检索结果-南通市图书馆

Efficient Intelligent E-Learning Behavior-Based Analytics of Student’s Performance Using Deep Forest Model

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2024年第5期48卷 1133-1147页

作者： Raed Alotaibi Omar Reyad Mohamed Esmail Karar applied College Shaqra UniversityP.O.Box 33Shaqra11961Saudi Arabia College of computing and Information Technology Shaqra UniversityP.O.Box 33Shaqra11961Saudi Arabia Faculty of Computers and Artificial Intelligence Sohag UniversitySohag82524Egypt Faculty of Electronic Engineering Menoufia UniversityMenouf32952Egypt

E-learning behavior data indicates several students’activities on the e-learning platform such as the number of accesses to a set of resources and number of participants in *** article proposes a new analytics systemto support academic evaluation for students via e-learning activities to overcome the challenges faced by traditional learning *** proposed e-learning analytics system includes a new deep forest *** consists of multistage cascade random forests with minimal hyperparameters compared to traditional deep neural *** developed forest model can analyze each student’s activities during the use of an e-learning platform to give accurate expectations of the student’s performance before ending the semester and/or the final *** have been conducted on the Open University Learning Analytics Dataset(OULAD)of 32,593 *** proposed deep model showed a competitive accuracy score of 98.0%compared to artificial intelligence-based models,such as ConvolutionalNeuralNetwork(CNN)and Long Short-TermMemory(LSTM)in previous *** allows academic advisors to support expected failed students significantly and improve their academic level at the right ***,the proposed analytics system can enhance the quality of educational services for students in an innovative e-learning framework.

关键词： E-learning behavior data student evaluation artificial intelligence machine learning

Atomically dispersed Fe sites on hierarchically porous carbon nanoplates for oxygen reduction reaction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第3期90卷 7-15,I0002页

作者： Ruixue Zheng Qinglei Meng Hao Zhang Teng Li Di Yang Li Zhang Xiaolong Jia Changpeng Liu Jianbing Zhu Xiaozheng Duan Meiling Xiao Wei Xing State Key Laboratory of Electroanalytical Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022JilinChina School of applied Chemistry and Engineering University of Science and Technology of ChinaHefei 230026AnhuiChina Laboratory of Advanced Power Sources Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022JilinChina Institute of Functional Nano&Soft Materials(FUNSOM) Jiangsu Key Laboratory for Carbon-Based Functional Materials&DevicesJiangsu Key Laboratory of Advanced Negative Carbon TechnologiesSoochow UniversitySuzhou 215123JiangsuChina State Key Laboratory of Polymer Physics and Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022JilinChina

Developing cost-effective,robust and stable non-precious metal catalysts for oxygen reduction reaction(ORR) is of paramount importance for electrochemical energy conversion devices such as fuel cells and metal-air *** Fe-N-C single atom catalysts(SACs) have been hailed as the most promising candidate due to the optimal binding strength of ORR intermediates on the Fe-N_(4) sites,they suffer from serious mass transport limitations as microporous templates/substrates,i.e.,zeolitic imidazolate frameworks(ZIFs),are usually employed to host the active *** by this challenge,we herein develop a hydrogen-bonded organic framework(HOF)-assisted pyrolysis strategy to construct hierarchical micro/mesoporous carbon nanoplates for the deposition of atomically dispersed Fe-N_(4) *** a design is accomplished by employing HOF nanoplates assembled from 2-aminoterephthalic acid(NH_(2)-BDC) and p-phenylenediamine(PDA) as both soft templates and C,N *** from the structural merits inherited from HOF templates,the optimized catalyst(denoted as Fe-N-C SAC-950) displays outstanding ORR activity with a high half-wave potential of 0.895 V(*** hydrogen electrode(RHE)) and a small overpotential of 356 mV at 10 mA cm^(-2) for the oxygen evolution reaction(OER).More excitingly,its application potential is further verified by delivering superb rechargeability and cycling stability with a nearly unfading charge-discharge gap of 0.72 V after 160 *** dynamics(MD) simulations reveal that micro/mesoporous structure is conducive to the rapid mass transfer of O_(2),thus enhancing the ORR *** situ Raman results further indicate that the conversion of O_(2) to~*O_(2)-the rate-determining step(RDS) for Fe-N-C *** work will provide a versatile strategy to construct single atom catalysts with desirable catalytic properties.

关键词： Fe single atom catalysts Oxygen reduction reaction Mesoporous structure Active sites Zinc-air battery

ＲＥＧＵＬＡＲＩＴＹＲＥＳＵＬＴＳＦＯＲＬＩＮＥＡＲＥＬＬＩＰＴＩＣＰＲＯＢＬＥＭＳＲＥＬＡＴＥＤＴＯＴＨＥＰＲＩＭＩＴＩＶＥＥＱＵＡＴＩＯＮＳ

在线全文

学校读者我要写书评

暂无评论

Chinese Annals of Mathematics,Series B 2002年第2期23卷 277-292页

作者： HU CHANGBING R.TEMAM M.ZIANE The TheDepartment of MathematicsUniversity of SouthernCalifornia Institute for Scientific Computing & Applied MathematicsIndiana Univ

The authors study the regularity of soutions of the GFD-Stokes problem and of some second order linear elliptic partial differential equations related to the PrimitiveEquations of the ocean .The present work generallizes the regularity results in[18] by taking into consideraion the non- homogeneous boundary conditions and teh dependence of solutions on the thickness of the domain occupied by the ocean and its varying bottom topography. These regularity results are important tools in the study of the PEs(see e.g.[6]), and they seem also to possess their own interest.

关键词： Primitive equations of the ocean Oceanograhy GFD Stokes problem Non-smooth domains

AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第2期39卷 401-420页

作者：龚成卢冶代素蓉邓倩杜承昆李涛 College of Software Nankai UniversityTianjin 300350China College of Computer Science Nankai UniversityTianjin 300350China State Key Laboratory of Processors Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China

Exploring the expected quantizing scheme with suitable mixed-precision policy is the key to compress deep neural networks(DNNs)in high efficiency and *** exploration implies heavy workloads for domain experts,and an automatic compression method is ***,the huge search space of the automatic method introduces plenty of computing budgets that make the automatic process challenging to be applied in real *** this paper,we propose an end-to-end framework named AutoQNN,for automatically quantizing different layers utilizing different schemes and bitwidths without any human *** can seek desirable quantizing schemes and mixed-precision policies for mainstream DNN models efficiently by involving three techniques:quantizing scheme search(QSS),quantizing precision learning(QPL),and quantized architecture generation(QAG).QSS introduces five quantizing schemes and defines three new schemes as a candidate set for scheme search,and then uses the Differentiable Neural Architecture Search(DNAS)algorithm to seek the layer-or model-desired scheme from the *** is the first method to learn mixed-precision policies by reparameterizing the bitwidths of quantizing schemes,to the best of our *** optimizes both classification loss and precision loss of DNNs efficiently and obtains the relatively optimal mixed-precision model within limited model size and memory *** is designed to convert arbitrary architectures into corresponding quantized ones without manual intervention,to facilitate end-to-end neural network *** have implemented AutoQNN and integrated it into *** experiments demonstrate that AutoQNN can consistently outperform state-of-the-art *** 2-bit weight and activation of AlexNet and ResNet18,AutoQNN can achieve the accuracy results of 59.75%and 68.86%,respectively,and obtain accuracy improvements by up to 1.65%and 1.74%,respectively,compared with state-of-the-art ***,c

关键词： automatic quantization mixed precision quantizing scheme search quantizing precision learning quan-tized architecture generation

Towards optimized tensor code generation for deep learning on sunway many-core processor

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

Stable ultraviolet ultrafast laser based on all-polarizationmaintaining fiber femtosecond laser

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第3期22卷 76-82页

作者：田昊朱喆林巍李子豪温俊鹏修昊范怡衡韦池一韦小明杨中民 School of Physics and Optoelectronics/State Key Laboratory of Luminescent Materials and Devices Guangdong Engineering Technology Research and Development Center of Special Optical Fiber Materials and DevicesGuangdong Provincial Key Laboratory of Fiber Laser Materials and Applied TechniquesSouth China University of TechnologyGuangzhou 510640China Research Institute of Future Technology South China Normal UniversityGuangzhou 510006China

We report a high-stability ultrafast ultraviolet(UV)laser source at 352 nm by exploring an all-fiber,all-polarizationmaintaining(all-PM),Yb-doped femtosecond fiber laser at 1060 *** output power,pulse width,and optical spectrum width of the fiber laser are 6 W,244 fs,and 17.5 nm,*** UV ultrashort pulses at a repetition rate of 28.9 MHz are generated by leveraging single-pass second-harmonic generation in a 1.3-mm-long BiB_(3)O_(6)(BIBO)and sum frequency generation in a 5.1-mm-long *** maximum UV output power is 596 *** root mean square error of the output power of UV pulses is 0.54%.This laser,with promising stability,is expected to be a nice source for frontier applications in the UV wavelength window.

关键词： all-polarization-maintaining fiber ultrafast fiber laser UV laser

Effect of coil and chamber structure on plasma radial uniformity in radio frequency inductively coupled plasma

在线全文

学校读者我要写书评

暂无评论

Plasma Science and Technology 2024年第7期26卷 58-66页

作者：赵洋周晓华高升荣宋莎莎赵玉真 Shaanxi International Joint Research center for applied Technology of Controllable Neutron Source Xijing UniversityXi’an 710123People’s Republic of China Technological Institute of Materials&Energy Science(TIMES) Xi’an Key Laboratory of Advanced Photo-electronics Materials and Energy Conversion DeviceSchool of Electronic InformationXijing UniversityXi’an 710123People’s Republic of China

Enhancing plasma uniformity can be achieved by modifying coil and chamber structures in radio frequency inductively coupled plasma(ICP)to meet the demand for large-area and uniformly distributed plasma in industrial *** study utilized a two-dimensional self-consistent fluid model to investigate how different coil configurations and chamber aspect ratios affect the radial uniformity of plasma in radio frequency *** findings indicate that optimizing the radial spacing of the coil enhances plasma uniformity but with a reduction in electron ***,optimizing the coil within the ICP reactor,using the interior point method in the Interior Point Optimizer significantly enhances plasma uniformity,elevating it from 56%to 96%within the range of the model ***,when the chamber aspect ratio k changes from 2.8 to 4.7,the plasma distribution changes from a center-high to a saddleshaped ***,the plasma uniformity becomes ***,adjusting process parameters,such as increasing source power and gas pressure,can enhance plasma *** findings contribute to optimizing the etching process by improving plasma radial uniformity.

关键词： inductively coupled plasma fluid simulation optimized coil chamber aspect ratio plasma uniformity

Continuity of the optimal value function and optimal solutions of parametric mixed-integer quadratic programs

在线全文

学校读者我要写书评

暂无评论

applied Mathematics(A Journal of Chinese Universities) 2010年第4期25卷 391-399页

作者： CHEN Zhi-ping HAN You-pan Department of scientific computing and applied Software, Faculty of Science, Xi’an Jiaotong University, Xi’an 710049, China Department of scientific computing and applied Software Faculty of Science Xi’an Jiaotong University Xi’an China

To properly describe and solve complex decision problems, research on theoretical properties and solution of mixed-integer quadratic programs is becoming very important. We establish in this paper different Lipschitz-type continuity results about the optimal value function and optimal solutions of mixed-integer parametric quadratic programs with parameters in the linear part of the objective function and in the right-hand sides of the linear constraints. The obtained results extend some existing results for continuous quadratic programs, and, more importantly, lay the foundation for further theoretical study and corresponding algorithm analysis on mixed-integer quadratic programs.

关键词： Mixed-integer quadratic program optimal value function optimal solution.

IoT Smart Devices Risk Assessment Model Using Fuzzy Logic and PSO

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2245-2267页

作者： Ashraf S.Mashaleh Noor Farizah Binti Ibrahim Mohammad Alauthman Mohammad Almseidin Amjad Gawanmeh School of Computer Sciences Universiti Sains MalaysiaPenangMalaysia Department Computer center Al-Balqa Applied UniversitySaltJordan Department of Information Security Faculty of Information TechnologyUniversity of PetraAmmanJordan Department of Computer Science Tafila Technical UniversityTafilaJordan College of Engineering and IT University of DubaiDubaiUnited Arab Emirates

Increasing Internet of Things(IoT)device connectivity makes botnet attacks more dangerous,carrying catastrophic *** IoT botnets evolve,their dynamic and multifaceted nature hampers conventional detection *** paper proposes a risk assessment framework based on fuzzy logic and Particle Swarm Optimization(PSO)to address the risks associated with IoT *** logic addresses IoT threat uncertainties and ambiguities *** component settings are optimized using PSO to improve *** methodology allows for more complex thinking by transitioning from binary to continuous *** of expert inputs,PSO data-driven tunes rules and membership *** study presents a complete IoT botnet risk assessment *** methodology helps security teams allocate resources by categorizing threats as high,medium,or low *** study shows how CICIoT2023 can assess cyber *** research has implications beyond detection,as it provides a proactive approach to risk management and promotes the development of more secure IoT environments.

关键词： IoT botnet detection risk assessment fuzzy logic particle swarm optimization(PSO) cybersecurity interconnected devices