A Deep Learning Driven Simulation Analysis of the Emotional Profiles of Depression Based on Facial Expression Dynamics.

Objective: : Diagnosis and assessment of depression rely on scoring systems based on questionnaires, either self-reported by patients or administered by clinicians, and observation of patient facial expressions during the interviews plays a crucial role in making impressions in clinical settings. Deep learning driven approaches can assist clinicians in the course of diagnosis of depression by recognizing subtle facial expressions and emotions in depression patients. Methods: : Seventeen simulated patients who acted as depressed patients participated in this study. A trained psychiatrist structurally interviewed each participant with moderate depression in accordance with a prepared scenario and without depressive features. Interviews were video-recorded, and a facial emotion recognition algorithm was used to classify emotions of each frame. Results: : Among seven emotions (anger, disgust, fear, happiness, neutral, sadness, and surprise), sadness was expressed in a higher proportion on average in the depression-simulated group compared to the normal group. Neutral and fear were expressed in higher proportions on average in the normal group compared to the normal group. The overall distribution of emotions between the two groups was significantly different (p ＜ 0.001). Variance in emotion was significantly less in the depression-simulated group (p ＜ 0.05). Conclusion: : This study suggests a novel and practical approach to understand the emotional expression of depression patients based on deep learning techniques. Further research would allow us to obtain more perspectives on the emotional profiles of clinical patients, potentially providing helpful insights in making diagnosis of depression patients.

Development of Maximum Residual Stress Prediction Technique for Shot-Peened Specimen Using Rayleigh Wave Dispersion Data Based on Convolutional Neural Network.

Shot peening is a surface treatment process that improves the fatigue life of a material and suppresses cracks by generating residual stress on the surface. The injected small shots create a compressive residual stress layer on the material's surface. Maximum compressive residual stress occurs at a certain depth, and tensile residual stress gradually occurs as the depth increases. This process is primarily used for nickel-based superalloy steel materials in certain environments, such as the aerospace industry and nuclear power fields. To prevent such a severe accident due to the high-temperature and high-pressure environment, evaluating the residual stress of shot-peened materials is essential in evaluating the soundness of the material. Representative methods for evaluating residual stress include perforation strain gauge analysis, X-ray diffraction (XRD), and ultrasonic testing. Among them, ultrasonic testing is a representative, non-destructive evaluation method, and residual stress can be estimated using a Rayleigh wave. Therefore, in this study, the maximum compressive residual stress value of the peened Inconel 718 specimen was predicted using a prediction convolutional neural network (CNN) based on the relationship between Rayleigh wave dispersion and stress distribution on the specimen. By analyzing the residual stress distribution in the depth direction generated in the model from various studies in the literature, 173 residual stress distributions were generated using the Gaussian function and factorial design approach. The distribution generated using the relationship was converted into 173 Rayleigh wave dispersion data to be used as a database for the CNN model. The CNN model was learned through this database, and performance was verified using validation data. The adopted Rayleigh wave dispersion and convolutional neural network procedures demonstrate the ability to predict the maximum compressive residual stress in the peened specimen.

Nondestructive Evaluation of Residual Stress in Shot Peened Inconel Using Ultrasonic Minimum Reflection Measurement.

Shot peening is a process wherein the surface of a material is impacted by small, spherical metal shots at high velocity to create residual stresses. Nickel-based superalloy is a material with high strength and hardness along with excellent corrosion and fatigue resistance, and it is therefore used in nuclear power plants and aerospace applications. The application of shot peening to INCONEL, a nickel-based superalloy, has been actively researched, and the measurement of residual stresses has been studied as well. Previous studies have used methods such as perforation strain gauge analysis and X-ray diffraction (XRD) to measure residual stress, which can be evaluated with high accuracy, but doing so damages the specimen and involves critical risks to operator safety due to radiation. On the other hand, ultrasonic testing (UT), which utilizes ultrasonic wave, has the advantage of relatively low unit cost and short test time. One UT method, minimum reflection measurement, uses Rayleigh waves to evaluate the properties of material surfaces. Therefore, the present study utilized ultrasonic minimum reflectivity measurements to evaluate the residual stresses in INCONEL specimens. Specifically, this study utilized ultrasonic minimum reflection measurements to evaluate the residual stress in INCONEL 718 specimens. Moreover, an estimation equation was assumed using exponential functions to estimate the residual stress with depth using the obtained data, and an optimization problem was solved to determine it. Finally, to evaluate the estimated residual stress graph, the residual stress of the specimen was measured and compared using the XRD method.

Development of depression detection algorithm using text scripts of routine psychiatric interview.

Background: A psychiatric interview is one of the important procedures in diagnosing psychiatric disorders. Through this interview, psychiatrists listen to the patient's medical history and major complaints, check their emotional state, and obtain clues for clinical diagnosis. Although there have been attempts to diagnose a specific mental disorder from a short doctor-patient conversation, there has been no attempt to classify the patient's emotional state based on the text scripts from a formal interview of more than 30 min and use it to diagnose depression. This study aimed to utilize the existing machine learning algorithm in diagnosing depression using the transcripts of one-on-one interviews between psychiatrists and depressed patients. Methods: Seventy-seven clinical patients [with depression (n = 60); without depression (n = 17)] with a prior psychiatric diagnosis history participated in this study. The study was conducted with 24 male and 53 female subjects with the mean age of 33.8 (± 3.0). Psychiatrists conducted a conversational interview with each patient that lasted at least 30 min. All interviews with the subjects between August 2021 and November 2022 were recorded and transcribed into text scripts, and a text emotion recognition module was used to indicate the subject's representative emotions of each sentence. A machine learning algorithm discriminates patients with depression and those without depression based on text scripts. Results: A machine learning model classified text scripts from depressive patients with non-depressive ones with an acceptable accuracy rate (AUC of 0.85). The distribution of emotions (surprise, fear, anger, love, sadness, disgust, neutral, and happiness) was significantly different between patients with depression and those without depression (p < 0.001), and the most contributing emotion in classifying the two groups was disgust (p < 0.001). Conclusion: This is a qualitative and retrospective study to develop a tool to detect depression against patients without depression based on the text scripts of psychiatric interview, suggesting a novel and practical approach to understand the emotional characteristics of depression patients and to use them to detect the diagnosis of depression based on machine learning methods. This model could assist psychiatrists in clinical settings who conduct routine conversations with patients using text transcripts of the interviews.