussain, Hee-Cheol Kim
Military object detection is an indispensable and challenging task for defence systems which includes the tracking, tracing, security, and surveillance of any territory or region. These systems should be very efficient, reliable, and accurate in executing their functions. A minute errant may result in mass destruction and loss. So automatic real-time object detections are imperative in today’s world. Although over the years, different traditional approaches and techniques have been used for the detection of military equipment, warheads, and other defence-related objects yet the efficiency and accuracy of those techniques are comparatively low compared to the artificial intelligence-based object detection techniques. Therefore, we demonstrate the latest computer vision-based real-time object detection technique to detect real-time military objects with high accuracy and precision. We introduced YOLOv5 for the detection of military tanks and flags. This model successfully detects the targeted objects i.e., tank and flag with high confidence and precision. We trained and evaluated the performance of YOLOv3, YOLOv4, and four versions of the YOLOv5 model i.e., YOLOVv5s, YOLOv5m, YOLOV51, YOLOV5x1 with 922 images consisting of tank and flag objects. The dataset has been divided into 80% training, 10% validation, and 10% testing. The detection results of all six YOLO versions are compared and evaluated. The experimental results showed that the YOLOv5xl achieved higher performance. The precision, recall, mAP_0.5, and mAP_0.95 were 0.99, 0.995, 0.995, and 0.892, respectively. Since YOLOv5 is one of the latest and fastest real-time object detection approaches so this model will empower and enhance the military surveillance systems by enabling the military personnels to take prompt and proactive actions against any potential threats.
{"title":"Computer Vision-Based Military Tank Recognition Using Object Detection Technique: An application of the YOLO Framework","authors":"Sikandar Ali, Abdullah, Ali Athar, Maisam Ali, Ali Hussain, Hee-Cheol Kim","doi":"10.1109/ICAISC56366.2023.10085552","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085552","url":null,"abstract":"Military object detection is an indispensable and challenging task for defence systems which includes the tracking, tracing, security, and surveillance of any territory or region. These systems should be very efficient, reliable, and accurate in executing their functions. A minute errant may result in mass destruction and loss. So automatic real-time object detections are imperative in today’s world. Although over the years, different traditional approaches and techniques have been used for the detection of military equipment, warheads, and other defence-related objects yet the efficiency and accuracy of those techniques are comparatively low compared to the artificial intelligence-based object detection techniques. Therefore, we demonstrate the latest computer vision-based real-time object detection technique to detect real-time military objects with high accuracy and precision. We introduced YOLOv5 for the detection of military tanks and flags. This model successfully detects the targeted objects i.e., tank and flag with high confidence and precision. We trained and evaluated the performance of YOLOv3, YOLOv4, and four versions of the YOLOv5 model i.e., YOLOVv5s, YOLOv5m, YOLOV51, YOLOV5x1 with 922 images consisting of tank and flag objects. The dataset has been divided into 80% training, 10% validation, and 10% testing. The detection results of all six YOLO versions are compared and evaluated. The experimental results showed that the YOLOv5xl achieved higher performance. The precision, recall, mAP_0.5, and mAP_0.95 were 0.99, 0.995, 0.995, and 0.892, respectively. Since YOLOv5 is one of the latest and fastest real-time object detection approaches so this model will empower and enhance the military surveillance systems by enabling the military personnels to take prompt and proactive actions against any potential threats.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130712453","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085076
Biswajit Mondal, Abhijit Banerjee, Subir Gupta
Cross-site scripting (XSS)has gotten little attention regarding detecting and keeping it secure, leaving artificial intelligence systems susceptible to assault. It is crucial to determine ways to make the detecting system more attack-resistant. This study aims to employ Trust Region Policy optimization (TRPO) reinforcement learning techniques to enhance XSS detection and prevent adversarial attacks. Before mining the model’s hostile inputs, the model’s information is obtained using a reinforcement learning framework. Second, a detection method and an adversarial method are simultaneously trained. New damaging data is introduced to the detection model every cycle to retrain it. The proposed XSS model mines risky inputs that black-box or white-box detection approaches miss during testing. It has been proved that the escape rate can be decreased by simultaneously training the detection technique and the attack model. It increases the models’ capacity for self-defense.
{"title":"XSS Filter detection using Trust Region Policy Optimization","authors":"Biswajit Mondal, Abhijit Banerjee, Subir Gupta","doi":"10.1109/ICAISC56366.2023.10085076","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085076","url":null,"abstract":"Cross-site scripting (XSS)has gotten little attention regarding detecting and keeping it secure, leaving artificial intelligence systems susceptible to assault. It is crucial to determine ways to make the detecting system more attack-resistant. This study aims to employ Trust Region Policy optimization (TRPO) reinforcement learning techniques to enhance XSS detection and prevent adversarial attacks. Before mining the model’s hostile inputs, the model’s information is obtained using a reinforcement learning framework. Second, a detection method and an adversarial method are simultaneously trained. New damaging data is introduced to the detection model every cycle to retrain it. The proposed XSS model mines risky inputs that black-box or white-box detection approaches miss during testing. It has been proved that the escape rate can be decreased by simultaneously training the detection technique and the attack model. It increases the models’ capacity for self-defense.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707838","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085680
Henriques Zacarias, Geraldo Cangondo, Leonice Souza-Pereira, N. Garcia, Bruno M. C. Silva, Nuno Pombo
Tourism is a major contributor to economic, social, and cultural development for countries and territories. It allows for the understanding of different cultures and customs, and the digital era, with its abundance of mobile technology, allows travellers to experience touristic activities while staying connected to the digital world. Mobile technologies can enhance the traveller’s experience and provide accurate recommendations. We propose a novel mobile recommendation system, which includes its architecture, components, and relevant features. The results showed that the K-means clustering model used is suitable, as evaluated by the Silhouette score, Calinski-Harabasz, and Davies-Bouldin indexes.
{"title":"Application of Content-Base Recommendation Algorithms on Mobile Travel Applications","authors":"Henriques Zacarias, Geraldo Cangondo, Leonice Souza-Pereira, N. Garcia, Bruno M. C. Silva, Nuno Pombo","doi":"10.1109/ICAISC56366.2023.10085680","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085680","url":null,"abstract":"Tourism is a major contributor to economic, social, and cultural development for countries and territories. It allows for the understanding of different cultures and customs, and the digital era, with its abundance of mobile technology, allows travellers to experience touristic activities while staying connected to the digital world. Mobile technologies can enhance the traveller’s experience and provide accurate recommendations. We propose a novel mobile recommendation system, which includes its architecture, components, and relevant features. The results showed that the K-means clustering model used is suitable, as evaluated by the Silhouette score, Calinski-Harabasz, and Davies-Bouldin indexes.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133796790","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085093
N. Sharma, M. Mangla, Mohammed Ishaque, S. Mohanty
Aspect Analysis of a multidimensional dataset aims to address diverse queries of the data analysts by analyzing different aspect of the data. Thus, it caters to the challenges faced by data analysts by presenting the solution to the most dilemmatic questions. Current research work focuses to present the various steps carried out during aspect analysis through statistical and visualization methods. For aspect analysis, authors have considered a dataset containing information about bookings of city hotel and resort hotels. The various features in the dataset are duration of stay, period of stay, and number of visitors (adults and children) among others. In order to maintain the privacy, authors have removed all personal information from the dataset. This aspect analysis of the data enables the owner to gain in-depth knowledge of the data that can be employed towards revenue generation, enhanced quality of service and well preparedness. Additionally, authors have also made an attempt to analyze the pattern in various actions of customers viz. arrival time, cancellations, and repeated check-ins etc. Understanding of such patterns not only helps in data analytics but also helps in boosting the sales.
{"title":"Inferential Statistics and Visualization Techniques for Aspect Analysis","authors":"N. Sharma, M. Mangla, Mohammed Ishaque, S. Mohanty","doi":"10.1109/ICAISC56366.2023.10085093","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085093","url":null,"abstract":"Aspect Analysis of a multidimensional dataset aims to address diverse queries of the data analysts by analyzing different aspect of the data. Thus, it caters to the challenges faced by data analysts by presenting the solution to the most dilemmatic questions. Current research work focuses to present the various steps carried out during aspect analysis through statistical and visualization methods. For aspect analysis, authors have considered a dataset containing information about bookings of city hotel and resort hotels. The various features in the dataset are duration of stay, period of stay, and number of visitors (adults and children) among others. In order to maintain the privacy, authors have removed all personal information from the dataset. This aspect analysis of the data enables the owner to gain in-depth knowledge of the data that can be employed towards revenue generation, enhanced quality of service and well preparedness. Additionally, authors have also made an attempt to analyze the pattern in various actions of customers viz. arrival time, cancellations, and repeated check-ins etc. Understanding of such patterns not only helps in data analytics but also helps in boosting the sales.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133242595","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085303
Amal Alkabkabi, Mounira Taileb
A large scale of data is posted every day on the social media platforms. Sentiment analysis classification is one of the useful techniques to extract useful information from those data. To train sentiment analysis models there is a need for labeled data, and it is one of the challenging issues. The available datasets are collected and labeled manually by humans which is a time-consuming process. The identification of machine learning classifier that provides the best performance is a second issue in sentiment analysis. A new hybrid sentiment analysis model is proposed in this paper. It relies on the use of the lexicon-based approach and majority voting. The best performance of the proposed model is when using the set of classifiers: NB, LogReg and SGD, it outperforms all the models with a single classifier in terms of accuracy, precision, recall and F-score.
{"title":"Hybrid Sentiment Analysis Model with Majority Voting for Un-labeled Arabic Text","authors":"Amal Alkabkabi, Mounira Taileb","doi":"10.1109/ICAISC56366.2023.10085303","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085303","url":null,"abstract":"A large scale of data is posted every day on the social media platforms. Sentiment analysis classification is one of the useful techniques to extract useful information from those data. To train sentiment analysis models there is a need for labeled data, and it is one of the challenging issues. The available datasets are collected and labeled manually by humans which is a time-consuming process. The identification of machine learning classifier that provides the best performance is a second issue in sentiment analysis. A new hybrid sentiment analysis model is proposed in this paper. It relies on the use of the lexicon-based approach and majority voting. The best performance of the proposed model is when using the set of classifiers: NB, LogReg and SGD, it outperforms all the models with a single classifier in terms of accuracy, precision, recall and F-score.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130267177","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085317
D. Sakthipriya, T. Chandrakumar, B. Johnson, Kumar Jb Prem
In Tamil Nadu, seasonal soil fertility, rainfall, and temperature account for more than 65% of agricultural output. Soils are one of the most valuable natural resources on the planet. The study’s goal was to analyze and survey the historical changes in soil parameter Index of Madurai District and Taluks, South India, using Clustering techniques of unsupervised learning to perform well for this proposed work. In this proposed work to involved, the survey should focus on the Soil parameters (N-Nitrogen, P-Phosphorus, K-potassium), rainfall, and temperature data retrieved from the agriculture government portal for the last five years. The study compares two machine learning clustering techniques, Hierarchical Clustering and K-Means Clustering in estimating soil features at Madurai Taluks. With the use of new agricultural technology, this proposed initiative intends to offer a better suggestion for obtaining an acceptable level of crop output to the Madurai surrounding blocks to get more benefits.
{"title":"A Survey - Soil Feature Analysis Using Clustering Techniques and Predict Various Crops in Madurai District","authors":"D. Sakthipriya, T. Chandrakumar, B. Johnson, Kumar Jb Prem","doi":"10.1109/ICAISC56366.2023.10085317","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085317","url":null,"abstract":"In Tamil Nadu, seasonal soil fertility, rainfall, and temperature account for more than 65% of agricultural output. Soils are one of the most valuable natural resources on the planet. The study’s goal was to analyze and survey the historical changes in soil parameter Index of Madurai District and Taluks, South India, using Clustering techniques of unsupervised learning to perform well for this proposed work. In this proposed work to involved, the survey should focus on the Soil parameters (N-Nitrogen, P-Phosphorus, K-potassium), rainfall, and temperature data retrieved from the agriculture government portal for the last five years. The study compares two machine learning clustering techniques, Hierarchical Clustering and K-Means Clustering in estimating soil features at Madurai Taluks. With the use of new agricultural technology, this proposed initiative intends to offer a better suggestion for obtaining an acceptable level of crop output to the Madurai surrounding blocks to get more benefits.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"520 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116265200","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：