In this study,texture features namely entropy,contrast,energy,and homogeneity are extracted from mature and immature coffee beans using image processing,and the values are inputted into MATLAB’s Classification Learne...In this study,texture features namely entropy,contrast,energy,and homogeneity are extracted from mature and immature coffee beans using image processing,and the values are inputted into MATLAB’s Classification Learner App for discrimination.Among the 23 machine-learning algorithms,the best performance was achieved by medium K-nearest neighbor which has 97%accuracy and 0.14574 seconds in speed.When compared with previous studies that used RGB and HSV color features to differentiate mature and immature coffee beans,it can be concluded that texture features are far superior in distinguishing the two coffee bean groups.展开更多
The wide variety of smart embedded computing devices and their increasing number of applications in our daily life have created new op- portunities to acquire knowledge from the physical world anytime and anywhere, wh...The wide variety of smart embedded computing devices and their increasing number of applications in our daily life have created new op- portunities to acquire knowledge from the physical world anytime and anywhere, which is envisioned as the＂Internet of Things＂ （IoT）. Since a huge number of heterogeneous resources are brought in- to IoT, one of the main challenges is how to effi- ciently manage the increasing complexity of IoT in a scalable, flexNle, and autonomic way. Further- more, the emerging IoT applications will require collaborations among loosely coupled devices, which may reside in various locations of the Inter- net. In this paper, we propose a new IoT network management architecture based on cognitive net- work management technology and Service-Orien- ted Architecture to provide effective and efficient network management of loT.展开更多
Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise info...Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.展开更多
Conventional communication technologies are targeted mainly at spectrum efficiency,but not energy efficiency and environmental friendliness.Recent efforts from both industry and academia have dedicated to reduce the e...Conventional communication technologies are targeted mainly at spectrum efficiency,but not energy efficiency and environmental friendliness.Recent efforts from both industry and academia have dedicated to reduce the energy consumption and carbon emissions of the information and communication technologies(ICTs).There are two ways to achieve this goal:one is to conserve energy through energy-aware operation optimiza-展开更多
Vehicular Social Networks(VSNs)is the bridge of social networks and Vehicular Ad-Hoc Networks(VANETs).VSNs are promising as they allow the exchange of various types of contents in large-scale through Vehicle-to-Vehicl...Vehicular Social Networks(VSNs)is the bridge of social networks and Vehicular Ad-Hoc Networks(VANETs).VSNs are promising as they allow the exchange of various types of contents in large-scale through Vehicle-to-Vehicle(V2V)and Vehicle-to-Infrastructure(V2I)communication protocols.Vehicular Named Data Networking(VNDN)is an auspicious communication paradigm for the challenging VSN environment since it can optimize content dissemination by decoupling contents from their physical locations.However,content dissemination and caching represent crucial challenges in VSNs due to short link lifetime and intermittent connectivity caused by vehicles’high mobility.Our aim with this paper is to improve content delivery and cache hit ratio,as well as decrease the transmission delay between end-users.In this regard,we propose a novel hybrid VNDN-VSN forwarding technique based on social communities,which allows requester vehicles to easily find the most suitable forwarder or producer among the community members in their neighborhood area.Furthermore,we introduce an effective caching mechanism by dividing the content store into two parts,one for community private contents and the second one for public contents.Simulation results show that our proposed forwarding technique can achieve a favorable performance compared with traditional VNDN,in terms of data delivery ratio,average data delivery delay,and cache hit ratio.展开更多
Bridge Scour is one of the major causes of bridge failures all around the world and there have been significant efforts for its detection and measurement using different acoustic approaches. In this paper, we propose ...Bridge Scour is one of the major causes of bridge failures all around the world and there have been significant efforts for its detection and measurement using different acoustic approaches. In this paper, we propose and investigate an effective method to utilize Received Signal Strength (RSS) for measuring scour depth where acoustic sensors are deployed. We also extend a statistical testing to determine the difference in signal levels at the sensor nodes prior to and after scour formation and subsequently determine the actual depth of scour. Additionally, we make an attempt to evaluate underwater distance and depth using signal strength perceived at the receiver which makes it free from the requirement of accurate receiver-sender synchronization in contrast to Time of Flight (ToF) or Time of Arrival (ToA) techniques. The scour depths are eventually compared for the conditions when the bottom is composed of a single or multiple layers. The simulation results clearly show that different depths are calculated for the case of multilayered bottom (0.8 to 3.9 meters for instance) as compared to a constant depth of 2 meters for the case of a single layered bottom.展开更多
In mobile edge computing(MEC),one of the important challenges is how much resources of which mobile edge server(MES)should be allocated to which user equipment(UE).The existing resource allocation schemes only conside...In mobile edge computing(MEC),one of the important challenges is how much resources of which mobile edge server(MES)should be allocated to which user equipment(UE).The existing resource allocation schemes only consider CPU as the requested resource and assume utility for MESs as either a random variable or dependent on the requested CPU only.This paper presents a novel comprehensive utility function for resource allocation in MEC.The utility function considers the heterogeneous nature of applications that a UE offloads to MES.The proposed utility function considers all important parameters,including CPU,RAM,hard disk space,required time,and distance,to calculate a more realistic utility value for MESs.Moreover,we improve upon some general algorithms,used for resource allocation in MEC and cloud computing,by considering our proposed utility function.We name the improved versions of these resource allocation schemes as comprehensive resource allocation schemes.The UE requests are modeled to represent the amount of resources requested by the UE as well as the time for which the UE has requested these resources.The utility function depends upon the UE requests and the distance between UEs and MES,and serves as a realistic means of comparison between different types of UE requests.Choosing(or selecting)an optimal MES with the optimal amount of resources to be allocated to each UE request is a challenging task.We show that MES resource allocation is sub-optimal if CPU is the only resource considered.By taking into account the other resources,i.e.,RAM,disk space,request time,and distance in the utility function,we demonstrate improvement in the resource allocation algorithms in terms of service rate,utility,and MES energy consumption.展开更多
Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtua...Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual net- works affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evalua- tion, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies （e.g., AT＆T, DFN） and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach.展开更多
文摘In this study,texture features namely entropy,contrast,energy,and homogeneity are extracted from mature and immature coffee beans using image processing,and the values are inputted into MATLAB’s Classification Learner App for discrimination.Among the 23 machine-learning algorithms,the best performance was achieved by medium K-nearest neighbor which has 97%accuracy and 0.14574 seconds in speed.When compared with previous studies that used RGB and HSV color features to differentiate mature and immature coffee beans,it can be concluded that texture features are far superior in distinguishing the two coffee bean groups.
基金supported by the National Sci.&Tech. Major Project of China(No.2010ZX03004-002)the National Natural Science Foundation of China(No.60972083)
文摘The wide variety of smart embedded computing devices and their increasing number of applications in our daily life have created new op- portunities to acquire knowledge from the physical world anytime and anywhere, which is envisioned as the＂Internet of Things＂ （IoT）. Since a huge number of heterogeneous resources are brought in- to IoT, one of the main challenges is how to effi- ciently manage the increasing complexity of IoT in a scalable, flexNle, and autonomic way. Further- more, the emerging IoT applications will require collaborations among loosely coupled devices, which may reside in various locations of the Inter- net. In this paper, we propose a new IoT network management architecture based on cognitive net- work management technology and Service-Orien- ted Architecture to provide effective and efficient network management of loT.
基金funded by the State Grid Jiangsu Electric Power Company(Grant No.JS2020112)the National Natural Science Foundation of China(Grant No.62272236).
文摘Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.
文摘Conventional communication technologies are targeted mainly at spectrum efficiency,but not energy efficiency and environmental friendliness.Recent efforts from both industry and academia have dedicated to reduce the energy consumption and carbon emissions of the information and communication technologies(ICTs).There are two ways to achieve this goal:one is to conserve energy through energy-aware operation optimiza-
文摘Vehicular Social Networks(VSNs)is the bridge of social networks and Vehicular Ad-Hoc Networks(VANETs).VSNs are promising as they allow the exchange of various types of contents in large-scale through Vehicle-to-Vehicle(V2V)and Vehicle-to-Infrastructure(V2I)communication protocols.Vehicular Named Data Networking(VNDN)is an auspicious communication paradigm for the challenging VSN environment since it can optimize content dissemination by decoupling contents from their physical locations.However,content dissemination and caching represent crucial challenges in VSNs due to short link lifetime and intermittent connectivity caused by vehicles’high mobility.Our aim with this paper is to improve content delivery and cache hit ratio,as well as decrease the transmission delay between end-users.In this regard,we propose a novel hybrid VNDN-VSN forwarding technique based on social communities,which allows requester vehicles to easily find the most suitable forwarder or producer among the community members in their neighborhood area.Furthermore,we introduce an effective caching mechanism by dividing the content store into two parts,one for community private contents and the second one for public contents.Simulation results show that our proposed forwarding technique can achieve a favorable performance compared with traditional VNDN,in terms of data delivery ratio,average data delivery delay,and cache hit ratio.
文摘Bridge Scour is one of the major causes of bridge failures all around the world and there have been significant efforts for its detection and measurement using different acoustic approaches. In this paper, we propose and investigate an effective method to utilize Received Signal Strength (RSS) for measuring scour depth where acoustic sensors are deployed. We also extend a statistical testing to determine the difference in signal levels at the sensor nodes prior to and after scour formation and subsequently determine the actual depth of scour. Additionally, we make an attempt to evaluate underwater distance and depth using signal strength perceived at the receiver which makes it free from the requirement of accurate receiver-sender synchronization in contrast to Time of Flight (ToF) or Time of Arrival (ToA) techniques. The scour depths are eventually compared for the conditions when the bottom is composed of a single or multiple layers. The simulation results clearly show that different depths are calculated for the case of multilayered bottom (0.8 to 3.9 meters for instance) as compared to a constant depth of 2 meters for the case of a single layered bottom.
基金National Research Foundation of Korea-Grant funded by the Korean Government(Ministry of Science and ICT)-NRF-2020R1AB5B02002478.
文摘In mobile edge computing(MEC),one of the important challenges is how much resources of which mobile edge server(MES)should be allocated to which user equipment(UE).The existing resource allocation schemes only consider CPU as the requested resource and assume utility for MESs as either a random variable or dependent on the requested CPU only.This paper presents a novel comprehensive utility function for resource allocation in MEC.The utility function considers the heterogeneous nature of applications that a UE offloads to MES.The proposed utility function considers all important parameters,including CPU,RAM,hard disk space,required time,and distance,to calculate a more realistic utility value for MESs.Moreover,we improve upon some general algorithms,used for resource allocation in MEC and cloud computing,by considering our proposed utility function.We name the improved versions of these resource allocation schemes as comprehensive resource allocation schemes.The UE requests are modeled to represent the amount of resources requested by the UE as well as the time for which the UE has requested these resources.The utility function depends upon the UE requests and the distance between UEs and MES,and serves as a realistic means of comparison between different types of UE requests.Choosing(or selecting)an optimal MES with the optimal amount of resources to be allocated to each UE request is a challenging task.We show that MES resource allocation is sub-optimal if CPU is the only resource considered.By taking into account the other resources,i.e.,RAM,disk space,request time,and distance in the utility function,we demonstrate improvement in the resource allocation algorithms in terms of service rate,utility,and MES energy consumption.
基金This work has been supported by National Science and Technology Major Project of China （NMP） （2010ZX03004-002 and 2012ZX03003-003）, the Strategic Pilot Project of Chinese Academy of Sciences （XDA06010302）, and the National Natural Science Foundation of China （Grant No. 60972083）.
文摘Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual net- works affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evalua- tion, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies （e.g., AT＆T, DFN） and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach.
