检索结果-内蒙古大学图书馆

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Gunawan, Fergianto E. Budiman, Arief S. Pardamean, Bens Juana, Endang Romeli, Sugiarto Cenggoro, Tjeng W. Purwandari, Kartika Hidayat, Alam A. Redi, Anak A.N.P. Asrol, Muhammad Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia PT Impack Pratama Industri Jakarta14350 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

An accurate predictive model of temperature and humidity plays a vital role in many industrial processes that utilize a closed space such as in agriculture and building management. With the exceptional performance of deep learning on time-series data, developing a predictive temperature and humidity model with deep learning is propitious. In this study, we demonstrated that deep learning models with multivariate time-series data produce remarkable performance for temperature and relative humidity prediction in a closed space. In detail, all deep learning models that we developed in this study achieve almost perfect performance with an R value over 0.99. © 2023 The Authors. Published by Elsevier B.V.

关键词： closed space deep learning humity prediction indoor temperature prediction

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Satellite Videos Using Diffusion Models

Anomaly Detection in Satellite Videos Using Diffusion Models

引用

IEEE Workshop on Multimedia Signal Processing

作者： Akash Awasthi Son T. Ly Jaer Nizam Videet Mehta Safwan Ahmad Ramakrishna Nemani Saurabh Prasad Hien Van Nguyen Electrical and Computer Engineering University of Houston Houston USA Computer Science University of Houston Houston USA Computer Science Massachusetts Institute of Technology Cambridge USA Advanced Supercomputing Division NASA Ames Research Center Moffett Field California USA

ISBN: (数字)9798350387254

ISBN: (纸本)9798350387261

Detecting anomalies in videos is a fundamental challenge in machine learning, particularly for applications like disaster management. Leveraging satellite data, with its high frequency and wide coverage, proves invaluable for promptly identifying extreme events such as wildfires, cyclones, or floods. Geostationary satellites, providing data streams at frequent intervals, effectively create a continuous video feed of Earth from space. This study focuses on detecting anomalies, specifically wildfires and smoke, in these high-frequency satellite videos. In contrast to prior endeavors in anomaly detection within surveillance videos, this study introduces a system tailored for high-frequency satellite videos, placing particular emphasis on two anomalies. Unlike the majority of existing Convolution Neural Network-based methods for wildfire detection that rely on labeled images or videos, our unsupervised approach addresses the challenges posed by high-frequency satellite videos with a high intensity of clouds. These Convolution Neural Network-based methods can only identify fires once they have reached a certain size and are susceptible to false positives. We frame the challenge of wildfire detection as a general anomaly detection problem. Introducing an innovative unsupervised approach involving diffusion models, which are state-of-the-art generative models for anomaly detection in satellite videos, we adopt a “generating-to-detecting” strategy. Performance evaluation, measured through AUC-ROC, underscores the superior efficacy of the diffusion model over CNN and Generative Adversarial Networks-based methods in detecting anomalies in these high-frequency satellite videos characterized by a high intensity of clouds. The dataset utilized can be accessed at this location.

关键词： Satellites Wildfires Convolution Clouds Surveillance Streaming media Diffusion models Anomaly detection Streams Videos

来源：评论

学校读者我要写书评

暂无评论

Painlevé Analysis and Kink-Type Solitary Waves of the Geophysical KdV Equation Involving a Source

引用

International Journal of Applied and Computational mathematics 2024年第2期10卷 1-10页

作者： Hosseini, K. Baleanu, D. Hincal, E. Manukure, S. Salahshour, S. Kaymakamzade, B. Mathematics Research Center Near East University TRNC Nicosia Mersin 10 99138 Turkey Department of Mathematics Near East University TRNC Nicosia Mersin 10 99138 Turkey Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Faculty of Art and Science University of Kyrenia Kyrenia TRNC Mersin 10 Turkey Institute of Space sciences-Subsidiary of INFLPR Magurele-Bucharest Romania Department of Mathematics Florida A & amp Faculty of Engineering and Natural Sciences Istanbul Okan University Istanbul Turkey Faculty of Engineering and Natural Sciences Bahcesehir University Istanbul Turkey Faculty of Science and Letters Piri Reis University Tuzla Istanbul Turkey

The geophysical KdV equation is used to explore the propagation of oceanic waves. In the present paper, the geophysical KdV equation involving a source (The source is a polynomial of degree n in the unknown function) is formally introduced. Through the Painlevé analysis, it is shown that the geophysical KdV equation with the source is not integrable. Under some necessary conditions for integrability, several kink-type solitary waves to the special cases of the governing model when n=2 and n=4 are derived using the classical Kudryashov method. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2024.

关键词： Geophysical KdV equation Integrability Kink-type solitary waves Kudryashov method Painlevé analysis Source

来源：评论

学校读者我要写书评

暂无评论

Deformed Helix Ferroelectric Liquid Crystal Based Threshold-Less Passive Vibration Sensing System

Deformed Helix Ferroelectric Liquid Crystal Based Threshold-...

引用

SID International Symposium Digest of Technical Papers, 2023

作者： Yu, Xinyi Sun, Zhibo Yuan, Zhengnan Vashchenko, Valerii V. Srivastava, Abhishek Kumar State Key Laboratory of Advanced Displays and Optoelectronics Technologies Centre for Display Research Electronics and Computer Engineering Department Hong Kong IAS Center for Quantum Technologies The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Advanced Display and Optoelectronics Hong Kong University of Science and Technology Hong Kong

In this article, we proposed a passive vibration sensing system using a threshold-less deformed helix ferroelectric liquid crystal (DHFLC) cell. Combining the DHFLC cell, piezoelectric film, and optical detector, the system can transform the slight vibration into light intensity signal without a power supply. The system can reach the sensitivity of 165 V/(m/s) and the linearity © 2023, John Wiley and Sons Inc. All rights reserved.

关键词： Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split Federated Learning Scheme for Non-IID Data 7

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split...

引用

7th Cyber Security in Networking Conference, CSNet 2023

作者： Arafeh, Mohamad Wazzeh, Mohamad Ould-Slimane, Hakima Talhi, Chamseddine Mourad, Azzam Otrok, Hadi Department of Software and It Engineering Montreal Canada Department of Mathematics and Computer Science Canada New York University Division of Science Abu Dhabi United Arab Emirates Cyber Security Systems and Applied Ai Research Center Lebanese American University Department of Csm Beirut Lebanon Khalifa University Department of Eecs Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350342871

This paper proposes a scheme addressing the challenges of integrating privacy-preserving distributed machine learning in the Internet of Things (IoT) context while improving the efficiency of the learning process and accelerating the convergence of the model. Specifically, it addresses the presence of non-independent and identically distributed (Non-IID) data and device heterogeneity, which occurs during parallel training and are common characteristics of IoT environments. In this context, SplitFed is a privacy-preserving technique that combines Federated Learning (FL) and Split Learning (SL) to enable fast and privacy-preserving model training on IoT devices. Through parallelism, FL allows fast and parallel model training. Furthermore, SL enables weak devices to train models through model splitting. However, SplitFed suffers from the increasing convergence time due to the FL parallelism introducing Non-IID and stragglers issues. In this paper, we aim to address the aforementioned problems by proposing a clustering parallelization scheme. As such, similar clients are combined based on their weight divergence and considered a single FL unit addressing the Non-IID problem. Moreover, to improve time efficiency and overcome the stragglers' presence, we offer a second clustering stage that separates clients by efficiency and uses FedAsync for model aggregation. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Electronic perturbation of Cu nanowire surfaces with functionalized graphdiyne for enhanced CO2 reduction reaction

引用

National science Review 2024年第12期11卷 28-37页

作者： Haiyuan Zou Dongfang Cheng Chao Tang Wen Luo Huatian Xiong Hongliang Dong Fan Li Tao Song Siyan Shu Hao Dai Ziang Cui Zhouguang Lu Lele Duan Department of Chemistry Southern University of Science and Technology Department of Chemical and Biomolecular Engineering University of California Los Angeles Department of Materials Science and Engineering Southern University of Science and Technology Center of Artificial Photosynthesis for Solar Fuels and Department of Chemistry School of Science Westlake University Center for High-Pressure Science and Technology Advanced Research Department of Chemistry Tsinghua University Division of Solar Energy Conversion and Catalysis at Westlake University Zhejiang Baima Lake Laboratory Co. Ltd Institute of Natural Sciences Westlake Institute for Advanced Study

Electronic perturbation of the surfaces of Cu catalysts is crucial for optimizing electrochemical CO2reduction activity, yet still poses great challenges. Herein, nanostructured Cu nanowires（NW） with fine-tuned surface electronic structure are achieved via surface encapsulation with electron-withdrawing（–F） and-donating（–Me） group-functionalized graphdiynes（R-GDY, R = –F and –Me） and the resulting catalysts, denoted as R-GDY/Cu NW, display distinct CO2reduction performances. In situ electrochemical spectroscopy revealed that the *CO（a key intermediate of the CO2reduction reaction） binding affinity and consequent *CO coverage positively correlate with the Cu surface oxidation state, leading to favorable C–C coupling on F-GDY/Cu NW over Me-GDY/Cu NW. Electrochemical measurements corroborate the favorable C2H4production with an optimum C2+selectivity of 73.15% ± 2.5% observed for F-GDY/Cu NW, while the predominant CH4production is favored by Me-GDY/Cu NW. Furthermore, by leveraging the *Cu–hydroxyl（OH）/*CO ratio as a descriptor, mechanistic investigation reveals that the protonation of distinct adsorbed *CO facilitated by *Cu–OH is crucial for the selective generation of C2H4and CH4on F-GDY/Cu NW and Me-GDY/Cu NW, respectively.

关键词： CO reduction reaction copper nanowire group-functionalized graphdiyne surface electronic perturbation

来源：评论

学校读者我要写书评

暂无评论

Adult dental epithelial stem cell-derived organoids deposit hydroxylapatite biomineral

引用

International Journal of Oral science 2023年第4期15卷 676-690页

作者： Hyun-Yi Kim Victoria Cooley Eun-Jung Kim Shujin Li Jong-Min Lee Dina Sheyfer Wenjun Liu Ophir D.Klein Derk Joester Han-Sung Jung NGeneS Inc. Ansan-siGyeonggi-doKorea Department of Materials Science and Engineering Northwestern UniversityEvanstonILUSA X-ray Science Division Advanced Photon SourceArgonne National LaboratoryLemontILUSA Division in Anatomy and Developmental Biology Department of Oral BiologyOral Science Research CenterBK21 FOUR ProjectYonsei University College of DentistrySeoulKorea Department of Orofacial Sciences and Program in Craniofacial Biology University of CaliforniaSan FranciscoCAUSA Department of Pediatrics Cedars-Sinai Guerin Children’sLos AngelesCAUSA

Ameloblasts are specialized cells derived from the dental epithelium that produce enamel,a hierarchically structured tissue comprised of highly elongated hydroxylapatite(OHAp)*** unique function of the epithelial cells synthesizing crystallites and assembling them in a mechanically robust structure is not fully elucidated yet,partly due to limitations with in vitro experimental ***,we demonstrate the ability to generate mineralizing dental epithelial organoids(DEOs)from adult dental epithelial stem cells(aDESCs)isolated from mouse incisor *** expressed ameloblast markers,could be maintained for more than five months(11 passages)in vitro in media containing modulators of Wnt,Egf,Bmp,Fgf and Notch signaling pathways,and were amenable to *** transplanted underneath murine kidney capsules,organoids produced OHAp crystallites similar in composition,size,and shape to mineralized dental tissues,including some enamel-like elongated *** are thus a powerful in vitro model to study mineralization process by dental epithelium,which can pave the way to understanding amelogenesis and developing regenerative therapy of enamel.

关键词： epithelium maintained specialized

来源：评论

学校读者我要写书评

暂无评论

Steering Customized AI Architectures for HPC Scientific Applications 38th

Steering Customized AI Architectures for HPC Scientific Appl...

引用

38th International Conference on High Performance Computing, ISC High Performance 2023

作者： Ltaief, Hatem Hong, Yuxi Dabah, Adel Alomairy, Rabab Abdulah, Sameh Goreczny, Chris Gepner, Pawel Ravasi, Matteo Gratadour, Damien Keyes, David Division of Computer Electrical and Mathematical Sciences and Engineering Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal Jeddah23955 Saudi Arabia Division of Physical Sciences and Engineering Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal Jeddah23955 Saudi Arabia Graphcore Gdańsk Poland Warsaw University of Technology Warsaw Poland Paris Observatory Paris France

ISBN: (纸本)9783031320408

AI hardware technologies have revolutionized computational science. While they have been mostly used to accelerate deep learning training and inference models for machine learning, HPC scientific applications do not seem to directly benefit from these specific hardware features unless AI-based components are introduced into their simulation workflows, for instance, as a replacement of their numerical solvers. This paper proposes to take another direction in an attempt to democratize customized AI architectures for HPC scientific computing. The main idea consists in demonstrating how legacy applications can leverage these AI engines after a necessary algorithmic redesign. It is critical that the resulting software implementations map onto the underlying memory-austere hardware architectures to extract the expected performance. To facilitate this process, we promote the matricization technique for restructuring codes (1) by exploiting data sparsity via algebraic compression and (2) by expressing the critical computational phases in terms of tile low-rank matrix-vector multiplications (TLR-MVM) and batch matrix-matrix multiplications (batch GEMM). Algebraic compression enables to reduce memory footprint and to fit into small local cache/memory, while batch execution ensures high occupancy. We highlight how we can steer the Graphcore AI-focused Wafer-on-Wafer Intelligence Processing Units (IPUs) to deliver high performance for both operations. We conduct a performance benchmarking campaign of these two matrix operations that account for most of the elapsed times of four real applications in computational astronomy, seismic imaging, wireless communications, and climate/weather predictions. We report bandwidth and execution rates with speedup factors up to 150X/14X/25X/40X, respectively, on IPUs compared to other systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Tunable ultrathin dual-phase P-doped Bi_(2)MoO_(6) nanosheets for advanced lithium and sodium storage

引用

Nano research 2022年第7期15卷 6128-6137页

作者： Fucong Lyu Zhe Jia Shanshan Zeng Fei-Xiang Ma Lulu Pan Lizi Cheng Yan Bao Ligang Sun Weihui Ou Peng Du Yang Yang Li Jian Lu Centre for Advanced Structural Materials City University of Hong Kong Shenzhen Research InstituteGreater Bay Joint DivisionShenyang National Laboratory for Materials ScienceShenzhen 518057China Hong Kong Branch of National Precious Metals Material Engineering Research Centre City University of Hong KongKowloonHong KongChina School of Materials Science and Engineering Southeast UniversityNanjing 211189China School of Science Harbin Institute of TechnologyShenzhen 518055China Department of Mechanical Engineering City University of Hong KongKowloonHong KongChina CityU-Shenzhen Futian Research Institute Shenzhen 518045China Center of Super-Diamond and Advanced Films(COSDAF) City University of Hong KongKowloonHong KongChina Department of Material Science and Engineering City University of Hong KongKowloonHong KongChina

The construction of electrode materials for lithium-ion batteries(LIBs)and sodium-ion batteries(SIBs)has gradually been an appealing and attractive technology in energy storage research *** the present work,a facile strategy of synthesizing ultrathin amorphous/nanocrystal dual-phase P-doped Bi_(2)MoO_(6)(denoted as P-BiMO)nanosheets via a one-step wet-chemical synthesis approach is *** distinct from conventional two-dimensional(2D)nanosheets,our newly developed ultrathin P-BiMO nanosheets exhibit a unique tunable amorphous/nanocrystalline dual-phase structure with several compelling advantages including fast ion exchange ability and superb volume change buffer *** experimental results reveal that our prepared P-BiMO-6 electrode delivers an excellent reversible capacity of 509.6 mA·g^(−1) after continuous 1,500 cycles at the current densities of 1,500 mA·g^(−1) and improved rate performance for *** the meanwhile,the P-BiMO-6 electrode also shows a reversible capacity of 300.6 mA·g^(−1) after 100 cycles at 50 mA·g^(−1) when being used as the SIBs *** present work uncovers an effective dual-phase nanosheet structure to improve the performance of batteries,providing an attractive paradigm to develop superior electrode materials.

关键词： amorphous/nanocrystalline dual-phase structure ultrathin nanosheets P-doped Bi_(2)MoO_(6) anode materials lithium-ion batteries sodium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Ni-SiO2 Cell-Assisted Thermally Stable Broadband Metamaterial Emitter

引用

IEEE Transactions on Nanotechnology 2025年 24卷 307-311页

作者： Saqlain, Muhammad Baqir, Muhammad Abuzar Choudhury, Pankaj Kumar COMSATS University Islamabad Department of Electrical and Computer Engineering Islamabad Pakistan Zhejiang University College of Optical Science and Engineering International Research Center for Advanced Photonics Haining 314400 China

A thermally stable ultra-broadband metasurface-based emitter comprising square-shaped Ni resonators on Si substrate was investigated. The planer multilayer metamaterial emitter exhibits high emissivity of 94% over a span of 400–8450 nm wavelength. With the optimized structural parameters, the results show the thermal emission efficiency of 93.55% and photothermal conversion efficiency of 90.5% at 900K, which determines strong solar energy absorption of the emitter cavity. However, variations in structural parameters and the angle of incidence leave a minor impact on thermal emissivity. The findings show the developed structure to be of potential in efficient solar energy utilization. © 2002-2012 IEEE.

关键词： Metamaterials nanophotonic devices thermal emitter thermal stability

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：