BACKGROUND The teaching mode of fitness exercise prescriptions for college students in physical education conforms to the scientific principles and rules of fitness,which can adapt to the characteristics of students’...BACKGROUND The teaching mode of fitness exercise prescriptions for college students in physical education conforms to the scientific principles and rules of fitness,which can adapt to the characteristics of students’individual physiological functions and stimulate their interest in learning.AIM To analyze the effect of prescribed exercise teaching on the sports quality and mental health of college students.METHODS The participants of the study were 240 students in our class of 2021,of which 142 were men and 98 were women.The 240 students were randomly divided into an experimental group using the exercise prescription teaching model and a control group using the conventional teaching model.The experimental and control groups were divided into four classes of 30 students each.The teaching activities of the two teaching mode groups were strictly controlled,and the same tests were used before and after the experiment to test the subjects’exercise quality(including standing long jump,50 m race,800 m race,sit-ups,sit-and-reach),physical form(including height,weight,Ketorolai index),cardiopulmonary function(including heart rate,blood pressure,spirometry,12-min running distance,maximum oxygen intake)and mental health(SCL-90,including somatization,obsessive-compulsive,interpersonal,depression,anxiety,hostility,phobia,paranoia,psychotic symptoms)to understand the effects of the exercise prescription teaching mode on students’physical and mental health status.RESULTS There were differences in the exercise scores of standing long jump,50 m,800 m/1000 m running,sit-ups,and sit-and-reach in the experimental group after the experiment compared with those before the experiment,and the above indices of the experimental group were different from those of the control group after the experiment(P<0.05).There were differences in body weight and Ketorolai index in the experimental group after the experiment compared to those before the experiment,and the indices of the experimental group were also different from those of the control group after the experiment(P<0.05).After the experiment,there were differences in spirometry,12-min running distance,and maximum oxygen intake in the experimental group compared to those before the experiment,and the indices of the experimental group were also different from those of the control group after the experiment(P<0.05).After the experiment,the indicators of somatization,interpersonal sensitivity,depression,anxiety,and hostility in the experimental group were different from those in the pre-experimental group,and the indexes of the experimental group were also different from those of the control group after the experiment(P<0.05).CONCLUSION Exercise prescription teaching can mobilize college students’consciousness,enthusiasm,and initiative;expand personalities;enhance physical fitness and improve their mental health more than the conventional fitness exercise prescription teaching method.展开更多
The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current re...The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.展开更多
The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.Howeve...The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.展开更多
The network is a major platform for implementing new cyber-telecom crimes.Therefore,it is important to carry out monitoring and early warning research on new cyber-telecom crime platforms,which will lay the foundation...The network is a major platform for implementing new cyber-telecom crimes.Therefore,it is important to carry out monitoring and early warning research on new cyber-telecom crime platforms,which will lay the foundation for the establishment of prevention and control systems to protect citizens’property.However,the deep-learning methods applied in the monitoring and early warning of new cyber-telecom crime platforms have some apparent drawbacks.For instance,the methods suffer from data-distribution differences and tremendous manual efforts spent on data labeling.Therefore,a monitoring and early warning method for new cyber-telecom crime platforms based on the BERT migration learning model is proposed.This method first identifies the text data and their tags,and then performs migration training based on a pre-training model.Finally,the method uses the fine-tuned model to predict and classify new cyber-telecom crimes.Experimental analysis on the crime data collected by public security organizations shows that higher classification accuracy can be achieved using the proposed method,compared with the deep-learning method.展开更多
A Service Level Agreement(SLA) is a legal contract between any two parties to ensure an adequate Quality of Service(Qo S). Most research on SLAs has concentrated on protecting the user data through encryption. However...A Service Level Agreement(SLA) is a legal contract between any two parties to ensure an adequate Quality of Service(Qo S). Most research on SLAs has concentrated on protecting the user data through encryption. However, these methods can not supervise a cloud service provider(CSP) directly. In order to address this problem, we propose a privacy-based SLA violation detection model for cloud computing based on Markov decision process theory. This model can recognize and regulate CSP's actions based on specific requirements of various users. Additionally, the model could make effective evaluation to the credibility of CSP, and can monitor events that user privacy is violated. Experiments and analysis indicate that the violation detection model can achieve good results in both the algorithm's convergence and prediction effect.展开更多
In order to solve the problems of data sharing security and policy conflict in multicloud storage systems(MCSS), this work designs an attribute mapping mechanism that extends ciphertext policy attribute-based encrypti...In order to solve the problems of data sharing security and policy conflict in multicloud storage systems(MCSS), this work designs an attribute mapping mechanism that extends ciphertext policy attribute-based encryption(CP-ABE), and proposes a multi-authority CP-ABE access control model that satisfies the need for multicloud storage access control. The mapping mechanism mainly involves the tree structure of CP-ABE and provides support for the types of attribute values. The framework and workflow of the model are described in detail. The effectiveness of the model is verified by building a simple prototype system, and the performance of the prototype system is analyzed. The results suggest that the proposed model is of theoretical and practical significance for access control research in MCSS. The CP-ABE has better performance in terms of computation time overhead than other models.展开更多
Attack surfaces, as one of the security models, can help people to analyse the security of systems in cyberspace, such as risk assessment by utilizing various security metrics or providing a cost-effective network har...Attack surfaces, as one of the security models, can help people to analyse the security of systems in cyberspace, such as risk assessment by utilizing various security metrics or providing a cost-effective network hardening solution. Numerous attack surface models have been proposed in the past decade,but they are not appropriate for describing complex systems with heterogeneous components. To address this limitation, we propose to use a two-layer Hierarchical Attack Surface Network(HASN) that models the data interactions and resource distribution of the system in a component-oriented view. First, we formally define the HASN by extending the entry point and exit point framework. Second, in order to assess data input risk and output risk on the HASN, we propose two behaviour models and two simulation-based risk metrics. Last, we conduct experiments for three network systems. Our experimental results show that the proposed approach is applicable and effective.展开更多
As an efficient technique for anti-counterfeiting,holographic diffraction labels has been widely applied to various fields.Due to their unique feature,traditional image recognition algorithms are not ideal for the hol...As an efficient technique for anti-counterfeiting,holographic diffraction labels has been widely applied to various fields.Due to their unique feature,traditional image recognition algorithms are not ideal for the holographic diffraction label recognition.Since a tensor preserves the spatiotemporal features of an original sample in the process of feature extraction,in this paper we propose a new holographic diffraction label recognition algorithm that combines two tensor features.The HSV(Hue Saturation Value)tensor and the HOG(Histogram of Oriented Gradient)tensor are used to represent the color information and gradient information of holographic diffraction label,respectively.Meanwhile,the tensor decomposition is performed by high order singular value decomposition,and tensor decomposition matrices are obtained.Taking into consideration of the different recognition capabilities of decomposition matrices,we design a decomposition matrix similarity fusion strategy using a typical correlation analysis algorithm and projection from similarity vectors of different decomposition matrices to the PCA(Principal Component Analysis)sub-space,then,the sub-space performs KNN(K-Nearest Neighbors)classification is performed.The effectiveness of our fusion strategy is verified by experiments.Our double tensor recognition algorithm complements the recognition capability of different tensors to produce better recognition performance for the holographic diffraction label system.展开更多
The feature analysis of fraudulent websites is of great significance to the combat,prevention and control of telecom fraud crimes.Aiming to address the shortcomings of existing analytical approaches,i.e.single dimensi...The feature analysis of fraudulent websites is of great significance to the combat,prevention and control of telecom fraud crimes.Aiming to address the shortcomings of existing analytical approaches,i.e.single dimension and venerability to anti-reconnaissance,this paper adopts the Stacking,the ensemble learning algorithm,combines multiple modalities such as text,image and URL,and proposes a multimodal fraudulent website identification method by ensembling heterogeneous models.Crossvalidation is first used in the training of multiple largely different base classifiers that are strong in learning,such as BERT model,residual neural network(ResNet)and logistic regression model.Classification of the text,image and URL features are then performed respectively.The results of the base classifiers are taken as the input of the meta-classifier,and the output of which is eventually used as the final identification.The study indicates that the fusion method is more effective in identifying fraudulent websites than the single-modal method,and the recall is increased by at least 1%.In addition,the deployment of the algorithm to the real Internet environment shows the improvement of the identification accuracy by at least 1.9%compared with other fusion methods.展开更多
Text analysis is a popular technique for finding the most significant information from texts including semantic,emotional,and other hidden features,which became a research hotspot in the last few years.Specially,there...Text analysis is a popular technique for finding the most significant information from texts including semantic,emotional,and other hidden features,which became a research hotspot in the last few years.Specially,there are some text analysis tasks with judgment reports,such as analyzing the criminal process and predicting prison terms.Traditional researches on text analysis are generally based on special feature selection and ontology model generation or require legal experts to provide external knowledge.All these methods require a lot of time and labor costs.Therefore,in this paper,we use textual data such as judgment reports creatively to perform prison term prediction without external legal knowledge.We propose a framework that combines value-based rules and a fuzzy text to predict the target prison term.The procedure in our framework includes information extraction,term fuzzification,and document vector regression.We carry out experiments with real-world judgment reports and compare our model’s performance with those of ten traditional classification and regression models and two deep learning models.The results show that our model achieves competitive results compared with other models as evaluated by the RMSE and R-squared metrics.Finally,we implement a prototype system with a user-friendly GUI that can be used to predict prison terms according to the legal text inputted by the user.展开更多
Platinum-decorated carbon nanotubes (CNT-Pt) were produced by the chemical reduction method. A novel modified electrode was fabricated by intercalated CNT-Pt in the surface of waxed graphite, which provided excellen...Platinum-decorated carbon nanotubes (CNT-Pt) were produced by the chemical reduction method. A novel modified electrode was fabricated by intercalated CNT-Pt in the surface of waxed graphite, which provided excellent electrocatalytic activity and selectivity for both oxidation and reduction of hydrogen peroxide. The current response of the modified electrode for hydrogen peroxide was very rapid and the detection limits in amperometry are 2.5×10^-6 mol/L at reduction potential and 4.8×10^-6 mol/L at oxidation potential. It was desmonstrated that the electrode with high electro-activity was a suitable basic electrode for preparing enzyme electrode.展开更多
Ceramic tiles are one of the most indispensable materials for interior decoration.The ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural textures.In this...Ceramic tiles are one of the most indispensable materials for interior decoration.The ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural textures.In this paper,we propose a sketch-based generation method for generating diverse ceramic tile images based on a hand-drawn sketches using Generative Adversarial Network(GAN).The generated tile images can be tailored to meet the specific needs of the user for the tile textures.The proposed method consists of four steps.Firstly,a dataset of ceramic tile images with diverse distributions is created and then pre-trained based on GAN.Secondly,for each ceramic tile image in the dataset,the corresponding sketch image is generated and then the mapping relationship between the images is trained based on a sketch extraction network using ResNet Block and jump connection to improve the quality of the generated sketches.Thirdly,the sketch style is redefined according to the characteristics of the ceramic tile images and then double cross-domain adversarial loss functions are employed to guide the ceramic tile generation network for fitting in the direction of the sketch style and to improve the training speed.Finally,we apply hidden space perturbation and interpolation for further enriching the output textures style and satisfying the concept of“one style with multiple faces”.We conduct the training process of the proposed generation network on 2583 ceramic tile images dataset.To measure the generative diversity and quality,we use Frechet Inception Distance(FID)and Blind/Referenceless Image Spatial Quality Evaluator(BRISQUE)metrics.The experimental results prove that the proposed model greatly enhances the generation results of the ceramic tile images,with FID of 32.47 and BRISQUE of 28.44.展开更多
Fingerprint identification systems have been widely deployed in many occasions of our daily life.However,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit finger...Fingerprint identification systems have been widely deployed in many occasions of our daily life.However,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit fingerprints.To address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s attention.The vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model generalization.Aiming at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint detection.Next,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection model.Finally,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and cross-sensor.The size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.展开更多
[Objectives]To optimize the determination method of oleandrin and adynerin in blood. [Methods]High performance liquid chromatography-mass spectrometry( HPLC-MS/MS) was applied to determine oleandrin and adynerin in bl...[Objectives]To optimize the determination method of oleandrin and adynerin in blood. [Methods]High performance liquid chromatography-mass spectrometry( HPLC-MS/MS) was applied to determine oleandrin and adynerin in blood. The blood sample was dispersed and fixed on a solid phase supported liquid-liquid extraction column and eluted with ethyl acetate. The resulting eluent was used for chromatographic separation with Kinetex C_(18) column as the separation column and gradient elution was performed using 10 mmol/L ammonium formate solution containing 0. 1%( volume fraction) formic acid and acetonitrile as the mobile phase. In the tandem mass spectrometry analysis,the detection was carried out using the electrospray positive ion source multiple reaction monitoring mode. [Results] The mass concentration of oleandrin and adynerin showed linear relationship in the range of 2-100 μg/L. The limit of detection( 3 S/N) of the method was 0. 5 μg/L.A blank sample was used as the substrate for the spike recovery test. The recovery rate was in the range of 90. 0%-98. 0%,and the relative standard deviation( RSD) of the measured values( n = 6) was in the range of 2. 1%-7. 3%. [Conclusions]The method established in this experiment has the benefits of simple pretreatment,good recovery,high sensitivity and strong specificity,and is expected to provide an ideal method for the determination of such drugs in blood.展开更多
The performance of deep learning models is heavily reliant on the quality and quantity of train-ing data.Insufficient training data will lead to overfitting.However,in the task of alert-situation text classification,i...The performance of deep learning models is heavily reliant on the quality and quantity of train-ing data.Insufficient training data will lead to overfitting.However,in the task of alert-situation text classification,it is usually difficult to obtain a large amount of training data.This paper proposes a text data augmentation method based on masked language model(MLM),aiming to enhance the generalization capability of deep learning models by expanding the training data.The method em-ploys a Mask strategy to randomly conceal words in the text,effectively leveraging contextual infor-mation to predict and replace masked words based on MLM,thereby generating new training data.Three Mask strategies of character level,word level and N-gram are designed,and the performance of each Mask strategy under different Mask ratios is analyzed and studied.The experimental results show that the performance of the word-level Mask strategy is better than the traditional data augmen-tation method.展开更多
In this paper,a prediction model is developed that combines a Gaussian mixture model(GMM) and a Kalman filter for online forecasting of traffic safety on expressways.Raw time-to-collision(TTC) samples are divided into...In this paper,a prediction model is developed that combines a Gaussian mixture model(GMM) and a Kalman filter for online forecasting of traffic safety on expressways.Raw time-to-collision(TTC) samples are divided into two categories:those representing vehicles in risky situations and those in safe situations.Then,the GMM is used to model the bimodal distribution of the TTC samples,and the maximum likelihood(ML) estimation parameters of the TTC distribution are obtained using the expectation-maximization(EM) algorithm.We propose a new traffic safety indicator,named the proportion of exposure to traffic conflicts(PETTC),for assessing the risk and predicting the safety of expressway traffic.A Kalman filter is applied to forecast the short-term safety indicator,PETTC,and solves the online safety prediction problem.A dataset collected from four different expressway locations is used for performance estimation.The test results demonstrate the precision and robustness of the prediction model under different traffic conditions and using different datasets.These results could help decision-makers to improve their online traffic safety forecasting and enable the optimal operation of expressway traffic management systems.展开更多
Most entity ranking research aims to retrieve a ranked list of entities from a Web corpus given a user query. The rank order of entities is determined by the relevance between the query and contexts of entities. Howev...Most entity ranking research aims to retrieve a ranked list of entities from a Web corpus given a user query. The rank order of entities is determined by the relevance between the query and contexts of entities. However, entities can be ranked directly based on their relative importance in a document collection, independent of any queries. In this paper, we introduce an entity ranking algorithm named NERank+. Given a document collection, NERank+ first constructs a graph model called Topical Tripartite Graph, consisting of document, topic and entity nodes. We design separate ranking functions to compute the prior ranks of entities and topics, respectively. A meta-path constrained random walk algorithm is proposed to propagate prior entity and topic ranks based on the graph model. We evaluate NERank+ over real-life datasets and compare it with baselines. Experimental results illustrate the effectiveness of our approach.展开更多
To investigate the effect of tunnel slope on hot gas movement and smoke distribution in a slopping tunnel fire,a series of tunnel fire models are built by fire dynamics simulator(FDS),with a slope varies from 0 to 10%...To investigate the effect of tunnel slope on hot gas movement and smoke distribution in a slopping tunnel fire,a series of tunnel fire models are built by fire dynamics simulator(FDS),with a slope varies from 0 to 10%.Parameters such as ceiling temperature and airflow velocity are measured.The results indicate that the relationship between smoke back-layering length and tunnel slope can be described as an exponential function.The smoke temperature at the downstream exit first increased and then decreased with a higher slope.The airflow velocity at downstream outlet increased nonlinearity when tunnel slope was less than 8%.In the slope tunnel,the fire smoke spread process can be divided into three stages.Fire smoke spreads upstream to the peak distance,subsequently,the upstream smoke layer decreases gradually,the tunnel fire reaches a quasi-steady state.The backflow characteristics of smoke in sloped tunnels are coupled with the downstream length and outlet smoke temperature.In the initial stage of a slope tunnel fire,smoke spreads upstream for a long distance,endangering human health.展开更多
文摘BACKGROUND The teaching mode of fitness exercise prescriptions for college students in physical education conforms to the scientific principles and rules of fitness,which can adapt to the characteristics of students’individual physiological functions and stimulate their interest in learning.AIM To analyze the effect of prescribed exercise teaching on the sports quality and mental health of college students.METHODS The participants of the study were 240 students in our class of 2021,of which 142 were men and 98 were women.The 240 students were randomly divided into an experimental group using the exercise prescription teaching model and a control group using the conventional teaching model.The experimental and control groups were divided into four classes of 30 students each.The teaching activities of the two teaching mode groups were strictly controlled,and the same tests were used before and after the experiment to test the subjects’exercise quality(including standing long jump,50 m race,800 m race,sit-ups,sit-and-reach),physical form(including height,weight,Ketorolai index),cardiopulmonary function(including heart rate,blood pressure,spirometry,12-min running distance,maximum oxygen intake)and mental health(SCL-90,including somatization,obsessive-compulsive,interpersonal,depression,anxiety,hostility,phobia,paranoia,psychotic symptoms)to understand the effects of the exercise prescription teaching mode on students’physical and mental health status.RESULTS There were differences in the exercise scores of standing long jump,50 m,800 m/1000 m running,sit-ups,and sit-and-reach in the experimental group after the experiment compared with those before the experiment,and the above indices of the experimental group were different from those of the control group after the experiment(P<0.05).There were differences in body weight and Ketorolai index in the experimental group after the experiment compared to those before the experiment,and the indices of the experimental group were also different from those of the control group after the experiment(P<0.05).After the experiment,there were differences in spirometry,12-min running distance,and maximum oxygen intake in the experimental group compared to those before the experiment,and the indices of the experimental group were also different from those of the control group after the experiment(P<0.05).After the experiment,the indicators of somatization,interpersonal sensitivity,depression,anxiety,and hostility in the experimental group were different from those in the pre-experimental group,and the indexes of the experimental group were also different from those of the control group after the experiment(P<0.05).CONCLUSION Exercise prescription teaching can mobilize college students’consciousness,enthusiasm,and initiative;expand personalities;enhance physical fitness and improve their mental health more than the conventional fitness exercise prescription teaching method.
基金supported by the National Social Science Fund of China(23BGL272)。
文摘The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.
基金This work was funded by the National Natural Science Foundation of China(Grant No.62172132)Public Welfare Technology Research Project of Zhejiang Province(Grant No.LGF21F020014)the Opening Project of Key Laboratory of Public Security Information Application Based on Big-Data Architecture,Ministry of Public Security of Zhejiang Police College(Grant No.2021DSJSYS002).
文摘The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.
基金supported in part by the Basic Public Welfare Research Program of Zhejiang Province under Grant LGF20G030001.
文摘The network is a major platform for implementing new cyber-telecom crimes.Therefore,it is important to carry out monitoring and early warning research on new cyber-telecom crime platforms,which will lay the foundation for the establishment of prevention and control systems to protect citizens’property.However,the deep-learning methods applied in the monitoring and early warning of new cyber-telecom crime platforms have some apparent drawbacks.For instance,the methods suffer from data-distribution differences and tremendous manual efforts spent on data labeling.Therefore,a monitoring and early warning method for new cyber-telecom crime platforms based on the BERT migration learning model is proposed.This method first identifies the text data and their tags,and then performs migration training based on a pre-training model.Finally,the method uses the fine-tuned model to predict and classify new cyber-telecom crimes.Experimental analysis on the crime data collected by public security organizations shows that higher classification accuracy can be achieved using the proposed method,compared with the deep-learning method.
基金supported in part by National Natural Science Foundation of China (NSFC) under Grant U1509219 and 2017YFB0802900
文摘A Service Level Agreement(SLA) is a legal contract between any two parties to ensure an adequate Quality of Service(Qo S). Most research on SLAs has concentrated on protecting the user data through encryption. However, these methods can not supervise a cloud service provider(CSP) directly. In order to address this problem, we propose a privacy-based SLA violation detection model for cloud computing based on Markov decision process theory. This model can recognize and regulate CSP's actions based on specific requirements of various users. Additionally, the model could make effective evaluation to the credibility of CSP, and can monitor events that user privacy is violated. Experiments and analysis indicate that the violation detection model can achieve good results in both the algorithm's convergence and prediction effect.
基金supported in part by the Basic Public Welfare Research Program of Zhejiang Province under Grant LGF19F020006 LGF20G030001 GF20G030006the NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization under Grant U1509219。
文摘In order to solve the problems of data sharing security and policy conflict in multicloud storage systems(MCSS), this work designs an attribute mapping mechanism that extends ciphertext policy attribute-based encryption(CP-ABE), and proposes a multi-authority CP-ABE access control model that satisfies the need for multicloud storage access control. The mapping mechanism mainly involves the tree structure of CP-ABE and provides support for the types of attribute values. The framework and workflow of the model are described in detail. The effectiveness of the model is verified by building a simple prototype system, and the performance of the prototype system is analyzed. The results suggest that the proposed model is of theoretical and practical significance for access control research in MCSS. The CP-ABE has better performance in terms of computation time overhead than other models.
基金supported by the Jiangsu Provincial Natural Science Foundation of China(no.BK20150721)the 2017 National Key Research and Development Program of China(no.2017YFB0802900)
文摘Attack surfaces, as one of the security models, can help people to analyse the security of systems in cyberspace, such as risk assessment by utilizing various security metrics or providing a cost-effective network hardening solution. Numerous attack surface models have been proposed in the past decade,but they are not appropriate for describing complex systems with heterogeneous components. To address this limitation, we propose to use a two-layer Hierarchical Attack Surface Network(HASN) that models the data interactions and resource distribution of the system in a component-oriented view. First, we formally define the HASN by extending the entry point and exit point framework. Second, in order to assess data input risk and output risk on the HASN, we propose two behaviour models and two simulation-based risk metrics. Last, we conduct experiments for three network systems. Our experimental results show that the proposed approach is applicable and effective.
基金supported by the National Natural Science Foundation of China(61202369)the NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization(U1509219)
基金This work was mainly supported by Public Welfare Technology and Industry Project of Zhejiang Provincial Science Technology Department.(No.LGG18F020013,No.LGG19F020016,LGF21F020006).
文摘As an efficient technique for anti-counterfeiting,holographic diffraction labels has been widely applied to various fields.Due to their unique feature,traditional image recognition algorithms are not ideal for the holographic diffraction label recognition.Since a tensor preserves the spatiotemporal features of an original sample in the process of feature extraction,in this paper we propose a new holographic diffraction label recognition algorithm that combines two tensor features.The HSV(Hue Saturation Value)tensor and the HOG(Histogram of Oriented Gradient)tensor are used to represent the color information and gradient information of holographic diffraction label,respectively.Meanwhile,the tensor decomposition is performed by high order singular value decomposition,and tensor decomposition matrices are obtained.Taking into consideration of the different recognition capabilities of decomposition matrices,we design a decomposition matrix similarity fusion strategy using a typical correlation analysis algorithm and projection from similarity vectors of different decomposition matrices to the PCA(Principal Component Analysis)sub-space,then,the sub-space performs KNN(K-Nearest Neighbors)classification is performed.The effectiveness of our fusion strategy is verified by experiments.Our double tensor recognition algorithm complements the recognition capability of different tensors to produce better recognition performance for the holographic diffraction label system.
基金supported by Zhejiang Provincial Natural Science Foundation of China(Grant No.LGF20G030001)Ministry of Public Security Science and Technology Plan Project(2022LL16)Key scientific research projects of agricultural and social development in Hangzhou in 2020(202004A06).
文摘The feature analysis of fraudulent websites is of great significance to the combat,prevention and control of telecom fraud crimes.Aiming to address the shortcomings of existing analytical approaches,i.e.single dimension and venerability to anti-reconnaissance,this paper adopts the Stacking,the ensemble learning algorithm,combines multiple modalities such as text,image and URL,and proposes a multimodal fraudulent website identification method by ensembling heterogeneous models.Crossvalidation is first used in the training of multiple largely different base classifiers that are strong in learning,such as BERT model,residual neural network(ResNet)and logistic regression model.Classification of the text,image and URL features are then performed respectively.The results of the base classifiers are taken as the input of the meta-classifier,and the output of which is eventually used as the final identification.The study indicates that the fusion method is more effective in identifying fraudulent websites than the single-modal method,and the recall is increased by at least 1%.In addition,the deployment of the algorithm to the real Internet environment shows the improvement of the identification accuracy by at least 1.9%compared with other fusion methods.
基金support of the Science&Technology Development Project of Hangzhou Province,China(Grant No.20162013A08)the Research Project Support for Education of Zhejiang Province,China(Grant No.Y201941372)。
文摘Text analysis is a popular technique for finding the most significant information from texts including semantic,emotional,and other hidden features,which became a research hotspot in the last few years.Specially,there are some text analysis tasks with judgment reports,such as analyzing the criminal process and predicting prison terms.Traditional researches on text analysis are generally based on special feature selection and ontology model generation or require legal experts to provide external knowledge.All these methods require a lot of time and labor costs.Therefore,in this paper,we use textual data such as judgment reports creatively to perform prison term prediction without external legal knowledge.We propose a framework that combines value-based rules and a fuzzy text to predict the target prison term.The procedure in our framework includes information extraction,term fuzzification,and document vector regression.We carry out experiments with real-world judgment reports and compare our model’s performance with those of ten traditional classification and regression models and two deep learning models.The results show that our model achieves competitive results compared with other models as evaluated by the RMSE and R-squared metrics.Finally,we implement a prototype system with a user-friendly GUI that can be used to predict prison terms according to the legal text inputted by the user.
基金supported by the National Natural Science Foundation of China (Grant Nos.29975024, 20275034)the Key Project of Science and Technology of Zhejiang Province (Grant Nos.2003C21024, Y4080223)
文摘Platinum-decorated carbon nanotubes (CNT-Pt) were produced by the chemical reduction method. A novel modified electrode was fabricated by intercalated CNT-Pt in the surface of waxed graphite, which provided excellent electrocatalytic activity and selectivity for both oxidation and reduction of hydrogen peroxide. The current response of the modified electrode for hydrogen peroxide was very rapid and the detection limits in amperometry are 2.5×10^-6 mol/L at reduction potential and 4.8×10^-6 mol/L at oxidation potential. It was desmonstrated that the electrode with high electro-activity was a suitable basic electrode for preparing enzyme electrode.
基金funded by the Public Welfare Technology Research Project of Zhejiang Province(Grant No.LGF21F020014)the Opening Project ofKey Laboratory of Public Security Information Application Based on Big-Data Architecture,Ministry of Public Security of Zhejiang Police College(Grant No.2021DSJSYS002).
文摘Ceramic tiles are one of the most indispensable materials for interior decoration.The ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural textures.In this paper,we propose a sketch-based generation method for generating diverse ceramic tile images based on a hand-drawn sketches using Generative Adversarial Network(GAN).The generated tile images can be tailored to meet the specific needs of the user for the tile textures.The proposed method consists of four steps.Firstly,a dataset of ceramic tile images with diverse distributions is created and then pre-trained based on GAN.Secondly,for each ceramic tile image in the dataset,the corresponding sketch image is generated and then the mapping relationship between the images is trained based on a sketch extraction network using ResNet Block and jump connection to improve the quality of the generated sketches.Thirdly,the sketch style is redefined according to the characteristics of the ceramic tile images and then double cross-domain adversarial loss functions are employed to guide the ceramic tile generation network for fitting in the direction of the sketch style and to improve the training speed.Finally,we apply hidden space perturbation and interpolation for further enriching the output textures style and satisfying the concept of“one style with multiple faces”.We conduct the training process of the proposed generation network on 2583 ceramic tile images dataset.To measure the generative diversity and quality,we use Frechet Inception Distance(FID)and Blind/Referenceless Image Spatial Quality Evaluator(BRISQUE)metrics.The experimental results prove that the proposed model greatly enhances the generation results of the ceramic tile images,with FID of 32.47 and BRISQUE of 28.44.
基金This work is supported by the National Natural Science Foundation of China under grant,62102189,U1936118,U1836208,U1836110,62122032by the Jiangsu Basic Research Programs-Natural Science Foundation under grant BK20200807+1 种基金by the Key Laboratory of Public Security Information Application Based on Big-Data Architecture,Ministry of Public Security(2021DSJSYS006)by the Research Startup Foundation of NUIST 2020r15.
文摘Fingerprint identification systems have been widely deployed in many occasions of our daily life.However,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit fingerprints.To address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s attention.The vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model generalization.Aiming at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint detection.Next,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection model.Finally,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and cross-sensor.The size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.
基金Supported by Project of National Natural Science Foundation(81273346)
文摘[Objectives]To optimize the determination method of oleandrin and adynerin in blood. [Methods]High performance liquid chromatography-mass spectrometry( HPLC-MS/MS) was applied to determine oleandrin and adynerin in blood. The blood sample was dispersed and fixed on a solid phase supported liquid-liquid extraction column and eluted with ethyl acetate. The resulting eluent was used for chromatographic separation with Kinetex C_(18) column as the separation column and gradient elution was performed using 10 mmol/L ammonium formate solution containing 0. 1%( volume fraction) formic acid and acetonitrile as the mobile phase. In the tandem mass spectrometry analysis,the detection was carried out using the electrospray positive ion source multiple reaction monitoring mode. [Results] The mass concentration of oleandrin and adynerin showed linear relationship in the range of 2-100 μg/L. The limit of detection( 3 S/N) of the method was 0. 5 μg/L.A blank sample was used as the substrate for the spike recovery test. The recovery rate was in the range of 90. 0%-98. 0%,and the relative standard deviation( RSD) of the measured values( n = 6) was in the range of 2. 1%-7. 3%. [Conclusions]The method established in this experiment has the benefits of simple pretreatment,good recovery,high sensitivity and strong specificity,and is expected to provide an ideal method for the determination of such drugs in blood.
基金Supported by the Humanities and Social Sciences Research Project of the Ministry of Education(No.22YJA840004).
文摘The performance of deep learning models is heavily reliant on the quality and quantity of train-ing data.Insufficient training data will lead to overfitting.However,in the task of alert-situation text classification,it is usually difficult to obtain a large amount of training data.This paper proposes a text data augmentation method based on masked language model(MLM),aiming to enhance the generalization capability of deep learning models by expanding the training data.The method em-ploys a Mask strategy to randomly conceal words in the text,effectively leveraging contextual infor-mation to predict and replace masked words based on MLM,thereby generating new training data.Three Mask strategies of character level,word level and N-gram are designed,and the performance of each Mask strategy under different Mask ratios is analyzed and studied.The experimental results show that the performance of the word-level Mask strategy is better than the traditional data augmen-tation method.
基金Project (No. 2011AA110304) supported by the National High-Tech R&D Program of China (863 program)
文摘In this paper,a prediction model is developed that combines a Gaussian mixture model(GMM) and a Kalman filter for online forecasting of traffic safety on expressways.Raw time-to-collision(TTC) samples are divided into two categories:those representing vehicles in risky situations and those in safe situations.Then,the GMM is used to model the bimodal distribution of the TTC samples,and the maximum likelihood(ML) estimation parameters of the TTC distribution are obtained using the expectation-maximization(EM) algorithm.We propose a new traffic safety indicator,named the proportion of exposure to traffic conflicts(PETTC),for assessing the risk and predicting the safety of expressway traffic.A Kalman filter is applied to forecast the short-term safety indicator,PETTC,and solves the online safety prediction problem.A dataset collected from four different expressway locations is used for performance estimation.The test results demonstrate the precision and robustness of the prediction model under different traffic conditions and using different datasets.These results could help decision-makers to improve their online traffic safety forecasting and enable the optimal operation of expressway traffic management systems.
文摘Most entity ranking research aims to retrieve a ranked list of entities from a Web corpus given a user query. The rank order of entities is determined by the relevance between the query and contexts of entities. However, entities can be ranked directly based on their relative importance in a document collection, independent of any queries. In this paper, we introduce an entity ranking algorithm named NERank+. Given a document collection, NERank+ first constructs a graph model called Topical Tripartite Graph, consisting of document, topic and entity nodes. We design separate ranking functions to compute the prior ranks of entities and topics, respectively. A meta-path constrained random walk algorithm is proposed to propagate prior entity and topic ranks based on the graph model. We evaluate NERank+ over real-life datasets and compare it with baselines. Experimental results illustrate the effectiveness of our approach.
基金National Nature Science Funds of China[No.52106185]Fellowship of China Postdoctoral Science Founda-tion[No.2021M693042].
文摘To investigate the effect of tunnel slope on hot gas movement and smoke distribution in a slopping tunnel fire,a series of tunnel fire models are built by fire dynamics simulator(FDS),with a slope varies from 0 to 10%.Parameters such as ceiling temperature and airflow velocity are measured.The results indicate that the relationship between smoke back-layering length and tunnel slope can be described as an exponential function.The smoke temperature at the downstream exit first increased and then decreased with a higher slope.The airflow velocity at downstream outlet increased nonlinearity when tunnel slope was less than 8%.In the slope tunnel,the fire smoke spread process can be divided into three stages.Fire smoke spreads upstream to the peak distance,subsequently,the upstream smoke layer decreases gradually,the tunnel fire reaches a quasi-steady state.The backflow characteristics of smoke in sloped tunnels are coupled with the downstream length and outlet smoke temperature.In the initial stage of a slope tunnel fire,smoke spreads upstream for a long distance,endangering human health.