The explosive growth ofmalware variants poses a major threat to information security. Traditional anti-virus systems based on signatures fail to classify unknown malware into their corresponding families and to detect...The explosive growth ofmalware variants poses a major threat to information security. Traditional anti-virus systems based on signatures fail to classify unknown malware into their corresponding families and to detect new kinds of malware pro- grams. Therefore, we propose a machine learning based malware analysis system, which is composed of three modules： data processing, decision making, and new malware detection. The data processing module deals with gray-scale images, Opcode n-gram, and import fimctions, which are employed to extract the features of the malware. The decision-making module uses the features to classify the malware and to identify suspicious malware. Finally, the detection module uses the shared nearest neighbor （SNN） clustering algorithm to discover new malware families. Our approach is evaluated on more than 20 000 malware instances, which were collected by Kingsoft, ESET NOD32, and Anubis. The results show that our system can effectively classify the un- known malware with a best accuracy of 98.9%, and successfully detects 86.7% of the new malware.展开更多
Carpal tunnel syndrome(CTS) is a common peripheral entrapment neuropathy of the median nerve at wrist level, and is thought to be caused by compression of the median nerve in the carpal tunnel. There is no standard qu...Carpal tunnel syndrome(CTS) is a common peripheral entrapment neuropathy of the median nerve at wrist level, and is thought to be caused by compression of the median nerve in the carpal tunnel. There is no standard quantitative reference for the diagnosis of CTS. Greyscale sonography and sonoelastography(SEL) have been used as diagnostic tools. The most commonly agreed findings in grey-scale sonography for the diagnosis of CTS is enlargement of the median nerve cross-sectional area(CSA). Several authors have assessed additional parameters. "Delta CSA" is the difference between the proximal median nerve CSA at the pronator quadratus and the maximal CSA within the carpal tunnel. The "CSA ratio" is the ratio of CSA in the carpal tunnel to the CSA at the mid forearm. These additional parameters showed better diagnostic accuracy than CSA measurement alone. Recently, a number of studies have investigated the elasticity of the median nerve using SEL, and have shown that this also has diagnostic value, as it was significantly stiffer in CTS patients compared to healthy volunteers. In this review, we summarize the usefulness of grey-scale sonography and SEL in diagnosing CTS.展开更多
We introduce first a sort of gray-scale morphological dilations and erosions, which might have some further applications in image analysis. Then we show that the dilation and the erosion defined here form adjunctive p...We introduce first a sort of gray-scale morphological dilations and erosions, which might have some further applications in image analysis. Then we show that the dilation and the erosion defined here form adjunctive pairs. The duality between the dilation and the erosion and some other properties, such as homothety, of these operators are discussed the Commuting property with translation and as well.展开更多
Using the high-speed camera the time sequences of the classical flow patterns of horizontal gas-liquid pipe flow are recorded, from which the average gray-scale values of single-frame images are extracted. Thus obtain...Using the high-speed camera the time sequences of the classical flow patterns of horizontal gas-liquid pipe flow are recorded, from which the average gray-scale values of single-frame images are extracted. Thus obtained gray-scale time series is decomposed by the Empirical Mode Decomposition (EMD) method, the various scales of the signals are processed by Hurst exponent method, and then the dual-fractal characteristics are obtained. The scattered bubble and the bubble cluster theories are applied to the evolution analysis of two-phase flow patterns. At the same time the various signals are checked in the chaotic recursion chart by which the two typical characteristics (diagonal average length and Shannon entropy) are obtained. Resulting term of these properties, the dynamic characteristics of gas-liquid two-phase flow patterns are quantitatively analyzed. The results show that the evolution paths of gas-liquid two-phase flow patterns can be well characterized by the integrated analysis on the basis of the gray-scale time series of flowing images from EMD, Hurst exponents and Recurrence Plot (RP). In the middle frequency section (2nd, 3rd, 4th scales), three flow patterns decomposed by the EMD exhibit dual fractal characteristics which represent the dynamic features of bubble cluster, single bubble, slug bubble and scattered bubble. According to the change of diagonal average lengths and recursive Shannon entropy characteristic value, the structure deterministic of the slug flow is better than the other two patterns. After the decomposition by EMD the slug flow and the mist flow in the high frequency section have obvious peaks. Anyway, it is an effective way to understand and characterize the dynamic characteristics of two-phase flow patterns using the multi-scale non-linear analysis method based on image gray-scale fluctuation signals.展开更多
A new cellular neural network (CNN) with nonlinear templates is presented forextracting convex corners of objects in gray-scale images. Application examples showed that the newCNN can even detect convex corner charact...A new cellular neural network (CNN) with nonlinear templates is presented forextracting convex corners of objects in gray-scale images. Application examples showed that the newCNN can even detect convex corner characteristics of objects in images with Gaussian noise.展开更多
The S/N of an underwater image is low and has a fuzzy edge.If using traditional methods to process it directly,the result is not satisfying.Though the traditional fuzzy C-means algorithm can sometimes divide the image...The S/N of an underwater image is low and has a fuzzy edge.If using traditional methods to process it directly,the result is not satisfying.Though the traditional fuzzy C-means algorithm can sometimes divide the image into object and background,its time-consuming computation is often an obstacle.The mission of the vision system of an autonomous underwater vehicle (AUV) is to rapidly and exactly deal with the information about the object in a complex environment for the AUV to use the obtained result to execute the next task.So,by using the statistical characteristics of the gray image histogram,a fast and effective fuzzy C-means underwater image segmentation algorithm was presented.With the weighted histogram modifying the fuzzy membership,the above algorithm can not only cut down on a large amount of data processing and storage during the computation process compared with the traditional algorithm,so as to speed up the efficiency of the segmentation,but also improve the quality of underwater image segmentation.Finally,particle swarm optimization (PSO) described by the sine function was introduced to the algorithm mentioned above.It made up for the shortcomings that the FCM algorithm can not get the global optimal solution.Thus,on the one hand,it considers the global impact and achieves the local optimal solution,and on the other hand,further greatly increases the computing speed.Experimental results indicate that the novel algorithm can reach a better segmentation quality and the processing time of each image is reduced.They enhance efficiency and satisfy the requirements of a highly effective,real-time AUV.展开更多
A novel learning method for multi-valued associative memory network is introduced, which is based on Hebb rule, but utilizes more information. According to the current probe vector, the connection weights matrix could...A novel learning method for multi-valued associative memory network is introduced, which is based on Hebb rule, but utilizes more information. According to the current probe vector, the connection weights matrix could be chosen dynamically. Double-valued and multi-valued associative memory are all realized in our simulation experiment. The experimental results show that the method could enhance the associative success rate.展开更多
基金Project supported by the Natiooal Natural Science Foundation of China （No. 61303264） and the National Basic Research Program （973） of China （Nos. 2012CB315906 and 0800065111001）
文摘The explosive growth ofmalware variants poses a major threat to information security. Traditional anti-virus systems based on signatures fail to classify unknown malware into their corresponding families and to detect new kinds of malware pro- grams. Therefore, we propose a machine learning based malware analysis system, which is composed of three modules： data processing, decision making, and new malware detection. The data processing module deals with gray-scale images, Opcode n-gram, and import fimctions, which are employed to extract the features of the malware. The decision-making module uses the features to classify the malware and to identify suspicious malware. Finally, the detection module uses the shared nearest neighbor （SNN） clustering algorithm to discover new malware families. Our approach is evaluated on more than 20 000 malware instances, which were collected by Kingsoft, ESET NOD32, and Anubis. The results show that our system can effectively classify the un- known malware with a best accuracy of 98.9%, and successfully detects 86.7% of the new malware.
文摘Carpal tunnel syndrome(CTS) is a common peripheral entrapment neuropathy of the median nerve at wrist level, and is thought to be caused by compression of the median nerve in the carpal tunnel. There is no standard quantitative reference for the diagnosis of CTS. Greyscale sonography and sonoelastography(SEL) have been used as diagnostic tools. The most commonly agreed findings in grey-scale sonography for the diagnosis of CTS is enlargement of the median nerve cross-sectional area(CSA). Several authors have assessed additional parameters. "Delta CSA" is the difference between the proximal median nerve CSA at the pronator quadratus and the maximal CSA within the carpal tunnel. The "CSA ratio" is the ratio of CSA in the carpal tunnel to the CSA at the mid forearm. These additional parameters showed better diagnostic accuracy than CSA measurement alone. Recently, a number of studies have investigated the elasticity of the median nerve using SEL, and have shown that this also has diagnostic value, as it was significantly stiffer in CTS patients compared to healthy volunteers. In this review, we summarize the usefulness of grey-scale sonography and SEL in diagnosing CTS.
基金Supported by the National Natural Science Foundation of China（11671293, 11271282）
文摘We introduce first a sort of gray-scale morphological dilations and erosions, which might have some further applications in image analysis. Then we show that the dilation and the erosion defined here form adjunctive pairs. The duality between the dilation and the erosion and some other properties, such as homothety, of these operators are discussed the Commuting property with translation and as well.
基金Supported by the National Natural Science Foundation of China （50976018） the Natural Science Foundation of JilinProvince （20101562）
文摘Using the high-speed camera the time sequences of the classical flow patterns of horizontal gas-liquid pipe flow are recorded, from which the average gray-scale values of single-frame images are extracted. Thus obtained gray-scale time series is decomposed by the Empirical Mode Decomposition (EMD) method, the various scales of the signals are processed by Hurst exponent method, and then the dual-fractal characteristics are obtained. The scattered bubble and the bubble cluster theories are applied to the evolution analysis of two-phase flow patterns. At the same time the various signals are checked in the chaotic recursion chart by which the two typical characteristics (diagonal average length and Shannon entropy) are obtained. Resulting term of these properties, the dynamic characteristics of gas-liquid two-phase flow patterns are quantitatively analyzed. The results show that the evolution paths of gas-liquid two-phase flow patterns can be well characterized by the integrated analysis on the basis of the gray-scale time series of flowing images from EMD, Hurst exponents and Recurrence Plot (RP). In the middle frequency section (2nd, 3rd, 4th scales), three flow patterns decomposed by the EMD exhibit dual fractal characteristics which represent the dynamic features of bubble cluster, single bubble, slug bubble and scattered bubble. According to the change of diagonal average lengths and recursive Shannon entropy characteristic value, the structure deterministic of the slug flow is better than the other two patterns. After the decomposition by EMD the slug flow and the mist flow in the high frequency section have obvious peaks. Anyway, it is an effective way to understand and characterize the dynamic characteristics of two-phase flow patterns using the multi-scale non-linear analysis method based on image gray-scale fluctuation signals.
基金This project is jointly supported by the National Nature Science Foundation of China(Nos.60074034,70271068),the Research Fund for the Doctoral Program of Higher Education(No.20020008004)and the Foundation for University Key Teacher by the Ministry of Ed
文摘A new cellular neural network (CNN) with nonlinear templates is presented forextracting convex corners of objects in gray-scale images. Application examples showed that the newCNN can even detect convex corner characteristics of objects in images with Gaussian noise.
基金Supported by the National Natural Science Foundation of China under Grant No.50909025/E091002the Open Research Foundation of SKLab AUV, HEU under Grant No.2008003
文摘The S/N of an underwater image is low and has a fuzzy edge.If using traditional methods to process it directly,the result is not satisfying.Though the traditional fuzzy C-means algorithm can sometimes divide the image into object and background,its time-consuming computation is often an obstacle.The mission of the vision system of an autonomous underwater vehicle (AUV) is to rapidly and exactly deal with the information about the object in a complex environment for the AUV to use the obtained result to execute the next task.So,by using the statistical characteristics of the gray image histogram,a fast and effective fuzzy C-means underwater image segmentation algorithm was presented.With the weighted histogram modifying the fuzzy membership,the above algorithm can not only cut down on a large amount of data processing and storage during the computation process compared with the traditional algorithm,so as to speed up the efficiency of the segmentation,but also improve the quality of underwater image segmentation.Finally,particle swarm optimization (PSO) described by the sine function was introduced to the algorithm mentioned above.It made up for the shortcomings that the FCM algorithm can not get the global optimal solution.Thus,on the one hand,it considers the global impact and achieves the local optimal solution,and on the other hand,further greatly increases the computing speed.Experimental results indicate that the novel algorithm can reach a better segmentation quality and the processing time of each image is reduced.They enhance efficiency and satisfy the requirements of a highly effective,real-time AUV.
文摘A novel learning method for multi-valued associative memory network is introduced, which is based on Hebb rule, but utilizes more information. According to the current probe vector, the connection weights matrix could be chosen dynamically. Double-valued and multi-valued associative memory are all realized in our simulation experiment. The experimental results show that the method could enhance the associative success rate.
