arXiv subjects

Yuliang Zhao

Publications and source records attributed to Yuliang Zhao.

8 recordsLinked to original sources

arXiv2025

The First MPDD Challenge: Multimodal Personality-aware Depression Detection

Depression is a widespread mental health issue affecting diverse age groups, with notable prevalence among college students and the elderly. However, existing datasets and detection methods primarily focus on young adults, neglecting the broader age spectrum and individual differences that influence depression manifestation. Current approaches often establish a direct mapping between multimodal data and depression indicators, failing to capture the complexity and diversity of depression across individuals. This challenge includes two tracks based on age-specific subsets: Track 1 uses the MPDD-Elderly dataset for detecting depression in older adults, and Track 2 uses the MPDD-Young dataset for detecting depression in younger participants. The Multimodal Personality-aware Depression Detection (MPDD) Challenge aims to address this gap by incorporating multimodal data alongside individual difference factors. We provide a baseline model that fuses audio and video modalities with individual difference information to detect depression manifestations in diverse populations. This challenge aims to promote the development of more personalized and accurate de pression detection methods, advancing mental health research and fostering inclusive detection systems. More details are available on the official challenge website: https://hacilab.github.io/MPDDChallenge.github.io.

cs.AI↗

arXiv2022

Data-Folding and Hyperspace Coding for Multi-Dimensonal Time-Series Data Imaging

Multi-Dimensional time series classification and prediction has been widely used in many fields, such as disease prevention, fault diagnosis and action recognition. However, the traditional method needs manual intervention and inference, and cannot realize the figurative expression of multi-Dimensional data, which lead to inadequate information mining. Inspired by the strong power of deep learning technology in image processing, we propose a unified time-series image fusion framework to transform multi-modal data into 2D-image, and then realize automatic feature extraction and classification based on a lightweight convolutional neural network. We present two basic image coding methods, Gray image coding, RGB image coding, and their step coding methods. Considering the universality of different application fields, we extended the coding method and propose two types transform coding, Transform-RGB coding and RGB-Transform coding, to improve the multi-domain representation ability. By applying to three typical scenes of Parkinson's disease diagnosis, bearing fault detection and gymnastics action recognition, we obtained the highest classification accuracy of 100%, 92.86% and 99.70% respectively, which were all higher than the classical processing methods. It proves the strong classification ability and universality of our coding framework to different multi-dimensional scenes. We expect that this method can be used and perform well in other scenarios, and be potential to facilitate the progress of related technology.

eess.SP↗

arXiv2019

3D characterization of the primary Al3Sc phases in an Al-Sc alloy using Synchrotron X-ray tomography and electron microscopy

The three-dimensional structures of the primary Al3Sc particles in an Al-2Sc master alloy were studied by synchrotron X-ray microtomography, scanning and transmission electron microscopy. The Al3Sc phases were found to be a single cube and a cluster of cubes. The surface area, equivalent diameter of the Al3Sc cubes increased with the increasing of cube volume, but the specific surface area decreases. The primary Al3Sc cubes and Al-matrix have the same crystal orientation, indicating that the Al3Sc phases are the heterogeneous nucleation sites for Al. The experimental results show that α-Al2O3 are the possible nucleation sites for the Al3Sc cubes.

cond-mat.mtrl-sci↗

arXiv2018

3D characterization of ultrasonic melt processing on the microstructural refinement of Al-Cu alloys by synchrotron X-ray tomography

The effect of ultrasonic melting processing on three-dimensional architecture of intermetallic phases and pores in two multicomponent cast Al-5.0Cu-0.6Mn-0.5 Fe alloys is characterized using conventional microscopy and synchrotron X-ray microtomography. The two alloys are found to contain intermetallic phases such as Al15(FeMn)3Cu2, Al7Cu2Fe, Al3(FeMn), Al6(FeMn), and Al2Cu that have complex networked morphology in 3D. The application of USP in alloys can obtained refined and equiaxed microstructures. The grain size of 0.5Fe and 1.0 Fe alloys is greatly decreased from 16.9 m, 15.8 m without USP to 13.3 m, 12.2 m with USP, respectively. The results show that USP significantly reduce the volume fraction, grain size, interconnectivity, and equivalent diameter of the intermetallic phases in both alloys. The volume fraction of pores in both alloys is reduced due to the USP degassing effect. The refinement mechanism of USP induced fragmentation of primary and secondary dendrites via acoustic bubbles and acoustic streaming flow were discussed.

cond-mat.mtrl-sci↗

arXiv2018

Synchrotron X-ray tomography investigation of 3D morphology of intermetallic phases and pores and their effect on the mechanical properties of cast Al-Cu alloys

The influence of Fe content on the three-dimensional (3D) morphology of Fe-rich intermetallic phases (Fe phases), Al2Cu, and pores and mechanical properties of cast Al-5.0Cu-0.6Mn alloys with 0.5 and 1.0 wt. % Fe are characterized using synchrotron X-ray tomography and a tensile test. The results show that both Fe phases and Al2Cu exhibit a complex 3D network structure, and the pores are irregular with complex interconnected and near-globular shape. As the Fe content increases from 0.5 % to 1.0 %, the volume fraction and equivalent diameter of Fe phases decrease, whereas both their interconnectivities decrease. Skeletonization analysis shows that the Chinese-script-shaped Fe phase is compacted than the plate-like Fe phases. The equivalent diameter and sphericity of pores vary with Fe content, and their relationships follow exponential functions, Y = 7.14*X-1.29 and Y = 7.06*X-1.20, respectively. The addition of Fe results in a decrease in the ultimate tensile strength and elongation from 223.7 MPa to 199.8 MPa and from 5.51 % to 3.64 %, respectively, owing to increasing volume fraction of sharp-edged Fe phases and pores, resulting in stress concentration during tensile test.

cond-mat.mtrl-sci↗

arXiv2018

The effect of Si addition on the microstructure and tensile properties of casting Al-5.0Cu-0.6Mn-1.2Fe alloys

In this work, we studied the effect of Si on the microstructure and tensile properties of the as-cast Al-5.0Cu-0.6Mn-1.2Fe alloys which were produced by casting with or without applied pressure. The results show that the addition of Si can significantly influence the microstructure and tensile properties of the alloys. For the alloys produced without pressure, the addition of Si can promote the formation of Chinese script α-Fe, suppress the precipitation of plate-like Al3(FeMn) and Chinese script Al6(FeMn) and increase the volume percent of porosity, resulting in a remarkable decrease in the ultimate tensile strength (UTS) and yield strength (YS). For the alloys produced with a pressure of 75 MPa, the addition of Si can also promote the formation of fine Chinese script α-Fe and high number density Al2Cu (θ) phases, resulting in a slight increase in UTS and YS. The strength and elongation of the alloys increases with increasing applied pressure at the same Si level, which are attributed to the elimination of porosity, grain refinement strengthening and solid-solution strengthening. The alloy with addition of 1.1 % Si produced under the applied pressure of 75 MPa shows the best tensile properties, where the UTS, YS and elongation is 237 MPa, 140 MPa and 9.8%, respectively.

cond-mat.mtrl-sci↗

arXiv2018

Microstructure and mechanical properties of Al-Cu alloy with 0.6%Fe produced with ultrasonic vibration and applied pressure

The combined effect of ultrasonic vibration (UT) and applied pressure (P) on microstructure and mechanical properties of Al-5.0Cu-0.6Mn-0.6Fe alloy were investigated. The best tensile properties produced by P+UT processing are UTS: 268MPa, YS: 192MPa, E.L.: 17.1%, respectively, which increasing by 64%, 59% and 307%, respectively, compare to the Non-treated alloy.

cond-mat.mtrl-sci↗

arXiv2017

Effect of Si on Fe-rich intermetallic formation and mechanical properties of heattreated Al-Cu-Mn-Fe alloys

The effect of Si on Fe-rich intermetallics formation and mechanical properties of heat-treated squeeze cast Al-5.0Cu-0.6Mn-0.7Fe alloy was investigated. Our results show that increasing Si content promotes the formation of Al15(FeMn)3(SiCu)2 ($α$-Fe), and varying the morphology of T (Al20Cu3Mn2) where the size decreases and the amount increases. The major reason is that Si promotes heterogeneous nucleation of the intermetallics leading to finer precipitates. Si addition significantly enhances ultimate tensile strength and yield strength of the alloys. The strengthening effect is mainly owing to the dispersoid strengthening by increasing volume fraction of T phase and less harmful $α$-Fe with a compact structure, which make the cracks more difficult to initiate and propagation during tensile test. The squeeze cast Al-5.0Cu-0.6Mn-0.7Fe alloy with 1.1% Si shows significantly improved mechanical properties than the alloy without Si addition, which has tensile strength of 386 MPa, yield strength of 280 MPa and elongation of 8.6%.

cond-mat.mtrl-sci↗