{"title":"Sarcasm Identification in text with deep learning models and Glove word embedding","authors":"Ganesh Chandrasekaran, D. Hemanth, M. Saravanan","doi":"10.1109/ICCCIS56430.2022.10037615","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037615","url":null,"abstract":"In social media, sarcasm is frequently found to convey a negative opinion employing positive or exaggerated positive terms. Sarcasm is necessary for and advantageous for many Natural Language Processing (NLP) algorithms. Unless explicitly constructed to compensate for it, sarcasm can readily fool sentiment analysis tools. Sarcasm abounds in viewer stuff, such as Facebook postings and Tweets. It’s quite difficult to spot sarcasm without a complete awareness of the event, the wider problem, and the context. Memory-based network models, notably Long Short Term Networks (LSTM), Bidirectional Long-Short Memory (Bi-LSTM), and Convolution Neural Network (CNN) algorithms, can identify sarcastic remarks in a corpus. We assess the efficacy of competing Deep Learning algorithms for text sarcasm identification using the SarcasmV2 corpus. Based on the results, we can infer that for sarcasm detection, the Bidirectional Long Short Term Memory Network (Bi-LSTM) model provides the best performance. The suggested approach involving deep networks is consistent towards many traditional approaches for sarcasm detection, and based on specific standard performance indicators, the current model outperforms these approaches.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126141374","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}
{"title":"Exploring Multiple Deep learning Models for Skin Cancer Classification","authors":"Ajay Krishan Gairola, Vidit Kumar, A. Sahoo","doi":"10.1109/ICCCIS56430.2022.10037675","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037675","url":null,"abstract":"The most frequent health concern is skin cancer, which is caused by exposure to UV light. Identification of the disorder is made when the epidermal tissues develop abnormally and acquire a non-normal color. Melanoma is caused by overexposure to UV radiation. Melanoma is curable if caught early enough. If cancer is not caught early enough, it can spread to other parts of the body and become extremely difficult to cure. Traditional approaches for identifying melanoma include visual inspection and biopsy; however, the accuracy of these methods varies widely. Medical imaging researchers now face a major challenge in trying to tell the difference between benign and malignant melanoma. In this paper, we look into how well CNN’s models perform in diagnosing skin cancer. Here, we examine characteristics shared by numerous Convolutional Neural Network (CNN) models, including Alex-Net VGGNet16, VGGNet19, ResNet18, ResNet50, ResNetl01, DenseNet121, and DenseNet161. To run the experiment, we have chosen the ISIC-2016 dataset. The results show that Densenet161 performs best when used for a single CNN classification. In addition, the results demonstrate that the fusion of many CNN features improves accuracy even further.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129419469","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}
{"title":"MQTT equipped Intrusion detection system for IoT devices based Machine Learning Algorithms","authors":"Priya P. Sharma, Sanjay Sharma, Diksha Dani","doi":"10.1109/ICCCIS56430.2022.10037613","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037613","url":null,"abstract":"In the era of COVID19, the world has shifted to an online presence and is now forced to embrace the usage of digital technology in their daily lives. With the meteoric rise of internet-based devices, there is a requirement for a protocol for secure communication between these devices. Message Queueing Telemetry Transport (MQTT) is the standard protocol for IoT devices. The MQTT implementation with IDS have very prominent usability and has huge potential for increasing efficiency. Therefore, in this paper, an IDS has been proposed with MQTT as a protocol for IoT devices, using machine learning to improve the pattern recognition of the IDS. The proposed system has been tested with three machine learning algorithms, namely, and the results show that they are adequate for the MQTT protocol","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128328362","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}
{"title":"Federated Learning with Blockchain: A Study of the Latest Decentralized Couple","authors":"Arman Rasool Faridi, Aiman Hafeez, Faraz Masood","doi":"10.1109/ICCCIS56430.2022.10037647","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037647","url":null,"abstract":"Federated learning is a method for machine learning that avoids the need to move data by training an algorithm in parallel on a large number of edge devices or servers that hold copies of the training data in their own memory. Conventional decentralized approaches often assume that local data samples are equally distributed, whereas typical centralized machine learning techniques involve uploading all local datasets to a single server. Federated learning has flaws like privacy and insufficient data. Blockchain’s rise offers a safe and effective method for Federated Learning implementation. In this paper, the collaboration of Federated learning and blockchain is discussed. Then the possible applications that can be developed using federated learning and blockchain are discussed. Furthermore, the challenges and opportunities for collaboration between these technologies are explained.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129015181","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}
{"title":"Secured Authentication by Single Sign On (SSO): A Big Picture","authors":"N. Shaikh, K. Kasat, Smita Jadhav","doi":"10.1109/ICCCIS56430.2022.10037708","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037708","url":null,"abstract":"Single Sign On (SSO) is a tool used for single login credentials to authorise the user to access all software or applications independent of each other, causing users to log in repeatedly. With the help of an administrator, it minimizes the security risk of managing the user. SSO allows users to access the various applications after one login. It does not mean that the Single Sign On system merges many different user account information for all the different services as well as the many applications and systems. SSO safely stores multiple user login information into a single account that, with the help of these credentials, users need to login. With the help of login credentials, the SSO system will generate authentication information that is accepted by the different applications and systems. In the present research article, many different types of technologies that operationalize SSO are collated. Various implementation types of SSO are explained. It also discusses the protocols used in SSO, SSO architecture, advantages of SSO, implementation of SSO in detail and challenges faced by SSO. An overall broader picture of SSO is discussed in this regard.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122356961","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}
{"title":"Technical Ameliorations in Automatic License Plate Number Recognition System: A Survey","authors":"Merajul Aarfeen, Paranjot Singh, Huzaif Mushtaq, Keshav Gupta","doi":"10.1109/ICCCIS56430.2022.10037733","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037733","url":null,"abstract":"With the increase in Urbanisation, there has been a Drastic Incremental Outlook in the field of Automobiles. Due to the escalated Population, Vehicular Involvement in Smart Cities is also on an extortionate ascent. To maintain Security and actuate Law & Order it becomes prominently important to integrate a Surveillance System for the same, to enable Increased Security with efficiency along with Less Human Intervention to diminish any Error. For catalyzing the above ideation, various methodologies have been incorporated, in order to prevent any anomaly, through Vehicular Reconnoitre. Inspection stands to be the most elucidated phenomenon for maintaining the fundamentals of the Smart System of Transportation. Diverse approaches have been inculcated for Vehicle Detection along with License Plate Number Detection to facilitate secure Transportation. In this paper, we’ve tried to understand the Technological Integrations into the domain of Smart Surveillance Systems for enabling Smart Transportation and thereby aiding to the Decorousness of the entire Automobile System.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130551421","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}
{"title":"A Novel Technique for Locating Faults Using Fuzzy Logic in HVDC Lines","authors":"A. Swetapadma, Tejashwi Shubham","doi":"10.1109/ICCCIS56430.2022.10037750","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037750","url":null,"abstract":"In this work, fuzzy inference system (FIS) based distance estimation has been proposed using voltage measurement for HVDC lines. In this method, rectifier end measurements are used to locate faults. Mamdani type FIS with triangular member function is used for locating the faults. Advantage of the method is that it has less error in fault location and more reach setting. The proposed method does not use signals from both end but only one end. Novelty of the work is that there is no FIS based fault location estimation schemes proposed as of author’s knowledge for DC transmission lines. Hence, the proposed method can locate faults in bipolar HVDC lines.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131695094","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}
{"title":"Semantic Segmentation in Medical Image Based on Hybrid Dlinknet and Unet","authors":"Suresh Samudrala, C. Mohan","doi":"10.1109/ICCCIS56430.2022.10037693","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037693","url":null,"abstract":"Medical imagery segmentation has been widely using deep learning approaches, which are quickly evolving in semantic segmentation. Nevertheless, due to their poor performance, newly proposed methods like Fully Convolutional Network, U-Net, LinkNet and SegNet still require enhancement to offer better semantic segmentation while identifying breast cancer. Therefore, this article presents a hybrid encoder and decoder framework in histology images of tissue slides. The novel network is designed with DlinkNet and UNet with a fusion of medical imagery data. An Attention Gate Module (AGM) is inserted into the proposed network to enrich the network learning’s capacity. This way, semantic features are extracted and semantically segmented in the tumors in the input image set. The effectiveness of the planned network is investigated concerning various parameters like Maximum Symmetric Surface Distance (MSSD 35.98), Accuracy (99.2%), Relative Absolute Volume Difference (RAVD 3.41), Jaccard index (0.83), Average Symmetric Surface Distance (ASSD 0.629), Sensitivity (91%) and Dice Coefficient (DICE) (0.928) with existing networks of FPN and SENet.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121403899","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}
Pasala Bharath Kumar Reddy, G. P. Reddy, Farhana Tabassum, Yogesh Kumar Bhawsar, Imteyaz Ahmad, J. Khoral
{"title":"Beam Hopping Technique For Indian Data Traffic","authors":"Pasala Bharath Kumar Reddy, G. P. Reddy, Farhana Tabassum, Yogesh Kumar Bhawsar, Imteyaz Ahmad, J. Khoral","doi":"10.1109/ICCCIS56430.2022.10037616","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037616","url":null,"abstract":"Current trend in space technology involves satellites that can provide variable Effective Isotropic Radiated Power (EIRP), variable bandwidth and flexible coverage area. With an inclination towards mass optimisation and to fully utilise the available resources on board by reusing them efficiently, a technique called beam hopping with spot beam technology has gained traction. In this paper, the feasibility of a beam hopping satellite for India along with its merits and demerits over conventional High Throughput Satellite (HTS) are discussed. Maximum advantage of beam hopping is obtained if the beams are hopped as per real time user demand which requires constant co-ordination between the satellite, ground station & the user. This requires dynamic resource allocation, thereby increasing the ground complexity manifold. In this paper, rather than dynamic hopping, probable data rate demand in various parts of India is analysed, a suitable probability distribution for the demand rate is identified and a beam hopping scheme is proposed to obtain near optimal throughput. Further, a comparative analysis of Beam Hopping HTS (BH HTS) is carried out with standard HTS to establish the effectiveness of beam hopping.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123793478","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}
G. Ananthakrishnan, Ashok Kumar Jayaraman, T. Trueman, Satanik Mitra, A. K, Abirami Murugappan
{"title":"Suicidal Intention Detection in Tweets Using BERT-Based Transformers","authors":"G. Ananthakrishnan, Ashok Kumar Jayaraman, T. Trueman, Satanik Mitra, A. K, Abirami Murugappan","doi":"10.1109/ICCCIS56430.2022.10037677","DOIUrl":"https://doi.org/10.1109/ICCCIS56430.2022.10037677","url":null,"abstract":"Suicidal intention or ideation detection is one of the evolving research fields in social media. People use this platform to share their thoughts, tendencies, opinions, and feelings toward suicide. Therefore, this task becomes a challenging one due to the unstructured and noisy texts. In this paper, we propose five BERT-based pre-trained transformer models, namely, BERT, DistilBERT, ALBERT, RoBERTa, and DistilRoBERTa, for the task of suicidal intention detection. The performance of these models evaluated using the standard classification metrics. Specifically, we use the one-cycle learning rate policy to train all models. Our results show that the RoBERTa model achieves a better performance than other BERT-based models. The model gains 99.23%, 96.35%, and 95.39% accuracy for training, validation, and testing, respectively.","PeriodicalId":286808,"journal":{"name":"2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131189940","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}