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.

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.

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.

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.

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.

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.

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.

Behavioral Intrusion Prediction Model on Bayesian Network over Healthcare Infrastructure

Due to polymorphic nature of malware attack,a signature-based analysis is no longer sufficient to solve polymorphic and stealth nature ofmalware attacks.On the other hand,state-of-the-art methods like deep learning require labelled dataset as a target to train a supervised model.This is unlikely to be the case in production network as the dataset is unstructured and has no label.Hence an unsupervised learning is recommended.Behavioral study is one of the techniques to elicit traffic pattern.However,studies have shown that existing behavioral intrusion detection model had a few issues which had been parameterized into its common characteristics,namely lack of prior information(p(θ)),and reduced parameters(θ).Therefore,this study aims to utilize the previously built Feature Selection Model subsequently to design a Predictive Analytics Model based on Bayesian Network used to improve the analysis prediction.Feature Selection Model is used to learn significant label as a target and Bayesian Network is a sophisticated probabilistic approach to predict intrusion.Finally,the results are extended to evaluate detection,accuracy and false alarm rate of the model against the subject matter expert model,Support Vector Machine(SVM),k nearest neighbor(k-NN)using simulated and ground-truth dataset.The ground-truth dataset from the production traffic of one of the largest healthcare provider in Malaysia is used to promote realism on the real use case scenario.Results have shown that the proposed model consistently outperformed other models.

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

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.

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.

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.

Eye-Tracking Based Autism Spectrum Disorder Diagnosis Using Chaotic Butterfly Optimization with Deep Learning Model

Autism spectrum disorder(ASD)can be defined as a neurodevelopmental condition or illness that can disturb kids who have heterogeneous characteristics,like changes in behavior,social disabilities,and difficulty communicating with others.Eye tracking(ET)has become a useful method to detect ASD.One vital aspect of moral erudition is the aptitude to have common visual attention.The eye-tracking approach offers valuable data regarding the visual behavior of children for accurate and early detection.Eye-tracking data can offer insightful information about the behavior and thought processes of people with ASD,but it is important to be aware of its limitations and to combine it with other types of data and assessment techniques to increase the precision of ASD detection.It operates by scanning the paths of eyes for extracting a series of eye projection points on images for examining the behavior of children with autism.The purpose of this research is to use deep learning to identify autistic disorders based on eye tracking.The Chaotic Butterfly Optimization technique is used to identify this specific disturbance.Therefore,this study develops an ET-based Autism Spectrum Disorder Diagnosis using Chaotic Butterfly Optimization with Deep Learning(ETASD-CBODL)technique.The presented ETASDCBODL technique mainly focuses on the recognition of ASD via the ET and DL models.To accomplish this,the ETASD-CBODL technique exploits the U-Net segmentation technique to recognize interested AREASS.In addition,the ETASD-CBODL technique employs Inception v3 feature extraction with CBO algorithm-based hyperparameter optimization.Finally,the long-shorttermmemory(LSTM)model is exploited for the recognition and classification of ASD.To assess the performance of the ETASD-CBODL technique,a series of simulations were performed on datasets from the figure-shared data repository.The experimental values of accuracy(99.29%),precision(98.78%),sensitivity(99.29%)and specificity(99.29%)showed a better performance in the ETASD-CBODL technique over recent approaches.

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%.

From beasts to bytes:Revolutionizing zoological research with artificial intelligence

Since the late 2010s,Artificial Intelligence(AI)including machine learning,boosted through deep learning,has boomed as a vital tool to leverage computer vision,natural language processing and speech recognition in revolutionizing zoological research.This review provides an overview of the primary tasks,core models,datasets,and applications of AI in zoological research,including animal classification,resource conservation,behavior,development,genetics and evolution,breeding and health,disease models,and paleontology.Additionally,we explore the challenges and future directions of integrating AI into this field.Based on numerous case studies,this review outlines various avenues for incorporating AI into zoological research and underscores its potential to enhance our understanding of the intricate relationships that exist within the animal kingdom.As we build a bridge between beast and byte realms,this review serves as a resource for envisioning novel AI applications in zoological research that have not yet been explored.

Visual Motion Segmentation in Crowd Videos Based on Spatial-Angular Stacked Sparse Autoencoders

Visual motion segmentation(VMS)is an important and key part of many intelligent crowd systems.It can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd stampedes and crashes,which pose a serious risk to public safety and have resulted in numerous fatalities over the past few decades.Trajectory clustering has become one of the most popular methods in VMS.However,complex data,such as a large number of samples and parameters,makes it difficult for trajectory clustering to work well with accurate motion segmentation results.This study introduces a spatial-angular stacked sparse autoencoder model(SA-SSAE)with l2-regularization and softmax,a powerful deep learning method for visual motion segmentation to cluster similar motion patterns that belong to the same cluster.The proposed model can extract meaningful high-level features using only spatial-angular features obtained from refined tracklets(a.k.a‘trajectories’).We adopt l2-regularization and sparsity regularization,which can learn sparse representations of features,to guarantee the sparsity of the autoencoders.We employ the softmax layer to map the data points into accurate cluster representations.One of the best advantages of the SA-SSAE framework is it can manage VMS even when individuals move around randomly.This framework helps cluster the motion patterns effectively with higher accuracy.We put forward a new dataset with itsmanual ground truth,including 21 crowd videos.Experiments conducted on two crowd benchmarks demonstrate that the proposed model can more accurately group trajectories than the traditional clustering approaches used in previous studies.The proposed SA-SSAE framework achieved a 0.11 improvement in accuracy and a 0.13 improvement in the F-measure compared with the best current method using the CUHK dataset.

Human neural stem cells promote proliferation of endogenous neural stem cells and enhance angiogenesis in ischemic rat brain

Transplantation of human neural stem cells into the dentate gyrus or ventricle of rodents has been reportedly to enhance neurogenesis. In this study, we examined endogenous stem cell proliferation and angiogenesis in the ischemic rat brain after the transplantation of human neural stem cells. Focal cerebral ischemia in the rat brain was induced by middle cerebral artery occlusion. Human neural stem cells were transplanted into the subventricular zone. The behavioral performance of human neural stem cells-treated ischemic rats was significantly improved and cerebral infarct volumes were reduced compared to those in untreated animals. Numerous transplanted human neural stem cells were alive and preferentially localized to the ipsilateral ischemic hemisphere. Furthermore, 5-bromo-2′-deoxyuridine-labeled endogenous neural stem cells were observed in the subventricular zone and hippocampus, where they differentiated into cells immunoreactive for the neural markers doublecortin, neuronal nuclear antigen Neu N, and astrocyte marker glial fibrillary acidic protein in human neural stem cells-treated rats, but not in the untreated ischemic animals. The number of 5-bromo-2′-deoxyuridine-positive ？ anti-von Willebrand factor-positive proliferating endothelial cells was higher in the ischemic boundary zone of human neural stem cells-treated rats than in controls. Finally, transplantation of human neural stem cells in the brains of rats with focal cerebral ischemia promoted the proliferation of endogenous neural stem cells and their differentiation into mature neural-like cells, and enhanced angiogenesis. This study provides valuable insights into the effect of human neural stem cell transplantation on focal cerebral ischemia, which can be applied to the development of an effective therapy for stroke.