Introduction: Real-time evaluations of the severity of depressive symptoms are of great significance for the diagnosis and treatment of patients with major depressive disorder (MDD). In clinical practice, the evaluation approaches are mainly based on psychological scales and doctor-patient interviews, which are time-consuming and labor-intensive. Also, the accuracy of results mainly depends on the subjective judgment of the clinician. With the development of artificial intelligence (AI) technology, more and more machine learning methods are used to diagnose depression by appearance characteristics. Most of the previous research focused on the study of single-modal data; however, in recent years, many studies have shown that multi-modal data has better prediction performance than single-modal data. This study aimed to develop a measurement of depression severity from expression and action features and to assess its validity among the patients with MDD.Methods: We proposed a multi-modal deep convolutional neural network (CNN) to evaluate the severity of depressive symptoms in real-time, which was based on the detection of patients’ facial expression and body movement from videos captured by ordinary cameras. We established behavioral depression degree (BDD) metrics, which combines expression entropy and action entropy to measure the depression severity of MDD patients.Results: We found that the information extracted from different modes, when integrated in appropriate proportions, can significantly improve the accuracy of the evaluation, which has not been reported in previous studies. This method presented an over 74% Pearson similarity between BDD and self-rating depression scale (SDS), self-rating anxiety scale (SAS), and Hamilton depression scale (HAMD). In addition, we tracked and evaluated the changes of BDD in patients at different stages of a course of treatment and the results obtained were in agreement with the evaluation from the scales.Discussion: The BDD can effectively measure the current state of patients’ depression and its changing trend according to the patient’s expression and action features. Our model may provide an automatic auxiliary tool for the diagnosis and treatment of MDD.

Soil-bentonite vertical cut-off wall is an emergency technique used for contaminant control in geo-environmental engineering, high-density polyethylene (HDPE) geomembrane (GM) with an extremely low-permeability coefficient is expected to enhance the contaminant barrier effect of the vertical cut-off wall. To evaluate the barrier performance of the composite barrier composed of GM and soil-bentonite mixture towards organic contaminant, while also quantitively revealing the impact of GM defects and placement, a one-dimensional transport model for organic contaminants in composite barrier is solved under semi-infinite boundary conditions. The proposed transport model is validated by numerical simulations using COMSOL Multiphysics 5.4, and the effects of GM defect rate, placement within the composite isolation wall, and contact level with soil-bentonite on contaminant transport behavior are further studied. The results show that as the average frequency of GM defects increases from 2.5 to 50 holes per hectare, the breakthrough time of organic contaminants through composite barrier decreases by almost 70%. Poor contact level between GM and soil-bentonite mixture may reduce the breakthrough time of the composite cut-off wall by 65%. Although the selection of GM placement has limited impact on the transient flux of contaminants, it does affect the total flux of contaminants over a certain period of time. The effects of permeability coefficient, effective diffusion coefficient, distribution coefficient, and hydraulic head of the composite cut-off wall can be considered by the proposed analytical solution, which would provide guidance and reference for the design and service performance evaluation of the composite cut-off wall.

This paper aims to investigate the interfacial strength characteristics, particularly the residual strength, of a high-density polyethylene smooth geomembrane (GMB-S)/nonwoven geotextile (NW GTX) interface using a novel ring shear apparatus under high normal stresses and two specimen conditions. A total of eight normal stresses (from 50 kPa to 2308 kPa) and two specimen conditions (dry and submerged at ambient temperature) are considered in this study. The reliability of using the novel ring shear apparatus to study the strength characteristics of the GMB-S/NW GTX interface was demonstrated by conducting a series of direct shear experiments with a maximum shear displacement of 40 mm and ring shear experiments with a shear displacement of 10 m. The peak strength, post-peak strength development, and residual strength determination method of the GMB-S/NW GTX interface are explained. Three exponential equations suitable for characterizing the relationship between the post-peak friction angle and the residual friction angle of the GMB-S/NW GTX interface are established. This relationship can be used with the relevant apparatus (i.e., an apparatus with deficiencies in executing large shear displacement) in determining the residual friction angle of the high-density polyethylene smooth geomembrane/nonwoven geotextile interface.

The utilization of geomembrane reinforcement technology is pervasive in marine sand foundation reinforcement projects. However, the elevated temperatures and intricate stress conditions prevalent in marine environments exert a notable influence on the mechanical characteristics of geomembrane interfaces comprising marine sand, which impedes the efficacy of geomembrane reinforcement in marine sand foundations. Nevertheless, there is a lack of research investigating the temperature-dependent interfacial mechanical performance of geomembranes and marine sand under diverse stress states. In this study, a series of monotonic shear tests were carried out on the interface between geomembranes and marine sand within a temperature range of 5 °C to 80 °C. These experiments were carried out using a self-developed large-scale temperature-controlled interfacial dynamic and static shear device. The experimental results demonstrate that temperature has a pronounced effect on the monotonic mechanical characteristics of the geomembrane–marine sand interface, which displays clear temperature dependence. The findings of this study may help in the design and optimization of offshore projects where a marine sand–polymer layer interface exists.