Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential rel...Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms:(1)multi-output regressor stacking;(2) multi-output extremely randomized trees; and(3) hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.展开更多
A clonal selection based memetic algorithm is proposed for solving job shop scheduling problems in this paper. In the proposed algorithm, the clonal selection and the local search mechanism are designed to enhance exp...A clonal selection based memetic algorithm is proposed for solving job shop scheduling problems in this paper. In the proposed algorithm, the clonal selection and the local search mechanism are designed to enhance exploration and exploitation. In the clonal selection mechanism, clonal selection, hypermutation and receptor edit theories are presented to construct an evolutionary searching mechanism which is used for exploration. In the local search mechanism, a simulated annealing local search algorithm based on Nowicki and Smutnicki's neighborhood is presented to exploit local optima. The proposed algorithm is examined using some well-known benchmark problems. Numerical results validate the effectiveness of the proposed algorithm.展开更多
In this paper,negative selection and genetic algorithms are combined and an improved bi-objective optimization scheme is presented to achieve optimized negative selection algorithm detectors.The main aim of the optima...In this paper,negative selection and genetic algorithms are combined and an improved bi-objective optimization scheme is presented to achieve optimized negative selection algorithm detectors.The main aim of the optimal detector generation technique is maximal nonself space coverage with reduced number of diversified detectors.Conventionally,researchers opted clonal selection based optimization methods to achieve the maximal nonself coverage milestone;however,detectors cloning process results in generation of redundant similar detectors and inefficient detector distribution in nonself space.In approach proposed in the present paper,the maximal nonself space coverage is associated with bi-objective optimization criteria including minimization of the detector overlap and maximization of the diversity factor of the detectors.In the proposed methodology,a novel diversity factorbased approach is presented to obtain diversified detector distribution in the nonself space.The concept of diversified detector distribution is studied for detector coverage with 2-dimensional pentagram and spiral self-patterns.Furthermore,the feasibility of the developed fault detection methodology is tested the fault detection of induction motor inner race and outer race bearings.展开更多
Using a relaying system to provide spatial diversity and improve the system performance is a tendency in the wireless cooperative communications. Amplify-and-forward (AF) mode with a low complexity is easy to be imp...Using a relaying system to provide spatial diversity and improve the system performance is a tendency in the wireless cooperative communications. Amplify-and-forward (AF) mode with a low complexity is easy to be implemented. Under the consideration of cooperative communication systems, the scenario includes one information source, M relay stations and N destinations. This work proposes a relay selection algorithm in the Raleigh fading channel. Based on the exhaustive search method, easily to realize, the optimal selection scheme can be found with a highly complicated calculation. In order to reduce the computational complexity, an approximate optimal solution with a greedy algorithm applied for the relay station selection is proposed. With different situations of the communication systems, the performance evaluation obtained by both the proposed algorithm and the exhaustive search algorithm are given for comparison. It shows the proposed algorithm could provide a solution approach to the optimal one.展开更多
The negative selection algorithm(NSA)is an adaptive technique inspired by how the biological immune system discriminates the self from nonself.It asserts itself as one of the most important algorithms of the artificia...The negative selection algorithm(NSA)is an adaptive technique inspired by how the biological immune system discriminates the self from nonself.It asserts itself as one of the most important algorithms of the artificial immune system.A key element of the NSA is its great dependency on the random detectors in monitoring for any abnormalities.However,these detectors have limited performance.Redundant detectors are generated,leading to difficulties for detectors to effectively occupy the non-self space.To alleviate this problem,we propose the nature-inspired metaheuristic cuckoo search(CS),a stochastic global search algorithm,which improves the random generation of detectors in the NSA.Inbuilt characteristics such as mutation,crossover,and selection operators make the CS attain global convergence.With the use of Lévy flight and a distance measure,efficient detectors are produced.Experimental results show that integrating CS into the negative selection algorithm elevated the detection performance of the NSA,with an average increase of 3.52%detection rate on the tested datasets.The proposed method shows superiority over other models,and detection rates of 98%and 99.29%on Fisher’s IRIS and Breast Cancer datasets,respectively.Thus,the generation of highest detection rates and lowest false alarm rates can be achieved.展开更多
In themarine electric power system,the marine generators will be disturbed by the large change of loads or the fault of the power system.The marine generators usually installed power system stabilizers to damp power s...In themarine electric power system,the marine generators will be disturbed by the large change of loads or the fault of the power system.The marine generators usually installed power system stabilizers to damp power system oscillations through the excitation control.This paper proposes a novel method to obtain optimal parameter values for Power System Stabilizer(PSS)to suppress low-frequency oscillations in the marine electric power system.In this paper,a newly developed immune clone selection algorithm was improved from the three aspects of the adaptive incentive degree,vaccination,and adaptive mutation strategies.Firstly,the typical PSS implementation type of leader-lag structure was adopted and the objective function was set in the optimization process.The performance of PSS tuned by improved immune clone selection algorithm was compared with PSS tuned by basic immune clone selection algorithm(ICSA)under various operating conditions and disturbances.Then,an improved immune clone selection algorithm(IICSA)optimization technique was implemented on two test systems for test purposes.Based on the simulations,it is found that an improved immune clone selection algorithm demonstrates superiority over the basic immune clone selection algorithm in getting a smaller number of iterations and fast convergence rates to achieve the optimal parameters of the power system stabilizers.Moreover,the proposed approach improves the stability and dynamic performance under various loads conditions and disturbances of the marine electric power system.展开更多
Based on the fuzzy expert system fault diagnosis theory, the knowledge base architecture and inference engine algorithm are put forward for avionic device fault diagnosis. The knowledge base is constructed by fault qu...Based on the fuzzy expert system fault diagnosis theory, the knowledge base architecture and inference engine algorithm are put forward for avionic device fault diagnosis. The knowledge base is constructed by fault query network, of which the basic ele- ment is the test-diagnosis fault unit. Every underlying fault cause's membership degree is calculated using fuzzy product inference algorithm, and the fault answer best selection algorithm is developed, to which the deep knowledge is applied. Using some examples the proposed algorithm is analyzed for its capability of synthesis diagnosis and its improvement compared to greater membership degree first principle.展开更多
Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,...Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,the nonselfdetector generation efficiency is low;a large number of nonselfdetector is needed for precise detection;low detection rate with various application data sets.Aiming at those problems,a novel radius adaptive based on center-optimized hybrid detector generation algorithm(RACO-HDG)is put forward.To our best knowledge,radius adaptive based on center optimization is first time analyzed and proposed as an efficient mechanism to improve both detector generation and detection rate without significant computation complexity.RACO-HDG works efficiently in three phases.At first,a small number of self-detectors are generated,different from typical NSAs with a large number of self-sample are generated.Nonself-detectors will be generated from those initial small number of self-detectors to make hybrid detection of self-detectors and nonself-detectors possible.Secondly,without any prior knowledge of the data sets or manual setting,the nonself-detector radius threshold is self-adaptive by optimizing the nonself-detector center and the generation mechanism.In this way,the number of abnormal detectors is decreased sharply,while the coverage area of the nonself-detector is increased otherwise,leading to higher detection performances of RACOHDG.Finally,hybrid detection algorithm is proposed with both self-detectors and nonself-detectors work together to increase detection rate as expected.Abundant simulations and application results show that the proposed RACO-HDG has higher detection rate,lower false alarm rate and higher detection efficiency compared with other excellent algorithms.展开更多
The recycling of glass bottles can reduce the consumption of resources and contribute to environmental protection.At present,the classification of recycled glass bottles is difficult due to the many differences in spe...The recycling of glass bottles can reduce the consumption of resources and contribute to environmental protection.At present,the classification of recycled glass bottles is difficult due to the many differences in specifications and models.This paper proposes a classification algorithm for glass bottles that is divided into two stages,namely the extraction of candidate regions and the classification of classifiers.In the candidate region extraction stage,aiming at the problem of the large time overhead caused by the use of the SIFT(scale-invariant feature transform)descriptor in SS(selective search),an improved feature of HLSN(Haar-like based on SPP-Net)is proposed.An integral graph is introduced to accelerate the process of forming an HBSN vector,which overcomes the problem of repeated texture feature calculation in overlapping regions by SS.In the classification stage,the improved SS algorithm is used to extract target regions.The target regions are merged using a non-maximum suppression algorithm according to the classification scores of the respective regions,and the merged regions are classified using the trained classifier.Experiments demonstrate that,compared with the original SS,the improved SS algorithm increases the calculation speed by 13.8%,and its classification accuracy is 89.4%.Additionally,the classification algorithm for glass bottles has a certain resistance to noise.展开更多
In order to accomplish the task of object recognition in natural scenes,a new object recognition algorithm based on an improved convolutional neural network(CNN)is proposed.First,candidate object windows are extracted...In order to accomplish the task of object recognition in natural scenes,a new object recognition algorithm based on an improved convolutional neural network(CNN)is proposed.First,candidate object windows are extracted from the original image.Then,candidate object windows are input into the improved CNN model to obtain deep features.Finally,the deep features are input into the Softmax and the confidence scores of classes are obtained.The candidate object window with the highest confidence score is selected as the object recognition result.Based on AlexNet,Inception V1 is introduced into the improved CNN and the fully connected layer is replaced by the average pooling layer,which widens the network and deepens the network at the same time.Experimental results show that the improved object recognition algorithm can obtain better recognition results in multiple natural scene images,and has a higher degree of accuracy than the classical algorithms in the field of object recognition.展开更多
Current mobility management schemes usually represent centralized or hierarchical architectures,which force data traffic to be processed by a centralized mobility anchor.This allows the mobile node(MN)to be reachable ...Current mobility management schemes usually represent centralized or hierarchical architectures,which force data traffic to be processed by a centralized mobility anchor.This allows the mobile node(MN)to be reachable anywhere and provides an efficient method for seamless session continuity.However,all of the signal messages and data traffic converge on particular mobility anchor,which causes excessive signaling and traffic at the centralized mobility anchor and single point of failure issues as data traffic increases.To overcome these limitations and handle increasing data traffic,the distributed mobility management(DMM)scheme has emerged as an alternative solution.Although previous researches have been conducted on DMM support,because their schemes employ an unconditional way to make direct paths after handover,they have some drawbacks,such as several signaling and chain of tunneling problems.Therefore,this paper introduces a new DMM scheme which adaptively creates a direct path.To support it,we present the path selection algorithm,which selects the most efficient path between a direct path and no direct path based on routing hops and traffic load.Through the performance analysis and results,we confirm that the proposed scheme is superior in terms of signaling and packet delivery costs.展开更多
This paper investigates the Quality of Experience(QoE)oriented channel access anti-jamming problem in 5th Generation Mobile Communication(5G)ultra-dense networks.Firstly,considering that the 5G base station adopts bea...This paper investigates the Quality of Experience(QoE)oriented channel access anti-jamming problem in 5th Generation Mobile Communication(5G)ultra-dense networks.Firstly,considering that the 5G base station adopts beamforming technology,an anti-jamming model under Space Division Multiple Access(SDMA)conditions is proposed.Secondly,the confrontational relationship between users and the jammer is formulated as a Stackelberg game.Besides,to achieve global optimization,we design a local cooperation mechanism for users and formulate the cooperation and competition among users as a local altruistic game.By proving that the local altruistic game is an Exact Potential Game(EPG),we further prove the existence of pure strategy Nash Equilibrium(NE)among users and Stackelberg Equilibrium(SE)between users and jammer.Thirdly,to obtain the equilibrium solutions of the proposed games,we propose an anti-jamming channel selection algorithm and improve its convergence speed through heterogeneous learning parameters.The simulation results validate the convergence and effectiveness of the proposed algorithm.Compared with the throughput optimization scheme,our proposed scheme obtain a greater network satisfaction rate.Finally,we also analyze user fairness changes during the algorithm convergence process and get some interesting conclusions.展开更多
In cloud computing Resource allocation is a very complex task.Handling the customer demand makes the challenges of on-demand resource allocation.Many challenges are faced by conventional methods for resource allocatio...In cloud computing Resource allocation is a very complex task.Handling the customer demand makes the challenges of on-demand resource allocation.Many challenges are faced by conventional methods for resource allocation in order tomeet the Quality of Service(QoS)requirements of users.For solving the about said problems a new method was implemented with the utility of machine learning framework of resource allocation by utilizing the cloud computing technique was taken in to an account in this research work.The accuracy in the machine learning algorithm can be improved by introducing Bat Algorithm with feature selection(BFS)in the proposed work,this further reduces the inappropriate features from the data.The similarities that were hidden can be demoralized by the Support Vector Machine(SVM)classifier which is also determine the subspace vector and then a new feature vector can be predicted by using SVM.For an unexpected circumstance SVM model can make a resource allocation decision.The efficiency of proposed SVM classifier of resource allocation can be highlighted by using a singlecell multiuser massive Multiple-Input Multiple Output(MIMO)system,with beam allocation problem as an example.The proposed resource allocation based on SVM performs efficiently than the existing conventional methods;this has been proven by analysing its results.展开更多
In service oriented architecture (SOA), service composition is a promising way to create new services. However, some technical challenges are hindering the application of service composition. One of the greatest cha...In service oriented architecture (SOA), service composition is a promising way to create new services. However, some technical challenges are hindering the application of service composition. One of the greatest challenges for composite service provider is to select a set of services to instantiate composite service with end- to-end quality of service (QoS) assurance across different autonomous networks and business regions. This paper presents an iterative service selection algorithm for quality driven service composition. The algorithm runs on a peer-to-peer (P2P) service execution environment--distributed intelligent service execution (DISE), which provides scalable QoS registry, dynamic service selection and service execution services. The most significant feature of our iterative service selection algorithm is that it can work on a centralized QoS registry as well as cross decentralized ones. Network status is an optional factor in our QoS model and selection algorithm. The algorithm iteratively selects services following service execution order, so it can be applied either before service execution or at service run-time without any modification. We test our algorithm with a series of experiments on DISE. Experimental results illustrated its excellent selection and outstanding performance.展开更多
Apple leaf disease is one of the main factors to constrain the apple production and quality.It takes a long time to detect the diseases by using the traditional diagnostic approach,thus farmers often miss the best tim...Apple leaf disease is one of the main factors to constrain the apple production and quality.It takes a long time to detect the diseases by using the traditional diagnostic approach,thus farmers often miss the best time to prevent and treat the diseases.Apple leaf disease recognition based on leaf image is an essential research topic in the field of computer vision,where the key task is to find an effective way to represent the diseased leaf images.In this research,based on image processing techniques and pattern recognition methods,an apple leaf disease recognition method was proposed.A color transformation structure for the input RGB(Red,Green and Blue)image was designed firstly and then RGB model was converted to HSI(Hue,Saturation and Intensity),YUV and gray models.The background was removed based on a specific threshold value,and then the disease spot image was segmented with region growing algorithm(RGA).Thirty-eight classifying features of color,texture and shape were extracted from each spot image.To reduce the dimensionality of the feature space and improve the accuracy of the apple leaf disease identification,the most valuable features were selected by combining genetic algorithm(GA)and correlation based feature selection(CFS).Finally,the diseases were recognized by SVM classifier.In the proposed method,the selected feature subset was globally optimum.The experimental results of more than 90%correct identification rate on the apple diseased leaf image database which contains 90 disease images for there kinds of apple leaf diseases,powdery mildew,mosaic and rust,demonstrate that the proposed method is feasible and effective.展开更多
Prediction plays a vital role in decision making. Correct prediction leads to right decision making to save the life, energy,efforts, money and time. The right decision prevents physical and material losses and it is ...Prediction plays a vital role in decision making. Correct prediction leads to right decision making to save the life, energy,efforts, money and time. The right decision prevents physical and material losses and it is practiced in all the fields including medical,finance, environmental studies, engineering and emerging technologies. Prediction is carried out by a model called classifier. The predictive accuracy of the classifier highly depends on the training datasets utilized for training the classifier. The irrelevant and redundant features of the training dataset reduce the accuracy of the classifier. Hence, the irrelevant and redundant features must be removed from the training dataset through the process known as feature selection. This paper proposes a feature selection algorithm namely unsupervised learning with ranking based feature selection(FSULR). It removes redundant features by clustering and eliminates irrelevant features by statistical measures to select the most significant features from the training dataset. The performance of this proposed algorithm is compared with the other seven feature selection algorithms by well known classifiers namely naive Bayes(NB),instance based(IB1) and tree based J48. Experimental results show that the proposed algorithm yields better prediction accuracy for classifiers.展开更多
To address cross-ISP traffic problem caused by BitTorrent,we present our design and evaluation of a proximity-aware BitTorrent system. In our approach,clients generate global proximity-aware information by using landm...To address cross-ISP traffic problem caused by BitTorrent,we present our design and evaluation of a proximity-aware BitTorrent system. In our approach,clients generate global proximity-aware information by using landmark clustering;the tracker uses this proximity to maintain all peers in an orderly way and hands back a biased subset consisting of the peers who are physically closest to the requestor. Our approach requires no co-operation between P2P users and their Internet infra structures,such as ISPs or CDNs,no constantly path monitoring or probing their neighbors. The simulation results show that our approach can not only reduce unnecessary cross-ISP traffic,but also allow downloadsing fast.展开更多
Objective: Identification of colorectal cancer (CRC) metastasis genes is one of the most important issues in CRC research. For the purpose of mining CRC metastasis-associated genes, an integrated analysis of mJcroa...Objective: Identification of colorectal cancer (CRC) metastasis genes is one of the most important issues in CRC research. For the purpose of mining CRC metastasis-associated genes, an integrated analysis of mJcroarray data was presented, by combined with evidence acquired from comparative genornic hybridization (CGH) data. Methods: Gene expression profile data of CRC samples were obtained at Gene Expression Omnibus (GEO) website. The 15 important chromosomal aberration sites detected by using CGH technology were used for integrated genomic and transcriptomic analysis. Significant Analysis of Microarray (SAM) was used to detect significantly differentially expressed genes across the whole genome. The overlapping genes were selected in their corresponding chromosomal aberration regions, and analyzed by using the Database for Annotation, Visualization and Integrated Discovery (DAVID). Finally, SVM-T-RFE gene selection algorithm was applied to identify ted genes in CRC. Results: A minimum gene set was obtained with the minimum number [14] of genes, and the highest classification accuracy (100%) in both PRI and META datasets. A fraction of selected genes are associated with CRC or its metastasis. Conclusions- Our results demonstrated that integration analysis is an effective strategy for mining cancer- associated genes.展开更多
基金mainly supported by the National Natural Science Foundation of China(Nos.61125201,61303070,and U1435219)
文摘Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms:(1)multi-output regressor stacking;(2) multi-output extremely randomized trees; and(3) hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.
文摘A clonal selection based memetic algorithm is proposed for solving job shop scheduling problems in this paper. In the proposed algorithm, the clonal selection and the local search mechanism are designed to enhance exploration and exploitation. In the clonal selection mechanism, clonal selection, hypermutation and receptor edit theories are presented to construct an evolutionary searching mechanism which is used for exploration. In the local search mechanism, a simulated annealing local search algorithm based on Nowicki and Smutnicki's neighborhood is presented to exploit local optima. The proposed algorithm is examined using some well-known benchmark problems. Numerical results validate the effectiveness of the proposed algorithm.
文摘In this paper,negative selection and genetic algorithms are combined and an improved bi-objective optimization scheme is presented to achieve optimized negative selection algorithm detectors.The main aim of the optimal detector generation technique is maximal nonself space coverage with reduced number of diversified detectors.Conventionally,researchers opted clonal selection based optimization methods to achieve the maximal nonself coverage milestone;however,detectors cloning process results in generation of redundant similar detectors and inefficient detector distribution in nonself space.In approach proposed in the present paper,the maximal nonself space coverage is associated with bi-objective optimization criteria including minimization of the detector overlap and maximization of the diversity factor of the detectors.In the proposed methodology,a novel diversity factorbased approach is presented to obtain diversified detector distribution in the nonself space.The concept of diversified detector distribution is studied for detector coverage with 2-dimensional pentagram and spiral self-patterns.Furthermore,the feasibility of the developed fault detection methodology is tested the fault detection of induction motor inner race and outer race bearings.
基金supported by National Science Council under Grant No.101-2221-E-029-020-MY3
文摘Using a relaying system to provide spatial diversity and improve the system performance is a tendency in the wireless cooperative communications. Amplify-and-forward (AF) mode with a low complexity is easy to be implemented. Under the consideration of cooperative communication systems, the scenario includes one information source, M relay stations and N destinations. This work proposes a relay selection algorithm in the Raleigh fading channel. Based on the exhaustive search method, easily to realize, the optimal selection scheme can be found with a highly complicated calculation. In order to reduce the computational complexity, an approximate optimal solution with a greedy algorithm applied for the relay station selection is proposed. With different situations of the communication systems, the performance evaluation obtained by both the proposed algorithm and the exhaustive search algorithm are given for comparison. It shows the proposed algorithm could provide a solution approach to the optimal one.
文摘The negative selection algorithm(NSA)is an adaptive technique inspired by how the biological immune system discriminates the self from nonself.It asserts itself as one of the most important algorithms of the artificial immune system.A key element of the NSA is its great dependency on the random detectors in monitoring for any abnormalities.However,these detectors have limited performance.Redundant detectors are generated,leading to difficulties for detectors to effectively occupy the non-self space.To alleviate this problem,we propose the nature-inspired metaheuristic cuckoo search(CS),a stochastic global search algorithm,which improves the random generation of detectors in the NSA.Inbuilt characteristics such as mutation,crossover,and selection operators make the CS attain global convergence.With the use of Lévy flight and a distance measure,efficient detectors are produced.Experimental results show that integrating CS into the negative selection algorithm elevated the detection performance of the NSA,with an average increase of 3.52%detection rate on the tested datasets.The proposed method shows superiority over other models,and detection rates of 98%and 99.29%on Fisher’s IRIS and Breast Cancer datasets,respectively.Thus,the generation of highest detection rates and lowest false alarm rates can be achieved.
基金This work is supported by Shanghai Science and Technology Planning Project(Project No.20040501200).
文摘In themarine electric power system,the marine generators will be disturbed by the large change of loads or the fault of the power system.The marine generators usually installed power system stabilizers to damp power system oscillations through the excitation control.This paper proposes a novel method to obtain optimal parameter values for Power System Stabilizer(PSS)to suppress low-frequency oscillations in the marine electric power system.In this paper,a newly developed immune clone selection algorithm was improved from the three aspects of the adaptive incentive degree,vaccination,and adaptive mutation strategies.Firstly,the typical PSS implementation type of leader-lag structure was adopted and the objective function was set in the optimization process.The performance of PSS tuned by improved immune clone selection algorithm was compared with PSS tuned by basic immune clone selection algorithm(ICSA)under various operating conditions and disturbances.Then,an improved immune clone selection algorithm(IICSA)optimization technique was implemented on two test systems for test purposes.Based on the simulations,it is found that an improved immune clone selection algorithm demonstrates superiority over the basic immune clone selection algorithm in getting a smaller number of iterations and fast convergence rates to achieve the optimal parameters of the power system stabilizers.Moreover,the proposed approach improves the stability and dynamic performance under various loads conditions and disturbances of the marine electric power system.
基金The 11th Five-year National Defense Preliminary Research Projects (B0520060455)
文摘Based on the fuzzy expert system fault diagnosis theory, the knowledge base architecture and inference engine algorithm are put forward for avionic device fault diagnosis. The knowledge base is constructed by fault query network, of which the basic ele- ment is the test-diagnosis fault unit. Every underlying fault cause's membership degree is calculated using fuzzy product inference algorithm, and the fault answer best selection algorithm is developed, to which the deep knowledge is applied. Using some examples the proposed algorithm is analyzed for its capability of synthesis diagnosis and its improvement compared to greater membership degree first principle.
基金supported by the National Natural Science Foundation of China(61502423,62072406)the Natural Science Foundation of Zhejiang Provincial(LY19F020025)the Major Special Funding for“Science and Technology Innovation 2025”in Ningbo(2018B10063)。
文摘Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,the nonselfdetector generation efficiency is low;a large number of nonselfdetector is needed for precise detection;low detection rate with various application data sets.Aiming at those problems,a novel radius adaptive based on center-optimized hybrid detector generation algorithm(RACO-HDG)is put forward.To our best knowledge,radius adaptive based on center optimization is first time analyzed and proposed as an efficient mechanism to improve both detector generation and detection rate without significant computation complexity.RACO-HDG works efficiently in three phases.At first,a small number of self-detectors are generated,different from typical NSAs with a large number of self-sample are generated.Nonself-detectors will be generated from those initial small number of self-detectors to make hybrid detection of self-detectors and nonself-detectors possible.Secondly,without any prior knowledge of the data sets or manual setting,the nonself-detector radius threshold is self-adaptive by optimizing the nonself-detector center and the generation mechanism.In this way,the number of abnormal detectors is decreased sharply,while the coverage area of the nonself-detector is increased otherwise,leading to higher detection performances of RACOHDG.Finally,hybrid detection algorithm is proposed with both self-detectors and nonself-detectors work together to increase detection rate as expected.Abundant simulations and application results show that the proposed RACO-HDG has higher detection rate,lower false alarm rate and higher detection efficiency compared with other excellent algorithms.
基金Research Foundation of Education Bureau of Jilin Province(JJKN20190710KJ)Science and Technology Innovation Development Plan Project of Jilin city(20190302202).
文摘The recycling of glass bottles can reduce the consumption of resources and contribute to environmental protection.At present,the classification of recycled glass bottles is difficult due to the many differences in specifications and models.This paper proposes a classification algorithm for glass bottles that is divided into two stages,namely the extraction of candidate regions and the classification of classifiers.In the candidate region extraction stage,aiming at the problem of the large time overhead caused by the use of the SIFT(scale-invariant feature transform)descriptor in SS(selective search),an improved feature of HLSN(Haar-like based on SPP-Net)is proposed.An integral graph is introduced to accelerate the process of forming an HBSN vector,which overcomes the problem of repeated texture feature calculation in overlapping regions by SS.In the classification stage,the improved SS algorithm is used to extract target regions.The target regions are merged using a non-maximum suppression algorithm according to the classification scores of the respective regions,and the merged regions are classified using the trained classifier.Experiments demonstrate that,compared with the original SS,the improved SS algorithm increases the calculation speed by 13.8%,and its classification accuracy is 89.4%.Additionally,the classification algorithm for glass bottles has a certain resistance to noise.
基金Supported by the National Natural Science Foundation of China(61701029)Basic Research Foundation of Beijing Institute of Technology(20170542008)Industry-University Research Innovation Foundation of the Science and Technology Development Center of the Ministry of Education(2018A02012)。
文摘In order to accomplish the task of object recognition in natural scenes,a new object recognition algorithm based on an improved convolutional neural network(CNN)is proposed.First,candidate object windows are extracted from the original image.Then,candidate object windows are input into the improved CNN model to obtain deep features.Finally,the deep features are input into the Softmax and the confidence scores of classes are obtained.The candidate object window with the highest confidence score is selected as the object recognition result.Based on AlexNet,Inception V1 is introduced into the improved CNN and the fully connected layer is replaced by the average pooling layer,which widens the network and deepens the network at the same time.Experimental results show that the improved object recognition algorithm can obtain better recognition results in multiple natural scene images,and has a higher degree of accuracy than the classical algorithms in the field of object recognition.
基金MKE(the Ministry of Knowledge Economy),Korea,under the Convergence-ITRC support program(NIPA-2011C6150-1101-0004)supervised by the NIPA(National IT Industry Promotion Agency)KCC(Korea Communications Commis-sion),Korea,under the R&D program supervised by the KCA(Korea Communications Agency)(KCA-2011-08913-05001)
文摘Current mobility management schemes usually represent centralized or hierarchical architectures,which force data traffic to be processed by a centralized mobility anchor.This allows the mobile node(MN)to be reachable anywhere and provides an efficient method for seamless session continuity.However,all of the signal messages and data traffic converge on particular mobility anchor,which causes excessive signaling and traffic at the centralized mobility anchor and single point of failure issues as data traffic increases.To overcome these limitations and handle increasing data traffic,the distributed mobility management(DMM)scheme has emerged as an alternative solution.Although previous researches have been conducted on DMM support,because their schemes employ an unconditional way to make direct paths after handover,they have some drawbacks,such as several signaling and chain of tunneling problems.Therefore,this paper introduces a new DMM scheme which adaptively creates a direct path.To support it,we present the path selection algorithm,which selects the most efficient path between a direct path and no direct path based on routing hops and traffic load.Through the performance analysis and results,we confirm that the proposed scheme is superior in terms of signaling and packet delivery costs.
基金supported by the National Natural Science Foundation of China under Grant No.61901523 and No.62071488.
文摘This paper investigates the Quality of Experience(QoE)oriented channel access anti-jamming problem in 5th Generation Mobile Communication(5G)ultra-dense networks.Firstly,considering that the 5G base station adopts beamforming technology,an anti-jamming model under Space Division Multiple Access(SDMA)conditions is proposed.Secondly,the confrontational relationship between users and the jammer is formulated as a Stackelberg game.Besides,to achieve global optimization,we design a local cooperation mechanism for users and formulate the cooperation and competition among users as a local altruistic game.By proving that the local altruistic game is an Exact Potential Game(EPG),we further prove the existence of pure strategy Nash Equilibrium(NE)among users and Stackelberg Equilibrium(SE)between users and jammer.Thirdly,to obtain the equilibrium solutions of the proposed games,we propose an anti-jamming channel selection algorithm and improve its convergence speed through heterogeneous learning parameters.The simulation results validate the convergence and effectiveness of the proposed algorithm.Compared with the throughput optimization scheme,our proposed scheme obtain a greater network satisfaction rate.Finally,we also analyze user fairness changes during the algorithm convergence process and get some interesting conclusions.
文摘In cloud computing Resource allocation is a very complex task.Handling the customer demand makes the challenges of on-demand resource allocation.Many challenges are faced by conventional methods for resource allocation in order tomeet the Quality of Service(QoS)requirements of users.For solving the about said problems a new method was implemented with the utility of machine learning framework of resource allocation by utilizing the cloud computing technique was taken in to an account in this research work.The accuracy in the machine learning algorithm can be improved by introducing Bat Algorithm with feature selection(BFS)in the proposed work,this further reduces the inappropriate features from the data.The similarities that were hidden can be demoralized by the Support Vector Machine(SVM)classifier which is also determine the subspace vector and then a new feature vector can be predicted by using SVM.For an unexpected circumstance SVM model can make a resource allocation decision.The efficiency of proposed SVM classifier of resource allocation can be highlighted by using a singlecell multiuser massive Multiple-Input Multiple Output(MIMO)system,with beam allocation problem as an example.The proposed resource allocation based on SVM performs efficiently than the existing conventional methods;this has been proven by analysing its results.
基金supported by the Natural Science Foundation of Jiangsu Province (No. BK20151479)the Open Foundation of Graduate Innovation Base in Nanjing University of Aeronautics and Astronautics(No. kfjj20190736)
基金the National Basic Research Program of China (973 program) (Grant No. 2003CB314806)the National High-Tech Research & Development Program of China (863 Program) (Grant No. 2006AA01Z164)+1 种基金the National Natural Science Foundation of China (Grant No. 60672121)the Program for New Century Excellent Talents in University (Grant No. NCET-05-0114)
文摘In service oriented architecture (SOA), service composition is a promising way to create new services. However, some technical challenges are hindering the application of service composition. One of the greatest challenges for composite service provider is to select a set of services to instantiate composite service with end- to-end quality of service (QoS) assurance across different autonomous networks and business regions. This paper presents an iterative service selection algorithm for quality driven service composition. The algorithm runs on a peer-to-peer (P2P) service execution environment--distributed intelligent service execution (DISE), which provides scalable QoS registry, dynamic service selection and service execution services. The most significant feature of our iterative service selection algorithm is that it can work on a centralized QoS registry as well as cross decentralized ones. Network status is an optional factor in our QoS model and selection algorithm. The algorithm iteratively selects services following service execution order, so it can be applied either before service execution or at service run-time without any modification. We test our algorithm with a series of experiments on DISE. Experimental results illustrated its excellent selection and outstanding performance.
基金Natural Science Foundation of China(grant Nos.61473237,61202170,and 61402331)It is also supported by the Shaanxi Provincial Natural Science Foundation Research Project(2014JM2-6096)+3 种基金Tianjin Research Program of Application Foundation and Advanced Technology(14JCYBJC42500)Tianjin science and technology correspondent project(16JCTPJC47300)the 2015 key projects of Tianjin science and technology support program(No.15ZCZDGX00200)the Fund of Tianjin Food Safety&Low Carbon Manufacturing Collaborative Innovation Center.
文摘Apple leaf disease is one of the main factors to constrain the apple production and quality.It takes a long time to detect the diseases by using the traditional diagnostic approach,thus farmers often miss the best time to prevent and treat the diseases.Apple leaf disease recognition based on leaf image is an essential research topic in the field of computer vision,where the key task is to find an effective way to represent the diseased leaf images.In this research,based on image processing techniques and pattern recognition methods,an apple leaf disease recognition method was proposed.A color transformation structure for the input RGB(Red,Green and Blue)image was designed firstly and then RGB model was converted to HSI(Hue,Saturation and Intensity),YUV and gray models.The background was removed based on a specific threshold value,and then the disease spot image was segmented with region growing algorithm(RGA).Thirty-eight classifying features of color,texture and shape were extracted from each spot image.To reduce the dimensionality of the feature space and improve the accuracy of the apple leaf disease identification,the most valuable features were selected by combining genetic algorithm(GA)and correlation based feature selection(CFS).Finally,the diseases were recognized by SVM classifier.In the proposed method,the selected feature subset was globally optimum.The experimental results of more than 90%correct identification rate on the apple diseased leaf image database which contains 90 disease images for there kinds of apple leaf diseases,powdery mildew,mosaic and rust,demonstrate that the proposed method is feasible and effective.
文摘Prediction plays a vital role in decision making. Correct prediction leads to right decision making to save the life, energy,efforts, money and time. The right decision prevents physical and material losses and it is practiced in all the fields including medical,finance, environmental studies, engineering and emerging technologies. Prediction is carried out by a model called classifier. The predictive accuracy of the classifier highly depends on the training datasets utilized for training the classifier. The irrelevant and redundant features of the training dataset reduce the accuracy of the classifier. Hence, the irrelevant and redundant features must be removed from the training dataset through the process known as feature selection. This paper proposes a feature selection algorithm namely unsupervised learning with ranking based feature selection(FSULR). It removes redundant features by clustering and eliminates irrelevant features by statistical measures to select the most significant features from the training dataset. The performance of this proposed algorithm is compared with the other seven feature selection algorithms by well known classifiers namely naive Bayes(NB),instance based(IB1) and tree based J48. Experimental results show that the proposed algorithm yields better prediction accuracy for classifiers.
基金supported in part by the National High-tech Research and Development Program (863 Program) of China under Grant No. 2009AA01Z210, No. 2009AA01Z250 and No. 2008AA01A324support from Guangdong Ministry of Education Industry-Academia-Research project No. 2009B090300315EU FP7 Project (INFSO-ICT- 215549)
文摘To address cross-ISP traffic problem caused by BitTorrent,we present our design and evaluation of a proximity-aware BitTorrent system. In our approach,clients generate global proximity-aware information by using landmark clustering;the tracker uses this proximity to maintain all peers in an orderly way and hands back a biased subset consisting of the peers who are physically closest to the requestor. Our approach requires no co-operation between P2P users and their Internet infra structures,such as ISPs or CDNs,no constantly path monitoring or probing their neighbors. The simulation results show that our approach can not only reduce unnecessary cross-ISP traffic,but also allow downloadsing fast.
基金supported by a grant from the National Natural Science Foundation of China(Grant No.61373057)a grant from the Zhejiang Provincial Natural Science Foundation of China(Grant No.Y1110763)
文摘Objective: Identification of colorectal cancer (CRC) metastasis genes is one of the most important issues in CRC research. For the purpose of mining CRC metastasis-associated genes, an integrated analysis of mJcroarray data was presented, by combined with evidence acquired from comparative genornic hybridization (CGH) data. Methods: Gene expression profile data of CRC samples were obtained at Gene Expression Omnibus (GEO) website. The 15 important chromosomal aberration sites detected by using CGH technology were used for integrated genomic and transcriptomic analysis. Significant Analysis of Microarray (SAM) was used to detect significantly differentially expressed genes across the whole genome. The overlapping genes were selected in their corresponding chromosomal aberration regions, and analyzed by using the Database for Annotation, Visualization and Integrated Discovery (DAVID). Finally, SVM-T-RFE gene selection algorithm was applied to identify ted genes in CRC. Results: A minimum gene set was obtained with the minimum number [14] of genes, and the highest classification accuracy (100%) in both PRI and META datasets. A fraction of selected genes are associated with CRC or its metastasis. Conclusions- Our results demonstrated that integration analysis is an effective strategy for mining cancer- associated genes.