Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defen...
详细信息
This paper proposes a unified framework for the stability analysis of discrete-time nonlinear systems from social networks, including the Friedkin-Johnsen opinion model, two opinion dynamics models in the study of soc...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
This paper proposes a unified framework for the stability analysis of discrete-time nonlinear systems from social networks, including the Friedkin-Johnsen opinion model, two opinion dynamics models in the study of social power, and a general nonlinear polar opinion model. Three novel convergence results are proposed to treat various conditions based on LaSalle invariance principle. Several applications are provided to illustrate the power of the proposed framework.
In this article, the use of channel state information (CSI) for indoor positioning is studied. In the considered model, a server equipped with several antennas sends pilot signals to users, while each user uses the re...
详细信息
Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this paper in...
详细信息
Semantic communication has emerged as a promising technology for enhancing communication efficiency. However, most existing research emphasizes single-task reconstruction, neglecting model adaptability and generalizat...
详细信息
The surge in the number of e-bikes also brings certain problems of traffic road order and safety management. Analyzing and mining the travel routes of e-bikes to discover the valuable patterns latent in large-scale tr...
详细信息
ISBN:
(数字)9798350376968
ISBN:
(纸本)9798350376975
The surge in the number of e-bikes also brings certain problems of traffic road order and safety management. Analyzing and mining the travel routes of e-bikes to discover the valuable patterns latent in large-scale trajectories will help the traffic department to manage e-bikes. For this reason, this paper proposes a frequent pattern mining method for trajectories based on deep clustering, which shows the travel patterns of e-bikes through frequent trajectory patterns in order to improve the transportation service capacity. In the feature extraction stage, the method transforms the trajectory point sequence into a raster sequence, and obtains the potential vectors of e-bike trajectories based on the autoencoder; in the clustering stage, it integrates the deep learning model and the improved clustering algorithm by adding the chameleon model to mine the frequent pattern of trajectory vectors, and completes the unsupervised clustering of deep learning by updating the parameters and clustering centers in the feature extraction stage. Finally, the effectiveness and application value of our method are proved by a large number of experiments.
In recent years, phishing scams have seriously threatened Ethereum's ecological security and caused massive economic losses. Moreover, the significant disparity between the number of normal addresses and phishing ...
详细信息
ISBN:
(数字)9798350376968
ISBN:
(纸本)9798350376975
In recent years, phishing scams have seriously threatened Ethereum's ecological security and caused massive economic losses. Moreover, the significant disparity between the number of normal addresses and phishing addresses on Ethereum poses a challenge for detecting phishing scams. Existing studies primarily employ methods such as oversampling, filtering rules, and traditional machine learning models to resolve the Ethereum data imbalance problem. However, these methods disregard topological structure features of the transaction network and the link relationship between nodes. In this paper, we propose an Ethereum phishing scams detection model based on Generative Adversarial Graph Networks called EGAGN to alleviate imbalanced data, enhance node representation, and then improve detection performance. Specifically, the graph generator and discriminator play with each other to generate synthetic nodes that satisfy the real nodes distribution to balance Ethereum data and extract effective network structural features. We further extract statistical features from the transaction network and aggregate transaction records based on time series to obtain trading features. The complete representation of nodes is composed of the above three types of features to detect phishing nodes. Experimental results on the real-world Ethereum dataset show that EGAGN outperforms existing models and is far ahead in recall, which indicates that our model can effectively detect Ethereum phishing scams.
Many chronic disease prediction methods have been proposed to predict or evaluate diabetes through artificial neural ***,due to the complexity of the human body,there are still many challenges to face in that *** of t...
详细信息
Many chronic disease prediction methods have been proposed to predict or evaluate diabetes through artificial neural ***,due to the complexity of the human body,there are still many challenges to face in that *** of them is how to make the neural network prediction model continuously adapt and learn disease data of different patients,*** paper presents a novel chronic disease prediction system based on an incremental deep neural *** propensity of users suffering from chronic diseases can continuously be evaluated in an incremental *** time,the system can predict diabetes more and more accurately by processing the feedback *** diabetes prediction studies are based on a common dataset,the Pima Indians diabetes dataset,which has only eight input *** order to determine the correlation between the pathological characteristics of diabetic patients and their daily living resources,we have established an in-depth cooperation with a hospital.A Chinese diabetes dataset with 575 diabetics was ***’data collected by different sensors were used to train the network *** evaluated our system using a real-world diabetes dataset to confirm its *** experimental results show that the proposed system can not only continuously monitor the users,but also give early warning of physiological data that may indicate future diabetic ailments.
Machine learning techniques have been have proven to be more effective than conventional extensively used in the creation of intrusion detection systems (IDS) that can swiftly and automatically identify and classify c...
Machine learning techniques have been have proven to be more effective than conventional extensively used in the creation of intrusion detection systems (IDS) that can swiftly and automatically identify and classify cyber attacks at the host-and network-levels. A scalable solution is needed since destructive attacks are happening so quickly and are changing all the time. For more investigation, the malware community has access to a number of malware databases. The performance of several machine learning algorithms on a range of datasets that were made available to the general public, however, has not yet been thoroughly evaluated by any study. The publicly available malware datasets should be regularly updated and benchmarked due to the dynamic nature of malware and the continuously evolving attacking techniques. In this study, a deep neural network (DNN), a type of deep learning model, is examined in order to create a flexible and efficient IDS to identify and categorise unexpected and unanticipated cyber threats. In order to analyse a variety of datasets that have been produced throughout time using both static and dynamic methodologies, it is vital to take into account the rapid increase in attacks and the constant evolution of network behaviour. It is simpler to select the most effective algorithm for accurately predicting forthcoming cyber attacks with the help of this type of research. Many publicly available benchmark malware datasets are used to offer a thorough review of DNN and other conventional machine learning classifier studies. The KDDCup 99 dataset and the accompanying hyper parameter selection techniques are used to choose the ideal network parameters and topologies for DNNs. A learning rate of [0.01-0.5] is applied to every 1,000-epoch DNN experiment. A variety of datasets, including NSL-KDD, UNSW-NB15, Kyoto, WSN-DS, and CICIDS 2017, as well as the DNN model that performed well on KDDCup 99 are used to conduct the benchmark. Our DNN model trains a
The increasing depth and applications of 5G wireless sensor networks also raise the possibility of network intrusions. In this research, a network intrusion detection system based on the ontology notion is proposed. A...
The increasing depth and applications of 5G wireless sensor networks also raise the possibility of network intrusions. In this research, a network intrusion detection system based on the ontology notion is proposed. As it creates ontologies and maintains the relationships among sensor nodes in a network, it is referred upon as a smart system. This proposed system finding is able to secure data in 5G networks. The current detection technique’s parameters such as patrol nodes, live nodes, hop, sensor nodes, and energy (in joules) are used to gauge how well the suggested system performs. Attack estimation rate (AER) and precision are the types of metrics in use.
暂无评论