Daimin Shi’s research while affiliated with Northwest Normal University and other places

... Bailey [13] found that the gender bias in DAIC-WOZ may affect classification performance. Liu [14] used gender recognition as an auxiliary task for depression recognition, and the average accuracy was improved by 6.1% compared with the nonauxiliary task. Verma [15] divided the features into four categories according to gender and emotion and tested the influence of gender and emotion on depression recognition, and used 1D-Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for depression recognition. ...

Reference:

Hierarchical Multi-Task Learning Based on Interactive Multi-Head Attention Feature Fusion for Speech Depression Recognition

... Consider the values n_estimators= [5,10,15,20], learning rate=[0.01, 0.1], and max depth= [5,15,2]. ...

Reference:

DepXGBoot: Depression detection using a robust tuned extreme gradient boosting model generator

... The metal samples produced by 4D printing exhibit greater mechanical qualities when compared with the majority of 4D printing materials, like hydrogels and polymers, demonstrating that this approach offers a wide variety of technical applications. In addition, laser stimulation's metallic 4D printing technology enables very flexible deformations of Carbon-based materials, such as carbon nanotubes (CNTs) or graphene 10 2 to 10 5 S/m Non-conductive polymers and composites 10 -12 to 10 2 S/m metallic 3D components [74,75]. As demonstrated in Fig. 9, the shape-morphing theory involves using a laser to serve as a stimulating source of heat to deliberately generate internal thermal stress in the specimen in order in order to accomplish 2D-to-3D structural transformation. ...

Reference:

A critical review on 4D printing and their processing parameters

... Similarly, [24] and [111] introduced models emphasizing comprehensive representation and non-content speech parameters, both showing promise in the accurate detection of depressive states. Adding to this, [71] introduced an attention-based residual network that outperforms traditional methods by using speech features related to negative questions under negative emotions, showing high accuracy for both male and female subjects. [80] and [130] used audiovisual and multimodal data, respectively, to predict depression and its relapse with promising results. ...

Reference:

The order in speech disorder: a scoping review of state of the art machine learning methods for clinical speech classification

... Arroz et al. [35] compared algorithms for unimodal, automatic, and multimodal classification conversations, with LSTM and gated recurrent units (GRU). Alternative approaches to multimodal depression detection encompass the examination of various indicators such as the dynamics of acoustic, facial, head movement [27], [39], behavioural and physiological signals [40], brain functional abnormalities, heart rate variability, hemodynamic parameters [41], and partially convergent structural features [23]. ...

Reference:

Taking All the Factors We Need: A Multimodal Depression Classification With Uncertainty Approximation

... However, this research stream has primarily focused on specific aspects of emotions, such as identifying depression (Rejaibi et al. 2022;Lin et al. 2020;An et al. 2019), early signs of diseases from patients' speech patterns (DeSouza et al. 2021;Khanbhai et al. 2021;Beltrami et al. 2018;Perez et al. 2018), or challenges in emotion recognition among older adults (Schuller et al. 2020), without fully harnessing the potential of those technologies for the automated assessment and monitoring of subjective wellbeing. By utilizing research on NLP analytic capabilities, we aim to address the global challenge of healthy aging by assessing subjective well-being through speech analysis. ...

Reference:

How are We Doing Today? Using Natural Speech Analysis to Assess Older Adults’ Subjective Well-Being