The concept of intelligent integrated network management (IINM) is briefly introduced. In order to analyze, design and implement IINM successfully, object oriented approach is testified to be an effective and efficien...The concept of intelligent integrated network management (IINM) is briefly introduced. In order to analyze, design and implement IINM successfully, object oriented approach is testified to be an effective and efficient way. In this paper, object oriented technique is applied to the structural model of IINM system, The Domain object class and the MU object class are used to represent the manager and the managed resources. Especially, NM IA is introduced which is a special object class with intelligent behaviors to manage the resources efficiently.展开更多
A novel reliable routing algorithm in mobile ad hoc networks using fuzzy Petri net with its reasoning mechanism was proposed to increase the reliability during the routing selection. The algorithm allows the structure...A novel reliable routing algorithm in mobile ad hoc networks using fuzzy Petri net with its reasoning mechanism was proposed to increase the reliability during the routing selection. The algorithm allows the structured representation of network topology, which has a fuzzy reasoning mechanism for finding the routing sprouting tree from the source node to the destination node in the mobile ad boc environment. Finally, by comparing the degree of reliability in the routing sprouting tree, the most reliable route can be computed. The algorithm not only offers the local reliability between each neighboring node, but also provides global reliability for the whole selected route. The algorithm can be applied to most existing on-demand routing protocols, and the simulation results show that the routing reliability is increased by more than 80% when applying the proposed algorithm to the ad hoc on demand distance vector routing protocol.展开更多
This paper proposed a watermarking algorithm for tamper-proof of web pages. For a web page, it generates a watermark consisting of a sequence of Space and Tab. The wa termark is then embedded into the web page after e...This paper proposed a watermarking algorithm for tamper-proof of web pages. For a web page, it generates a watermark consisting of a sequence of Space and Tab. The wa termark is then embedded into the web page after each word and each line. When a watermarked web page is tampered, the extracted watermark can detect and locate the modifications to the web page. Besides, the framework of watermarked Web Server system was given. Compared with traditional digital signature methods, this watermarking method is more transparent in that there is no necessary to detach the watermark before displaying web pages. The e xperimental results show that the proposed scheme is an effective tool for tamper-proof of web pages.展开更多
Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN con...Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN controllers need to centralizedly perform a shortest-path query for every flow,usually on large-scale network. Unfortunately,one of the challenges is that current algorithms will become incalculable as the network size increases. Therefore, inspired by the compression graph in the field of compute visualization,we propose an efficient shortest path algorithm by compressing the original big network graph into a small one, but the important graph properties used to calculate path is reserved. We implement a centralized version of our approach in SDN-enabled network,and the evaluations validate the improvement compared with the well-known algorithms.展开更多
The Pathfinder paradigm has been used in generating and analyzing graph models that support clustering similar concepts and minimum-cost paths to provide an associative network structure within a domain. The co-occurr...The Pathfinder paradigm has been used in generating and analyzing graph models that support clustering similar concepts and minimum-cost paths to provide an associative network structure within a domain. The co-occurrence pathfinder network （ CPFN ） extends the traditional pathfinder paradigm so that co-occurring concepts can be calculated at each sampling time. Existing algorithms take O（n（s）） time to calculate the pathfinder network （PFN） at each sampling time for a non-completed input graph of a CPFN （r = ∞, q = n - 1）, where n is the number of nodes in the input graph, r is the Minkowski exponent and q is the maximum number of links considered in finding a minimum cost path between vertices. To reduce the complexity of calculating the CPFN, we propose a greedy based algorithm, MEC（G） algorithm, which takes shortcuts to avoid unnecessary steps in the existing algorithms, to correctly calculate a CPFN （r = ∞, q= n - 1） in O（klogk） time where k is the number of edges of the input graph. Our example demonstrates the efficiency and correctness of the proposed MEC（G） algorithm, confirming our mathematic analysis on this algorithm.展开更多
This paper presents a hybrid soft computing modeling approach for a neurofuzzy system based on rough set theory and the genetic algorithms (NFRSGA). The fundamental problem of a neurofuzzy system is that when the inpu...This paper presents a hybrid soft computing modeling approach for a neurofuzzy system based on rough set theory and the genetic algorithms (NFRSGA). The fundamental problem of a neurofuzzy system is that when the input dimension increases, the fuzzy rule base increases exponentially. This leads to a huge infrastructure network which results in slow convergence. To solve this problem, rough set theory is used to obtain the reductive rules, which are used as fuzzy rules of the fuzzy system. The number of rules decrease, and each rule does not need all the conditional attribute values. This results in a reduced, or not fully connected, neural network. The structure of the neural network is relatively small and thus the weights to be trained decrease. The genetic algorithm is used to search the optimal discretization of the continuous attributes. The NFRSGA approach has been applied in the practical application of building a soft sensor model for estimating the freezing point of the light diesel fuel in a Fluid Catalytic Cracking Unit (FCCU), and satisfying results are obtained.展开更多
A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The st...A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.展开更多
This paper investigates the routing among autonomous systems (ASs) with quality of service (QoS) requirements. To avoid the intractability of the problem, abstract QoS capability must be informed among ASs, because th...This paper investigates the routing among autonomous systems (ASs) with quality of service (QoS) requirements. To avoid the intractability of the problem, abstract QoS capability must be informed among ASs, because the routhing which constrained QoS has been proved to be nondeterministic polynomial-time (NP) hard even inside an AS. This paper employs the modified Dijkstra algorithm to compute the maximum bottleneck bandwidth inside an AS. This approach lays a basis for the AS-level switching capability on which interdomain advertisement can be performed. Furthermore, the paper models the aggregated traffic in backbone network with fractional Brownian motion (FBM), and by integrating along the time axis in short intervals, a good estimation of the distribution of queue length in the next short intervals can be obtained. The proposed advertisement mechanism can be easily implemented with the current interdomain routing protocols. Numerical study indicates that the presented scheme is effective and feasible.展开更多
The construction of multirate rearrangeable network has long been an interesting problem. Of many results published, all were achieved on 3-stage Clos network. The monotone routing algorithm proposed by Hu et al.(2001...The construction of multirate rearrangeable network has long been an interesting problem. Of many results published, all were achieved on 3-stage Clos network. The monotone routing algorithm proposed by Hu et al.(2001) was also first applied to 3-stage Clos network. In this work, we adopt this algorithm and apply it to logd(N,m,p) networks. We first analyze the properties of logd(N,m,p) networks. Then we use monotone algorithm in logd(N,0,p) network. Furthermore we extend the result to construct multirate rearrangeable networks based on logd(N,m,p) network (1≤m≤n?1).展开更多
Artifi cial neural network is a kind of artificial intelligence method to simulate the function of human brain, and deep learning technology can establish a depth network model with hierarchical structure on the basis...Artifi cial neural network is a kind of artificial intelligence method to simulate the function of human brain, and deep learning technology can establish a depth network model with hierarchical structure on the basis of artificial neural network. Deep learning brings new development direction to artificial neural network. Convolution neural network is a new artificial neural network method, which combines artificial neural network and deep learning technology, and this new neural network is widely used in many fields of computer vision. Modern image recognition algorithm requires classifi cation system to adapt to different types of tasks, and deep network and convolution neural network is a hot research topic in neural networks. According to the characteristics of satellite digital image, we use the convolution neural network to classify the image, which combines texture features with spectral features. The experimental results show that the convolution neural network algorithm can effectively classify the image.展开更多
In this paper, we incorporated peer-to-peer (P2P) concept with agent technology and put forward a collaborative work model based on peer-to-peer network (P2PCWM) after investigating into business demands of modern ent...In this paper, we incorporated peer-to-peer (P2P) concept with agent technology and put forward a collaborative work model based on peer-to-peer network (P2PCWM) after investigating into business demands of modern enterprises and problems prevailing in mainstream collaborative work systems based on central server. Theoretically, the P2PCWM can effectively overcome the problems in a conventional system with a central server and meet the practical demands of modern businesses. It is distinguished from other systems by its features of equality, openness, promptness, fairness, expandability and convenience.展开更多
Finding the shortest path （SP） in a large-scale network analysis between any two nodes is a tough but very significant task. The SP can help us to analyze the information spreading performance and research the laten...Finding the shortest path （SP） in a large-scale network analysis between any two nodes is a tough but very significant task. The SP can help us to analyze the information spreading performance and research the latent relationship in the weighted social network, and so on. As the size of the social network increases, the traditional SP algorithms have poor performance and there is not a suitable algorithm for weighted social network. Some features of the network analysis are beneficial to solve this problem, and community structure ignored by the traditional methods is one of the most important features. In this paper, we propose a shortest path algorithm based on community detection （SPCD） by integrating community detection algorithm with traditional search methods. SPCD constructs a community graph by using community structure to narrow the searching scope. The algorithm presented improves the time efficiency and maintains the accuracy scale of the SR Experimental results on five real-world networks demonstrate the effectiveness of the proposed methods for the SP problem.展开更多
Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented ...Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented in this paper. It applies the recognition rate of training samples to the learning progress of network parameters. The learning vector quantization is employed to group training samples and the Genetic algorithm （GA） is used for training the network＇ s smoothing parameters and hidden central vector for detemlining hidden neurons. Utilizing the standard dataset I （a） of BCI Competition 2003 and comparing with other classification methods, the experiment results show that the best performance of pattern recognition Js got in this way, and the classification accuracy can reach to 93.8%, which improves over 5% compared with the best result （88.7 % ） of the competition. This technology provides an effective way to EEG classification in practical system of BCI.展开更多
Learning English requires an English environment, but it is impossible for us to communicate with the English speaking people face-to-face frequently, Computer network can he said to narrow the distance between people...Learning English requires an English environment, but it is impossible for us to communicate with the English speaking people face-to-face frequently, Computer network can he said to narrow the distance between people from the space, turn the world into a global village, and provide people in the world with more and more convenient opporttmities. The use of computer-aided English teaching can make up for the deficiencies of the traditional English teaching methods, which will greatly improve English teaching. In this paper, in view of the perspective of psycholinguistics to analyze common English pod cast, network language and foreign learning phenomenon.展开更多
In this paper, a new algorithm HCOUNT ＋ is proposed to find frequent items over data stream based on the HCOUNT algorithm. The new algorithm adopts aided measures to improve the precision of HCOUNT greatly. In additi...In this paper, a new algorithm HCOUNT ＋ is proposed to find frequent items over data stream based on the HCOUNT algorithm. The new algorithm adopts aided measures to improve the precision of HCOUNT greatly. In addition,HCOUNT ＋ is introduced to time critical applications and a novel sliding windows-based algorithm SL-HCOUNT ＋ is proposed to mine the most frequent items occurring recently.This algorithm uses limited memory （nB · （1 ＋α） · e/ε·In（-M/lnρ）（α〈1） counters）, requires constant processing time per packet （only （1＋α） · ln（-M/lnρ（α〈1）） counters are updated）, makes only one pass over the streaming data,and is shown to work well in the experimental results.展开更多
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope wit...Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.展开更多
In this paper, we conduct research on the causes and coping strategies of the land subsidence caused by the tunnel construction projects. We analyze the issues from the following of the perspectives. （1） Analysis me...In this paper, we conduct research on the causes and coping strategies of the land subsidence caused by the tunnel construction projects. We analyze the issues from the following of the perspectives. （1） Analysis method. To solve large scale system of the development of computer hardware and the numerical calculation method, we use the basic analysis to deal with it. （2） The empirical of methods. Ground motion is usually leads to the basic development of the inclined tunnel surface vertical displacement, the result of the movement process can turn to a settling tank. （3） Machine learning based approaches. In one of biggest difficulties when using neural network method is to obtain all possible parameters related to ground subsidence, we use the machine learning model to handle the challenge. In the final part, we show prospect for the future research, we will combine more numerical analysis tools to optimize the current methodology.展开更多
This study looks into new perspectives in preschoolers＇ assessment of being at risk for learning disabilities. Precisely, two innovative assessment approaches are examined in order to reveal new research perspectives...This study looks into new perspectives in preschoolers＇ assessment of being at risk for learning disabilities. Precisely, two innovative assessment approaches are examined in order to reveal new research perspectives. The first tool, a traditional approach, is the ＂Early Dyslexia Identification Test＂ and the second tool, a computerized approach, is an lnternet based Speech Pathology Diagnostic Expert System named ＂APLo＂. Both evaluate the sectors of phonological awareness, memory, psychomotor development, pre-writing and pre-reading skills in Greek. The findings o f the current study formulate three directions： （1） the complementary of speech language and learning disorders as a systemic approach, （2） the diagnosis of suspicious factors and compatibilities of learning disabilities even at the preschool age, and （3） the application of alternative methods of assessment aiming for a multidimentional approach with the combined prospect and potential of web tools in the early diagnosis and intervention in learning disabilities.展开更多
This paper first describes the basic theory of BP neural network algorithm, defects and improved methods, establishes a computer network security evaluation index system, explores the computer network security evaluat...This paper first describes the basic theory of BP neural network algorithm, defects and improved methods, establishes a computer network security evaluation index system, explores the computer network security evaluation method based on BP neural network, and has designed to build the evaluation model, and shows that the method is feasible through the MATLAB simulation experiments.展开更多
文摘The concept of intelligent integrated network management (IINM) is briefly introduced. In order to analyze, design and implement IINM successfully, object oriented approach is testified to be an effective and efficient way. In this paper, object oriented technique is applied to the structural model of IINM system, The Domain object class and the MU object class are used to represent the manager and the managed resources. Especially, NM IA is introduced which is a special object class with intelligent behaviors to manage the resources efficiently.
文摘A novel reliable routing algorithm in mobile ad hoc networks using fuzzy Petri net with its reasoning mechanism was proposed to increase the reliability during the routing selection. The algorithm allows the structured representation of network topology, which has a fuzzy reasoning mechanism for finding the routing sprouting tree from the source node to the destination node in the mobile ad boc environment. Finally, by comparing the degree of reliability in the routing sprouting tree, the most reliable route can be computed. The algorithm not only offers the local reliability between each neighboring node, but also provides global reliability for the whole selected route. The algorithm can be applied to most existing on-demand routing protocols, and the simulation results show that the routing reliability is increased by more than 80% when applying the proposed algorithm to the ad hoc on demand distance vector routing protocol.
文摘This paper proposed a watermarking algorithm for tamper-proof of web pages. For a web page, it generates a watermark consisting of a sequence of Space and Tab. The wa termark is then embedded into the web page after each word and each line. When a watermarked web page is tampered, the extracted watermark can detect and locate the modifications to the web page. Besides, the framework of watermarked Web Server system was given. Compared with traditional digital signature methods, this watermarking method is more transparent in that there is no necessary to detach the watermark before displaying web pages. The e xperimental results show that the proposed scheme is an effective tool for tamper-proof of web pages.
基金supported by the National Natural Science Foundation of China(No.61521003)
文摘Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN controllers need to centralizedly perform a shortest-path query for every flow,usually on large-scale network. Unfortunately,one of the challenges is that current algorithms will become incalculable as the network size increases. Therefore, inspired by the compression graph in the field of compute visualization,we propose an efficient shortest path algorithm by compressing the original big network graph into a small one, but the important graph properties used to calculate path is reserved. We implement a centralized version of our approach in SDN-enabled network,and the evaluations validate the improvement compared with the well-known algorithms.
文摘The Pathfinder paradigm has been used in generating and analyzing graph models that support clustering similar concepts and minimum-cost paths to provide an associative network structure within a domain. The co-occurrence pathfinder network （ CPFN ） extends the traditional pathfinder paradigm so that co-occurring concepts can be calculated at each sampling time. Existing algorithms take O（n（s）） time to calculate the pathfinder network （PFN） at each sampling time for a non-completed input graph of a CPFN （r = ∞, q = n - 1）, where n is the number of nodes in the input graph, r is the Minkowski exponent and q is the maximum number of links considered in finding a minimum cost path between vertices. To reduce the complexity of calculating the CPFN, we propose a greedy based algorithm, MEC（G） algorithm, which takes shortcuts to avoid unnecessary steps in the existing algorithms, to correctly calculate a CPFN （r = ∞, q= n - 1） in O（klogk） time where k is the number of edges of the input graph. Our example demonstrates the efficiency and correctness of the proposed MEC（G） algorithm, confirming our mathematic analysis on this algorithm.
基金Sponsored by the National High Technology Research and Development Program of China (Grant No.G2001 AA413130).
文摘This paper presents a hybrid soft computing modeling approach for a neurofuzzy system based on rough set theory and the genetic algorithms (NFRSGA). The fundamental problem of a neurofuzzy system is that when the input dimension increases, the fuzzy rule base increases exponentially. This leads to a huge infrastructure network which results in slow convergence. To solve this problem, rough set theory is used to obtain the reductive rules, which are used as fuzzy rules of the fuzzy system. The number of rules decrease, and each rule does not need all the conditional attribute values. This results in a reduced, or not fully connected, neural network. The structure of the neural network is relatively small and thus the weights to be trained decrease. The genetic algorithm is used to search the optimal discretization of the continuous attributes. The NFRSGA approach has been applied in the practical application of building a soft sensor model for estimating the freezing point of the light diesel fuel in a Fluid Catalytic Cracking Unit (FCCU), and satisfying results are obtained.
基金Funded by the Open Research Fund Program of GIS Laboratory of Wuhan University (No. wd200609).
文摘A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.
文摘This paper investigates the routing among autonomous systems (ASs) with quality of service (QoS) requirements. To avoid the intractability of the problem, abstract QoS capability must be informed among ASs, because the routhing which constrained QoS has been proved to be nondeterministic polynomial-time (NP) hard even inside an AS. This paper employs the modified Dijkstra algorithm to compute the maximum bottleneck bandwidth inside an AS. This approach lays a basis for the AS-level switching capability on which interdomain advertisement can be performed. Furthermore, the paper models the aggregated traffic in backbone network with fractional Brownian motion (FBM), and by integrating along the time axis in short intervals, a good estimation of the distribution of queue length in the next short intervals can be obtained. The proposed advertisement mechanism can be easily implemented with the current interdomain routing protocols. Numerical study indicates that the presented scheme is effective and feasible.
基金Project (No. 10371028) supported by the National Natural ScienceFoundation of China
文摘The construction of multirate rearrangeable network has long been an interesting problem. Of many results published, all were achieved on 3-stage Clos network. The monotone routing algorithm proposed by Hu et al.(2001) was also first applied to 3-stage Clos network. In this work, we adopt this algorithm and apply it to logd(N,m,p) networks. We first analyze the properties of logd(N,m,p) networks. Then we use monotone algorithm in logd(N,0,p) network. Furthermore we extend the result to construct multirate rearrangeable networks based on logd(N,m,p) network (1≤m≤n?1).
文摘Artifi cial neural network is a kind of artificial intelligence method to simulate the function of human brain, and deep learning technology can establish a depth network model with hierarchical structure on the basis of artificial neural network. Deep learning brings new development direction to artificial neural network. Convolution neural network is a new artificial neural network method, which combines artificial neural network and deep learning technology, and this new neural network is widely used in many fields of computer vision. Modern image recognition algorithm requires classifi cation system to adapt to different types of tasks, and deep network and convolution neural network is a hot research topic in neural networks. According to the characteristics of satellite digital image, we use the convolution neural network to classify the image, which combines texture features with spectral features. The experimental results show that the convolution neural network algorithm can effectively classify the image.
文摘In this paper, we incorporated peer-to-peer (P2P) concept with agent technology and put forward a collaborative work model based on peer-to-peer network (P2PCWM) after investigating into business demands of modern enterprises and problems prevailing in mainstream collaborative work systems based on central server. Theoretically, the P2PCWM can effectively overcome the problems in a conventional system with a central server and meet the practical demands of modern businesses. It is distinguished from other systems by its features of equality, openness, promptness, fairness, expandability and convenience.
文摘Finding the shortest path （SP） in a large-scale network analysis between any two nodes is a tough but very significant task. The SP can help us to analyze the information spreading performance and research the latent relationship in the weighted social network, and so on. As the size of the social network increases, the traditional SP algorithms have poor performance and there is not a suitable algorithm for weighted social network. Some features of the network analysis are beneficial to solve this problem, and community structure ignored by the traditional methods is one of the most important features. In this paper, we propose a shortest path algorithm based on community detection （SPCD） by integrating community detection algorithm with traditional search methods. SPCD constructs a community graph by using community structure to narrow the searching scope. The algorithm presented improves the time efficiency and maintains the accuracy scale of the SR Experimental results on five real-world networks demonstrate the effectiveness of the proposed methods for the SP problem.
基金Supported by the National Natural Science Foundation of China (No. 30570485)the Shanghai "Chen Guang" Project (No. 09CG69).
文摘Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented in this paper. It applies the recognition rate of training samples to the learning progress of network parameters. The learning vector quantization is employed to group training samples and the Genetic algorithm （GA） is used for training the network＇ s smoothing parameters and hidden central vector for detemlining hidden neurons. Utilizing the standard dataset I （a） of BCI Competition 2003 and comparing with other classification methods, the experiment results show that the best performance of pattern recognition Js got in this way, and the classification accuracy can reach to 93.8%, which improves over 5% compared with the best result （88.7 % ） of the competition. This technology provides an effective way to EEG classification in practical system of BCI.
文摘Learning English requires an English environment, but it is impossible for us to communicate with the English speaking people face-to-face frequently, Computer network can he said to narrow the distance between people from the space, turn the world into a global village, and provide people in the world with more and more convenient opporttmities. The use of computer-aided English teaching can make up for the deficiencies of the traditional English teaching methods, which will greatly improve English teaching. In this paper, in view of the perspective of psycholinguistics to analyze common English pod cast, network language and foreign learning phenomenon.
文摘In this paper, a new algorithm HCOUNT ＋ is proposed to find frequent items over data stream based on the HCOUNT algorithm. The new algorithm adopts aided measures to improve the precision of HCOUNT greatly. In addition,HCOUNT ＋ is introduced to time critical applications and a novel sliding windows-based algorithm SL-HCOUNT ＋ is proposed to mine the most frequent items occurring recently.This algorithm uses limited memory （nB · （1 ＋α） · e/ε·In（-M/lnρ）（α〈1） counters）, requires constant processing time per packet （only （1＋α） · ln（-M/lnρ（α〈1）） counters are updated）, makes only one pass over the streaming data,and is shown to work well in the experimental results.
文摘Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.
文摘In this paper, we conduct research on the causes and coping strategies of the land subsidence caused by the tunnel construction projects. We analyze the issues from the following of the perspectives. （1） Analysis method. To solve large scale system of the development of computer hardware and the numerical calculation method, we use the basic analysis to deal with it. （2） The empirical of methods. Ground motion is usually leads to the basic development of the inclined tunnel surface vertical displacement, the result of the movement process can turn to a settling tank. （3） Machine learning based approaches. In one of biggest difficulties when using neural network method is to obtain all possible parameters related to ground subsidence, we use the machine learning model to handle the challenge. In the final part, we show prospect for the future research, we will combine more numerical analysis tools to optimize the current methodology.
文摘This study looks into new perspectives in preschoolers＇ assessment of being at risk for learning disabilities. Precisely, two innovative assessment approaches are examined in order to reveal new research perspectives. The first tool, a traditional approach, is the ＂Early Dyslexia Identification Test＂ and the second tool, a computerized approach, is an lnternet based Speech Pathology Diagnostic Expert System named ＂APLo＂. Both evaluate the sectors of phonological awareness, memory, psychomotor development, pre-writing and pre-reading skills in Greek. The findings o f the current study formulate three directions： （1） the complementary of speech language and learning disorders as a systemic approach, （2） the diagnosis of suspicious factors and compatibilities of learning disabilities even at the preschool age, and （3） the application of alternative methods of assessment aiming for a multidimentional approach with the combined prospect and potential of web tools in the early diagnosis and intervention in learning disabilities.
文摘This paper first describes the basic theory of BP neural network algorithm, defects and improved methods, establishes a computer network security evaluation index system, explores the computer network security evaluation method based on BP neural network, and has designed to build the evaluation model, and shows that the method is feasible through the MATLAB simulation experiments.
