With the continuous advancement of automotive intelligence and ubiquitous connection, In-Vehicle Networks (IVN) are confronted with heightened security challenges. Attackers can inject false messages to manipulate or disrupt critical functional modules on the vehicle, leading to significant safety issues. Given the real-time requirements and resource constraints of the in-vehicle network, a lightweight Intrusion Detection System (IDS) is needed to deal with the security threats caused by attacks. This paper proposes an effective intrusion detection method to address these requirements. The method combines refined CAN traffic features with a lightweight Deep Learning (DL) network. The time interval series, ID and the CAN message payload are extracted by a T-shaped window, vectorized to form a one-dimensional data frame, and the detection is completed by a lightweight 1D deep learning model using efficient convolution calculation. In binary and multiclass experiments on two publicly available datasets, the feature refinement strategy is discussed. Compared to existing deep learning-based intrusion detection methods, our approach demonstrates advantages in both intrusion detection performance and computational complexity, highlighting its deployment potential in embedded IVN environments.

Devices equipped with algorithms for detecting infant cries allow parents to respond immediately to their crying babies. However, improving detection performance often requires complex algorithms that consume more computing resources, leading to increased power consumption and prices. In this study, we propose a novel approach that leverages first-order Wavelet Scattering Coefficients (WSC) as translation-invariant and deformation-stable representations of infant crying sounds. Based on this approach, we introduce an end-to-end Deep Neural Network (DNN) architecture designed to detect crying using merely 17K parameters and 22.7M MACs. The accuracy results, with a 96.98% accuracy rate on open-source datasets, demonstrate the effectiveness and robustness of our model for detecting infant cries in real-world environments.

The physics-determined broadband spectral energy distributions (SEDs) of blazars have been widely used to study their properties during their flaring/outburst states, while the nonflaring state takes up most of their lifetime and the general property of blazars has been barely discussed. In this work, for the first time, we used the archival data and employed the physics-determined SED processing method to form approximately average-state SEDs for 513 Fermi bright BL Lacs. In general, we found that the magnetic field (B) is weaker than those obtained for the flaring/outburst state by nearly 1 order of magnitude, and the dissipation region size (R) is larger than those obtained for the flaring/outburst state, suggesting that the dissipation region could be more extended and less magnetized. A correlation between the synchrotron self-Compton peak frequency ( log ν ssc ) and the synchrotron peak frequency ( log ν sy ) suggests that the inverse Compton scattering of higher-synchrotron-peaked BL Lacs suffers a significant Klein–Nishina (KN) suppression; we quantified the condition of KN suppression by determining the critical synchrotron peak frequency ( ν sy c ) and found 359 out of 513 sources in our sample suffer KN suppression. Furthermore, our analysis of the relationship between synchrotron curvature (1/b _sy) and log ν sy indicates that the energy-dependent probability acceleration mechanism may dominate the particle acceleration in BL Lac jets.

In the forthcoming era of big astronomical data, it is a burden to find target sources from ground-based and space-based telescopes. Although machine-learning methods have been extensively utilized to address this issue, the incorporation of in-depth data analysis can significantly enhance the efficiency of identifying target sources when dealing with massive volumes of astronomical data. In this work, we focused on the task of finding active galactic nucleus (AGN) candidates and identifying BL Lacertae objects (BL Lac) or flat spectrum radio quasar (FSRQ) candidates from the 4FGL_DR3 uncertain sources. We studied the correlations among the attributes of the 4FGL_DR3 catalog and proposed a novel method, named fractal dimension–inverse discrete wavelet transform (FDIDWT), to transform the original data. The transformed data set is characterized as low-dimensional and feature-highlighted, with the estimation of correlation features by fractal dimension theory and the multi-resolution analysis by inverse discrete wavelet transform (IDWT). Combining the FDIDWT method with an improved lightweight MatchboxConv1D model, we accomplished two missions: (1) to distinguish the AGNs from others (non-AGNs) in the 4FGL_DR3 uncertain sources with an accuracy of 96.65% ± 1.32%, namely Mission A; and (2) to classify blazar candidates of uncertain type into BL Lacs or FSRQs with an accuracy of 92.03% ± 2.2%, namely Mission B. There are 1354 AGN candidates in Mission A, and 482 BL Lacs candidates and 128 FSRQ candidates were found in Mission B. The results show a high consistency of greater than 98% with the results in previous works. In addition, our method has the advantage of finding less variable and relatively faint sources than ordinary methods.

In our study of the correlations between IceCube-detected neutrino events and γ-ray properties of blazars, we recognize the inherent challenges posed by the limited detection of neutrinos. In this paper, we explore few-shot learning to deal with the class imbalance and few-shot issues presented in the incremental version of the 12 yr Fermi-LAT γ-ray source catalog (4FGL_ DR3). Specifically, we train a triplet network to transform the blazars with neutrino emission (NBs) and nonblazar samples into an embedding space where their similarities can be measured. With two-way three-shot learning, 199 out of 3708 blazars without neutrino emission (non-NBs) are considered as the potential blazars emitting neutrinos (NB candidates, or NBCs for short), with a similarity score against NBs exceeding 98%. Moreover, the Kolmogorov–Smirnov test supports our identification of NBCs.