检索结果-内蒙古大学图书馆

32nd IEEE International Conference on Microelectronics, MIEL 2021

作者： Banach, M. Dlugosz, Z. Dlugosz, R. Talaska, T. Poznan University of Technology Institute of Architecture and Spatial Planning Poznan Poland Bydgoszcz University of Science and Technology Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz Poland

ISBN: (纸本)9781665445283

The paper presents a concept of an air pollution monitoring system based on a wireless sensor network, in which particular sensors are able to predict future pollution levels within a specific time horizon. In the solutions reported in state-of-The art literature, forecasting the changes in pollution levels is usually based on the use of artificial neural networks (ANNs), globally trained for a given area, e.g. a city. In contrast, we propose to equip the sensors with hardware-implemented ANN s that could make the prediction based on data that the network obtains from the place where particular sensor is installed. Such networks require appropriate hardware optimization to maintain low energy consumption of the overall sensor. For this reason, in this paper we present a method of optimizing one of more complex components that is involved in determining the value of neuron weights in the network training process. In this work, we focus on the backpropagation (BP) learning algorithm, which results from the widespread use of this type of network in predicting air pollution levels. © 2021 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Stress-Resiliency of AI Implementations on FPGAs

Stress-Resiliency of AI Implementations on FPGAs

引用

International Conference on Field Programmable Logic and Applications

作者： Jonas Krautter Paul R. Genssler Gloria Sepanta Hussam Amrouch Mehdi Tahoori Institute of Computer Engineering Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Chair of Semiconductor Test and Reliability (STAR) University of Stuttgart Stuttgart Germany Chair of AI Processor Design Technical University of Munich (TUM) Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany

FPGAs have become a popular choice for machine learning acceleration for both cloud and edge devices. While traditional neural networks show impressive performance in classification tasks, Hyperdimensional Computing (HDC) is rapidly emerging as a promising novel machine learning approach for its hardware-friendly inference. In HDC, classes are embedded into high-dimensional vectors during training, and inputs can be classified by computing similarity metrics between class-vectors during inference. HDC inference is especially promoted in terms of its resiliency against errors, attributed to the large inherent redundancy. In this work, we perform a thorough experimental investigation of the fault resiliency of various FPGA-based machine learning implementations under different aspects of stress, comparing HDC with classical neural network approaches. We explore both the amount of faulty classifications as well as system crashes while subjecting the designs to timing stress using overclocking, voltage stress with excessive switching activity, and thermal stress.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Media Literacy: The Effectiveness of (Human) Annotations and Bias Visualizations on Bias Detection

arXiv

引用

arXiv 2024年

作者： Spinde, Timo Wu, Fei Gaissmaier, Wolfgang Demartini, Gianluca Giese, Helge Department of Computer Science University of Göttingen Göttingen Germany Institute for Natural Language Processing University of Stuttgart Stuttgart Germany Department of Psychology University of Konstanz Konstanz Germany Cluster for the Advanced Study of Collective Behavior University of Konstanz Konstanz Germany School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia Heisenberg Chair for Medical Risk Literacy and Evidence-Based Decisions Charité – Universitätsmedizin Berlin Berlin Germany

Marking biased texts is a practical approach to increase media bias awareness among news consumers. However, little is known about the generalizability of such awareness to new topics or unmarked news articles, and the role of machine-generated bias labels in enhancing awareness remains unclear. This study tests how news consumers may be trained and pre-bunked to detect media bias with bias labels obtained from different sources (Human or AI) and in various manifestations. We conducted two experiments with 470 and 846 participants, exposing them to various bias-labeling conditions. We subsequently tested how much bias they could identify in unlabeled news materials on new topics. The results show that both Human (t(467) = 4.55, p 2part = 0.048). Our experimental framework provides theoretical implications for systematically assessing the generalizability of learning effects in identifying media bias. These findings also provide practical implications for developing news-reading platforms that offer bias indicators and designing media literacy curricula to enhance media bias awareness. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text-guided diverse-expression diffusion model for molecule generation

引用

Chinese Physics B 2025年第5期 109-117页

作者：翁文超蒋涵羽孔祥杰 Giovanni Pau College of Computer Science and Technology Zhejiang University of Technology Hangzhou Dianzi University ITMO Joint Institute Hangzhou Dianzi University Faculty of Engineering and Architecture Kore University of Enna

The task of molecule generation guided by specific text descriptions has been proposed to generate molecules that match given text inputs. Mainstream methods typically use simplified molecular input line entry system(SMILES) to represent molecules and rely on diffusion models or autoregressive structures for modeling. However, the one-to-many mapping diversity when using SMILES to represent molecules causes existing methods to require complex model architectures and larger training datasets to improve performance, which affects the efficiency of model training and generation. In this paper, we propose a text-guided diverse-expression diffusion(TGDD) model for molecule generation. TGDD combines both SMILES and self-referencing embedded strings(SELFIES) into a novel diverse-expression molecular representation, enabling precise molecule mapping based on natural language. By leveraging this diverse-expression representation, TGDD simplifies the segmented diffusion generation process, achieving faster training and reduced memory consumption, while also exhibiting stronger alignment with natural language. TGDD outperforms both TGM-LDM and the autoregressive model MolT5-Base on most evaluation metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Metaheuristic Optimization Techniques in Insulation Problem 8

Performance Evaluation of Metaheuristic Optimization Techniq...

引用

8th International Conference on Information Technology Trends, ITT 2022

作者： Gunal, Ozen Akpinar, Mustafa Akpinar, Kevser Ovaz Turgutlu Vocational School Manisa Celal Bayar University Department of Computer Programming Manisa Turkey Sakarya University Department of Software Engineering Sakarya Turkey School of Engineering Architecture and Interior Design Amity University Dubai Dubai United Arab Emirates Rochester Institute of Technology Department of Computing Security Dubai United Arab Emirates

ISBN: (数字)9781665487429

ISBN: (纸本)9781665487412

Selection of insulation material and determination of its thickness are the two most important parameters that prevent heat loss. Too much thickness complicates the price and use. The low coefficient of thermal conductivity of the insulation material reduces heat loss and increases the cost. One of the most important factors when determining the material thickness and conductivity coefficient is the price. In this study, two cases were examined under certain conditions, independent of the price. In the first case, the insulation material is determined, whereas the material thickness is determined in the second case. Six different current metaheuristic algorithms were used to calculate the two cases. It has been observed that harris hawks optimization (HHO), salp swarm optimization (SSO), and whale optimization (WO) algorithms determine the global optimum point without any error in determining the targets of the problem while the processing times were short. Overall, it has been seen that all six algorithms can create solutions to heat transfer problems with very low errors. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Sequential solution strategies for the Cahn-Hilliard-Biot model

arXiv

引用

arXiv 2024年

作者： Storvik, Erlend Riethmüller, Cedric Both, Jakub W. Radu, Florin A. Department of Computer science Electrical engineering and Mathematical sciences Western Norway University of Applied sciences Norway Institute of Applied Analysis and Numerical Simulation University of Stuttgart Germany Centre for Modeling of Coupled Subsurface Dynamics Department of Mathematics University of Bergen Norway

This paper presents a study of solution strategies for the Cahn-Hilliard-Biot equations, a complex mathematical model for understanding flow in deformable porous media with changing solid phases. Solving the Cahn-Hilliard-Biot system poses significant challenges due to its coupled, nonlinear and non-convex nature. We explore various solution algorithms, comparing monolithic and splitting strategies, focusing on both their computational efficiency and robustness. © 2024, CC BY.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Characterization and Control of a Superconducting Homopolar Motor with Cryogenic GaN Inverter for Electric Aircrafts

Characterization and Control of a Superconducting Homopolar ...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Felix Gliese Matthew G. S. Pearce Aaron Wadsworth Mohammad Siamaki James Storey Grant Lumsden Duleepa J. Thrimawithana Rod Badcock Joerg Roth-Stielow Martin Neuburger Faculty of Mobility and Technology Esslingen University Germany Dept. of Electrical Computer and Software Engineering The University of Auckland New Zealand OpenStar Technologies New Zealand Robinson Research Institute Victoria University of Wellington New Zealand Institute for Power Electronics and Electrical Drives University of Stuttgart Germany

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

In the quest for a zero-emissions future, the aviation sector is facing the challenge of reducing its carbon footprint. This paper presents a characterization of a superconducting homopolar motor designed to meet the stringent power and efficiency requirements of all-electric aircraft. The control system, which features field-oriented control and a multi-layer architecture, ensures precise operation of the motor under various load conditions. The motor uses a stationary cryogenic superconducting DC coil to generate the rotor’s magnetic field. Utilizing superconducting materials helps produce the high power densities critical for aviation. The characterization of the key parameters of the motor, such as inductances, stator resistance and flux, are presented. A description of the cryogenic GaN power electronic inverter power stage immersed in liquid nitrogen is provided. This design enables future integration next to the motor, and improved power density and efficiency. This paper outlines the design, implementation, and initial testing of the superconducting homopolar motor and its power electronics, highlighting its potential for electric propulsion in aviation by providing a viable solution for long-range flights.

关键词： Resistance Power system measurements Electric potential Torque Density measurement Cryogenics Motors Control systems Inverters Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Reliable Federated Learning in Heterogeneous Mobile-Edge Computing

Energy-Efficient and Reliable Federated Learning in Heteroge...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yan Xu Liying Li Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

As a decentralized machine learning paradigm, Federated Learning (FL) is an emerging technique to protect user data privacy in Mobile Edge Computing (MEC). FL adopts the idea of distributed privacy computing, enabling the terminal devices to train machine learning models required by servers locally and upload model parameters to servers for aggregation. However, in the process of coupling FL with MEC systems, device heterogeneity, malicious use of poisoned data by users and limited system resources will seriously affect FL training accuracy, system reliability and energy efficiency. In this paper, a highly reliable and energy-efficient FL scheme is designed to solve these issues. Specifically, we first propose a calculation method for estimating the reliability of heterogeneous devices. Then, we design a highly reliable device selection scheme based on devices’ reliability, computing power, and participation times. Finally, we utilize the slack time in FL training to dynamically adjust the voltage and frequency of devices for reducing the energy consumption of training. Experimental results show that our proposed scheme improves the accuracy by up to 36.45% on average and saves energy by up to 48.63% when compared to the baseline and benchmarking methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Environmental Factors for Smart Farming: An Internet of Things Based Approach 10

Analysis of Environmental Factors for Smart Farming: An Inte...

引用

10th International Conference on System Modeling and Advancement in Research Trends, SMART 2021

作者： Agarwal, Ambuj Kumar Ather, Danish Astya, Rani Parygin, Danila Garg, Amit Raj, Dharm Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Sharda University Department of Computer Science and Engineering Greater Noida India Volgograd State Technical University Department of Digital Technologies in Urban Studies Architecture and Construction Volgograd Russia Chandigarh University AIT-Computer Science and Engineering Department Chandigarh India

ISBN: (纸本)9781665439701

The Internet of Things also referred to as IoT plays an important role in our everyday lives by allowing us to control electrical gadgets through networks. Controlling is accomplished by meticulously watching key parameters that produce critical information about the operation of this electrical equipment. At the same time, the critical information will transfer from the transmitting device and preserved on the cloud for apps and secondary processes to access. This investigation connects the results of environmental measures such as temperature and humidity taken by making use of sensors. The data acquired might be put to good use to create activities such as faraway dominating long-term statistics, cooling, or heating devices that can be utilised to govern the situation. The observed data is transferred to a cloud storage service through the internet and linked to an Android application. Arduino UNO and sensor devices, and ESP8266 Wi-Fi module are used in the system. Using Arduino UNO. The testing and findings will disclose the live temperature and humidity of the surroundings, as well as the soil moisture of sample soil.. The sensor element is used to check the humidity and temperature using the DHT 11 sensor. The sensors are used to take temperature readings from the environment and store the data on Thinkspeak Cloud. The ESP8266 Wi-Fi module was utilized to connect with the internet and store the data on the Thinkspeak cloud in this project. © 2021 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Standardized Post-Quantum Cryptography and Recent Developments in Quantum computers 1

Standardized Post-Quantum Cryptography and Recent Developmen...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Chib, Shiney Devarajan, Harshitha Raghavan Chundru, Swathi Pulivarthy, Padmaja Isaac, R. Augustian Oku, KrishnaMurthy Meghe Institute of Management Studies Department of Management Datta Maharashtra Nagpur India New York University Department of Computer Science United States Motivity labs INC United States Samsung Korea Republic of Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Tamil Nadu Chennai602105 India AT&T Services Inc Tech Lead Infrastructure/Cloud Architecture Department of Automation platform Development India

ISBN: (纸本)9798331518578

Traditional cryptographic frameworks are seriously threatened by the quick development of quantum computing, especially those that depend on public-key cryptosystems like RSA and ECC. Post-quantum cryptography (PQC) seeks to create cryptographic methods that are impervious to quantum computer assaults in order to overcome this difficulty. The National institute of Standards and Technology (NIST), which has selected and standardised quantum-resistant techniques like CRYSTALS-Kyber for key encapsulation and CRYSTALS-Dilithium for digital signatures, has sparked recent advancements in PQC. At the same time, the need for reliable PQC solutions has increased due to developments in quantum computing, such as IBM's improvements in qubit stability and Google's 'quantum supremacy' assertion. In order to protect data security in the post-quantum age, PQC regulations must be adopted globally, as highlighted by the intersection of these fields. Current developments in PQC standardisation and the changing state of quantum computing technology are highlighted in this paper. © 2025 IEEE.

关键词： Quantum cryptography

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：