Graph Edit Distance (GED) is a classical graph similarity metric. Since exact GED computation is NP-hard, existing GNN-based methods try to approximate GED in polynomial time. However, they still lack support for edge...
详细信息
Data augmentation is a technique that improves the ability of neural networks to make accurate predictions by increasing the size of the training dataset. However, it is still uncertain how to properly use data augmen...
详细信息
Modern households are increasingly adopting smart home devices powered by the Internet of Things (IoT). From smart thermostats and security systems to voice assistants, connected IoT devices enable seamless and respon...
详细信息
Food packaging serves several purposes, including food preservation, shelf-life extension, and upholding quality and safety requirements throughout manufacturing and storage. Intelligent food packaging, on the other h...
详细信息
The exploration of the memristor model in the discrete domain is a fascinating *** electromagnetic induction on neurons has also begun to be simulated by some discrete ***,most of the current investigations are based ...
详细信息
The exploration of the memristor model in the discrete domain is a fascinating *** electromagnetic induction on neurons has also begun to be simulated by some discrete ***,most of the current investigations are based on the integer-order discrete memristor,and there are relatively few studies on the form of fractional *** this paper,a new fractional-order discrete memristor model with prominent nonlinearity is constructed based on the Caputo fractional-order difference ***,the dynamical behaviors of the Rulkov neuron under electromagnetic radiation are simulated by introducing the proposed discrete *** integer-order and fractional-order peculiarities of the system are analyzed through the bifurcation graph,the Lyapunov exponential spectrum,and the iterative *** results demonstrate that the fractional-order system has more abundant dynamics than the integer one,such as hyper-chaos,multi-stable and transient *** addition,the complexity of the system in the fractional form is evaluated by the means of the spectral entropy complexity algorithm and consequences show that it is affected by the order of the fractional *** feature of fractional difference lays the foundation for further research and application of the discrete memristor and the neuron map in the future.
Given the high annotation costs and ethical considerations associated with medical images, leveraging a limited number of annotated samples for Few-Shot Medical Image Segmentation (FSMIS) has become increasingly preva...
详细信息
The rise in mobile internet usage especially using cellular networks demands efficient performance for web traffic, primarily made up of short TCP flows. For TCP, Cubic is the most widely deployed congestion control a...
详细信息
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking pe...
详细信息
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.
In academia and industries,graph neural networks(GNNs)have emerged as a powerful approach to graph data processing ranging from node classification and link prediction tasks to graph clustering *** models are usually ...
详细信息
In academia and industries,graph neural networks(GNNs)have emerged as a powerful approach to graph data processing ranging from node classification and link prediction tasks to graph clustering *** models are usually ***,building handcrafted GNN models is difficult and requires expert experience because GNN model components are complex and sensitive to *** complexity of GNN model components has brought significant challenges to the existing efficiencies of ***,many studies have focused on building automated machine learning frameworks to search for the best GNN models for targeted *** this work,we provide a comprehensive review of automatic GNN model building frameworks to summarize the status of the field to facilitate future *** categorize the components of automatic GNN model building frameworks into three dimensions according to the challenges of building *** reviewing the representative works for each dimension,we discuss promising future research directions in this rapidly growing field.
Insider threats are considered a major issue in the field of system engineering. For modern applications, which demand a seamless integration among humans and machines, human interactions along with the applications a...
详细信息
ISBN:
(纸本)9798331509675
Insider threats are considered a major issue in the field of system engineering. For modern applications, which demand a seamless integration among humans and machines, human interactions along with the applications are assumed as a significant phase of operation. It generates security issues within the network while safeguarding the network from insider threats. Due to the development of technologies, vulnerabilities within the networks and third-party access from the external environment remain the primary keys for security issues. Among other security threats, insider attacks are similarly challenging as exterior threats. However, insider attacks are unrecognized for a long period, and currently no effective measures to address the security issues as well as to safeguard the network from insider threats. The primary issue faced by the current technology is to detect insider attacks within the cloud. If the information in the system gets lost, then negotiating with the cloud consumers becomes hard. Moreover, cloud networks are less trusted as they lack to guarantee of security and privacy to the data. Currently, various solutions are presented to ensure external privacy for cloud systems. Yet, the challenges due to internal or insider threats must be tackled. Thus, it is crucial to address various problems produced by the traditional insider threat detection model including human actions. So, a novel deep learning-based insider threat prediction model using human behavior is suggested here. Initially, insider thread prediction data utilized for the validation are collected from benchmark resources. Next, the collected data is provided for the insider threats prediction phase. In the insider threats prediction phase, a developed Attention-based Deep Serial Cascaded Network (A-DSCNet) is used to identify the insider threats. The developed A-DSCNet is the integrated version of Deep Belief Network (DBN) and Capsule Network (CapsNet). Finally, various analyses are exec
暂无评论