检索结果-内蒙古大学图书馆

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

作者： William T. Redman Francisco Acosta Santiago Acosta-Mendoza Nina Miolane Intelligent Systems Center Johns Hopkins Applied Physics Laboratory Department of Physics University of California Santa Barbara Dynamical Neuroscience University of California Santa Barbara Department of Electrical & Computer Engineering University of California Santa Barbara

ISBN: (纸本)9798331314385

Success in collaborative and competitive environments, where agents must work with or against each other, requires individuals to encode the position and trajectory of themselves and others. Decades of neurophysiological experiments have shed light on how brain regions [e.g., medial entorhinal cortex (MEC), hippocampus] encode the self's position and trajectory. However, it has only recently been discovered that MEC and hippocampus are modulated by the positions and trajectories of others. To understand how encoding spatial information of multiple agents shapes neural representations, we train a recurrent neural network (RNN) model that captures properties of MEC to path integrate trajectories of two agents simultaneously navigating the same environment. We find significant differences between these RNNs and those trained to path integrate only a single agent. At the individual unit level, RNNs trained to path integrate more than one agent develop weaker grid responses, stronger border responses, and tuning for the relative position of the two agents. At the population level, they develop more distributed and robust representations, with changes in network dynamics and manifold topology. Our results provide testable predictions and open new directions with which to study the neural computations supporting spatial navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unraveling the ‘Anomaly’ in Time Series Anomaly Detection: A Self-supervised Tri-domain Solution

arXiv

引用

arXiv 2023年

作者： Sun, Yuting Pang, Guansong Ye, Guanhua Chen, Tong Hu, Xia Yin, Hongzhi School of Electrical Engineering and Computer Science The University of Queensland Australia School of Computing and Information Systems Singapore Management University Singapore Research and Development Department Deep Neural Computing Company Limited Department of Computer Science Rice University United States

The ongoing challenges in time series anomaly detection (TSAD), notably the scarcity of anomaly annotations and the variability in anomaly lengths and shapes, have led to the need for a more all-encompassing and efficient solution. As limited anomaly labels pose a significant obstacle for traditional supervised models in anomaly classification, various state-of-the-art deep learning techniques, such as self-supervised learning, have been introduced to tackle this issue. However, they encounter difficulties handling variations in anomaly lengths and shapes, limiting their adaptability to diverse anomalies. Additionally, many benchmark datasets suffer from the problem of having explicit anomalies that even random functions can detect. This problem is exacerbated by ill-posed evaluation metrics, such as point adjustment (PA) prior to scoring, which can result in inflated model performance. In this context, we propose a novel self-supervised learning based Tri-domain Anomaly Detector (TriAD), which addresses these challenges by modeling features across three data domains – temporal, frequency, and residual domains – without relying on anomaly labels. Unlike traditional contrastive learning methods, TriAD employs both inter-domain and intra-domain contrastive loss to learn common attributes among normal data and differentiate them from anomalies. Additionally, our approach can detect anomalies of varying lengths by integrating with a discord discovery algorithm. It is worth noting that this study is the first to reevaluate the deep learning potential in TSAD, utilizing both rigorously designed datasets (i.e., UCR Time Series Anomaly Archive) and evaluation metrics (i.e., PA%K and affiliation). Through experimental results on the UCR dataset, TriAD demonstrates a significant improvement in prediction performance across diverse evaluation metrics, achieving an impressive three-fold increase in PA%K based F1 scores over state-of-the-art (SOTA) deep learning models. Moreover

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Internal short circuit fault diagnosis for automotive lithium-ion batteries using an adaptive parameter identification model

引用

Measurement: Journal of the International Measurement Confederation 2025年 253卷

作者： Tao, Qian Wang, Yiming Tian, Engang Tao, Hongfeng Chen, Hongtian Chen, Yiyang School of Mechanical and Electrical Engineering Soochow University Suzhou215137 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Jiangnan University Wuxi Jiangsu214122 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China

This paper develops a model-based diagnostic method for internal short circuit (ISC) faults in lithium-ion batteries. This method utilizes a second-order equivalent circuit model (ECM) combined with a recursive least squares method with an adaptive forgetting factor for online parameter identification, with initial parameters optimized by a particle swarm optimization (PSO) algorithm. An extended Kalman filter (EKF) is then employed for state estimation to generate residuals, which are analyzed using the refined cumulative sum (CUSUM) statistical method to detect and diagnose ISC faults. Experimental results show that this method effectively identifies ISC faults in automotive power batteries under various initial state of charge (SOC) levels and fault-free conditions. At 100% initial SOC, fault detection times are 104 seconds for a 15Ω fault, 77 seconds for a 10Ω fault, and 27 seconds for a 1Ω fault;at 90% initial SOC, detection for a 10Ω fault takes 97 seconds, demonstrating high accuracy and robustness. © 2025 Elsevier Ltd

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

A Six Components Seismic Detection Method Based on Rotation and Motion 13th

A Six Components Seismic Detection Method Based on Rotation ...

引用

13th International Field Exploration and Development Conference, IFEDC 2023

作者： Feng, Hai-Xin Li, You-Ming Si, Jie-Ge Li, Zheng-Bin Cao, Yu The 3rd Research Institute of CETC Beijing China Key Laboratory of Petroleum Resources Research Institute of Geology and Geophysics Chinese Academy of Sciences Beijing China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing China Institute of Acoustics Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9789819704828

This paper is based on elastic wave propagation and six component seismic detection methods to detect underwater targets, which makes up for the shortcomings of traditional underwater acoustic passive detection methods that cannot effectively detect targets in near shallow water. The implementation of this article requires four steps: firstly, using a self-developed six component seismometer to collect seismic signals excited by the target;Secondly, screen out abnormal six component seismic signals;Step 3: Data preprocessing such as denoising and azimuth correction;Finally, the target direction finding is achieved by comprehensively utilizing rotational and translational seismic signals. Through multiple experiments, it can be concluded that: (1) using a six component seismic sensor can detect the six component seismic signal excited by the target, and the lower the detection frequency band, the easier it is to detect the low-frequency signal excited by the target;(2) It can be clearly observed in the time-frequency domain that moving targets have a close far passing characteristic;(3) The energy of the six component seismic signal has a certain proportional relationship with the target distance. The closer the target distance is, the greater the energy of the excited six component seismic signal;(4) Six component seismic signals can be used to achieve target detection and positioning. Compared to traditional seismic detection, six component seismic detection has a higher ability and is an important supplement to traditional underwater acoustic detection methods. This article first discovered that underwater moving targets not only generate seismic translational signals, but also contain low-frequency rotational seismic signals. The accurate direction finding of the target was achieved using the six component seismic direction finding method proposed for the first time in this article. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 20

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

eShadow+: Mixed Reality Storytelling Inspired by Traditional Shadow Theatre 46

eShadow+: Mixed Reality Storytelling Inspired by Traditional...

引用

46th IEEE Annual computers, Software, and Applications Conference, COMPSAC 2022

作者： Moumoutzis, Nektarios Christoulakis, Marios Xanthaki, Chara Maragoudakis, Yiannis Christodoulakis, Stavros Paneva-Marinova, Desislava Pavlova, Lilia Institute of Mathematics and Informatics Bulgarian Academy of Sciences Sofia Bulgaria School of Electrical & Computer Eng. Technical University of Crete Lab. of Distr. Multimedia Inf. Systems & Applications Chania Greece Computer Science Teacher Directorate of Secondary Education Chania Greece Academy of Sciences Laboratory of Telematics Bulgarian Sofia Bulgaria

ISBN: (纸本)9781665488105

eShadow is a digital storytelling platform inspired by traditional Shadow Theatre. It enables the creation of digital stories within a project-based approach that may start from scenario development and include the creation of digital puppets and sceneries, the set-up and recording of story scenes and the final assembly of a digital story. This paper presents how eShadow can be enhanced to solve the problem of creating mixed reality installations to offer rich learning experiences in informal learning settings. This enhanced version is eShadow+ and it is evaluated via two installations which are described and compared. The evaluation results demonstrate the effectiveness of the approach thus offering new learning opportunities that are aligned with current trends in the use of mixed reality technologies. © 2022 IEEE.

关键词： Theaters

来源：评论

学校读者我要写书评

暂无评论

Nearest Neighbor Classification Algorithm Based on Minimum Component Eigenvector Subspace Projection

引用

Science Technology and engineering 2024年第36期24卷 15511-15517页

作者： Li, Meng-Meng Yang, Zhong-Liang Yue, Cai-Tong Wan, Hong Li, Zhi-Hui Shang, Zhi-Gang School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou450001 China Sany Heavy Industry Co. Ltd. Suzhou215300 China

The nearest neighbor algorithm is one of the most classical pattern recognition algorithms, which classification performance highly depends on the distance metric between samples. Appropriate distance metric can help improve the classification performance of the algorithm. However, such algorithms mostly seek metrics to maximize classification effectiveness from the perspective of discriminant models currently, ignoring the aggregation properties of various sample sets belonging to different classes. In view of this, a nearest neighbor classification algorithm based on minimum component eigenvector subspace projection (NN_MCESP) was proposed. This algorithm combined classic principal component analysis (PCA) and nearest neighbor algorithm, which can effectively implement aggregation properties analysis of various sample clusters based on minimum component eigenvector projection, and complete classification based on subspace nearest neighbor voting criteria. The effectiveness and stability of NN_MCESP were validated by comparing with other classification algorithms on multiple data sets. © 2024 Beijing Kexue Jishu yu Gongcheng Zazhishe. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

The State of Diversity and Inclusion in Apache: A Pulse Check

arXiv

引用

arXiv 2023年

作者： Feng, Zixuan Guizani, Mariam Gerosa, Marco A. Sarma, Anita School of Electrical Engineering and Computer Science Oregon State University CorvallisOR United States School of Informatics Computing and Cyber Systems Northern Arizona University FlagstaffAZ United States

Diversity and inclusion (D&I) in open source software (OSS) is a multifaceted concept that arises from differences in contributors’ gender, seniority, language, region, and other characteristics. D&I has received growing attention in OSS ecosystems and projects, and various programs have been implemented to foster contributor diversity. However, we do not yet know how the state of D&I is evolving. By understanding the state of D&I in OSS projects, the community can develop new and adjust current strategies to foster diversity among contributors and gain insights into the mechanisms and processes that facilitate the development of inclusive communities. In this paper, we report and compare the results of two surveys of Apache Software Foundation (ASF) contributors conducted over two years (n=624 & n=432), considering a variety of D&I aspects. We see improvements in engagement among those traditionally underrepresented in OSS, particularly those who are in gender minority or not confident in English. Yet, the gender gap in the number of contributors remains. We expect this study to help communities tailor their efforts in promoting D&I in OSS. Copyright © 2023, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Angle-of-Arrival Sensing and Anomalous Deflection with Aperiodically Loaded Patch Arrays

arXiv

引用

arXiv 2025年

作者： Movahediqomi, Mostafa Vuyyuru, Sravan K.R. Ptitcyn, Grigorii Valkonen, Risto Asadchy, Viktar S. Kwon, Do-Hoon Tretyakov, Sergei A. Department of Electronics and Nanoengineering School of Electrical Engineering Aalto University Espoo02150 Finland Nokia Bell Labs Karakaari 7 Espoo02610 Finland Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Department of Electrical and Computer Engineering University of Massachusetts Amherst AmherstMA01003 United States

We propose and numerically demonstrate a reconfigurable patch antenna array that enables simultaneous incident wave sensing and anomalous reflection without prior knowledge of the propagation environment. We acquire anomalous reflection by suppressing parasitic scattering through accurate and efficient optimization of induced load currents and by varying impedances of reactive loads. By mitigating parasitic scattering lobes, we demonstrate the feasibility of accurately detecting the incoming illumination angle via the spatial Fourier transform of the optimized load current distribution, facilitated by tunable reactive loads. This approach eliminates the need for additional RF chains, pre-computed data, or calibration measurements. The developed strategy, which integrates arithmetic load optimization with angle-of-arrival sensing, is applicable to general finite-size arrays. © 2025, CC BY.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Deep Q-learning Sampling Based on Advantages 5

Deep Q-learning Sampling Based on Advantages

引用

5th International Conference on Intelligent Robotics and Control engineering, IRCE 2022

作者： Xie, Ming Ren, Xinrui Yu, Jianbo Shu, Feng Shanghai Engineering Research Center of Ultra-Precision Motion Control and Measurement Academy for Engineering and Technology Fudan University Shanghai China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Microelectronics Fudan University State Key Laboratory of ASIC and System Shanghai200433 China

ISBN: (数字)9781665469951

ISBN: (纸本)9781665469951

Deep Q-learning (DQN) has shown recent success on a wide range of complicated sequential decision-making issues, especially in the classic control area. However, in most DQN training, the sampling policies, particularly the ϵ-greedy policy and its derivation rules, produce noise erroneously due to the unsteadiness and unreliability of Q values utilized for searching for optimum actions. We begin with a fundamental hypothesis: complete advantages-based exploitation may be employed to help in successful exploration, and the gap between advantages on outstanding and poor actions tends to extend during the early phases of training before stabilizing. We then present a novel DQN architecture with a superior sampling policy that is totally and directly based on advantage values. This new DQN is named A-sampling DQN, and it requires minor code changes based on the original DQN codes. In most cases, A-sampling DQN and its derivatives outperformed the traditional DQN method. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Volt-Var Control for Utility-scale Solar PV Plants to Replace SVCs

Volt-Var Control for Utility-scale Solar PV Plants to Replac...

引用

International Conference on High Voltage engineering and Power systems (ICHVEPS)

作者： Ken Shimomukai Haruka Maeda Goro Fujita Functional Control Systems Graduate School of Engineering and Science Shibaura Institute of Technology Tokyo Japan Department of Electrical Engineering and Computer Science Graduate School of Engineering and Science Shibaura Institute of Technology Tokyo Japan Department of Electrical Engineering Shibaura Institute of Technology Tokyo Japan

One way to increase solar photovoltaic penetration in the grid is management of voltage fluctuations. This is because a photovoltaic plant cannot be interconnected to the grid if it causes voltage violations. Voltage violation is where voltage exceeds the acceptable range. Often, grid operators request photovoltaic plant owners to regulate voltage sufficiently with expensive and space-consuming static Var compensators. Unfortunately, this sometimes makes the project less feasible. This paper argues that there are better ways to regulate voltage. We ran a simulation with a 70 MWp photovoltaic plant as an addition to the grid. Without voltage regulation, voltage violations were found to be significant. This paper found that oversizing the inverter sufficiently would remove all voltage violations without deploying a static Var compensator. This is often a cheaper and space-saving solution for voltage management. This paper argues that economics and spatial efficiency of reactive power compensation devices is key to increasing photovoltaic penetration.

关键词：

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：