Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009440
H. Rajaguru, Sannasi Chakravarthy S R, S. Chidambaram
Being a fatal disorder, lung cancer becoming a primary reason for mortality in people who are affected with various symptoms. This implies that there is always a necessity in the medical field to have a promising approach for detection and timely treatment for such disorders. Also, it is required to be done at an earlier stage to attain a reduced mortality rate among cancer patients. The work intended to propose a hybrid machine learning (ML) strategy for the classification of lung cancer. The approach incorporates both Non-Linear Regression (NLR) and Gaussian Mixture Model (GMM), combinely termed as NLR-GMM algorithm. The algorithm takes the key advantages of both machine learning models for better classification of lung cancer data. For this, the work employs the lung cancer dataset constituted using its symptoms. The data set is preprocessed and visualized for analysis. Then classification is performed using the proposed hybrid ML approach which provides a maximum performance of 92.88% of classification accuracy. The results are compared with the existing ML algorithms such as Gaussian Naïve Bayes and K-Nearest Neighbor algorithms for checking the proposed strategy.
{"title":"Gaussian Mixture Model based Hybrid Machine Learning for Lung Cancer Classification using Symptoms","authors":"H. Rajaguru, Sannasi Chakravarthy S R, S. Chidambaram","doi":"10.1109/STCR55312.2022.10009440","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009440","url":null,"abstract":"Being a fatal disorder, lung cancer becoming a primary reason for mortality in people who are affected with various symptoms. This implies that there is always a necessity in the medical field to have a promising approach for detection and timely treatment for such disorders. Also, it is required to be done at an earlier stage to attain a reduced mortality rate among cancer patients. The work intended to propose a hybrid machine learning (ML) strategy for the classification of lung cancer. The approach incorporates both Non-Linear Regression (NLR) and Gaussian Mixture Model (GMM), combinely termed as NLR-GMM algorithm. The algorithm takes the key advantages of both machine learning models for better classification of lung cancer data. For this, the work employs the lung cancer dataset constituted using its symptoms. The data set is preprocessed and visualized for analysis. Then classification is performed using the proposed hybrid ML approach which provides a maximum performance of 92.88% of classification accuracy. The results are compared with the existing ML algorithms such as Gaussian Naïve Bayes and K-Nearest Neighbor algorithms for checking the proposed strategy.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"06 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127274988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009566
T. Perarasi, K. Ali, M. Moses, C. Poongodi, R. Gayathri, D. Deepa
In this paper, an antenna for a narrow band in dual mode of operation for radio frequency applications is presented and is assumed to be Smart. The performance of antenna is analyzed to enhance radiation characteristics of autonomous vehicle system that are predominant in today’s technology operated at 76 GHz and 78 GHz. A bowtie structured antenna which are apt design for size reduction are operated and designed in two bands by changing its mechanical functionalities and other structure is also compared. For the effective transmission of signals in all the directions for vehicle, a dual-mode design is proposed with the directivity of 5 dB. Is radiation characteristics validates the better coverage and its radiation efficiency is estimated as 73% as compared with existing 51%. From value of insertion loss of -13.3 dB it is validated that the value of VSWR is lesser than unity. Current distribution provides its coverage and it is absolutely working better at operating frequency of autonomous vehicle band. Gain is increased by approximately by 2 dB and front to back ratio as 3.13 dB which helps in size reduction of around 11.2%.
{"title":"Design of Dual Narrowband High Frequency Smart Antenna","authors":"T. Perarasi, K. Ali, M. Moses, C. Poongodi, R. Gayathri, D. Deepa","doi":"10.1109/STCR55312.2022.10009566","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009566","url":null,"abstract":"In this paper, an antenna for a narrow band in dual mode of operation for radio frequency applications is presented and is assumed to be Smart. The performance of antenna is analyzed to enhance radiation characteristics of autonomous vehicle system that are predominant in today’s technology operated at 76 GHz and 78 GHz. A bowtie structured antenna which are apt design for size reduction are operated and designed in two bands by changing its mechanical functionalities and other structure is also compared. For the effective transmission of signals in all the directions for vehicle, a dual-mode design is proposed with the directivity of 5 dB. Is radiation characteristics validates the better coverage and its radiation efficiency is estimated as 73% as compared with existing 51%. From value of insertion loss of -13.3 dB it is validated that the value of VSWR is lesser than unity. Current distribution provides its coverage and it is absolutely working better at operating frequency of autonomous vehicle band. Gain is increased by approximately by 2 dB and front to back ratio as 3.13 dB which helps in size reduction of around 11.2%.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125346990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009102
S. Thenmozhi, Bharath M. B
Data security is essential for information distribution in the world of information and communication tools today. Data concealing has grown more and more important with the rise of intense multimedia sharing and secret discussions. Steganography is a method of obscuring data in a way that makes it nearly impossible to find. According to a recent study, when the networks between the layers closest to the input and those closest to the output are thinner, convolutional neural networks can become noticeably deeper, more precise, and easier to train. The fundamental drawback of R-CNN, which was previously utilized in place of CNN, is that it adds the characteristics while CNN is used to concatenate them.
{"title":"CNN based Image Steganography Techniques: A Cutting Edge/State of Art Review","authors":"S. Thenmozhi, Bharath M. B","doi":"10.1109/STCR55312.2022.10009102","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009102","url":null,"abstract":"Data security is essential for information distribution in the world of information and communication tools today. Data concealing has grown more and more important with the rise of intense multimedia sharing and secret discussions. Steganography is a method of obscuring data in a way that makes it nearly impossible to find. According to a recent study, when the networks between the layers closest to the input and those closest to the output are thinner, convolutional neural networks can become noticeably deeper, more precise, and easier to train. The fundamental drawback of R-CNN, which was previously utilized in place of CNN, is that it adds the characteristics while CNN is used to concatenate them.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114899442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009353
K. B, Meghana G, Roshni M, B. N
Usage of Machine Learning algorithms for assisting healthcare providers is increasing day by day. But the performance and robustness of the machine learning algorithms are the main concerns while implementing them for critical healthcare applications such as detection of cancer. This work concentrates on the performance improvement of supervised classifiers through the feature transform based on Rat Swarm Optimizer in diagnosing lung cancer using histopathological images. Rat Swarm Optimizer used for the transformation of features. These transformed features are more capable of providing better classification accuracy when compared to normal features. The dataset is downloaded from the publicly available website and three classes are present: normal, lung squamous cell carcinomas, and lung adenocarcinomas. In each class, 1000 histopathological images are considered. Four supervised classifiers namely Histogram-Gradient boosting classifier, Random forest classifier, K-Nearest Neighbor classifier, and Linear Discriminant Analysis classifiers are tested. The highest accuracy of 90.66% is offered by Histogram-Gradient boosting classifier and this is increased to 95.82% when Rat Swarm Optimizer is used as transform before classification.
{"title":"Rat Swarm Optimizer based Transform for Performance Improvement of Machine Learning Classifiers in Diagnosis of Lung Cancer","authors":"K. B, Meghana G, Roshni M, B. N","doi":"10.1109/STCR55312.2022.10009353","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009353","url":null,"abstract":"Usage of Machine Learning algorithms for assisting healthcare providers is increasing day by day. But the performance and robustness of the machine learning algorithms are the main concerns while implementing them for critical healthcare applications such as detection of cancer. This work concentrates on the performance improvement of supervised classifiers through the feature transform based on Rat Swarm Optimizer in diagnosing lung cancer using histopathological images. Rat Swarm Optimizer used for the transformation of features. These transformed features are more capable of providing better classification accuracy when compared to normal features. The dataset is downloaded from the publicly available website and three classes are present: normal, lung squamous cell carcinomas, and lung adenocarcinomas. In each class, 1000 histopathological images are considered. Four supervised classifiers namely Histogram-Gradient boosting classifier, Random forest classifier, K-Nearest Neighbor classifier, and Linear Discriminant Analysis classifiers are tested. The highest accuracy of 90.66% is offered by Histogram-Gradient boosting classifier and this is increased to 95.82% when Rat Swarm Optimizer is used as transform before classification.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115065451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009300
K. Priyadharsini, Sudharsan Perumal, J. D. Dinesh Kumar, K. Darshan, S. Vignesh, P. Vinoth
Identifying strong handwritten characters is a difficult task in the field of medical field and it is tedious process on decoding handwritten medicines. Recognition of handwritten mathematical expressions is a complex issue. The distribution and classification of specific characters makes the task more difficult. In our project, handwritten numbers and symbols are read and further addition, subtraction and multiplication operations are performed. The project includes a study about model deployment using convoluted neural networks and flasks. We use the CNN to classify specific characters. Tracking of character string operations are used to solve equations. The maximum accuracy of the proposed model is 99.12% recall is 95%, sensitivity is 89% and specificity is 68%. Effectiveness of our proposed system is helpful for students who want to get handwritten answers. The equation can be extended to more complex equations and more user data can be trained to improve correction and accuracy.
{"title":"Performance Investigation of Handwritten Equation Solver using CNN for Betterment","authors":"K. Priyadharsini, Sudharsan Perumal, J. D. Dinesh Kumar, K. Darshan, S. Vignesh, P. Vinoth","doi":"10.1109/STCR55312.2022.10009300","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009300","url":null,"abstract":"Identifying strong handwritten characters is a difficult task in the field of medical field and it is tedious process on decoding handwritten medicines. Recognition of handwritten mathematical expressions is a complex issue. The distribution and classification of specific characters makes the task more difficult. In our project, handwritten numbers and symbols are read and further addition, subtraction and multiplication operations are performed. The project includes a study about model deployment using convoluted neural networks and flasks. We use the CNN to classify specific characters. Tracking of character string operations are used to solve equations. The maximum accuracy of the proposed model is 99.12% recall is 95%, sensitivity is 89% and specificity is 68%. Effectiveness of our proposed system is helpful for students who want to get handwritten answers. The equation can be extended to more complex equations and more user data can be trained to improve correction and accuracy.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009596
T. Subburaj, T. Nagalakshmi, N. Krishnamoorthy, J. Uthayakumar, R. Thiyagarajan, S. Arun
An intrusion detection system that employs a variety of system tasks and log files that are being generated on the host machine to detect HIDS refers to high-intensity distributed denial-of-service attacks. To enhance the capacity of intrusion detection systems, Big Data with Deep Learning Methods are combined. Deep Neural Network (DNN) and highly proficient approaches, Random Forest as well as Gradient Boosting Tree, are utilized to categories internet traffic datasets. Deep learning algorithms are widely used to develop an intrusion detection system (IDS) task of automatically recognizing and characterizing attacks at the host addressing performance in real time. Researchers utilize a homogeneity measure to analyze characteristics to identify its most productivity and organizational from dataset. As according to extensive experimental research, DNNs outperform classical machine learning classifiers in terms of performance. The findings shows that DNN has a good precision for different classifiers detection on datasets with accuracy rate for multi-class categorization. Employing Apache Flink to simplify the process and handling the streaming capabilities.
{"title":"Descriptive Analytics Solution for Attack Detection by Utilizing DL Strategies","authors":"T. Subburaj, T. Nagalakshmi, N. Krishnamoorthy, J. Uthayakumar, R. Thiyagarajan, S. Arun","doi":"10.1109/STCR55312.2022.10009596","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009596","url":null,"abstract":"An intrusion detection system that employs a variety of system tasks and log files that are being generated on the host machine to detect HIDS refers to high-intensity distributed denial-of-service attacks. To enhance the capacity of intrusion detection systems, Big Data with Deep Learning Methods are combined. Deep Neural Network (DNN) and highly proficient approaches, Random Forest as well as Gradient Boosting Tree, are utilized to categories internet traffic datasets. Deep learning algorithms are widely used to develop an intrusion detection system (IDS) task of automatically recognizing and characterizing attacks at the host addressing performance in real time. Researchers utilize a homogeneity measure to analyze characteristics to identify its most productivity and organizational from dataset. As according to extensive experimental research, DNNs outperform classical machine learning classifiers in terms of performance. The findings shows that DNN has a good precision for different classifiers detection on datasets with accuracy rate for multi-class categorization. Employing Apache Flink to simplify the process and handling the streaming capabilities.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129096002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009058
Shivappriya S N, Pasupathy S A, H. R, Shanmuga Priya J, Pavenashri Raj, Vikram L
In the recent years, considerably most of the people suffer from severe eye related diseases due to irregular check-up and high consuming time. The main of the work is to recognize to major different kind of eye related diseases such as Cotton-wool spots, Fibrosis, Fundus neoplasm, Maculopathy, Myelinated nerve fiber, Optic atrophy, Peripheral retinal degeneration and break, Possible glaucoma, Preretinal hemorrhage, Severe hypertensive retinopathy through Convolution Neural Network and detect diseases in less time. Retinal fundal images are collected from kaggle source and preprocessed by performing gray scale conversion, image enhancement, histogram equalization and standardization techniques. By comparing the existing architecture such as mobile net, Resnet50 and VGG19 with the customized new architecture and show better performance than the existing one by comparing its quantitative analysis and the result is obtained by predicting accurate diseases with less training and validation time with high accuracy.
{"title":"A Customized Deep Learning Algorithm for Prediction of Eye Diseases from Color Fundus Photography","authors":"Shivappriya S N, Pasupathy S A, H. R, Shanmuga Priya J, Pavenashri Raj, Vikram L","doi":"10.1109/STCR55312.2022.10009058","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009058","url":null,"abstract":"In the recent years, considerably most of the people suffer from severe eye related diseases due to irregular check-up and high consuming time. The main of the work is to recognize to major different kind of eye related diseases such as Cotton-wool spots, Fibrosis, Fundus neoplasm, Maculopathy, Myelinated nerve fiber, Optic atrophy, Peripheral retinal degeneration and break, Possible glaucoma, Preretinal hemorrhage, Severe hypertensive retinopathy through Convolution Neural Network and detect diseases in less time. Retinal fundal images are collected from kaggle source and preprocessed by performing gray scale conversion, image enhancement, histogram equalization and standardization techniques. By comparing the existing architecture such as mobile net, Resnet50 and VGG19 with the customized new architecture and show better performance than the existing one by comparing its quantitative analysis and the result is obtained by predicting accurate diseases with less training and validation time with high accuracy.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130606595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009607
M. Ramkumar, C. Ganesh Babu, A. R. Abdul Wahhab, K. Abinaya, B. Abinesh Balaji, N. Aniruth Chakravarthy
The diagnosis and analysis of the lung diseases has been an appealing task for the clinical experts in the dawning and in the latter days. To certain extent, the analysis has to be done in an appropriate way to eliminate the risk of human lives by the prior detection of tumorous growth. Henceforth, there are various diagnosis technique available in the world and yet various stochastic expedient has been carried out. In the validating conviction, the enactment of the neural network technique has been initiated to examine the cancerous growth in the gathered image datasets. With the help of Artificial intelligence and deep learning technique the cancerous growth can be evaluated. In accordance to knock back the performance measures the supervised learning technique is implemented with the use of the deep learning technique. Convolutional Neural Network the stratagem for the tumor detection. The substructure of this work includes following constraints such as image acquisition, image pre-processing, image enhancement, image segmentation, feature extraction, neural identification. To put it succinctly, machine learning technique gives an innovational approach to enrich the decision support in lung tumor medicaments at less cost.
{"title":"Detection and Diagnosis of Lung Cancer using Machine Learning Convolutional Neural Network Technique","authors":"M. Ramkumar, C. Ganesh Babu, A. R. Abdul Wahhab, K. Abinaya, B. Abinesh Balaji, N. Aniruth Chakravarthy","doi":"10.1109/STCR55312.2022.10009607","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009607","url":null,"abstract":"The diagnosis and analysis of the lung diseases has been an appealing task for the clinical experts in the dawning and in the latter days. To certain extent, the analysis has to be done in an appropriate way to eliminate the risk of human lives by the prior detection of tumorous growth. Henceforth, there are various diagnosis technique available in the world and yet various stochastic expedient has been carried out. In the validating conviction, the enactment of the neural network technique has been initiated to examine the cancerous growth in the gathered image datasets. With the help of Artificial intelligence and deep learning technique the cancerous growth can be evaluated. In accordance to knock back the performance measures the supervised learning technique is implemented with the use of the deep learning technique. Convolutional Neural Network the stratagem for the tumor detection. The substructure of this work includes following constraints such as image acquisition, image pre-processing, image enhancement, image segmentation, feature extraction, neural identification. To put it succinctly, machine learning technique gives an innovational approach to enrich the decision support in lung tumor medicaments at less cost.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"26-27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123647321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009350
T. Thiyagu, S. Krishnaveni
Cyber-attacks on the Internet of Things have improved significantly more in previous years, with the expansion of intelligent internet-connected systems and functions. The Internet of Things aims to create a better environment for people to automatically understand their needs and act accordingly. This project aims to identify a wormhole attack against Routing Protocol for Low Power and Lossy Networks (RPL) of the Internet of Things, which is the technology behind most of the devices and sensors in the Internet of Things. This study proposes a deep learning-based advanced gated recurrent unit (AGRU) network model. The proposed model is compared to Logistic regression and One Support Vector Machine using different weight states and node power consumption. As a result, the model’s predictions and promises regarding IoT security and source effectiveness seem to be accurate. In terms of source efficiency and IoT security, it is evident that the results confirmed the commitment and expectations of the study. According to previous literature studies, RPL flood attacks are associated with a reduced error rate in detecting attacks.
{"title":"RPL Attacks Detection and Prevention in IOT Networks with Advanced GRU Deep Learning Algorithm","authors":"T. Thiyagu, S. Krishnaveni","doi":"10.1109/STCR55312.2022.10009350","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009350","url":null,"abstract":"Cyber-attacks on the Internet of Things have improved significantly more in previous years, with the expansion of intelligent internet-connected systems and functions. The Internet of Things aims to create a better environment for people to automatically understand their needs and act accordingly. This project aims to identify a wormhole attack against Routing Protocol for Low Power and Lossy Networks (RPL) of the Internet of Things, which is the technology behind most of the devices and sensors in the Internet of Things. This study proposes a deep learning-based advanced gated recurrent unit (AGRU) network model. The proposed model is compared to Logistic regression and One Support Vector Machine using different weight states and node power consumption. As a result, the model’s predictions and promises regarding IoT security and source effectiveness seem to be accurate. In terms of source efficiency and IoT security, it is evident that the results confirmed the commitment and expectations of the study. According to previous literature studies, RPL flood attacks are associated with a reduced error rate in detecting attacks.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121182802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009581
Insha Syed, Mir Nazish, Ishfaq Sultan, M. T. Banday
Lightweight cryptography is gaining popularity for securing private and sensitive data collected by smart IoT devices. It provides security solutions tailored for constrained devices with the low area, low power and low latency requirements. The PRESENT is one of the most popular block cyphers that are efficient in hardware and offer an optimum level of security. However, the PRESENT cypher does not provide much security against the linear cryptanalytic attack. These security concerns have been addressed through the design of the GIFT block cypher that makes an appropriate choice and efficient use of lighter s-box and bit-permutations, thereby making the overall design more secure and hardware efficient than the PRESENT block cypher. However, the realisation of the linear layer by the bit-permutation method makes the GIFT cypher inefficient in software. This paper describes the software-efficient lookup table, bit-slicing and fix-slicing implementation techniques for the GIFT block cypher. These techniques have been simulated in KEIL MDK IDE and implemented on the ARM Cortex-M3-based LPC1768 hardware platform. Performance comparison of these techniques has been carried out using ULINKpro and ULINKplus debug adapters in terms of various metrics such as power, energy, execution time and memory code size.
{"title":"Implementation Techniques for GIFT Block Cypher: A Real-Time Performance Comparison","authors":"Insha Syed, Mir Nazish, Ishfaq Sultan, M. T. Banday","doi":"10.1109/STCR55312.2022.10009581","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009581","url":null,"abstract":"Lightweight cryptography is gaining popularity for securing private and sensitive data collected by smart IoT devices. It provides security solutions tailored for constrained devices with the low area, low power and low latency requirements. The PRESENT is one of the most popular block cyphers that are efficient in hardware and offer an optimum level of security. However, the PRESENT cypher does not provide much security against the linear cryptanalytic attack. These security concerns have been addressed through the design of the GIFT block cypher that makes an appropriate choice and efficient use of lighter s-box and bit-permutations, thereby making the overall design more secure and hardware efficient than the PRESENT block cypher. However, the realisation of the linear layer by the bit-permutation method makes the GIFT cypher inefficient in software. This paper describes the software-efficient lookup table, bit-slicing and fix-slicing implementation techniques for the GIFT block cypher. These techniques have been simulated in KEIL MDK IDE and implemented on the ARM Cortex-M3-based LPC1768 hardware platform. Performance comparison of these techniques has been carried out using ULINKpro and ULINKplus debug adapters in terms of various metrics such as power, energy, execution time and memory code size.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114369685","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：