检索结果-内蒙古大学图书馆

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Reference trustable decoding: a training-free augmentation paradigm for large language models 24

Reference trustable decoding: a training-free augmentation p...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Luohe Shi Yao Yao Zuchao Li Lefei Zhang Hai Zhao National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan P. R. China Department of Computer Science and Engineering Shanghai Jiao Tong University

ISBN: (纸本)9798331314385

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage. Our code can be found at https://***/ShiLuohe/ReferenceTrustableDecoding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based models for predicting calibration cost of flowmeters in the oil industry

引用

Neural Computing and Applications 2024年第4期37卷 2537-2556页

作者： Mohammed, Awsan Javaid, Abdullah Ghaithan, Ahmed AlDhafer, Osamah Al-shaibani, Maged S. Alshibani, Adel Architectural Engineering and Construction Management Department King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Interdisciplinary Research Center for Smart Mobility and Logistics King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Software Engineering University of Prince Mugrin Madinah40202 Saudi Arabia Department of Computer Science King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Interdisciplinary Research Center of Construction and Building Materials King Fahd University of Petroleum and Minerals Dhahran34463 Saudi Arabia

Accurate measurement of liquid volume in pipelines is a crucial and sensitive process in the petroleum industry. Flowmeter is a common device used to measure the volume of the liquid passing through the pipeline and to invoice clients. Improving flowmeter calibration preserves functionality, identifies issues, and ensures accurate market valuation and pricing. Estimating the cost of third-party calibration is a challenging task for decision-makers in the petroleum industry. Thus, this paper proposes machine-learning algorithms to predict and analyze the cost of flowmeter calibration in the petroleum industry. These techniques include artificial neural networks, SGDRegressor, XGBoost, AdaBoost, support vector machine, K-nearest neighbors, and random forest. Prior to developing the model, the factors impacting the cost calibration of the flowmeters are identified from the literature and finalized by oil and gas experts. In addition, the relationship between the input factors and the output is examined to ensure the quality of the data. The analysis indicated that the most crucial factors affecting the calibration cost are the flowmeter size, flange class, flowmeter type, calibration method, and calibration factor. Furthermore, the developed machine learning-based models are validated by using 153 new additional data. The results revealed that the random forest is the best technique for estimating calibration costs, with an accuracy of 99%, followed by AdaBoost with an accuracy of 97%, and artificial neural network with an accuracy of 96%. The proposed models provide superior accuracy and efficiency which will significantly contribute to estimating calibration costs, assisting decision-makers in establishing a budget for flowmeter calibration. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

How Do Hackathons Foster Creativity? Towards Automated Evaluation of Creativity at Scale 25

How Do Hackathons Foster Creativity? Towards Automated Evalu...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Falk, Jeanette Chen, Yiyi Rafner, Janet Zhang, Mike Bjerva, Johannes Nolte, Alexander Computer Science Aalborg University Copenhagen Denmark Department of Computer Science Aalborg University Copenhagen Denmark Center for Hybrid Intelligence Department of Management Aarhus University Aarhus Denmark Aarhus Institute for Advanced Studies Aarhus University Aarhus Denmark Software Engineering and Technology Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9798400713941

Hackathons have become popular collaborative events for accelerating the development of creative ideas and prototypes. There are several case studies showcasing creative outcomes across domains such as industry, education, and research. However, there are no large-scale studies on creativity in hackathons which can advance theory on how hackathon formats lead to creative outcomes. We conducted a computational analysis of 193,353 hackathon projects. By operationalizing creativity through usefulness and novelty, we refined our dataset to 10,363 projects, allowing us to analyze how participant characteristics, collaboration patterns, and hackathon setups influence the development of creative projects. The contribution of our paper is twofold: We identified means for organizers to foster creativity in hackathons. We also explore the use of large language models (LLMs) to augment the evaluation of creative outcomes and discuss challenges and opportunities of doing this, which has implications for creativity research at large. © 2025 Copyright held by the owner/author(s).

关键词： Hackathons

来源：评论

学校读者我要写书评

暂无评论

Submarine Hunter: Efficient and Secure Multi-Type Unmanned Vehicles

引用

computers, Materials & Continua 2023年第7期76卷 573-589页

作者： Halah Hasan Mahmoud Marwan Kadhim Mohammed Al-Shammari Gehad Abdullah Amran Elsayed Tag eldin Ala R.Alareqi Nivin A.Ghamry Ehaa A.Lnajjar Esmail Almosharea Computer Center University of BaghdadBaghdad6751Iraq Department of Management Science and Engineering Dalian University of TechnologyLiaoningDalian116024China Department of Information Technology Faculty of Computer Sciences and Information Technology AL Razi UniversitySana’aYemen Faculty of Engineering and Technology Future University in EgyptNew Cairo11835Egypt Faculty of Engineering Mechanics Dalian University of TechnologyLiaoningDalian116024China Faculty of Computers and Artificial Intelligence Cairo UniversityGizaEgypt Department of Business Administration Dalian University of TechnologyLiaoningDalian116024China College of Software Engineering Dalian University of TechnologyChina

Utilizing artificial intelligence(AI)to protect smart coastal cities has become a novel vision for scientific and industrial *** of these AI technologies is using efficient and secure multi-environment Unmanned Vehicles(UVs)for anti-submarine *** study’s contribution is the early detection of a submarine assault employing hybrid environment UVs that are controlled using swarm optimization and secure the information in between UVs using a decentralized cybersecurity *** Dragonfly Algorithm is used for the orientation and clustering of the UVs in the optimization approach,and the Re-fragmentation strategy is used in the Network layer of the TCP/IP protocol as a cybersecurity *** research’s noteworthy findings demonstrate UVs’logistical capability to promptly detect the target and address the problem while securely keeping the drone’s geographical *** results suggest that detecting the submarine early increases the likelihood of averting a *** dragonfly strategy of sensing the position of the submersible and aggregating around it demonstrates the reliability of swarm intelligence in increasing access *** communication between Unmanned Aerial Vehicles(UAVs)improves the level of secrecy necessary for the *** swarm navigation is based on a peer-to-peer system,which allows each UAV to access information from its ***,in turn,helps the UAVs to determine the best route to take and to avoid collisions with other *** dragonfly strategy also increases the speed of the mission by minimizing the time spent finding the target.

关键词： Unmanned vehicles unmanned aerial vehicles unmanned underwater vehicles high altitude unmanned aerial vehicles anti-submarine warfare re-fragmentation dragonfly algorithm

来源：评论

学校读者我要写书评

暂无评论

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics 40

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficien...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Chen, Yu Zhang, Sheng Zhou, Ziying Wang, Xiaokun Liang, Yu Chen, Ning Yan, Yuting Xiao, Mingjun Wu, Jie Qian, Zhuzhong Xu, Harry Nanjing University State Key Lab. for Novel Software Technology China School of Systems Science Beijing Normal University China School of Computer and Electronic Information School of Artificial Intelligence Nanjing Normal University China School of Computer Science and Technology University of Science and Technology of China China Temple University Center for Networked Computing United States Samueli School of Engineering University of California Computer Science Department Los Angeles United States

ISBN: (纸本)9798350317152

In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy;meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning

arXiv

引用

arXiv 2024年

作者： Gilkarov, Daniel Dubin, Ran The Department of Computer Science Ariel Cyber Innovation Center Ariel University Ariel Israel The Department of Computer and Software Engineering Ariel Cyber Innovation Center Ariel University Ariel Israel

The potential for exploitation of AI models has increased due to the rapid advancement of Artificial Intelligence (AI) and the widespread use of platforms like Model Zoo for sharing AI models. Attackers can embed malware within AI models through steganographic techniques, taking advantage of the substantial size of these models to conceal malicious data and use it for nefarious purposes, e.g. Remote Code Execution. Ensuring the security of AI models is a burgeoning area of research essential for safeguarding the multitude of organizations and users relying on AI technologies. This study leverages well-studied image few-shot learning techniques by transferring the AI models to the image field using a novel image representation. Applying few-shot learning in this field enables us to create practical models, a feat that previous works lack. Our method addresses critical limitations in state-of-the-art detection techniques that hinder their practicality. This approach reduces the required training dataset size from 40000 models to just 6. Furthermore, our methods consistently detect delicate attacks of up to 25% embedding rate and even up to 6% in some cases, while previous works were only shown to be effective for a 100%-50% embedding rate. We employ a strict evaluation strategy to ensure the trained models are generic concerning various factors. In addition, we show that our trained models successfully detect novel spread-spectrum steganography attacks, demonstrating the models' impressive robustness just by learning one type of attack. We open-source our code to support reproducibility and enhance the research in this new field. © 2024, CC BY-NC-ND.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Inaudible Sound Covert Channel with Anti-Jamming Capability: Attacks vs. Countermeasure

引用

Journal of Electronic science and Technology 2022年第4期20卷 396-415页

作者： Xiao-Hang Wang Shou-Bin Li Ying-Tao Jiang Amit Kumar Singh Bi-Yun Ma Le-Tian Huang Mei Yang Fen Guo School of Cyber Science and Technology Zhejiang UniversityHangzhou 310012 ZJU-Hangzhou Global Scientific and Technological Innovation Center Hangzhou 310012 School of Software Engineering South China University of TechnologyGuangzhou 510006 Department of Electrical and Computer Engineering University of NevadaLas Vegas 89154 School of Computer Science and Electronic Engineering University of EssexColchester CO43SQ School of Electronics and Information Engineering South China University of TechnologyGuangzhou 510640 School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610054

When an inaudible sound covert channel(ISCC)attack is launched inside a computer system,sensitive data are converted to inaudible sound waves and then *** receiver at the other end picks up the sound signal,from which the original sensitive data can be *** a forceful countermeasure against the ISCC attack,strong noise can be used to jam the channel and literally shut down any possible sound data *** this paper,enhanced ISCC is proposed,whose transmission frequency can be dynamically ***,if the transmitter detects that the covert channel is being jammed,the transmitter and receiver both will switch to another available frequency and re-establish their communications,following the proposed communications *** results show that the proposed enhanced ISCC can remain connected even in the presence of a strong jamming noise ***,a detection method based on frequency scanning is proposed to help to combat such an anti-jamming sound *** the proposed countermeasure,the bit error rate(BER)of the data communications over enhanced ISCC soars to more than 48%,essentially shutting down the data transmission,and thus neutralizing the security threat.

关键词： Countermeasure inaudible sound covert channel(ISCC)

来源：评论

学校读者我要写书评

暂无评论

Attack and Improvement of a Hidden Vector Encryption Scheme 12

Attack and Improvement of a Hidden Vector Encryption Scheme

引用

12th International Conference on Electronics, Communications and Networks, CECNet 2022

作者： Wang, Ke Wang, Zhikun Luo, Song Guan, Zhi Key Laboratory of High Confidence Software Technologies Peking University MoE Beijing China Department of Computer Science and Technology Eecs Peking University Beijing China School of Computer Science and Engineering Chongqing University of Technology Chongqing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (纸本)9781643683683

Hidden Vector Encryption (HVE) is a new kind of attribute-based encryption in which a vector is hidden in the ciphertext or linked with the secret key. In ESORICS 2014, Phuong et al. proposed an HVE scheme with constant-size ciphertext which is constructed in the prime order setting. In this paper, we show that Phuong et al.'s scheme is not vector-hiding due to public parameters in their scheme leak some information about vectors. Furthermore, an improved HVE scheme is proposed in the prime order setting and its security is proven in the security model. Comparison shows our scheme has more efficient in decryption than current other HVE schemes. © 2022 The authors and IOS Press.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

SDN control plane security: Attacks and mitigation techniques 2021

SDN control plane security: Attacks and mitigation technique...

引用

4th International Conference on Networking, Information Systems and Security, NISS 2021

作者： Fatima, Kiran Zahoor, Kanwal Bawany, Narmeen Zakaria Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women

ISBN: (纸本)9781450388719

Traditional networks are complex and hard to manage due to many reasons such as manual configuration requirements of dedicated devices, lack of flexibility and a non-dynamic approach. To overcome these limitations and to meet the challenges of modern networks a new networking paradigm software Defined Networking (SDN) has been introduced. SDN presents a centralized and completely dynamic environment which provides flexibility and programmability in networks. It enables the network to be controlled centrally and intelligently using multiple software applications. SDN being in its infancy, brings along new challenges. Standardization of various interfaces, scalability, compatibility of contrasting or divergent networks, and vulnerability issues are few of them. This paper discusses various vulnerabilities and possible attacks on every layer of an SDN and focuses on control plane attacks. Further, it presents a comprehensive survey on numerous attacks on the brain of an SDN i.e. the control plane along with existing solutions. The study concludes that despite the challenges that are worth debating, SDN has many characteristics that make it an ideal candidate for future networks. © 2021 ACM.

关键词： Attacks on control plane SDN security software defined network (SDN) Vulnerabilities of SDN

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：