检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Sun, Zhenglong Han, Junpeng Chen, Weihan Zhang, Rui Liu, Yong Levron, Yoash Belikov, Juri Department of Electrical Engineering Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Software Science Tallinn University of Technology Akadeemia Tee 15a Tallinn12618 Estonia

With the rapid growth of renewable energy in the power system and the implementation of large-capacity LCC-HVDC projects, the frequency support capability of the grid has been reduced. Simultaneously, the renewables-rich grid faces the risk of high-power shocks due to LCC-HVDC blocking. Existing centralized, single-measure approaches and the model-based emergency frequency control (EFC) methods are facing tremendous challenges. To fill this gap, this paper proposes a frequency emergency control method for renewables-rich grids that coordinates LCC-HVDC emergency power support and load shedding. The coordination of the two stabilization measures is modeled as a decentralized partially observable Markov decision process, and a multi-agent reinforcement learning (MADRL) approach is employed to optimize the power of measures for each stabilization control substation. An MADRL algorithm that integrates the system frequency response model is developed to overcome the problem of inaccurate evaluation of centralized action value in the MADRL algorithm used for EFC. This approach allows for the global optimization of the distributed coordination strategy through centralized training. The effectiveness and adaptability of the proposed method are demonstrated through simulations of the modified IEEE 39-bus system. © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HDTCNet: A hybrid-dimensional convolutional network for multivariate time series classification

引用

Pattern Recognition 2025年 168卷

作者： Gu, Yongli Yan, Xiang Qin, Hanlin Akhtar, Naveed Yuan, Shuai Fu, Honghao Yang, Shuowen Mian, Ajmal School of Optoelectronic Engineering Xidian University Xi'an710071 China Xi'an Key Laboratory of Infrared Technology and System Xi'an710071 China School of Computing and Information Systems The University of Melbourne ParkvilleVIC3052 Australia School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore School of Computer Science and Software Engineering The University of Western Australia CrawleyWA6009 Australia

Currently, transformer-based models dominate time series classification due to their ability to capture global data dependencies. However, their large memory footprint and high computational demands make them less desirable for long multivariate time series modeling. At the same time, convolution-based models promise a desirable performance versus efficiency trade-off for the task. Nevertheless, the popularity of transformer models has impeded exploration of sophisticated convolution-based modeling for time series classification. In this work, we introduce a novel convolution-based model, called HDTCNet, that alternates between 1D and 2D convolutional modes to capture temporal pattern correlations between intra- and inter-sensor variations. We develop a Wavelet Time Convolution block to expand the effective receptive field of the underlying neural model with a small convolutional kernel that embeds a set of 1D convolution operators between a cascade of wavelet decomposition and reconstruction of the input time series. To efficiently represent the local features of multivariate time series, we devise a hierarchical difference convolution network to capture intra- and inter-sensor gradient variations. To refine the feature representation of sensor-level time series and achieve multi-view self-enhancement, we design a self-enhancing module. These innovations enable HDTCNet to achieve superior performance while maintaining efficiency as a purely convolutional model. Experimental results demonstrate that HDTCNet achieves 2.1% accuracy and 1% F1-score performance improvements over state-of-the-art methods on 25 UEA classification datasets and 3 anomaly detection datasets, respectively, while reducing parameter counts by two orders of magnitude. Our code will be available at https://***/Guuuli/HDTCNet. © 2025

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Robust model predictive control for linear systems with polytopic uncertainties under weighted mef-tod protocol

引用

IEEE Transactions on systems, Man, and Cybernetics: systems 2019年第7期49卷 1470-1481页

作者： Song, Yan Wang, Zidong Ding, Derui Wei, Guoliang Department of Control Science and Engineering Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and Technology Shanghai200093 China Department of Computer Science Brunel University London Uxbridge21589 United Kingdom School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia

This paper is concerned with the robust {-Grant-info-{2}/H-\infty } model predictive control problem for a class of linear systems with polytopic uncertainties under weighted maximum-error-first and try-once-discard (MEF-TOD) protocol. To prevent data from collision, the weighted MEF-TOD protocol is employed during the data transmission from sensors to controller, where only one sensor is allowed to transmit the measurement at every time instant. A switched linear system is established with respect to the switching signals generated by the adopted weighted MEF-TOD protocol. By taking the influence of the exogenous disturbance and the weighted MEF-TOD protocol into consideration, an online optimization problem with nonconvex conditions is formulated. Then, to deal with the couplings of unknown variables, singular value decomposition technique is utilized to transform the nonconvex conditions into solvable ones. Subsequently, a set of dynamic output-feedback controllers is designed to guarantee the stability of the closed-loop system with guaranteed robust { H-{2}/H-\infty } performance. Finally, a direct current motor example is used to illustrate the validity and effectiveness of the proposed methods. © 2013 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Raspberry Pi-based Traumatic Brain Injury detection system for single-channel Electroencephalogram

arXiv

引用

arXiv 2021年

作者： Dhillon, Navjodh Singh Sutandi, Agustinus Vishwanath, Manoj Lim, Miranda M. Cao, Hung Si, Dong Computing and Software Systems University of Washington BothellWA United States Department of Electrical Engineering and Computer Science University of California IrvineCA United States VA Portland Health Care System PortlandOR United States Department of Neurology Oregon Health & Science University PortlandOR United States Department of Biomedical Engineering University of California IrvineCA United States

Traumatic Brain Injury (TBI) is a common cause of death and disability. However, existing tools for TBI diagnosis are either subjective or require extensive clinical setup and expertise. The increasing affordability and reduction in the size of relatively high-performance computing systems combined with promising results from TBI related machine learning research make it possible to create compact and portable systems for early detection of TBI. This work describes a Raspberry Pi based portable, real-time data acquisition, and automated processing system that uses machine learning to efficiently identify TBI and automatically score sleep stages from a single-channel Electroencephalogram (EEG) signal. We discuss the design, implementation, and verification of the system that can digitize the EEG signal using an Analog to Digital Converter (ADC) and perform real-time signal classification to detect the presence of mild TBI (mTBI). We utilize Convolutional Neural Networks (CNN) and XGBoost based predictive models to evaluate the performance and demonstrate the versatility of the system to operate with multiple types of predictive models. We achieve a peak classification accuracy of more than 90% with a classification time of less than 1 s across 16 s - 64 s epochs for TBI vs control conditions. This work can enable the development of systems suitable for field use without requiring specialized medical equipment for early TBI detection applications and TBI research. Further, this work opens avenues to implement connected, real-time TBI related health and wellness monitoring systems. © 2021, CC BY.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Double JPEG Compression Detection Based on Markov Model 18th

Double JPEG Compression Detection Based on Markov Model

引用

18th International Workshop on Digital Forensics and Watermarking, IWDW 2019

作者： Wang, Jinwei Huang, Wei Luo, Xiangyang Shi, Yung-Qing Nanjing University of Information Science and Technology Nanjing210044 China Department of Computer and Software Nanjing University of Information Science and Technology NanjingJiangsu210044 China Shanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China State Key Laboratory of Information Security Institute Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Electrical Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

ISBN: (纸本)9783030435745

In this paper, a feature based on the Markov model in quaternion discrete cosine transform (QDCT) domain is proposed for double JPEG compression detection. Firstly, a given JPEG image is extracted from blocked images to obtain amplitude and three angles (ψ, φ, and θ). Secondly, when extracting the Markov features, we process the transition probability matrix with the corresponding refinement. Our proposed refinement method not only reduces redundant features, but also makes the acquired features more efficient for detection. Finally, a support vector machine (SVM) is employed for NA-DJPEG compression detection. It is well known that detecting NA-DJPEG compressed images with (Formula Presented) is a challenging task, and when the images with small size (i.e., 64 × 64), the detection will be more difficult. The experimental result indicates that our method can still achieve a high classification accuracy in this case. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Narrowband-internet of things (NB-IoT) system for elderly healthcare services 5

Narrowband-internet of things (NB-IoT) system for elderly he...

引用

5th International Conference on engineering, Applied Sciences and Technology, ICEAST 2019

作者： Manatarinat, Wiraphon Poomrittigul, Suvit Tantatsanawong, Panjai Electrical Engineering Department Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand Software Engineering and Information System Department Faculty of Science and Technology Pathumwan Institute of Technology Bangkok Thailand Computer Technology Department Faculty of Science Silpakorn University Bangkok Thailand

ISBN: (纸本)9781728100678

3G and 4G wireless communication technology, which requires broad network resources and large amounts of available electricity, was designed for high-speed Internet usage. Most narrowband-Internet of Things (NB-IoT) devices do not require high-speed Internet because most IoTs work by sending commands to and receiving commands from a server only. NB-IoT is a low-power wide area (LPWA) technology that was developed to accommodate a broad variety of new IoT devices. A low-power wide area network (LPWAN) uses narrow frequencies that support the use of devices in the 900 MHz frequency range that are inexpensive and that can be used in both buildings and wide areas. NB-IoT devices can also be used to assist medical patients, the elderly, and disabled people that are susceptible to falling. Our newly developed monitoring system has the ability to immediately recognize a fall, and then automatically alert up to 4 contacts via the LINE application. If dispatch of a medical unit is required, the patient's location is automatically available without the need for voice contact by the patient. © 2019 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Design of a Cryptographically Secure Pseudo Random Number Generator with Grammatical Evolution

Research Square

引用

Research Square 2021年

作者： Ryan, Conor Kshirsagar, Meghana Vaidya, Gauri Cunningham, Andrew Sivaraman, R. Biocomputing and Developmental Systems Group Lero The Science Foundation Ireland Research Centre for Software Computer Science and Information System Department University of Limerick LimerickV94 T9PX Ireland Intel Research and Development Ireland Limited LeixlipW23 CX68 Ireland Department of Electronics Communication Engineering School of Electrical and Electronics Engineering Shanmugha Arts Science Technology and Research Academy Deemed to be University Thanjavur613401 India

This work investigates the potential of evolving an initial seed with Grammatical Evolution (GE), for the construction of cryptographically secure (CS) pseudo-random number generator (PRNG). We harness the flexibility of GE as an entropy source for returning initial seeds. The initial seeds returned by GE demonstrate an average entropy value of 7.920261600000001 which is extremely close to the ideal value of 8. The initial seed combined with our proposed approach, control_flow_incrementor, is used to construct both, GE-PRNG and GE-CSPRNG. The random numbers generated with CSPRNG meet the prescribed National Institute of Standards and Technology (NIST) SP800-22 requirements. Monte Carlo simulations established the efficacy of the PRNG. The experimental setup was designed to estimate the value for pi, in which 100,000,000 random numbers were generated by our system and which resulted in returning the value of pi to 3.146564000, with a precision up to six decimal digits. The random numbers by GE-PRNG were compared against those generated by Python’s rand() function for sampling. The sampling results, when measured for accuracy against twenty-nine real world regression datasets, showed that GE-PRNG had less error when compared to Python’s rand() against the ground truths in seventeen of those, while there was no discernible difference in the remaining twelve. © 2021, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Requirements Dependency Extraction by Integrating Active Learning with Ontology-Based Retrieval

Requirements Dependency Extraction by Integrating Active Lea...

引用

IEEE International Conference on Requirements engineering

作者： Gouri Deshpande Quim Motger Cristina Palomares Ikagarjot Kamra Katarzyna Biesialska Xavier Franch Guenther Ruhe Jason Ho dept. of Computer Science University of Calgary Calgary Canada dept. of Service and Information System Engineering (ESSI) Universitat Politècnica de Catalunya Barcelona Spain dept. of Electrical and Software Engineering University of Calgary Calgary Canada Blackline Safety. Inc Calgary Canada

ISBN: (数字)9781728174389

ISBN: (纸本)9781728174396

Context: Incomplete or incorrect detection of requirement dependencies has proven to result in reduced release quality and substantial rework. Additionally, the extraction of dependencies is challenging since requirements are mostly documented in natural language, which makes it a cognitively difficult task. Moreover, with ever-changing and new requirements, a manual analysis process must be repeated, which imposes extra hardship even for domain experts. Objective: The three main objectives of this research are: 1) Proposing a new dependency extraction method using a variant of Active Learning (AL). 2) Evaluating this AL and Ontology-based Retrieval (OBR) as baseline methods for dependency extraction on the two industrial data sets. 3) Analyzing the value gained from integrating these diverse approaches to form two hybrid methods. Method: Building on the general AL, ensemble and semi-supervised machine learning, a variant of AL was developed, which was further integrated with OBR to form two hybrid methods (Hybrid1, Hybrid2) for extracting three types of dependencies (requires, refines, other): Hybrid1 used OBR as a substitute for human expert; Hybrid2 used dependencies extracted through the OBR as an additional input for training set in AL. Results: For two industrial case studies, AL extracted more dependencies than OBR. Hybrid1 showed improvement for both data sets. For one of them, F1 score increased to 82.6% compared to the AL baseline score of 49.9%. Hybrid2 increased the accuracy by 25% to the level of 75.8% compared to the AL baseline accuracy. OBR also complemented the AL approach by reducing 50% of the human effort.

关键词： Training Ontologies Machine learning Data mining Electronic mail Requirements engineering Safety

来源：评论

学校读者我要写书评

暂无评论

CRNN based jersey-bib number/text recognition in sports and marathon images 15

CRNN based jersey-bib number/text recognition in sports and ...

引用

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Nag, Sauradip Ramachandra, Raghavendra Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kankanhalli, Mohan Department of Computer Science & Engineering Kalyani Government Engineering College Kalyani India Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Norway Faculty of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9781728128610

The primary challenge in tracing the participants in sports and marathon video or images is to detect and localize the jersey/Bib number that may present in different regions of their outfit captured in cluttered environment conditions. In this work, we proposed a new framework based on detecting the human body parts such that both Jersey Bib number and text is localized reliably. To achieve this, the proposed method first detects and localize the human in a given image using Single Shot Multibox Detector (SSD). In the next step, different human body parts namely, Torso, Left Thigh, Right Thigh, that generally contain a Bib number or text region is automatically extracted. These detected individual parts are processed individually to detect the Jersey Bib number/text using a deep CNN network based on the 2-channel architecture based on the novel adaptive weighting loss function. Finally, the detected text is cropped out and fed to a CNN-RNN based deep model abbreviated as CRNN for recognizing jersey/Bib/text. Extensive experiments are carried out on the four different datasets including both bench-marking dataset and a new dataset. The performance of the proposed method is compared with the state-of-the-art methods on all four datasets that indicates the improved performance of the proposed method on all four datasets. © 2019 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Environmentally safe layered crystal produced from hazardous chemical elements: TlPb2BrI4, a new promising detector material

引用

Journal of Alloys and Compounds 2022年 924卷 1页

作者： Khyzhun, O.Y. Vu, Tuan V. Parasyuk, O.V. Fedorchuk, A.O. Fochuk, P.M. Lavrentyev, A.A. Gabrelian, B.V. Levchuk, Ievgen Matt, Gebhard J. Tedde, Sandro F. Schmidt, Oliver Shrestha, Shreetu Brabec, Christoph J. Kityk, I.V. Piasecki, M. Frantsevych Institute for Problems of Materials Science National Academy of Sciences of Ukraine 3 Krzhyzhanovsky Street KyivUA-03142 Ukraine Faculty of Mechanical - Electrical and Computer Engineering School of Engineering and Technology Van Lang University Ho Chi Minh City Viet Nam Department of Inorganic and Physical Chemistry Lesya Ukrainka Volyn National University 13 Voli Avenue LutskUA-43025 Ukraine Department of Inorganic and Organic Chemistry Lviv National University of Veterinary Medicine and Biotechnologies 50 Pekarska Street Lviv79010 Ukraine Yuriy Fed'kovych Chernivtsi National University 2 Kotziubynskoho Street Chernivtsi58012 Ukraine Department of Electrical Engineering and Electronics Don State Technical University 1 Gagarin Square Rostov-on-Don344010 Russia Department of Computational Technique and Automated System Software Don State Technical University 1 Gagarin Square Rostov-on-Don344010 Russia Martensstrasse 7 Erlangen91058 Germany Siemens Healthineers Technology Center Guenther-Scharowsky-Str. 1 Erlangen91058 Germany Electrical Engineering Department Czestochowa University Technology Armii Krajowej 17 Częstochowa42217 Poland Departmentof Experimental Physics and Information-measuring Technology Lesya Ukrainka Volyn National University Voli Avenue 13 Lutsk43025 Ukraine J.Dlugosz University Częstochowa Armii Krajowej 13/15 Częstochowa42200 Poland

Exploring better Gamma, X-Ray and IR-Mid-R detectors, adequately sensitive to ambient temperatures and environmental conditions, is highly desirable. Therefore, following this path, we present detecting opportunities, based on data of experimental and theoretical investigation of the electronic and optical properties, photocurrent behavior at different bias voltages as well as the reflection for the He-Cd cw laser after irradiation by three different IR laser wavelengths, for recently grown TlPb2BrI4 single crystal with strong anisotropic, two-dimensional (2D) layered structure. The X-ray photoelectron spectroscopy brings data on binding energy values of core levels of TlPb2BrI4 for both as-grown and Ar+-ion-treated crystal surfaces as well as for elucidation of the energy distribution of the valence electronic states. In opposite to well-known IR-detector materials, TlPb2BrI4 crystal surface shows high chemical stability concerning Ar+-ion bombardment. Further, we carry out ab initio band-structure calculations to gain curves of total and partial densities of states and to elucidate the principal optical constants of TlPb2BrI4. The present studies indicate that, in spite of the fact that the TlPb2BrI4 crystal contains two very hazardous/toxic chemical elements, thallium and lead;however, it is chemically stable and reveals very low hygroscopic behavior when being exposed to environmental conditions. © 2022 Elsevier B.V.

关键词： X ray photoelectron spectroscopy

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：