{"title":"An Advanced Approach for Detection of Distributed Denial of Service (DDoS) Attacks Using Machine Learning Techniques","authors":"G. Sujatha, Yash Kanchal, Geogen George","doi":"10.1109/ICOSEC54921.2022.9951944","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9951944","url":null,"abstract":"One of the most hazardous attacks in network security is the Distributed Denial of Service (DDoS) attack. DDoS is endangering the internet because it halts the functionality of vital services of online applications. When a system is under a DDoS attack, it is unable to provide services to its customers as the system is busy with false requests coming from the attackers. Which can cause a serious problem if banking, healthcare, or government service went under such an attack. DDoS attacks are rapidly increasing and are getting more sophisticated, so it has become difficult to detect these attacks and at the same time protect online services from them. This research study suggests an advanced approach for the detection of such attacks by integrating machine learning techniques.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122225828","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":"Survey: An Automatic Parallel Parking using Path Planning Methodologies","authors":"Poojitha Cheedalla, Madhavi Karanam","doi":"10.1109/ICOSEC54921.2022.9952024","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9952024","url":null,"abstract":"Throughout the years, the expectations and capabilities of autonomous vehicles have increased, as has the level of automotive intelligence. In the majority of research studies, longitudinal and lateral control topics have been explored to understand and design intelligent systems. For example: Automatic parallel parking, Adaptive cruise control, co-operative adaptive cruise control, semi and fully autonomous cars. Sensors onboard the vehicle and communications networks transmit scene information to other vehicles and infrastructure. To be able to achieve autonomously driving on complex environments and to utilize the information as part of the motion planning and control schemes, different motion planning and control techniques were implemented. Upon implementing these initiatives, the main task is executed to increase the level of safety, comfort, and energy efficiency in the workplace. As part of the present paper, an in-depth review of various parallel parking methodologies based on automatic parallel parking is presented. In this presentation, the main topics that will be covered will be algorithm types, simulations, and field tests, as well as human factors that influence vehicle behavior. Additionally, various parking information services are also offered for parking guidance, facility management, and even for providing an insight into the parking situation. We have also provided a brief description of the techniques used by research teams, a comparison between these techniques, and additional information about the research teams’ contributions to motion planning. The paper concludes by discussing a future research direction and application.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126821205","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}
S. Bharathi, A. Balaji, Dolly Irene. J, C. Kalaivanan, R. Anusuya
{"title":"An Efficient Liver Disease Prediction based on Deep Convolutional Neural Network using Biopsy Images","authors":"S. Bharathi, A. Balaji, Dolly Irene. J, C. Kalaivanan, R. Anusuya","doi":"10.1109/ICOSEC54921.2022.9951870","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9951870","url":null,"abstract":"The much more prevalent reason for chronic liver illness in the United States is a condition known as nonalcoholic fatty liver disease (NAFLD). This condition affects thirty percent of adult Americans, has the potential to develop into nonalcoholic steatohepatitis (NASH) as well as end-stage liver problems, and causes significant predictor for diabetes and cardiovascular disease. Steatosis is indeed the development of benign fatty tissues, which, at greater rates, contributes to the advancement of NASH Hepatic fibrosis and cirrhosis, as well as hepatocellular cancer, are both linked to steatosis. Hepatocellular carcinoma is more likely to occur in those with steatosis (HCC). In latest days, the healthcare industry has placed a greater emphasis on avoiding the advancement of these disorders. The computed tomography that is considered to be the standard method in current medical studies is microscopic biopsy pictures. By learning a convolutional neural network (CNN) as well as evaluating its detection performance with that of several pretrained deep CNN designs, the study that is being offered intends to achieve a good generalization capabilities of four histological liver features. The improved CNN model achieved a generalization ability of 96.8 percent on the enhanced picture database, while AlexNet emerged to be the most efficient architecture with such a matching efficiency of 96.89 percent All diagnosis efforts were done on the supplemented image dataset","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116657470","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 Deep Review and State-of-the-art Performance on Fingerprint Liveness Detection Databases","authors":"B. R. Rajakumar, S. Amala Shanthi","doi":"10.1109/ICOSEC54921.2022.9951934","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9951934","url":null,"abstract":"The need of effective Fingerprint Liveness Detection (FLD) has been arising due to advancements in spoofing fingerprint. The literature has been reported with numerous FLD techniques, which have been experimented on different datasets. However, the literature lags on deep details of benchmark databases and own databases of researchers. This poses a challenge to researchers in contributing and experimenting FLD techniques in a common platform. Hence, this paper extensively reviews the databases that have been used in the literature in the past decade. The review discusses the characteristics of the databases, volume of images and image acquisition environment. In addition, this review paper presents the state-of-the-art performance achieved on FLD databases and the methodology used to achieve them.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125630904","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}
P. Abdul Hafeez, Gurpreet Singh, Jasrpreet Singh, C. Prabha, Amit Verma
{"title":"IoT in Agriculture and Healthcare: Applications and Challenges","authors":"P. Abdul Hafeez, Gurpreet Singh, Jasrpreet Singh, C. Prabha, Amit Verma","doi":"10.1109/ICOSEC54921.2022.9952061","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9952061","url":null,"abstract":"The Internet of Things (IoT) is the present and future of every field, influencing everyone’s lives by making everything smart. Almost every industry, including agriculture and healthcare, has been rebuilt as a result of the quick rise of Internet-of-Things-based technologies. Agriculture’s significant developments with the deployment of IoT are changing the landscape of traditional farming methods by making them not only more productive but also more financially viable and sustainable for farmers.Health is the most pressing concern for the bulk of the population, irrespective of age. IoT has shown potential in connecting a variety of medical devices, sensors, and healthcare experts in order to provide high-quality medical treatment. The flow of this current study gives a complete collection of information on the IoT environment,including most commonly utilized IoT sensors. The significance of integrating IoT technologies into the agriculture and healthcare domains has also been presented herein in the tabular form. Incorporating Agriculture- IoT and Health-IoT systems into a real- time scenario can provide ample scope for research in predicting, processing, and analyzing circumstances, as well as boosting timely actions.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"16 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114022021","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}
MangiReddiHemanth, M. Chandra, VaddeRaviteja, R. Sumathi, J. Jeyaranjani
{"title":"Analysis of Predicting Bitcoin Price using Deep Learning Technique","authors":"MangiReddiHemanth, M. Chandra, VaddeRaviteja, R. Sumathi, J. Jeyaranjani","doi":"10.1109/ICOSEC54921.2022.9951929","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9951929","url":null,"abstract":"The major aim of this work is to uncover the accuracy of the Bitcoin price in any fiat/flat currency that can be predicted in advance. Bitcoin is a form of cryptocurrency and is now one of the most popular types of investments in the stock market. And bitcoin is the only form of cryptocurrency that has been on the rise in the last few years, and sometimes a sudden collapse without knowing the impact behind it in the stock market. To utilize the long short-term memory for predicting the bitcoin value in advance. Many researchers used RNN for this bitcoin prediction and observed that it lacks in consistency, to overcome this issue LSTM and ARIMA are used to ensure the accuracy and yields better prediction in terms of time series and proves that it is superior to existing state of art techniques.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131400241","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 Research on the Perspective of Exploring Restricted Decentralized Blockchain by Applying PoFE: Proof of Familiarity and Existence to Reinforce Multiple Domains","authors":"K. Sheela, C. Priya","doi":"10.1109/ICOSEC54921.2022.9952095","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9952095","url":null,"abstract":"Incorporation of Blockchain technology into our real-life scenarios serves in many aspects to improvise their services. Blockchain is a node-to-node decentralized distributed ledger system which provides clarity and unchangeable records of any digital assets while avoiding the intervention of a middleman. It is a new and revolutionary technology that is gaining a lot of attention because of its ability to eliminate threats and frauds on a large scale. The complete decentralized nature of blockchain has certain drawbacks wherein a restricted decentralized network can be accomplished in order to direct the overall process. The centralized server will be maintained along with its basic distributed nature with an authorized controller or miner. Every transaction will be stored in all the nodes and one node will be considered as a chief node wherein certain authenticating powers are provided to monitor and direct the operation in a successful manner. This process eliminates the involvement of multiple parties called miners to mine the block which reduces certain complications like time consumption for choosing miners, finding a fault node in case of breakdown and so on. Certain procedures are implemented to prove the presence of the records along with a process which encourages synergistic decision making for users using the Proof of Familiarity and Existence algorithm. Also, an approach of utilizing the nodes of any sector will be considered for smooth maintenance of an entire data in a blockchain platform. An approach of collaborating Proof of Familiarity and Proof of Existence will be carried out to enrich the decision-making system in both private and public sectors.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115160226","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}
Rashiduzzaman Shakil, Bonna Akter, F. M. Javed Mehedi Shamrat, Nusrat Jahan, S. Hasan, Ankit Khater
{"title":"Systematic Analysis of Several Deep Learning Approaches for COVID-19 Detection Using X-ray Images","authors":"Rashiduzzaman Shakil, Bonna Akter, F. M. Javed Mehedi Shamrat, Nusrat Jahan, S. Hasan, Ankit Khater","doi":"10.1109/ICOSEC54921.2022.9952147","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9952147","url":null,"abstract":"COVID-19 is a virus-borne malady. A clinical study of infected COVID-19 patients found that most COVID-19 patients suffered lung infection after contracting the disease. Consequently, chest X-rays are a more effective and lower-cost imaging technique for diagnosing lung-related problems. This study used deep learning models, including MobileNetV2,DenseNet201, ResNet50, and VGG19, for COVID-19 prediction. For the study, we used chest X-ray image data for binary classification of COVID-19. 7207 chest X-ray image data were obtained from the Kaggle repository, with 5761 being utilized for training and 1446 being used for validation. A comparative analysis was conducted among the models and examined their accuracy. It has been determined that the DenseNet201 models achieved the highest accuracy of 93.02% for detecting COVID-19 in the lowest compilation time of 27secs. The models, MobileNetV2, ResNet50, and VGG19 had the accuracy rate of 77.28%, 65.86% and 74.92%, respectively. The research indicates that the DenseNet201 model is the most effective in detecting COVID-19 using x-ray imaging.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132541431","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":"KCIR: A Novel Iris Recognition System using Deep CNN with Kalman Filtering","authors":"Vinolyn Vijaykumar, K. Selvam","doi":"10.1109/ICOSEC54921.2022.9951932","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9951932","url":null,"abstract":"In today’s environment, authorizing somebody has become a critical requirement. In such conditions, the incorporation of artificial intelligence into biometric authentication systems has altered the lives of people and operations at diverse stages. Machine learning is becoming ever more popular in various fields of computer science. A powerful visual representation of machine learning is a deep conventional neural network. For an authentication system using iris, it tends to present resilience and effective structure. The Iris arrangement is a biological trait that is unique to each person, paving way for a vital and effective tool for authenticating a person. This research provides a robust iris recognition strategy based on a Convolutional Neural Network using Kalman Filter. The suggested system outperforms certain current iris recognition strategies on public iris databases, such as Ubiris.v2, CASIA, and MMU V1.0, in terms of experimental findings, with an accuracy of above 99 percent.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131825871","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":"Research on Optimization of Neural Network Structure based on Variational Inequality: from the Perspective of Connection Structure","authors":"Yufeng Pan","doi":"10.1109/ICOSEC54921.2022.9952022","DOIUrl":"https://doi.org/10.1109/ICOSEC54921.2022.9952022","url":null,"abstract":"This paper analyzes the stability of generalized projective neural networks based on optimization theory, projective theory, stability theory of differential equations, and the principle of invariance, and gives solutions to generalized variational inequalities and a class of common sense monotonic linear variational inequalities. The new neural network model of the problem rigorously proves the various stability of the new chess pattern theoretically, especially the numerical examples of asymptotic stability show the feasibility and effectiveness of these networks at the same time. Due to the limitations of analysis methods, some existing neural networks for solving variational inequality problems (delay/non-delay) have relatively conservative stability conditions.","PeriodicalId":221953,"journal":{"name":"2022 3rd International Conference on Smart Electronics and Communication (ICOSEC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132294662","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}