S. Baskaran, L. Ali, A. Anitharani, E. Rani, N. Nandhagopal
Pupil detection techniques are an essential diagnostic technique in medical applications. Pupil detection becomes more complex because of the dynamic movement of the pupil region and it’s size. Eye-tracking is either the method of assessing the point of focus (where one sees) or the orientation of an eye relative to the head. An instrument used to control eye positions and eye activity is the eye tracker. As an input tool for human-computer interaction, eye trackers are used in research on the visual system, in psychology, psycholinguistics, marketing, and product design. Eye detection is one in all the applications in the image process. This is very important in human identification and it will improve today’s identification technique that solely involves the eye detection to spot individuals. This technology is still new, only a few domains are applying this technology as their medical system. The proposed work is developing an eye pupil detection method in real-time, stable, using an intensity labeling algorithm. The proposed hardware architecture is designed using the median filter, segmentation using the threshold process, and morphology to detect pupil shape. Finally, an intensity Labeling algorithm is done to locate an exact eye pupil region. A Real-time FPGA implementation is done by Altera Quartus II software with cyclone IV FPGA.
瞳孔检测技术是一项重要的医学诊断技术。由于瞳孔区域的动态运动和瞳孔的大小，瞳孔检测变得更加复杂。眼球追踪是一种评估焦点(一个人看到的地方)或眼睛相对于头部的方向的方法。眼球追踪仪是一种用来控制眼球位置和眼球活动的仪器。眼动仪作为人机交互的输入工具，广泛应用于视觉系统、心理学、心理语言学、市场营销和产品设计等领域的研究。眼睛检测是图像处理中的一种应用。这在人类识别中是非常重要的，它将改进目前仅通过眼睛检测来识别个体的识别技术。该技术尚属新兴技术，目前只有少数领域将其应用于医疗系统。提出的工作是开发一种实时，稳定的眼睛瞳孔检测方法，使用强度标记算法。硬件结构采用中值滤波、阈值分割和形态学检测瞳孔形状。最后，利用强度标记算法对瞳孔区域进行精确定位。采用Altera Quartus II软件和cyclone IV FPGA实现实时FPGA。
{"title":"Pupil Detection System Using Intensity Labeling Algorithm in Field Programmable Gate Array","authors":"S. Baskaran, L. Ali, A. Anitharani, E. Rani, N. Nandhagopal","doi":"10.1166/JCTN.2020.9429","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9429","url":null,"abstract":"Pupil detection techniques are an essential diagnostic technique in medical applications. Pupil detection becomes more complex because of the dynamic movement of the pupil region and it’s size. Eye-tracking is either the method of assessing the point of focus (where one sees)\u0000 or the orientation of an eye relative to the head. An instrument used to control eye positions and eye activity is the eye tracker. As an input tool for human-computer interaction, eye trackers are used in research on the visual system, in psychology, psycholinguistics, marketing, and product\u0000 design. Eye detection is one in all the applications in the image process. This is very important in human identification and it will improve today’s identification technique that solely involves the eye detection to spot individuals. This technology is still new, only a few domains\u0000 are applying this technology as their medical system. The proposed work is developing an eye pupil detection method in real-time, stable, using an intensity labeling algorithm. The proposed hardware architecture is designed using the median filter, segmentation using the threshold process,\u0000 and morphology to detect pupil shape. Finally, an intensity Labeling algorithm is done to locate an exact eye pupil region. A Real-time FPGA implementation is done by Altera Quartus II software with cyclone IV FPGA.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5364-5367"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41900363","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}
With increase in growth of data and digital threat, demand of securing the data communicated over the internet is an essential play in the digital world. In the vision of digitalizing services with the next generation of security to the sensitive data transmitted over the internet by hiding the existence of the data using next generation cryptography by fusing cryptography techniques is one the major technique adopted. With this the aim in traditional Least Significant Bit (LSB) is one of the widely used technique. Where the secret message or image are placed in the cover image in the least significant bits of RGB Channels resulting in a stego image. But the drawback is, on suspecting the differences in the pixels of original and stegoimage in the secret data embedded can be guessed and extracted by attacker. The Proposed visual crypto-mask steganography method overcomes this drawback and support good payload capacity with multi modal approach of embedding biometrics, resulting in ∞ PSNR. The authenticated person face and fingerprint information is transmitted in a cover image and mask image (magic sheet) using proposed steganography and is combined with Random Visual Crypto Technique. Which results in enhanced and advance visual crypto steganography secured model in communicating sensitive (biometric features) information over the internet. Where the complete information cannot be extracted using only cover image. Mask image (magic sheet) is used along with cover image that reveals the secret data in the receiving end.
{"title":"Novel Multifold Secured System by Combining Multimodal Mask Steganography and Naive Based Random Visual Cryptography System for Digital Communication","authors":"S. Jahnavi, C. Nandini","doi":"10.1166/JCTN.2020.9420","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9420","url":null,"abstract":"With increase in growth of data and digital threat, demand of securing the data communicated over the internet is an essential play in the digital world. In the vision of digitalizing services with the next generation of security to the sensitive data transmitted over the internet by\u0000 hiding the existence of the data using next generation cryptography by fusing cryptography techniques is one the major technique adopted. With this the aim in traditional Least Significant Bit (LSB) is one of the widely used technique. Where the secret message or image are placed in the cover\u0000 image in the least significant bits of RGB Channels resulting in a stego image. But the drawback is, on suspecting the differences in the pixels of original and stegoimage in the secret data embedded can be guessed and extracted by attacker. The Proposed visual crypto-mask steganography method\u0000 overcomes this drawback and support good payload capacity with multi modal approach of embedding biometrics, resulting in ∞ PSNR. The authenticated person face and fingerprint information is transmitted in a cover image and mask image (magic sheet) using proposed steganography and is\u0000 combined with Random Visual Crypto Technique. Which results in enhanced and advance visual crypto steganography secured model in communicating sensitive (biometric features) information over the internet. Where the complete information cannot be extracted using only cover image. Mask image\u0000 (magic sheet) is used along with cover image that reveals the secret data in the receiving end.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5279-5295"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44079784","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 recent times, COVID-19 has appeared as a major threat to healthcare professionals, governments, and research communities over the world from its diagnosis to medication. Several research works have been carried out for obtaining the possible solutions for controlling the epidemic proficiently. An effective diagnosis of COVID-19 has been carried out using computed tomography (CT) scans and X-rays to examine the lung image. But it necessitates diverse radiologists and time to examine every report, which is a tedious task. Therefore, this paper presents an automated deep learning (DL) based COVID-19 detection and classification model. The presented model performs preprocessing, feature extraction and classification. In the earlier stage, median filtering (MF) technique is applied to preprocess the input image. Next, convolutional neural network (CNN) based VGGNet-19 model is applied as a feature extractor. At last, artificial neural network (ANN) is employed as a classification model to identify and classify the existence of COVID-19. An extensive set of simulation analysis takes place to ensure the superior performance of the applied model. The outcome of the experiments showcased the betterment interms of different measures.
{"title":"Automated Detection and Classification of COVID-19 from Chest X-ray Images Using Deep Learning","authors":"K. Shankar, E. Perumal","doi":"10.1166/JCTN.2020.9439","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9439","url":null,"abstract":"In recent times, COVID-19 has appeared as a major threat to healthcare professionals, governments, and research communities over the world from its diagnosis to medication. Several research works have been carried out for obtaining the possible solutions for controlling the epidemic\u0000 proficiently. An effective diagnosis of COVID-19 has been carried out using computed tomography (CT) scans and X-rays to examine the lung image. But it necessitates diverse radiologists and time to examine every report, which is a tedious task. Therefore, this paper presents an automated deep\u0000 learning (DL) based COVID-19 detection and classification model. The presented model performs preprocessing, feature extraction and classification. In the earlier stage, median filtering (MF) technique is applied to preprocess the input image. Next, convolutional neural network (CNN) based\u0000 VGGNet-19 model is applied as a feature extractor. At last, artificial neural network (ANN) is employed as a classification model to identify and classify the existence of COVID-19. An extensive set of simulation analysis takes place to ensure the superior performance of the applied model.\u0000 The outcome of the experiments showcased the betterment interms of different measures.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5457-5463"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46083860","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 recent days, content based image retrieval (CBIR) becomes a hot research area, which aims to determine the relevant images to the query image (QI) from the available large sized database. This paper presents an optimal hybrid feature extraction with similarity measure (OHFE-SM) for CBIR. Initially, histogram equalization of images takes place as a preprocessing step. Then, texture, shape and color features are extracted. The texture features include Gray Level Co-Occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) is extracted, where the optimal number of features will be chosen by whale optimization algorithm (WOA). Afterwards, the shape feature extraction takes place by Crest lines and color feature extraction process will be carried out using Quaternion moments. Finally, Euclidean distance will be applied as a similarity measure to determine the distance among the feature vectors exist in the database and QI. The images with higher similarity index will be considered as relevant images and is retrieved from the database. A detailed experimental validation takes place against Corel10K dataset. The simulation results showed that the proposed OHFE-SM model has outperformed the existing methods with the higher average precision of 0.915 and recall of 0.780.
{"title":"An Ensemble of Feature Extraction with Whale Optimization Algorithm for Content Based Image Retrieval System","authors":"P. Sasikumar, K. Venkatachalapathy","doi":"10.1166/JCTN.2020.9432","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9432","url":null,"abstract":"In recent days, content based image retrieval (CBIR) becomes a hot research area, which aims to determine the relevant images to the query image (QI) from the available large sized database. This paper presents an optimal hybrid feature extraction with similarity measure (OHFE-SM) for\u0000 CBIR. Initially, histogram equalization of images takes place as a preprocessing step. Then, texture, shape and color features are extracted. The texture features include Gray Level Co-Occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) is extracted, where the optimal number\u0000 of features will be chosen by whale optimization algorithm (WOA). Afterwards, the shape feature extraction takes place by Crest lines and color feature extraction process will be carried out using Quaternion moments. Finally, Euclidean distance will be applied as a similarity measure to determine\u0000 the distance among the feature vectors exist in the database and QI. The images with higher similarity index will be considered as relevant images and is retrieved from the database. A detailed experimental validation takes place against Corel10K dataset. The simulation results showed that\u0000 the proposed OHFE-SM model has outperformed the existing methods with the higher average precision of 0.915 and recall of 0.780.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5386-5398"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45769328","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}
Now is the era of online data and transaction, all this happens on an unsecured channel. With this huge data transfer, comes the need of protecting this data. Thus, to achieve security during transmission, several symmetric key encryption algorithms have been proposed. Inspired from researchers, we propose an asymmetric key image security algorithm based on chaotic tent map integrated with Optimized Salp Swarm Algorithm (SSA) for key generation and encryption for gray scale images. Diffusion and confusion are carried out in each round to mix plain text and key to it more secure. Experimental analysis shown by SSA are encouraging and is secure enough to resist brute force, differential cryptoanalysis and key sensitivity analysis attack and is suitable for practical application.
{"title":"Public Key Cryptosystem Based on Optimized Chaos-Based Image Encryption","authors":"Supriya Khaitan, Shrddha Sagar, Rashi Agarwal","doi":"10.1166/JCTN.2020.9411","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9411","url":null,"abstract":"Now is the era of online data and transaction, all this happens on an unsecured channel. With this huge data transfer, comes the need of protecting this data. Thus, to achieve security during transmission, several symmetric key encryption algorithms have been proposed. Inspired from\u0000 researchers, we propose an asymmetric key image security algorithm based on chaotic tent map integrated with Optimized Salp Swarm Algorithm (SSA) for key generation and encryption for gray scale images. Diffusion and confusion are carried out in each round to mix plain text and key to it more\u0000 secure. Experimental analysis shown by SSA are encouraging and is secure enough to resist brute force, differential cryptoanalysis and key sensitivity analysis attack and is suitable for practical application.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5217-5223"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46245103","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}
Content-Based Image Retrieval (CBIR) is another yet broadly recognized method for distinguishing images from monstrous and unannotated image databases. With the improvement of network and mixed media headways ending up being increasingly famous, customers are not content with the regular information retrieval progresses. So nowadays, Content-Based Image Retrieval (CBIR) is the perfect and fast recovery source. Lately, various strategies have been created to improve CBIR execution. Data clustering is an overlooked method of hiding formatting extraction from large data blocks. With large data sets, there is a possibility of high dimensionality Models are a challenging domain with both massive numerical accuracy and efficiency for multidimensional data sets. The calibration and rich information dataset contain the problem of recovery and handling of medical images. Every day, more medical images were converted to digital format. Therefore, this work has applied these data to manage and file a novel approach, the “Clustering (MHC) Approach Using Content-Based Medical Image Retrieval Hybrid.” This work is implemented as four levels. With each level, the effectiveness of job retention is improved. Compared to some of the existing works that are being done in the analysis of this work’s literature, the results of this work are compared. The classification and learning features are used to retrieve medical images in a database. The proposed recovery system performs better than the traditional approach; with precision, recall, F-measure, and accuracy of proposed method are 97.29%, 95.023%, 4.36%, and 98.55% respectively. The recommended approach is most appropriate for recuperating clinical images for various parts of the body.
{"title":"Content Based Medical Image Retrieval Using Multilevel Hybrid Clustering Segmentation with Feed Forward Neural Network","authors":"R. Inbaraj, G. Ravi","doi":"10.1166/JCTN.2020.9452","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9452","url":null,"abstract":"Content-Based Image Retrieval (CBIR) is another yet broadly recognized method for distinguishing images from monstrous and unannotated image databases. With the improvement of network and mixed media headways ending up being increasingly famous, customers are not content with the regular\u0000 information retrieval progresses. So nowadays, Content-Based Image Retrieval (CBIR) is the perfect and fast recovery source. Lately, various strategies have been created to improve CBIR execution. Data clustering is an overlooked method of hiding formatting extraction from large data blocks.\u0000 With large data sets, there is a possibility of high dimensionality Models are a challenging domain with both massive numerical accuracy and efficiency for multidimensional data sets. The calibration and rich information dataset contain the problem of recovery and handling of medical images.\u0000 Every day, more medical images were converted to digital format. Therefore, this work has applied these data to manage and file a novel approach, the “Clustering (MHC) Approach Using Content-Based Medical Image Retrieval Hybrid.” This work is implemented as four levels. With each\u0000 level, the effectiveness of job retention is improved. Compared to some of the existing works that are being done in the analysis of this work’s literature, the results of this work are compared. The classification and learning features are used to retrieve medical images in a database.\u0000 The proposed recovery system performs better than the traditional approach; with precision, recall, F-measure, and accuracy of proposed method are 97.29%, 95.023%, 4.36%, and 98.55% respectively. The recommended approach is most appropriate for recuperating clinical images for various\u0000 parts of the body.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5550-5562"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47429339","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. Sharmila, C. Rekha, D. Devi, K. Revathi, K. Sornalatha
Alzheimer’s disease (AD) is a serious neurological brain disease. It terminates brain cells, causing loss of memory, mental function and the capability to continue their daily actions. AD is incurable, but early detection can greatly improve symptoms. Machine learning can greatly develop the accurate analysis of AD. In this paper, we have implemented the two different hybrid algorithms for feature extraction and classification. Hybrid feature extraction algorithm is based on Empirical mode decomposition (EMD) and Gray-Level Co-Occurrence Matrix (GLCM), which is named as EMDGLCM. For classification purpose Support vector machine (SVM) and Convolution neural network (CNN) which is named as SVM-CNN. The proposed hybrid algorithm feature extraction and classification Improves the proposed system performance the proposed system has analysis with the help of OASIS dataset. The proposed results and comparative results shows that the proposed system provides the better results.
{"title":"Hybrid Feature Extraction and Classification for Alzheimer’s Disease Detection","authors":"P. Sharmila, C. Rekha, D. Devi, K. Revathi, K. Sornalatha","doi":"10.1166/JCTN.2020.9455","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9455","url":null,"abstract":"Alzheimer’s disease (AD) is a serious neurological brain disease. It terminates brain cells, causing loss of memory, mental function and the capability to continue their daily actions. AD is incurable, but early detection can greatly improve symptoms. Machine learning can greatly\u0000 develop the accurate analysis of AD. In this paper, we have implemented the two different hybrid algorithms for feature extraction and classification. Hybrid feature extraction algorithm is based on Empirical mode decomposition (EMD) and Gray-Level Co-Occurrence Matrix (GLCM), which is named\u0000 as EMDGLCM. For classification purpose Support vector machine (SVM) and Convolution neural network (CNN) which is named as SVM-CNN. The proposed hybrid algorithm feature extraction and classification Improves the proposed system performance the proposed system has analysis with the help of\u0000 OASIS dataset. The proposed results and comparative results shows that the proposed system provides the better results.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5577-5581"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49378738","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}
Presently, rapid and precise disease identification process plays a vital role to increase agricultural productivity in a sustainable manner. Conventionally, human experts identify the existence of anomaly in plants occurred due to disease, pest, nutrient deficient, weather conditions. Since manual diagnosis process is a tedious and time consuming task, computer vision approaches have begun to automatically detect and classify the plant diseases. The general image processing tasks involved in plant disease detection are preprocessing, segmentation, feature extraction and classification. This paper performs a review of computer vision based plant disease detection and classification techniques. The existing plant disease detection approaches including segmentation and feature extraction techniques have been reviewed. Additionally, a brief survey of machine learning (ML) and deep learning (DL) models to identify plant diseases also takes place. Furthermore, a set of recently developed DL based tomato plant leaf disease detection and classification models are surveyed under diverse aspects. To further understand the reviewed methodologies, a detailed comparative study also takes place to recognize the unique characteristics of the reviewed models.
{"title":"Analysis of Plant Disease Detection and Classification Models: A Computer Vision Perspective","authors":"K. Jayaprakash, S. Balamurugan","doi":"10.1166/JCTN.2020.9435","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9435","url":null,"abstract":"Presently, rapid and precise disease identification process plays a vital role to increase agricultural productivity in a sustainable manner. Conventionally, human experts identify the existence of anomaly in plants occurred due to disease, pest, nutrient deficient, weather conditions.\u0000 Since manual diagnosis process is a tedious and time consuming task, computer vision approaches have begun to automatically detect and classify the plant diseases. The general image processing tasks involved in plant disease detection are preprocessing, segmentation, feature extraction and\u0000 classification. This paper performs a review of computer vision based plant disease detection and classification techniques. The existing plant disease detection approaches including segmentation and feature extraction techniques have been reviewed. Additionally, a brief survey of machine\u0000 learning (ML) and deep learning (DL) models to identify plant diseases also takes place. Furthermore, a set of recently developed DL based tomato plant leaf disease detection and classification models are surveyed under diverse aspects. To further understand the reviewed methodologies, a detailed\u0000 comparative study also takes place to recognize the unique characteristics of the reviewed models.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5422-5428"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43485106","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}
Rapidly improving video editing software tools have made video content manipulation feasible. Consequently malicious attackers are trying to manipulate the videos. Detecting video tampering is a major need for many applications. In this paper we propose a model called Evidence chain based on Blockchain to ensure the credibility of the video. Unlike bitcoin which is a digital currency the Proposed system documents video hash by using hash based technology and elliptic curve cryptography. Video segments are hashed and stored in chronological order as a chain of blocks which are detectable and non-altering guaranteeing the validity of the video information. This research is significant in establishing the trust between any two parties.
{"title":"Blockchain Solution for Evidence Forgery Detection","authors":"B. Kumar, K. R. Kumar","doi":"10.1166/JCTN.2020.9454","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9454","url":null,"abstract":"Rapidly improving video editing software tools have made video content manipulation feasible. Consequently malicious attackers are trying to manipulate the videos. Detecting video tampering is a major need for many applications. In this paper we propose a model called Evidence chain\u0000 based on Blockchain to ensure the credibility of the video. Unlike bitcoin which is a digital currency the Proposed system documents video hash by using hash based technology and elliptic curve cryptography. Video segments are hashed and stored in chronological order as a chain of blocks which\u0000 are detectable and non-altering guaranteeing the validity of the video information. This research is significant in establishing the trust between any two parties.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5570-5576"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43290743","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}
Serverless computing is growing rapidly due to its rapid adoption by the cloud providers and tenants in terms of its scalability, elasticity, flexibility and ease of deployment. Such increase in deployment of serverless computing makes the research to rethink on its security aspects. Since, the serverless security computing may undergo problems due to malicious users or hackers. In this paper, a secure and an efficient access control system is designed for serverless security computing for both knowledge and resource sharing using attributed based encryption. Initially, the data is encrypted using user attributes; further the data is split into cipher text. It is finally decrypted using a decryption algorithm and then the shares of the cipher text are distributed in the network and the encapsulated texts are stored in the serverless system. The performance on security analysis shows that the proposed method achieves improved data security in serverless environment than the existing methods.
{"title":"Improved Encryption Towards Data Security in Serverless Computing","authors":"A. Arulprakash, K. Sampathkumar","doi":"10.1166/JCTN.2020.9417","DOIUrl":"https://doi.org/10.1166/JCTN.2020.9417","url":null,"abstract":"Serverless computing is growing rapidly due to its rapid adoption by the cloud providers and tenants in terms of its scalability, elasticity, flexibility and ease of deployment. Such increase in deployment of serverless computing makes the research to rethink on its security aspects.\u0000 Since, the serverless security computing may undergo problems due to malicious users or hackers. In this paper, a secure and an efficient access control system is designed for serverless security computing for both knowledge and resource sharing using attributed based encryption. Initially,\u0000 the data is encrypted using user attributes; further the data is split into cipher text. It is finally decrypted using a decryption algorithm and then the shares of the cipher text are distributed in the network and the encapsulated texts are stored in the serverless system. The performance\u0000 on security analysis shows that the proposed method achieves improved data security in serverless environment than the existing methods.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":"17 1","pages":"5256-5260"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44741719","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：