Online Learning Behavior Analysis and Prediction Based on Spiking Neural Networks

The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of education.This study utilizes the historical and final learning behavior data of over 300000 learners from 17 courses offered on the edX platform by Harvard University and the Massachusetts Institute of Technology during the 2012-2013 academic year.We have developed a spike neural network to predict learning outcomes,and analyzed the correlation between learning behavior and outcomes,aiming to identify key learning behaviors that significantly impact these outcomes.Our goal is to monitor learning progress,provide targeted references for evaluating and improving learning effectiveness,and implement intervention measures promptly.Experimental results demonstrate that the prediction model based on online learning behavior using spiking neural network achieves an impressive accuracy of 99.80%.The learning behaviors that predominantly affect learning effectiveness are found to be students’academic performance and level of participation.

Distribution and origin of brine-type Li-Rb mineralization in the Qaidam Basin,NW China

The Qaidam Basin on the Qinghai-Tibet Plateau is well endowed with a variety of critical metals,such as Li and Rb.However,little is known about the distribution,source,and enrichment mechanisms of these elements.In this paper,we present results of systematic geochemical and H-O-B isotopic analyses of brines in the Tertiary and Quaternary sediments of the Qaidam basin.The results reveal that the paleobrines from oil-bearing anticlines at Dafengshan,Nanyishan,Youquanzi,Jiandingshan,and Jianshishan are significantly enriched in Li and Rb,whose contents are 81.1-128.9 mg L^(-1)and 4.5-29.2 mg L^(-1),respectively,reaching levels of economic significance.High Rb contents(up to 12.5 mg L^(-1))and well-endowment of Li also characterize the Dongtai,Xitai,Yiliping,and Senie salt lakes in the Qaidam Basin.The Tertiary paleobrine average inδD andδ18O at-40.7‰and 2.84‰,respectively.The paleobrine with the highest Li and Rb hasδD andδ^(18)O values close to magmatic water.Theδ^(11)B values are lower than those of river water but close to those of geothermal fluids,suggesting that replenishment by deep magmatic hydrothermal fluid is most likely the key mechanism for the anomalous enrichment of these elements in the paleobrines,though evaporation and water-rock reactions have contributed to the critical metal mineralization.The anomalous enrichment of Li and Rb in modern salt lake brines is closely related to the input of volcanic geothermal water.The relatively high Li and Rb contents of intercrystalline brines in salt lakes of the western Qaidam Basin and the increase of Li and Rb contents with increasing depth were caused by upwelling of local paleobrines along the fault zones.

Reworking of the Juvenile Crust in the Late Mesozoic in North Qinling,Central China

The Qinling Orogen resulted from the collision between the North and South China blocks in the Triassic.Mesozoic granitoids,ranging from the Triassic to the Cretaceous,are widely distributed in this orogen,and they provide excellent clues for understanding the crustal evolution and geodynamic evolution of the orogenic belt.The Triassic belt is mostly located in the South Qinling,whereas the Cretaceous belt is located mostly in the North Qinling.The Taibai complex pluton is located at the conjunction of the two belts.Here we present a data set comprising zircon U-Pb dating and elemental and Sr-Nd isotopic geochemistry for Late Mesozoic granite and microgranular enclaves(MME)exposed in the Taibai complex pluton.The granite and MME yield concordant U-Pb zircon ages of 124 to 118 Ma,indicating that they were products of roughly simultaneous magmatism in the Late Mesozoic.The granite rocks are high-K,calc-alkaline,and weakly peraluminous in compositions,and they are characterized by enrichment in large ion lithophile elements(e.g.,Rb,Ba),depletion in high field strength elements(e.g.,Nb,Ta,Zr,Ti),and variable Sr/Y ratios of 7.64 to 63.6.Low MgO,Cr,and Ni contents imply that the magma(s)were essentially crust-derived.Both the granite and the MME show relative depletion in Sr-Nd isotopic composition(initial ^(87)Sr/^(86)Sr of 0.7044 to 0.7067,initialε_(Nd) values of-3.4 to-2.6),suggesting that the magma(s)originated from juvenile crustal rocks.These Sr-Nd isotopic characteristics are significantly different from those of other Late Mesozoic granitoids exposed elsewhere in the Qinling orogenic belt,which formed from much older and enriched sources and with negligible contributions from mantle or juvenile crust.We propose a reworking event of the juvenile crust during the Late Mesozoic that was triggered by the tectonic extension and subsequent asthenospheric upwelling that occurred in eastern China.

Zircon U-Pb Ages and Magmatic History of the Kashan Plutons in the Central Urumieh-Dokhtar Magmatic Arc,Iran:Evidence for Neotethyan Subduction during Paleogene-Neogene

The Kashan plutons are situated in the central part of Urumieh-Dokhtar magmatic arc recording subduction-related magmatism within the Alpine-Himalayan orogeny in Iran.These rocks consist of different calc-alkaline plutonic rocks including gabbro,gabbroic diorite,microdiorite,monzodiorite,tonalite,granodiorite,and granite.The plutons were emplaced into the Jurassic sedimentary units(Shemshak Formation)and the Eocene calc-alkaline volcanic and pyroclastic rocks.New U-Pb zircon ages show that the Kashan plutons formed during two main periods at 35.20±0.71 Ma in the Late Eocene(Priabonian)and at 18.90±0.84,19.26±0.83,19.30±1.2,and 17.3±1.8 Ma in the Early Miocene(Burdigalian).The reported events in the Kashan plutons imply the final phases of subductionrelated magmatism before the collision which happened between the Arabian and Iranian plates in the Middle Miocene.The plutonic activity in the Kashan region occurred during the transition from Eocene subduction-related setting to Middle Miocene collisional setting.

DPTP-LICD:A differential privacy trajectory protection method based on latent interest community detection

With the rapid development of high-speed mobile network technology and high-precision positioning technology,the trajectory information of mobile users has received extensive attention from academia and industry in the field of Location-based Social Networks.Researchers can mine users’trajectories in Location-based Social Networks to obtain sensitive information,such as friendship groups,activity patterns,and consumption habits.Therefore,mobile users’privacy and security issues have received growing attention in Location-based Social networks.It is crucial to strike a balance between privacy protection and data availability.This paper proposes a differential privacy trajectory protection method based on latent interest community detection(DPTP-LICD),ensuring strict privacy protection standards and user data availability.Firstly,based on the historical trajectory information of users,spatiotemporal constraint information is extracted to construct a potential community strength model for mobile users.Secondly,the latent interest community obtained from the analysis is used to identify preferred hot spots on the user’s trajectory,and their priorities are assigned based on a popularity model.A reasonable privacy budget is allocated to prevent excessive noise from being added and rendering the protected trajectory data unusable.Finally,to prevent privacy leakage,we add Laplace and exponential noise in generating preferred hot spots and recommending user interest points.Security and effectiveness analysis shows that our mechanism provides effective points of interest recommendations and protects users’privacy from disclosure.