From Generalized Gauss Bounds to Distributionally Robust Fault Detection with Unimodality Information

Probabilistic methods have attracted much interest in fault detection design, but its need for complete distributional knowledge is seldomly fulfilled. This has spurred endeavors in distributionally robust fault detection (DRFD) design, which secures robustness against inexact distributions by using moment-based ambiguity sets as a prime modelling tool. However, with the worst-case distribution being implausibly discrete, the resulting design suffers from over-pessimisim and can mask the true fault. This paper aims at developing a new DRFD design scheme with reduced conservatism, by assuming unimodality of the true distribution, a property commonly encountered in real-life practice. To tackle the chance constraint on false alarms, we first attain a new generalized Gauss bound on the probability outside an ellipsoid, which is less conservative than known Chebyshev bounds. As a result, analytical solutions to DRFD design problems are obtained, which are less conservative than known ones disregarding unimodality. We further encode bounded support information into ambiguity sets, derive a tightened multivariate Gauss bound, and develop approximate reformulations of design problems as convex programs. Moreover, the derived generalized Gauss bounds are broadly applicable to versatile change detection tasks for setting alarm thresholds. Results on a laborotary system shown that, the incorporation of unimodality information helps reducing conservatism of distributionally robust design and leads to a better tradeoff between robustness and sensitivity.

Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation

Medical report generation is one of the most challenging tasks in medical image analysis. Although existing approaches have achieved promising results, they either require a predefined template database in order to retrieve sentences or ignore the hierarchical nature of medical report generation. To address these issues, we propose MedWriter that incorporates a novel hierarchical retrieval mechanism to automatically extract both report and sentence-level templates for clinically accurate report generation. MedWriter first employs the Visual-Language Retrieval~(VLR) module to retrieve the most relevant reports for the given images. To guarantee the logical coherence between sentences, the Language-Language Retrieval~(LLR) module is introduced to retrieve relevant sentences based on the previous generated description. At last, a language decoder fuses image features and features from retrieved reports and sentences to generate meaningful medical reports. We verified the effectiveness of our model by automatic evaluation and human evaluation on two datasets, i.e., Open-I and MIMIC-CXR.

Explainable AI For COVID-19 CT Classifiers: An Initial Comparison Study

Artificial Intelligence (AI) has made leapfrogs in development across all the industrial sectors especially when deep learning has been introduced. Deep learning helps to learn the behaviour of an entity through methods of recognising and interpreting patterns. Despite its limitless potential, the mystery is how deep learning algorithms make a decision in the first place. Explainable AI (XAI) is the key to unlocking AI and the black-box for deep learning. XAI is an AI model that is programmed to explain its goals, logic, and decision making so that the end users can understand. The end users can be domain experts, regulatory agencies, managers and executive board members, data scientists, users that use AI, with or without awareness, or someone who is affected by the decisions of an AI model. Chest CT has emerged as a valuable tool for the clinical diagnostic and treatment management of the lung diseases associated with COVID-19. AI can support rapid evaluation of CT scans to differentiate COVID-19 findings from other lung diseases. However, how these AI tools or deep learning algorithms reach such a decision and which are the most influential features derived from these neural networks with typically deep layers are not clear. The aim of this study is to propose and develop XAI strategies for COVID-19 classification models with an investigation of comparison. The results demonstrate promising quantification and qualitative visualisations that can further enhance the clinicians understanding and decision making with more granular information from the results given by the learned XAI models.

Scalable universal tunable virtual-wavevector spatial frequency shift (TVSFS) super-resolution imaging

Developing a chip-based super-resolution imaging technique with large field-of-view (FOV), deep subwavelength resolution, and compatibility for both fluorescent and non-fluorescent samples is desired for material science, biomedicine, and life researches, etc. Previous on-chip super-resolution methods focus on either fluorescent or non-fluorescent imaging, putting an urgent requirement on the general imaging technique compatible with both of them. Here, we introduce a universal super-resolution imaging method based on tunable virtual-wavevector spatial frequency shift (TVSFS), realizing both labeled and label-free super-resolution imaging on a single delicately fabricated scalable photonic chip. Theoretically, with TVSFS, the diffraction limit of a linear optical system can be overcome, and the resolution can be improved more than three times, which is the limitation for most super-resolution imaging based on spatial frequency engineering. Diffractive units were fabricated on the chips surface to provide a wavevector-variable evanescent wave illumination and induce tunable deep SFS in the samples Fourier space. A resolution of {lambda}/4.7 for the label-free sample and {lambda}/7.1 for the labeled sample with a large FOV could be achieved with a CMOS-compatible process on a GaP chip. The large FOV, high-compatibility, and high-integration TVSFS chip may advance the fields like cell engineering, precision inspection in the industry, chemical research, etc.

Synchronized resistance to inhomogeneous magnetic field-induced dephasing of an image stored in a cold atomic ensemble

Long-lived storage of arbitrary transverse multimodes is important for establishing a high-channel-capacity quantum network. Most of the pioneering works focused on atomic diffusion as the dominant impact on the retrieved pattern in an atom-based memory. In this work, we demonstrate that the unsynchronized Larmor precession of atoms in the inhomogeneous magnetic field dominates the distortion of the pattern stored in a cold-atom-based memory. We find that this distortion effect can be eliminated by applying a strong uniform polarization magnetic field. By preparing atoms in magnetically insensitive states, the destructive interference between different spin-wave components is diminished, and the stored localized patterns are synchronized further in a single spin-wave component; then, an obvious enhancement in preserving patterns for a long time is obtained. The reported results are very promising for studying transverse multimode decoherence in storage and high-dimensional quantum networks in the future.

Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at unboxing how AI systems black-box choices are made. This research field inspects the measures and models involved in decision-making and seeks solutions to explain them explicitly. Many of the machine learning algorithms can not manifest how and why a decision has been cast. This is particularly true of the most popular deep neural network approaches currently in use. Consequently, our confidence in AI systems can be hindered by the lack of explainability in these black-box models. The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend in performance. The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are uncommon. In this study, we first surveyed the current progress of XAI and in particular its advances in healthcare applications. We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios. Comprehensive quantitative and qualitative analyses can prove the efficacy of our proposed XAI solutions, from which we can envisage successful applications in a broader range of clinical questions.

Excitation Energies from Thermally-Assisted-Occupation Density Functional Theory: Theory and Computational Implementation

The time-dependent density functional theory (TDDFT) has been broadly used to investigate the excited-state properties of various molecular systems. However, the current TDDFT heavily relies on outcomes from the corresponding ground-state density functional theory (DFT) calculations which may be prone to errors due to the lack of proper treatment in the non-dynamical correlation effects. Recently, thermally-assisted-occupation density functional theory (TAO-DFT) [J.-D. Chai, textit{J. Chem. Phys.} textbf{136}, 154104 (2012)], a DFT with fractional orbital occupations, was proposed, explicitly incorporating the non-dynamical correlation effects in the ground-state calculations with low computational complexity. In this work, we develop time-dependent (TD) TAO-DFT, which is a time-dependent, linear-response theory for excited states within the framework of TAO-DFT. With tests on the excited states of H$_{2}$, the first triplet excited state ($1^3Sigma_u^+$) was described well, with non-imaginary excitation energies. TDTAO-DFT also yields zero singlet-triplet gap in the dissociation limit, for the ground singlet ($1^1Sigma_g^+$) and the first triplet state ($1^3Sigma_u^+$). In addition, as compared to traditional TDDFT, the overall excited-state potential energy surfaces obtained from TDTAO-DFT are generally improved and better agree with results from the equation-of-motion coupled-cluster singles and doubles (EOM-CCSD).

Accelerating CFD simulation with high order finite difference method on curvilinear coordinates for modern GPU clusters

A high fidelity flow simulation for complex geometries for high Reynolds number ($Re$) flow is still very challenging, which requires more powerful computational capability of HPC system. However, the development of HPC with traditional CPU architecture suffers bottlenecks due to its high power consumption and technical difficulties. Heterogeneous architecture computation is raised to be a promising solution of difficulties of HPC development. GPU accelerating technology has been utilized in low order scheme CFD solvers on structured grid and high order scheme solvers on unstructured meshes. The high order finite difference methods on structured grid possess many advantages, e.g. high efficiency, robustness and low storage, however, the strong dependence among points for a high order finite difference scheme still limits its application on GPU platform. In present work, we propose a set of hardware-aware technology to optimize the efficiency of data transfer between CPU and GPU, and efficiency of communication between GPUs. An in-house multi-block structured CFD solver with high order finite difference methods on curvilinear coordinates is ported onto GPU platform, and obtain satisfying performance with speedup maximum around 2000x over a single CPU core. This work provides efficient solution to apply GPU computing in CFD simulation with certain high order finite difference methods on current GPU heterogeneous computers. The test shows that significant accelerating effects can been achieved for different GPUs.

CFR-RL: Traffic Engineering with Reinforcement Learning in SDN

Traditional Traffic Engineering (TE) solutions can achieve the optimal or near-optimal performance by rerouting as many flows as possible. However, they do not usually consider the negative impact, such as packet out of order, when frequently rerouting flows in the network. To mitigate the impact of network disturbance, one promising TE solution is forwarding the majority of traffic flows using Equal-Cost Multi-Path (ECMP) and selectively rerouting a few critical flows using Software-Defined Networking (SDN) to balance link utilization of the network. However, critical flow rerouting is not trivial because the solution space for critical flow selection is enormous. Moreover, it is impossible to design a heuristic algorithm for this problem based on fixed and simple rules, since rule-based heuristics are unable to adapt to the changes of the traffic matrix and network dynamics. In this paper, we propose CFR-RL (Critical Flow Rerouting-Reinforcement Learning), a Reinforcement Learning-based scheme that learns a policy to select critical flows for each given traffic matrix automatically. CFR-RL then reroutes these selected critical flows to balance link utilization of the network by formulating and solving a simple Linear Programming (LP) problem. Extensive evaluations show that CFR-RL achieves near-optimal performance by rerouting only 10%-21.3% of total traffic.

Model Quality Aware RANSAC: A Robust Camera Motion Estimator

Robust estimation of camera motion under the presence of outlier noise is a fundamental problem in robotics and computer vision. Despite existing efforts that focus on detecting motion and scene degeneracies, the best existing approach that builds on Random Consensus Sampling (RANSAC) still has non-negligible failure rate. Since a single failure can lead to the failure of the entire visual simultaneous localization and mapping, it is important to further improve robust estimation algorithm. We propose a new robust camera motion estimator (RCME) by incorporating two main changes: model-sample consistence test at model instantiation step and inlier set quality test that verifies model-inlier consistence using differential entropy. We have implemented our RCME algorithm and tested it under many public datasets. The results have shown consistent reduction in failure rate when comparing to RANSAC-based Gold Standard approach. More specifically, the overall failure rate for indoor environments has reduced from 1.41% to 0.02%.