In order to optionally regulate embedding capacity and embedding transparency according to user's requirements in voice-over-IP(VoIP) steganography,a dynamic matrix encoding strategy(DMES) was presented.Differing ...In order to optionally regulate embedding capacity and embedding transparency according to user's requirements in voice-over-IP(VoIP) steganography,a dynamic matrix encoding strategy(DMES) was presented.Differing from the traditional matrix encoding strategy,DMES dynamically chose the size of each message group in a given set of adoptable message sizes.The appearance possibilities of all adoptable sizes were set in accordance with the desired embedding performance(embedding rate or bit-change rate).Accordingly,a searching algorithm that could provide an optimal combination of appearance possibilities was proposed.Furthermore,the roulette wheel algorithm was employed to determine the size of each message group according to the optimal combination of appearance possibilities.The effectiveness of DMES was evaluated in StegVoIP,which is a typical covert communication system based on VoIP.The experimental results demonstrate that DMES can adjust embedding capacity and embedding transparency effectively and flexibly,and achieve the desired embedding performance in any case.For the desired embedding rate,the average errors are not more than 0.000 8,and the standard deviations are not more than 0.002 0;for the desired bit-change rate,the average errors are not more than 0.001 4,and the standard deviations are not more than 0.002 6.展开更多
There are many cloud data security techniques and algorithms available that can be used to detect attacks on cloud data,but these techniques and algorithms cannot be used to protect data from an attacker.Cloud cryptog...There are many cloud data security techniques and algorithms available that can be used to detect attacks on cloud data,but these techniques and algorithms cannot be used to protect data from an attacker.Cloud cryptography is the best way to transmit data in a secure and reliable format.Various researchers have developed various mechanisms to transfer data securely,which can convert data from readable to unreadable,but these algorithms are not sufficient to provide complete data security.Each algorithm has some data security issues.If some effective data protection techniques are used,the attacker will not be able to decipher the encrypted data,and even if the attacker tries to tamper with the data,the attacker will not have access to the original data.In this paper,various data security techniques are developed,which can be used to protect the data from attackers completely.First,a customized American Standard Code for Information Interchange(ASCII)table is developed.The value of each Index is defined in a customized ASCII table.When an attacker tries to decrypt the data,the attacker always tries to apply the predefined ASCII table on the Ciphertext,which in a way,can be helpful for the attacker to decrypt the data.After that,a radix 64-bit encryption mechanism is used,with the help of which the number of cipher data is doubled from the original data.When the number of cipher values is double the original data,the attacker tries to decrypt each value.Instead of getting the original data,the attacker gets such data that has no relation to the original data.After that,a Hill Matrix algorithm is created,with the help of which a key is generated that is used in the exact plain text for which it is created,and this Key cannot be used in any other plain text.The boundaries of each Hill text work up to that text.The techniques used in this paper are compared with those used in various papers and discussed that how far the current algorithm is better than all other algorithms.Then,the Kasiski test is used to verify the validity of the proposed algorithm and found that,if the proposed algorithm is used for data encryption,so an attacker cannot break the proposed algorithm security using any technique or algorithm.展开更多
深度子空间聚类(DSC)基于原始数据位于低维非线性子空间的集合中的假设。其中深度子空间聚类多尺度表示学习方法在深度自编码器的基础上,将每一层的编码器与对应的解码器之间都添加全连接层,并以此捕获多尺度的特征,但它没有深度分析多...深度子空间聚类(DSC)基于原始数据位于低维非线性子空间的集合中的假设。其中深度子空间聚类多尺度表示学习方法在深度自编码器的基础上,将每一层的编码器与对应的解码器之间都添加全连接层,并以此捕获多尺度的特征,但它没有深度分析多尺度特征的性质,也没有考虑输入数据和输出数据之间多尺度的重构损失。为了解决上述问题,首先建立每个网络层的重构损失函数,监督不同级别编码器参数的学习;然后利用多尺度特征共有的自表示矩阵和特有的自表示矩阵的和具有块对角性,提出更有效的多尺度自表示模块;最后分析不同尺度特征特有的自表示矩阵之间的多样性,有效地利用了多尺度的特征矩阵。在此基础上,提出一种基于一致性和多样性的多尺度自表示学习的深度子空间聚类(MSCD-DSC)方法。在数据集Extended Yale B、ORL、COIL20和Umist上的实验结果表明,相较于次优的MLRDSC(Multi-Level Representation learning for Deep Subspace Clustering),MSCD-DSC的聚类错误率分别降低了15.44%、2.22%、3.37%和13.17%,表明MSCD-DSC的聚类效果优于已有的方法。展开更多
大部分现有的用于预测环状RNA(circRNA)与疾病之间关联关系的计算模型通常使用circRNA和疾病相关数据等生物学知识,配合已知的circRNA-疾病关联信息对来挖掘出潜在的关联信息。然而这些模型受已知关联构成的网络稀疏性、负样本过少等固...大部分现有的用于预测环状RNA(circRNA)与疾病之间关联关系的计算模型通常使用circRNA和疾病相关数据等生物学知识,配合已知的circRNA-疾病关联信息对来挖掘出潜在的关联信息。然而这些模型受已知关联构成的网络稀疏性、负样本过少等固有问题的影响,导致预测性能不佳。因此,在图自动编码器基础上引入归纳式矩阵补全及自注意力机制进行二阶段融合,以实现circRNA-疾病关联预测,由此构建的模型叫GIS-CDA(Graph auto-encoder combining Inductive matrix complementation and Self-attention mechanism for predicting Circ RNA-Disease Association)。首先,计算circRNA集成和疾病集成的相似性,并利用图自动编码器学习circRNA和疾病的潜在特征,以获得低维表征;接着,将学习到的特征输入归纳式矩阵补全,以提高节点之间的相似性和依赖性;然后,将circRNA特征矩阵和疾病特征矩阵整合为circRNA-疾病特征矩阵,以增强预测的稳定性和精确性;最后,引入自注意力机制,从特征矩阵中提取重要特征,并减少对其他生物信息的依赖。五折交叉和十折交叉验证的结果显示:GIS-CDA获得的平均接收者操作特征曲线下面积(AUROC)值分别为0.9303和0.9393,前者比基于KATZ测度的人类circRNA-疾病关联预测模型(KATZHCDA)、基于深度矩阵分解方法的circRNA-疾病关联(DMFCDA)预测模型、RWR(Random Walk with Restart)和基于加速归纳式矩阵补全的circRNA-疾病关联(SIMCCDA)预测模型分别高出了13.19、35.73、13.28和5.01个百分点;GIS-CDA的精确率-召回率曲线下面积(AUPR)值分别为0.2271和0.2340,前者比上述对比模型分别高出了21.72、22.43、21.96和13.86个百分点。此外,在circRNADisease、circ2Disease和circ R2Disease数据集上的消融实验和案例研究进一步验证了GIS-CDA在预测circRNA-疾病的潜在关联方面具有较好的性能。展开更多
基金Project(2009AA01A402) supported by the National High-Tech Research and Development Program of ChinaProject(NCET-06-0650) supported by Program for New Century Excellent Talents in University Project(IRT-0725) supported by Program for Changjiang Scholars and Innovative Research Team in Chinese University
文摘In order to optionally regulate embedding capacity and embedding transparency according to user's requirements in voice-over-IP(VoIP) steganography,a dynamic matrix encoding strategy(DMES) was presented.Differing from the traditional matrix encoding strategy,DMES dynamically chose the size of each message group in a given set of adoptable message sizes.The appearance possibilities of all adoptable sizes were set in accordance with the desired embedding performance(embedding rate or bit-change rate).Accordingly,a searching algorithm that could provide an optimal combination of appearance possibilities was proposed.Furthermore,the roulette wheel algorithm was employed to determine the size of each message group according to the optimal combination of appearance possibilities.The effectiveness of DMES was evaluated in StegVoIP,which is a typical covert communication system based on VoIP.The experimental results demonstrate that DMES can adjust embedding capacity and embedding transparency effectively and flexibly,and achieve the desired embedding performance in any case.For the desired embedding rate,the average errors are not more than 0.000 8,and the standard deviations are not more than 0.002 0;for the desired bit-change rate,the average errors are not more than 0.001 4,and the standard deviations are not more than 0.002 6.
基金This research was supported by the Researchers supporting program(TUMAProject-2021-27)Almaarefa University,Riyadh,Saudi Arabia.
文摘There are many cloud data security techniques and algorithms available that can be used to detect attacks on cloud data,but these techniques and algorithms cannot be used to protect data from an attacker.Cloud cryptography is the best way to transmit data in a secure and reliable format.Various researchers have developed various mechanisms to transfer data securely,which can convert data from readable to unreadable,but these algorithms are not sufficient to provide complete data security.Each algorithm has some data security issues.If some effective data protection techniques are used,the attacker will not be able to decipher the encrypted data,and even if the attacker tries to tamper with the data,the attacker will not have access to the original data.In this paper,various data security techniques are developed,which can be used to protect the data from attackers completely.First,a customized American Standard Code for Information Interchange(ASCII)table is developed.The value of each Index is defined in a customized ASCII table.When an attacker tries to decrypt the data,the attacker always tries to apply the predefined ASCII table on the Ciphertext,which in a way,can be helpful for the attacker to decrypt the data.After that,a radix 64-bit encryption mechanism is used,with the help of which the number of cipher data is doubled from the original data.When the number of cipher values is double the original data,the attacker tries to decrypt each value.Instead of getting the original data,the attacker gets such data that has no relation to the original data.After that,a Hill Matrix algorithm is created,with the help of which a key is generated that is used in the exact plain text for which it is created,and this Key cannot be used in any other plain text.The boundaries of each Hill text work up to that text.The techniques used in this paper are compared with those used in various papers and discussed that how far the current algorithm is better than all other algorithms.Then,the Kasiski test is used to verify the validity of the proposed algorithm and found that,if the proposed algorithm is used for data encryption,so an attacker cannot break the proposed algorithm security using any technique or algorithm.
文摘深度子空间聚类(DSC)基于原始数据位于低维非线性子空间的集合中的假设。其中深度子空间聚类多尺度表示学习方法在深度自编码器的基础上,将每一层的编码器与对应的解码器之间都添加全连接层,并以此捕获多尺度的特征,但它没有深度分析多尺度特征的性质,也没有考虑输入数据和输出数据之间多尺度的重构损失。为了解决上述问题,首先建立每个网络层的重构损失函数,监督不同级别编码器参数的学习;然后利用多尺度特征共有的自表示矩阵和特有的自表示矩阵的和具有块对角性,提出更有效的多尺度自表示模块;最后分析不同尺度特征特有的自表示矩阵之间的多样性,有效地利用了多尺度的特征矩阵。在此基础上,提出一种基于一致性和多样性的多尺度自表示学习的深度子空间聚类(MSCD-DSC)方法。在数据集Extended Yale B、ORL、COIL20和Umist上的实验结果表明,相较于次优的MLRDSC(Multi-Level Representation learning for Deep Subspace Clustering),MSCD-DSC的聚类错误率分别降低了15.44%、2.22%、3.37%和13.17%,表明MSCD-DSC的聚类效果优于已有的方法。
基金supported by the National Natural Science Foundation of China(1127105011371183+2 种基金61403036)the Science and Technology Development Foundation of CAEP(2013A04030202013B0403068)
文摘大部分现有的用于预测环状RNA(circRNA)与疾病之间关联关系的计算模型通常使用circRNA和疾病相关数据等生物学知识,配合已知的circRNA-疾病关联信息对来挖掘出潜在的关联信息。然而这些模型受已知关联构成的网络稀疏性、负样本过少等固有问题的影响,导致预测性能不佳。因此,在图自动编码器基础上引入归纳式矩阵补全及自注意力机制进行二阶段融合,以实现circRNA-疾病关联预测,由此构建的模型叫GIS-CDA(Graph auto-encoder combining Inductive matrix complementation and Self-attention mechanism for predicting Circ RNA-Disease Association)。首先,计算circRNA集成和疾病集成的相似性,并利用图自动编码器学习circRNA和疾病的潜在特征,以获得低维表征;接着,将学习到的特征输入归纳式矩阵补全,以提高节点之间的相似性和依赖性;然后,将circRNA特征矩阵和疾病特征矩阵整合为circRNA-疾病特征矩阵,以增强预测的稳定性和精确性;最后,引入自注意力机制,从特征矩阵中提取重要特征,并减少对其他生物信息的依赖。五折交叉和十折交叉验证的结果显示:GIS-CDA获得的平均接收者操作特征曲线下面积(AUROC)值分别为0.9303和0.9393,前者比基于KATZ测度的人类circRNA-疾病关联预测模型(KATZHCDA)、基于深度矩阵分解方法的circRNA-疾病关联(DMFCDA)预测模型、RWR(Random Walk with Restart)和基于加速归纳式矩阵补全的circRNA-疾病关联(SIMCCDA)预测模型分别高出了13.19、35.73、13.28和5.01个百分点;GIS-CDA的精确率-召回率曲线下面积(AUPR)值分别为0.2271和0.2340,前者比上述对比模型分别高出了21.72、22.43、21.96和13.86个百分点。此外,在circRNADisease、circ2Disease和circ R2Disease数据集上的消融实验和案例研究进一步验证了GIS-CDA在预测circRNA-疾病的潜在关联方面具有较好的性能。