检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Muhammad Kashif Emman Sychiuco Muhammad Shafique eBrain Lab Division of Engineering Center for Quantum and Topological Systems NYUAD Research Institute New York University Abu Dhabi Abu Dhabi UAE

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The Hybrid Quantum Neural Networks (HyQNNs) hold great promise for various quantum machine learning tasks, but their performance can be significantly affected by the quantum noise in NISQ devices. In this paper, we comprehensively analyze the influence of different quantum noise gates, including Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarizing Channel, on the performance of HyQNNs. Our results reveal distinct and significant effects on HyQNNs training and validation accuracies across different probabilities of noise. For instance, the Phase Flip gate introduces phase errors, and we observe that HyQNNs exhibit resilience at higher probability (p = 1.0), adapting effectively to consistent noise patterns, whereas at intermediate probabilities, the performance declines. Bit Flip errors, represented by the Pauli X gate, impact HyQNNs in a similar way to that Phase Flip error gate. The HyQNNs, can adapt such kind of errors at maximum probability (p = 1.0). Unlike Phase and Bit Flip error gates, Phase Damping and Amplitude Damping gates disrupt quantum information, with HyQNNs demonstrating resilience at lower probabilities but facing challenges at higher probabilities. Amplitude Damping, in particular, poses efficiency and accuracy issues at higher probabilities, however with lowest probability (p =0.1),it has the least effect, i.e., HyQNNs, although not very effectively, but still tends to learn. The Depolarizing Channel proves most detrimental to HyQNNs performance, with limited or no training improvements. There was no training potential observed regardless of the probability of this noise gate. These findings underscore the critical need for advanced quantum error mitigation and resilience strategies in the design and training of HyQNNs, especially in environments prone to depolarizing noise. This paper quantitatively investigate that understanding the impact of quantum noise gates is essential for harnessing the full potential of quantum c

关键词： Damping Training Performance evaluation Accuracy Quantum computing Prevention and mitigation Noise

来源：评论

学校读者我要写书评

暂无评论

CE-FFT: Communication-Efficient Federated Fine-Tuning for Large Language Models via Quantization and In-Context Learning

CE-FFT: Communication-Efficient Federated Fine-Tuning for La...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Pengyu Zhang Yingjie Liu Yingbo Zhou Ming Hu Xian Wei Mingsong Chen MoE Engineering Research Center of SW/HW Co-Design Technology and Application East China Normal University School of Computing and Information Systems Singapore Management University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Although Federated Fine-Tuning (FFT) facilitates the fine-tuning of Large Language Models (LLMs) across data owners without compromising their privacy, it suffers from severe communication overheads caused by numerous parameters of LLMs even with Parameter-Efficient Fine-Tuning (PEFT) methods. To address this, we propose a novel communication-efficient FFT framework by reducing per-round transmission costs and simultaneously diminishing the required convergence rounds. Specifically, we freeze the parameter-intensive backbone of LLMs, activate low-rank adapters for fine-tuning, and design a parameter quantization mechanism to reduce per-round communication costs. Additionally, inspired by in-context learning, we align the distributions of local data by identifying and rewriting unimportant samples using the global model, retaining important local information, and guiding local fine-tuning towards a uniform trajectory, thereby accelerating convergence and reducing transmission burdens. Experiments on two instruction datasets show that our method can reduce communication costs by up to 7.76× without compromising performance.

关键词： Training Data privacy Costs Quantization (signal) Large language models LoRa Data models Trajectory Speech processing Convergence

来源：评论

学校读者我要写书评

暂无评论

Multiple Sequential Network Attacks Detection Based on DTW-HMM 7

Multiple Sequential Network Attacks Detection Based on DTW-H...

引用

7th IEEE International Conference on Data Science in Cyberspace, DSC 2022

作者： Liu, Haitian Jiang, Rong Zhou, Bin Rong, Xing Li, Juan Li, Aiping College of Computer National University of Defense Technology Changsha China China Electronic Device Systems Engineering Corporation Beijing China China Information Technology Security Evaluation Center Beijing China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

With the increasing severity of network threats, network security has become a global concern. Especially the Sequential network attacks (SNAs), are becoming increasingly prominent. Hidden Markov Model (HMM) is often used to model such problems. By revealing the early life cycle of SNAs, it helps to understand attacker strategies. Based on this, this paper proposes a new intrusion detection mechanism for SNA detection to meet the challenges of modeling and detecting multiple sequential network attack scenarios. We developed an architecture capable of identifying these organized attack processes. The system goes through three main stages. The first stage processes the alerts output by IDS and feeds them into different sub-alert sequences belonging to different attackers. The second stage uses the DTW&1NN algorithm to classify sub-alert sequences belonging to the same SNA scenario. The third stage of the proposed system is attack decoding, which utilizes a Hidden Markov Model (HMM) to determine the most likely sequence of SNA phases for a given sequence of relevant alerts. Finally, simulation experiments are carried out based on the public dataset of CSE-CIC-IDS2018 to verify the effectiveness of the proposed architecture. © 2022 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Active Vapor-Based Robotic Wiper

Active Vapor-Based Robotic Wiper

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Takuya Kiyokawa Hiroki Katayama Jun Takamatsu Kensuke Harada Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan Division of Information Science Nara Institute of Science and Technology (NAIST) Japan

ISBN: (数字)9798331521554

ISBN: (纸本)9798331521561

This paper presents a method for estimating normals of mirrors and transparent objects challenging for cameras to recognize. We propose spraying water vapor onto mirror or transparent surfaces to create a diffuse reflective surface. Using an ultrasonic humidifier on a robotic arm, we apply water vapor to the target object's surface, forming a cross-shaped misted area. This creates partially diffuse reflective surfaces, enabling the camera to detect the target object's surface. Adjusting the gripper-mounted camera viewpoint maximizes the extracted misted area's appearance in the image, allowing normal estimation of the target surface. Experiments show the method's effectiveness, with RMSEs of azimuth estimation for mirrors and transparent glass approximately 4.2° and 5.8°, respectively. Our robot experiments demonstrated that our robotic wiper can perform contact-force-regulated wiping motions to clean a transparent window, akin to human performance.

关键词： Surface cleaning Estimation error Robot vision systems Spraying Glass Cameras Manipulators Sensor systems Windows Mirrors

来源：评论

学校读者我要写书评

暂无评论

An Efficient Collaborative Task Offloading Approach Based on Multi-Objective Algorithm in MEC-Assisted Vehicular Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Chen, Shuaijie Li, Wenfeng Sun, Jingtao Pace, Pasquale He, Lijun Fortino, Giancarlo Wuhan University of Technology State Key Laboratory of Maritime Technology and Safety School of Transportation and Logistics Engineering Hubei Wuhan430063 China National Institute of Informatics Information Systems Architecture Research Division Tokyo Japan University of Calabria Department of Informatics Modeling Electronics and Systems Rende87036 Italy

Mobile edge computing assisting vehicular networks to achieve collaborative computing is a significant research area, as it can effectively expand the on-board computational resources, thereby improving the responsiveness of vehicular applications and reducing energy consumption. However, the existing task offloading schemes still have various gaps and face challenges that should be addressed because task offloading problems are usually multi-objective optimization problems (MOOP) and NP-hard problems. In this respect, we formulate a new multi-objective model for vehicle-centered task offloading tacking into account the queuing and computing processes of tasks. The minimization of the average delay time, average energy consumption, and average payment cost for each vehicle is defined as a MOOP. We propose an efficient collaborative offloading approach based on task triage strategy and multi-objective optimization to address the model. Specifically, this approach can be decomposed into two stages. First, a task triage strategy is developed based on a comprehensive analysis of task urgency and task criticality to make offloading decisions for triaged tasks with extreme characteristics. Then, we propose a novel multi-objective optimization framework for the MOOP. Finally, we develop a multi-objective hybrid genetic algorithm that integrates the associative learning immediate memory strategy and genetic operations to solve the MOOP. Extensive experiments and performance evaluations based on real-world traces of taxis demonstrate the effectiveness of the proposed approach. The results indicate that the approach outperforms six other well-known multi-objective algorithms in solving the MOOP. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Gas Source Localization for UAV Using Infotaxis-Based Three-Dimensional Algorithm and Particle Filtering

Gas Source Localization for UAV Using Infotaxis-Based Three-...

引用

第43届中国控制会议

作者： Duan He Cheng Lei Wang Rong Zhang Yu Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology School of Information Science and Engineering Wuhan University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Unmanned aerial vehicles(UAVs) are extensively utilized in gas source localization tasks due to their payload capacity and maneuverability. This paper presents a UAV gas source localization algorithm that utilizes three-dimensional Infotaxis and particle filter. The algorithm is designed for gas source localization of UAVs in dynamic outdoor airflow *** source localization process comprises UAV search area partitioning, particle filter initialization, observation and update of probability map, entropy calculation and direction selection, particle direction and weight update, and UAV movement. To validate the effectiveness of the algorithm, we build a CFD gas environment and UAV source localization platform, and compare it with traditional Infotaxis-based source localization algorithms. The proposed algorithm based on three-dimensional Infotaxis and particle filter demonstrates higher accuracy.

关键词： infotaxis particle filtering gas source localization olfactory drone path planning

来源：评论

学校读者我要写书评

暂无评论

Towards Trustworthy AI for QoE prediction in B5G/6G Networks 1

Towards Trustworthy AI for QoE prediction in B5G/6G Networks

引用

1st International Workshop on Artificial Intelligence in Beyond 5G and 6G Wireless Networks, AI6G 2022

作者： Corcuera Bárcena, José Luis Ducange, Pietro Marcelloni, Francesco Nardini, Giovanni Noferi, Alessandro Renda, Alessandro Stea, Giovanni Virdis, Antonio Department of Information Engineering University of Pisa Largo Lucio Lazzarino 1 Pisa56122 Italy Center for Logistic Systems University of Pisa Via dei Pensieri 60 Livorno57124 Italy

The ability to forecast Quality of Experience (QoE) metrics will be crucial in several applications and services offered by the future B5G/6G networks. However, QoE timeseries forecasting has not been adequately investigated so far, mainly due to the lack of available realistic datasets. In this paper, we first present a novel QoE forecasting dataset obtained from realistic 5G network simulations and characterized by Quality of Service (QoS) and QoE metrics for a video-streaming application;then, we embrace the topical challenge of trustworthiness in the adoption of AI systems for tackling the QoE prediction task. We show how an eXplainable Artificial Intelligence (XAI) model, namely Decision Tree, can be effectively leveraged for addressing the forecasting problem. Finally, we identify federated learning as a suitable paradigm for privacy-preserving collaborative model training and outline the related challenges from both an algorithmic and 6G network support perspective. © 2022 Copyright for this paper by its authors.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Modified Bat Algorithm for Optimal VM’s in Cloud Computing

引用

Computers, Materials & Continua 2022年第8期72卷 2877-2894页

作者： Amit Sundas Sumit Badotra Youseef Alotaibi Saleh Alghamdi Osamah Ibrahim Khalaf Department of Computer Science and Engineering Lovely Professional UniversityPhagwaraPunjab144411India Department of Computer Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Al-Nahrain Nano-Renewable Energy Research Center Al-Nahrain UniversityBaghdad10072Iraq

All task scheduling applications need to ensure that resources are optimally used,performance is enhanced,and costs are *** purpose of this paper is to discuss how to Fitness Calculate Values(FCVs)to provide application software with a reliable solution during the initial stages of load *** cloud computing environment is the subject of this *** consists of both physical and logical components(most notably cloud infrastructure and cloud storage)(in particular cloud services and cloud platforms).This intricate structure is interconnected to provide services to users and improve the overall system’s *** case study is one of the most important segments of cloud computing,i.e.,Load *** paper aims to introduce a new approach to balance the load among Virtual Machines(VM’s)of the cloud computing *** proposed method led to the proposal and implementation of an algorithm inspired by the Bat Algorithm(BA).This proposed Modified Bat Algorithm(MBA)allows balancing the load among virtual *** proposed algorithm works in two variants:MBA with Overloaded Optimal Virtual Machine(MBAOOVM)and Modified Bat Algorithm with Balanced Virtual Machine(MBABVM).MBA generates cost-effective solutions and the strengths of MBA are finally validated by comparing it with Bat Algorithm.

关键词： Bat algorithm cloud computing fitness value calculation load balancing modified bat algorithm

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Robustness Metrics for Defense of Machine Learning systems

Evaluation of Robustness Metrics for Defense of Machine Lear...

引用

International Conference on Military Communications and information systems (ICMCIS)

作者： J. DeMarchi R. Rijken J. Melrose B. Madahar G. Fumera F. Roli E. Ledda M. Aktaş F. Kurth P. Baggenstoss B. Pelzer L. Kanestad Collaborative Engineering Systems & Aerospace Systems Information Supremacy Royal Netherlands Aerospace Centre NLR Amsterdam NLD Cyber & Information Systems Division Defence Science and Technology Laboratory Portondown GBR Department of Electrical and Electronic Engineering University of Cagliari Cagliari ITA Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa ITA Department of Computer Control and Management Engineering Sapienza University of Rome Rome ITA Defence Systems Technologies Division ASELSAN Ankara TUR Fraunhofer Institute for Communication Information Processing and Ergonomics Bonn DEU Swedish Defence Research Agency Cyber Defence and C2 Technology Division Stockholm SWE

In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Gas Classification Method Based on The Improved GasNet

A Novel Gas Classification Method Based on The Improved GasN...

引用

第43届中国控制会议

作者： Xiaolin Qin Lei Cheng Xiang Tao Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology School of Information Science and Engineering Wuhan University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Accurately and promptly identifying harmful gases in the environment can effectively prevent many accidents. Most existing pattern recognition methods are focused on addressing gas classification problems in static scenarios, but the real world is a dynamic and changing environment. Therefore, researching gas classification in continuous learning scenarios will better meet the needs of suddenly emerging gas classification tasks in real-world environments. To address this issue, an incremental learning model was introduced into gas classification, and an improved deep convolutional network was proposed for gas image feature extraction. The proposed model and other baseline methods experimented on an open-source gas dataset. The proposed model reduces knowledge loss due to catastrophic forgetting and effectively classifies the 10 gas samples in the dataset in continuous learning scenarios compared to non-incremental methods. It outperforms other baseline incremental methods by optimizing the network's shortcut connections, making the feature extraction network easier to train and improving gas classification performance. In dynamic learning scenarios, the proposed model achieved a classification accuracy of 86.30% for 10 gas *** experimental results demonstrate that the proposed method effectively mitigates catastrophic forgetting interference and completes gas classification tasks in continuous learning scenarios.

关键词： Gas classification Incremental learning Shortcut connection Catastrophic forgetting

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：