Search

With the development of technology, the chemical production process is becoming increasingly complex and large-scale, making fault diagnosis particularly important. However, current diagnostic methods struggle to address the complexities of large-scale production processes. In this paper, we integrate the strengths of deep learning and machine learning technologies, combining the advantages of bidirectional long and short-term memory neural networks, fully connected neural networks, and the extra trees algorithm to propose a novel fault diagnostic model named three-layer deep learning network random trees (TDLN-trees). First, the deep learning component extracts temporal features from industrial data, combining and transforming them into a higher-level data representation. Second, the machine learning component processes and classifies the features extracted in the first step. An experimental analysis based on the Tennessee Eastman process verifies the superiority of the proposed method.

With the advent of universal function approximators in the domain of reinforcement learning, the number of practical applications leveraging deep reinforcement learning (DRL) has exploded. Decision-making in automated driving tasks has emerged as a chief application among them, taking the sensor data or the higher-order kinematic variables as the input and providing a discrete choice or continuous control output. However, the black-box nature of the models presents an overwhelming limitation that restricts the real-world deployment of DRL in autonomous vehicles (AVs). Therefore, in this research work, we focus on the interpretability of an attention-based DRL framework. We use a continuous proximal policy optimization-based DRL algorithm as the baseline model and add a multi-head attention framework in an open-source AV simulation environment. We provide some analytical techniques for discussing the interpretability of the trained models in terms of explainability and causality for spatial and temporal correlations. We show that the weights in the first head encode the positions of the neighboring vehicles while the second head focuses on the leader vehicle exclusively. Also, the ego vehicle's action is causally dependent on the vehicles in the target lane spatially and temporally. Through these findings, we reliably show that these techniques can help practitioners decipher the results of the DRL algorithms., Comment: Submitted for peer-review

To address the challenges of low detection accuracy and high false positive rates of transmission lines in UAV (Unmanned Aerial Vehicle) images, we explore the linear features and spatial distribution. We introduce an enhanced stochastic Hough transform technique tailored for detecting transmission lines in complex backgrounds. By employing the Hessian matrix for initial preprocessing of transmission lines, and utilizing boundary search and pixel row segmentation, our approach distinguishes transmission line areas from the background. We significantly reduce both false positives and missed detections, thereby improving the accuracy of transmission line identification. Experiments demonstrate that our method not only processes images more rapidly, but also yields superior detection results compared to conventional and random Hough transform methods.

Stylized text-to-image generation focuses on creating images from textual descriptions while adhering to a style specified by a few reference images. However, subtle style variations within different reference images can hinder the model from accurately learning the target style. In this paper, we propose InstaStyle, a novel approach that excels in generating high-fidelity stylized images with only a single reference image. Our approach is based on the finding that the inversion noise from a stylized reference image inherently carries the style signal, as evidenced by their non-zero signal-to-noise ratio. We employ DDIM inversion to extract this noise from the reference image and leverage a diffusion model to generate new stylized images from the "style" noise. Additionally, the inherent ambiguity and bias of textual prompts impede the precise conveying of style. To address this, we introduce a learnable style token via prompt refinement, which enhances the accuracy of the style description for the reference image. Qualitative and quantitative experimental results demonstrate that InstaStyle achieves superior performance compared to current benchmarks. Furthermore, our approach also showcases its capability in the creative task of style combination with mixed inversion noise., Comment: 21 pages,20 figures

Point defects may introduce defect levels into the fundamental band gap of the host semiconductors that alter the electrical properties of the material. As a consequence, the in-gap defect levels and states automatically lower the threshold energy of optical excitation associated with the optical gap of the host semiconductor. It is, therefore, a common assumption that solid state defect emitters in semiconductors ultimately alter the conductivity of the host. Here we demonstrate on a particular defect in 4H silicon carbide that a yet unrecognized class of point defects exists which are optically active but electrically inactive in the ground state., Comment: 7 pages, 4 figures

Intelligent vehicle anticipation of the movement intentions of other drivers can reduce collisions. Typically, when a human driver of another vehicle (referred to as the target vehicle) engages in specific behaviors such as checking the rearview mirror prior to lane change, a valuable clue is therein provided on the intentions of the target vehicle's driver. Furthermore, the target driver's intentions can be influenced and shaped by their driving environment. For example, if the target vehicle is too close to a leading vehicle, it may renege the lane change decision. On the other hand, a following vehicle in the target lane is too close to the target vehicle could lead to its reversal of the decision to change lanes. Knowledge of such intentions of all vehicles in a traffic stream can help enhance traffic safety. Unfortunately, such information is often captured in the form of images/videos. Utilization of personally identifiable data to train a general model could violate user privacy. Federated Learning (FL) is a promising tool to resolve this conundrum. FL efficiently trains models without exposing the underlying data. This paper introduces a Personalized Federated Learning (PFL) model embedded a long short-term transformer (LSTR) framework. The framework predicts drivers' intentions by leveraging in-vehicle videos (of driver movement, gestures, and expressions) and out-of-vehicle videos (of the vehicle's surroundings - frontal/rear areas). The proposed PFL-LSTR framework is trained and tested through real-world driving data collected from human drivers at Interstate 65 in Indiana. The results suggest that the PFL-LSTR exhibits high adaptability and high precision, and that out-of-vehicle information (particularly, the driver's rear-mirror viewing actions) is important because it helps reduce false positives and thereby enhances the precision of driver intention inference., Comment: Submitted for presentation only at the 2024 Annual Meeting of the Transportation Research Board

Quantum error correction codes based on continuous variables play an important role for the implementation of quantum communication systems. A natural application of such codes occurs within quantum repeater systems which are used to combat severe channel losses and local gate errors. In particular, channel loss drastically reduces the distance of communication between remote users. Here we consider a cavity-QED based repeater scheme to address the losses in the quantum channel. This repeater scheme relies on the transmission of a specific class of rotationally invariant error-correcting codes. We compare several rotation-symmetric bosonic codes (RSBCs) being used to encode the initial states of two remote users connected by a quantum repeater network against the convention of the cat codes and we quantify the performance of the system using the secret key rate. In particular, we determine the number of stations required to exchange a secret key over a fixed distance and establish the resource overhead., Comment: 10 pages, 7 figures

We study quasi-stationary distribution of the continuous-state branching process with competition introduced in Berestycki, Fittipaldi and Fontbona\ (Probab. Theory Relat. Fields, 2018). This process is constructed as the unique strong solution to a stochastic integral equation with jumps. An important example is the logistic branching process constructed in Lambert (Ann. Appl. Probab., 2005). We establish the strong Feller property,trajectory Feller property, Lyapunov condition, weak Feller property and irreducibility, respectively. These properties together allow us to prove that when the competition term is strong enough near $+\infty$, then there is a unique quasi-stationary distribution, which attracts all initial distributions with exponential rates.

Van der Waals structures present a unique opportunity for tailoring material interfaces and integrating photonic functionalities. By precisely manipulating the twist angle and stacking sequences, it is possible to elegantly tune and functionalize the electronic and optical properties of layered van der Waals structures. Among these materials, two-dimensional hexagonal boron nitride (hBN) stands out for its remarkable optical properties and wide band gap, making it a promising host for solid state single photon emitters at room temperature. Previous investigations have demonstrated the observation of bright single photon emission in hBN across a wide range of wavelengths. In this study, we unveil an application of van der Waals technology in modulating their spectral shapes and brightness by carefully controlling the stacking sequences and polytypes. Our theoretical analysis reveals remarkably large variations in the Huang-Rhys factors-an indicator of the interaction between a defect and its surrounding lattice-reaching up to a factor of 3.3 for the same defect in different stackings. We provide insights into the underlying mechanism behind these variations, shedding light on the design principles necessary to achieve rational and precise control of defect emission. This work paves the way for enhancing defect identification and facilitating the engineering of highly efficient single photon sources and qubits using van der Waals materials., Comment: 8 pages, 5 figures