检索结果-内蒙古大学图书馆

2nd International Conference on Multidisciplinary engineering and Applied science, ICMEAS 2023

作者： Ayoade, Idowu Adetona Nwakanma, Cosmas Ifeanyi Alimi, Sheriff Akinde, Olusola Kunle Adebisi, Oluwadare Oladeji, Dolapo Michael Ajayi, Dolapo Boluwatife Kayode, Michael Ife First Technical University Department of Mechatronics Engineering Ibadan Nigeria Kumoh National Institute of Technology ICT Convergence Research Center Gumi Korea Republic of Babcock University Ilishan Department of Computer Science and Artificial Intelligence Remo Nigeria First Technical University Department of Electrical and Electronics Engineering Ibadan Nigeria

ISBN: (纸本)9798350358834

Farmers in developing nations are faced with limited technology for smart and economical ways of irrigation. This is worsened by the high cost of imports since most of these nations are import-dependent. Increasing agricultural yield to meet the growing population in most of these nations has led their governments to pursue cost-effective ways of managing water and other resources required for optimum agricultural yield. In this study, the Internet of Things (IoT) and edge computing are proposed to provide an intelligent irrigation system to bridge the irrigation gap. This research was carried out using a greenhouse with a controlled environment i.e., the ambient temperature, air humidity, ultraviolet radiations (UV), soil temperature, and soil moisture content were all monitored and measured in real-Time within the controlled environment. These data were collected using field sensors processed using IoT-enabled microcontrollers (Arduino kits). The data were processed via Amazon Web Services (A WS) for ontological capabilities of the system consisting of computational capabilities of IoT server and Edge Server. Internet-enabled mobile devices were used to monitor and adopt preferential yield rates for cultivation. Also, an irrigation sequencing algorithm was developed, which uses predictive machine learning K-Mean Clustering Algorithm to predict a more accurate soil moisture content with minimum standard error and a lower mean square error of 0.11 to the predicted soil content compared to when only SVR with mean square error of 0.12. © 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

An Optimal Framework for SDN Based on Deep Neural Network

引用

computers, Materials & Continua 2022年第10期73卷 1125-1140页

作者： Abdallah Abdallah Mohamad Khairi Ishak Nor Samsiah Sani Imran Khan Fahad RAlbogamy Hirofumi Amano Samih M.Mostafa Department of Industrial Engineering School of Applied Technical Sciences German Jordanian UniversityAmman35247Jordan School of Electrical and Electronic Engineering Universiti Sains MalaysiaNibong Tebal14300Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and TechnologyThe National University of Malaysia(UKM)Bangi43600SelangorMalaysia Department of Electrical Engineering University of Engineering and TechnologyPeshawar814Pakistan Turabah University College Computer Sciences ProgramTaif UniversityTaif21944Saudi Arabia Research Institute for Information Technology Kyushu UniversityFukuoka819-0395Japan Computer Science-Mathematics Department Faculty of ScienceSouth Valley UniversityQena83523Egypt

Software-defined networking(SDN)is a new paradigm that promises to change by breaking vertical integration,decoupling network control logic from the underlying routers and switches,promoting(logical)network control centralization,and introducing network ***,the controller is similarly vulnerable to a“single point of failure”,an attacker can execute a distributed denial of service(DDoS)attack that invalidates the controller and compromises the network security in *** address the problem of DDoS traffic detection in SDN,a novel detection approach based on information entropy and deep neural network(DNN)is *** approach contains a DNN-based DDoS traffic detection module and an information-based entropy initial inspection *** initial inspection module detects the suspicious network traffic by computing the information entropy value of the data packet’s source and destination Internet Protocol(IP)addresses,and then identifies it using the DDoS detection module based on *** assaults were found when suspected irregular traffic was *** reveal that the algorithm recognizes DDoS activity at a rate of more than 99%,with a much better accuracy *** false alarm rate(FAR)is much lower than that of the information entropy-based detection ***,the proposed framework can shorten the detection time and improve the resource utilization efficiency.

关键词： Deep neural network computer networks data security optimization

来源：评论

学校读者我要写书评

暂无评论

FogROS2-FT: Fault Tolerant Cloud robotics

FogROS2-FT: Fault Tolerant Cloud Robotics

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Kaiyuan Chen Kush Hari Trinity Chung Michael Wang Nan Tian Christian Juette Jeffrey Ichnowski Liu Ren John Kubiatowicz Ion Stoica Ken Goldberg Department of Electrical Engineering and Computer Science University of California Berkeley CA USA Robert Bosch Research and Technology Center North America Sunnyvale CA USA Robotics Institute Carnegie Mellon University Department of Industrial Engineering and Operations Research University of California Berkeley CA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Cloud robotics enables robots to offload complex computational tasks to cloud servers for performance and ease of management. However, cloud compute can be costly, cloud services can suffer occasional downtime, and connectivity between the robot and cloud can be prone to variations in network Quality-of-Service (QoS). We present FogROS2-FT (Fault Tolerant) to mitigate these issues by introducing a multi-cloud extension that automatically replicates independent stateless robotic services, routes requests to these replicas, and directs the first response back. With replication, robots can still benefit from cloud computations even when a cloud service provider is down or there is low QoS. Additionally, many cloud computing providers offer low-cost "spot" computing instances that may shutdown unpredictably. Normally, these low-cost instances would be inappropriate for cloud robotics, but the fault tolerance nature of FogROS2-FT allows them to be used reliably. We demonstrate FogROS2-FT fault tolerance capabilities in 3 cloud-robotics scenarios in simulation (visual object detection, semantic segmentation, motion planning) and 1 physical robot experiment (scan-pick-and-place). Running on the same hardware specification, FogROS2-FT achieves motion planning with up to 2.2x cost reduction and up to a 5.53x reduction on 99 Percentile (P99) long-tail latency. FogROS2-FT reduces the P99 long-tail latency of object detection and semantic segmentation by 2.0x and 2.1x, respectively, under network slowdown and resource contention. Videos and code are available at https://***/view/fogros2-ft.

关键词： Fault tolerance Heavily-tailed distribution Semantic segmentation Fault tolerant systems Quality of service Object detection Planning Servers Robots Cloud robotics

来源：评论

学校读者我要写书评

暂无评论

Magnetoelastic coupling driven magnon gap in a honeycomb antiferromagnet

引用

Physical Review B 2024年第10期110卷 104419页

作者： Jeongheon Choe Andrey Baydin Gaihua Ye Bowen Ma Cynthia Nnokwe Martin Rodriguez-Vega David Lujan Swati Chaudhary Fuyang Tay Jiaming He Hiroyuki Nojiri Jianshi Zhou Gregory A. Fiete Junichiro Kono Rui He Xiaoqin Li Department of Physics Center of Complex Quantum Systems Center for Dynamics and Control of Materials Department of Electrical and Computer Engineering Smalley–Curl Institute Department of Physics Applied Physics Graduate Program Smalley–Curl Institute Department of Mechanical Engineering Institute for Materials Research Department of Physics and Astronomy Department of Materials Science and NanoEngineering

Cobalt titanate, CoTiO3, is a honeycomb antiferromagnet recently confirmed experimentally to host Dirac magnons, topological spin-orbit excitons, and chiral phonons. Here, we investigate a magnon gap at the zone center which calls for a refined spin Hamiltonian. We propose a microscopic model for the magnon gap and attribute it to a lattice-distortion (phonon)-induced higher-order spin interaction. Strong magnetoelastic coupling in CoTiO3 is also evident in Raman spectra, in which the magnetic order exerts a stronger influence on phonons corresponding to in-plane ionic motions than those with out-of-plane motions. We further examine the evolution of the zone-center magnons in a high magnetic field up to 18.5 T via THz absorption spectroscopy measurements. Based on this field dependence, we propose a spin Hamiltonian that not only agrees with magnon dispersion measured by inelastic neutron scattering but also includes fewer exchange constants and a realistic anisotropy term. Our work highlights the broad implications of magnetoelastic coupling in the study of topologically protected bosonic excitations.

关键词： Magnetism Magnons Topological materials Raman spectroscopy Terahertz spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Short-term solar eruptive activity prediction models based on machine learning approaches:A review

引用

science China Earth sciences 2024年第12期67卷 3727-3764页

作者： Xin HUANG Zhongrui ZHAO Yufeng ZHONG Long XU Marianna B.KORSÓS R.ERDÉLYI Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China School of Astronomy and Space Science University of Chinese Academy of SciencesBeijing 100049China Beijing Cellular Exploration Science and Technology Center Beijing 100190China Dipartimento di Fisica e Astronomia“Ettore Majorana” Universitàdi CataniaCatania I 95123Italy Department of Astronomy Eötvös Loránd UniversityBudapest H-1112Hungary Hungarian Solar Physics Foundation Gyula H-5700Hungary Solar Physics&Space Plasma Research Center(SP2RC) School of Mathematics and StatisticsUniversity of SheffieldSheffield S37RHUK

Solar eruptive activities,mainly including solar flares,coronal mass ejections(CME),and solar proton events(SPE),have an important impact on space weather and our *** short-term solar eruptive activity prediction is an active field of research in the space weather ***,statistical,and machine learning methods are proposed to build prediction models of the solar eruptive *** the development of space-based and ground-based facilities,a large amount of observational data of the Sun is accumulated,and data-driven prediction models of solar eruptive activities have made a significant *** this review,we briefly introduce the machine learning algorithms applied in solar eruptive activity prediction,summarize the prediction modeling process,overview the progress made in the field of solar eruptive activity prediction model,and look forward to the possible directions in the future.

关键词： Solar flare Coronal mass ejection Solar proton event Machine learning Prediction model

来源：评论

学校读者我要写书评

暂无评论

An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Gong, Xueluan Tian, Bowei Xue, Meng Wu, Yuan Chen, Yanjiao Wang, Qian Nanyang Technological University Singapore Wuhan University School of Cyber Science and Engineering China Hong Kong University of Science and Technology Department of Computer Science and Engineering China Wuhan Textile University School of Computer Science and Artificial Intelligence Engineering Research Center of Hubei Province for Clothing Information China Zhejiang University College of Electrical Engineering China

Recent studies have revealed the vulnerability of Deep Neural Network (DNN) models to backdoor attacks. However, existing backdoor attacks arbitrarily set the trigger mask or use a randomly selected trigger, which restricts the effectiveness and robustness of the generated backdoor triggers. In this paper, we propose a novel attention-based mask generation methodology that searches for the optimal trigger shape and location. We also introduce a Quality-of-Experience (QoE) term into the loss function and carefully adjust the transparency value of the trigger in order to make the backdoored samples to be more natural. To further improve the prediction accuracy of the victim model, we propose an alternating retraining algorithm in the backdoor injection process. The victim model is retrained with mixed poisoned datasets in even iterations and with only benign samples in odd iterations. Besides, we launch the backdoor attack under a co-optimized attack framework that alternately optimizes the backdoor trigger and backdoored model to further improve the attack performance. Apart from DNN models, we also extend our proposed attack method against vision transformers. We evaluate our proposed method with extensive experiments on VGG-Flower, CIFAR-10, GTSRB, CIFAR-100, and ImageNette datasets. It is shown that we can increase the attack success rate by as much as 82% over baselines when the poison ratio is low and achieve a high QoE of the backdoored samples. Our proposed backdoor attack framework also showcases robustness against state-of-the-art backdoor defenses. © 2004-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Nonlinear Delay Differential System for Analyzing Vulnerabilities in Nanoscale Hardware Implants: A Deep Dive into Intelligent Computing Networks

引用

Nano 2025年第3期20卷

作者： Asif Raja, Muhammad Junaid Ali Masood, Zaheer Hussain, Ijaz Zameer, Aneela Mehmood, Ammara Raja, Muhammad Asif Zahoor Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Electrical Engineering Capital University of Science and Technology Islamabad Pakistan Department of Computer and Information Sciences Pakistan Institute of Engineering & Applied Sciences Islamabad Pakistan School of Electrical and Data Engineering University of Technology Sydney Australia Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan

In the annals of contemporary innovation, the study of miniature marvels nanoscale hardware implants emerged as a pivotal instrument, scarcely perceptible to the naked eye, embodies a prowess of cutting-edge technologies and clandestine intrigue. The objective of this research is to introduce a time delay nonlinear system for nanoscale hardware implants vulnerabilities that portray the exploitation of a system by utilizing the stupendous knacks of advanced deep bidirectional long short-term memory (LSTM) networks for time series predictions. Firmware-level bugs present the potential for escalating privileges and executing of code remotely beneath the operating system, allowing for infiltration or complete intervention within a computer system. The designed deep bidirectional LSTM is configured to precisely predict and forecast the dynamic states of time delay differential system, offering a robust framework for mimicking delays that commonly manifest in the real cyber-physical systems. To orchestrate the system compromises in real scenarios through the activation of bugged hardware, time delay factors τ1 and τ2 are introduced to account the time delays necessary for exploiting the bugged and patched nodes, respectively. Synthetic data is generated to train the LSTM network for all scenarios of the model for the dynamics of bugged, compromised, patched nodes and these acquired information is used for training, testing and validation purposes regarding exploitation of the bugged hardware. Comparative analysis on exhaustive simulations revealed a minimal difference between the LSTM's predictions and those from the numerical outcomes with MSE in the range of 10-7, underscoring the network's effectiveness, robustness and stability in modeling complex system dynamics of hardware vulnerabilities. © 2025 World Scientific Publishing Company.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Industry 4.0: Architecture and Equipment Revolution

引用

computers, Materials & Continua 2021年第2期66卷 1175-1194页

作者： Ahmed Bashar Fakhri Saleem Latteef Mohammed Imran Khan Ali Safaa Sadiq Basem Alkazemi Prashant Pillai Bong Jun Choi Department of Medical Instrumentation Techniques Engineering Electrical Engineering Technical CollegeMiddle Technical UniversityBaghdadIraq Department of Electrical Engineering University of Engineering and Technology PeshawarPeshawarPakistan School of Mathematics and Computer Science University of WolverhemptonWulfruna StreetWolverhemptonUK Center of Artificial Intelligence Research and Optimization Torrens UniversityBrisbaneAustralia Department of Computer Science College of Computer&Information SystemsUmm Al-Qura UniversityMeccaSaudi Arabia School of Computer Science and Engineering Soongsil UniversitySeoulSouth Korea

The development of science and technology has led to the era of Industry *** core concept is the combination of“material and informationization”.In the supply chain and manufacturing process,the“material”of the physical entity world is realized by data,identity,intelligence,and *** 4.0 is a disruptive transformation and upgrade of intelligent industrialization based on the Internet-of-Things and Big Data in traditional *** goal is“maximizing production efficiency,minimizing production costs,and maximizing the individual needs of human beings for products and services.”Achieving this goal will surely bring about a major leap in the history of the industry,which will lead to the“Fourth Industrial Revolution.”This paper presents a detailed discussion of industrial big data,strategic roles,architectures,characteristics,and four types of innovative business models that can generate profits for *** key revolutionary aspect of Industry 4.0 is explained,which is the equipment *** important attributes of equipment are explained under the Industry 4.0 perspective.

关键词： Industry 4.0 big data smart manufacturing business model equipment revolution

来源：评论

学校读者我要写书评

暂无评论

An 8-bit Quantized Globalization Model for Cat Skin Disease Detection Using Convolutional Neural Networks and TensorFlow Lite

An 8-bit Quantized Globalization Model for Cat Skin Disease ...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Karisma Trinanda Putra Hasan Zidni Rifdha Turrizka Hsueh-Ting Chu Dinh-Trung Vu Prayitno Department of Electrical Engineering Center of Artificial Intelligence and Robotics Studies Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Electrical Engineering Institut Teknologi Bandung Bandung Indonesia Department of Electrical Engineering Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Computer Science and Information Engineering Asia University Taichung Taiwan Department of Electrical Engineering Semarang State Polytechnic Semarang Indonesia

ISBN: (数字)9798350379839

ISBN: (纸本)9798350379846

Skin diseases are health issues that can be experienced by pets and potentially be transmitted from wild animals. However, current prediction systems predominantly rely on complex calculations that necessitate high computational power, making them challenging to deploy on mobile applications. Therefore, this study aims to optimize a skin disease detection system based on convolutional neural networks (CNN) using datasets from both wild and domestic cats. The quantized globalization model is a modified ResNet50 converted with TensorFlow Lite. This 8-bit quantization is necessary to develop a lightweight deep learning model that could operate on low-computational power units, such as smartphone or 8-bit edge computing devices. This study utilized a dataset comprising 343 images, categorized into six classes: five classes of diseases (abscesses, mange, ringworm, skin cancer, dermatitis) and one class for healthy skin. Next, the dataset was augmented to increase data variation and quantity. Subsequently, the dataset was trained on the ResNet-50 model and then converted to TensorFlow Lite with 8-bit integer data type. Finally, the quantized globalization model was validated using a separate 20% of the dataset. The validation results yielded an accuracy score of 0.930, a precision of 0.908, a recall of 0.902, and an F1-score of 0.903. Additionally, there was a significant 74.7% reduction in model size compared to the non-quantized version, demonstrating the efficiency and effectiveness of the quantization process in maintaining performance while substantially decreasing the computational resource requirements.

关键词： Analytical models Accuracy Computational modeling Globalization Predictive models Skin Data models Convolutional neural networks Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Four-dimensional conserved topological charge vectors in plasmonic quasicrystals

引用

science (New York, N.Y.) 2025年第6734期387卷 644-648页

作者： Tsesses, Shai Dreher, Pascal Janoschka, David Neuhaus, Alexander Cohen, Kobi Meiler, Tim C. Bucher, Tomer Sapir, Shay Frank, Bettina Davis, Timothy J. Meyer Zu Heringdorf, Frank Giessen, Harald Bartal, Guy rew and Erna Viterbi Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Department of Physics MIT-Harvard Center for Ultracold Atoms and Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge MA United States Faculty of Physics and Center for Nanointegration University of Duisburg-Essen Duisburg-Essen (CENIDE) Duisburg Germany 4th Physics Institute Research Center SCoPE Integrated Quantum Science and Technology Center University of Stuttgart Stuttgart Germany Centre for Disruptive Photonic Technologies and School of Physical and Mathematical Sciences Nanyang Technological University Singapore Faculty of Mathematics and Computer Science Weitzmann Institute of Science Rehovot Israel School of Physics University of Melbourne Parkville VIC Australia

According to Noether's theorem, symmetries in a physical system are intertwined with conserved quantities. These symmetries often determine the system topology, which is made ever more complex with increased dimensionality. Quasicrystals have neither translational nor global rotational symmetry, yet they intrinsically inhabit a higher-dimensional space in which symmetry resurfaces. Here, we discovered topological charge vectors in four dimensions (4D) that govern the real-space topology of 2D quasicrystals and reveal their inherent conservation laws. We demonstrate control over the topology in pentagonal plasmonic quasilattices, mapped by both phase-resolved and time-domain near-field microscopy, showing that their temporal evolution continuously tunes the 2D projections of their distinct 4D topologies. Our work provides a route to experimentally probe the thermodynamic properties of quasicrystals and topological physics in 4D and above.

关键词：

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：