Transient stability assessment (TSA) in power systems evaluates the system’s ability to withstand and recover from disturbances, which can be formulated as a classification problem. This paper presents a quantum machine learning-based TSA approach that leverages quantum embedded kernels (QEKs) to map nonlinear power system features into a high-dimensional Hilbert space, where the data becomes linearly separable. By employing a quantum kernel function and Kernel Target Alignment (KTA), we optimize a variational quantum circuit for the stability classification of power systems. Through extensive experiments on both noise-free quantum simulators and noisy quantum environments, we demonstrated the accuracy and noise resilience of the developed algorithm.

Magnetic resonance sounding (MRS) measurements used for detecting the subsurface aquifers commonly suffer from the notoriously low signal-to-noise ratio (SNR). The conventional approaches usually deal with the specific noise components step by step to improve the SNR, but the denoising effect is limited. MRS denoising methods based on neural networks show great potential in recovering the effective signals at low SNRs, but need large amount of high-quality labeled training datasets and have limitations in the application of measured data. And the denoising model trained for specific noise without noise type identification leads to excessive noise cancellation and low effective signal fidelity. To address these issues, we propose an intelligent denoising process by combining the noise detection method using support vector machine (SVM) and the intelligent denoising models for suppressing the specific noise. We first consider the discriminative features from the noisy signal in time and frequency domains for specific types of noise to be identified, so as to construct 3D feature vectors. Second, the noise detection model using SVM with radial basis function (RBF) kernel function is trained on the training samples. And the cross-validation technique is adapted to assess the performance of the noise detectors in the training process. Finally, the combination of the well-trained SVM noise detectors and the Dn-ResUnet models for specific noise is applied to process the noisy MRS data. The results of the simulation and field experiments show that our proposed method provides a one-stop flow for automatic noise identification and intelligent noise removal, which achieves a better denoising performance compared with the existing denoising methods.

Magnetic resonance sounding (MRS) is the only technology capable of noninvasive direct detection of subsurface water content. However, MRS often suffers from weak signals (10-9V) and may prohibit application in complex interference environments. To effectively recover the MRS signals regardless of whether they are corrupted by single spike or cascades of spikes, a method based on proximate wavelet coefficient recovery technology is proposed. Compared with the conventional methods, the proposed method improves the measurement efficiency by eliminating the demand for multiple recordings. The accuracy and stability of the proposed method are investigated using simulated signals from complex noise environments and geological conditions. Simulation results show significant improvements in signal-to-noise ratio (SNR) and retrieval of signal parameters, which demonstrate the validity of the proposed method. Moreover, the proposed method is applied on the synthetic signals embedded in noise-only data recorded in the urban environment. The results show that the proposed method can maintain a balance between preserving the signal component and suppressing complex spiky noise. The proposed method is implemented for the field data and the results demonstrate good practicality. The research results provide technical support for rapid detection in complex interference environments.

Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness. However, it is unclear whether DL projects, as software systems, are tested thoroughly or functionally correct when there is a need to treat and test them like other software systems. Therefore, we empirically study the unit tests in open-source DL projects, analyzing 9,129 projects from GitHub. We find that: (1) unit tested DL projects have positive correlation with the open-source project metrics and have a higher acceptance rate of pull requests; (2) 68% of the sampled DL projects are not unit tested at all; (3) the layer and utilities (utils) of DL models have the most unit tests. Based on these findings and previous research outcomes, we built a mapping taxonomy between unit tests and faults in DL projects. We discuss the implications of our findings for developers and researchers and highlight the need for unit testing in open-source DL projects to ensure their reliability and stability. The study contributes to this community by raising awareness of the importance of unit testing in DL projects and encouraging further research in this area.

Age-of-Information (AoI) has been recently reckoned as a suitable parameter to evaluate the freshness of collected information, which is essential for data retrieval in Internet of Things, especially the monitoring tasks, e.g., the operating situation of equipments. To motivate a large number of sensor nodes and solicit more up-to-date information from these nodes, the control center usually allocates rewards to nodes according to their proportional contributions. This induces intense competitions among nodes who try to gain high payoffs by carefully balancing the rewards and the costs. In this article, we propose a novel stochastic game model to formulate the competition among sensor nodes, which considers AoI as a metric used by the control center to quantify the contributions of nodes. We also take into account the uncertainty of channel quality, which affects the transmission success ratio of packets generated by nodes. Finally, we design an ϵ-Nash learning algorithm, which adopts the θ-greedy exploration strategy, to derive the ϵ-approximate Nash equilibrium such that nodes can maximize their long-term payoffs. Our substantive simulation results and analysis verify that the proposed algorithm outperforms baseline algorithms in bringing higher payoffs to nodes and more fresh information to the control center.

Crowdsourcing has become a popular paradigm to leverage the collective intelligence of massive crowd workers to perform certain tasks in a cost-effective way. Task assignment is an essential issue in crowdsourcing platforms owing to heterogeneous tasks and work skills. In this article, we focus on assigning workers with diversified skill levels to crowdsourcing tasks with different quality requirements and budget constraints. Task assignment is fundamentally a many-to-one matching problem, where one task is allocated to multiple users who can meet the minimum quality requirement of the task within the limited budget. While most existing works try to maximize the utility of the crowdsourcing platform, we take into account the individual preferences of crowdsourcers and workers toward each other to ensure the stability of task assignment results. In this article, we propose task assignment mechanisms that can guarantee stable outcomes for the many-to-one matching problem with lower and upper bounds (i.e., quality requirement and budget constraint) in regard to heterogeneous worker skill levels. Extensive simulation results show that the proposed algorithms can greatly improve the success ratio of task accomplishment and worker happiness compared with existing algorithms.

Pavement crack detection is a critical task for insuring road safety. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background, e.g., the low contrast with surrounding pavements and possible shadows with a similar intensity. Inspired by recent advances of deep learning in computer vision, we propose a novel network architecture, named feature pyramid and hierarchical boosting network (FPHBN), for pavement crack detection. The proposed network integrates context information to low-level features for crack detection in a feature pyramid way, and it balances the contributions of both easy and hard samples to loss by nested sample reweighting in a hierarchical way during training. In addition, we propose a novel measurement for crack detection named average intersection over union (AIU). To demonstrate the superiority and generalizability of the proposed method, we evaluate it on five crack datasets and compare it with the state-of-the-art crack detection, edge detection, and semantic segmentation methods. The extensive experiments show that the proposed method outperforms these methods in terms of accuracy and generalizability. Code and data can be found in https://github.com/fyangneil/pavement-crack-detection.

In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking. LaSOT consists of 1,400 sequences with more than 3.5M frames in total. Each frame in these sequences is carefully and manually annotated with a bounding box, making LaSOT the largest, to the best of our knowledge, densely annotated tracking benchmark. The average video length of LaSOT is more than 2,500 frames, and each sequence comprises various challenges deriving from the wild where target objects may disappear and re-appear again in the view. By releasing LaSOT, we expect to provide the community with a large-scale dedicated benchmark with high quality for both the training of deep trackers and the veritable evaluation of tracking algorithms. Moreover, considering the close connections of visual appearance and natural language, we enrich LaSOT by providing additional language specification, aiming at encouraging the exploration of natural linguistic feature for tracking. A thorough experimental evaluation of 35 tracking algorithms on LaSOT is presented with detailed analysis, and the results demonstrate that there is still a big room for improvements.

Two surface-based multi-channel radar systems, operating in the VHF and UHF bands, were designed, developed and deployed to the East Greenland Ice-coring Project (EGRIP) site in Summer 2018 for ice sheet sounding and imaging. Both radar systems, sharing the same digital waveform generator and digitizer, were installed and operated inside a tracked vehicle. The VHF system operates over the frequency range of 170-230 MHz with a peak transmit power of 600 W. The radar is equipped with an 8-m long monopole array. The UHF system operates from 600 to 900 MHz with a peak transmit power of 800 W, and is equipped with a large and lightweight 16 m × 17 m antenna array arranged in a Mill's Cross configuration. In this paper, we will present the design of the two radar systems and the radar data collected from EGRIP.