For S is a dominating set of G and V-S V(G) of a center smooth graph Gis called amixed inverse center smooth set if (i) For every vεV-S, |N[v]∩V(G)| 1(mod p) and (ii) Every elementuεS is either adjacent or incident to an element of V-S. The number of vertices in a mixed inversecenter smooth set is called the mixed inverse center smooth number and it is denoted by γmcs(G).Inthis paper, we introduce the new concept of mixed inverse center smooth number and establish someresults on this new parameter. Also, we determine the bounds of γmcs- set of some graph classes.
{"title":"A Study on Mixed Inverse Center-Smooth Set of Some Graphs and its application","authors":"","doi":"10.46632/daai/3/2/32","DOIUrl":"https://doi.org/10.46632/daai/3/2/32","url":null,"abstract":"For S is a dominating set of G and V-S V(G) of a center smooth graph Gis called amixed inverse center smooth set if (i) For every vεV-S, |N[v]∩V(G)| 1(mod p) and (ii) Every elementuεS is either adjacent or incident to an element of V-S. The number of vertices in a mixed inversecenter smooth set is called the mixed inverse center smooth number and it is denoted by γmcs(G).Inthis paper, we introduce the new concept of mixed inverse center smooth number and establish someresults on this new parameter. Also, we determine the bounds of γmcs- set of some graph classes.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123871276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) has recently emerged as a cutting-edge technology for creating smart environments. The Internet of Things (IoT) connects systems, applications, data storage, and services, which may be a new entry point for cyber-attacks as they provide continuous services in the organization. At the current time, software piracy and malware attacks pose significant threats to IoT security. These threats may grab vital information, causing economic and reputational harm. The Internet of Medical Things (IoMT) is a subset of the Internet of Things in which medical equipment exchanges highly confidential with one another. These advancements allow the healthcare industry to maintain a higher level of touch and care for its patients. Security is viewed as a significant challenge in any technology's reliance on the IoT. Remote hijacking, impersonation, denial of service attacks, password guessing, and man-in-the-middle are all security concerns. Critical data associated with IoT connectivity may be revealed, altered, or even rendered inaccessible to authenticated persons in the event of such attacks. the deep recurrent neural network is used to detect malicious infections in IoT networks by displaying color images. In this paper, we propose a method for detecting cyber-attacks on IoMT systems that tends to make use of innovative deep learning. Specifically, our method incorporates a set of long short-term memory (LSTM) modules into a detector ensemble using a recurrent neural network.
{"title":"Malware detection in IOMT (MDI) using RNN-LSTM","authors":"M. Uma Maheshwari, M. Suguna","doi":"10.46632/daai/3/2/19","DOIUrl":"https://doi.org/10.46632/daai/3/2/19","url":null,"abstract":"The Internet of Things (IoT) has recently emerged as a cutting-edge technology for creating smart environments. The Internet of Things (IoT) connects systems, applications, data storage, and services, which may be a new entry point for cyber-attacks as they provide continuous services in the organization. At the current time, software piracy and malware attacks pose significant threats to IoT security. These threats may grab vital information, causing economic and reputational harm. The Internet of Medical Things (IoMT) is a subset of the Internet of Things in which medical equipment exchanges highly confidential with one another. These advancements allow the healthcare industry to maintain a higher level of touch and care for its patients. Security is viewed as a significant challenge in any technology's reliance on the IoT. Remote hijacking, impersonation, denial of service attacks, password guessing, and man-in-the-middle are all security concerns. Critical data associated with IoT connectivity may be revealed, altered, or even rendered inaccessible to authenticated persons in the event of such attacks. the deep recurrent neural network is used to detect malicious infections in IoT networks by displaying color images. In this paper, we propose a method for detecting cyber-attacks on IoMT systems that tends to make use of innovative deep learning. Specifically, our method incorporates a set of long short-term memory (LSTM) modules into a detector ensemble using a recurrent neural network.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126970254","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}
In the medical era, skin disease is considered one of the most common diseases among humans. Skin cancer is the most dangerous type, which can be curable if identified at the initial stage. The severity of skin cancer and the rapid count of affected people make it necessary to introduce an automatic detection scheme. Generally, analyzing and identifying skin disease in a short time is the most complex and challenging task. Several deep learning (DL) and machine learning (ML) are introduced to achieve this. However, the still fulfilling the skin cancer diagnosis is not accomplished completely. To achieve this, we proposed a machine learning model using an ensemble classifier with PCA to predict skin disease with maximum accuracy. The proposed Ensemble classifier is based on similar features and classifies several stages. It is executed by labeling vertebral disorder images according to these statistical features. The performance obtained by the ensemble classifier is compared with Support Vector Machine (SVM) and Resent with several evaluation metrics. The analysis shows that the accuracy attained by the proposed ensemble classifier is 97 % which is far better than the others in terms of classification and accuracy.
{"title":"Skin Disease Prediction Machine Learning Model Using Ensemble Classifier with PCA","authors":"","doi":"10.46632/daai/3/2/31","DOIUrl":"https://doi.org/10.46632/daai/3/2/31","url":null,"abstract":"In the medical era, skin disease is considered one of the most common diseases among humans. Skin cancer is the most dangerous type, which can be curable if identified at the initial stage. The severity of skin cancer and the rapid count of affected people make it necessary to introduce an automatic detection scheme. Generally, analyzing and identifying skin disease in a short time is the most complex and challenging task. Several deep learning (DL) and machine learning (ML) are introduced to achieve this. However, the still fulfilling the skin cancer diagnosis is not accomplished completely. To achieve this, we proposed a machine learning model using an ensemble classifier with PCA to predict skin disease with maximum accuracy. The proposed Ensemble classifier is based on similar features and classifies several stages. It is executed by labeling vertebral disorder images according to these statistical features. The performance obtained by the ensemble classifier is compared with Support Vector Machine (SVM) and Resent with several evaluation metrics. The analysis shows that the accuracy attained by the proposed ensemble classifier is 97 % which is far better than the others in terms of classification and accuracy.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122493974","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}
Detection of an object from a satellite image is a difficult process because the presence of objects in a satellite image is unpredictable. Different approaches have been available to detect vehicles, buildings, trees however all these objects were detected individually through machine learning and some other methods. Similarly accuracy in object detection is another major issue. In our proposed work, To analyze the object accurately, Polygon approach is implemented which includes both shape and color as input and processes it with datasets to attain maximum accurate result. Here image parameters have been extracted accurately through feature detection. After segmentation of a particular object from image CNN classification is implemented. Through this, in our proposal we are going to detect roads, trees, buildings, waterway and few other objects accurately with this single approach.
{"title":"Object Recognition in Earth Surface Satellite Images Using Digital Image Processing and Machine Learning Techniques with Big Data Technologies","authors":"Misba Khan k","doi":"10.46632/daai/3/2/27","DOIUrl":"https://doi.org/10.46632/daai/3/2/27","url":null,"abstract":"Detection of an object from a satellite image is a difficult process because the presence of objects in a satellite image is unpredictable. Different approaches have been available to detect vehicles, buildings, trees however all these objects were detected individually through machine learning and some other methods. Similarly accuracy in object detection is another major issue. In our proposed work, To analyze the object accurately, Polygon approach is implemented which includes both shape and color as input and processes it with datasets to attain maximum accurate result. Here image parameters have been extracted accurately through feature detection. After segmentation of a particular object from image CNN classification is implemented. Through this, in our proposal we are going to detect roads, trees, buildings, waterway and few other objects accurately with this single approach.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121161345","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}
In the 1980s and 1990s, a field known as scientific computing or computational science began to emerge as a result of the increasing significance of using computers to carry out numerical operations in order to solve mathematical models of the world. This paper examines numerical analysis’s application from a computer science view point; see[3][4][5].In this paper, Iterative methods like Gauss Jacobi and Gauss Serial were used to solve the system of simultaneous equation by using Python Programming.
{"title":"Certain Iterative Methods to Solve System of Equations by Python Programming","authors":"","doi":"10.46632/daai/3/2/37","DOIUrl":"https://doi.org/10.46632/daai/3/2/37","url":null,"abstract":"In the 1980s and 1990s, a field known as scientific computing or computational science began to emerge as a result of the increasing significance of using computers to carry out numerical operations in order to solve mathematical models of the world. This paper examines numerical analysis’s application from a computer science view point; see[3][4][5].In this paper, Iterative methods like Gauss Jacobi and Gauss Serial were used to solve the system of simultaneous equation by using Python Programming.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127883688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The first distributed recordkeeping system with a built-in trust structure is the block chain. It creates a dependable architecture for decentralized control through information redundancy across multiple nodes. Based on this, this study suggests a minimal block chain-based IoT information exchange security framework. The framework uses a double-chain approach that combines the data block chain and the transaction block chain. Distributed storage and tamper-proof data are implemented in the data block chain, and the consensus process is improved using the improved practical Byzantine fault-tolerant (PBFT) mechanism. Data registration efficiency, resource and data transfers, and privacy protection are all enhanced by better partial blind signature-based algorithms in the transaction block chain. This article focuses on how well the consensus algorithms employed in a block chain system for the Internet of Things perform (IoT). Such systems' time requirements to accomplish. Consensus ought to be minimal. The three most popular consensus algorithms—modified proof of work, realistic byzantine fault tolerance, and binary consensus—are assessed under various conditions, including mote type, number of participating nodes, and radio propagation model. To enable an IoT node to switch between different consensus algorithms, a comprehensive solution is put forward. The Contiki IoT operating system simulations display strong performance (time to achieve consensus less than seconds)
{"title":"Block Chain for IOT Security Using Consensus Algorithms","authors":"P. Kalpana, I. Anusha Prem","doi":"10.46632/daai/3/2/16","DOIUrl":"https://doi.org/10.46632/daai/3/2/16","url":null,"abstract":"The first distributed recordkeeping system with a built-in trust structure is the block chain. It creates a dependable architecture for decentralized control through information redundancy across multiple nodes. Based on this, this study suggests a minimal block chain-based IoT information exchange security framework. The framework uses a double-chain approach that combines the data block chain and the transaction block chain. Distributed storage and tamper-proof data are implemented in the data block chain, and the consensus process is improved using the improved practical Byzantine fault-tolerant (PBFT) mechanism. Data registration efficiency, resource and data transfers, and privacy protection are all enhanced by better partial blind signature-based algorithms in the transaction block chain. This article focuses on how well the consensus algorithms employed in a block chain system for the Internet of Things perform (IoT). Such systems' time requirements to accomplish. Consensus ought to be minimal. The three most popular consensus algorithms—modified proof of work, realistic byzantine fault tolerance, and binary consensus—are assessed under various conditions, including mote type, number of participating nodes, and radio propagation model. To enable an IoT node to switch between different consensus algorithms, a comprehensive solution is put forward. The Contiki IoT operating system simulations display strong performance (time to achieve consensus less than seconds)","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129371398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The unemployment rate is a key indicator of economic performance and financial market risk. The main causes of unemployment in India are Large population, lack of professional qualifications, or poorly educated workforce. Labor-intensive sectors have suffered from a slowdown in private investment, especially after the banknote withdrawal. The Covid surge has made unemployment one of the biggest problems in India. The purpose of this project is to predict the future unemployment rate in India using the FB Prophet model. This model is used to predict the future values and developed by Facebook. There are many predictive model in unemployment using LSTM and ARIMA model but the values are not much precise, so we proposed the FB Prophet model for predicting the precise value. We can get a precise with the help of FB Prophet Model. The values are predicted using the FB prophet model and the predicted values are displayed in the form of graph.
{"title":"Prediction of Unemployment In India Using Fb Prophet","authors":"","doi":"10.46632/daai/3/1/5","DOIUrl":"https://doi.org/10.46632/daai/3/1/5","url":null,"abstract":"The unemployment rate is a key indicator of economic performance and financial market risk. The main causes of unemployment in India are Large population, lack of professional qualifications, or poorly educated workforce. Labor-intensive sectors have suffered from a slowdown in private investment, especially after the banknote withdrawal. The Covid surge has made unemployment one of the biggest problems in India. The purpose of this project is to predict the future unemployment rate in India using the FB Prophet model. This model is used to predict the future values and developed by Facebook. There are many predictive model in unemployment using LSTM and ARIMA model but the values are not much precise, so we proposed the FB Prophet model for predicting the precise value. We can get a precise with the help of FB Prophet Model. The values are predicted using the FB prophet model and the predicted values are displayed in the form of graph.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115405293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The goal of this study of group behavior is to comprehend how people act in a social networking setting. Social media platforms like Facebook, Twitter, Flickr, and YouTube produce vast amounts of data. Opportunities and difficulties for large-scale research on group behavior. In this research, our goal is to develop the ability to forecast group behavior on social media. How can we, in particular, infer the behavior of unobserved individuals in the same network given information about some individuals?
{"title":"Public Web Chat Application Monitering System","authors":"","doi":"10.46632/daai/3/1/1","DOIUrl":"https://doi.org/10.46632/daai/3/1/1","url":null,"abstract":"The goal of this study of group behavior is to comprehend how people act in a social networking setting. Social media platforms like Facebook, Twitter, Flickr, and YouTube produce vast amounts of data. Opportunities and difficulties for large-scale research on group behavior. In this research, our goal is to develop the ability to forecast group behavior on social media. How can we, in particular, infer the behavior of unobserved individuals in the same network given information about some individuals?","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125263998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Technology is transforming human life into a smart world due to its rapid expansion. To make people's lives easier, smart sensors connected to physical items give data. We show a case study of a smart water dispenser that uses weight sensors, temperature sensors, and Arduino to track how much water customers and water bottle suppliers use on a daily basis. When the water in the dispenser is ready to run out, the smart water dispenser weighs the water that is still within and sends out a warning. It takes the temperature and sends the user notifications regarding water use. Here, we propose an Arduino and Relay-based completely automated RFID-based water dispenser system. Using solenoid tap and sensors, the device may fully automate the water distribution process. In order to prevent water deterioration if no glass is placed at the counter panel, the system also detects the presence of glass there. Infrared (IR) sensors are used by the system to identify glass, after which the sensors provide a signal to the microcontroller. Now that the sensors have provided information, the microcontroller is processing it to see if glass is present. The system features an RFID Reader that may be used to read specific tags and provide information about valid tags to the microcontroller. When a valid tag is found, the system now sends a signal to the controller, which then determines whether glass is there before starting the motor to pour water into the glass while the glass is still there. If glass is removed while the process is running, the mechanism shuts off the water flow until glass is found. So, in this article, we propose a smart water dispenser system with a water-saving feature.
{"title":"Voice Control Hot-Cold Water Dispenser System Using Arduino","authors":"","doi":"10.46632/daai/3/1/7","DOIUrl":"https://doi.org/10.46632/daai/3/1/7","url":null,"abstract":"The Technology is transforming human life into a smart world due to its rapid expansion. To make people's lives easier, smart sensors connected to physical items give data. We show a case study of a smart water dispenser that uses weight sensors, temperature sensors, and Arduino to track how much water customers and water bottle suppliers use on a daily basis. When the water in the dispenser is ready to run out, the smart water dispenser weighs the water that is still within and sends out a warning. It takes the temperature and sends the user notifications regarding water use. Here, we propose an Arduino and Relay-based completely automated RFID-based water dispenser system. Using solenoid tap and sensors, the device may fully automate the water distribution process. In order to prevent water deterioration if no glass is placed at the counter panel, the system also detects the presence of glass there. Infrared (IR) sensors are used by the system to identify glass, after which the sensors provide a signal to the microcontroller. Now that the sensors have provided information, the microcontroller is processing it to see if glass is present. The system features an RFID Reader that may be used to read specific tags and provide information about valid tags to the microcontroller. When a valid tag is found, the system now sends a signal to the controller, which then determines whether glass is there before starting the motor to pour water into the glass while the glass is still there. If glass is removed while the process is running, the mechanism shuts off the water flow until glass is found. So, in this article, we propose a smart water dispenser system with a water-saving feature.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125459883","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}
Systematic and well grounded data transmission over wireless networks has been substance of uninterrupted research over the last few years. The paramount is scrutinizing the amount of security provisioning owing to the security challenges during transmission over wireless network. In fact, it is moderate to eavesdrop and alter data packets. Accessing the personal computer and public network possess the potentiality to apprehend the network traffic possibly compromising the privacy. Therefore for wireless applications, it is essential to ensure data integrity during data transmission. To efficiently address the above issues, a Deep Neural Certificate less Hessian Curve Heap Sign cryption (DNC-HCHS) method for secured data transmission in wireless network is proposed. Compared with the conventional, Certificate less Sign cryption DNC-HCHS method improves the data confidentiality and data integrity by generating smaller keys employing the Hessian Curve Heap function. Additionally with the assistance of the access point or the aggregator, the sensitivity of heaped sign crypted cipher text can improve the security of data transmission and reduce the message delivery time. Aimed at reducing the delay in data transmission, application of Certificate less Hessian Curve Heap Sign cryption in Deep Learning (i.e., Deep Neural Network) performs the overall process in a swift manner and performs a much better encryption. Simulation is performed to validate the viability and efficiency of the proposed method. The results show that the data confidentiality and data integrity rate are strongly improved, while the delay is minimized.
在过去几年中，通过无线网络进行系统的、接地良好的数据传输一直是不间断研究的内容。最重要的是仔细检查由于无线网络传输过程中的安全挑战而提供的安全配置数量。实际上，窃听和篡改数据包是适度的。访问个人计算机和公共网络具有捕获可能危及隐私的网络流量的潜力。因此，对于无线应用来说，确保数据传输过程中的数据完整性至关重要。为了有效地解决上述问题，提出了一种无深度神经证书的Hessian曲线堆符号加密(DNC-HCHS)无线网络安全数据传输方法。与传统的无证书签名加密DNC-HCHS方法相比，DNC-HCHS方法利用Hessian曲线堆函数生成更小的密钥，提高了数据的保密性和数据完整性。此外，在接入点或聚合器的辅助下，堆签名加密密文的敏感性可以提高数据传输的安全性，缩短消息传递时间。为了减少数据传输的延迟，在深度学习(即深度神经网络)中应用Certificate - less Hessian Curve Heap Sign加密，可以快速完成整个过程，并且加密效果更好。通过仿真验证了该方法的可行性和有效性。结果表明，该方法在最大限度地降低时延的同时，数据保密性和数据完整性得到了极大的提高。
{"title":"Deep Neural Certificate less Hessian Heap Sign cryption for Secure Data Transmission in Wireless Network","authors":"N. Shoba, V. Sathya","doi":"10.46632/daai/3/2/23","DOIUrl":"https://doi.org/10.46632/daai/3/2/23","url":null,"abstract":"Systematic and well grounded data transmission over wireless networks has been substance of uninterrupted research over the last few years. The paramount is scrutinizing the amount of security provisioning owing to the security challenges during transmission over wireless network. In fact, it is moderate to eavesdrop and alter data packets. Accessing the personal computer and public network possess the potentiality to apprehend the network traffic possibly compromising the privacy. Therefore for wireless applications, it is essential to ensure data integrity during data transmission. To efficiently address the above issues, a Deep Neural Certificate less Hessian Curve Heap Sign cryption (DNC-HCHS) method for secured data transmission in wireless network is proposed. Compared with the conventional, Certificate less Sign cryption DNC-HCHS method improves the data confidentiality and data integrity by generating smaller keys employing the Hessian Curve Heap function. Additionally with the assistance of the access point or the aggregator, the sensitivity of heaped sign crypted cipher text can improve the security of data transmission and reduce the message delivery time. Aimed at reducing the delay in data transmission, application of Certificate less Hessian Curve Heap Sign cryption in Deep Learning (i.e., Deep Neural Network) performs the overall process in a swift manner and performs a much better encryption. Simulation is performed to validate the viability and efficiency of the proposed method. The results show that the data confidentiality and data integrity rate are strongly improved, while the delay is minimized.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126923587","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：