Ambient Assisted Living(AAL) is becoming an important research field. Many technologies have emerged related with pervasive computing vision, which can give support for AAL. One of the most reliable approaches is base...Ambient Assisted Living(AAL) is becoming an important research field. Many technologies have emerged related with pervasive computing vision, which can give support for AAL. One of the most reliable approaches is based on wireless sensor networks(WSNs). In this paper, we propose a coverage-aware unequal clustering protocol with load separation(CUCPLS) for data gathering of AAL applications based on WSNs. Firstly, the coverage overlap factor for nodes is introduced that accounts for the degree of target nodes covered. In addition, to balance the intra-cluster and inter-cluster energy consumptions, different competition radiuses of CHs are computed theoretically in different rings, and smaller clusters are formed near the sink. Moreover, two CHs are selected in each cluster for load separation to alleviate the substantial energy consumption difference between a single CH and its member nodes. Furthermore, a backoff waiting time is adopted during the selection of the two CHs to reduce the number of control messages employed. Simulation results demonstrate that the CUCPLS not only can achieve better coverage performance, but also balance the energy consumption of a network and prolong network lifetime.展开更多
Routers have traditionally been architected as two elements: forwarding plane and control plane through For CES or other protocols. Each forwarding plane aggregates a fixed amount of computing, memory, and network int...Routers have traditionally been architected as two elements: forwarding plane and control plane through For CES or other protocols. Each forwarding plane aggregates a fixed amount of computing, memory, and network interface resources to forward packets. Unfortunately, the tight coupling of packet-processing tasks with network interfaces has severely restricted service innovation and hardware upgrade. In this context, we explore the insightful prospect of functional separation in forwarding plane to propose a next-generation router architecture, which, if realized, can provide promises both for various packet-processing tasks and for flexible deployment while solving concerns related to the above problems. Thus, we put forward an alternative construction in which functional resources within a forwarding plane are disaggregated. A forwarding plane is instead separated into two planes: software data plane(SDP) and flow switching plane(FSP), and each plane can be viewed as a collection of "building blocks". SDP is responsible for packet-processing tasks without its expansibility restricted with the amount and kinds of network interfaces. FSP is in charge of packet receiving/transmitting tasks and can incrementally add switching elements, such as general switches, or even specialized switches, to provide network interfaces for SDP. Besides, our proposed router architecture uses network fabrics to achievethe best connectivity among building blocks,which can support for network topology reconfiguration within one device.At last,we make an experiment on our platform in terms of bandwidth utilization rate,configuration delay,system throughput and execution time.展开更多
Network intrusion detection plays a critical role in safeguarding network security;however,traditional detection methods often struggle with complex attacks and large-scale data.To address these challenges,we propose ...Network intrusion detection plays a critical role in safeguarding network security;however,traditional detection methods often struggle with complex attacks and large-scale data.To address these challenges,we propose a novel network intrusion detection model named GCM-CSDNN,which integrates the group cloud model(GCM)with a depthwise separable convolutional neural network(CSDNN).The model introduces group cloud transformation to reduce data dimensionality and employs 3D channel fusion technology to enhance feature extraction capabilities,thereby improving both accuracy and computational efficiency.We conducted extensive experiments on multiple benchmark datasets—including UNSW-NB15,KDD99,WSN-DS,and WADI—which cover diverse network environments and attack types.Experimental results demonstrate that GCM-CSDNN significantly outperforms traditional machine learning models and deep learning models in terms of accuracy and F1-score,achieving 98.79%and 98.81%respectively,and surpassing the next-best model,SSG-DCNN.Moreover,GCM-CSDNN exhibits excellent performance on high-dimensional and large-scale datasets,significantly reducing training and testing times while demonstrating strong robustness and generalization capabilities.These findings indicate that GCM-CSDNN can efficiently and accurately detect network intrusions,making it suitable for real-time network security environments requiring the processing of large volumes of data.展开更多
基金supported by the National Nature Science Foundation of China (61170169, 61170168)
文摘Ambient Assisted Living(AAL) is becoming an important research field. Many technologies have emerged related with pervasive computing vision, which can give support for AAL. One of the most reliable approaches is based on wireless sensor networks(WSNs). In this paper, we propose a coverage-aware unequal clustering protocol with load separation(CUCPLS) for data gathering of AAL applications based on WSNs. Firstly, the coverage overlap factor for nodes is introduced that accounts for the degree of target nodes covered. In addition, to balance the intra-cluster and inter-cluster energy consumptions, different competition radiuses of CHs are computed theoretically in different rings, and smaller clusters are formed near the sink. Moreover, two CHs are selected in each cluster for load separation to alleviate the substantial energy consumption difference between a single CH and its member nodes. Furthermore, a backoff waiting time is adopted during the selection of the two CHs to reduce the number of control messages employed. Simulation results demonstrate that the CUCPLS not only can achieve better coverage performance, but also balance the energy consumption of a network and prolong network lifetime.
基金supported by Program for National Basic Research Program of China(973 Program)‘Reconfigurable Network Emulation Testbed for Basic Network Communication’(2012CB315906)
文摘Routers have traditionally been architected as two elements: forwarding plane and control plane through For CES or other protocols. Each forwarding plane aggregates a fixed amount of computing, memory, and network interface resources to forward packets. Unfortunately, the tight coupling of packet-processing tasks with network interfaces has severely restricted service innovation and hardware upgrade. In this context, we explore the insightful prospect of functional separation in forwarding plane to propose a next-generation router architecture, which, if realized, can provide promises both for various packet-processing tasks and for flexible deployment while solving concerns related to the above problems. Thus, we put forward an alternative construction in which functional resources within a forwarding plane are disaggregated. A forwarding plane is instead separated into two planes: software data plane(SDP) and flow switching plane(FSP), and each plane can be viewed as a collection of "building blocks". SDP is responsible for packet-processing tasks without its expansibility restricted with the amount and kinds of network interfaces. FSP is in charge of packet receiving/transmitting tasks and can incrementally add switching elements, such as general switches, or even specialized switches, to provide network interfaces for SDP. Besides, our proposed router architecture uses network fabrics to achievethe best connectivity among building blocks,which can support for network topology reconfiguration within one device.At last,we make an experiment on our platform in terms of bandwidth utilization rate,configuration delay,system throughput and execution time.
基金Supported by National Statistical Science Research Major Project of China(2022LZ30)。
文摘Network intrusion detection plays a critical role in safeguarding network security;however,traditional detection methods often struggle with complex attacks and large-scale data.To address these challenges,we propose a novel network intrusion detection model named GCM-CSDNN,which integrates the group cloud model(GCM)with a depthwise separable convolutional neural network(CSDNN).The model introduces group cloud transformation to reduce data dimensionality and employs 3D channel fusion technology to enhance feature extraction capabilities,thereby improving both accuracy and computational efficiency.We conducted extensive experiments on multiple benchmark datasets—including UNSW-NB15,KDD99,WSN-DS,and WADI—which cover diverse network environments and attack types.Experimental results demonstrate that GCM-CSDNN significantly outperforms traditional machine learning models and deep learning models in terms of accuracy and F1-score,achieving 98.79%and 98.81%respectively,and surpassing the next-best model,SSG-DCNN.Moreover,GCM-CSDNN exhibits excellent performance on high-dimensional and large-scale datasets,significantly reducing training and testing times while demonstrating strong robustness and generalization capabilities.These findings indicate that GCM-CSDNN can efficiently and accurately detect network intrusions,making it suitable for real-time network security environments requiring the processing of large volumes of data.
