Behavior analysis and formative assessments in online oral medicine education during the COVID-19 pandemic

BACKGROUND During the coronavirus disease 2019(COVID-19)pandemic,traditional teaching methods were disrupted and online teaching became a new topic in education reform and informatization.In this context,it is important to investigate the necessity and effectiveness of online teaching methods for medical students.This study explored stomatology education in China to evaluate the development and challenges facing the field using massive open online courses(MOOCs)for oral medicine education during the pandemic.AIM To investigate the current situation and challenges facing stomatology education in China,and to assess the necessity and effectiveness of online teaching methods among medical students.METHODS Online courses were developed and offered on personal computers and mobile terminals.Behavioral analysis and formative assessments were conducted to evaluate the learning status of students.RESULTS The results showed that most learners had already completed MOOCs and achieved better results.Course behavior analysis and student surveys indicated that students enjoyed the learning experience.However,the development of oral MOOCs during the COVID-19 pandemic faced significant challenges.CONCLUSION This study provides insights into the potential of using MOOCs to support online professional learning and future teaching innovation,but emphasizes the need for careful design and positive feedback to ensure their success.

An Event Alarm System Based on Single and Group Human Behavior Analysis

Due to the increasing demand for security, the development of intelligent surveillance systems has attracted considerable attention in recent years. This study aims to develop a system that is able to identify whether or not the people need help in a public place. Different from previous work, our work considers not only the behaviors of the target person but also the interaction between him and nearby people. In the paper, we propose an event alarm system which can detect the human behaviors and recognize the happening event through integrating the results generated from the single and group behavior analysis. Several new effective features are proposed in the study. Besides, a mechanism capable of extracting one-to-one and multiple-to-one relations is also developed. Experimental results show that the proposed approach can correctly detect human behaviors and provide the alarm messages when emergency events occur.

Digital Twin for Human-Robot Interactive Welding and Welder Behavior Analysis

This paper presents an innovative investigation on prototyping a digital twin(DT)as the platform for human-robot interactive welding and welder behavior analysis.This humanrobot interaction(HRI)working style helps to enhance human users'operational productivity and comfort;while data-driven welder behavior analysis benefits to further novice welder training.This HRI system includes three modules:1)a human user who demonstrates the welding operations offsite with her/his operations recorded by the motion-tracked handles;2)a robot that executes the demonstrated welding operations to complete the physical welding tasks onsite;3)a DT system that is developed based on virtual reality(VR)as a digital replica of the physical human-robot interactive welding environment.The DT system bridges a human user and robot through a bi-directional information flow:a)transmitting demonstrated welding operations in VR to the robot in the physical environment;b)displaying the physical welding scenes to human users in VR.Compared to existing DT systems reported in the literatures,the developed one provides better capability in engaging human users in interacting with welding scenes,through an augmented VR.To verify the effectiveness,six welders,skilled with certain manual welding training and unskilled without any training,tested the system by completing the same welding job;three skilled welders produce satisfied welded workpieces,while the other three unskilled do not.A data-driven approach as a combination of fast Fourier transform(FFT),principal component analysis(PCA),and support vector machine(SVM)is developed to analyze their behaviors.Given an operation sequence,i.e.,motion speed sequence of the welding torch,frequency features are firstly extracted by FFT and then reduced in dimension through PCA,which are finally routed into SVM for classification.The trained model demonstrates a 94.44%classification accuracy in the testing dataset.The successful pattern recognition in skilled welder operations should benefit to accelerate novice welder training.

Brain Storm Optimization Based Clustering for Learning Behavior Analysis

Recently,online learning platforms have proven to help people gain knowledge more conveniently.Since the outbreak of COVID-19 in 2020,online learning has become a mainstream mode,as many schools have adopted its format.The platforms are able to capture substantial data relating to the students’learning activities,which could be analyzed to determine relationships between learning behaviors and study habits.As such,an intelligent analysis method is needed to process efficiently this high volume of information.Clustering is an effect data mining method which discover data distribution and hidden characteristic from uncharacterized online learning data.This study proposes a clustering algorithm based on brain storm optimization(CBSO)to categorize students according to their learning behaviors and determine their characteristics.This enables teaching to be tailored to taken into account those results,thereby,improving the education quality over time.Specifically,we use the individual of CBSO to represent the distribution of students and find the optimal one by the operations of convergence and divergence.The experiments are performed on the 104 students’online learning data,and the results show that CBSO is feasible and efficient.

DYNAMIC BEHAVIOR ANALYSIS OF VISCOELASTICALLY DAMPED STRUCTURES

Analysis method for the dynamic behavior of viscoelastically damped structures isstudied.A finite element model of sandwich beams with eight degrees of freedom is set upand the finite element formulation of the equations of motion is given for theviscoelastically damped structures.An iteration method for solving nonlinear eigenvalueproblems is suggested to analyze the dynamic behavior of viscoelastically damped structures.The method has been applied to the complex model analysis of a sandwich cantileverbeam with viscoelastic damping material core.

Bibliometric study and critical individual literature review of driving behavior analysis methods based on brain imaging from 1993 to 2022

Brain imaging methods have effectively revealed drivers’underlying psychological and neural processes when they perform driving tasks and promote driving behavior research in a more scientific direction.With research no longer limited to indirect inferences about external behavior,some researchers combine behavior and driver brain activity to understand the human factors in driving essentially.However,most researchers in the field of driving behavior still have little understanding of how brain imaging methods are used.This paper aims to review and analyze the application of brain imaging methods in driving behavior research,including bibliometric analysis and an individual critical literature review.Regarding bibliometric analysis,this field’s knowledge structure and development trend are described macroscopically,using data such as annual distribution of publications,country/region statistics and partnerships,publication sources,literature co-citation analysis,and keyword co-occurrence analysis.In a review of the individual critical literature,eight research themes were identified that examined driving behavior using brain imaging methods:substance consumption,fatigue or sleep deprivation,workload,distraction,aging brains,brain impairment and other diseases,automated/semi-automated environments,emotions influence and risk-taking,and general driving process.In addition,the study reports on six brain imaging methods and their advantages and disadvantages,involving electroencephalography(EEG),functional magnetic resonance imaging(fMRI),functional near-infrared spectroscopy(fNIRS),magnetoencephalography(MEG),positron emission tomography(PET),and transcranial magnetic stimulation(TMS).The contribution of this study is twofold.The first part relates to providing the researchers with a comprehensive understanding of the field’s knowledge structure and development trends.The second part goes beyond reviewing and analyzing previous studies,and the discussion section points out the directions and challenges for future research.

Transformer-Aided Deep Double Dueling Spatial-Temporal Q-Network for Spatial Crowdsourcing Analysis

With the rapid development ofmobile Internet,spatial crowdsourcing has becomemore andmore popular.Spatial crowdsourcing consists of many different types of applications,such as spatial crowd-sensing services.In terms of spatial crowd-sensing,it collects and analyzes traffic sensing data from clients like vehicles and traffic lights to construct intelligent traffic prediction models.Besides collecting sensing data,spatial crowdsourcing also includes spatial delivery services like DiDi and Uber.Appropriate task assignment and worker selection dominate the service quality for spatial crowdsourcing applications.Previous research conducted task assignments via traditional matching approaches or using simple network models.However,advanced mining methods are lacking to explore the relationship between workers,task publishers,and the spatio-temporal attributes in tasks.Therefore,in this paper,we propose a Deep Double Dueling Spatial-temporal Q Network(D3SQN)to adaptively learn the spatialtemporal relationship between task,task publishers,and workers in a dynamic environment to achieve optimal allocation.Specifically,D3SQNis revised through reinforcement learning by adding a spatial-temporal transformer that can estimate the expected state values and action advantages so as to improve the accuracy of task assignments.Extensive experiments are conducted over real data collected fromDiDi and ELM,and the simulation results verify the effectiveness of our proposed models.

User Profile & Attitude Analysis Based on Unstructured Social Media and Online Activity

As social media and online activity continue to pervade all age groups, it serves as a crucial platform for sharing personal experiences and opinions as well as information about attitudes and preferences for certain interests or purchases. This generates a wealth of behavioral data, which, while invaluable to businesses, researchers, policymakers, and the cybersecurity sector, presents significant challenges due to its unstructured nature. Existing tools for analyzing this data often lack the capability to effectively retrieve and process it comprehensively. This paper addresses the need for an advanced analytical tool that ethically and legally collects and analyzes social media data and online activity logs, constructing detailed and structured user profiles. It reviews current solutions, highlights their limitations, and introduces a new approach, the Advanced Social Analyzer (ASAN), that bridges these gaps. The proposed solutions technical aspects, implementation, and evaluation are discussed, with results compared to existing methodologies. The paper concludes by suggesting future research directions to further enhance the utility and effectiveness of social media data analysis.

Abnormal Crowd Behavior Detection Using Optimized Pyramidal Lucas-Kanade Technique

Abnormal behavior detection is challenging and one of the growing research areas in computer vision.The main aim of this research work is to focus on panic and escape behavior detections that occur during unexpected/uncertain events.In this work,Pyramidal Lucas Kanade algorithm is optimized using EME-HOs to achieve the objective.First stage,OPLKT-EMEHOs algorithm is used to generate the opticalflow from MIIs.Second stage,the MIIs opticalflow is applied as input to 3 layer CNN for detect the abnormal crowd behavior.University of Minnesota(UMN)dataset is used to evaluate the proposed system.The experi-mental result shows that the proposed method provides better classification accu-racy by comparing with the existing methods.Proposed method provides 95.78%of precision,90.67%of recall,93.09%of f-measure and accuracy with 91.67%.

Implementation of Online Teaching Behavior Analysis System

Online teaching is gradually spreading widely,but there are problems in online teaching evaluation,such as lack of reference index,students’learning state feedback being hard to get in real-time.To improve online teaching quality and evaluation,a classroom behavior analysis and evaluation system based on deep learning face recognition technology is proposed.This system conducts the model training and tests on the deep learning development framework(TensorFlow).It implements the frame image processing through the Mask R-CNN network,extracts the skeleton and the angle direction information to establish the vector,thus carries out the classroom behavior recognition and analysis,and serves as the appraisal important index.The behavior analysis is made and the results show that the recognition rate is high and the learning situation feedback is given in real time.The experiment shows that the system has certain robustness and high accuracy in the real scene.It is convenient for classroom teaching management and implementation,and is helpful to improve the teaching quality.

Analysis and Guiding Strategy of Female College Students' Behaviors in the Webcast

With the rise of live webcasts,the phenomenon of female college students'live webcasts is worthy of attention.According to the present situation,female college students'behaviors of the live webcast are different because of the difference in subject attributes,and they have higher cognition degrees due to the effect of advertisement implantation.Thanks to the convenient means of live broadcast,the diversity of the motive of live broadcast,and the multi-dimensional content,they have higher participation.There are many hidden dangers because of weak supervision and management.The main problems are as follows:the content has a vulgar tendency,public opinion has out-of-control risk,competition has hidden violence,supervision has a“Vacuum zone”.To strengthen the education and guidance of female college students'live webcast behaviors,we should adhere to the valuable guidance and set up the correct network values.Meanwhile,we also need to strengthen the guidance of public opinions,purify the field of live broadcast public opinion,and improve media literacy to establish an excellent concept of network security,strengthen network supervision,and build a perfect system of live broadcast rules.

Android Vault Application Behavior Analysis and Detection

With the widespread application of Android smartphones,privacy protection plays a crucial role.Android vault application provides content hiding on personal terminals to protect user privacy.However,some vault applications do not achieve real privacy protection,and its camouflage ability can be maliciously used to hide illegal information to avoid forensics.In order to solve these two issues,behavior analysis is conducted to compare three aspects of typical vaults in the third-party market.The conclusions and recommendations were given.Support Vector Machine(SVM)was used to distinguish vault from normal applications.Extensive experiments show that SVM can achieve 93.33%classification accuracy rate.

User Behavior Path Analysis Based on Sales Data

With the rapid development of science and technology and the increasing popularity of the Internet,the number of network users is gradually expanding,and the behavior of network users is becoming more and more complex.Users’actual demand for resources on the network application platform is closely related to their historical behavior records.Therefore,it is very important to analyze the user behavior path conversion rate.Therefore,this paper analyses and studies user behavior path based on sales data.Through analyzing the user quality of the website as well as the user’s repurchase rate,repurchase rate and retention rate in the website,we can get some user habits and use the data to guide the website optimization.

The Numerical Analysis of Strain Behavior at Solder Joint and Interface of Flip Chip Package

The flip chip package is a kind of advanced electri ca l packages. Due to the requirement of miniaturization, lower weight, higher dens ity and higher performance in the advanced electric package, it is expected that flip chip package will soon be a mainstream technology. The silicon chip is dir ectly connected to printing circuit substrate by SnPb solder joints. Also, the u nderfill, a composite of polymer and silica particles, is filled in the gap betw een the chip and substrate around the solder joints to improve the reliabili ty of solder joints. When flip chip package specimen is tested with thermal cycl ing, the cyclic stress/strain response that exists at the underfill interfaces and solder joints may result in interfacial crack initiation and propagation. Therefore, the chip cracking and the interfacial delamination between underfill and chip corner have been investigated in many studies. Also, most researches h ave focused on the effect of fatigue and creep properties of solder joint induce d by the plastic strain alternation and accumulation. The nuderfill must have lo w viscosity in the liquid state and good adhesion to the interface after solidif ying. Also, the mechanical behavior of such epoxy material has much dependen ce on temperature in its glass transition temperature range that is usually cove red by the temperature range of thermal cycling test. Therefore, the materia l behavior of underfill exists a significant non-linearity and the assumption o f linear elastic can lack for accuracy in numerical analysis. Through numerical analysis, this study had some comparisons about the effect of linear and non -linear properties of underfill on strain behaviors around the interface of fli p chip assembly. Especially, the deformation tendency inside solder bumps could be predicted. Also, it is worthily mentioned that we have pointed out which comp onent of plastic strain, thus, either normal or shear, has dominant influence to the fatigue and creep of solder bump, which have not brought up before. About the numerical analysis to the thermal plastic strain occurs in flip chip i nterconnection during thermal cycling test, a commercial finite element software , namely, ANSYS, was employed to simulate the thermal cycling test obeyed by MIL-STD-883C. The temperatures of thermal cycling ranged from -55 ℃ to 125 ℃ with ramp rate of 36 ℃/min and a dwell time of 25 min at peak temperature. T he schematic drawing of diagonal cross-section of flip chip package composed of FR-4 substrate, silicon chip, underfill and solder bump was shown as Fig.1. Th e numerical model was two-dimensional (2-D) with plane strain assumption and o nly one half of the cross-section was modeled due to geometry symmetry. The dim ensions and boundary conditions of numerical model were shown in Fig.2. The symm etric boundary conditions were applied along the left edge of the model, and the left bottom corner was additional constrained in vertical direction to prevent body motion. The finite element meshes of overall and local numerical model was shown as Fig.3. In this study, two cases of material model were used to describe the material behavior of the underfill: the case1 was linear elastic model that assumed Young’s Modulus (E) and thermal expansion coefficient (CTE) were consta nt during thermal cycling; the case2 was MKIN model (in ANSYS) that had nonlinea r temperature-dependent stress-strain relationship and temperature-dependent CTE. The material model applied to the solder bump was ANAND model (in ANSYS) th at described time-dependent plasticity phenomenon of viscoplastic material. Bot h the FR-4 substrate and silicon chip were assumed as temperature-independent elastic material; moreover, FR-4 substrate is orthotropic while silicon chip is isotropic. From the comparison between numerical results of linear and nonlinear material a ssumption of underfill, (i.e. case1 and case2), the quantities of plastic strain around the interconnection from case1 are higher than that in case2. Thus, the linear

Effect of Huanglian Jiedu Decoction on the Behavior of Zebrafish with Alzheimer's Disease

[Objectives]To study the effect of Huanglian Jiedu Decoction on the behavior of zebrafish with Alzheimer's disease caused by AlCl 3.[Methods]Each portion of Huanglian Jiedu Decoction was prepared according to the proportion of Coptis chinensis∶Phellodendron chinense Rupr.∶Scutellaria baicalensis Georgi∶Gardenia jasminoides Ellis=63 g∶42 g∶42 g∶63 g.After that,each portion of Huanglian Jiedu Decoction was soaked in 6.3 L water for 30 min and boiled twice at 100℃.The extracts were combined twice and filtered,then concentrated to 308 g/L and put into refrigerator for later use.Before training,zebrafishes were put into T-maze to adapt for 2 d,and then behavioral training was carried out for 7 d.After video recording,the behavior of zebrafish was analyzed by Smart 3.0,and qualified zebrafishes were selected for follow-up experiments.Then 60 successfully trained zebrafishes were randomly divided into control group,model group,positive group,low-dose group,medium-dose group and high-dose group of Huanglian Jiedu Decoction.Except for the control group,all the other groups were exposed to 100μg/L AlCl 3 for 7 d.After that,video was recorded,and behavioral analysis was carried out with behavioral record and analysis software Smart 3.0.And then the zebrafishes in the other four groups except the model group were treated with Huperzine A(4μg/L)and Huanglian Jiedu Decoction(154,308,616 mg/L)for 6 d,respectively.After that,it was recorded and the behavior of each group was analyzed.[Results]There was a significant difference in the time spent in the left area and the percentage of time in the left area between the control group and the model group(P<0.001).The time spent in the left area and the percentage of time in the left area in the model group and positive group,low,medium and high dose groups of Huanglian Jiedu Decoction decreased significantly(P<0.05,P<0.01,P<0.001).The swimming distance in the left area and the percentage of swimming distance in the left area in the model group were significantly higher than those in the control group(P<0.001).There was a significant difference in swimming distance between model group and positive group,low,medium and high dose groups of Huanglian Jiedu Decoction(P<0.01,P<0.001).In the percentage of swimming distance in the left area,there was a significant difference between the model group and the low and high dose groups of Huanglian Jiedu Decoction(P<0.01,P<0.001).[Conclusions]Huanglian Jiedu Decoction can improve the behavior of zebrafish with Alzheimer's disease.

Outlier Behavior Detection for Indoor Environment Based on t-SNE Clustering

In this study,we propose a low-cost system that can detect the space outlier utilization of residents in an indoor environment.We focus on the users’app usage to analyze unusual behavior,especially in indoor spaces.This is reflected in the behavioral analysis in that the frequency of using smartphones in personal spaces has recently increased.Our system facilitates autonomous data collection from mobile app logs and Google app servers and generates a high-dimensional dataset that can detect outlier behaviors.The density-based spatial clustering of applications with noise(DBSCAN)algorithm was applied for effective singular movement analysis.To analyze high-level mobile phone usage,the t-distributed stochastic neighbor embedding(t-SNE)algorithm was employed.These two clustering algorithms can effectively detect outlier behaviors in terms of movement and app usage in indoor spaces.The experimental results showed that our system enables effective spatial behavioral analysis at a low cost when applied to logs collected in actual living spaces.Moreover,large volumes of data required for outlier detection can be easily acquired.The system can automatically detect the unusual behavior of a user in an indoor space.In particular,this study aims to reflect the recent trend of the increasing use of smartphones in indoor spaces to the behavioral analysis.

Game Outlier Behavior Detection System Based on Dynamic Time Warp Algorithm

This paper proposes a methodology for using multi-modal data in gameplay to detect outlier behavior.The proposedmethodology collects,synchronizes,and quantifies time-series data fromwebcams,mouses,and keyboards.Facial expressions are varied on a one-dimensional pleasure axis,and changes in expression in the mouth and eye areas are detected separately.Furthermore,the keyboard and mouse input frequencies are tracked to determine the interaction intensity of users.Then,we apply a dynamic time warp algorithm to detect outlier behavior.The detected outlier behavior graph patterns were the play patterns that the game designer did not intend or play patterns that differed greatly from those of other users.These outlier patterns can provide game designers with feedback on the actual play experiences of users of the game.Our results can be applied to the game industry as game user experience analysis,enabling a quantitative evaluation of the excitement of a game.

Empirically supported psychological treatments:The challenges of comorbid psychiatric and behavioral disorders in people with intellectual disability

This paper reviews the current state of knowledge on psychological interventions with empirical evidence of efficacy in treating common psychiatric and behavioral disorders in people with intellectual disability(ID)at all stages of their life.We begin with a brief presentation of what is meant by psychiatric and behavioral disorders in this population,along with an explanation of some of the factors that contribute to the increased psychosocial vulnerability of this group to present with these problems.We then conduct a review of empirically supported psychological therapies used to treat psychiatric and behavioral disorders in people with ID.The review is structured around the three generations of therapies:Applied behavior analysis(e.g.,positive behavior support),cognitive behavioral therapies(e.g.,mindfulness-based cognitive therapy),and contextual therapies(e.g.,dialectical behavior therapy).We conclude with some recommendations for professional practice in the fields of ID and psychiatry.

Impact Analysis of Fluid-structure Coupling Embedded Weapon Bay

The coupling behavior of the imbedded weapon store occurring between the local unsteady flow field round the store and the structure response on the processing of opening its bay-door is simulated by using numerical method based on computational fluid mechanics(CFD).The transient aerodynamic behaviors when opening door under various flight altitudes and the corresponding structure deformation evolution in the unsteady flow fields are analyzed respectively and presented.The rules of aircraft attitude parameters′impacting to the responses of structure and the bay-door′s opening process are obtained by comparing with the analysis results.These rules can be applied to the structure design of bay-door and route specification of missile when disengaged and launched from within store.