Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-vary...Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-varying characteristics in sound propagation channels and cannot easily extract valuable waveform features.Sound propagation channels in seawater are time-and space-varying convolutional channels.In the extraction of the waveform features of underwater acoustic signals,the effect of high-accuracy underwater acoustic signal recognition is identified by eliminating the influence of time-and space-varying convolutional channels to the greatest extent possible.We propose a hash aggregate discriminative network(HADN),which combines hash learning and deep learning to minimize the time-and space-varying effects on convolutional channels and adaptively learns effective underwater waveform features to achieve high-accuracy underwater pulse waveform recognition.In the extraction of the hash features of acoustic signals,a discrete constraint between clusters within a hash feature class is introduced.This constraint can ensure that the influence of convolutional channels on hash features is minimized.In addition,we design a new loss function called aggregate discriminative loss(AD-loss).The use of AD-loss and softmax-loss can increase the discriminativeness of the learned hash features.Experimental results show that on pool and ocean datasets,which were collected in pools and oceans,respectively,by using acoustic collectors,the proposed HADN performs better than other comparative models in terms of accuracy and mAP.展开更多
The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos ...The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos characteristics is proposed. First, the chaos sequence is gotten by iterating cellular neural network with Runge Kutta algorithm, and then the chaos sequence is iterated with the message. The hash code is obtained through the corre- sponding transform of the latter chaos sequence. Simulation and analysis demonstrate that the new method has the merit of convenience, high sensitivity to initial values, good hash performance, especially the strong stability.展开更多
In this paper,based on coupled network generated by chaotic logarithmic map,a novel algorithm for constructing hash functions is proposed,which can transform messages and can establish a mapping from the transformed m...In this paper,based on coupled network generated by chaotic logarithmic map,a novel algorithm for constructing hash functions is proposed,which can transform messages and can establish a mapping from the transformed messages to the coupled matrix of the network.The network model is carefully designed to ensure the network dynamics to be chaotic.Through the chaotic iterations of the network,quantization and exclusive-or (XOR) operations,the algorithm can construct hash value with arbitrary length.It is shown by simulations that the algorithm is extremely sensitive to the initial values and the coupled matrix of the network,and has excellent performance in one-way,confusion and diffusion,and collision resistance.展开更多
In this paper, we propose a new online system that can quickly detect malicious spam emails and adapt to the changes in the email contents and the Uniform Resource Locator (URL) links leading to malicious websites by ...In this paper, we propose a new online system that can quickly detect malicious spam emails and adapt to the changes in the email contents and the Uniform Resource Locator (URL) links leading to malicious websites by updating the system daily. We introduce an autonomous function for a server to generate training examples, in which double-bounce emails are automatically collected and their class labels are given by a crawler-type software to analyze the website maliciousness called SPIKE. In general, since spammers use botnets to spread numerous malicious emails within a short time, such distributed spam emails often have the same or similar contents. Therefore, it is not necessary for all spam emails to be learned. To adapt to new malicious campaigns quickly, only new types of spam emails should be selected for learning and this can be realized by introducing an active learning scheme into a classifier model. For this purpose, we adopt Resource Allocating Network with Locality Sensitive Hashing (RAN-LSH) as a classifier model with a data selection function. In RAN-LSH, the same or similar spam emails that have already been learned are quickly searched for a hash table in Locally Sensitive Hashing (LSH), in which the matched similar emails located in “well-learned” are discarded without being used as training data. To analyze email contents, we adopt the Bag of Words (BoW) approach and generate feature vectors whose attributes are transformed based on the normalized term frequency-inverse document frequency (TF-IDF). We use a data set of double-bounce spam emails collected at National Institute of Information and Communications Technology (NICT) in Japan from March 1st, 2013 until May 10th, 2013 to evaluate the performance of the proposed system. The results confirm that the proposed spam email detection system has capability of detecting with high detection rate.展开更多
In the era of big data rich inWe Media,the single mode retrieval system has been unable to meet people’s demand for information retrieval.This paper proposes a new solution to the problem of feature extraction and un...In the era of big data rich inWe Media,the single mode retrieval system has been unable to meet people’s demand for information retrieval.This paper proposes a new solution to the problem of feature extraction and unified mapping of different modes:A Cross-Modal Hashing retrieval algorithm based on Deep Residual Network(CMHR-DRN).The model construction is divided into two stages:The first stage is the feature extraction of different modal data,including the use of Deep Residual Network(DRN)to extract the image features,using the method of combining TF-IDF with the full connection network to extract the text features,and the obtained image and text features used as the input of the second stage.In the second stage,the image and text features are mapped into Hash functions by supervised learning,and the image and text features are mapped to the common binary Hamming space.In the process of mapping,the distance measurement of the original distance measurement and the common feature space are kept unchanged as far as possible to improve the accuracy of Cross-Modal Retrieval.In training the model,adaptive moment estimation(Adam)is used to calculate the adaptive learning rate of each parameter,and the stochastic gradient descent(SGD)is calculated to obtain the minimum loss function.The whole training process is completed on Caffe deep learning framework.Experiments show that the proposed algorithm CMHR-DRN based on Deep Residual Network has better retrieval performance and stronger advantages than other Cross-Modal algorithms CMFH,CMDN and CMSSH.展开更多
A novel scheme to construct a hash function based on a weighted complex dynamical network （WCDN） generated from an original message is proposed in this paper. First, the original message is divided into blocks. Then...A novel scheme to construct a hash function based on a weighted complex dynamical network （WCDN） generated from an original message is proposed in this paper. First, the original message is divided into blocks. Then, each block is divided into components, and the nodes and weighted edges are well defined from these components and their relations. Namely, the WCDN closely related to the original message is established. Furthermore, the node dynamics of the WCDN are chosen as a chaotic map. After chaotic iterations, quantization and exclusive-or operations, the fixed-length hash value is obtained. This scheme has the property that any tiny change in message can be diffused rapidly through the WCDN, leading to very different hash values. Analysis and simulation show that the scheme possesses good statistical properties, excellent confusion and diffusion, strong collision resistance and high efficiency.展开更多
Traditional routing protocols as TCP/IP can not be directly used in WSN, so special data-centric routing protocols must be established. The raised data-centric routing protocols can not identify the sensor nodes, beca...Traditional routing protocols as TCP/IP can not be directly used in WSN, so special data-centric routing protocols must be established. The raised data-centric routing protocols can not identify the sensor nodes, because many nodes work under a monitoring task, and the source of data is not so important some times. The sensor node in the network can not judge weather data is come from the some sink node. What’s more, the traditional method use IP to identify sensors in Internet is not suitable for WSN. In this paper, we propose a new naming scheme to identify sensor nodes, which based on a description of sensor node, the description of a sensor node is hashed to a hash value to identify this sensor. The different description generates different identifier. Different from IP schema, this identifier is something about the information of the sensor node. In the above naming scheme, we propose a new data-centric routing mechanism. Finally, the simulation of the routing mechanism is carried out on MATLAB. The result shows our routing mechanism’s predominate increase when network size increase.展开更多
Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed sto...Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.展开更多
The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of...The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of data by homomorphic hash function,and then it compares the hash value with the receiving message digest.Because the feedback channel is deliberately removed during the distribution process,the rateless codes are often vulnerable when they face security issues such as packets contamination or attack.This method prevents contaminating or attack on rateless codes and reduces the potential risks of decoding failure.Compared with the SHA1 and MD5,HHA,which has a much shorter message digest,will deliver more data.The simulation results show that to transmit and verify the same amount of OAP data,HHA method sends 17.9% to 23.1%fewer packets than MD5 and SHA1 under different packet loss rates.展开更多
基金partially supported by the National Key Research and Development Program of China(No.2018 AAA0100400)the Natural Science Foundation of Shandong Province(Nos.ZR2020MF131 and ZR2021ZD19)the Science and Technology Program of Qingdao(No.21-1-4-ny-19-nsh).
文摘Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-varying characteristics in sound propagation channels and cannot easily extract valuable waveform features.Sound propagation channels in seawater are time-and space-varying convolutional channels.In the extraction of the waveform features of underwater acoustic signals,the effect of high-accuracy underwater acoustic signal recognition is identified by eliminating the influence of time-and space-varying convolutional channels to the greatest extent possible.We propose a hash aggregate discriminative network(HADN),which combines hash learning and deep learning to minimize the time-and space-varying effects on convolutional channels and adaptively learns effective underwater waveform features to achieve high-accuracy underwater pulse waveform recognition.In the extraction of the hash features of acoustic signals,a discrete constraint between clusters within a hash feature class is introduced.This constraint can ensure that the influence of convolutional channels on hash features is minimized.In addition,we design a new loss function called aggregate discriminative loss(AD-loss).The use of AD-loss and softmax-loss can increase the discriminativeness of the learned hash features.Experimental results show that on pool and ocean datasets,which were collected in pools and oceans,respectively,by using acoustic collectors,the proposed HADN performs better than other comparative models in terms of accuracy and mAP.
基金supported by Key Program of Natural Science Fund of Tianjin of China (Grant No 07JCZDJC06600)
文摘The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos characteristics is proposed. First, the chaos sequence is gotten by iterating cellular neural network with Runge Kutta algorithm, and then the chaos sequence is iterated with the message. The hash code is obtained through the corre- sponding transform of the latter chaos sequence. Simulation and analysis demonstrate that the new method has the merit of convenience, high sensitivity to initial values, good hash performance, especially the strong stability.
基金supported by the Program for New Century Excellent Talents in University of China(No.NCET-06-0510)National Natural Science Founda-tion of China(No. 60874091)Six Projects Sponsoring Talent Summits of Jiangsu Province(No. SJ209006)
文摘In this paper,based on coupled network generated by chaotic logarithmic map,a novel algorithm for constructing hash functions is proposed,which can transform messages and can establish a mapping from the transformed messages to the coupled matrix of the network.The network model is carefully designed to ensure the network dynamics to be chaotic.Through the chaotic iterations of the network,quantization and exclusive-or (XOR) operations,the algorithm can construct hash value with arbitrary length.It is shown by simulations that the algorithm is extremely sensitive to the initial values and the coupled matrix of the network,and has excellent performance in one-way,confusion and diffusion,and collision resistance.
文摘In this paper, we propose a new online system that can quickly detect malicious spam emails and adapt to the changes in the email contents and the Uniform Resource Locator (URL) links leading to malicious websites by updating the system daily. We introduce an autonomous function for a server to generate training examples, in which double-bounce emails are automatically collected and their class labels are given by a crawler-type software to analyze the website maliciousness called SPIKE. In general, since spammers use botnets to spread numerous malicious emails within a short time, such distributed spam emails often have the same or similar contents. Therefore, it is not necessary for all spam emails to be learned. To adapt to new malicious campaigns quickly, only new types of spam emails should be selected for learning and this can be realized by introducing an active learning scheme into a classifier model. For this purpose, we adopt Resource Allocating Network with Locality Sensitive Hashing (RAN-LSH) as a classifier model with a data selection function. In RAN-LSH, the same or similar spam emails that have already been learned are quickly searched for a hash table in Locally Sensitive Hashing (LSH), in which the matched similar emails located in “well-learned” are discarded without being used as training data. To analyze email contents, we adopt the Bag of Words (BoW) approach and generate feature vectors whose attributes are transformed based on the normalized term frequency-inverse document frequency (TF-IDF). We use a data set of double-bounce spam emails collected at National Institute of Information and Communications Technology (NICT) in Japan from March 1st, 2013 until May 10th, 2013 to evaluate the performance of the proposed system. The results confirm that the proposed spam email detection system has capability of detecting with high detection rate.
文摘In the era of big data rich inWe Media,the single mode retrieval system has been unable to meet people’s demand for information retrieval.This paper proposes a new solution to the problem of feature extraction and unified mapping of different modes:A Cross-Modal Hashing retrieval algorithm based on Deep Residual Network(CMHR-DRN).The model construction is divided into two stages:The first stage is the feature extraction of different modal data,including the use of Deep Residual Network(DRN)to extract the image features,using the method of combining TF-IDF with the full connection network to extract the text features,and the obtained image and text features used as the input of the second stage.In the second stage,the image and text features are mapped into Hash functions by supervised learning,and the image and text features are mapped to the common binary Hamming space.In the process of mapping,the distance measurement of the original distance measurement and the common feature space are kept unchanged as far as possible to improve the accuracy of Cross-Modal Retrieval.In training the model,adaptive moment estimation(Adam)is used to calculate the adaptive learning rate of each parameter,and the stochastic gradient descent(SGD)is calculated to obtain the minimum loss function.The whole training process is completed on Caffe deep learning framework.Experiments show that the proposed algorithm CMHR-DRN based on Deep Residual Network has better retrieval performance and stronger advantages than other Cross-Modal algorithms CMFH,CMDN and CMSSH.
基金Project supported by the Natural Science Foundation of Jiangsu Province, China (Grant No. BK2010526)the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20103223110003)The Ministry of Education Research in the Humanities and Social Sciences Planning Fund, China (Grant No. 12YJAZH120)
文摘A novel scheme to construct a hash function based on a weighted complex dynamical network （WCDN） generated from an original message is proposed in this paper. First, the original message is divided into blocks. Then, each block is divided into components, and the nodes and weighted edges are well defined from these components and their relations. Namely, the WCDN closely related to the original message is established. Furthermore, the node dynamics of the WCDN are chosen as a chaotic map. After chaotic iterations, quantization and exclusive-or operations, the fixed-length hash value is obtained. This scheme has the property that any tiny change in message can be diffused rapidly through the WCDN, leading to very different hash values. Analysis and simulation show that the scheme possesses good statistical properties, excellent confusion and diffusion, strong collision resistance and high efficiency.
文摘Traditional routing protocols as TCP/IP can not be directly used in WSN, so special data-centric routing protocols must be established. The raised data-centric routing protocols can not identify the sensor nodes, because many nodes work under a monitoring task, and the source of data is not so important some times. The sensor node in the network can not judge weather data is come from the some sink node. What’s more, the traditional method use IP to identify sensors in Internet is not suitable for WSN. In this paper, we propose a new naming scheme to identify sensor nodes, which based on a description of sensor node, the description of a sensor node is hashed to a hash value to identify this sensor. The different description generates different identifier. Different from IP schema, this identifier is something about the information of the sensor node. In the above naming scheme, we propose a new data-centric routing mechanism. Finally, the simulation of the routing mechanism is carried out on MATLAB. The result shows our routing mechanism’s predominate increase when network size increase.
基金Supported by the National Natural Science Foundation of China(61373100)the Open Funding Project of State Key Laboratory of Virtual Reality Technology and Systems(BUAA-VR-16KF-13,BUAA-VR-17KF-14,BUAA-VR-17KF-15)the Research Project Supported by Shanxi Scholarship Council of China(2016-038)
文摘Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.
基金Supported by the National Science and Technology Support Program(Y2140161A5)the National High Technology Research and Development Program of China(863Program)(O812041A04)
文摘The homomorphic hash algorithm(HHA)is introduced to help on-the-fly verify the vireless sensor network(WSN)over-the-air programming(OAP)data based on rateless codes.The receiver calculates the hash value of a group of data by homomorphic hash function,and then it compares the hash value with the receiving message digest.Because the feedback channel is deliberately removed during the distribution process,the rateless codes are often vulnerable when they face security issues such as packets contamination or attack.This method prevents contaminating or attack on rateless codes and reduces the potential risks of decoding failure.Compared with the SHA1 and MD5,HHA,which has a much shorter message digest,will deliver more data.The simulation results show that to transmit and verify the same amount of OAP data,HHA method sends 17.9% to 23.1%fewer packets than MD5 and SHA1 under different packet loss rates.
