Search

In order to avoid repeated task offloading and realize the reuse of popular task computing results, we construct a novel content caching-assisted vehicular edge computing (VEC) framework. In the face of irregular network topology and unknown environmental dynamics, we further propose a multi-agent graph attention reinforcement learning (MGARL) based edge caching scheme, which utilizes the graph attention convolution kernel to integrate the neighboring nodes' features of each agent and further enhance the cooperation among agents. Our simulation results show that our proposed scheme is capable of improving the utilization of caching resources while reducing the long-term task computing latency compared to the baselines., Comment: 6 pages, 5 figures

Speech emotion recognition plays a crucial role in human-machine interaction systems. Recently various optimized Transformers have been successfully applied to speech emotion recognition. However, the existing Transformer architectures focus more on global information and require large computation. On the other hand, abundant speech emotional representations exist locally on different parts of the input speech. To tackle these problems, we propose a Multi-Scale TRansfomer (MSTR) for speech emotion recognition. It comprises of three main components: (1) a multi-scale temporal feature operator, (2) a fractal self-attention module, and (3) a scale mixer module. These three components can effectively enhance the transformer's ability to learn multi-scale local emotion representations. Experimental results demonstrate that the proposed MSTR model significantly outperforms a vanilla Transformer and other state-of-the-art methods across three speech emotion datasets: IEMOCAP, MELD and, CREMAD. In addition, it can greatly reduce the computational cost.

Due to its excellent performance in rate and resolution, fully-digital (FD) massive multiple-input multiple-output (MIMO) antenna arrays has been widely applied in data transmission and direction of arrival (DOA) measurements, etc. But it confronts with two main challenges: high computational complexity and circuit cost. The two problems may be addressed well by hybrid analog-digital (HAD) structure. But there exists the problem of phase ambiguity for HAD, which leads to its low-efficiency or high-latency. Does exist there such a MIMO structure of owning low-cost, low-complexity and high time efficiency at the same time. To satisfy the three properties, a novel heterogeneous hybrid MIMO receiver structure of integrating FD and heterogeneous HAD ($\rm{H}^2$AD-FD) is proposed and corresponding multi-modal (MD)-learning framework is developed. The framework includes three major stages: 1) generate the candidate sets via root multiple signal classification (Root-MUSIC) or deep learning (DL); 2) infer the class of true solutions from candidate sets using machine learning (ML) methods; 3) fuse the two-part true solutions to achieve a better DOA estimation. The above process form two methods named MD-Root-MUSIC and MDDL. To improve DOA estimation accuracy and reduce the clustering complexity, a co-learning-aided MD framework is proposed to form two enhanced methods named CoMDDL and CoMD-RootMUSIC. Moreover, the Cramer-Rao lower bound (CRLB) for the proposed $\rm{H}^2$AD-FD structure is also derived. Experimental results demonstrate that our proposed four methods could approach the CRLB for signal-to-noise ratio (SNR) > 0 dB and the proposed CoMDDL and MDDL perform better than CoMD-RootMUSIC and MD-RootMUSIC, particularly in the extremely low SNR region.

The rapid evolution of Internet of Things (IoT) technology has spurred the widespread adoption of Human Activity Recognition (HAR) in various daily life domains. Federated Learning (FL) is frequently utilized to build a global HAR model by aggregating user contributions without transmitting raw individual data. Despite substantial progress in user privacy protection with FL, challenges persist. Regulations like the General Data Protection Regulation (GDPR) empower users to request data removal, raising a new query in FL: How can a HAR client request data removal without compromising other clients' privacy? In response, we propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data. Our method employs a third-party dataset unrelated to model training. Using KL divergence as a loss function for fine-tuning, we aim to align the predicted probability distribution on forgotten data with the third-party dataset. Additionally, we introduce a membership inference evaluation method to assess unlearning effectiveness. Experimental results across diverse datasets show our method achieves unlearning accuracy comparable to \textit{retraining} methods, resulting in speedups ranging from hundreds to thousands.

Fine holes are an important structural component of industrial components, and their inner surface quality is closely related to their function.In order to detect the quality of the inner surface of the fine hole,a special optical measurement system was investigated in this paper. A sight pipe is employed to guide the external illumination light into the fine hole and output the relevant images simultaneously. A flexible light array is introduced to suit the narrow space, and the effective field of view is analyzed. Besides, the arc surface projection error and manufacturing assembly error of the device are analyzed, then compensated or ignored if small enough. In the test of prefabricated circular defects with the diameter {\phi}0.1mm, {\phi}0.2mm, 0.4mm distance distribution and the fissure defects with the width 0.3mm, the maximum measurement error standard deviation are all about 10{\mu}m. The minimum diameter of the measured fine hole is 4mm and the depth can reach 47mm.

We recently proposed a high-granularity calorimeter insert for the Electron-Ion Collider (EIC) that uses plastic scintillator tiles read out by SiPMs. Among its innovative features are an ASIC-away-of-SiPM strategy for reducing cooling requirements and minimizing space use, along with employing 3D-printed frames to reduce optical crosstalk and dead areas. To evaluate these features, we built a 40-channel prototype and tested it using a 4 GeV positron beam at Jefferson Laboratory. The measured energy spectra and 3D shower shapes are well described by simulations, confirming the effectiveness of the design, construction techniques, and calibration strategy. This constitutes the first use of SiPM-on-tile technology in EIC detector designs.

Measuring the region $0.1 < Q^{2} < 1.0$ GeV$^{2}$ is essential to support searches for gluon saturation at the future Electron-Ion Collider. Recent studies have revealed that covering this region at the highest beam energies is not feasible with current detector designs, resulting in the so-called $Q^{2}$ gap. In this work, we present a design for the Few-Degree Calorimeter (FDC), which addresses this issue. The FDC uses SiPM-on-tile technology with tungsten absorber and covers the range of $-4.6 < \eta < -3.6$. It offers fine transverse and longitudinal granularity, along with excellent time resolution, enabling standalone electron tagging. Our design represents the first concrete solution to bridge the $Q^{2}$ gap at the EIC.

Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreover, the temporal scales of important information may vary over a large range within and across speech segments. Although transformer-based models have made progress in this field, the existing models could not precisely locate important regions at different temporal scales. To address the issue, we propose Dynamic Window transFormer (DWFormer), a new architecture that leverages temporal importance by dynamically splitting samples into windows. Self-attention mechanism is applied within windows for capturing temporal important information locally in a fine-grained way. Cross-window information interaction is also taken into account for global communication. DWFormer is evaluated on both the IEMOCAP and the MELD datasets. Experimental results show that the proposed model achieves better performance than the previous state-of-the-art methods., Comment: 4 pages, 5 figures, 3 tables, accepted by 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP2023)

Multi-spectral CT (MSCT) is increasingly used in industrial non-destructive testing and medical diagnosis because of its outstanding performance like material distinguishability. The process of obtaining MSCT data can be modeled as nonlinear equations and the basis material decomposition comes down to the inverse problem of the nonlinear equations. For different spectra data, geometric inconsistent parameters cause geometrical inconsistent rays, which will lead to mismatched nonlinear equations. How to solve the mismatched nonlinear equations accurately and quickly is a hot issue. This paper proposes a general iterative method to invert the mismatched nonlinear equations and develops Schmidt orthogonalization to accelerate convergence. The validity of the proposed method is verified by MSCT basis material decomposition experiments. The results show that the proposed method can decompose the basis material images accurately and improve the convergence speed greatly.

Hydrides offer an opportunity to study high-temperature (Tc) superconductivity at experimentally achievable pressures. However, they remained extremely high. Using density functional theory calculations, herein we demonstrated that a newly rare earth hydride, namely bulk ErH2, could be superconducting with a Tc around 80 K at 14.5 GPa. To date, the drived pressure is the lowest reported value for compressed hydrides. Besides superconductivity, Fermi Surface nesting and Kondo effect were manifested at this pressure. Intriguingly, due to Kondo destruction, superconductivity was prone to exist at 15 GPa. Under the rest of applied pressures, we also revealed a gap of band structure at 20 GPa on the background of normal metallic states. At 20 GPa, this compressed system could act as a host of superconductor being judged from a sharp jump of spontaneous magnetic susceptibility with an evanescent spin density of state at Fermi level along with the competition between spin density wave and superconductivity. Finally, electron pairing glue for ErH2 at these three typical pressures was attributed to the antiferromagnetic spin fluctuation.

State-of-the-art speaker recognition systems are trained with a large amount of human-labeled training data set. Such a training set is usually composed of various data sources to enhance the modeling capability of models. However, in practical deployment, unseen condition is almost inevitable. Domain mismatch is a common problem in real-life applications due to the statistical difference between the training and testing data sets. To alleviate the degradation caused by domain mismatch, we propose a new feature-based unsupervised domain adaptation algorithm. The algorithm we propose is a further optimization based on the well-known CORrelation ALignment (CORAL), so we call it CORAL++. On the NIST 2019 Speaker Recognition Evaluation (SRE19), we use SRE18 CTS set as the development set to verify the effectiveness of CORAL++. With the typical x-vector/PLDA setup, the CORAL++ outperforms the CORAL by 9.40% relatively on EER., Comment: 5 pages, 1 figures. This paper has been accepted to IEEE ICASSP 2022

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be accurately estimated and subtracted. In this paper we propose two novel approaches to estimate the ILM based on Listen-Attend-Spell (LAS) framework. The first method is to replace the context vector of the LAS decoder at every time step with a vector that is learned with training transcripts. Furthermore, we propose another method that uses a lightweight feed-forward network to directly map query vector to context vector in a dynamic sense. Since the context vectors are learned by minimizing the perplexities on training transcripts, and their estimation is independent of encoder output, hence the ILMs are accurately learned for both methods. Experiments show that the ILMs achieve the lowest perplexity, indicating the efficacy of the proposed methods. In addition, they also significantly outperform the shallow fusion method, as well as two previously proposed ILM Estimation (ILME) approaches on several datasets., Comment: Proceedings of INTERSPEECH

In a secure spatial modulation with a malicious full-duplex attacker, how to obtain the interference space or channel state information (CSI) is very important for Bob to cancel or reduce the interference from Mallory. In this paper, different from existing work with a perfect CSI, the covariance matrix of malicious interference (CMMI) from Mallory is estimated and is used to construct the null-space of interference (NSI). Finally, the receive beamformer at Bob is designed to remove the malicious interference using the NSI. To improve the estimation accuracy, a rank detector relying on Akaike information criterion (AIC) is derived. To achieve a high-precision CMMI estimation, two methods are proposed as follows: principal component analysis-eigenvalue decomposition (PCA-EVD), and joint diagonalization (JD). The proposed PCA-EVD is a rank deduction method whereas the JD method is a joint optimization method with improved performance in low signal to interference plus noise ratio (SINR) region at the expense of increased complexities. Simulation results show that the proposed PCA-EVD performs much better than the existing method like sample estimated covariance matrix (SCM) and EVD in terms of normalized mean square error (NMSE) and secrecy rate (SR). Additionally, the proposed JD method has an excellent NMSE performance better than PCA-EVD in the low SINR region (SINR < 0dB) while in the high SINR region PCA-EVD performs better than JD., Comment: 5 pages, 4 figures