It is difficult to measure the online values of biochemical oxygen demand(BOD) due to the characteristics of nonlinear dynamics, large lag and uncertainty in wastewater treatment process. In this paper, based on the k...It is difficult to measure the online values of biochemical oxygen demand(BOD) due to the characteristics of nonlinear dynamics, large lag and uncertainty in wastewater treatment process. In this paper, based on the knowledge representation ability and learning capability, an improved T–S fuzzy neural network(TSFNN) is introduced to predict BOD values by the soft computing method. In this improved TSFNN, a K-means clustering is used to initialize the structure of TSFNN, including the number of fuzzy rules and parameters of membership function. For training TSFNN, a gradient descent method with the momentum item is used to adjust antecedent parameters and consequent parameters. This improved TSFNN is applied to predict the BOD values in effluent of the wastewater treatment process. The simulation results show that the TSFNN with K-means clustering algorithm can measure the BOD values accurately. The algorithm presents better approximation performance than some other methods.展开更多
Compared with accurate diagnosis, the system’s selfdiagnosing capability can be greatly increased through the t/kdiagnosis strategy at most k vertexes to be mistakenly identified as faulty under the comparison model,...Compared with accurate diagnosis, the system’s selfdiagnosing capability can be greatly increased through the t/kdiagnosis strategy at most k vertexes to be mistakenly identified as faulty under the comparison model, where k is typically a small number. Based on the Preparata, Metze, and Chien(PMC)model, the n-dimensional hypercube network is proved to be t/kdiagnosable. In this paper, based on the Maeng and Malek(MM)*model, a novel t/k-fault diagnosis(1≤k≤4) algorithm of ndimensional hypercube, called t/k-MM*-DIAG, is proposed to isolate all faulty processors within the set of nodes, among which the number of fault-free nodes identified wrongly as faulty is at most k. The time complexity in our algorithm is only O(2~n n~2).展开更多
A contour shape descriptor based on discrete Fourier transform （DFT） and a K-means al- gorithm modified self-organizing feature map （SOFM） neural network are established for shape clus- tering. The given shape is ...A contour shape descriptor based on discrete Fourier transform （DFT） and a K-means al- gorithm modified self-organizing feature map （SOFM） neural network are established for shape clus- tering. The given shape is first sampled uniformly in the polar coordinate. Then the discrete series is transformed to frequency domain and constructed to a shape characteristics vector. Firstly, sample set is roughly clustered using SOFM neural network to reduce the scale of samples. K-means algo- rithm is then applied to improve the performance of SOFM neural network and process the accurate clustering. K-means algorithm also increases the controllability of the clustering. The K-means algo- rithm modified SOFM neural network is used to cluster the shape characteristics vectors which is previously constructed. With leaf shapes as an example, the simulation results show that this method is effective to cluster the contour shapes.展开更多
In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (...In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.展开更多
Bushnell and the author proposed the neural networks for NOT, AND, OR, NAND, NOR, XOR and XNOR gates. Using these neural networks, the neural networks of any logic circuits can be constructd. From this, the consistent...Bushnell and the author proposed the neural networks for NOT, AND, OR, NAND, NOR, XOR and XNOR gates. Using these neural networks, the neural networks of any logic circuits can be constructd. From this, the consistent signals in the logic circuits will be transformed into the global minimal points of a quadratic pseudo Boolean function. Thus the neural network application in the field of circuit modeling and automatic test pattern generation can be widened.展开更多
A mapping f: X→Y is called weak sequence-covering if whenever {ya} is a sequence in Y converging to y ∈ Y, there exist a subsequence {ynk} and xk∈f^-1(ynk)(k∈N) ,x∈f^-1 (y) such that xk→x. The main results are: ...A mapping f: X→Y is called weak sequence-covering if whenever {ya} is a sequence in Y converging to y ∈ Y, there exist a subsequence {ynk} and xk∈f^-1(ynk)(k∈N) ,x∈f^-1 (y) such that xk→x. The main results are: (1) Y is a sequential, Frechet, strongly Frechet space iff every weak sepuence-covering mapping onto Y is quotient, pseudo-open, countably bi-quotient respectively, (2) weak sequence-covering mapping preserves cs-network and certain k-(cs-)networks, thus some new mapping theorems on k-(cs-)notworks are proved.展开更多
The probability model is used to analyze the fault tolerance of mesh. To simplify its analysis, it is as-sumed that the failure probability of each node is independent. A 3-D mesh is partitioned into smaller submeshes...The probability model is used to analyze the fault tolerance of mesh. To simplify its analysis, it is as-sumed that the failure probability of each node is independent. A 3-D mesh is partitioned into smaller submeshes,and then the probability with which each submesh satisfies the defined condition is computed. If each submesh satis-fies the condition, then the whole mesh is connected. Consequently, the probability that a 3-D mesh is connected iscomputed assuming each node has a failure probability. Mathematical methods are used to derive a relationship be-tween network node failure probability and network connectivity probability. The calculated results show that the 3-D mesh networks can remain connected with very high probability in practice. It is formally proved that when thenetwork node failure probability is boutded by 0.45 %, the 3-D mesh networks of more than three hundred thousandnodes remain connected with probability larger than 99 %. The theoretical results show that the method is a power-ful technique to calculate the lower bound of the connectivity probability of mesh networks.展开更多
A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low...A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low-dimensional ones, and moreover, to implement data compression and play down complexity of the neural network. With the character to reduce eigenspace dimensionality of K-L transform and the ability to map data of BP network, the method does effectively in recognizing license plates.展开更多
In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS n...In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS networks restrict the number of paths that a commodity can use, for maintaining the quality of service (QoS) of the users, the demand of each commodity must be satisfied. Under the above conditions, some links in the network may be too much loaded, affecting the performance of the whole network drastically. For this problem, in [1], we proposed two mathematical models to describe it and a heuristic algorithm which quickly finds transmitting paths for each commodity are also presented. In this paper, we propose a new heuristic algorithm which finds a feasible path set for each commodity, and then select some paths from the path set through a mixed integer linear programming to transmit the demand of each commodity. This strategy reduces the scale of the original problem to a large extent. We test 50 instances and the results show the effectiveness of the new heuristic algorithm.展开更多
基金Supported by the National Natural Science Foundation of China(61203099,61034008,61225016)Beijing Science and Technology Project(Z141100001414005)+3 种基金Beijing Science and Technology Special Project(Z141101004414058)Ph.D.Program Foundation from Ministry of Chinese Education(20121103120020)Beijing Nova Program(Z131104000413007)Hong Kong Scholar Program(XJ2013018)
文摘It is difficult to measure the online values of biochemical oxygen demand(BOD) due to the characteristics of nonlinear dynamics, large lag and uncertainty in wastewater treatment process. In this paper, based on the knowledge representation ability and learning capability, an improved T–S fuzzy neural network(TSFNN) is introduced to predict BOD values by the soft computing method. In this improved TSFNN, a K-means clustering is used to initialize the structure of TSFNN, including the number of fuzzy rules and parameters of membership function. For training TSFNN, a gradient descent method with the momentum item is used to adjust antecedent parameters and consequent parameters. This improved TSFNN is applied to predict the BOD values in effluent of the wastewater treatment process. The simulation results show that the TSFNN with K-means clustering algorithm can measure the BOD values accurately. The algorithm presents better approximation performance than some other methods.
基金supported by the National Natural Science Foundation of China(61363002)
文摘Compared with accurate diagnosis, the system’s selfdiagnosing capability can be greatly increased through the t/kdiagnosis strategy at most k vertexes to be mistakenly identified as faulty under the comparison model, where k is typically a small number. Based on the Preparata, Metze, and Chien(PMC)model, the n-dimensional hypercube network is proved to be t/kdiagnosable. In this paper, based on the Maeng and Malek(MM)*model, a novel t/k-fault diagnosis(1≤k≤4) algorithm of ndimensional hypercube, called t/k-MM*-DIAG, is proposed to isolate all faulty processors within the set of nodes, among which the number of fault-free nodes identified wrongly as faulty is at most k. The time complexity in our algorithm is only O(2~n n~2).
基金Supported by Guangdong Province Key Science and TechnologyItem(2011A010801005,2010A080402015)the National NaturalScience Foundation of China(61171142)
文摘A contour shape descriptor based on discrete Fourier transform （DFT） and a K-means al- gorithm modified self-organizing feature map （SOFM） neural network are established for shape clus- tering. The given shape is first sampled uniformly in the polar coordinate. Then the discrete series is transformed to frequency domain and constructed to a shape characteristics vector. Firstly, sample set is roughly clustered using SOFM neural network to reduce the scale of samples. K-means algo- rithm is then applied to improve the performance of SOFM neural network and process the accurate clustering. K-means algorithm also increases the controllability of the clustering. The K-means algo- rithm modified SOFM neural network is used to cluster the shape characteristics vectors which is previously constructed. With leaf shapes as an example, the simulation results show that this method is effective to cluster the contour shapes.
文摘In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.
文摘Bushnell and the author proposed the neural networks for NOT, AND, OR, NAND, NOR, XOR and XNOR gates. Using these neural networks, the neural networks of any logic circuits can be constructd. From this, the consistent signals in the logic circuits will be transformed into the global minimal points of a quadratic pseudo Boolean function. Thus the neural network application in the field of circuit modeling and automatic test pattern generation can be widened.
文摘A mapping f: X→Y is called weak sequence-covering if whenever {ya} is a sequence in Y converging to y ∈ Y, there exist a subsequence {ynk} and xk∈f^-1(ynk)(k∈N) ,x∈f^-1 (y) such that xk→x. The main results are: (1) Y is a sequential, Frechet, strongly Frechet space iff every weak sepuence-covering mapping onto Y is quotient, pseudo-open, countably bi-quotient respectively, (2) weak sequence-covering mapping preserves cs-network and certain k-(cs-)networks, thus some new mapping theorems on k-(cs-)notworks are proved.
基金Project (69928201) supported by the National Science Fund for Distinguished Young Scholars+1 种基金project (90104028) by the National Natural Science Foundation of China Project by Changjiang Scholar Re-ward Project
文摘The probability model is used to analyze the fault tolerance of mesh. To simplify its analysis, it is as-sumed that the failure probability of each node is independent. A 3-D mesh is partitioned into smaller submeshes,and then the probability with which each submesh satisfies the defined condition is computed. If each submesh satis-fies the condition, then the whole mesh is connected. Consequently, the probability that a 3-D mesh is connected iscomputed assuming each node has a failure probability. Mathematical methods are used to derive a relationship be-tween network node failure probability and network connectivity probability. The calculated results show that the 3-D mesh networks can remain connected with very high probability in practice. It is formally proved that when thenetwork node failure probability is boutded by 0.45 %, the 3-D mesh networks of more than three hundred thousandnodes remain connected with probability larger than 99 %. The theoretical results show that the method is a power-ful technique to calculate the lower bound of the connectivity probability of mesh networks.
文摘A method of vehicle license plate recognition utilizing Karhunen-Loeve(K-L) transform is provided. The transform is used to extract features from a mass of image templates, to describe high-dimensional images with low-dimensional ones, and moreover, to implement data compression and play down complexity of the neural network. With the character to reduce eigenspace dimensionality of K-L transform and the ability to map data of BP network, the method does effectively in recognizing license plates.
文摘In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS networks restrict the number of paths that a commodity can use, for maintaining the quality of service (QoS) of the users, the demand of each commodity must be satisfied. Under the above conditions, some links in the network may be too much loaded, affecting the performance of the whole network drastically. For this problem, in [1], we proposed two mathematical models to describe it and a heuristic algorithm which quickly finds transmitting paths for each commodity are also presented. In this paper, we propose a new heuristic algorithm which finds a feasible path set for each commodity, and then select some paths from the path set through a mixed integer linear programming to transmit the demand of each commodity. This strategy reduces the scale of the original problem to a large extent. We test 50 instances and the results show the effectiveness of the new heuristic algorithm.
