arXiv subjects

Junjie Guo

Publications and source records attributed to Junjie Guo.

24 records · Page 2Linked to original sources

arXiv2024

Advancing Financial Risk Prediction Through Optimized LSTM Model Performance and Comparative Analysis

This paper focuses on the application and optimization of LSTM model in financial risk prediction. The study starts with an overview of the architecture and algorithm foundation of LSTM, and then details the model training process and hyperparameter tuning strategy, and adjusts network parameters through experiments to improve performance. Comparative experiments show that the optimized LSTM model shows significant advantages in AUC index compared with random forest, BP neural network and XGBoost, which verifies its efficiency and practicability in the field of financial risk prediction, especially its ability to deal with complex time series data, which lays a solid foundation for the application of the model in the actual production environment.

cs.LG↗

arXiv2024

Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation

Emotion Recognition in Conversation (ERC) involves detecting the underlying emotion behind each utterance within a conversation. Effectively generating representations for utterances remains a significant challenge in this task. Recent works propose various models to address this issue, but they still struggle with differentiating similar emotions such as excitement and happiness. To alleviate this problem, We propose an Emotion-Anchored Contrastive Learning (EACL) framework that can generate more distinguishable utterance representations for similar emotions. To achieve this, we utilize label encodings as anchors to guide the learning of utterance representations and design an auxiliary loss to ensure the effective separation of anchors for similar emotions. Moreover, an additional adaptation process is proposed to adapt anchors to serve as effective classifiers to improve classification performance. Across extensive experiments, our proposed EACL achieves state-of-the-art emotion recognition performance and exhibits superior performance on similar emotions. Our code is available at https://github.com/Yu-Fangxu/EACL.

cs.CL↗

arXiv2024

DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion

Infrared-visible object detection aims to achieve robust even full-day object detection by fusing the complementary information of infrared and visible images. However, highly dynamically variable complementary characteristics and commonly existing modality misalignment make the fusion of complementary information difficult. In this paper, we propose a Dynamic Adaptive Multispectral Detection Transformer (DAMSDet) to simultaneously address these two challenges. Specifically, we propose a Modality Competitive Query Selection strategy to provide useful prior information. This strategy can dynamically select basic salient modality feature representation for each object. To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object. In addition, we further adopt the cascade structure of DETR to better mine complementary information. Experiments on four public datasets of different scenes demonstrate significant improvements compared to other state-of-the-art methods. The code will be released at https://github.com/gjj45/DAMSDet.

cs.CV↗

arXiv2023

Coupler RF kick and emittance optimization of the SHINE injector

Coupler RF kick due to the asymmetric structure caused by the coupler, is more likely to lead to emittance growth in the SHINE injector with low beam energy. The calculation of coupler RF kick and resulting emittance dilution has been studied in detail in the literature. In this paper, a novel approach is provided that a lossy material is placed on the surface of the superconducting cavity to approximate the Q0 of the TESLA cavity, and a frequency solver of CST is used to simulate the electromagnetic field distribution, which is used to calculate coupler RF kick, and calibrated against the results of CST Particle Tracking Studio with a good agreement. In order to minimize the emittance growth of SHINE injector, a 1.3 GHz symmetric twin-coupler cavity is adoped in the single-cavity cryomodule, and the rotational angle and permutation of the 8 cavities in the 8-cavities cryomodule is optimized. Ultimately, the optimized emittance is lower than the design parameter.

physics.acc-ph↗

arXiv2017

Gate-controlled reversible rectifying behaviour in tunnel contacted atomically-thin MoS$_{2}$ transistor

Atomically-thin 2D semiconducting materials integrated into van der Waals heterostructures have enabled architectures that hold great promise for next generation nanoelectronics. However, challenges still remain to enable their full acceptance as compliant materials for integration in logic devices. Two key-components to master are the barriers at metal/semiconductor interfaces and the mobility of the semiconducting channel, which endow the building-blocks of ${pn}$ diode and field effect transistor. Here, we have devised a reverted stacking technique to intercalate a wrinkle-free h-BN tunnel layer between MoS$_{2}$ channel and contacting electrodes. Vertical tunnelling of electrons therefore makes it possible to suppress the Schottky barriers and Fermi level pinning, leading to homogeneous gate-control of the channel chemical potential across the bandgap edges. The observed unprecedented features of ambipolar ${pn}$ to ${np}$ diode, which can be reversibly gate tuned, paves the way for future logic applications and high performance switches based on atomically thin semiconducting channel.

physics.app-ph↗

arXiv2015

Gigahertz Dielectric Polarization of Single-atom Niobium Substituted in Graphitic layers

We have synthesized two Nb@C composites with an order of magnitude difference in the density of single-atom niobium substituted into graphitic layers. The concentration and sites of single-atom Nb are identified using aberration-corrected scanning transmission electron microscopy and density functional theory. Comparing the complex permittivity spectra show that the representative dielectric resonance at ~16 GHz originates from the intrinsic polarization of single-atom Nb sites, confirmed by theoretical simulations. The single-atom dielectric resonance represents the physical limit of the electromagnetic response of condensed matter, and thus might open up a new avenue for designing electromagnetic wave absorption materials. Single-atom resonance also has important implications in understanding the correlation between the macroscopic dielectric behaviors and the atomic-scale structural origin.

cond-mat.mtrl-sci↗