Multistage Method Research Articles

Explainable tele-ultrasound diagnosis of blast lung injury via incremental multimodal multistage fusion and video transformer

Blast lung injury (BLI) is a significant concern in cases of explosive events and can have severe consequences for victims. The injury is often irreversible, emphasizing the need for early symptom confirmation and intervention. Tele-ultrasound (Tele-US) is a novel approach that enables healthcare professionals to remotely interpret US images and provide diagnostic assessments, which can offer timely and accurate assessments for BLI. In this study, we propose an explainable two-stream tele-US diagnosis method for BLI, which is an incremental multimodal multistage fusion method (IM3S-Fusion). This method is the first deep learning-based diagnosis method for BLI and, specifically, the first exploration of video Transformers in this field. It integrates optical flow into US videos, enhancing model interpretability and improving diagnostic accuracy. By integrating incremental broad learning system (IBLS), IM3S-Fusion can incrementally update its parameters with new samples in a lifelong learning fashion, especially for those misdiagnosed samples. The results show its superiority in diagnosing BLI with (87.50 ± 2.76)%, (89.06 ± 2.71)%, (88.09 ± 5.26)%, (85.71 ± 7.14)% and (88.43 ± 2.24)% in accuracy, recall, precision, specificity and F1-score, respectively. Explanatory assistance including fused US video with optical flow, class activation map videos and confidence scores, is provided for doctors to facilitate their diagnosis.

A Multi-Stage Constraint-Handling Multi-Objective Optimization Method for Resilient Microgrid Energy Management

In recent years, renewable energy has seen widespread application. However, due to its intermittent nature, there is a need to develop energy management systems for its scheduling and control. This paper introduces a multi-stage constraint-handling multi-objective optimization method tailored for resilient microgrid energy management. The microgrid encompasses diesel generators, energy storage systems, renewable energy sources, and various load types. The intelligent management of generators, batteries, switchable loads, and controllable loads ensures a reliable power supply for the critical loads. Beyond operational costs, our model also considers grid dependency as a key objective, making it particularly suited for energy management in extreme environments such as islands, border regions, and military bases. Managing complex controls of generators, batteries, switchable loads, and controllable loads presents challenging constraints that the management strategy must meet. To tackle this challenge, we propose an multi-objective optimization algorithm with multi-stage constraint-handling strategy to handle the high-dimensional complex constraints of the resilient energy management problem. Our proposed approach demonstrates superior performance compared to nine leading constrained multi-objective optimization algorithms across various test scenarios. Furthermore, the benefits of our method become increasingly evident as the complexity of the problem increases. Compared to the classical NSGA-II, the proposed NSGA-II-MC method achieved a 49.7% improvement in the Hypervolume metric on large-scale problems.

A study on the dual use of e-cigarettes and cigarettes among adolescents in Shandong Province

Objective: To understand the current status and its associated factors of dual use of e-cigarettes and cigarettes among adolescents in Shandong Province and explore the reasons for dual use behavior. Methods: A self-administered survey was conducted among 7 999 middle school students who were selected by stratified multi-stage cluster sample method. Data were weighted and analyzed by the SPSS 25.0 complex program. Results: In Shandong Province, the prevalence rates of attempting and current dual use of e-cigarettes and cigarettes among adolescents appeared as 7.7% and 1.3%, respectively. Male, friends smoking, and secondhand smoke exposure in the past 7 days were risk factors for dual use. Compared with cigarette smokers, dual users have no differences in cognition and behavior in quitting smoking (P>0.05). The main reason for dual users to smoke e-cigarettes was curiosity. Conclusions: Dual use of e-cigarettes and cigarettes is common among adolescents in Shandong Province, and its influencing factors are similar to traditional cigarettes. Dual use is not a transitional stage for smoking cessation. Dual users are more likely to continue smoking in the future, which should be paid attention and concern.

The green reductive leaching of manganiferous iron ore and Mn3O4 nanoparticles production: Kinetic modeling and comparison of various reductants

BackgroundSecuring critical metals is crucial for the transition from fossil fuels to renewable energies. In this regard, extracting metals from various sources and low-grade ores can lead to the sustainable production of metals. Manganese, as a strategic metal, can play a significant role in achieving this goal. MethodsIn this study, various reductants such as oxalic acid, citric acid, ascorbic acid, acetic acid, tannic acid, hydrogen peroxide, iron (II) sulfate, sodium thiosulfate, and DL-malic acid were used to evaluate the feasibility and comparison on the manganiferous iron ore leaching. Significant findingsDL-malic acid was chosen as the main reductant to investigate other factors because it is novel (as a reductant), eco-friendly, cost-effective, accessible, and easily storable. Therefore, more detailed studies on the dissolution of manganiferous iron ore in the presence of DL-malic acid as the reductant were carried out considering different levels of temperature, particle size, acid concentrations, and leaching time. Increasing the temperature from 298 K to 348 K notably boosted the leaching recovery from 27.00 % to 70.11 %. It was observed that decreasing the ore particle size from -212 μm to -38 μm resulted in an enhancement of leaching recovery from 57.74 % to 70.11 %. Also, adding only 250 % stoichiometry of DL-malic acid notably increased the leaching recovery to 70.11 %, compared to just 5.32 % in a reductant-free medium. It should be noted that the concentration of sulfuric acid had a direct impact on leaching recovery, increasing by 28.28 % with a concentration of 0.5 M and by 93.08 % with a concentration of 4 M. In this research work, the kinetic of the leaching process was modeled using the modified shrinking core model (MSCM). The calculated activation energy was about 33 kJ/mole, which confirmed that the mixed mechanism controlled the reaction. Mn3O4 nanoparticles were synthesized using a pregnant leach solution (PLS) and through a multi-stage co-precipitation method. In this method, hydrogen peroxide was used to modify the manganese hydroxide phase as a more eco-friendly method than other heat treatment methods. The SEM and EDX analyses revealed an average particle size of 80 nm with spherical shapes and no impurities. The XRD pattern of the synthesized nanoparticles confirmed the Mn3O4 phase composition.

Design of Battery Charging System with CC-CV Method Using Interleaved Buck-Boost Converter

The transition of renewable energy has become an interesting issue and a worldwide concern that is frequently discussed. Solar panels are regarded to have the most potential in tropical areas like Indonesia. However, weather and sunlight intensity have a substantial impact on the amounts of electricity generated by solar panels. Therefore, a battery which functions as a backup supply is required. Lead acid batteries are used in numerous applications. The performance of lead-acid battery is commonly influenced by temperature and charging time, which makes it vulnerable to overcharging. Multistage charge methods, namely Constant Current-Constant Voltage (CC-CV), are used to extend battery life, reduce charging time, and avoid the risk of overcharging. Fuzzy Logic Controller (FLC) is used to adjust charging current and voltage on the battery based on the setpoint. Based on the CC-CV charging system simulation results, a constant current value can be obtained when the CC condition is 4.5 A, and a transition to the CV condition occurs when the voltage value on the battery reaches 14.4 V. When the battery reaches its maximum capacity, the current is reduced to 3% of the battery’s capacity. The rate of fully charged current triggers the relay to turn on, to ensure that the charging process has been completed.

Assessment of Learning Environment of Undergraduates in the Faculty of Engineering in Higher Institutions of Learning

The review researched the learning climate of Designing understudies in higher foundation of learning in Nigeria. The motivation behind the review was to decide the accessibility and usefulness of educational assets for showing designing courses in schools. The concentrate likewise explored the impact of these assets on the scholarly execution of understudies as well as their pioneering abilities. The review embraced the unmistakable examination of an overview type. The example for the review comprised 200 college understudies chosen through the multistage testing method from chose higher establishments in SouthWest, Nigeria. Two exploration questions were raised and three speculations were created for the review. Information were investigated utilizing both illustrative and inferential measurements. The outcome from the understudies' reactions showed that educational assets were accessible yet not satisfactory, hence, the usefulness level is low. Nonetheless, the accessibility of educational assets and language of guidance doesn't impact the presentation of understudies or level of appreciation in the class.

The relationship between individual internal factors and the prevention of obesity in students of junior secondary education level (Grades 7-9)

Purpose: Obesity is a risk factor for non-communicable diseases in children contributing to their physical, mental and social effects. This study aimed to investigate the relationship between individual internal factors and the prevention of obesity in students at the junior secondary education level.
 Design/Methodology/Approach: A multi-stage random selection method was used to select 273 junior secondary education level (grades 7-9) students from the province of Chachoengsao to participate as the study's sample. A questionnaire was used for data collection and was divided into 7 parts: (1) general information about the sample, (2) knowledge about the prevention of obesity, (3) attitudes towards the prevention of obesity, (4) motivation in obesity prevention, (5) habits in obesity prevention, (6) student allowance management and (7) obesity prevention behavior. The data were analyzed using frequency, percentage and correlation analysis.
 Findings: Factors correlated with obesity prevention behavior were obesity prevention habits (r=0.382) and student allowance (r=0.294).
 Conclusion: Parents and schools should give importance to building obesity prevention habits and encourage children to manage their allowance efficiently to be able to help prevent obesity in students at the junior secondary education level. The results from the research can be used to create a model for modifying dietary habits accordingly. The emphasis is placed on involving children in the selection of nutritious foods. Cooking substantial meals or snacks will help to develop healthy eating habits gradually. Add exercise in the form of sports games. In addition, teaching children to record their daily income and expenses for food and snacks will help them use their daily money to their full potential and build habits and values.

Controllable-gradient-porous cooling materials driven by multistage solvent displacement method

Passive radiative cooling holds significant potential for efficiently cooling terrestrial objects by simultaneously reflecting sunlight and radiating heat to the cold outer space. Numerous studies have designed high-performance radiative cooling structures using polymethyl methacrylate (PMMA) due to its inherent extinction coefficient.However, obtaining highly favorable spectral characteristics for reflecting sunlight using PMMA, often done through the fabrication of micro/nanoscale structures, remains a central barrier for widespread application. Herein, we report a facile, economical, and scalable multistage solvent displacement-based method for fabricating hierarchically gradient porous PMMA metafilms with highly efficient daytime and nighttime passive radiative cooling performance. Here, the “ouzo effect” works as the driving force for micro/nanopore formation by solvent displacement, which also controls the size of the pores based on different solution ratios. The PMMA metafilm features an ultrahigh solar reflectance of 0.99 and superior mid-infrared thermal emittance of 0.97, which allows for the average and peak subambient temperature drops of 4.6 °C and 8.2 °C, respectively, along with an average radiative cooling power of 90 W/m2 during a 24-h uninterrupted thermal measurement. The hierarchically gradient micro/nanopore distribution of the PMMA metafilm significantly enhances the solar reflectance and thermal emittance within the atmospheric transparency window. Moreover,the multistage solvent displacement method is highly versatile and promising for fabricating porous structures, further offering a cost-efficient, eco-friendly, and sustainable manufacturing path for high-performance radiative cooling application.

Enhancing temporal action localization in an end-to-end network through estimation error incorporation

Temporal action localization presents a significant challenge in computer vision, as the development of an efficient method for this task remains elusive. The objective is to identify human activities within untrimmed videos, determining when and which actions occur in each video. While using trimmed videos could potentially resolve the localization problem and enhance classification accuracy, it is impractical for real-world applications as the trimming process itself requires human intervention. This highlights the importance of temporal localization. Due to the availability of several successful approaches for action recognition in trimmed video, conventional multi-stage methods for untrimmed video, commonly employ a network to generate activity proposals, followed by a separate network for classification. These disjoint networks are optimized individually and thus usually vary from the global optimum, leading to less precise candidate action proposals. To address this challenge, we propose a novel end-to-end neural network that utilizes error estimation for precise action localization and recognition in untrimmed videos. The proposed method performs the localization and classification of action instances simultaneously, thereby optimizing the corresponding networks concurrently. To increase the precision of the action proposal boundaries, the Regression module is innovatively utilized as part of the proposed end-to-end network, along with the Evaluation and Classification modules. This module estimates the potential error in proposal time boundaries and enhances the result accuracy. We have conducted experiments on THUMOS 14 and ActivityNet-1.3, which are considered the most challenging datasets for temporal action localization. The novel, yet fairly simple, proposed network achieves remarkable performance improvement compared to the other state-of-the-art methods. This improvement, which is more pronounced in the cases of high temporal intersection with ground truth, is accomplished without requiring extra data or complicated architecture. By incorporating error estimation, we achieved improvement in mean Average Precision (mAP). The proposed approach particularly shines for the localization of challenging activities in the complex and diverse dataset ActivityNet-1.3. For instance, for the “drinking coffee” activity, the mean Average Precision (mAP) was enhanced fivefold compared to the best-reported results.

Anomaly based multi-stage attack detection method.

Multi-stage attacks are one of the most critical security threats in the current cyberspace. To accurately identify multi-stage attacks, this paper proposes an anomaly-based multi-stage attack detection method. It constructs a Multi-Stage Profile (MSP) by modeling the stable system's normal state to detect attack behaviors. Initially, the method employs Doc2Vec to vectorize alert messages generated by the intrusion detection systems (IDS), extracting profound inter-message correlations. Subsequently, Hidden Markov Models (HMM) are employed to model the normal system state, constructing an MSP, with relevant HMM parameters dynamically acquired via clustering algorithms. Finally, the detection of attacks is achieved by determining the anomaly threshold through the generation probability (GP). To evaluate the performance of the proposed method, experiments were conducted using three public datasets and compared with three advanced multi-stage attack detection methods. The experimental results demonstrate that our method achieves an accuracy of over 99% and precision of 100% in multi-stage attack detection. This confirms the effectiveness of our method in adapting to different attack scenarios and ultimately completing attack detection.

Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although there are some works that employ open-source LLMs for the tool-learning task, most of them are trained in a controlled environment in which LLMs only learn to execute the human-provided tools. However, selecting proper tools from the large toolset is also a crucial ability for the tool-learning model to be applied in real-world applications. Existing methods usually directly employ self-instruction methods to train the model, which ignores differences in tool complexity. In this paper, we propose the Confucius a novel tool-learning framework to train LLM to use complicated tools in real-world scenarios, which contains two main phases: (1) We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum; (2) thenceforth, we propose the Iterative Self-instruct from Introspective Feedback (ISIF) to dynamically construct the dataset to improve the ability to use the complicated tool. Extensive experiments conducted on both controlled and real-world settings demonstrate the superiority of our tool-learning framework in the real-world application scenario compared to both tuning-free (e.g., ChatGPT, Claude) and tuning-based baselines (e.g., GPT4Tools).

Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation

Compared to conventional semantic segmentation with pixel-level supervision, weakly supervised semantic segmentation (WSSS) with image-level labels poses the challenge that it commonly focuses on the most discriminative regions, resulting in a disparity between weakly and fully supervision scenarios. A typical manifestation is the diminished precision on object boundaries, leading to deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into certain regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we propose an adaptive masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that confident regions should be robust enough to preserve the global semantics, and introduce a complementary self-distillation method that constrains semantic consistency between confident regions and an augmented view with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art counterparts but also surpasses multi-stage methods that trade complexity for accuracy.

On mathematical problems of two-coefficient inverse problems of ultrasonic tomography

This paper proves the theorem of uniqueness for the solution of a coefficient inverse problem for the wave equation in (with two unknown coefficients: speed of sound and absorption. The original nonlinear coefficient inverse problem is reduced to an equivalent system of two uniquely solvable linear integral equations of the first kind with respect to the sound speed and absorption coefficients. Estimates are made, substantiating the multistage method for two unknown coefficients. These estimates show that given sufficiently low frequencies and small inhomogeneities, the residual functional for the nonlinear inverse problem approaches a convex one. This solution method for nonlinear coefficient inverse problems is not linked to the limit approach as frequency tends to zero, but assumes solving the inverse problem using sufficiently low, but not zero, frequencies at the first stage. For small inhomogeneities that are typical, for instance, for medical tasks, carrying out real experiments at such frequencies does not present major difficulties. The capabilities of the method are demonstrated on a model inverse problem with unknown sound speed and absorption coefficients. The method effectively solves the nonlinear problem with parameter values typical for tomographic diagnostics of soft tissues in medicine. A resolution of approximately 2 mm was achieved using an average sounding pulse wavelength of 5 mm.

U-ETMVSNet: Uncertainty-Epipolar Transformer Multi-View Stereo Network for Object Stereo Reconstruction

The Multi-View Stereo model (MVS), which utilizes 2D images from multiple perspectives for 3D reconstruction, is a crucial technique in the field of 3D vision. To address the poor correlation between 2D features and 3D space in existing MVS models, as well as the high sampling rate required for static sampling, we proposeU-ETMVSNet in this paper. Initially, we employ an integrated epipolar transformer module (ET) to establish 3D spatial correlations along epipolar lines, thereby enhancing the reliability of aggregated cost volumes. Subsequently, we devise a sampling module based on probability volume uncertainty to dynamically adjust the depth sampling range for the next stage. Finally, we utilize a multi-stage joint learning method based on multi-depth value classification to evaluate and optimize the model. Experimental results demonstrate that on the DTU dataset, our method achieves a relative performance improvement of 27.01% and 11.27% in terms of completeness error and overall error, respectively, compared to CasMVSNet, even at lower depth sampling rates. Moreover, our method exhibits excellent performance with a score of 58.60 on the Tanks &Temples dataset, highlighting its robustness and generalization capability.

Towards clinically applicable automated mandibular canal segmentation on CBCT

ObjectivesTo develop a deep learning-based system for precise, robust, and fully automated segmentation of the mandibular canal on cone beam computed tomography (CBCT) images. MethodsThe system was developed on 536 CBCT scans (training set: 376, validation set: 80, testing set: 80) from one center and validated on an external dataset of 89 CBCT scans from 3 centers. Each scan was annotated using a multi-stage annotation method and refined by oral and maxillofacial radiologists. We proposed a three-step strategy for the mandibular canal segmentation: extraction of the region of interest based on 2D U-Net, global segmentation of the mandibular canal, and segmentation refinement based on 3D U-Net. ResultsThe system consistently achieved accurate mandibular canal segmentation in the internal set (Dice similarity coefficient [DSC], 0.952; intersection over union [IoU], 0.912; average symmetric surface distance [ASSD], 0.046 mm; 95% Hausdorff distance [HD95], 0.325 mm) and the external set (DSC, 0.960; IoU, 0.924; ASSD, 0.040 mm; HD95, 0.288 mm). ConclusionsThese results demonstrated the potential clinical application of this AI system in facilitating clinical workflows related to mandibular canal localization. Clinical significanceAccurate delineation of the mandibular canal on CBCT images is critical for implant placement, mandibular third molar extraction, and orthognathic surgery. This AI system enables accurate segmentation across different models, which could contribute to more efficient and precise dental automation systems.

Physical Activity Promotion in Schools Using Theoretically Designed Mobile Phone Application.

Regular physical activity for adolescents has many health benefits, many of which also affect adulthood. Physical activity is a behavior that requires planning and choosing an appropriate educational method, model, or theory. However, mobile phone applications are known as a suitable method to increase physical activity according to the guidelines. This study aims to increase physical activity in female students based on the theory of planned behavior using mobile phone applications. This quasi-experimental study was implemented on 220 high school students (110 people in each group). The samples were selected by a multi-stage cluster method and their information was collected by the International Physical Activity Questionnaire (IPAQ) and the Theory of Planned Behavior (TPB) questionnaire whose validity and reliability were confirmed. The intervention group received 8 sessions of education through a mobile phone application that was designed by the constructs of the theory of planned behavior. The samples were evaluated in three stages, through a pre-test, post-test, and two-month follow-up. The results showed a significant difference in the post-test and two months after the intervention between intervention and control groups in terms of attitude, perceived behavioral control, intention, and physical activity. There was a significant difference between intervention and control groups in subjective norms in the post-test, but there was no significant difference in the two-month follow-up compared to the post-test (P = 0.08). An educational intervention based on the theory of planned behavior using mobile phone applications led to an increase in the physical activity of girl high school students. However, to determine the full effectiveness of this study, it is recommended to implement this intervention in all schools.

On the Convergence of Multi-Stage Differential Transform Method

In many paper, Multi-stage Differential Transform Method (MsDTM) has been presented as a method to solve linear and nonlinear equations of various kinds. Multi-stage Differential Transform method has been used to find the exact or analytical approximate solution of the different problems. But only a few works have been considered of convergence of this method. In this paper, Convergence analysis of multi-stage differential transform method is presented. Some numerical examples are proposed to verify the convergence of the proposed method

An Evaluation of Projection Methods for Detailed Small Area Projections: An Application and Validation to King County, Washington.

Population projections are used by a number of local agencies to better prepare for the future resource needs of counties, ensuring that educational, health, housing, and economic demands of individuals are met. Meeting the specific needs of a county's population, such as what resources to provide, where to target resources, and ensure an equitable distribution of those resources, requires population projections which are both demographically detailed, such as by age, race, and ethnicity, and geographically precise, such as at the census tract level. Despite this need, an evaluation of which methods are best suited to produce population projections at this level are lacking. In this study, we evaluate the accuracy of several cohort-based methods for small area population projections by race and ethnicity. We apply these methods to population projections of King County, Washington and assess the validity of projections using past population estimates. We find a clear pattern that demonstrates while simplified methods perform well in near term forecasts, methods which employ smoothing strategies perform better in long-term forecasting scenarios. Furthermore, we demonstrate that model's incorporating multiple stages of smoothing can provide detailed insights into the projected population size of King county and the places and groups which will most contribute to this growth. Detailed projections, such as those provided by multi-stage smoothing methods, enable city planners and policy makers a detailed view of the future structure of their county's population and provide for them a resource to better meet the needs of future populations.

A machine learning driven automated system for safety data sheet indexing

Safety Data Sheets (SDS) are foundational to chemical management systems and are used in a wide variety of applications such as green chemistry, industrial hygiene, and regulatory compliance, among others within the Environment, Health, and Safety (EHS) and the Environment, Social, and Governance (ESG) domains. Companies usually prefer to have key pieces of information extracted from these datasheets and stored in an easy to access structured repository. This process is referred to as SDS “indexing”. Historically, SDS indexing has always been done manually, which is labor-intensive, time-consuming, and costly. In this paper, we present an automated system to index the composition information of chemical products from SDS documents using a multi-stage ensemble method with a combination of machine learning models and rule-based systems stacked one after the other. The system specifically indexes the ingredient names, their corresponding Chemical s Service (CAS) numbers, and weight percentages. It takes the SDS document in PDF format as the input and gives the list of ingredient names along with their corresponding CAS numbers and weight percentages in a tabular format as the output. The system achieves a precision of 0.93 at the document level when evaluated on 20,000 SDS documents annotated for this purpose.

Evaluation of Virtual Learning Environment using DELES questionnaire in Medical Students of Mashhad University of Medical Sciences

Introduction: The environment governing learning is one of the most important influencing factors in education. The outbreak of corona virus (COVID-19) has led to a special attention to E-learning as an aid to break the chain of virus transmission. This study was conducted to determine the status of the learning environment of virtual education of medical students of Mashhad University of Medical Sciences (MUMS) using DELES (The Distance Education Learning Environment Survey) questionnaire. Methods: This cross-sectional study was conducted in the academic year of 2022 at MUMS. Sampling was a multi-stage method. In this way, at first students in different educational levels (basic science, physiopathology, externship and internship) were considered. For gathering data DELES questionnaire was used. Then the link of the tool was shared in internet groups of medical students .Data were analyzed by T-test , ANOVA, Pearson correlation test through SPSS. In all tests p-value was less than or equal to 0.05. Results: A total of 202 medical students with an average age of 22.88±2.48 years were included in the study. The Mean response of participants studied the courses during the semester in the virtual environment was 49.78 ± 27.76 . The participants in the study reported the education situation to be relatively favorable, so that their satisfaction was more in the area of student independence (Relatively favorable) and less in the area of professors' support (poor). The results of the one-way ANOVA test showed that the average satisfaction score of basic science students is significantly higher than that of externship and internship students (P<0.001, F=7.861). Also, the results of the T-Student test showed that there is no statistically significant difference between students in terms of gender and marital status, but non-native students were less satisfied than native students in terms of interactions between students and colleagues (P < 0.03). Conclusion: The attitude of the students towards distance education during the covid-19 epidemic in medical students of MUMS was relatively favorable or relative satisfaction. Therefore, in order to improving the situation of distance education, it is recommended to implement methods to increase the support of professors and improve their communication with students in the virtual education environment.