Contrastive learning underpins most current self-supervised time series representation methods. The strategy for constructing positive and negative sample pairs significantly affects the final representation quality. However, due to the continuous nature of time series semantics, the modeling approach of contrastive learning struggles to accommodate the characteristics of time series data. This results in issues such as difficulties in constructing hard negative samples and the potential introduction of inappropriate biases during positive sample construction. Although some recent works have developed several scientific strategies for constructing positive and negative sample pairs with improved effectiveness, they remain constrained by the contrastive learning framework. To fundamentally overcome the limitations of contrastive learning, this paper introduces Frequency-masked Embedding Inference (FEI), a novel non-contrastive method that completely eliminates the need for positive and negative samples. The proposed FEI constructs 2 inference branches based on a prompting strategy: 1) Using frequency masking as prompts to infer the embedding representation of the target series with missing frequency bands in the embedding space, and 2) Using the target series as prompts to infer its frequency masking embedding. In this way, FEI enables continuous semantic relationship modeling for time series. Experiments on 8 widely used time series datasets for classification and regression tasks, using linear evaluation and end-to-end fine-tuning, show that FEI significantly outperforms existing contrastive-based methods in terms of generalization. This study provides new insights into self-supervised representation learning for time series.

This article investigates the sliding mode fault-tolerant secure control for cyber-physical system facing jamming attacks and multiple physical faults. An intelligent attacker is capable of emitting interference power and adjusting its strategy by observing the transmitter's sending power, leading to packet dropouts in the controller-to-actuator channel. A Bayesian Stackelberg game is exploited to capture these competitive interactions between the two players, in which the transmitter and the intelligent attacker can only probabilistically obtain information about each other's channel state and transmission cost. Meanwhile, the transmitter has only statistical knowledge about either the presence or absence of the attacker in the practical environment. First, optimal transmission power strategies for both sides are studied using the backward induction method and the Karush-Kuhn-Tucker condition. Second, an integrated observer is designed to simultaneously estimate the system state, actuator fault, and sensor fault. Furthermore, the reaching law is proposed so that the state trajectories can reach the preselect sliding surface during the assigned finite time interval from any initial state. Sufficient criteria are derived to guarantee stochastic finite-time boundedness during reaching and sliding motion phases of closed-loop systems using a sliding-mode fault-tolerant secure controller. Finally, simulation results validate the effectiveness and superiority of the proposed method.

Deep learning techniques have been used to enhance the joint inversion process of dc resistivity and seismic travel time data. Specifically, we introduce deep perceptual losses (DPLs) derived from a pretrained edge detection network. These losses play a pivotal role in enforcing structural constraints during the training of encoder-decoder networks for model prediction. Our approach is based on the assumption of structural similarity, meaning that we presume a shared structure between pairs of resistivity and velocity models, without necessitating prior relationships between the property values. We provide an exhaustive exposition of our joint inversion framework, elucidating the network construction and training dataset design. Numerical examples demonstrate our DPL-based method outperforms the conventional separate inversions and cross-gradient-based joint inversion in view of recovered property values and boundaries of the anomalous bodies. Furthermore, our approach retains the traditional workflows of separate inversions, endowing our framework with the flexibility to expand into multiphysics joint inversion scenarios. To illustrate this adaptability, we incorporate induced polarization data into the framework, further validating its efficacy.

This paper investigates the finite-time sliding mode fault-tolerant secure control issue for cyber-physical systems under period denial-of-service (DoS) jamming attacks and packet dropouts. The considered cyber attacks are periodic DoS attacks which are modeled by a kind of periodic jamming signals that cause data dropouts on the sensor-to-observer channel. Additionally, an update rule is proposed to characterize packet dropouts caused by intrinsic factors and periodic DoS jamming attacks of wireless channels. Based on the update rule, an observer is presented to obtain the unknown state and fault information. Then, a sliding mode fault-tolerant secure controller is designed using estimated information to ensure the estimated state reaches the sliding surface within a finite time, entering the quasi-sliding mode domain. Moreover, sufficient conditions are provided to guarantee the stochastic finite-time boundedness of the closed-loop system during the whole phase, even in the presence of packet dropouts and DoS jamming attacks. Finally, a simulation result validates the effectiveness and superiority of the proposed method.

In this abstract, we introduce a deep learning enhanced (DLE) framework for solving multi-physics joint inversion. For the inceptive DLE joint inversion scheme, a well-trained neural network based on structural similarity is used to provide better initials for the separate inversions. The preservation of the separate inversions makes the framework flexible to deal with different sensing configurations, nonconforming discretization, as well as joint inversion of multiple data types. Further, deep perceptual losses (DPL) derived from a pre-trained edge detection network are introduced to enforce structural constraints. Synthetic examples demonstrate improved inversion results from the DLE framework compared to the separate inversions and cross-gradient-based joint inversion. In addition, the DLE framework is simplified to solve 3D joint inversion of the airborne magnetic and gravity gradient data collected from the Decorah area. The inversion results verify the effectiveness and higher efficiency of the DL-based method compared to the cross-gradient-based joint inversion.

Full-waveform inversion (FWI) plays a significant role in producing high-resolution subsurface imaging in seismic prospecting and ground penetrating radar (GPR). However, FWI faces various challenges in practice. For example, the lack of low-frequency information due to acquisition limitations will make the FWI prone to falling to the local minimum. In this project, a deep learning-based approach is proposed to extrapolate the low-frequency data. Specifically, we propose a robust progressive learning (RPL) algorithm that combines physics-guided FWI and data-driven deep learning technology. The proposed method is robust against the choice of the initial model. Experimental results show that our method can achieve high efficiency and accuracy by using a limited amount of training data. The subsurface structures are successfully reconstructed with our extrapolated low-frequency data.

In this article, a new scheme based on the supervised descent method (SDM) for solving directional electromagnetic logging-while-drilling (LWD) inverse problems is proposed. The SDM provides us a new perspective to combine the classical gradient-based inversion and machine-learning-based inversion schemes. It iteratively learns a set of descent directions in the offline training process, where the training model set is generated in advance according to the prior information, and then updates the models with the learned descent directions as well as data residuals in the prediction stage, resulting in great flexibility to incorporate prior information, the capability of skipping local minima, and accelerated convergence. The generalization ability of the SDM to interrogate new models that are not contained in the training model set is also explored. By utilizing real-time information obtained from the logging process, the learned descent directions can be slightly revised with a higher efficiency to get closer to the true model. In addition, we probe the sensitivity of the SDM by adding different levels of random noise to the measurements. Numerical examples demonstrate that SDM-based inversion can achieve a higher resolution, faster convergence, and higher robustness than conventional schemes such as Occam's inversion.

As blockchain technologies mature and ecosystems over blockchain evolve, peers on blockchain networks often face situations in which they need to conduct voting for decision-making; as happened in the case of the DAO hard fork event on Ethereum. However, a natively built-in voting mechanism is not available on any of the existing blockchain platforms. Thus, the decision making either is delegated to a few network members who make such decisions offline or is dependent on third party online voting services. In both cases, peers directly or indirectly rely on trusted parties or centralized systems. This is against the basic decentralization principle of blockchain and exposes the election to frauds. To facilitate decision-making in a decentralized and secure manner, we propose a native blockchain voting protocol for peers to vote over their existing blockchain network without the need of any trusted or third party. Our protocol preserves end-to-end privacy and possesses desirable properties such as detectability and correctability against cheating. A reference implementation of our protocol on Hyperledger Fabric that demonstrates the validity and practical applicability of our protocol is also provided.

This paper deals with the state estimation fusion problem for stochastic continuous-time systems over wireless sensor networks (WSNs) with multi-sensor scheduling. Due to the power limitation and communication constraints in WSNs, a closed-loop stochastic event-triggered mechanism is designed to reduce the redundant data transmission. Since this design preserves the Gaussian property of the conditional distribution of the system state, an exact minimum mean square error (MMSE) estimator could be presented for every sensor subsystem. Then, the distributed event-triggered information fusion estimator is proposed based on maximum a posterior probability criterion by a matrix-weighted combination of all available local estimates from sensor subsystems. The proposed distributed algorithm has advantages on reliability, computation efficiency due to the netted parallel structure. A numerical simulation is conducted to illustrate the effectiveness of the proposed distributed estimator.

The MPEG committee has completed development of a new audio coding standard called “MPEG-4 advanced audio coding-enhanced low delay” (AAC-ELD). AAC-ELD uses low delay spectral band replication (LD-SBR) technology together with a low delay time domain alias cancellation (LD TDAC) filterbank in the encoder to achieve both high coding efficiency and low algorithmic delay. In this paper, we present fast algorithms for implementing LD-TDAC filterbanks in AAC-ELD. Two types of fast algorithms are presented. In the first, we map LD-TDAC analysis and synthesis filterbanks to modified discrete cosine transform (MDCT) and inverse modified discrete cosine transform (IMDCT), respectively. Since MDCT/IMDCT are already extensively used in AAC and they have many fast algorithms, this mapping not only provides a fast implementation but also allows a common implementation of the filterbanks in AAC Low Complexity (AAC-LC), AAC Low Delay (AAC-LD) and AAC-ELD codecs. In the second algorithm, we provide a mapping to discrete Cosine transform of type II. The mapping to DCT-II allows the merger of the matrix operations with the windowing stage that precedes or follows them. This further reduces the number of multiplications and leads to an algorithm with the lowest known arithmetic complexity. For filterbanks of lengths 1024 and 960, we also present a new fast factorization of 15-point DCT-II that requires only 14 irrational multiplications, 3 dyadic rational multiplications and 67 additions.

In a virtual machine system, the scheduler within the virtual machine monitor (VMM) plays a key role in determining the overall fairness and performance characteristics of the whole system. However, traditional VMM schedulers focus on sharing the processor resources fairly among guest domains while leaving the scheduling of I/O missions as a secondary concern. This would cause serious degradation of I/O performance and make virtualization less desirable for I/O-intensive applications. In order to eliminate the I/O performance bottleneck caused by scheduling delay, this paper proposes a virtual machine I/O scheduling model based on multi-core dynamic partitioning, and implements a prototype based on Xen virtual machine. In this model, I/O operations of guest domains are monitored and the runtime information is analyzed. When the preset conditions are satisfied, the processor cores of the system are divided into three subsets to undertake different missions respectively. Each subset employs specific scheduling strategy to meet the requirement of different tasks. Experiment results demonstrate that our scheduling model can efficiently improve the I/O performance of virtual machine system: in comparison with the case using default Xen credit scheduler, the network and disk bandwidth increase by 35% and 12% respectively, and the average latency of ping operations drops by 37%. At the same time, our method only causes slight negative effect on the performance of compute-intensive applications, and the scheduling fairness can also be guaranteed.