Journal of Mechanics in Medicine and Biology

Body imbalance is one cause of sleep disorders. If one continues to sleep in an unbalanced state, various diseases, as well as headaches and stress, may occur. Some studies have been conducted to solve body imbalance during sleep, but most have used spring mattresses, and because body pressure varies by user, limitations exist for balancing pressure with this type of mattress. In our study, we investigated sleep quality using a transforming bed that conformed to the body and a flat bed that did not conform, considering user body pressure on both. We evaluated sleep quality with polysomnography and the Pittsburgh Sleep Quality Index, Korean version (PSQI–K) for 30 participants. Polysomnography showed that the ratio of delta and alpha waves in flat bed sleep was high; the ratio of theta waves was higher in transforming bed sleep than it was in flat bed sleep. The PSQI–K showed that most participants had a lower sleep index when using the transforming bed than when using the flat bed. Thus, we confirmed that sleep quality using a transforming bed was better than that of a flat bed. Therefore, considering body balance during sleep can help improve sleep quality.

The detailed effect of Q808 (6-(4-chlorophenoxy)-tetrazolo[5,1-a]phthalazine) which has been demonstrated to have anti-epileptic activity, on the protection from neuronal damage in temporal lobe epilepsy (TLE) still remains unclear. The purpose of this study was to evaluate the protective effects of Q808 on neuronal damage by exploring its mechanism of hippocampal neuronal apoptosis in a rat model of TLE. Fifty rats were divided equally into five groups. The normal group $(n=10)$ served as the normal non-seizure and untreated group. To induce the TLE model, pilocarpine (20mg/kg) was intraperitoneally administered to the other 40 rats; 33 rats successfully developed TLE status. Subsequently, the TLE group $(n=9)$, VPA group $(n=8)$, Q808-L group $(n=8)$, and Q808-H group $(n=8)$ were, respectively, treated with 5ml normal saline, 1ml/kg valproate, 0.5ml/kg Q808, and 1ml/kg Q808 solution once daily for 28 days. The Morris water maze test was performed to evaluate the effects of Q808 on cognitive impairment in the TLE model. Hematoxylin-eosin (HE) staining was performed to determine histopathological changes in the hippocampus, immunohistochemistry was performed to determine the expression of caspase-3 in the hippocampus, and western blotting was performed to determine the expression levels of apoptosis-related proteins, including Apaf-1, caspase-9, and caspase-3. Q808 decreased the expression levels of the apoptosis-related proteins in the TLE hippocampal tissue, and higher doses are more effective. Besides, Q808 did not impair spatial cognition and memory. Furthermore, the results indicated that Q808 treatment inhibited neuronal cell death, and significantly decreased the expression levels of apoptotic factors, including Apaf-1, caspase-9, and caspase-3. Q808 prevented neuronal damage in the hippocampus of TLE rats by targeting the intrinsic apoptotic pathway of neurons.

Objective: To explore the impact of plan-do-check-act (PDCA) cycle intervention on negative emotion and rehabilitation effects in older adults after hip replacement. Methods: Between January 2019 and 2021, 100 elderly adults who underwent hip replacements were randomly divided into control ($n=50$) and study groups ($n=50$), respectively. The control group received routine nursing, whilst the study group underwent PDCA cycle interventions. Anxiety [self-rating anxiety scale [SAS]), depression (self-rating depression scale (SDS), hip function score (Harris score), daily living activities (ADL score), and adverse complication incidence before and after intervention were compared. Results: No significant difference ($P>0.05$) in SDS and SAS scores occurred between groups before intervention, but were lower in both groups after intervention Moreover, study group scores were lower than control group ($P<0.05$). Before intervention, there was no significant difference ($P>0.05$) in Harris and ADL scores between groups. Scores of both groups increased following intervention, with the study group scoring higher than the control group ($P<0.05$). Lower limb venous thrombosis, phobia, delirium, and other adverse complications were lower in the study group than in the control group ($P<0.05$). Conclusion: PDCA is safe and effectively alleviates negative emotions, promotes limb function recovery, and improves the quality of life.

For the purpose of improving the classification accuracy of single-trial electroencephalogram (EEG) signal during motor imagery (MI) process, this study proposed a classification method which combines intrinsic mode functions (IMFs) energy entropy and improved empirical mode decomposition (EMD) scheme. Singular value decomposition (SVD), Gaussian mixture model (GMM), EMD and IMF energy entropy were employed for the newly designed scheme. After removing noise and artifacts from acquired EEG signals in EEGLAB, SVD was applied, and the singular values were clustered by GMM. The insignificant characteristics indicated by the small SVD values were then removed, and the signals were reconstructed, feeding to EMD algorithm. Those IMFs mapping to $\delta$, $\theta$, $\alpha ,$ and $\beta$ frequencies were selected as the major features of the Electroencephalogram signal. The SVM classifier with Radial Basis Function Neural Network, linear, and polynomial kernel functions and voting mechanism then kicked in for classification. The results were compared with that of the traditional EMD and EEMD through simulation, showing that the proposed scheme can eliminate mode mixing effectively and improve the single-trial EEG signal classification accuracy significantly, suggesting the probability of designing a more efficient EEG control system based on the proposed scheme.

Implantation of the blood pump is an important method to treat heart failure (HF) at present. Many studies have shown that the pressure waveform produced by the constant speed of the rotary blood pump lacks fluctuation, which may cause a series of body damage. Therefore, it is believed that it is beneficial for the body to produce higher pressure fluctuation by rapidly adjusting the speed of the blood pump, but how to set the parameters in the speed waveform is a big challenge. The purpose of this study is to obtain the regularity of the blood pump’s changing speed on hemodynamics. In this study, a lumped parameter coupling model of the blood pump and cardiovascular system was established, and the blood pump model was improved by introducing the pulsation characteristic component. A velocity regulation waveform that is consistent with the trend of the ventricular activation function was selected. The effects of different speed control parameters on hemodynamic parameters were analyzed, and comparisons with the constant speed were made. The results show that the pulse pressure (PP) is higher at variable speed. The hemolysis value under variable speed is higher than constant speed, and increases with the decreases of speed modulation frequency. We also found that the PP will increase with the decrease of the speed control frequency. To explain this phenomenon, a dimensionless parameter S that combines the integral of the speed pulsation amplitude with the modulation cycle and the heartbeat cycle was proposed. By comparing the S and PP values, it shows that the change rules of the two are compatible. Therefore, the speed modulation of the blood pump should also consider the integral effect of the rotation speed in the cardiac cycle.

The diaphragm is an essential respiratory muscle that accounts for 70% of the inspiratory function during stable breathing. Diaphragm weakness leads to decreased thoracic mobility due to inspiratory assist muscles overuse. It is closely related to respiratory dysfunction. This study aims to define the effect of TECAR therapy using Winback on diaphragm movement and chest mobility in adults with limited chest mobility. Thirty-six young adults with limited chest mobility were selected as participants in this study. TECAR therapy was applied to the participant’s diaphragm for 15min. Ultrasound measured each group’s diaphragm movement, and a tape measure was used to measure chest mobility. A paired t-test analyzed each group’s diaphragm movement and chest mobility change, and an independent t-test analyzed the difference in the amount of change between groups. The value was set to 0.05. As a result, after the intervention, diaphragm movement (unit: cm) significantly increased from $0.958\pm 1.04$ to $3.037\pm 2.96$ ($p<0.05$). Upper chest movement (unit: cm) significantly increased from $3.4\pm 4.70$-$6.1\pm 5.17$, middle chest movement (unit: cm) increased from $3.1\pm 2.16$-$5.3\pm 4.08$, and lower chest movement (unit: cm) increased from $2.7\pm 2.08$-$3.3\pm 2.92$ ($p<0.05$). The results provide innovative clinical evidence that TECAR therapy significantly affected diaphragm movement and chest mobility improvement in young adults with limited chest mobility.

The growing interest in gait recognition based on surface electromyography (sEMG) signals is attributed to their capability to anticipate motion characteristics during human movement. This paper focuses on gait pattern recognition using sEMG signals. Initially, the muscles responsible for collecting sEMG signals are determined based on the distinct characteristics of human gait, and data for 12 different gait patterns are collected. Subsequently, the acquired sEMG signals undergo preprocessing and feature extraction stages. Moreover, various algorithms relevant to gait classification based on surface myoelectric signals are investigated. In this study, we propose an improved particle swarm optimization algorithm (MPSO-LSTM) for accurately classifying gait patterns using surface myoelectric signals. Experimental results demonstrate the effectiveness of the MPSO-LSTM algorithm in gait recognition based on sEMG signals.

Background: This study was performed to compare the clinical effect of bipolar hemiarthroplasty via the direct anterior approach (DAA) or minimally invasive posterolateral approach (MIPA) in elderly patients with femoral neck fracture. Methods: In total, 196 elderly patients with femoral neck fractures were divided into the DAA group ($n=98$) and MIPA group ($n=98$). The clinical data, postoperative pain and complications, time until able to remain seated for 1 hour and walk independently, postoperative Harris score of functional activity at 6 weeks and 2 years postoperatively, and mortality at 2 years postoperatively were compared between the groups. Results: The DAA group had a longer operation time but a lower incidence of pneumonia 72 hours postoperatively, lower visual analogue scale score 24 hours postoperatively, and earlier time until able to remain seated for 1 hour and walk independently ($P<0.05$). Six weeks postoperatively, the Harris scores for putting on socks, tying shoelaces, sitting comfortably on a chair, and climbing stairs were better in the DAA than the MIPA group ($P<0.05$). After 2 years, there was no significant difference in the Harris scores between the two groups ($P>0.05$). Conclusion: In elderly patients undergoing bipolar hemiarthroplasty, the DAA can be more effective than the MIPA in reducing the incidence of complications associated with long-term bed rest, relieving early postoperative pain, and improving early postoperative hip function.

This study aims to develop effective predictive models to assess knee replacement (KR) risk in knee osteoarthritis (KOA) patients, which is important in the personalized diagnosis, assessment, and treatment of KOA. A total of 269KOA patients were selected from the osteoarthritis initiative (OAI) public database and their clinical and knee cartilage image feature data were included in this study. First, the clinical risk factors were screened using univariate Cox regression and then used in the construction of the Clinical model. Next, their image features were selected using univariate and least absolute shrinkage and selection operator (LASSO) Cox methods step by step, and then used in the construction of the Image model. Finally, the Image+Clinical model was constructed by combining the Image model and clinical risk factors, which was then converted into a nomogram for better visualization and future clinical use. All models were validated and compared using the metric of C-index. In addition, Kaplan–Meier (KM) survival curve with log-rank test and calibration curve were also included in the assessment of the model risk stratification ability and prediction consistency. Age and three Western Ontario and McMaster Universities (WOMAC) scores were found significantly correlated with KR, and thus included in Clinical model construction. Fifty-eight features were selected from 92knee cartilage image features using univariate cox, and four image features were retained using the LASSO Cox method. Image+Clinical model and nomogram were finally constructed by combining clinical risk factors and the Image model. Among all models, the Image+Clinical model showed the best predictive performance, and the Image model was better than the Clinical model in the KR risk predictive consistency. By determining an optimal cutoff value, both Image and Image+Clinical models could effectively stratify the KOA patients into KR high-risk and low-risk groups (log-rank test: $p<0.05$). In addition, the calibration curves also showed that model predictions were in excellent agreement with the actual observations for both 3-year and 6-year KR risk probabilities, both in training and test sets. The constructed model and nomogram showed excellent risk stratification and prediction ability, which can be used as a useful tool to evaluate the progress and prognosis of KOA patients individually, and guide the clinical decision-making of KOA treatment and prognosis.

Pneumothorax is a common yet potentially serious lung disease, which makes prompt diagnosis and treatment critical in clinical practice. Deep learning methods have proven effective in detecting pneumothorax lesions in medical images and providing quantitative analysis. However, due to the irregular shapes and uncertain positions of pneumothorax lesions, current segmentation methods must be further improved to increase accuracy. This study aimed to propose a Dense Swin-Unet algorithm that integrated the Dense Swin Transformer Block with the Swin-Unet model. The Dense Swin-Unet algorithm employed a sliding window self-attentiveness mechanism on different scales to enhance multiscale long-range dependencies. We designed an enhanced loss function that accelerated the convergence speed to address the issue of class imbalance. Given the limited availability of data in pneumothorax image processing, we created a new dataset and evaluated the efficacy of our model on this dataset. The results demonstrated that our lesion segmentation algorithm attained a Dice coefficient of 88.8%, representing a 1.5% improvement compared with previous deep learning algorithms. Notably, our algorithm achieved a significant enhancement in segmenting small microlesions.

Objective: Knee replacement (KR) is a widely accepted procedure for end-stage knee arthritis. Patients’ subjective perception of knee joint symptoms is an important factor in their decision to undergo knee replacement. This paper mainly studies the correlation between knee joint symptoms and knee replacement, aimed to establish the corresponding preoperative decision-making model. Methods: 122 knee arthritis patients were included from the knee arthritis database FNIH OAI, of which 61 had knee arthroplasty and 61 without knee arthroplasty. First, WOMAC score was used to quantitatively evaluate the knee joint symptoms of patients; then the correlation between clinical risk factors, single WOMAC score and knee replacement was analyzed. Then K-means cluster analysis was used to divide the multidimensional WOMAC score into different groups of knee arthritis symptoms’ severity. Finally, based on the retained clinical risk factors and WOMAC cluster variables, the clinical models, WOMAC scoring model and clinical +WOMAC scoring model were constructed, respectively, and compared. Results: Age and BMI were significant risk factors for knee replacement ($p<0.05$), which could be used to construct the clinical model. There was no significant correlation between any single WOMAC score and knee replacement ($p>0.05$). The cluster variable of WOMAC score obtained by cluster analysis was significantly correlated with knee replacement ($p<0.05$). Based on the above risk factors, we established the Age+BMI, Cluster and Age+BMI+Cluster models, respectively. The comparison results showed that the Age+BMI+Cluster model ($\mathrm{\text{AUC}}=0.750$) showed the highest predictive value for knee replacement, and the corresponding nomogram also showed good predictive consistency; the performance of Cluster model ($\mathrm{\text{AUC}}=0.681$) was the second. The pure clinical risk factor model Age+BMI showed the worst predictive performance ($\mathrm{\text{AUC}}=0.577$). Conclusion: This paper analyzed the correlation between patients’ subjective perception of knee arthritis symptoms and the final knee replacement, and constructed a new biomarker based on the WOMAC score. After analysis and modeling, this marker could be used to predict knee replacement. The constructed Age+BMI+Cluster nomogram could be used for personalized assessment of the risk of knee replacement.

In recent years, the prevalence of cardiovascular diseases has been growing geometrically, especially among the elderly. Real-time heart rate monitoring becomes an effective measure for preventing cardiovascular diseases. Traditional contact-based real-time heart rate measurement methods require long-term wearing of contact electrodes, which can cause inconvenience to the elderly population. In this study, a wide spectrum full color night vision elderly face video heart rate automatic measurement and early warning system was designed and developed by combining imaging photoplethysmography (IPPG), video acquisition equipment based on starlight wide spectrum camera and high-speed face recognition signal processing algorithm based on deep learning. By constructing a software and hardware platform, a comprehensive evaluation of the system’s application in elderly facial video heart rate measurement experiments was conducted.

Objective: This study aimed to compare the differences between narrowband imaging (NBI) and Lugo’s iodine staining endoscopy (LCE) for detecting and elucidating the site, clarity, and diagnostic accuracy of early esophageal cancer and precancerous lesions. Methods: We included patients with a high risk of developing esophageal cancer who visited the Zhongjiang County People’s Hospital between October 2020 and October 2022. Endoscopic examination was performed on each study participant. White-light endoscopy was used to observe and locate the diseased mucosa, after which NBI mode and LCE staining were used to observe the boundary between the diseased and normal mucosa. Abnormal lesions were found, and biopsies were performed on the identifiable diseased parts for pathological examination. Inflammation, LGIN, HGIN, and early esophageal cancer were diagnosed, and the differences between them were compared in terms of the two enhanced-image endoscopy techniques. A semantic segmentation model based on deep learning was adopted to assist in the diagnosis of early esophageal cancer and accurately locate cancerous areas. In order to improve its accurate diagnostic rate, we also built a semantic segmentation network model to assist in the computer-aided diagnosis of early esophageal cancer. Results: A total of 69 cases of early esophageal cancer were included in this study. The patients were aged 40–75 years, with an average age of $62\pm 2.0$ years. Most early esophageal cancer lesions were located in the middle of the esophagus in 45/69 (65.2%) cases. LCE obtained higher clarity of lesion boundaries than NBI (59.4% versus 45.0% and 27.7% versus 15.9%, respectively), and the proportion of unclear lesions was lower (8.6% versus 21.7% and 4.3% versus 17.4%, respectively; $p<0.05$). For early esophageal cancer and precancerous lesions, the missed-diagnosis rate of white-light endoscopy was 20%, that of NBI was 3.15%, and that of LCE was 0%, with statistical significance ($p<0.05$). The rate of missed diagnosis of LGIN (three cases) by NBI was 3.15%, which was not significantly different from that of LCE ($p>0.05$). We found that the lesion area could be more accurately determined using deep learning models to segment NBI images. By constructing a deep learning model for the diagnosis and classification of esophageal cancer, its diagnostic rate rose to 99.5%. Conclusion: The age range of patients with early esophageal cancer in Zhongjiang County, Sichuan Province, was 40–75 years, and tumors mostly occurred in the middle of the esophagus. The boundary clarity of early esophageal carcinomas was higher on LCE than that on NBI. The diagnostic accuracies of NBI and LCE are much higher than those of conventional white-light endoscopy. Therefore, both LCE and NBI are helpful for detecting early esophageal cancer and precancerous lesions. Moreover, the diagnostic rate of clinical esophageal cancer can be effectively improved using a dedicated deep learning network model.

With the rapid development of intelligent information technology, human–computer interaction for unmanned aerial vehicle (UAV) systems has gradually developed from single-mode interaction to multi-modal interaction. Due to the problems of information ambiguity and operational redundancy in multi-modal interaction, and the inability to effectively realize the coupling of human–computer interaction of different modalities, a priority strategy for multi-modal interaction for UAV systems is proposed. Living cells or tissues, whether in a static or active state, will produce regular electrical phenomena called bioelectricity. Human–computer interaction intention recognition technology based on bioelectrical signals can significantly enhance the real-time performance and flexibility of human–computer interaction and has great development potential. The characteristics of human–computer interaction intention recognition methods based on bioelectrical signals, such as electroencephalograms (EEGs), electromyograms (EMGs), electrooculograms (EOGs), and other conventional methods are introduced and analyzed, and then the basic characteristics of single-mode interaction and multi-modal interaction are compared. Furthermore, the priority strategies for UAV systems under different interaction modes are studied based on the analysis of task value evaluation parameters. The cumulative value, urgency, and task complexity are comprehensively analyzed and evaluated, and a set of priority strategies for multi-modal interaction is integrated. Through the simulation and verification of the multi-modal human–computer interaction software of the UAV system, it is determined that the proposed priority strategy conforms to the operation intention of the user, which improves the interaction efficiency and the reliability. In noisy environments, the UAV system control can be combined with the complementary information of various interaction methods to achieve precise control, which has obvious advantages.

Hepatic injury induced by blunt abdominal impact is a major cause of death in vehicle crashes. However, few works have been done effectively in cadaver experiments to clarify the liver’s specific dynamic behavior and mechanical characteristics. This paper described the dynamic behavior and mechanical characteristics of the liver under blunt impacts to the upper abdomen with the finite element model (FEM) of the Chinese human body — the 50 percentile-sized male (CHUBM-M50). The simulation matrix, three directions (frontal, oblique, lateral), and four speeds included in each group were designed with a 23.4kg, rigid cylindrical impactor aligning the T11 level. The liver deformation contours displayed compression against the spine and rotation in the horizontal plane, which were the two main features in liver motion. Pressure distribution in the liver capsule and parenchyma was discussed to elucidate the biomechanical characteristics related to impact direction. Generally, the stress distribution in the capsule was 10 times higher than that in the parenchyma. A discussion of the injury mechanism of the liver capsule and parenchyma observed in the simulations was given upon the pressure distribution. It demonstrated that the capsule could protect liver parenchyma at low-speed impacts and should not be neglected for understanding liver injury mechanisms.

Parkinson’s disease (PD) is a neurodegenerative disease that progresses slowly. In this study, a tuna swarm optimization (TSO)-based hybrid kernel extreme learning machine (HKELM) method was proposed for early phonetic recognition of PD. Herein, HKELM models were optimized using multi-strategy (reverse learning and greedy selection swarm initialization, sin–cos strategy disturbance, and Weibull variation disturbance) improved TSO for early diagnosis of PD. The HKELM was employed for early diagnosis of PD and its classification accuracy was evaluated. The results of the experiments reveal that, as compared to the unimproved tuna technique for optimizing ELM, the suggested algorithm converges faster, can leap out of the local optimal, and has higher optimization accuracy.

Stress is a pervasive phenomenon with significant implications for individual well-being. Understanding the neural processes underlying stress responses and recovery is crucial for developing effective interventions. This study employed functional magnetic resonance imaging (fMRI) to investigate the brain activation patterns during stress induction and recovery in healthy adults. The Montreal Imaging Stress Task (MIST) was utilized to elicit acute stress in participants. The results revealed that during the stress task phase, the right hemisphere showed activation in the Inferior Parietal Lobule, Postcentral Gyrus, and Precuneus, while the left hemisphere demonstrated activation in the Inferior Parietal Lobule, Postcentral Gyrus, Middle Frontal Gyrus, and Superior Frontal Gyrus. Following the stress task, during the recovery phase, the right hemisphere exhibited activation in the Precuneus, Middle Occipital Gyrus, Superior Occipital Gyrus, Angular Gyrus, Medial Frontal Gyrus, Middle Frontal Gyrus, and Posterior Cingulate, whereas the left hemisphere displayed activation primarily in the Cuneus. Comparing the two phases, the left frontal lobe and occipital lobe exhibited increased activation during the rest period after stress. In contrast, the parietal lobe showed decreased activation during the recovery phase. These findings contribute to our understanding of the neural mechanisms associated with stress responses and recovery, providing insights into potential interventions for stress management and promoting well-being.

This study optimized spatial resolution of mammography imaging quality using a CIRS-016A commercial line gauge and the Taguchi methodology. The line gauge with a precise line pair from 5lp/mm to 20lp/mm was placed on top of triangular PMMA plates to simulate the female breast undergoing mammography. Five factors: target/filter, kVp, mAs, PMMA plate thickness, and compression force, were organized into 18 groups according to the Taguchi L${}_{18}$ orthogonal array. Tactically, the 18 various combinations of factors could provide similar confidence levels, as those following the full factorial combination in reality. Seven experienced radiology experts judged the 18 imaging qualities based on contrast, sharpness, and spatial resolution. Then the signal-to-noise ratio was calculated according to the “the larger, the better” ranking order. The optimal preset of mammography was verified from the unique fish bone plot and the follow-up analysis of variance (ANOVA) test. The optimal combination of factors was as follows: Rh/Ag as target/filter, 32kVp, 36mAs, a 45mm thick PMMA plate, and a 13daN compression force in routine diagnosis. The concurrent resolution of 6lp/mm or about a 0.09mm minimum detectable difference (MDD) was superior to 5lp/mm of the conventional preset or combinations of factors of either highest Avg or lowest std. Compared to other studies with various facilities, this was the finest resolution among the routine X-ray, cardiac X-ray or computed tomography (CT), and computed tomography angiography (CTA).

Objective: This study used CiteSpace to look at the current state of research on epilepsy and synaptic plasticity and to point out the hotspots and frontiers. Method: We searched Web of Science (WoS) for studies related to epilepsy and synaptic plasticity. CiteSpace was used to construct network maps of cooperation across countries, institutions, and authors to identify frontiers and hotspots in epilepsy and synaptic plasticity research. Results: A total of 1700 studies on epilepsy and synaptic plasticity were retrieved from the WoS. The United States and Baylor College of Medicine were the most prolific nation and institution in this field with 680 and 28 publications, respectively. The most prolific author (11 articles) was Xuefeng Wang. The Journal of Neuroscience published the most articles (71, 6.71%) and had the most co-citations (1557, 4.57%). In this paper, the interaction and mechanism between epilepsy and synaptic plasticity, as well as future research hotspots, are highlighted. Conclusion: CiteSpace can reveal the institutions, leaders, journals, cited papers, and research hotspots involved in epilepsy and synaptic plasticity. To the best of our knowledge, this is the first study that visualizes the relationship between epilepsy and synaptic plasticity and provides references for future research directions.

The emotional well-being of college students is of utmost significance. The psychological states of college students who are on the verge of entering the social work field form the key factor that directly influences the quality of social construction because these students constitute the primary driving force in the field. On the other hand, the overwhelming amount of schoolwork, the intense level of competitiveness, and the undeveloped psychological qualities of college students are the primary contributors to their mental health problems. Currently, an increasing number of college students are struggling with mental health issues, which will have a significant impact on the growth of families and schools and the future construction of the nation. In this paper, deep features and a multiview fuzzy clustering technique are presented, as well as a mental health assessment model (CNN-MV-MEC) that is proposed for college students. The primary purpose of this research is to determine the mental state of the input sample by classifying and identifying an EEG that was acquired through the application of CNN-MV-MEC. If a certain number of samples are found to be in negative emotional states on a regular basis or for an extended period of time, this indicates that the sample most likely contains individuals who struggle with mental health issues. At this point in time, university officials are in a position to implement follow-up mental health management actions based on the outcomes of the model evaluation process. The primary contributions of this study are as follows. First, to extract the deep features from the given dataset, this paper makes use of a traditional convolutional neural network (CNN). In the second step, a classification model is trained using a multiview maximum entropy clustering (MV-MEC) technique. In the final step, the input test data are categorized by employing the trained classification model to determine the emotional state of the sample. The SEED dataset is used as the training data for the mental health assessment model proposed in this paper. Thus, the performance of the model can be evaluated. Model comparison experiments demonstrate that the proposed approach yields more accurate results than competing methods when assessing the mental health of college students.

The level of human–machine interaction experience is raising its bar as artificial intelligence develops quickly. An important trend in this application is the improvement of the friendliness, harmony, and simplicity of human–machine communication. Electroencephalogram (EEG) signal-driven emotion identification has recently gained popularity in the area of human–computer interaction (HCI) because of its advantages of being simple to extract, difficult to conceal, and real-time differences. The corresponding research is ultimately aimed at imbuing computers with feelings to enable fully harmonic and organic human–computer connections. This study applies three-dimensional convolutional neural networks (3DCNNs) and attention mechanisms to an environment for HCI and offers a dual-attention 3D convolutional neural networks (DA-3DCNNs) model from the standpoint of spatio-temporal convolution. With the purpose of extracting more representative spatio-temporal characteristics, the new model first thoroughly mines the spatio-temporal distribution information of EEG signals using 3DCNN, taking into account the temporal fluctuation of EEG data. Yet, a dual-attention technique based on EEG channels is utilized at the same time to strengthen or weaken the feature information and understand the links between various brain regions and emotional activities, highlighting the variations in the spatiotemporal aspects of various emotions. Finally, three sets of experiments were planned on the Database for Emotion Analysis using Physiological Signals (DEAP) dataset for cross-subject emotion classification experiments, channel selection experiments, and ablation experiments, respectively, to show the validity and viability of the DA-3DCNN model for HCI emotion recognition applications. The outcomes show that the new model may significantly increase the model’s accuracy in recognizing emotions, acquire the spatial relationship of channels, and more thoroughly extract dynamic information from EEG.

Deep learning simultaneously learns a large amount of data, correct answers (labels), and extracts and learns features from the data. When training a deep learning model, the amount of data in your dataset has a significant impact on model performance. However, in the case of medical images, it is difficult to collect a large amount of data due to problems such as personal information protection. Also, since dedicated expertise is required to build an effective dataset, the amount of data that can be obtained is limited. Data augmentation techniques have been utilized to improve performance in various medical artificial intelligence studies and are considered an essential process to improve the performance of deep learning models. Data augmentation allows you to learn from different types of data. However, the standard process for achieving good performance when using a specific size of training data is still unclear. We compared the classification performance of several convolutional neural network models using datasets with different amounts of data to identify the optimal amount of training data that ensures good performance. We attempted to quantify the optimal amount of data for each convolutional neural network model by comparing overall results using both real and augmented datasets.

Objective: This study aimed to investigate the effect of Suile ointment wound dressing on wound healing in patients with pressure injury (PI). Methods: Patients with stage II and III PI who met the inclusion criteria were randomly divided into two groups of 20 patients each, according to the National Pressure Ulcer Advisory Panel’s staging table. After debridement, the patients’ wounds in the control group were covered with petrolatum gauze and sterile dressing in the outer layer. Suile ointment wound dressing was applied externally to those in the experimental group, and the outer layer was covered with a sterile dressing. The experimental group included 20 patients with 27 wounds, and the control group included 20 patients with 30 wounds. The white blood cell count, erythrocyte sedimentation rate, and hypersensitive C-reactive protein levels were measured to control wound infection. Results: The overall response rates in the experimental group and the control group were 96.3% and 47%, respectively, and the results were statistically significant. Conclusion: Suile ointment wound dressing (wound care ointment) effectively removes dead tissue, promotes tissue regeneration and local vascular expansion, effectively controls wound infection, and relieves pain in patients with stage II and III PI.

With the development of computer technology and neural networks, artificial intelligence (AI) has become sufficiently mature to assist in various technical and medical tasks, including the prenatal diagnosis of congenital heart disease (CHD). Moreover, the AI-based approach to solving this challenge has provided new ideas, concepts, and techniques. This review focuses on fetal CHD and conventional methods of its diagnostics, highlights the main achievements and particular techniques of AI application to CHD diagnostics, and discusses their advantages, drawbacks, and ways of further improvement regarding CHD and other heart disease.