- Yijing Chen;Bo Pang;Guolin Shao;Guozhu Wen;Xingshu Chen;
Botnets based on the Domain Generation Algorithm(DGA) mechanism pose great challenges to the main current detection methods because of their strong concealment and robustness. However, the complexity of the DGA family and the imbalance of samples continue to impede research on DGA detection. In the existing work, the sample size of each DGA family is regarded as the most important determinant of the resampling proportion; thus,differences in the characteristics of various samples are ignored, and the optimal resampling effect is not achieved.In this paper, a Long Short-Term Memory-based Property and Quantity Dependent Optimization(LSTM.PQDO)method is proposed. This method takes advantage of LSTM to automatically mine the comprehensive features of DGA domain names. It iterates the resampling proportion with the optimal solution based on a comprehensive consideration of the original number and characteristics of the samples to heuristically search for a better solution around the initial solution in the right direction; thus, dynamic optimization of the resampling proportion is realized.The experimental results show that the LSTM.PQDO method can achieve better performance compared with existing models to overcome the difficulties of unbalanced datasets; moreover, it can function as a reference for sample resampling tasks in similar scenarios.
2021年04期 v.26 387-402页 [查看摘要][在线阅读][下载 2064K] [下载次数：76 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：1 ] - Yijing Chen;Bo Pang;Guolin Shao;Guozhu Wen;Xingshu Chen;
Botnets based on the Domain Generation Algorithm(DGA) mechanism pose great challenges to the main current detection methods because of their strong concealment and robustness. However, the complexity of the DGA family and the imbalance of samples continue to impede research on DGA detection. In the existing work, the sample size of each DGA family is regarded as the most important determinant of the resampling proportion; thus,differences in the characteristics of various samples are ignored, and the optimal resampling effect is not achieved.In this paper, a Long Short-Term Memory-based Property and Quantity Dependent Optimization(LSTM.PQDO)method is proposed. This method takes advantage of LSTM to automatically mine the comprehensive features of DGA domain names. It iterates the resampling proportion with the optimal solution based on a comprehensive consideration of the original number and characteristics of the samples to heuristically search for a better solution around the initial solution in the right direction; thus, dynamic optimization of the resampling proportion is realized.The experimental results show that the LSTM.PQDO method can achieve better performance compared with existing models to overcome the difficulties of unbalanced datasets; moreover, it can function as a reference for sample resampling tasks in similar scenarios.
2021年04期 v.26 387-402页 [查看摘要][在线阅读][下载 2064K] [下载次数：76 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：0 ] - Yijing Chen;Bo Pang;Guolin Shao;Guozhu Wen;Xingshu Chen;
Botnets based on the Domain Generation Algorithm(DGA) mechanism pose great challenges to the main current detection methods because of their strong concealment and robustness. However, the complexity of the DGA family and the imbalance of samples continue to impede research on DGA detection. In the existing work, the sample size of each DGA family is regarded as the most important determinant of the resampling proportion; thus,differences in the characteristics of various samples are ignored, and the optimal resampling effect is not achieved.In this paper, a Long Short-Term Memory-based Property and Quantity Dependent Optimization(LSTM.PQDO)method is proposed. This method takes advantage of LSTM to automatically mine the comprehensive features of DGA domain names. It iterates the resampling proportion with the optimal solution based on a comprehensive consideration of the original number and characteristics of the samples to heuristically search for a better solution around the initial solution in the right direction; thus, dynamic optimization of the resampling proportion is realized.The experimental results show that the LSTM.PQDO method can achieve better performance compared with existing models to overcome the difficulties of unbalanced datasets; moreover, it can function as a reference for sample resampling tasks in similar scenarios.
2021年04期 v.26 387-402页 [查看摘要][在线阅读][下载 2064K] [下载次数：76 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：0 ] - Ji Li;Xin Pei;Xuejiao Wang;Danya Yao;Yi Zhang;Yun Yue;
Global Positioning System(GPS) trajectory data can be used to infer transportation modes at certain times and locations. Such data have important applications in many transportation research fields, for instance,to detect the movement mode of travelers, calculate traffic flow in an area, and predict the traffic flow at a certain time in the future. In this paper, we propose a novel method to infer transportation modes from GPS trajectory data and Geographic Information System(GIS) information. This method is based on feature extraction and machine learning classification algorithms. While using GIS information to improve inference accuracy, we ensure that the algorithm is simple and easy to use on mobile devices. Applied to GeoLife GPS trajectory dataset, our method achieves 91.1% accuracy while inferring transportation modes, such as walking, bike, bus, car, and subway, with random forest classification algorithm. GIS features in our method improved the overall accuracy by 2.5% while raising the recall of the bus and subway transportation mode categories by 3.4% and 18.5%. We believe that many algorithms used in detecting the transportation modes from GPS trajectory data that do not utilize GIS information can improve their inference accuracy by using our GIS features, with a slight increase in the consumption of data storage and computing resources.
2021年04期 v.26 403-416页 [查看摘要][在线阅读][下载 4031K] [下载次数：157 ] |[网刊下载次数：0 ] |[引用频次：19 ] |[阅读次数：0 ] - Ji Li;Xin Pei;Xuejiao Wang;Danya Yao;Yi Zhang;Yun Yue;
Global Positioning System(GPS) trajectory data can be used to infer transportation modes at certain times and locations. Such data have important applications in many transportation research fields, for instance,to detect the movement mode of travelers, calculate traffic flow in an area, and predict the traffic flow at a certain time in the future. In this paper, we propose a novel method to infer transportation modes from GPS trajectory data and Geographic Information System(GIS) information. This method is based on feature extraction and machine learning classification algorithms. While using GIS information to improve inference accuracy, we ensure that the algorithm is simple and easy to use on mobile devices. Applied to GeoLife GPS trajectory dataset, our method achieves 91.1% accuracy while inferring transportation modes, such as walking, bike, bus, car, and subway, with random forest classification algorithm. GIS features in our method improved the overall accuracy by 2.5% while raising the recall of the bus and subway transportation mode categories by 3.4% and 18.5%. We believe that many algorithms used in detecting the transportation modes from GPS trajectory data that do not utilize GIS information can improve their inference accuracy by using our GIS features, with a slight increase in the consumption of data storage and computing resources.
2021年04期 v.26 403-416页 [查看摘要][在线阅读][下载 4031K] [下载次数：157 ] |[网刊下载次数：0 ] |[引用频次：19 ] |[阅读次数：0 ] - Ji Li;Xin Pei;Xuejiao Wang;Danya Yao;Yi Zhang;Yun Yue;
Global Positioning System(GPS) trajectory data can be used to infer transportation modes at certain times and locations. Such data have important applications in many transportation research fields, for instance,to detect the movement mode of travelers, calculate traffic flow in an area, and predict the traffic flow at a certain time in the future. In this paper, we propose a novel method to infer transportation modes from GPS trajectory data and Geographic Information System(GIS) information. This method is based on feature extraction and machine learning classification algorithms. While using GIS information to improve inference accuracy, we ensure that the algorithm is simple and easy to use on mobile devices. Applied to GeoLife GPS trajectory dataset, our method achieves 91.1% accuracy while inferring transportation modes, such as walking, bike, bus, car, and subway, with random forest classification algorithm. GIS features in our method improved the overall accuracy by 2.5% while raising the recall of the bus and subway transportation mode categories by 3.4% and 18.5%. We believe that many algorithms used in detecting the transportation modes from GPS trajectory data that do not utilize GIS information can improve their inference accuracy by using our GIS features, with a slight increase in the consumption of data storage and computing resources.
2021年04期 v.26 403-416页 [查看摘要][在线阅读][下载 4031K] [下载次数：157 ] |[网刊下载次数：0 ] |[引用频次：19 ] |[阅读次数：0 ] - Liping Wang;Wenhui Fan;
To reduce intermediate levels of splitting process and enhance sampling accuracy, a multilevel splitting algorithm for quick sampling is proposed in this paper. Firstly, the selected area of the elite set is expanded to maintain the diversity of the samples. Secondly, the combined use of an adaptive difference evolution algorithm and a local searching algorithm is proposed for the splitting procedure. Finally, a suite of benchmark functions are used for performance testing. The results indicate that the convergence rate and stability of this algorithm are superior to those of the classical importance splitting algorithm and an adaptive multilevel splitting algorithm.
2021年04期 v.26 417-425页 [查看摘要][在线阅读][下载 521K] [下载次数：22 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Liping Wang;Wenhui Fan;
To reduce intermediate levels of splitting process and enhance sampling accuracy, a multilevel splitting algorithm for quick sampling is proposed in this paper. Firstly, the selected area of the elite set is expanded to maintain the diversity of the samples. Secondly, the combined use of an adaptive difference evolution algorithm and a local searching algorithm is proposed for the splitting procedure. Finally, a suite of benchmark functions are used for performance testing. The results indicate that the convergence rate and stability of this algorithm are superior to those of the classical importance splitting algorithm and an adaptive multilevel splitting algorithm.
2021年04期 v.26 417-425页 [查看摘要][在线阅读][下载 521K] [下载次数：22 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Liping Wang;Wenhui Fan;
To reduce intermediate levels of splitting process and enhance sampling accuracy, a multilevel splitting algorithm for quick sampling is proposed in this paper. Firstly, the selected area of the elite set is expanded to maintain the diversity of the samples. Secondly, the combined use of an adaptive difference evolution algorithm and a local searching algorithm is proposed for the splitting procedure. Finally, a suite of benchmark functions are used for performance testing. The results indicate that the convergence rate and stability of this algorithm are superior to those of the classical importance splitting algorithm and an adaptive multilevel splitting algorithm.
2021年04期 v.26 417-425页 [查看摘要][在线阅读][下载 521K] [下载次数：22 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Xuesong Li;Fengyuan Ren;Bailong Yang;
Recently, 10 Gbps or higher speed links are being widely deployed in data centers. Novel high-speed packet I/O frameworks have emerged to keep pace with such high-speed links. These frameworks mainly use techniques, such as memory preallocation, busy polling, zero copy, and batch processing, to replace costly operations(e.g., interrupts, packet copy, and system call) in native OS kernel stack. For high-speed packet I/O frameworks,costs per packet, saturation throughput, and latency are performance metrics that are of utmost concern, and various factors have an effect on these metrics. To acquire a comprehensive understanding of high-speed packet I/O, we propose an analytical model to formulate its packet forwarding(receiving–processing–sending) flow. Our model takes the four main techniques adopted by the frameworks into consideration, and the concerned performance metrics are derived from it. The validity and correctness of our model are verified by real system experiments. Moreover, we explore how each factor impacts the three metrics through a model analysis and then provide several useful insights and suggestions for performance tuning.
2021年04期 v.26 426-439页 [查看摘要][在线阅读][下载 1146K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Xuesong Li;Fengyuan Ren;Bailong Yang;
Recently, 10 Gbps or higher speed links are being widely deployed in data centers. Novel high-speed packet I/O frameworks have emerged to keep pace with such high-speed links. These frameworks mainly use techniques, such as memory preallocation, busy polling, zero copy, and batch processing, to replace costly operations(e.g., interrupts, packet copy, and system call) in native OS kernel stack. For high-speed packet I/O frameworks,costs per packet, saturation throughput, and latency are performance metrics that are of utmost concern, and various factors have an effect on these metrics. To acquire a comprehensive understanding of high-speed packet I/O, we propose an analytical model to formulate its packet forwarding(receiving–processing–sending) flow. Our model takes the four main techniques adopted by the frameworks into consideration, and the concerned performance metrics are derived from it. The validity and correctness of our model are verified by real system experiments. Moreover, we explore how each factor impacts the three metrics through a model analysis and then provide several useful insights and suggestions for performance tuning.
2021年04期 v.26 426-439页 [查看摘要][在线阅读][下载 1146K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Xuesong Li;Fengyuan Ren;Bailong Yang;
Recently, 10 Gbps or higher speed links are being widely deployed in data centers. Novel high-speed packet I/O frameworks have emerged to keep pace with such high-speed links. These frameworks mainly use techniques, such as memory preallocation, busy polling, zero copy, and batch processing, to replace costly operations(e.g., interrupts, packet copy, and system call) in native OS kernel stack. For high-speed packet I/O frameworks,costs per packet, saturation throughput, and latency are performance metrics that are of utmost concern, and various factors have an effect on these metrics. To acquire a comprehensive understanding of high-speed packet I/O, we propose an analytical model to formulate its packet forwarding(receiving–processing–sending) flow. Our model takes the four main techniques adopted by the frameworks into consideration, and the concerned performance metrics are derived from it. The validity and correctness of our model are verified by real system experiments. Moreover, we explore how each factor impacts the three metrics through a model analysis and then provide several useful insights and suggestions for performance tuning.
2021年04期 v.26 426-439页 [查看摘要][在线阅读][下载 1146K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Hongma Liu;Yali Li;Shengjin Wang;
A Brain-Computer Interface(BCI) aims to produce a new way for people to communicate with computers.Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio(SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition Ⅲ Dataset Ⅱ.
2021年04期 v.26 440-451页 [查看摘要][在线阅读][下载 1746K] [下载次数：31 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Hongma Liu;Yali Li;Shengjin Wang;
A Brain-Computer Interface(BCI) aims to produce a new way for people to communicate with computers.Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio(SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition Ⅲ Dataset Ⅱ.
2021年04期 v.26 440-451页 [查看摘要][在线阅读][下载 1746K] [下载次数：31 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Hongma Liu;Yali Li;Shengjin Wang;
A Brain-Computer Interface(BCI) aims to produce a new way for people to communicate with computers.Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio(SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition Ⅲ Dataset Ⅱ.
2021年04期 v.26 440-451页 [查看摘要][在线阅读][下载 1746K] [下载次数：31 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Xiaohe Hu;Yang Xiang;Yifan Li;Buyi Qiu;Kai Wang;Jun Li;
Network monitoring is receiving more attention than ever with the need for a self-driving network to tackle increasingly severe network management challenges. Advanced management applications rely on traffic data analyses, which require network monitoring to flexibly provide comprehensive traffic characteristics. Moreover, in virtualized environments, software network monitoring is constrained by available resources and requirements of cloud operators. In this paper, Trident, a policy-based network monitoring system at the host, is proposed. Trident is a novel monitoring approach, off-path configurable streaming, which offers remote analyzers a fine-grained holistic view of the network traffic. A novel fast path packet classification algorithm and a corresponding cached flow form are also proposed to improve monitoring efficiency. Evaluated in a practical deployment, Trident demonstrates negligible interference with forwarding and requires no additional software dependencies. Trident has been deployed in production networks of several Tier-IV datacenters.
2021年04期 v.26 452-463页 [查看摘要][在线阅读][下载 9513K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Xiaohe Hu;Yang Xiang;Yifan Li;Buyi Qiu;Kai Wang;Jun Li;
Network monitoring is receiving more attention than ever with the need for a self-driving network to tackle increasingly severe network management challenges. Advanced management applications rely on traffic data analyses, which require network monitoring to flexibly provide comprehensive traffic characteristics. Moreover, in virtualized environments, software network monitoring is constrained by available resources and requirements of cloud operators. In this paper, Trident, a policy-based network monitoring system at the host, is proposed. Trident is a novel monitoring approach, off-path configurable streaming, which offers remote analyzers a fine-grained holistic view of the network traffic. A novel fast path packet classification algorithm and a corresponding cached flow form are also proposed to improve monitoring efficiency. Evaluated in a practical deployment, Trident demonstrates negligible interference with forwarding and requires no additional software dependencies. Trident has been deployed in production networks of several Tier-IV datacenters.
2021年04期 v.26 452-463页 [查看摘要][在线阅读][下载 9513K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Xiaohe Hu;Yang Xiang;Yifan Li;Buyi Qiu;Kai Wang;Jun Li;
Network monitoring is receiving more attention than ever with the need for a self-driving network to tackle increasingly severe network management challenges. Advanced management applications rely on traffic data analyses, which require network monitoring to flexibly provide comprehensive traffic characteristics. Moreover, in virtualized environments, software network monitoring is constrained by available resources and requirements of cloud operators. In this paper, Trident, a policy-based network monitoring system at the host, is proposed. Trident is a novel monitoring approach, off-path configurable streaming, which offers remote analyzers a fine-grained holistic view of the network traffic. A novel fast path packet classification algorithm and a corresponding cached flow form are also proposed to improve monitoring efficiency. Evaluated in a practical deployment, Trident demonstrates negligible interference with forwarding and requires no additional software dependencies. Trident has been deployed in production networks of several Tier-IV datacenters.
2021年04期 v.26 452-463页 [查看摘要][在线阅读][下载 9513K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Jian Guo;Hong Liang;Songpu Ai;Chao Lu;Haochen Hua;Junwei Cao;
Electrical power network analysis and computation play an important role in the planning and operation of the power grid, and they are modeled mathematically as differential equations and network algebraic equations.The direct method based on Gaussian elimination theory can obtain analytical results. Two factors affect computing efficiency: the number of nonzero element fillings and the length of elimination tree. This article constructs mapping correspondence between eliminated tree nodes and quotient graph nodes through graph and quotient graph theories.The Approximate Minimum Degree(AMD) of quotient graph nodes and the length of the elimination tree nodes are composed to build an Approximate Minimum Degree and Minimum Length(AMDML) model. The quotient graph node with the minimum degree, which is also the minimum length of elimination tree node, is selected as the next ordering vector. Compared with AMD ordering method and other common methods, the proposed method further reduces the length of elimination tree without increasing the number of nonzero fillings; the length was decreased by about 10% compared with the AMD method. A testbed for experiment was built. The efficiency of the proposed method was evaluated based on different sizes of coefficient matrices of power flow cases.
2021年04期 v.26 464-474页 [查看摘要][在线阅读][下载 2018K] [下载次数：27 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Jian Guo;Hong Liang;Songpu Ai;Chao Lu;Haochen Hua;Junwei Cao;
Electrical power network analysis and computation play an important role in the planning and operation of the power grid, and they are modeled mathematically as differential equations and network algebraic equations.The direct method based on Gaussian elimination theory can obtain analytical results. Two factors affect computing efficiency: the number of nonzero element fillings and the length of elimination tree. This article constructs mapping correspondence between eliminated tree nodes and quotient graph nodes through graph and quotient graph theories.The Approximate Minimum Degree(AMD) of quotient graph nodes and the length of the elimination tree nodes are composed to build an Approximate Minimum Degree and Minimum Length(AMDML) model. The quotient graph node with the minimum degree, which is also the minimum length of elimination tree node, is selected as the next ordering vector. Compared with AMD ordering method and other common methods, the proposed method further reduces the length of elimination tree without increasing the number of nonzero fillings; the length was decreased by about 10% compared with the AMD method. A testbed for experiment was built. The efficiency of the proposed method was evaluated based on different sizes of coefficient matrices of power flow cases.
2021年04期 v.26 464-474页 [查看摘要][在线阅读][下载 2018K] [下载次数：27 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Jian Guo;Hong Liang;Songpu Ai;Chao Lu;Haochen Hua;Junwei Cao;
Electrical power network analysis and computation play an important role in the planning and operation of the power grid, and they are modeled mathematically as differential equations and network algebraic equations.The direct method based on Gaussian elimination theory can obtain analytical results. Two factors affect computing efficiency: the number of nonzero element fillings and the length of elimination tree. This article constructs mapping correspondence between eliminated tree nodes and quotient graph nodes through graph and quotient graph theories.The Approximate Minimum Degree(AMD) of quotient graph nodes and the length of the elimination tree nodes are composed to build an Approximate Minimum Degree and Minimum Length(AMDML) model. The quotient graph node with the minimum degree, which is also the minimum length of elimination tree node, is selected as the next ordering vector. Compared with AMD ordering method and other common methods, the proposed method further reduces the length of elimination tree without increasing the number of nonzero fillings; the length was decreased by about 10% compared with the AMD method. A testbed for experiment was built. The efficiency of the proposed method was evaluated based on different sizes of coefficient matrices of power flow cases.
2021年04期 v.26 464-474页 [查看摘要][在线阅读][下载 2018K] [下载次数：27 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Shaojun Guo;Feng Liu;Xiaohu Yuan;Chunrong Zou;Li Chen;Tongsheng Shen;
The Histograms of Oriented Gradients(HOG) can produce good results in an image target recognition mission, but it requires the same size of the target images for classification of inputs. In response to this shortcoming,this paper performs spatial pyramid segmentation on target images of any size, gets the pixel size of each image block dynamically, and further calculates and normalizes the gradient of the oriented feature of each block region in each image layer. The new feature is called the Histogram of Spatial Pyramid Oriented Gradients(HSPOG).This approach can obtain stable vectors for images of any size, and increase the target detection rate in the image recognition process significantly. Finally, the article verifies the algorithm using VOC2012 image data and compares the effect of HOG.
2021年04期 v.26 475-483页 [查看摘要][在线阅读][下载 6662K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Shaojun Guo;Feng Liu;Xiaohu Yuan;Chunrong Zou;Li Chen;Tongsheng Shen;
The Histograms of Oriented Gradients(HOG) can produce good results in an image target recognition mission, but it requires the same size of the target images for classification of inputs. In response to this shortcoming,this paper performs spatial pyramid segmentation on target images of any size, gets the pixel size of each image block dynamically, and further calculates and normalizes the gradient of the oriented feature of each block region in each image layer. The new feature is called the Histogram of Spatial Pyramid Oriented Gradients(HSPOG).This approach can obtain stable vectors for images of any size, and increase the target detection rate in the image recognition process significantly. Finally, the article verifies the algorithm using VOC2012 image data and compares the effect of HOG.
2021年04期 v.26 475-483页 [查看摘要][在线阅读][下载 6662K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Shaojun Guo;Feng Liu;Xiaohu Yuan;Chunrong Zou;Li Chen;Tongsheng Shen;
The Histograms of Oriented Gradients(HOG) can produce good results in an image target recognition mission, but it requires the same size of the target images for classification of inputs. In response to this shortcoming,this paper performs spatial pyramid segmentation on target images of any size, gets the pixel size of each image block dynamically, and further calculates and normalizes the gradient of the oriented feature of each block region in each image layer. The new feature is called the Histogram of Spatial Pyramid Oriented Gradients(HSPOG).This approach can obtain stable vectors for images of any size, and increase the target detection rate in the image recognition process significantly. Finally, the article verifies the algorithm using VOC2012 image data and compares the effect of HOG.
2021年04期 v.26 475-483页 [查看摘要][在线阅读][下载 6662K] [下载次数：25 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Mohammad Hashem Haghighat;Jun Li;
Several security solutions have been proposed to detect network abnormal behavior. However, successful attacks is still a big concern in computer society. Lots of security breaches, like Distributed Denial of Service(DDoS),botnets, spam, phishing, and so on, are reported every day, while the number of attacks are still increasing. In this paper, a novel voting-based deep learning framework, called VNN, is proposed to take the advantage of any kinds of deep learning structures. Considering several models created by different aspects of data and various deep learning structures, VNN provides the ability to aggregate the best models in order to create more accurate and robust results. Therefore, VNN helps the security specialists to detect more complicated attacks. Experimental results over KDDCUP'99 and CTU-13, as two well known and more widely employed datasets in computer network area, revealed the voting procedure was highly effective to increase the system performance, where the false alarms were reduced up to 75% in comparison with the original deep learning models, including Deep Neural Network(DNN), Convolutional Neural Network(CNN), Long Short-Term Memory(LSTM), and Gated Recurrent Unit(GRU).
2021年04期 v.26 484-495页 [查看摘要][在线阅读][下载 2653K] [下载次数：64 ] |[网刊下载次数：0 ] |[引用频次：22 ] |[阅读次数：0 ] - Mohammad Hashem Haghighat;Jun Li;
Several security solutions have been proposed to detect network abnormal behavior. However, successful attacks is still a big concern in computer society. Lots of security breaches, like Distributed Denial of Service(DDoS),botnets, spam, phishing, and so on, are reported every day, while the number of attacks are still increasing. In this paper, a novel voting-based deep learning framework, called VNN, is proposed to take the advantage of any kinds of deep learning structures. Considering several models created by different aspects of data and various deep learning structures, VNN provides the ability to aggregate the best models in order to create more accurate and robust results. Therefore, VNN helps the security specialists to detect more complicated attacks. Experimental results over KDDCUP'99 and CTU-13, as two well known and more widely employed datasets in computer network area, revealed the voting procedure was highly effective to increase the system performance, where the false alarms were reduced up to 75% in comparison with the original deep learning models, including Deep Neural Network(DNN), Convolutional Neural Network(CNN), Long Short-Term Memory(LSTM), and Gated Recurrent Unit(GRU).
2021年04期 v.26 484-495页 [查看摘要][在线阅读][下载 2653K] [下载次数：64 ] |[网刊下载次数：0 ] |[引用频次：22 ] |[阅读次数：0 ] - Mohammad Hashem Haghighat;Jun Li;
Several security solutions have been proposed to detect network abnormal behavior. However, successful attacks is still a big concern in computer society. Lots of security breaches, like Distributed Denial of Service(DDoS),botnets, spam, phishing, and so on, are reported every day, while the number of attacks are still increasing. In this paper, a novel voting-based deep learning framework, called VNN, is proposed to take the advantage of any kinds of deep learning structures. Considering several models created by different aspects of data and various deep learning structures, VNN provides the ability to aggregate the best models in order to create more accurate and robust results. Therefore, VNN helps the security specialists to detect more complicated attacks. Experimental results over KDDCUP'99 and CTU-13, as two well known and more widely employed datasets in computer network area, revealed the voting procedure was highly effective to increase the system performance, where the false alarms were reduced up to 75% in comparison with the original deep learning models, including Deep Neural Network(DNN), Convolutional Neural Network(CNN), Long Short-Term Memory(LSTM), and Gated Recurrent Unit(GRU).
2021年04期 v.26 484-495页 [查看摘要][在线阅读][下载 2653K] [下载次数：64 ] |[网刊下载次数：0 ] |[引用频次：22 ] |[阅读次数：0 ] - Baoyu Liu;Xiaoping Zou;Dan Chen;Taoran Liu;Yuhua Zuo;Jun Zheng;Zhi Liu;Buwen Cheng;
In recent years, Perovskite Light-Emitting Diodes(PeLEDs) have received considerable attention in academia. However, with the development of PeLEDs, commercial applications of full-color PeLED technology are largely limited by the progress of blue-emitting devices, due to the uncontrollably accurate composition, unstable properties, and low luminance. In this article, we add Cesium chloride(CsCl) to the quasi-two-dimensional(quasi-2D)perovskite precursor solution and achieve the relatively blue shifts of PeLED emission peak by introducing chloride ions for photoluminescence(PL) and electroluminescence(EL). We also found that the introduction of chlorine ions can make quasi-2D perovskite films thinner with smoother surface of 0.408 nm. It is interesting that the EL peaks and intensities of PeLED are adjustable under different driving voltages in high concentration chlorine-added perovskite devices, and different processes of photo-excited, photo-quenched, and photo-excited occur sequentially with the increasing driving voltage. Our work provides a path for demonstrating full-color screens in the future.
2021年04期 v.26 496-504页 [查看摘要][在线阅读][下载 5155K] [下载次数：28 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Baoyu Liu;Xiaoping Zou;Dan Chen;Taoran Liu;Yuhua Zuo;Jun Zheng;Zhi Liu;Buwen Cheng;
In recent years, Perovskite Light-Emitting Diodes(PeLEDs) have received considerable attention in academia. However, with the development of PeLEDs, commercial applications of full-color PeLED technology are largely limited by the progress of blue-emitting devices, due to the uncontrollably accurate composition, unstable properties, and low luminance. In this article, we add Cesium chloride(CsCl) to the quasi-two-dimensional(quasi-2D)perovskite precursor solution and achieve the relatively blue shifts of PeLED emission peak by introducing chloride ions for photoluminescence(PL) and electroluminescence(EL). We also found that the introduction of chlorine ions can make quasi-2D perovskite films thinner with smoother surface of 0.408 nm. It is interesting that the EL peaks and intensities of PeLED are adjustable under different driving voltages in high concentration chlorine-added perovskite devices, and different processes of photo-excited, photo-quenched, and photo-excited occur sequentially with the increasing driving voltage. Our work provides a path for demonstrating full-color screens in the future.
2021年04期 v.26 496-504页 [查看摘要][在线阅读][下载 5155K] [下载次数：28 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Baoyu Liu;Xiaoping Zou;Dan Chen;Taoran Liu;Yuhua Zuo;Jun Zheng;Zhi Liu;Buwen Cheng;
In recent years, Perovskite Light-Emitting Diodes(PeLEDs) have received considerable attention in academia. However, with the development of PeLEDs, commercial applications of full-color PeLED technology are largely limited by the progress of blue-emitting devices, due to the uncontrollably accurate composition, unstable properties, and low luminance. In this article, we add Cesium chloride(CsCl) to the quasi-two-dimensional(quasi-2D)perovskite precursor solution and achieve the relatively blue shifts of PeLED emission peak by introducing chloride ions for photoluminescence(PL) and electroluminescence(EL). We also found that the introduction of chlorine ions can make quasi-2D perovskite films thinner with smoother surface of 0.408 nm. It is interesting that the EL peaks and intensities of PeLED are adjustable under different driving voltages in high concentration chlorine-added perovskite devices, and different processes of photo-excited, photo-quenched, and photo-excited occur sequentially with the increasing driving voltage. Our work provides a path for demonstrating full-color screens in the future.
2021年04期 v.26 496-504页 [查看摘要][在线阅读][下载 5155K] [下载次数：28 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Jiajun Lin;Liyan Liang;Xu Han;Chen Yang;Xiaogang Chen;Xiaorong Gao;
In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover,this study designed a transfer-extended Canonical Correlation Analysis(t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies,t-eCCA obtained an average accuracy of 86.96%˙12.87% across 12 subjects using only half of the calibration time,which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis(88.32%˙13.97%) and task-related component analysis(88.92%˙14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis(CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.
2021年04期 v.26 505-522页 [查看摘要][在线阅读][下载 3116K] [下载次数：95 ] |[网刊下载次数：0 ] |[引用频次：13 ] |[阅读次数：0 ] - Jiajun Lin;Liyan Liang;Xu Han;Chen Yang;Xiaogang Chen;Xiaorong Gao;
In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover,this study designed a transfer-extended Canonical Correlation Analysis(t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies,t-eCCA obtained an average accuracy of 86.96%˙12.87% across 12 subjects using only half of the calibration time,which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis(88.32%˙13.97%) and task-related component analysis(88.92%˙14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis(CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.
2021年04期 v.26 505-522页 [查看摘要][在线阅读][下载 3116K] [下载次数：95 ] |[网刊下载次数：0 ] |[引用频次：13 ] |[阅读次数：0 ] - Jiajun Lin;Liyan Liang;Xu Han;Chen Yang;Xiaogang Chen;Xiaorong Gao;
In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover,this study designed a transfer-extended Canonical Correlation Analysis(t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies,t-eCCA obtained an average accuracy of 86.96%˙12.87% across 12 subjects using only half of the calibration time,which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis(88.32%˙13.97%) and task-related component analysis(88.92%˙14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis(CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.
2021年04期 v.26 505-522页 [查看摘要][在线阅读][下载 3116K] [下载次数：95 ] |[网刊下载次数：0 ] |[引用频次：13 ] |[阅读次数：0 ] - Yan Huo;Jingjing Fan;Yingkun Wen;Ruinian Li;
In this paper, we design a friendly jammer selection scheme for the social Internet of Things(IoT). A typical social IoT is composed of a cellular network with underlaying Device-to-Device(D2D) communications. In our scheme, we consider signal characteristics over a physical layer and social attribute information of an application layer simultaneously. Using signal characteristics, one of the D2D gadgets is selected as a friendly jammer to improve the secrecy performance of a cellular device. In return, the selected D2D gadget is allowed to reuse spectrum resources of the cellular device. Using social relationship, we analyze and quantify the social intimacy degree among the nodes in IoT to design an adaptive communication time threshold. Applying an artificial intelligence forecasting model, we further forecast and update the intimacy degree, and then screen and filter potential devices to effectively reduce the detection and calculation costs. Finally, we propose an optimal scheme to integrate the virtual social relationship with actual communication systems. To select the optimal D2D gadget as a friendly jammer, we apply Kuhn-Munkres(KM) algorithm to solve the maximization problem of social intimacy and cooperative jamming.Comprehensive numerical results are presented to validate the performance of our scheme.
2021年04期 v.26 523-535页 [查看摘要][在线阅读][下载 3516K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：10 ] |[阅读次数：0 ] - Yan Huo;Jingjing Fan;Yingkun Wen;Ruinian Li;
In this paper, we design a friendly jammer selection scheme for the social Internet of Things(IoT). A typical social IoT is composed of a cellular network with underlaying Device-to-Device(D2D) communications. In our scheme, we consider signal characteristics over a physical layer and social attribute information of an application layer simultaneously. Using signal characteristics, one of the D2D gadgets is selected as a friendly jammer to improve the secrecy performance of a cellular device. In return, the selected D2D gadget is allowed to reuse spectrum resources of the cellular device. Using social relationship, we analyze and quantify the social intimacy degree among the nodes in IoT to design an adaptive communication time threshold. Applying an artificial intelligence forecasting model, we further forecast and update the intimacy degree, and then screen and filter potential devices to effectively reduce the detection and calculation costs. Finally, we propose an optimal scheme to integrate the virtual social relationship with actual communication systems. To select the optimal D2D gadget as a friendly jammer, we apply Kuhn-Munkres(KM) algorithm to solve the maximization problem of social intimacy and cooperative jamming.Comprehensive numerical results are presented to validate the performance of our scheme.
2021年04期 v.26 523-535页 [查看摘要][在线阅读][下载 3516K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：10 ] |[阅读次数：0 ] - Yan Huo;Jingjing Fan;Yingkun Wen;Ruinian Li;
In this paper, we design a friendly jammer selection scheme for the social Internet of Things(IoT). A typical social IoT is composed of a cellular network with underlaying Device-to-Device(D2D) communications. In our scheme, we consider signal characteristics over a physical layer and social attribute information of an application layer simultaneously. Using signal characteristics, one of the D2D gadgets is selected as a friendly jammer to improve the secrecy performance of a cellular device. In return, the selected D2D gadget is allowed to reuse spectrum resources of the cellular device. Using social relationship, we analyze and quantify the social intimacy degree among the nodes in IoT to design an adaptive communication time threshold. Applying an artificial intelligence forecasting model, we further forecast and update the intimacy degree, and then screen and filter potential devices to effectively reduce the detection and calculation costs. Finally, we propose an optimal scheme to integrate the virtual social relationship with actual communication systems. To select the optimal D2D gadget as a friendly jammer, we apply Kuhn-Munkres(KM) algorithm to solve the maximization problem of social intimacy and cooperative jamming.Comprehensive numerical results are presented to validate the performance of our scheme.
2021年04期 v.26 523-535页 [查看摘要][在线阅读][下载 3516K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：10 ] |[阅读次数：0 ] - Xuan Zhao;Zhongdao Wang;Lei Gao;Yali Li;Shengjin Wang;
In this study, we address the problems encountered by incremental face clustering. Without the benefit of having observed the entire data distribution, incremental face clustering is more challenging than static dataset clustering. Conventional methods rely on the statistical information of previous clusters to improve the efficiency of incremental clustering; thus, error accumulation may occur. Therefore, this study proposes to predict the summaries of previous data directly from data distribution via supervised learning. Moreover, an efficient framework to cluster previous summaries with new data is explored. Although learning summaries from original data costs more than those from previous clusters, the entire framework consumes just a little bit more time because clustering current data and generating summaries for new data share most of the calculations. Experiments show that the proposed approach significantly outperforms the existing incremental face clustering methods, as evidenced by the improvement of average F-score from 0.644 to 0.762. Compared with state-of-the-art static face clustering methods, our method can yield comparable accuracy while consuming much less time.
2021年04期 v.26 536-547页 [查看摘要][在线阅读][下载 4813K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Xuan Zhao;Zhongdao Wang;Lei Gao;Yali Li;Shengjin Wang;
In this study, we address the problems encountered by incremental face clustering. Without the benefit of having observed the entire data distribution, incremental face clustering is more challenging than static dataset clustering. Conventional methods rely on the statistical information of previous clusters to improve the efficiency of incremental clustering; thus, error accumulation may occur. Therefore, this study proposes to predict the summaries of previous data directly from data distribution via supervised learning. Moreover, an efficient framework to cluster previous summaries with new data is explored. Although learning summaries from original data costs more than those from previous clusters, the entire framework consumes just a little bit more time because clustering current data and generating summaries for new data share most of the calculations. Experiments show that the proposed approach significantly outperforms the existing incremental face clustering methods, as evidenced by the improvement of average F-score from 0.644 to 0.762. Compared with state-of-the-art static face clustering methods, our method can yield comparable accuracy while consuming much less time.
2021年04期 v.26 536-547页 [查看摘要][在线阅读][下载 4813K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Xuan Zhao;Zhongdao Wang;Lei Gao;Yali Li;Shengjin Wang;
In this study, we address the problems encountered by incremental face clustering. Without the benefit of having observed the entire data distribution, incremental face clustering is more challenging than static dataset clustering. Conventional methods rely on the statistical information of previous clusters to improve the efficiency of incremental clustering; thus, error accumulation may occur. Therefore, this study proposes to predict the summaries of previous data directly from data distribution via supervised learning. Moreover, an efficient framework to cluster previous summaries with new data is explored. Although learning summaries from original data costs more than those from previous clusters, the entire framework consumes just a little bit more time because clustering current data and generating summaries for new data share most of the calculations. Experiments show that the proposed approach significantly outperforms the existing incremental face clustering methods, as evidenced by the improvement of average F-score from 0.644 to 0.762. Compared with state-of-the-art static face clustering methods, our method can yield comparable accuracy while consuming much less time.
2021年04期 v.26 536-547页 [查看摘要][在线阅读][下载 4813K] [下载次数：30 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：0 ] - Miao Wang;Wentao Han;Wenguang Chen;
Online Judge(OJ) systems are a basic and important component of computer education. Here, we present MetaOJ, an OJ system that can be used for holding massive programming tests online. MetaOJ is designed to create a distributed, fault-tolerant, and easy-to-scale OJ system from an existing ordinary OJ system by adding several interfaces into it and creating multiple instances of it. Our case on modifying the TUOJ system shows that the modification adds no more than 3% lines of code and the performance loss on a single OJ instance is no more than 12%. We also introduce mechanisms to integrate the system with cloud infrastructure to automate the deployment process. MetaOJ provides a solution for those OJ systems that are designed for a specific programming contest and are now facing performance bottlenecks.
2021年04期 v.26 548-557页 [查看摘要][在线阅读][下载 928K] [下载次数：300 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Miao Wang;Wentao Han;Wenguang Chen;
Online Judge(OJ) systems are a basic and important component of computer education. Here, we present MetaOJ, an OJ system that can be used for holding massive programming tests online. MetaOJ is designed to create a distributed, fault-tolerant, and easy-to-scale OJ system from an existing ordinary OJ system by adding several interfaces into it and creating multiple instances of it. Our case on modifying the TUOJ system shows that the modification adds no more than 3% lines of code and the performance loss on a single OJ instance is no more than 12%. We also introduce mechanisms to integrate the system with cloud infrastructure to automate the deployment process. MetaOJ provides a solution for those OJ systems that are designed for a specific programming contest and are now facing performance bottlenecks.
2021年04期 v.26 548-557页 [查看摘要][在线阅读][下载 928K] [下载次数：300 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Miao Wang;Wentao Han;Wenguang Chen;
Online Judge(OJ) systems are a basic and important component of computer education. Here, we present MetaOJ, an OJ system that can be used for holding massive programming tests online. MetaOJ is designed to create a distributed, fault-tolerant, and easy-to-scale OJ system from an existing ordinary OJ system by adding several interfaces into it and creating multiple instances of it. Our case on modifying the TUOJ system shows that the modification adds no more than 3% lines of code and the performance loss on a single OJ instance is no more than 12%. We also introduce mechanisms to integrate the system with cloud infrastructure to automate the deployment process. MetaOJ provides a solution for those OJ systems that are designed for a specific programming contest and are now facing performance bottlenecks.
2021年04期 v.26 548-557页 [查看摘要][在线阅读][下载 928K] [下载次数：300 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Zewei Sun;Hanwen Liu;Chao Yan;Ran An;
With the ever-increasing number of natural disasters warning documents in document databases, the document database is becoming an economic and efficient way for enterprise staffs to learn and understand the contents of the natural disasters warning through searching for necessary text documents. Generally, the document database can recommend a mass of documents to the enterprise staffs through analyzing the enterprise staff's precisely typed keywords. In fact, these recommended documents place a heavy burden on the enterprise staffs to learn and select as the enterprise staffs have little background knowledge about the contents of the natural disasters warning. Thus, the enterprise staffs fail to retrieve and select appropriate documents to achieve their desired goals.Considering the above drawbacks, in this paper, we propose a fuzzy keywords-driven Natural Disasters Warning Documents retrieval approach(named NDWDkeyword). Through the text description mining of documents and the fuzzy keywords searching technology, the retrieval approach can precisely capture the enterprise staffs' target requirements and then return necessary documents to the enterprise staffs. Finally, a case study is run to explain our retrieval approach step by step and demonstrate the effectiveness and feasibility of our proposal.
2021年04期 v.26 558-564页 [查看摘要][在线阅读][下载 353K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ] - Zewei Sun;Hanwen Liu;Chao Yan;Ran An;
With the ever-increasing number of natural disasters warning documents in document databases, the document database is becoming an economic and efficient way for enterprise staffs to learn and understand the contents of the natural disasters warning through searching for necessary text documents. Generally, the document database can recommend a mass of documents to the enterprise staffs through analyzing the enterprise staff's precisely typed keywords. In fact, these recommended documents place a heavy burden on the enterprise staffs to learn and select as the enterprise staffs have little background knowledge about the contents of the natural disasters warning. Thus, the enterprise staffs fail to retrieve and select appropriate documents to achieve their desired goals.Considering the above drawbacks, in this paper, we propose a fuzzy keywords-driven Natural Disasters Warning Documents retrieval approach(named NDWDkeyword). Through the text description mining of documents and the fuzzy keywords searching technology, the retrieval approach can precisely capture the enterprise staffs' target requirements and then return necessary documents to the enterprise staffs. Finally, a case study is run to explain our retrieval approach step by step and demonstrate the effectiveness and feasibility of our proposal.
2021年04期 v.26 558-564页 [查看摘要][在线阅读][下载 353K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ] - Zewei Sun;Hanwen Liu;Chao Yan;Ran An;
With the ever-increasing number of natural disasters warning documents in document databases, the document database is becoming an economic and efficient way for enterprise staffs to learn and understand the contents of the natural disasters warning through searching for necessary text documents. Generally, the document database can recommend a mass of documents to the enterprise staffs through analyzing the enterprise staff's precisely typed keywords. In fact, these recommended documents place a heavy burden on the enterprise staffs to learn and select as the enterprise staffs have little background knowledge about the contents of the natural disasters warning. Thus, the enterprise staffs fail to retrieve and select appropriate documents to achieve their desired goals.Considering the above drawbacks, in this paper, we propose a fuzzy keywords-driven Natural Disasters Warning Documents retrieval approach(named NDWDkeyword). Through the text description mining of documents and the fuzzy keywords searching technology, the retrieval approach can precisely capture the enterprise staffs' target requirements and then return necessary documents to the enterprise staffs. Finally, a case study is run to explain our retrieval approach step by step and demonstrate the effectiveness and feasibility of our proposal.
2021年04期 v.26 558-564页 [查看摘要][在线阅读][下载 353K] [下载次数：34 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：0 ] 下载本期数据