检索结果-内蒙古大学图书馆

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

In-situ fabrication of on-chip 1T'-MoTe_(2)/Ge Schottky junction photodetector for self-powered broadband infrared imaging and position sensing

引用

Nano Research 2024年第6期17卷 5587-5594页

作者： Menglei Zhu Kunxuan Liu Di Wu Yunrui Jiang Xue Li Pei Lin Zhifeng Shi Xinjian Li Ran Ding Yalun Tang Xuechao Yu Longhui Zeng School of Physics and Microelectronics and Key Laboratory of Material PhysicsZhengzhou UniversityZhengzhou 450052China Department of Electrical and Computer Engineering University of California San DiegoLa JollaCA 92093USA State Key Laboratory of Integrated Optoelectronics College of Electronic Science and EngineeringJilin UniversityChangchun 130012China Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou Institute of Nano-Tech and Nano-BionicsChinese Academy of SciencesSuzhou 215123China

High-sensitivity room-temperature multi-dimensional infrared(IR)detection is crucial for military and civilian ***,the gapless electronic structures and unique optoelectrical properties have made the two-dimensional(2D)topological semimetals promising candidates for the realization of multifunctional optoelectronic ***,we demonstrated the in-situ construction of high-performance 1T’-MoTe_(2)/Ge Schottky junction device by inserting an ultrathin AlOx passivation *** good detection performance with an ultra-broadband detection wavelength range of up to 10.6 micron,an ultrafast response time of~160 ns,and a large specific detectivity of over 109 Jones in mid-infrared(MIR)range surpasses that of most 2D materials-based IR sensors,approaching the performance of commercial IR *** on-chip integrated device arrays with 64 functional detectors feature high-resolution imaging capability at room *** these outstanding detection features have enabled the demonstration of position-sensitive detection *** demonstrates an exceptional position sensitivity of 14.9 mV/mm,an outstanding nonlinearity of 6.44%,and commendable trajectory tracking and optoelectronic demodulation *** study not only offers a promising route towards room-temperature MIR optoelectronic applications,but also demonstrates a great potential for application in optical sensing systems.

关键词： MoTe_(2) broadband photodetection Schottky junction imaging position sensitive detector

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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

Cooperative Selection and Communications in 6G Ultra-mMTC IoV Networks 4

Cooperative Selection and Communications in 6G Ultra-mMTC Io...

引用

4th International Symposium on Electrical, Electronics and Information engineering, ISEEIE 2024

作者： Huang, He Huang, Wei College of Communication Technology Chengdu China School of Computer Science and Information Engineering Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei China

ISBN: (纸本)9798350355772

Although Cooperative Communications (CC) already exists in 4G/5G, performance improvement is just not enough. As 5G standard has gradually established recently, CC has been one of most critical communication technologies which plays a founding role in 6G IoV networks. Therefore, it is important to apply collaborative technology to achieve Internet of Everything (IoV) and improve communication quality significantly in 6G IoV ultra-mMTC networks. In this study, we review that collaborative ideology has been regarded as foundation theory which widely exists in future multiple hybrid scenarios, such as, Cognitive Internet of Things (C-IoT) networks, UAVs (Unmanned Aerial Vehicles) communications, air-space-ground integrated networks, underwater acoustic communication and so on. Besides, we discuss key communication technologies that are closely combined with unique communication scenes, and elaborate critical problems that shall be solved in 6G ultra-mMTC IoV networks. Furthermore, we discuss extreme low complexity and fast ultra-massive relays selection algorithm in all sorts of future 6G scenarios. At last, it is concluded that for arbitrary two communication points (source/destination devices, sensors, relays, IoT nodes and so on), ideology of nodes selection of collaborative communication is theory of foundation to realize IoV and optimize communication transmission performance in future networks. © 2024 IEEE.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Frequency Domain Auto-tuning of Structured LPV Controllers for High-Precision Motion Control 63

Frequency Domain Auto-tuning of Structured LPV Controllers f...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Broens, Yorick Butler, Hans Toth, Roland Asml Veldhoven Netherlands Eindhoven University of Technology Department of Electrical Engineering Eindhoven Netherlands Hunren Institute for Computer Science and Control Systems and Control Laboratory Hungary

ISBN: (纸本)9798350316339

Motion systems are a vital part of many industrial processes. However, meeting the increasingly stringent demands of these systems, especially concerning precision and throughput, requires novel control design methods that can go beyond the capabilities of traditional solutions. Traditional control methods often struggle with the complexity and position-dependent effects inherent in modern motion systems, leading to compromises in performance and a laborious task of controller design. This paper addresses these challenges by introducing a novel structured feedback control auto-tuning approach for multiple-input multiple-output (MIMO) motion systems. By leveraging frequency response function (FRF) estimates and the linear-parameter-varying (LPV) control framework, the proposed approach automates the controller design, while providing local stability and performance guarantees. Key innovations include norm-based magnitude optimization of the sensitivity functions, an automated stability check through a novel extended factorized Nyquist criterion, a modular structured MIMO LPV controller parameterization, and a controller discretization approach which preserves the continuous-time (CT) controller parameterization. The proposed approach is validated through experiments using a state-of-the-art moving-magnet planar actuator prototype. © 2024 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

A robust and consistent stack generalized ensemble-learning framework for image segmentation

引用

Journal of engineering and Applied science 2023年第1期70卷 74页

作者： Faska, Zahra Khrissi, Lahbib Haddouch, Khalid El Akkad, Nabil Laboratory of Engineering Systems and Applications ENSA Sidi Mohamed Ben Abdellah University Fez Morocco LIIAN Department of Computer Science FSDM of Fez Sidi Mohamed Ben Abdellah University Fez Morocco

In the present study, we aim to propose an effective and robust ensemble-learning approach with stacked generalization for image segmentation. Initially, the input images are processed for feature extraction and edge detection using the Gabor filter and the Canny algorithms, respectively;our main goal is to determine the most feature descriptions. Subsequently, we applied the stacking generalization technique, which is generally built with two main learning levels. The first level is composed of two algorithms that give good results in the literature, namely: LightGBM (Light Gradient Boosting Machine) and SVM (support vector machine). The second level is the meta-model in which we use a predictor model that takes the base-level predictions to improve the accuracy of the final prediction. In the stacked generalization process, we use the Extreme Gradient Boosting (XGBoost);it takes as input the sub-models’ outputs to better classify each pixel of the image to give the final prediction. Today, several research works exist in the literature using different machine learning algorithms;in fact, instead of trying to find a single efficient and optimal learner, ensemble-based techniques take the advantage of each basic model;they integrate their outputs to obtain a more consistent and reliable learner. The result obtained from the models of individuals and our proposed approach is compared using a set of evaluation measures for image quality such as IoU, DSC, CC, SSIM, SAM, and UQI. The evaluation and a comparison of the results obtained showed more consistent predictions for the proposed model. Thus, we have made a comparison with some recent deep learning-based unsupervised segmentation methods. The evaluation and a comparison of the results obtained showed more coherent predictions for our stacked generalization in terms of precision, robustness, and consistency. © 2023, The Author(s).

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

WIP: An Engaging Undergraduate Intro to Model Checking in Software engineering Using TLA+ 54

WIP: An Engaging Undergraduate Intro to Model Checking in So...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Läufer, Konstantin Mertin, Gunda Thiruvathukal, George K. Loyola University Software and Systems Laboratory Department of Computer Science Chicago United States Institute for Software Engineering and Programming Languages University of Lübeck Germany

ISBN: (纸本)9798350351507

Background: In this Innovative Practice Work in Progress, we present our initial efforts to integrate formal methods, with a focus on model-checking specifications written in Temporal Logic of Actions (TLA+), into computer science education, targeting undergraduate juniors/seniors and graduate students. Many safety-critical systems and services crucially depend on correct and reliable behavior. Formal methods can play a key role in ensuring correct and safe system behavior, yet remain underutilized in educational and industry contexts. Aims: We aim to (1) qualitatively assess the state of formal methods in computer science programs, (2) construct level-appropriate examples that could be included midway into one's undergraduate studies, (3) demonstrate how to address successive 'failuresy' through progressively stringent safety and liveness requirements, and (4) establish an ongoing framework for assessing interest and relevance among students. Methods: We detail our pedagogical strategy for embedding TLA+ into an intermediate course on formal methods at our institution. After starting with a refresher on mathematical logic, students specify the rules of simple puzzles in TLA+ and use its included model checker (known as TLC) to find a solution. We gradually escalate to more complex, dynamic, event-driven systems, such as the control logic of a microwave oven, where students will study safety and liveness requirements. We subsequently discuss explicit concurrency, along with thread safety and deadlock avoidance, by modeling bounded counters and buffers. Results: Our initial findings suggest that through careful curricular design and choice of examples and tools, it is possible to inspire and cultivate a new generation of software engineers proficient in formal methods. Conclusions: Our initial efforts suggest that 84% of our students had a positive experience in our formal methods course. Our future plans include a longitudinal analysis within our own institution and

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Applying Process Mining to Sensor Data in Smart Environment: A Comparative Study 7th

Applying Process Mining to Sensor Data in Smart Environment:...

引用

7th International Conference on Smart City Applications, SCA 2022

作者： Iman, Elkodssi Laanaoui, My Driss Sbai, Hanae Mathematics Computer Science and Application Laboratory FST Mohammedia Hassan II University of Casablanca Casablanca Morocco Computer Systems Engineering Laboratory Cadi Ayyad University of Marrakech Marrakech Morocco

ISBN: (纸本)9783031268519

Business process management is a popular approach that has caught the attention of several researchers over the years. BPM has been extended to Business Process Intelligence in order to add more intelligence to managing business processes. Process Mining is one of the emerging areas of Business Process Intelligence, which aims to automatically discover, verify and improve business processes. Nowadays, the emergence of smart environment. The data that occurs in this environment are more varied and are kind of unstructured data. In this sense, applying process mining, to analyze processes in a smart context is a challenging task, since the process mining techniques relies on a structured event log. In this paper, we present a comparative study of existing approaches on applying process mining techniques in smart BPM, as a first step towards developing a new approach to discover and analyze business processes from sensor data perspective. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Reassessing Glove Embeddings in Deep Learning: A Comparative Study with Classical ML Approaches 15

Reassessing Glove Embeddings in Deep Learning: A Comparative...

引用

15th International Conference on Emerging Ubiquitous systems and Pervasive Networks / 14th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, EUSPN/ICTH 2024

作者： Labd, Zakia Bahassine, Said Housni, Khalid Aadi, Fatima Zahrae Aithamou Laboratory of research in informatics LatRI Department of Computer Science Faculty of Sciences Ibn Tofail University Kenitra Morocco Laboratory of Artificial Intelligence and Complex Systems Engineering Department of Computer Science National Higher School of Arts and Crafts Hassan II University Casablanca Morocco

The importance of text classification algorithms has increased due to the growing availability of large-scale data. This has led to a greater demand for efficient classification techniques and encoding algorithms. Word embedding techniques, like Glove, have shown significant success in encoding semantic relationships between words. This research paper aims to reassess the effectiveness of Glove embeddings coupled with deep learning algorithms. The impact of Glove embedding on two widely used deep learning models: Recurrent Neural Networks (RNN) and Recurrent Convolutional Neural Networks (RCNN) is analyzed. The results highlight the impact of Glove embeddings on deep learning models, showcasing significant performance enhancements in some cases while having minimal effects in others. By examining the impact of Glove embeddings on traditional ML algorithms in a previous study, valuable context for understanding the performance differences between the two approaches is obtained. © 2024 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks

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：