Search

This research introduces a novel framework utilizing a sequential gated graph convolutional neural network (GGCN) designed specifically for botnet detection within Internet of Things (IoT) network environments. By capitalizing on the strengths of graph neural networks (GNNs) to represent network traffic as complex graph structures, our approach adeptly handles the temporal dynamics inherent to botnet attacks. Key to our approach is the development of a time-stamped multi-edge graph structure that uncovers subtle temporal patterns and hidden relationships in network flows, critical for recognizing botnet behaviors. Moreover, our sequential graph learning framework incorporates time-sequenced edges and multi-edged structures into a two-layered gated graph model, which is optimized with specialized message-passing layers and aggregation functions to address the challenges of time-series traffic data effectively. Our comparative analysis with the state of the art reveals that our sequential gated graph convolutional neural network achieves substantial improvements in detecting IoT botnets. The proposed GGCN model consistently outperforms the conventional model, achieving improvements in accuracy ranging from marginal to substantial—0.01% for BoT IoT and up to 25% for Mirai. Moreover, our empirical analysis underscores the GGCN's enhanced capabilities, particularly in binary classification tasks, on imbalanced datasets. These findings highlight the model's ability to effectively navigate and manage the varying complexity and characteristics of IoT security threats across different datasets. [ABSTRACT FROM AUTHOR]

With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%. [ABSTRACT FROM AUTHOR]

When quantifying the importance of supply and demand for oil price fluctuations, a wide range of estimates have been reported. Models identified via a sharp upper bound on the short‐run price elasticity of supply find supply shocks to be minor drivers. In turn, when replacing the upper bound with a weakly informative prior, supply shocks turn out to be substantially more important. In this paper, I revisit the evidence in a model that combines weakly informative priors with identification by non‐Gaussianity. For this purpose, a SVAR is developed where the unknown distributions of the structural shocks are modeled nonparametrically. The empirical findings suggest that once identification by non‐Gaussianity is incorporated into the model, posterior mass of the short‐run oil supply elasticity shifts toward zero and oil supply shocks become minor drivers of oil prices. In terms of contributions to the forecast error variance of oil prices, the model arrives at median estimates of just 6% over a 16‐month horizon. [ABSTRACT FROM AUTHOR]

We discuss combining sign restrictions with information in external instruments (proxy variables) to identify structural vector autoregressive (SVAR) models. In one setting, we assume the availability of valid external instruments. Sign restrictions may then be used to identify further orthogonal shocks, or as an additional piece of information to pin down the shocks identified by the external instruments more precisely. In a second setting, we assume that proxy variables are only "plausibly exogenous" and suggest various types of inequality restrictions to bound the relation between structural shocks and the external variable. This can be combined with conventional sign restrictions to further narrow down the set of admissible models. Within a proxy-augmented SVAR, we conduct Bayesian inference and discuss computation of Bayes factors. They can be useful to test either the sign- or IV restrictions as overidentifying. We illustrate the usefulness of our methodology in estimating the effects of oil supply and monetary policy shocks. [ABSTRACT FROM AUTHOR]

The strobed preamble approach introduced in the X-MAC protocol minimizes long preamble duration, overhearing, and per-hop latency in conventional wireless sensor networks (WSNs). However, it incurs high per-packet overhead and extra delay under high traffic scenarios as it operates only in the unsynchronized state. In this paper, we model a variant of X-MAC, namely XX-MAC, which employs an adaptive duty-cycling algorithm to address this issue in low data rate WSNs with short, fixed inter-packet arrival time. Furthermore, we identify the shortcoming of XX-MAC as well as propose a request-based MAC protocol, namely EX-MAC, targeting WSNs in dynamic traffic scenarios. Simulations show that at optimum slot duration, XX-MAC reduces the per-packet delay by 13.53% and 48.86% than the delay experienced by X-MAC and B-MAC, respectively. XX-MAC, on average, can deliver 92.5% of packets to the receiver, whereas X-MAC and B-MAC respectively support 91.66% and 82.91% packet delivery. XX-MAC also reduces the energy consumption per received packet by 2.61% than X-MAC, and by 65.31% than the B-MAC protocol. Experimental results also demonstrate that under variable traffic conditions, EX-MAC offers the lowest packet loss (8.55%), whilst XX-MAC and X-MAC experience 13.1% and 18.3% packet loss, respectively. EX-MAC decreases per-packet network energy consumption (3.056mJ/packet) compared with XX-MAC (3.107mJ/packet) and X-MAC (3.424mJ/packet). Furthermore, EX-MAC minimizes the mean delay per received packet by 5.758% and 10.457% (approximately) than that of XX-MAC and X-MAC, respectively. [ABSTRACT FROM AUTHOR]

We propose to exploit stochastic volatility for statistical identification of structural vector autoregressive models (SV-SVAR). We discuss full and partial identification of the model and develop efficient EMalgorithms formaximum likelihood inference. Simulation evidence suggests that the SV-SVARworks well in identifying structural parameters also under misspecification of the variance process, particularly if compared to alternative heteroscedastic SVARs. We apply the model to study the importance of oil supply shocks for driving oil prices. Since shocks identified by heteroscedasticity may not be economically meaningful, we exploit the framework to test instrumental variable restrictions which are overidentifying in the heteroscedasticmodel. Our findings suggest that conventional supply shocks are negligible, while news shocks about future supply account for almost all the variation in oil prices. [ABSTRACT FROM AUTHOR]

Electro-migration (EM) induced by electric current under the conditions of multi-physical fields in integrated circuits and electronic packaging is a crucial factor that affects reliability and safety of the entire system. The uncertainty quantification and propagation in the EM process are the challenging issues that deserve more attention. In this article, the uncertainties in the related material parameters of the Sn–Ag–Cu (SAC) solder and copper conductors are taken into consideration based on the stochastic finite-element model. The corners and edges of the contact surface in the SAC solder are the most dynamic and active places with the maximum concentration gradient. This reaches a satisfied agreement with the experimental results and parallel numerical investigations in the literatures. The extreme values of the concentration and its gradient in each time step are computed and recorded. The accuracy and convergence of results are confirmed by the comparison of different period durations and time step scales with discrete time points. Furthermore, the probability density distribution, mean, and variance of the extreme values in different time steps are recorded and compared. Based on the huge database provided by the Monte Carlo-based stochastic finite-element model (MC-SFEM), the correlations between the material parameters and the concentration as well as the concentration gradients are analyzed. The proposed MC-SFEM is a feasible and effective model for the comprehensive analysis of EM with the potential in uncertainty and reliability analysis. [ABSTRACT FROM AUTHOR]

Road target recognition ability of automotive millimetre-wave (mmWave) radar is crucial in areas such as autonomous driving, advanced driver assistance systems (ADAS), and automated emergency braking systems (AEBS). Current mmWave radar systems are primarily utilized for speed, distance, and angle measurements, with limited capability or unsatisfactory performance in target classification. In response to this limitation, this paper proposes a novel method for road target recognition, using radar range-Doppler spectrum as input data and introducing a global attention mechanism and SCConv module. First, the range-Doppler spectrum is processed by the clutter removal algorithm block to remove background clutter and vibration interference. Second, considering the small features and susceptibility to noise interference in the range-Doppler spectrum, we have devised a deep residual network based on a global attention mechanism, significantly enhancing the model’s accuracy in range-Doppler spectrum classification. Finally, we introduce the SCConv module and improve the downsampling module in ResNet to enhance the model’s classification accuracy. Experimental results demonstrate that the model achieves an average accuracy of 99.79% in classifying six types of road targets, significantly outperforming other methods. This research is of significant importance in advancing the understanding of road traffic conditions by autonomous driving systems and enhancing system safety. [ABSTRACT FROM AUTHOR]