检索结果-内蒙古大学图书馆

作者： Xie, Gengsheng Wen, Xianbin Yuan, Liming Wang, Jianchen Guo, Changlun Jia, Yansong Li, Minghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

Learning distinguishing features from training datasets while filtering features of occlusions is critical to person retrieval scenarios. Most of the current person re-identification (Re-ID) methods based on classification or deep metric representation learning tend to overlook occlusion issues on the training set. Such representations from obstacles are easily over-fitted and misleading due to being considered as a part of the human body. To alleviate the occlusion problem, we propose a pose-guided feature region-based fusion network (PFRFN), to utilize pose landmarks as guidance to guide local learning for a good property of local feature, and the representation learning risk is evaluated on each part loss separately. Compared with only using global classification loss, concurrently considering local loss and the results of robust pose estimation enable the deep network to learn the representations of the body parts that prominently displayed in the image and gain the discriminative faculties on occluded scenes. Experimental results on multiple datasets, i.e., Market-1501, DukeMTMC, CUHK03, demonstrate the effectiveness of our method in a variety of scenarios. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Analog parallel processor for broadband multifunctional integrated system based on silicon photonic platform

引用

Light(Science & Applications) 2025年第3期14卷 746-756页

作者： Na Qian Defu Zhou Haowen Shu Ming Zhang Xingjun Wang Daoxin Dai Xiao Deng Weiwen Zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghaiChina State Key Laboratory of Advanced Optical Communications System and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBejingChina State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and EngineeringInternational Research Center for Advanced PhotonicsZhejiang UniversityHangzhouChina

Sharing the hardware platform between diverse information systems to establish full cooperation among different functionalities has attracted substantial ***,broadband multifunctional integrated systems with large operating frequency ranges are challenging due to the bandwidth and computing speed restrictions of electronic ***,we report an analog parallel processor(APP)based on the silicon photonic platform that directly discretizes and parallelizes the broadband signal in the analog *** APP first discretizes the signal with the optical frequency comb and then adopts optical dynamic phase interference to reassign the analog signal into 2N parallel *** photonic analog parallelism,data rate and data volume in each sequence are simultaneously compressed,which mitigates the requirement on each parallel computing ***,the fusion of the outputs from each computing core is equivalent to directly processing broadband *** the proof-of-concept experiment,two-channel analog parallel processing of broadband radar signals and high-speed communication signals is implemented on the single photonic integrated *** bandwidth of broadband radar signal is 6 GHz and the range resolution of 2.69 cm is *** wireless communication rate of 8 Gbit/s is also *** the bandwidth and speed limitations of the single-computing core along with further exploring the multichannel potential of this architecture,we anticipate that the proposed APP will accelerate the development of powerful optoelectronic processors as critical support for applications such as satellite networks and intelligent driving.

关键词： analog parallel processor sharing hardware platform multifunctional integrated systems establish full cooperation different functionalities analog parallel processor app based silicon photonic platform electronic circuitryherewe broadband signal

来源：评论

学校读者我要写书评

暂无评论

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Wu, Guotong Nan, Yang Shang, Ke Ishibuchi, Hisao Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9781665410205

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Evolving Lightweight Intrusion Detection systems for RPL-Based Internet of Things 26th

Evolving Lightweight Intrusion Detection Systems for RPL-Ba...

引用

26th International Conference on Applications of Evolutionary Computation, EvoApplications 2023, held as part of EvoStar 2023

作者： Deveci, Ali Yilmaz, Selim Sen, Sevil WISE Laboratory Department of Computer Engineering Hacettepe University Ankara Turkey Department of Software Engineering Muğla Sıtkı Koçman University Muğla Turkey

ISBN: (纸本)9783031302282

With the integration of efficient computation and communication technologies into sensory devices, the Internet of Things (IoT) applications have increased tremendously in recent decades. While these applications provide numerous benefits to our daily lives, they also pose a great potential risk in terms of security. One of the reasons for this is that devices in IoT-based networks are highly resource constrained and interconnected over lossy links that can be exposed by attackers. The Routing Protocol for Low-Power and Lossy Network (RPL) is the standard routing protocol for such lossy networks. Despite the efficient routing built by RPL, this protocol is susceptible to insider attacks. Therefore, researchers have been working on developing effective intrusion detection systems for RPL-based IoT. However, most of these studies consume excessive resources (e.g., energy, memory, communication, etc.) and do not consider the constrained characteristics of the network. Hence, they might not be suitable for some devices/networks. Therefore, in this study, we aim to develop an intrusion detection system (IDS) that is both effective and efficient in terms of the cost consumed by intrusion detection (ID) nodes. For this multiple-objective problem, we investigate the use of evolutionary computation-based algorithms and show the performance of evolved intrusion detection algorithms against various RPL-specific attacks. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

RSP-gcForest: A Distributed Deep Forest via Random Sample Partition

RSP-gcForest: A Distributed Deep Forest via Random Sample Pa...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Li, Mark Junjie Cai, Wenzhu Lin, Yigang Huang, Sunjie Huang, Joshua Zhexue Peng, Patrick Xiaogang Shenzhen University College of Computer Science and Software Engineering Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Shenzhen Academy of Inspection and Quarantine China

ISBN: (纸本)9798350324457

Deep Forest, a powerful alternative to deep neural networks, has gained much attention due to its advantages, such as low complexity, minimal hyperparameter requirements, and strong application performance. In the current big data environment, where data volumes and model complexities are growing rapidly, distributed computing is needed to increase computational efficiency. Recently, a distributed deep forest approach, called BLB-gcForest (Bag of Little Bootstraps-gcForest), has been successful in reducing training instances within cascade forests, combining BLB and granularity segmentation, thus improving the computational efficiency and scalability of distributed deep forests. However, it still transmits the entire data set between layers and requires double sampling with BLB, limiting the amount of data and the scalability of resource utilization. This paper introduces a novel algorithm, RSP-gcForest, based on Random Sample Partition (RSP) to improve distributed deep forests computational efficiency and scalability. RSP-gcForest uses block-level samples that replace the full dataset, significantly reducing interlayer instance transmission and prediction within cascade forests. Additionally, RSP blocks are integrated with the segmentation granularity of cascade forests for ensemble learning, effectively addressing computational efficiency and resource constraints. We conducted experiments on four extensive datasets using Spark and evaluated performance across five key metrics. The results clearly show that RSP-gcForest, while maintaining high classification quality, surpasses state-of-the-art methods in terms of computational efficiency and resource utilization. Furthermore, it achieves superior load balancing, demonstrating its potential as a powerful tool in big data and distributed computing. © 2023 IEEE.

关键词： Deep forest Distributed Computing Ensemble Learning Random Sample Partition

来源：评论

学校读者我要写书评

暂无评论

Improved Demonstration-Knowledge Utilization in Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2139-2150页

作者： Liu, Yanyu Zeng, Yifeng Ma, Biyang Pan, Yinghui Gao, Huifan Zhang, Yuting Xiamen University Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Department of Automation Xiamen361102 China Northumbria University Department of Computer and Information Sciences NewcastleNE1 8ST United Kingdom Minnan Normal University Department of Computer Science Zhangzhou363000 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Reinforcement learning (RL) has made great success in recent years. Generally, the learning process requires a huge amount of interaction with the environment before an agent can achieve acceptable performance. This motivates many techniques, such as incorporating prior knowledge which is usually presented as experts' demonstration, and using a probability distribution to represent state-and-action values, to accelerate the learning process. The methods perform well when the prior knowledge is genuinely correct and no much change occurs to the learning environment. However, the requirement is not perfectly realistic in many complex applications. The demonstration knowledge may not reflect the true environment and even be full of noise. In this article, we introduce a dynamic distribution merging method to improve knowledge utilization in a general RL algorithm, namely Q-learning. The new method adapts a normal distribution to represent state-action values and merges the prior and learned knowledge in a discriminative way. We theoretically analyze the new learning method and demonstrate its empirical performance over multiple problem domains. © 2020 IEEE.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

A study on the impact of pre-trained model on Just-In-Time defect prediction 23

A study on the impact of pre-trained model on Just-In-Time d...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China City University of Hong Kong Department of Computer Science Hong Kong

ISBN: (纸本)9798350319583

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone's pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Towards Classifying File Segments in Memory Using Machine-Learning 9

Towards Classifying File Segments in Memory Using Machine-Le...

引用

9th International Conference on Information Technology Trends, ITT 2023

作者： Al-Saleh, Mohammed I. Alkouz, Akram Alarabeyyat, Abdulsalam Bouchahma, Majed Jordan University of Science and Technology Computer Science Department Jordan Higher Colleges of Technology Computer Information System United Arab Emirates Al-Balqa Applied University Software Engineering Department Jordan-Salt Jordan

ISBN: (纸本)9798350327502

Digital media triage is a main challenge that faces a digital investigator. Knowing what might be useful during crime investigation could greatly save the investigator's time and enhance outcomes. Memory investigation can get potential benefit from the triage process because of its scattered and diverse contents. The Operating system's paging scheme might map the contents of a file into non-consecutive page frames in the physical memory, making the file-type classification and identification process harder. This paper tackles the memory content triage problem at the page level using a machine-learning methodology. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Dynamic State Estimation for DFIG with Unknown Inputs Based on Cubature Kalman Filter and Adaptive Interpolation

引用

Journal of Modern Power systems and Clean Energy 2023年第4期11卷 1086-1099页

作者： Maolin Zhu Hao Liu Junbo Zhao Bendong Tan Tianshu Bi Samson Shenglong Yu State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijingChina Department of Electrical and Computer Engineering University of ConnecticutStorrs06269USA School of Engineering Deakin University75 Pigdons RoadWaurn PondsVIC3216Australia

Dynamic state estimation(DSE)accurately tracks the dynamics of power systems and demonstrates the evolution of the system state in real *** paper proposes a DSE approach for a doubly-fed induction generator(DFIG)with unknown inputs based on adaptive interpolation and cubature Kalman filter(AICKF-UI).DFIGs adopt different control strategies in normal and fault conditions;thus,the existing DSE approaches based on the conventional control model of DFIG are not applicable in all ***,the DSE model of DFIGs is reformulated to consider the converter controller outputs as unknown inputs,which are estimated together with the DFIG dynamic states by an exponential smoothing model and augmented-state cubature Kalman ***,as the reporting rate of existing synchro-phasor data is not sufficiently high to capture the fast dynamics of DFIGs,a large estimation error may occur or the DSE approach may *** this end,in this paper,a local-truncation-error-guided adaptive interpolation approach is *** simulations conducted on a wind farm and the modified IEEE 39-bus test system show that the proposed AICKF-UI can(1)effectively address the divergence issues of existing cubature Kalman filters while being computationally more efficient;(2)accurately track the dynamic states and unknown inputs of the DFIG;and(3)deal with various types of system operating conditions such as time-varying wind and different system faults.

关键词： Adaptive interpolation cubature Kalman filter doubly-fed induction generator(DFIG) dynamic state estimation unknown input

来源：评论

学校读者我要写书评

暂无评论

GPT-4 enhanced multimodal grounding for autonomous driving:Leveraging cross-modal attention with large language models

引用

Communications in Transportation Research 2024年第1期4卷 5-23页

作者： Haicheng Liao Huanming Shen Zhenning Li Chengyue Wang Guofa Li Yiming Bie Chengzhong Xu State Key Laboratory of Internet of Things for Smart City and Department of Computer and Information Science University of MacaoMacao SAR999078China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610000China State Key Laboratory of Internet of Things for Smart City and Departments of Civil and Environmental Engineering and Computer and Information Science University of MacaoMacao SAR999078China State Key Laboratory of Internet of Things for Smart City and Departments of Civil and Environmental Engineering University of MacaoMacao SAR999078China College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing400030China School of Transportation Jilin UniversityChangchun130000China

In the field of autonomous vehicles(AVs),accurately discerning commander intent and executing linguistic commands within a visual context presents a significant *** paper introduces a sophisticated encoder-decoder framework,developed to address visual grounding in *** Context-Aware Visual Grounding(CAVG)model is an advanced system that integrates five core encoders—Text,Emotion,Image,Context,and Cross-Modal—with a multimodal *** integration enables the CAVG model to adeptly capture contextual semantics and to learn human emotional features,augmented by state-of-the-art Large Language Models(LLMs)including *** architecture of CAVG is reinforced by the implementation of multi-head cross-modal attention mechanisms and a Region-Specific Dynamic(RSD)layer for attention *** architectural design enables the model to efficiently process and interpret a range of cross-modal inputs,yielding a comprehensive understanding of the correlation between verbal commands and corresponding visual *** evaluations on the Talk2Car dataset,a real-world benchmark,demonstrate that CAVG establishes new standards in prediction accuracy and operational ***,the model exhibits exceptional performance even with limited training data,ranging from 50%to 75%of the full *** feature highlights its effectiveness and potential for deployment in practical AV ***,CAVG has shown remarkable robustness and adaptability in challenging scenarios,including long-text command interpretation,low-light conditions,ambiguous command contexts,inclement weather conditions,and densely populated urban environments.

关键词： Autonomous driving Visual grounding Cross-modal attention Large language models Human-machine interaction

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：