检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence and computer Information technology (AICIT)

作者： Qiugen Pei Yuxuan Lai Nianxing Wei Shiting Wu Enterprise Architecture and Digitalization Department Guangdong Power Grid Co. Ltd. Guangzhou China Dept. School of Computer Science Guangdong University of Technology Guangzhou China Huizhou Boluo Power Supply Bureau Guangdong Power Grid Co. Ltd. Huizhou China

ISBN: (数字)9798350365443

ISBN: (纸本)9798350365450

Object detection algorithms constitute a pivotal task in the realm of computer vision, aiming to precisely identify and locate objects within images across diverse scenarios. In power systems, especially in aerial images used to detect wire breaks or scattered anomalies, object detection faces significant challenges. The distribution of wires is often uneven, appearing in different sizes in high-resolution images, and the diversity of fault shapes and sizes makes it difficult for traditional object detection models to recognize accurately. Moreover, the detection of small targets also limits the precision of traditional methods. To address the issue of diversity in fault shapes and sizes in high-resolution images, which makes it difficult for traditional object detection models to recognize accurately, first, we collect fault images of wire breaks and scatter under common scenarios, constructing the “EWF _detection” (Electric wire fault) dataset, and propose a Pyramid Multi-scale Object Detection Model, establishing the Hybrid Spatial Attention Pooling module, HSAP, which significantly enhances the multi-scale feature extraction capability. It not only improves the model's ability to focus on key features, but also suppresses unnecessary features, enhancing the expressiveness of the network, and effectively adapting to complex backgrounds, variable lighting conditions, and different line scales and directions for transmission line detection needs. This improvement makes our model perform exceptionally well in detecting rare faults in wires and accurately locate fault positions. These achievements provide reliable technical support for wire anomaly detection in the power industry and indicate a broad prospect of application in future power scenarios. Our method not only improves detection accuracy, but also maintains efficient detection speed, reducing reliance on a large number of fault line images. These advantages make our model an important technical tool for pow

关键词： Adaptation models Image recognition Shape Lighting Object detection Feature extraction Power industry Robustness Maintenance Wire

来源：评论

学校读者我要写书评

暂无评论

A methodological framework for futures studies: integrating normative backcasting approaches and descriptive case study design for strategic data-driven smart sustainable city planning

引用

Energy Informatics 2020年第1期3卷 1-42页

作者： Bibri, Simon Elias Department of Computer Science The Norwegian University of Science and Technology Sem Saelands veie 9 TrondheimNO–7491 Norway Department of Architecture and Planning The Norwegian University of Science and Technology Alfred Getz vei 3 Sentralbygg 1 5th floor TrondheimNO–7491 Norway

Originally proposed as an alternative to traditional energy planning methodology in the 1970s, backcasting is increasingly applied in futures studies related to sustainability, as it is viewed as a natural step in operationalizing sustainable development. This futures study is concerned with data-driven smart sustainable urbanism as an instance of sustainable urban development—a strategic approach to achieving the long-term goals of urban sustainability. This is at the core of backcasting, which typically defines criteria for a desirable (sustainable) future and builds a set of feasible and logical pathways between the state of the future and the present. This paper reviews, discusses, and justifies the methodological framework applied in the futures study. This aims to analyze, investigate, and develop a novel model for data-driven smart sustainable cities of the future as a form of transformative change towards sustainability. This paper corroborates that the backcasting approach—as applied in the futures study—is well-suited for long-term urban problems and sustainability solutions due to its normative, goal-oriented, and problem-solving character. It also suggests that case study research is the most effective way to underpin and increase the feasibility of future visions. Indeed, the case study approach as a research strategy facilitates the investigation and understanding of the underlying principles in the real-world phenomena involved in the construction of the future vision in the backcasting study. The novelty of this work lies in the integration of a set of principles underlying several normative backcasting approaches with descriptive case study design to devise a framework for strategic urban planning whose core objective is clarifying which city model is desired and working towards that goal. Visionary images of a long-term future based on normative backcasting can spur innovative thinking about and accelerate the movement towards sustainability. The p

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

The eco-city and its core environmental dimension of sustainability: green energy technologies and their integration with data-driven smart solutions

引用

Energy Informatics 2020年第1期3卷 1-26页

作者： Bibri, Simon Elias Department of Computer Science The Norwegian University of Science and Technology Sem Saelands veie 9 NO–7491 Trondheim Norway Department of Architecture and Planning The Norwegian University of Science and Technology Alfred Getz vei 3 Sentralbygg 1 5th floor NO–7491 Trondheim Norway

Ecological urbanism is seen today as one of the keys towards unlocking the quest for a low-carbon or fossil fuel–free society. Global and local policies promote and advocate the eco–city as the most environmentally sound model of sustainable urbanism. It is argued that the eco–city strategies and solutions are expected to deliver positive outcomes in terms of minimal demand on energy resources and thus minimal environmental impacts. Moreover, it has recently been suggested that the eco-city needs to embrace and leverage what advanced ICT has to offer, particularly with regard to sustainable energy systems, so as to improve and advance its contribution to the goals of environmental sustainability. This paper examines how the eco–city especially its core environmental dimension is practiced and justified in urban planning and development with respect to sustainable energy systems and their integration with data-driven smart technologies at the district level. To illuminate this urban phenomenon accordingly, a descriptive case study is adopted as a qualitative research methodology where the empirical basis is formed by urban planning and development documents combined with secondary data and scientific literature. To provide a theoretical foundation and produce a rationale for this study, this paper first provides a state–of–the–art review of the field of ecological urbanism in terms of its foundations, models, strategies, research issues, as well as data–driven smart technological trends. This study shows that the Eco-city District of Stockholm Royal Seaport uses green energy and data-driven smart technologies as the key strategies and solutions for achieving the environmental objectives of sustainable development in terms of lowering energy consumption and mitigating pollution. This entails conserving and decreasing the demand for energy through renewable resources (i.e., sun, wind, and water), bio–fuelled Combined Heat Power system, large-scale smart grid system, en

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

A Machine Vision-Based Person Detection under Low-Illuminance Conditions Using High Dynamic Range Imagery for Visual Surveillance System 3

A Machine Vision-Based Person Detection under Low-Illuminanc...

引用

3rd International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2022

作者： Susa, Julie Ann B. Militante, Sammy V. Acoba, Aimee G. Evangelista, Ryan Soriente Lacatan, Luisito Lolong Lavina, Charlemagne G. Tanguilig, Bartolome T. Southern Luzon State University Dept. of Computer Engineering Quezon Lucban Philippines College of Engineering and Architecture University of Antique Antique Philippines Technological University of the Philippines Electronics Eng'g Technology Department Manila Philippines School of Graduate Studies Sulu State College Sulu Philippines College of Computing and Engineering Pamantasan Ng Cabuyao Laguna Philippines

ISBN: (纸本)9781665456647

The most difficult component of any computer vision application objects recognition and tracking. Video surveillance is a major study subject in computer vision in a dynamic environment, especially for security purposes. Video surveillance technology is critical in preventing crime, terrorism, and other threats. Several existing technologies can accurately monitor a person's mobility in interior environments. As well as regulated outdoor settings, object recognition and tracking at night, on the other hand, remain significant challenges for visual surveillance. The objects are usually farther away, inconspicuous, and have low brightness against the background. In this paper, detecting objects specifically people under low lighting conditions with the help of deep learning algorithms was used. For applications like in-car cameras and surveillance systems that operate in low light, these algorithms might improve picture identification performance. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements 63

A Multi-Player Potential Game Approach for Sensor Network Lo...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Xu, Gehui Chen, Guanpu Fidan, Baris Hong, Yiguang Qi, Hongsheng Parisini, Thomas Johansson, Karl H. Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm100 44 Sweden University of Waterloo Department of Mechanical and Mechatronics Engineering WaterlooONN2L 3G1 Canada Tongji University Department of Control Science and Engineering shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China University of Chinese Academy of Sciences School of Mathematical Sciences Beijing China Aalborg University Department of Electronic Systems Denmark Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom University of Trieste Department of Engineering and Architecture Italy

ISBN: (纸本)9798350316339

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multiplayer non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies. © 2024 IEEE.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

The emerging data–driven Smart City and its innovative applied solutions for sustainability: the cases of London and Barcelona

引用

Energy Informatics 2020年第1期3卷 1-42页

作者： Bibri, Simon Elias Krogstie, John Department of Computer Science The Norwegian University of Science and Technology Sem Saelands veie 9 TrondheimNO–7491 Norway Department of Architecture and Planning The Norwegian University of Science and Technology Alfred Getz vei 3 Sentralbygg 1 5th floor TrondheimNO–7491 Norway

The big data revolution is heralding an era where instrumentation, datafication, and computation are increasingly pervading the very fabric of cities. Big data technologies have become essential to the functioning of cities. Consequently, urban processes and practices are becoming highly responsive to a form of data-driven urbanism that is the key mode of production for smart cities. Such form is increasingly being directed towards tackling the challenges of sustainability in the light of the escalating urbanization trend. This paper investigates how the emerging data-driven smart city is being practiced and justified in terms of the development and implementation of its innovative applied solutions for sustainability. To illuminate this new urban phenomenon, a descriptive case study is adopted as a qualitative research methodology to examine and compare London and Barcelona as the leading data-driven smart cities in Europe. This study shows that these cities have a high level of the development of applied data-driven technologies, but they slightly differ in the level of the implementation of such technologies in different city systems and domains with respect to sustainability areas. They also moderately differ in the degree of their readiness as to the availability and development level of the competences and infrastructure needed to generate, transmit, process, and analyze large masses of data to extract useful knowledge for enhanced decision making and deep insights pertaining to urban operational functioning, management, and planning in relation to sustainability. London takes the lead as regards the ICT infrastructure and data sources, whereas Barcelona has the best practices in the data-oriented competences, notably horizontal information platforms, operations centers, dashboards, training programs and educational institutes, innovation labs, research centers, and strategic planning offices. This research enhances the scholarly community’s current understand

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Gravity Currents with Internal Strati Cation in Semicircular Channels

SSRN

引用

SSRN 2022年

作者： Chiapponi, Luca Zemach, Tamar Petrolo, Diana Ungarish, Marius Longo, Sandro Department of Engineering and Architecture Università degli Studi di Parma Parco Area delle Scienze 181/A Parma43124 Italy Department of Computer Science Tel-Hai College Tel-Hai 1220800 Israel Department of Computer Science Technion Israel Institute of Technology Haifa32000 Israel

We present an experimental study of gravity currents (GCs) with internal stratification in a semicircular channel in the inertial–buoyancy and Boussinesq regime. Forty tests were performed with a denser volume of fluid (brine advancing in a fresh water ambient fluid) in lock-release. The lock contains an internal stratification, with a layer of density ρL overlain by a layer of density ρU, where ρa U L and ρa is the density of the ambient fluid. The experiments cover both a full depth and a partial depth configuration. The measurements consist of marking the front position of the currents as a function of the time from release, t. Two lateral video-cameras were used to detect the flow profile. Also local instantaneous density and velocity profiles data were collected in a fixed section downstream of the gate, in order to give further details and a better description of the physical phenomenon. The integral data of front speed and current thickness were compared to a theoretical model [1] based on (i) a Boussinesq flow;(ii) large Reynolds number;(iii) current advancing in shallow water conditions;and (iv) negligible ambient fluid dynamics. The system of equations and boundary conditions allows the prediction of the motion of the GC, in particular the position and speed of the nose xN (t) and uN (t). The agreement of theory and experiments is fairly good, especially for the full depth configuration. The partial depth configuration experiments are less accurately reproduced by the theory, and require a correction coefficient of the Froude number at the front, mimicking dissipation and mixing. A thorough investigation was carried out for density profiles, average velocities within the current, and buoyancy fluxes of a turbulent diffusive nature, with a quadrant analysis distinguishing the origin and direction of the fluxes. © 2022, The Authors. All rights reserved.

关键词： Gravity waves

来源：评论

学校读者我要写书评

暂无评论

Environmentally data-driven smart sustainable cities: applied innovative solutions for energy efficiency, pollution reduction, and urban metabolism

引用

Energy Informatics 2020年第1期3卷 1-59页

The IoT and big data technologies have become essential to the functioning of both smart cities and sustainable cities, and thus, urban operational functioning and planning are becoming highly responsive to a form of data-driven urbanism. This offers the prospect of building models of smart sustainable cities functioning in real time from routinely sensed data. This in turn allows to monitor, understand, analyze, and plan such cities to improve their energy efficiency and environmental health in real time thanks to new urban intelligence functions as an advanced form of decision support. However, prior studies tend to deal largely with data-driven technologies and solutions in the realm of smart cities, mostly in relation to economic and social aspects, leaving important questions involving the underlying substantive and synergistic effects on environmental sustainability barely explored to date. These issues also apply to sustainable cities, especially eco-cities. Therefore, this paper investigates the potential and role of data-driven smart solutions in improving and advancing environmental sustainability in the context of smart cities as well as sustainable cities, under what can be labeled "environmentally data-driven smart sustainable cities." To illuminate this emerging urban phenomenon, a descriptive/illustrative case study is adopted as a qualitative research methodology§ to examine and compare Stockholm and Barcelona as the ecologically and technologically leading cities in Europe respectively. The results show that smart grids, smart meters, smart buildings, smart environmental monitoring, and smart urban metabolism are the main data-driven smart solutions applied for improving and advancing environmental sustainability in both eco-cities and smart cities. There is a clear synergy between such solutions in terms of their interaction or cooperation to produce combined effects greater than the sum of their separate effects—with respect to the environment. Th

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Modelling Brain Connectivity Networks by Graph Embedding for Dyslexia Diagnosis 1st

Modelling Brain Connectivity Networks by Graph Embedding for...

引用

1st International Conference on Bioengineering and Biomedical Signal and Image Processing, BIOMESIP 2021

作者： Formoso, Marco A. Ortiz, Andrés Martínez-Murcia, Francisco J. Gallego-Molina, Nicolás Luque, Juan L. Escobar, Juan J. Montoya, Francisco G. Department of Communications Engineering University of Málaga Malaga Spain Department of Signal Theory Telematic and Communications University of Granada Granada Spain Granada Spain Department of Developmental Psychology University of Málaga Malaga Spain Department of Computer Architecture And Technology CITIC University Of Granada Granada Spain Department of Engineering University of Almeria Almeria Spain

ISBN: (纸本)9783030881627

Several methods have been developed to extract information from electroencephalograms (EEG). One of them is Phase-Amplitude Coupling (PAC) which is a type of Cross-Frequency Coupling (CFC) method, consisting in measure the synchronization of phase and amplitude for the different EEG bands and electrodes. This provides information regarding brain areas that are synchronously activated, and eventually, a marker of functional connectivity between these areas. In this work, intra and inter electrode PAC is computed obtaining the relationship among different electrodes used in EEG. The connectivity information is then treated as a graph in which the different nodes are the electrodes and the edges PAC values between them. These structures are embedded to create a feature vector that can be further used to classify multichannel EEG samples. The proposed method has been applied to classified EEG samples acquired using specific auditory stimuli in a task designed for dyslexia disorder diagnosis in seven years old children EEG’s. The proposed method provides AUC values up to 0.73 and allows selecting the most discriminant electrodes and EEG bands. © 2021, Springer Nature Switzerland AG.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

arXiv

引用

arXiv 2022年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

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：