: Bioinformaticians face an issue in analyzing and studying protein similarity as the number of proteins grows. Protein sequence analysis helps in the prediction of protein functions. It is critical for the analysis process to be able to appropriately categorize proteins based on their sequences. The extraction of features from protein sequences is done using a variety of methods. The goal of this study is to investigate the different variations of data on the classification performance of a deep learning model employing 3D data. First, few research questions were formulated regarding the impact of the following criteria: dataset size, IMF importance, feature size, and preprocessing on the proposed deep learning classification process. Second, comprehensive experiments were conducted to answer the research questions. Six feature extraction methods were utilized to create 3D features with two sizes (7x7x7 and 9x9x9), which were then fed into a convolutional neural network. Three datasets different in their sorts, sizes, and balance state were used. Accuracy, precision, recall and F1-score are the standard assessment metrics used. Experimental results draw significant conclusions. First, the 7x7x7 feature matrix has a positive correlation between its dimensions, which improved the results. Second, using the sum of the first three IMF components had better impact than using the first IMF component. Third, the classification process did not benefit from the normalization of features for small datasets unlike the large dataset. Finally, the dataset size had a significant impact on training the CNN model, with a training accuracy reaching 84.03%.
{"title":"UNCOVERING THE EFFECTS OF DATA VARIATION ON PROTEIN SEQUENCE CLASSIFICATION USING DEEP LEARNING","authors":"F. Mostafa, Y. Afify, R. Ismail, N. Badr","doi":"10.21608/ijicis.2022.123177.1168","DOIUrl":"https://doi.org/10.21608/ijicis.2022.123177.1168","url":null,"abstract":": Bioinformaticians face an issue in analyzing and studying protein similarity as the number of proteins grows. Protein sequence analysis helps in the prediction of protein functions. It is critical for the analysis process to be able to appropriately categorize proteins based on their sequences. The extraction of features from protein sequences is done using a variety of methods. The goal of this study is to investigate the different variations of data on the classification performance of a deep learning model employing 3D data. First, few research questions were formulated regarding the impact of the following criteria: dataset size, IMF importance, feature size, and preprocessing on the proposed deep learning classification process. Second, comprehensive experiments were conducted to answer the research questions. Six feature extraction methods were utilized to create 3D features with two sizes (7x7x7 and 9x9x9), which were then fed into a convolutional neural network. Three datasets different in their sorts, sizes, and balance state were used. Accuracy, precision, recall and F1-score are the standard assessment metrics used. Experimental results draw significant conclusions. First, the 7x7x7 feature matrix has a positive correlation between its dimensions, which improved the results. Second, using the sum of the first three IMF components had better impact than using the first IMF component. Third, the classification process did not benefit from the normalization of features for small datasets unlike the large dataset. Finally, the dataset size had a significant impact on training the CNN model, with a training accuracy reaching 84.03%.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126144887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient Hybrid approach for diagnosis High dimensional data for Alzheimer's diseases Using Machine Learning algorithms","authors":"Nour ElZawawi, H. Saber, M. Hashem, Tarek G Gharib","doi":"10.21608/ijicis.2022.116420.1153","DOIUrl":"https://doi.org/10.21608/ijicis.2022.116420.1153","url":null,"abstract":"","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133694994","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 evolution of heterogeneous data residing in various data sources (e
:驻留在不同数据源中的异构数据的演变
{"title":"ONTOLOGY-BASED DATA ACCESS TO HETEROGENEOUS DATA SOURCES: STATE OF THE ART APPROACHES AND APPLICATIONS","authors":"Naglaa Fathy, Walaa K. Gad, N. Badr, M. Hashem","doi":"10.21608/ijicis.2022.110450.1144","DOIUrl":"https://doi.org/10.21608/ijicis.2022.110450.1144","url":null,"abstract":": The evolution of heterogeneous data residing in various data sources (e","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125677381","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}
: Modern surveys reveal diminishing of socio-demographic segment descriptors, and evolution of dramatic increase of online services and customers. These conditions attract both researchers and decision makers to enhance market segmentation to gain customer loyalty and prevent customer attrition. This research contributes in developing a minor expert system to automate the evaluation of clustering process to enhance the Clustering as a Service (CaaS) through customer behavior segmentation case study. It comes as a part of the software development process to develop Customer Loyalty Intelligent Personalization (CLIP) system. The proposed expert system has been successfully implemented and tested over four months in two different dataset to proof the flexibility of implementation . The used data is a real customer data, it consists of 1659 customers, 146 products, and 5685 orders. The other datset consists of 668 transactions of real data in restaurant. The clustering is applied using the hierarchical clustering and it reached a good results with high efficiency. The proposed solution aims to be integrated with a plug and play product as it will be configured in different domains.
{"title":"Smart Support System for Evaluating Clustering as a Service: Behaviour Segmentation Case Study","authors":"M. Galal, Tamer Salah, M. Aref, Esam Elgohary","doi":"10.21608/ijicis.2021.69041.1074","DOIUrl":"https://doi.org/10.21608/ijicis.2021.69041.1074","url":null,"abstract":": Modern surveys reveal diminishing of socio-demographic segment descriptors, and evolution of dramatic increase of online services and customers. These conditions attract both researchers and decision makers to enhance market segmentation to gain customer loyalty and prevent customer attrition. This research contributes in developing a minor expert system to automate the evaluation of clustering process to enhance the Clustering as a Service (CaaS) through customer behavior segmentation case study. It comes as a part of the software development process to develop Customer Loyalty Intelligent Personalization (CLIP) system. The proposed expert system has been successfully implemented and tested over four months in two different dataset to proof the flexibility of implementation . The used data is a real customer data, it consists of 1659 customers, 146 products, and 5685 orders. The other datset consists of 668 transactions of real data in restaurant. The clustering is applied using the hierarchical clustering and it reached a good results with high efficiency. The proposed solution aims to be integrated with a plug and play product as it will be configured in different domains.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127622396","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}
: Heart diseases are one of the main reasons that cause human death. The early-stage detection of heart diseases can prevent irreversible heart muscle damage or heart failure. Electrocardiogram (ECG) is one of the main heart signals that can be useful in early diagnosis because of its obvious peaks and segments. This paper focuses on using a methodology depending on deep learning for the diagnosis of the electrocardiogram records into normal (N), Supraventricular arrhythmia (SV), ST-segment changes (ST), and myocardial infarction (MYC) conditions. The continuous wavelet transform (CWT) converts the ECG signals to the time-frequency domain to compute the scalogram of the ECG signals and for the conversion of ECG signal from one dimension signal to a two-dimension image. In addition to this, a pertained model using transfer learning is applied based on Resnet50. Moreover, three main classifiers are verified to estimate the accuracy of the proposed system which are based on the Softmax, Random Forest (RF), and XGBoost classifier. An experiment is applied for the diagnosis of four main kinds of ECG records. Finally, the results based on the class-oriented schema achieved an accuracy of 98.3% based on Resnet50 with the XGBoost classifier. The comparison with the related previous work presented the excellent performance of the proposed methodology as it can be applied as a clinical application.
心脏病是导致人类死亡的主要原因之一。心脏病的早期检测可以防止不可逆的心肌损伤或心力衰竭。心电图(Electrocardiogram, ECG)具有明显的波峰和波段，是早期诊断的主要心脏信号之一。本文的重点是使用一种基于深度学习的方法将心电图记录诊断为正常(N)、室上性心律失常(SV)、ST段改变(ST)和心肌梗死(MYC)。连续小波变换(CWT)将心电信号转换到时频域，计算心电信号的尺度图，并将心电信号从一维信号转换为二维图像。除此之外，基于Resnet50应用了一个使用迁移学习的相关模型。此外，验证了基于Softmax, Random Forest (RF)和XGBoost分类器的三种主要分类器来估计所提出系统的准确性。实验应用于四种主要心电记录的诊断。最后，基于面向类模式的结果在使用XGBoost分类器的Resnet50上实现了98.3%的准确率。通过与先前相关工作的比较，提出了该方法的优异性能，因为它可以作为临床应用。
{"title":"DEEP LEARNING APPROACH BASED ON TRANSFER LEARNING WITH DIFFERENT CLASSIFIERS FOR ECG DIAGNOSIS","authors":"M. Bassiouni, I. Hegazy, N. Rizk, E. El-Dahshan, A. Salem","doi":"10.21608/ijicis.2022.105574.1137","DOIUrl":"https://doi.org/10.21608/ijicis.2022.105574.1137","url":null,"abstract":": Heart diseases are one of the main reasons that cause human death. The early-stage detection of heart diseases can prevent irreversible heart muscle damage or heart failure. Electrocardiogram (ECG) is one of the main heart signals that can be useful in early diagnosis because of its obvious peaks and segments. This paper focuses on using a methodology depending on deep learning for the diagnosis of the electrocardiogram records into normal (N), Supraventricular arrhythmia (SV), ST-segment changes (ST), and myocardial infarction (MYC) conditions. The continuous wavelet transform (CWT) converts the ECG signals to the time-frequency domain to compute the scalogram of the ECG signals and for the conversion of ECG signal from one dimension signal to a two-dimension image. In addition to this, a pertained model using transfer learning is applied based on Resnet50. Moreover, three main classifiers are verified to estimate the accuracy of the proposed system which are based on the Softmax, Random Forest (RF), and XGBoost classifier. An experiment is applied for the diagnosis of four main kinds of ECG records. Finally, the results based on the class-oriented schema achieved an accuracy of 98.3% based on Resnet50 with the XGBoost classifier. The comparison with the related previous work presented the excellent performance of the proposed methodology as it can be applied as a clinical application.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133638169","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}
Image understanding and scene classification are keystone tasks in computer vision. The advancement of technology and the abundance of available datasets in the field of image classification and recognition study provide plenty of attempts for advancement. In the scene classification problem, transfer learning is commonly utilized as a branch of machine learning. Despite existing machine learning models' superior performance in image interpretation and scene classification, there are still challenges to overcome. The weights and current models aren't suitable in most circumstances. Instead of using the weights of data-dependent models, in this work, a novel machine learning model for the scene classification task is provided that converges rapidly. The proposed model has been tested on the Intel scenes dataset for a comprehensive evaluation of our model. The proposed model RepConv over-performed four existing benchmark models in a low number of epochs and training parameters, and it achieved 93.55 ± 0.11, 75.54 ± 0.14 accuracies for training and validation data respectively. Furthermore, re-categorization of the data set is performed for a new classification problem that is not previously reported in the literature (natural scenes; real scenes). The accuracy of the proposed model on the binary model was 98.08 ± 0.05 on training data and 92.70 ± 0.08 on validation data which is not reported previously in any other publication.
{"title":"RepConv: A novel architecture for image scene classification on Intel scenes dataset","authors":"Mohamed Soudy, Y. Afify, N. Badr","doi":"10.21608/ijicis.2022.118834.1163","DOIUrl":"https://doi.org/10.21608/ijicis.2022.118834.1163","url":null,"abstract":"Image understanding and scene classification are keystone tasks in computer vision. The advancement of technology and the abundance of available datasets in the field of image classification and recognition study provide plenty of attempts for advancement. In the scene classification problem, transfer learning is commonly utilized as a branch of machine learning. Despite existing machine learning models' superior performance in image interpretation and scene classification, there are still challenges to overcome. The weights and current models aren't suitable in most circumstances. Instead of using the weights of data-dependent models, in this work, a novel machine learning model for the scene classification task is provided that converges rapidly. The proposed model has been tested on the Intel scenes dataset for a comprehensive evaluation of our model. The proposed model RepConv over-performed four existing benchmark models in a low number of epochs and training parameters, and it achieved 93.55 ± 0.11, 75.54 ± 0.14 accuracies for training and validation data respectively. Furthermore, re-categorization of the data set is performed for a new classification problem that is not previously reported in the literature (natural scenes; real scenes). The accuracy of the proposed model on the binary model was 98.08 ± 0.05 on training data and 92.70 ± 0.08 on validation data which is not reported previously in any other publication.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114864313","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}
- A Mobile Social Network (MSN) consists of nodes that are related socially, in addition to their physical connection through wireless links. In terms of mobile devices, social connection reflects the frequency of encounter, so that the users of these devices are socially connected if they communicate with each other frequently. This layer of social connectivity, combined with the physical connectivity of being in the communication range of each other, can help improve the routing performance. However, it also inherits the challenges of mobile adhoc networks. These challenges include the limited energy resource, intermittent connectivity, and the limited storage. To overcome these challenges and improve routing efficiency, social metrics are exploited to carefully choose the candidate relays in MSNs. In this paper, the routing protocols proposed or candidate to be implemented in MSN are reviewed, focusing on the routing metrics used to select the candidate relays. In addition, the authors describe a list of performance measures that are useful in comparing current and future MSN routing protocols.
—移动社交网络(Mobile Social Network, MSN)是由节点之间除了通过无线链路进行物理连接外，还具有社交关系的网络。对于移动设备来说，社交连接反映的是相遇的频率，如果这些设备的用户经常交流，那么这些设备的用户就是社交连接的。这一层的社交连通性，结合彼此处于通信范围内的物理连通性，可以帮助提高路由性能。然而，它也继承了移动自组织网络的挑战。这些挑战包括有限的能源资源、间歇性连接和有限的存储。为了克服这些挑战并提高路由效率，利用社会指标来仔细选择候选的msn中继。本文回顾了MSN中提出的或候选的路由协议，重点介绍了用于选择候选中继的路由度量。此外，作者还描述了一系列性能指标，这些指标在比较当前和未来的MSN路由协议时非常有用。
{"title":"A Review of Routing Protocols for Mobile Social Networks","authors":"Hadeer Shahin","doi":"10.21608/ijicis.2022.92114.1120","DOIUrl":"https://doi.org/10.21608/ijicis.2022.92114.1120","url":null,"abstract":"- A Mobile Social Network (MSN) consists of nodes that are related socially, in addition to their physical connection through wireless links. In terms of mobile devices, social connection reflects the frequency of encounter, so that the users of these devices are socially connected if they communicate with each other frequently. This layer of social connectivity, combined with the physical connectivity of being in the communication range of each other, can help improve the routing performance. However, it also inherits the challenges of mobile adhoc networks. These challenges include the limited energy resource, intermittent connectivity, and the limited storage. To overcome these challenges and improve routing efficiency, social metrics are exploited to carefully choose the candidate relays in MSNs. In this paper, the routing protocols proposed or candidate to be implemented in MSN are reviewed, focusing on the routing metrics used to select the candidate relays. In addition, the authors describe a list of performance measures that are useful in comparing current and future MSN routing protocols.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114545934","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}
A.E. Amin* Department of Computer Science, Mansoura University, Mansoura 35516, Egypt ahmedel_sayed@mans.edu.eg Received 202106-29; Revised 2021-09-30; Accepted 2021-10-12 Abstract: This paper deals with images using the theory of neutrosophic, which the idea of working, on set about the degree of truth, indeterminacy, and falsity. Which helped to discover the hidden features of the images that were segmented by using neutrosophic image processing into objects and then extracting the features into the three truth, indeterminacy, and falsity levels of the image and combining these features to extract the original image features. The proposed similarity model namely weighted Hamming distance measure that based on the single-value neutrosophic set was used to retrieve images from the database, by matching with the query image that extracted its feature in the same way. The results showed that the proposed system is highly efficient in retrieving images compared to different distance measures such as Euclidian, Manhattan, and Minkowski. Finally, A novel similarity model used to match the neutrosophic image features for CBIRs. In the proposed system, an image is segmented into objects, edges, and backgrounds by using neutrosophic image processing.
{"title":"An Optimal Similarity Neutrosophic Model Based on Distance Measuring to Improving Content-based Image Retrieval","authors":"A. Amin","doi":"10.21608/ijicis.2021.83197.1109","DOIUrl":"https://doi.org/10.21608/ijicis.2021.83197.1109","url":null,"abstract":"A.E. Amin* Department of Computer Science, Mansoura University, Mansoura 35516, Egypt ahmedel_sayed@mans.edu.eg Received 202106-29; Revised 2021-09-30; Accepted 2021-10-12 Abstract: This paper deals with images using the theory of neutrosophic, which the idea of working, on set about the degree of truth, indeterminacy, and falsity. Which helped to discover the hidden features of the images that were segmented by using neutrosophic image processing into objects and then extracting the features into the three truth, indeterminacy, and falsity levels of the image and combining these features to extract the original image features. The proposed similarity model namely weighted Hamming distance measure that based on the single-value neutrosophic set was used to retrieve images from the database, by matching with the query image that extracted its feature in the same way. The results showed that the proposed system is highly efficient in retrieving images compared to different distance measures such as Euclidian, Manhattan, and Minkowski. Finally, A novel similarity model used to match the neutrosophic image features for CBIRs. In the proposed system, an image is segmented into objects, edges, and backgrounds by using neutrosophic image processing.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126339764","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}
Melanoma is a dangerous and metastatic cancer that may be fatal and it has a high ability to invade other tissues and organs. Early diagnosis is an important reason to recover from melanoma and reduce mortality. So, automatic skin segmentation is considered an enthusiastic study at present. In this paper, we investigate the applicability of deep learning approaches to the segmentation of skin lesions by evaluating five architectures: Deeplabv3plus, Inception-ResNet-v2-unet, mobilenetv2_unet, Resnet50_unet, vgg19_unet by providing a comparative study of those methods. All methods were trained on the ISIC2017 dataset. The methods were trained on the original dataset, and then the dataset was pre-processed for use in training the five methods. We used quantitative evaluation metrics to evaluate the performance of the methods. The Deeplabv3+ architecture showed significant results compared to the rest of the architecture in F1 as high as 89%, Jaccard as high as 83% and Recall as high as 91%.
{"title":"Experimental Comparative Study on Autoencoder Performance for Aided Melanoma Skin Disease Recognition","authors":"Zahraa E. Diame, Maryam ElBery, M. Salem, Mohamed Roushdy","doi":"10.21608/ijicis.2022.104799.1136","DOIUrl":"https://doi.org/10.21608/ijicis.2022.104799.1136","url":null,"abstract":"Melanoma is a dangerous and metastatic cancer that may be fatal and it has a high ability to invade other tissues and organs. Early diagnosis is an important reason to recover from melanoma and reduce mortality. So, automatic skin segmentation is considered an enthusiastic study at present. In this paper, we investigate the applicability of deep learning approaches to the segmentation of skin lesions by evaluating five architectures: Deeplabv3plus, Inception-ResNet-v2-unet, mobilenetv2_unet, Resnet50_unet, vgg19_unet by providing a comparative study of those methods. All methods were trained on the ISIC2017 dataset. The methods were trained on the original dataset, and then the dataset was pre-processed for use in training the five methods. We used quantitative evaluation metrics to evaluate the performance of the methods. The Deeplabv3+ architecture showed significant results compared to the rest of the architecture in F1 as high as 89%, Jaccard as high as 83% and Recall as high as 91%.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122138320","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}
: Nowadays, one of the most complex problems in telemedicine and E-health is the preservation of patient data due to the integration between the development of technology and the medical sector. To protect patient privacy, the transmission of the secured medical image requires adequate techniques. This study aims at encrypting COVID-19 images of Computed Tomography (CT) chest scan into secured and sensitive cipher images for the infected patient. To achieve a high degree of security in the encryption process, protein key generation for the encryption process has been proposed. This study aims to encrypt images using 2 round AES plus Protein key. The histogram has been used to estimate the degree of security for the proposed method. Four criteria have been selected to evaluate the degree of security for the proposed method Number of Pixel Change Rate, Correlation coefficient, Entropy, and Unified Average Changing Intensity. The result indicated that the proposed method has 99.5% and above NPCR, Correlation coefficient close to zero, UACI above 30%, and Entropy near to 8. The results confirm that the proposed method achieves a high level of security and sensitivity when compared with previous work. Therefore, the proposed method can be considered as a successfully applied algorithm to satisfy the security requirements of transmitting CT images for COVID-19 patients .
{"title":"Protein Key Generation for Secure CT-Chest Images Encryption","authors":"Sara Shehab","doi":"10.21608/ijicis.2021.82820.1108","DOIUrl":"https://doi.org/10.21608/ijicis.2021.82820.1108","url":null,"abstract":": Nowadays, one of the most complex problems in telemedicine and E-health is the preservation of patient data due to the integration between the development of technology and the medical sector. To protect patient privacy, the transmission of the secured medical image requires adequate techniques. This study aims at encrypting COVID-19 images of Computed Tomography (CT) chest scan into secured and sensitive cipher images for the infected patient. To achieve a high degree of security in the encryption process, protein key generation for the encryption process has been proposed. This study aims to encrypt images using 2 round AES plus Protein key. The histogram has been used to estimate the degree of security for the proposed method. Four criteria have been selected to evaluate the degree of security for the proposed method Number of Pixel Change Rate, Correlation coefficient, Entropy, and Unified Average Changing Intensity. The result indicated that the proposed method has 99.5% and above NPCR, Correlation coefficient close to zero, UACI above 30%, and Entropy near to 8. The results confirm that the proposed method achieves a high level of security and sensitivity when compared with previous work. Therefore, the proposed method can be considered as a successfully applied algorithm to satisfy the security requirements of transmitting CT images for COVID-19 patients .","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123217831","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：