With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy...With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.展开更多
Grid-scale energy storage systems provide effective solutions to address challenges such as supply-load imbalances and voltage violations resulting from the non-coinciding nature of renewable energy generation and pea...Grid-scale energy storage systems provide effective solutions to address challenges such as supply-load imbalances and voltage violations resulting from the non-coinciding nature of renewable energy generation and peak demand incidents.While battery and hydrogen storage are commonly used for peak shaving,ice-based thermal energy storage systems(TESSs)offer a direct way to reduce cooling loads without electrical conversion.This paper presents a multi-objective planning framework that optimizes TESS dispatch,network topology,and photovoltaic(PV)inverter reactive power support to address operational issues in active distribution networks.The objectives of the proposed scheme include minimizing peak demand,voltage deviations,and PV inverter VAr dependency.The mixed-integer nonlinear programming problem is solved using a Pareto-based multi-objective particle swarm optimization(MOPSO)method.The MATLAB-OpenDSS simulations for a modified IEEE-123 bus system show a 7.1%reduction in peak demand,a 13%reduction in voltage deviation,and a 52%drop in PV inverter VAr usage.The obtained solutions confirm minimal operational stress on control devices such as switches and PV inverters.Thus,unlike earlier studies,this work combines all three strategies to offer an effective solution for the operational planning of the active distribution network.展开更多
With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with ...With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with complex attacks in SDN environments,thus to address the network security issues from the viewpoint of Artificial Intelligence(AI),this paper introduces the Crayfish Optimization Algorithm(COA)to the field of intrusion detection for both SDN and traditional network architectures,and based on the characteristics of the original COA,an Improved Crayfish Optimization Algorithm(ICOA)is proposed by integrating strategies of elite reverse learning,Levy flight,crowding factor and parameter modification.The ICOA is then utilized for AI-integrated feature selection of intrusion detection for both SDN and traditional network architectures,to reduce the dimensionality of the data and improve the performance of network intrusion detection.Finally,the performance evaluation is performed by testing not only the NSL-KDD dataset and the UNSW-NB 15 dataset for traditional networks but also the InSDN dataset for SDN-based networks.Experimental results show that ICOA improves the accuracy by 0.532%and 2.928%respectively compared with GWO and COA in traditional networks.In SDN networks,the accuracy of ICOA is 0.25%and 0.3%higher than COA and PSO.These findings collectively indicate that AI-integrated feature selection based on the proposed ICOA can promote network intrusion detection for both SDN and traditional architectures.展开更多
The probability of phase formation was predicted using k-nearest neighbor algorithm(KNN)and artificial neural network algorithm(ANN).Additionally,the composition ranges of Ti,Cu,Ni,and Hf in 40 unknown amorphous alloy...The probability of phase formation was predicted using k-nearest neighbor algorithm(KNN)and artificial neural network algorithm(ANN).Additionally,the composition ranges of Ti,Cu,Ni,and Hf in 40 unknown amorphous alloy composites(AACs)were predicted using ANN.The predicted alloys were then experimentally verified through X-ray diffraction(XRD)and high-resolution transmission electron microscopy(HRTEM).The prediction accuracies of the ANN for AM and IM phases are 93.12%and 85.16%,respectively,while the prediction accuracies of KNN for AM and IM phases are 93%and 84%,respectively.It is observed that when the contents of Ti,Cu,Ni,and Hf fall within the ranges of 32.7−34.5 at.%,16.4−17.3 at.%,30.9−32.7 at.%,and 17.3−18.3 at.%,respectively,it is more likely to form AACs.Based on the results of XRD and HRTEM,the Ti_(34)Cu17Ni_(31.36)Hf_(17.64)and Ti_(36)Cu_(18)Ni_(29.44)Hf_(16.56)alloys are identified as good AACs,which are in closely consistent with the predicted amorphous alloy compositions.展开更多
The radial basis function （RBF）, a kind of neural networks algorithm, is adopted to select clusterheads. It has many advantages such as simple parallel distributed computation, distributed storage, and fast learning...The radial basis function （RBF）, a kind of neural networks algorithm, is adopted to select clusterheads. It has many advantages such as simple parallel distributed computation, distributed storage, and fast learning. Four factors related to a node becoming a cluster-head are drawn by analysis, which are energy （ energy available in each node）, number （the number of neighboring nodes）, centrality （ a value to classify the nodes based on the proximity how central the node is to the cluster）, and location （the distance between the base station and the node）. The factors are as input variables of neural networks and the output variable is suitability that is the degree of a node becoming a cluster head. A group of cluster-heads are selected according to the size of network. Then the base station broadcasts a message containing the list of cluster-heads＇ IDs to all nodes. After that, each cluster-head announces its new status to all its neighbors and sets up a new cluster. If a node around it receives the message, it registers itself to be a member of the cluster. After identifying all the members, the cluster-head manages them and carries out data aggregation in each cluster. Thus data flowing in the network decreases and energy consumption of nodes decreases accordingly. Experimental results show that, compared with other algorithms, the proposed algorithm can significantly increase the lifetime of the sensor network.展开更多
It is a hot issue in communication research field to select the best network for Heterogeneous Wireless Networks(HWNs),and it is also a difficult problem to reduce the handoff number of vertical handoff.In order to so...It is a hot issue in communication research field to select the best network for Heterogeneous Wireless Networks(HWNs),and it is also a difficult problem to reduce the handoff number of vertical handoff.In order to solve this problem,the paper proposes a multiple attribute network selection algorithm based on Analytic Hierarchy Process(AHP)and synergetic theory.The algorithm applies synergetics to network selection,considering the candidate network as a compound system composed of multiple attribute subsystems,and combines the subsystem order degree with AHP weight to obtain entropy of the compound system,which is opposite the synergy degree of a network system.The greater the synergy degree,the better the network performance.The algorithm takes not only the coordination of objective attributes but also Quality of Service(QoS)requirements into consideration,ensuring that users select the network with overall good performance.The simulation results show that the proposed algorithm can effectively reduce the handoff number and provide uses with satisfactory QoS according to different services.展开更多
This paper deals with network selection problem for users in heterogeneous network environment. The main context is to improve the TOPSIS( Technique for Order Preference by Similarity to Ideal Solution) network scheme...This paper deals with network selection problem for users in heterogeneous network environment. The main context is to improve the TOPSIS( Technique for Order Preference by Similarity to Ideal Solution) network scheme by combining the network properties and the users' requirement accurately and decrease ping-pong effect. The method of entropy and FAHP( Fuzzy Analytic Hierarchy Process) are used to calculate weight value and the sojourn time calculation is used to avoid ping-pang effect. The simulation results show that the improved scheme enhances the more accuracy of network selection than the existing methods and reduces the number of ping-pang effect.展开更多
Even though various wireless Net- work Access Technologies （NATs） with dif- ferent specifications and applications have been developed in the recent years, no single wireless technology alone can satisfy the any- ti...Even though various wireless Net- work Access Technologies （NATs） with dif- ferent specifications and applications have been developed in the recent years, no single wireless technology alone can satisfy the any- time, anywhere, and any service wire- less-access needs of mobile users. A real seamless wireless mobile environment is only realized by considering vertical and horizontal handoffs together. One of the major design issues in heterogeneous wireless networks is the support of Vertical Handoff （VHO）. VHO occurs when a multi-interface enabled mobile terminal changes its Point of Attachment （PoA） from one type of wireless access technology to another, while maintaining an active session. In this paper we present a novel multi-criteria VHO algorithm, which chooses the target NAT based on several factors such as user preferences, system parameters, and traf- tic-types with varying Quality of Service （QoS） requirements. Two modules i.e., VHO Neces- sity Estimation （VHONE） module and target NAT selection module, are designed. Both modules utilize several ＂weighted＂ users＇ and system＇s parameters. To improve the robust- ness of the proposed algorithm, the weighting system is designed based on the concept of fuzzy linguistic variables.展开更多
In order to support advanced vehicular Internet-of-Things(IoT)applications,information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in ...In order to support advanced vehicular Internet-of-Things(IoT)applications,information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular environments.Federated learning(FL),which is a type of distributed learning technology,has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user privacy.However,client selection and networking scheme for enabling FL in dynamic vehicular environments,which determines the communication delay between FL clients and the central server that aggregates the models received from the clients,is still under-explored.In this paper,we propose an edge computing-based joint client selection and networking scheme for vehicular IoT.The proposed scheme assigns some vehicles as edge vehicles by employing a distributed approach,and uses the edge vehicles as FL clients to conduct the training of local models,which learns optimal behaviors based on the interaction with environments.The clients also work as forwarder nodes in information sharing among network entities.The client selection takes into account the vehicle velocity,vehicle distribution,and the wireless link connectivity between vehicles using a fuzzy logic algorithm,resulting in an efficient learning and networking architecture.We use computer simulations to evaluate the proposed scheme in terms of the communication overhead and the information covered in learning.展开更多
Landslide susceptibility prediction(LSP)is significantly affected by the uncertainty issue of landslide related conditioning factor selection.However,most of literature only performs comparative studies on a certain c...Landslide susceptibility prediction(LSP)is significantly affected by the uncertainty issue of landslide related conditioning factor selection.However,most of literature only performs comparative studies on a certain conditioning factor selection method rather than systematically study this uncertainty issue.Targeted,this study aims to systematically explore the influence rules of various commonly used conditioning factor selection methods on LSP,and on this basis to innovatively propose a principle with universal application for optimal selection of conditioning factors.An'yuan County in southern China is taken as example considering 431 landslides and 29 types of conditioning factors.Five commonly used factor selection methods,namely,the correlation analysis(CA),linear regression(LR),principal component analysis(PCA),rough set(RS)and artificial neural network(ANN),are applied to select the optimal factor combinations from the original 29 conditioning factors.The factor selection results are then used as inputs of four types of common machine learning models to construct 20 types of combined models,such as CA-multilayer perceptron,CA-random forest.Additionally,multifactor-based multilayer perceptron random forest models that selecting conditioning factors based on the proposed principle of“accurate data,rich types,clear significance,feasible operation and avoiding duplication”are constructed for comparisons.Finally,the LSP uncertainties are evaluated by the accuracy,susceptibility index distribution,etc.Results show that:(1)multifactor-based models have generally higher LSP performance and lower uncertainties than those of factors selection-based models;(2)Influence degree of different machine learning on LSP accuracy is greater than that of different factor selection methods.Conclusively,the above commonly used conditioning factor selection methods are not ideal for improving LSP performance and may complicate the LSP processes.In contrast,a satisfied combination of conditioning factors can be constructed according to the proposed principle.展开更多
In intelligent transportation system(ITS), the interworking of vehicular networks(VN) and cellular networks(CN) is proposed to provide high-data-rate services to vehicles. As the network access quality for CN and VN i...In intelligent transportation system(ITS), the interworking of vehicular networks(VN) and cellular networks(CN) is proposed to provide high-data-rate services to vehicles. As the network access quality for CN and VN is location related, mobile data offloading(MDO), which dynamically selects access networks for vehicles, should be considered with vehicle route planning to further improve the wireless data throughput of individual vehicles and to enhance the performance of the entire ITS. In this paper, we investigate joint MDO and route selection for an individual vehicle in a metropolitan scenario. We aim to improve the throughput of the target vehicle while guaranteeing its transportation efficiency requirements in terms of traveling time and distance. To achieve this objective, we first formulate the joint route and access network selection problem as a semi-Markov decision process(SMDP). Then we propose an optimal algorithm to calculate its optimal policy. To further reduce the computation complexity, we derive a suboptimal algorithm which reduces the action space. Simulation results demonstrate that the proposed optimal algorithm significantly outperforms the existing work in total throughput and the late arrival ratio.Moreover, the heuristic algorithm is able to substantially reduce the computation time with only slight performance degradation.展开更多
Heterogeneous wireless access technologies will coexist in next generation wireless networks.These technologies form integrated networks,and these networks support multiple services with high quality level.Various acc...Heterogeneous wireless access technologies will coexist in next generation wireless networks.These technologies form integrated networks,and these networks support multiple services with high quality level.Various access technologies allow users to select the best available access network to meet the requirements of each type of communication service.Being always best connected anytime and anywhere is a major concern in a heterogeneous wireless networks environment.Always best connected enables network selection mechanisms to keep mobile users always connected to the best network.We present an overview of the network selection and prediction problems and challenges.In addition,we discuss a comprehensive classification of related theoretic approaches,and also study the integration between these methods,finding the best solution of network selection and prediction problems.The optimal solution can fulfill the requirements of the next generation wireless networks.展开更多
This paper brings forward a novel dynamic multiple access network selection scheme(NDMAS),which could achieve less energy loss and improve the poor adaptive capability caused by the variable network parameters.Firstly...This paper brings forward a novel dynamic multiple access network selection scheme(NDMAS),which could achieve less energy loss and improve the poor adaptive capability caused by the variable network parameters.Firstly,a multiple access network selection mathematical model based on information theory is presented.From the perspective of information theory,access selection is essentially a process to reduce the information entropy in the system.It can be found that the lower the information entropy is,the better the system performance fulfills.Therefore,this model is designed to reduce the information entropy by removing redundant parameters,and to avoid the computational cost as well.Secondly,for model implementation,the Principal Component Analysis(PCA) is employed to process the observation data to find out the related factors which affect the users most.As a result,the information entropy is decreased.Theoretical analysis proves that system loss and computational complexity have been decreased by using the proposed approach,while the network QoS and accuracy are guaranteed.Finally,simulation results show that our scheme achieves much better system performance in terms of packet delay,throughput and call blocking probability than other currently existing ones.展开更多
The hybrid satellite-UAV-terrestrial maritime networks have shown great promise for broadband coverage at sea.The existing works focused on vessels collaboratively served by UAV-enabled aerial base station(ABSs)and te...The hybrid satellite-UAV-terrestrial maritime networks have shown great promise for broadband coverage at sea.The existing works focused on vessels collaboratively served by UAV-enabled aerial base station(ABSs)and terrestrial base stations(TBSs)deployed along the coast,and proved that data rate could be improved by optimizing transmit power and ABS’s position.In practice,users on a vessel can be collaboratively served by an ABS and a vesselenabled base station(VBS)in different networks.In this case,how to select the network for users on a vessel is still an open issue.In this paper,a TBS and a satellite respectively provide wireless backhaul for the ABS and the VBS.The network selection is jointly optimized with transmit power of ABS and VBS,and ABS’s position for improving data rate of all users.We solve it by finding candidates for network selection and iteratively solving transmit power and ABS’s position for each candidate.Simulation results demonstrate that data rate can be improved by collaborative coverage for users on a vessel.展开更多
The literature generally agrees that longer-horizon(over a month) predictions make more sense than short-horizon ones. However, it's an especially challenging task due to the lack of data(in unit of long horizon)a...The literature generally agrees that longer-horizon(over a month) predictions make more sense than short-horizon ones. However, it's an especially challenging task due to the lack of data(in unit of long horizon)and economic data have a low S/N ratio. We hypothesize that the stock trend is largely dictated by driving factors which are filtered by psychological factors and work on behavioral factors: representative indicators from these three aspects would be adequate in trend prediction. We then extend the Stepwise Regression Analysis(SRA)algorithm to constrained SRA(c SRA) to carry out a further feature selection and lag optimization. During modeling stage, we introduce the Deep Neural Network(DNN) model in stock prediction under the suspicion that economic interactions are too complex for shallow networks to capture. Our experiments indeed show that deep structures generally perform better than shallow ones. Instead of comparing to a kitchen sink model, where over-fitting can easily happen with a shortage of data, we turn around and use a model ensemble approach which indirectly demonstrates our proposed method is adequate.展开更多
Objective:To explore the acupoint selection rules of acupuncture for trigeminal neuralgia(TN) based on complex network.Methods:The articles on clinical research of acupuncture for TN published up to March 2019 were se...Objective:To explore the acupoint selection rules of acupuncture for trigeminal neuralgia(TN) based on complex network.Methods:The articles on clinical research of acupuncture for TN published up to March 2019 were searched from the databases,i.e.CNKI,Wanfang,VIP,PubMed,Web of Science and Science Direct.A prescription database of acupuncture for TN was established.Using complex network,the core acupoints and acupoint selection rules were analyzed for TN treated with acupuncture.Results:A total of 304 articles,including 272 acupoint prescriptions were obtained.The complex network constructed for TN treated with acupuncture was in compliance with the small world effect.Using k-core analytic hierarchy process,36 acupoints were screened,and the total frequency of acupoints is1175.Regarding the meridian distribution,the points of yangming meridians of hand and foot were predominated,accounting for 50.21% of the overall(590/1175).In terms of acupoint location,the acupoints on the head and face were predominated,accounting for 52.51%(617/1175).For the types of acupoint,the specific acupoints were predominated,accounting for 71.32%(838/1175) and the majority was the intersecting points,accounting for 33.87%(398/1175).Based on community structure partition,the treatment of TN with acupuncture was divided into the treatment for symptoms,etiological treatment,and mind regulation.Besides,the supplementary acupoints based on the involved nerve branches of TN and those based on syndrome differentiation were recommended.Conclusion:The core acupoints of acupuncture for TN are Hégu(合谷LI4),Xiaguan(下关ST7),Tàichong(太冲LR3),Fēngchí(风池GB20) and Sìbái(四白ST2).In clinical treatment,the main therapeutics include the local analgesia for the symptoms and etiological treatment,associated with mind regulation.展开更多
An artificial neural networks(ANNs) based gear material selection hybrid intelligent system is established by analyzing the individual advantages and weakness of expert system (ES) and ANNs and the applications in mat...An artificial neural networks(ANNs) based gear material selection hybrid intelligent system is established by analyzing the individual advantages and weakness of expert system (ES) and ANNs and the applications in material select of them. The system mainly consists of tow parts: ES and ANNs. By being trained with much data samples, the back propagation (BP) ANN gets the knowledge of gear materials selection, and is able to inference according to user input. The system realizes the complementing of ANNs and ES. Using this system, engineers without materials selection experience can conveniently deal with gear materials selection.展开更多
This paper has concluded six features that belong to passenger vehicle types based on genetic algorithm(GA)of feature selection.We have obtained an optimal feature subset,including length,ratio of width and length,and...This paper has concluded six features that belong to passenger vehicle types based on genetic algorithm(GA)of feature selection.We have obtained an optimal feature subset,including length,ratio of width and length,and ratio of height and length.And then we apply this optimal feature subset as well as another feature set,containing length,width and height,to the network input.Back-propagation(BP)neural network and support vector machine(SVM)are applied to classify the passenger vehicle type.There are four passenger vehicle types.This paper selects 400 samples of passenger vehicles,among which 320 samples are used as training set(each class has 80 samples)and the other 80 samples as testing set,taking the feature of the samples as network input and taking four passenger vehicle types as output.For the test,we have applied BP neural network to choose the optimal feature subset as network input,and the results show that the total classification accuracy rate can reach 96%,and the classification accuracy rate of first type can reach 100%.In this condition,we obtain a conclusion that this algorithm is better than the traditional ones[9].展开更多
Over the last decade,mobile Adhoc networks have expanded dramati-cally in popularity,and their impact on the communication sector on a variety of levels is enormous.Its uses have expanded in lockstep with its growth.D...Over the last decade,mobile Adhoc networks have expanded dramati-cally in popularity,and their impact on the communication sector on a variety of levels is enormous.Its uses have expanded in lockstep with its growth.Due to its instability in usage and the fact that numerous nodes communicate data concur-rently,adequate channel and forwarder selection is essential.In this proposed design for a Cognitive Radio Cognitive Network(CRCN),we gain the confidence of each forwarding node by contacting one-hop and second level nodes,obtaining reports from them,and selecting the forwarder appropriately with the use of an optimization technique.At that point,we concentrate our efforts on their channel,selection,and lastly,the transmission of data packets via the designated forwarder.The simulation work is validated in this section using the MATLAB program.Additionally,steps show how the node acts as a confident forwarder and shares the channel in a compatible method to communicate,allowing for more packet bits to be transmitted by conveniently picking the channel between them.We cal-culate the confidence of the node at the start of the network by combining the reliability report for thefirst hop and the reliability report for the secondary hop.We then refer to the same node as the confident node in order to operate as a forwarder.As a result,we witness an increase in the leftover energy in the output.The percentage of data packets delivered has also increased.展开更多
Wireless Sensor Network(WSN)forms an essential part of IoT.It is embedded in the target environment to observe the physical parameters based on the type of application.Sensor nodes inWSN are constrained by different f...Wireless Sensor Network(WSN)forms an essential part of IoT.It is embedded in the target environment to observe the physical parameters based on the type of application.Sensor nodes inWSN are constrained by different features such as memory,bandwidth,energy,and its processing capabilities.In WSN,data transmission process consumes the maximum amount of energy than sensing and processing of the sensors.So,diverse clustering and data aggregation techniques are designed to achieve excellent energy efficiency in WSN.In this view,the current research article presents a novel Type II Fuzzy Logic-based Cluster Head selection with Low Complexity Data Aggregation(T2FLCH-LCDA)technique for WSN.The presented model involves a two-stage process such as clustering and data aggregation.Initially,three input parameters such as residual energy,distance to Base Station(BS),and node centrality are used in T2FLCH technique for CH selection and cluster construction.Besides,the LCDA technique which follows Dictionary Based Encoding(DBE)process is used to perform the data aggregation at CHs.Finally,the aggregated data is transmitted to the BS where it achieves energy efficiency.The experimental validation of the T2FLCH-LCDAtechnique was executed under three different scenarios based on the position of BS.The experimental results revealed that the T2FLCH-LCDA technique achieved maximum energy efficiency,lifetime,Compression Ratio(CR),and power saving than the compared methods.展开更多
文摘With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.
基金supported by the US Appalachian Regional Commission(ARC)under Grant MU-21579-23。
文摘Grid-scale energy storage systems provide effective solutions to address challenges such as supply-load imbalances and voltage violations resulting from the non-coinciding nature of renewable energy generation and peak demand incidents.While battery and hydrogen storage are commonly used for peak shaving,ice-based thermal energy storage systems(TESSs)offer a direct way to reduce cooling loads without electrical conversion.This paper presents a multi-objective planning framework that optimizes TESS dispatch,network topology,and photovoltaic(PV)inverter reactive power support to address operational issues in active distribution networks.The objectives of the proposed scheme include minimizing peak demand,voltage deviations,and PV inverter VAr dependency.The mixed-integer nonlinear programming problem is solved using a Pareto-based multi-objective particle swarm optimization(MOPSO)method.The MATLAB-OpenDSS simulations for a modified IEEE-123 bus system show a 7.1%reduction in peak demand,a 13%reduction in voltage deviation,and a 52%drop in PV inverter VAr usage.The obtained solutions confirm minimal operational stress on control devices such as switches and PV inverters.Thus,unlike earlier studies,this work combines all three strategies to offer an effective solution for the operational planning of the active distribution network.
基金supported by the National Natural Science Foundation of China under Grant 61602162the Hubei Provincial Science and Technology Plan Project under Grant 2023BCB041.
文摘With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with complex attacks in SDN environments,thus to address the network security issues from the viewpoint of Artificial Intelligence(AI),this paper introduces the Crayfish Optimization Algorithm(COA)to the field of intrusion detection for both SDN and traditional network architectures,and based on the characteristics of the original COA,an Improved Crayfish Optimization Algorithm(ICOA)is proposed by integrating strategies of elite reverse learning,Levy flight,crowding factor and parameter modification.The ICOA is then utilized for AI-integrated feature selection of intrusion detection for both SDN and traditional network architectures,to reduce the dimensionality of the data and improve the performance of network intrusion detection.Finally,the performance evaluation is performed by testing not only the NSL-KDD dataset and the UNSW-NB 15 dataset for traditional networks but also the InSDN dataset for SDN-based networks.Experimental results show that ICOA improves the accuracy by 0.532%and 2.928%respectively compared with GWO and COA in traditional networks.In SDN networks,the accuracy of ICOA is 0.25%and 0.3%higher than COA and PSO.These findings collectively indicate that AI-integrated feature selection based on the proposed ICOA can promote network intrusion detection for both SDN and traditional architectures.
基金supported by the National Natural Science Foundation of China(No.51601019)the Guangdong Basic and Applied Basic Research Foundation,China(No.2022A1515010233)+1 种基金the Key Project of Shaanxi Province of Qinchuangyuan“Scientist and Engineer”Team Construction,China(No.2023KXJ-123)the Natural Science Foundation of Shaanxi Province,China(No.2024JC-YBMS-014).
文摘The probability of phase formation was predicted using k-nearest neighbor algorithm(KNN)and artificial neural network algorithm(ANN).Additionally,the composition ranges of Ti,Cu,Ni,and Hf in 40 unknown amorphous alloy composites(AACs)were predicted using ANN.The predicted alloys were then experimentally verified through X-ray diffraction(XRD)and high-resolution transmission electron microscopy(HRTEM).The prediction accuracies of the ANN for AM and IM phases are 93.12%and 85.16%,respectively,while the prediction accuracies of KNN for AM and IM phases are 93%and 84%,respectively.It is observed that when the contents of Ti,Cu,Ni,and Hf fall within the ranges of 32.7−34.5 at.%,16.4−17.3 at.%,30.9−32.7 at.%,and 17.3−18.3 at.%,respectively,it is more likely to form AACs.Based on the results of XRD and HRTEM,the Ti_(34)Cu17Ni_(31.36)Hf_(17.64)and Ti_(36)Cu_(18)Ni_(29.44)Hf_(16.56)alloys are identified as good AACs,which are in closely consistent with the predicted amorphous alloy compositions.
基金The National Natural Science Foundation of China(No.60472053),the Natural Science Foundation of Jiangsu Province(No.BK2003055),the Specialized Research Fund for the Doctoral Pro-gram of Higher Education (No.20030286017).
文摘The radial basis function （RBF）, a kind of neural networks algorithm, is adopted to select clusterheads. It has many advantages such as simple parallel distributed computation, distributed storage, and fast learning. Four factors related to a node becoming a cluster-head are drawn by analysis, which are energy （ energy available in each node）, number （the number of neighboring nodes）, centrality （ a value to classify the nodes based on the proximity how central the node is to the cluster）, and location （the distance between the base station and the node）. The factors are as input variables of neural networks and the output variable is suitability that is the degree of a node becoming a cluster head. A group of cluster-heads are selected according to the size of network. Then the base station broadcasts a message containing the list of cluster-heads＇ IDs to all nodes. After that, each cluster-head announces its new status to all its neighbors and sets up a new cluster. If a node around it receives the message, it registers itself to be a member of the cluster. After identifying all the members, the cluster-head manages them and carries out data aggregation in each cluster. Thus data flowing in the network decreases and energy consumption of nodes decreases accordingly. Experimental results show that, compared with other algorithms, the proposed algorithm can significantly increase the lifetime of the sensor network.
基金Supported by the Major State Basic Research Development Program of China(973 Program)(No.2013CB329005)the National Natural Science Foundation of China(No.61171094)+1 种基金the National Science & Technology Key Project(No.2011ZX03001-006-02.No.2011ZX03005004-03)the Key Project of Jiangsu Provincial Natural Science Foundation(No.BK2011027)
文摘It is a hot issue in communication research field to select the best network for Heterogeneous Wireless Networks(HWNs),and it is also a difficult problem to reduce the handoff number of vertical handoff.In order to solve this problem,the paper proposes a multiple attribute network selection algorithm based on Analytic Hierarchy Process(AHP)and synergetic theory.The algorithm applies synergetics to network selection,considering the candidate network as a compound system composed of multiple attribute subsystems,and combines the subsystem order degree with AHP weight to obtain entropy of the compound system,which is opposite the synergy degree of a network system.The greater the synergy degree,the better the network performance.The algorithm takes not only the coordination of objective attributes but also Quality of Service(QoS)requirements into consideration,ensuring that users select the network with overall good performance.The simulation results show that the proposed algorithm can effectively reduce the handoff number and provide uses with satisfactory QoS according to different services.
基金Sponsored by the National Natural Science Foundation of China for Young Scholar(Grant No.61302080)the National Natural Science Foundation of China(Grant No.61271182)the National High Technology Research and Development Program of China(863 Program)(Grant No.2012AA01A508)
文摘This paper deals with network selection problem for users in heterogeneous network environment. The main context is to improve the TOPSIS( Technique for Order Preference by Similarity to Ideal Solution) network scheme by combining the network properties and the users' requirement accurately and decrease ping-pong effect. The method of entropy and FAHP( Fuzzy Analytic Hierarchy Process) are used to calculate weight value and the sojourn time calculation is used to avoid ping-pang effect. The simulation results show that the improved scheme enhances the more accuracy of network selection than the existing methods and reduces the number of ping-pang effect.
文摘Even though various wireless Net- work Access Technologies （NATs） with dif- ferent specifications and applications have been developed in the recent years, no single wireless technology alone can satisfy the any- time, anywhere, and any service wire- less-access needs of mobile users. A real seamless wireless mobile environment is only realized by considering vertical and horizontal handoffs together. One of the major design issues in heterogeneous wireless networks is the support of Vertical Handoff （VHO）. VHO occurs when a multi-interface enabled mobile terminal changes its Point of Attachment （PoA） from one type of wireless access technology to another, while maintaining an active session. In this paper we present a novel multi-criteria VHO algorithm, which chooses the target NAT based on several factors such as user preferences, system parameters, and traf- tic-types with varying Quality of Service （QoS） requirements. Two modules i.e., VHO Neces- sity Estimation （VHONE） module and target NAT selection module, are designed. Both modules utilize several ＂weighted＂ users＇ and system＇s parameters. To improve the robust- ness of the proposed algorithm, the weighting system is designed based on the concept of fuzzy linguistic variables.
基金This research was supported in part by the National Natural Science Foundation of China under Grant No.62062031 and 61877053in part by Inner Mongolia natural science foundation grant number 2019MS06035,and Inner Mongolia Science and Technology Major Project,China+1 种基金in part by ROIS NII Open Collaborative Research 21S0601in part by JSPS KAKENHI grant numbers 18KK0279,19H04093,20H00592,and 21H03424.
文摘In order to support advanced vehicular Internet-of-Things(IoT)applications,information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular environments.Federated learning(FL),which is a type of distributed learning technology,has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user privacy.However,client selection and networking scheme for enabling FL in dynamic vehicular environments,which determines the communication delay between FL clients and the central server that aggregates the models received from the clients,is still under-explored.In this paper,we propose an edge computing-based joint client selection and networking scheme for vehicular IoT.The proposed scheme assigns some vehicles as edge vehicles by employing a distributed approach,and uses the edge vehicles as FL clients to conduct the training of local models,which learns optimal behaviors based on the interaction with environments.The clients also work as forwarder nodes in information sharing among network entities.The client selection takes into account the vehicle velocity,vehicle distribution,and the wireless link connectivity between vehicles using a fuzzy logic algorithm,resulting in an efficient learning and networking architecture.We use computer simulations to evaluate the proposed scheme in terms of the communication overhead and the information covered in learning.
基金funded by the Natural Science Foundation of China(Grant Nos.42377164 and 41972280)the Badong National Observation and Research Station of Geohazards(Grant No.BNORSG-202305).
文摘Landslide susceptibility prediction(LSP)is significantly affected by the uncertainty issue of landslide related conditioning factor selection.However,most of literature only performs comparative studies on a certain conditioning factor selection method rather than systematically study this uncertainty issue.Targeted,this study aims to systematically explore the influence rules of various commonly used conditioning factor selection methods on LSP,and on this basis to innovatively propose a principle with universal application for optimal selection of conditioning factors.An'yuan County in southern China is taken as example considering 431 landslides and 29 types of conditioning factors.Five commonly used factor selection methods,namely,the correlation analysis(CA),linear regression(LR),principal component analysis(PCA),rough set(RS)and artificial neural network(ANN),are applied to select the optimal factor combinations from the original 29 conditioning factors.The factor selection results are then used as inputs of four types of common machine learning models to construct 20 types of combined models,such as CA-multilayer perceptron,CA-random forest.Additionally,multifactor-based multilayer perceptron random forest models that selecting conditioning factors based on the proposed principle of“accurate data,rich types,clear significance,feasible operation and avoiding duplication”are constructed for comparisons.Finally,the LSP uncertainties are evaluated by the accuracy,susceptibility index distribution,etc.Results show that:(1)multifactor-based models have generally higher LSP performance and lower uncertainties than those of factors selection-based models;(2)Influence degree of different machine learning on LSP accuracy is greater than that of different factor selection methods.Conclusively,the above commonly used conditioning factor selection methods are not ideal for improving LSP performance and may complicate the LSP processes.In contrast,a satisfied combination of conditioning factors can be constructed according to the proposed principle.
基金the National Natural Science Foundation of China under Grants 61631005 and U1801261the National Key R&D Program of China under Grant 2018YFB1801105+3 种基金the Central Universities under Grant ZYGX2019Z022the Key Areas of Research and Development Program of Guangdong Province, China, under Grant 2018B010114001the 111 Project under Grant B20064the China Postdoctoral Science Foundation under Grant No. 2018M631075
文摘In intelligent transportation system(ITS), the interworking of vehicular networks(VN) and cellular networks(CN) is proposed to provide high-data-rate services to vehicles. As the network access quality for CN and VN is location related, mobile data offloading(MDO), which dynamically selects access networks for vehicles, should be considered with vehicle route planning to further improve the wireless data throughput of individual vehicles and to enhance the performance of the entire ITS. In this paper, we investigate joint MDO and route selection for an individual vehicle in a metropolitan scenario. We aim to improve the throughput of the target vehicle while guaranteeing its transportation efficiency requirements in terms of traveling time and distance. To achieve this objective, we first formulate the joint route and access network selection problem as a semi-Markov decision process(SMDP). Then we propose an optimal algorithm to calculate its optimal policy. To further reduce the computation complexity, we derive a suboptimal algorithm which reduces the action space. Simulation results demonstrate that the proposed optimal algorithm significantly outperforms the existing work in total throughput and the late arrival ratio.Moreover, the heuristic algorithm is able to substantially reduce the computation time with only slight performance degradation.
基金funded by the University of Malaya, under Grant No.RG208-11AFR
文摘Heterogeneous wireless access technologies will coexist in next generation wireless networks.These technologies form integrated networks,and these networks support multiple services with high quality level.Various access technologies allow users to select the best available access network to meet the requirements of each type of communication service.Being always best connected anytime and anywhere is a major concern in a heterogeneous wireless networks environment.Always best connected enables network selection mechanisms to keep mobile users always connected to the best network.We present an overview of the network selection and prediction problems and challenges.In addition,we discuss a comprehensive classification of related theoretic approaches,and also study the integration between these methods,finding the best solution of network selection and prediction problems.The optimal solution can fulfill the requirements of the next generation wireless networks.
基金supported by National Natural Science Foundation of China under Grant No.60971083National International Science and Technology Cooperation Project of China (No.2010DFA11320)
文摘This paper brings forward a novel dynamic multiple access network selection scheme(NDMAS),which could achieve less energy loss and improve the poor adaptive capability caused by the variable network parameters.Firstly,a multiple access network selection mathematical model based on information theory is presented.From the perspective of information theory,access selection is essentially a process to reduce the information entropy in the system.It can be found that the lower the information entropy is,the better the system performance fulfills.Therefore,this model is designed to reduce the information entropy by removing redundant parameters,and to avoid the computational cost as well.Secondly,for model implementation,the Principal Component Analysis(PCA) is employed to process the observation data to find out the related factors which affect the users most.As a result,the information entropy is decreased.Theoretical analysis proves that system loss and computational complexity have been decreased by using the proposed approach,while the network QoS and accuracy are guaranteed.Finally,simulation results show that our scheme achieves much better system performance in terms of packet delay,throughput and call blocking probability than other currently existing ones.
基金supported in part by the National Natural Science Foundation of China(Grant No.62001265)the Fundamental Research Funds for the Central Universities(Grant No.buctrc202124)。
文摘The hybrid satellite-UAV-terrestrial maritime networks have shown great promise for broadband coverage at sea.The existing works focused on vessels collaboratively served by UAV-enabled aerial base station(ABSs)and terrestrial base stations(TBSs)deployed along the coast,and proved that data rate could be improved by optimizing transmit power and ABS’s position.In practice,users on a vessel can be collaboratively served by an ABS and a vesselenabled base station(VBS)in different networks.In this case,how to select the network for users on a vessel is still an open issue.In this paper,a TBS and a satellite respectively provide wireless backhaul for the ABS and the VBS.The network selection is jointly optimized with transmit power of ABS and VBS,and ABS’s position for improving data rate of all users.We solve it by finding candidates for network selection and iteratively solving transmit power and ABS’s position for each candidate.Simulation results demonstrate that data rate can be improved by collaborative coverage for users on a vessel.
基金the National Natural Science Foundation of China(Nos.11501355 and 71571116)the Project of Knowledge Innovation Program of Shanghai Municipal Education Commission(No.15ZZ090)+2 种基金the 59th China Postdoctoral Sciences Foundation Funded Project(No.2016M591640)the Humanities and Social Sciences Research Project of Ministry of Education(No.15YJA790039)the National Social Science Foundation of China(No.15ZDA058)
文摘The literature generally agrees that longer-horizon(over a month) predictions make more sense than short-horizon ones. However, it's an especially challenging task due to the lack of data(in unit of long horizon)and economic data have a low S/N ratio. We hypothesize that the stock trend is largely dictated by driving factors which are filtered by psychological factors and work on behavioral factors: representative indicators from these three aspects would be adequate in trend prediction. We then extend the Stepwise Regression Analysis(SRA)algorithm to constrained SRA(c SRA) to carry out a further feature selection and lag optimization. During modeling stage, we introduce the Deep Neural Network(DNN) model in stock prediction under the suspicion that economic interactions are too complex for shallow networks to capture. Our experiments indeed show that deep structures generally perform better than shallow ones. Instead of comparing to a kitchen sink model, where over-fitting can easily happen with a shortage of data, we turn around and use a model ensemble approach which indirectly demonstrates our proposed method is adequate.
基金Supported by National Program on Key Basic Research Project:No.2014CB543201Tianjin College Students’Innovative and Entrepreneurial Training Program,grant number:No.201910063032Tianjin University of Traditional Chinese Medicine College Students’Innovative and Entrepreneurial Training Program,No.CXJJ2019YG03。
文摘Objective:To explore the acupoint selection rules of acupuncture for trigeminal neuralgia(TN) based on complex network.Methods:The articles on clinical research of acupuncture for TN published up to March 2019 were searched from the databases,i.e.CNKI,Wanfang,VIP,PubMed,Web of Science and Science Direct.A prescription database of acupuncture for TN was established.Using complex network,the core acupoints and acupoint selection rules were analyzed for TN treated with acupuncture.Results:A total of 304 articles,including 272 acupoint prescriptions were obtained.The complex network constructed for TN treated with acupuncture was in compliance with the small world effect.Using k-core analytic hierarchy process,36 acupoints were screened,and the total frequency of acupoints is1175.Regarding the meridian distribution,the points of yangming meridians of hand and foot were predominated,accounting for 50.21% of the overall(590/1175).In terms of acupoint location,the acupoints on the head and face were predominated,accounting for 52.51%(617/1175).For the types of acupoint,the specific acupoints were predominated,accounting for 71.32%(838/1175) and the majority was the intersecting points,accounting for 33.87%(398/1175).Based on community structure partition,the treatment of TN with acupuncture was divided into the treatment for symptoms,etiological treatment,and mind regulation.Besides,the supplementary acupoints based on the involved nerve branches of TN and those based on syndrome differentiation were recommended.Conclusion:The core acupoints of acupuncture for TN are Hégu(合谷LI4),Xiaguan(下关ST7),Tàichong(太冲LR3),Fēngchí(风池GB20) and Sìbái(四白ST2).In clinical treatment,the main therapeutics include the local analgesia for the symptoms and etiological treatment,associated with mind regulation.
文摘An artificial neural networks(ANNs) based gear material selection hybrid intelligent system is established by analyzing the individual advantages and weakness of expert system (ES) and ANNs and the applications in material select of them. The system mainly consists of tow parts: ES and ANNs. By being trained with much data samples, the back propagation (BP) ANN gets the knowledge of gear materials selection, and is able to inference according to user input. The system realizes the complementing of ANNs and ES. Using this system, engineers without materials selection experience can conveniently deal with gear materials selection.
基金China Postdoctoral Science Foundation(No.20100481307)Natural Science Foundation of Shanxi(No.2009011018-3)
文摘This paper has concluded six features that belong to passenger vehicle types based on genetic algorithm(GA)of feature selection.We have obtained an optimal feature subset,including length,ratio of width and length,and ratio of height and length.And then we apply this optimal feature subset as well as another feature set,containing length,width and height,to the network input.Back-propagation(BP)neural network and support vector machine(SVM)are applied to classify the passenger vehicle type.There are four passenger vehicle types.This paper selects 400 samples of passenger vehicles,among which 320 samples are used as training set(each class has 80 samples)and the other 80 samples as testing set,taking the feature of the samples as network input and taking four passenger vehicle types as output.For the test,we have applied BP neural network to choose the optimal feature subset as network input,and the results show that the total classification accuracy rate can reach 96%,and the classification accuracy rate of first type can reach 100%.In this condition,we obtain a conclusion that this algorithm is better than the traditional ones[9].
文摘Over the last decade,mobile Adhoc networks have expanded dramati-cally in popularity,and their impact on the communication sector on a variety of levels is enormous.Its uses have expanded in lockstep with its growth.Due to its instability in usage and the fact that numerous nodes communicate data concur-rently,adequate channel and forwarder selection is essential.In this proposed design for a Cognitive Radio Cognitive Network(CRCN),we gain the confidence of each forwarding node by contacting one-hop and second level nodes,obtaining reports from them,and selecting the forwarder appropriately with the use of an optimization technique.At that point,we concentrate our efforts on their channel,selection,and lastly,the transmission of data packets via the designated forwarder.The simulation work is validated in this section using the MATLAB program.Additionally,steps show how the node acts as a confident forwarder and shares the channel in a compatible method to communicate,allowing for more packet bits to be transmitted by conveniently picking the channel between them.We cal-culate the confidence of the node at the start of the network by combining the reliability report for thefirst hop and the reliability report for the secondary hop.We then refer to the same node as the confident node in order to operate as a forwarder.As a result,we witness an increase in the leftover energy in the output.The percentage of data packets delivered has also increased.
文摘Wireless Sensor Network(WSN)forms an essential part of IoT.It is embedded in the target environment to observe the physical parameters based on the type of application.Sensor nodes inWSN are constrained by different features such as memory,bandwidth,energy,and its processing capabilities.In WSN,data transmission process consumes the maximum amount of energy than sensing and processing of the sensors.So,diverse clustering and data aggregation techniques are designed to achieve excellent energy efficiency in WSN.In this view,the current research article presents a novel Type II Fuzzy Logic-based Cluster Head selection with Low Complexity Data Aggregation(T2FLCH-LCDA)technique for WSN.The presented model involves a two-stage process such as clustering and data aggregation.Initially,three input parameters such as residual energy,distance to Base Station(BS),and node centrality are used in T2FLCH technique for CH selection and cluster construction.Besides,the LCDA technique which follows Dictionary Based Encoding(DBE)process is used to perform the data aggregation at CHs.Finally,the aggregated data is transmitted to the BS where it achieves energy efficiency.The experimental validation of the T2FLCH-LCDAtechnique was executed under three different scenarios based on the position of BS.The experimental results revealed that the T2FLCH-LCDA technique achieved maximum energy efficiency,lifetime,Compression Ratio(CR),and power saving than the compared methods.
