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

Energy-Efficient Clustered Data Dissemination Based Routing in D2D Collaborative Vehicular Networks

Energy-Efficient Clustered Data Dissemination Based Routing ...

引用

Frontier Technologies and Solutions (ICFTS), International Conference on

作者： Shital Y. Gaikwad G. Anjaneyulu Dalia Al-Tarazi M. Rama Vivek M. Korde Kaniga Perumal Department of Computer Science and Engineering Mahatma Gandhi Missions College of Engineering and Technology Nanded M.S India Department of CE QIS College of Engineering and Technology (QISCET) Ongole Department of Architecture Engg Faculty of Engineering Zarqa university Zarqa Jordan College of Engineering University of Business and Technology Jeddah SA Department of ECE QIS College of Engineering and Technology Ongole AP Dept of Mechanical Engg Yeshwantrao Chavan College of Engineering Nagpur India Faculty of Science and Technology Spectrum International University College Selangor Malaysia

ISBN: (数字)9798331502768

ISBN: (纸本)9798331502775

VANETs are crucial for intelligent transportation systems, allowing V2V and V2I communication. A study introduces the ECDDR model using D2D for efficient data distribution and transmission in VANETs. The model optimizes shared uplink resources between mobile and vehicle user devices in a single-cell setup, focusing on large-scale fading for multi-hop ad-hoc routing. To enhance information dissemination, energy-efficient vehicle clustering is applied, with buses as Cluster Heads (CH) for improved resource utilization in urban settings. Experiments show the ECDDR model outperforms existing methods in data delivery ratio, network throughput, and energy efficiency while reducing routing cost and energy consumption. The model integrates D2D communication, multi-hop routing, and strategic clustering to boost reliability and efficiency in VANET operations, supporting smart city initiatives and autonomous vehicle technologies.

关键词： Costs Vehicle-to-infrastructure Vehicular ad hoc networks Spread spectrum communication Routing Throughput Energy efficiency Data models Device-to-device communication Reliability

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

Dynamic Optimizations in GPU Using Roofline Model

Dynamic Optimizations in GPU Using Roofline Model

引用

IEEE International Symposium on Circuits and Systems

作者： Winnie Thomas Suryakant Toraskar Virendra Singh Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering Indian Institute of Technology Bombay India

ISBN: (纸本)9781728192017;9781728192024

Massively parallel processors such as graphics processing units (GPUs) often face the challenge of resource underutilization due to varying resource proclivity of workloads. Running multiple applications on a GPU has been an efficient and known alternative to mitigate underutilization. This paper proposes a multi-application oriented framework that carries out dynamic optimizations based on the operational intensities of various applications. Our framework analyzes applications based on operational intensities to identify their bottleneck resources using Roofline model. We demonstrate that the proposed optimizations improve the utilization and system-wide throughput of the GPU co-running applications with irregular resource demands. The dynamic optimizations improve the performance by 14.8% on average and up to 72.4% over a state-of-the-art spatial multitasking technique.

关键词： Heuristic algorithms Graphics processing units Throughput Multitasking Resource management Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

Intelligent Optimization of Blasting Parameters in Railroad Tunnels Based on Blasting Quality Control

引用

Journal of Construction Engineering and Management 2025年第8期151卷

作者： Ma, Zhaoxi Gu, Jingtian Zhao, Qin Yang, Mingsong Qian, Chengwei He, Min Hei, Xinhong Dept. of Civil Engineering and Architecture Xi'an Univ. of Technology Shaanxi Xi'an710048 China Dept. of Computer Science and Engineering Xi'an Univ. of Technology Shaanxi Xi'an710048 China

Blasting parameters are crucial factors that directly affect the quality of tunnel excavation. To achieve optimal blasting results, it is necessary to continuously optimize the blasting parameters throughout the construction process, taking into account geological conditions. However, current research mainly focuses on optimizing single-type borehole parameters and fails to simultaneously address the requirements for minimizing overexcavation, underexcavation, and fragment size. This study proposes an intelligent optimization method for blasting construction parameters that combines support vector regression (SVR) with the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). Through grid search and genetic optimization algorithms, the SVR regression model is refined, establishing an accurate nonlinear mapping relationship between the borehole parameters of peripheral holes, auxiliary holes, and slot holes, and the resulting blasting effects. The NSGA-II algorithm is then employed to search for the Pareto optimal set of blasting construction parameters, with the goal of minimizing average linear overexcavation and the maximum fragment diameter. The technique for order of preference by similarity to the ideal solution (TOPSIS) method is used for multiattribute decision-making to identify the optimal blasting plan. The results show that the SVR model, optimized by the genetic algorithm, provides high prediction accuracy for blasting construction parameters, with determination coefficients of 0.89 and 0.97. Multiobjective optimization of blasting parameters using NSGA-II explores the effects of different parameter combinations on tunnel blasting outcomes. In designing and optimizing blasting parameters, particular attention should be paid to the optimization of peripheral and slot hole parameters to effectively control overexcavation, underexcavation, and fragment size. The intelligent optimization method proposed in this study, which integrates advanced intelligent al

关键词： Blasting

来源：评论

学校读者我要写书评

暂无评论

OCT based scanning system to enable 3D viewing, sharing and printing of artworks

OCT based scanning system to enable 3D viewing, sharing and ...

引用

3D Image Acquisition and Display: technology, Perception and Applications, 3D 2021 - Part of Imaging and Applied Optics Congress 2021

作者： Zhou, Xingyu In, Darlene Xiong, Xinchang Yang, Kunze Chen, Xing McCune Bruhn, Heather Liu, Xuan Yang, Yi Dept. of Electrical and Computer Engineering New Jersey Institute of Technology University Heights NewarkNJ07102 United States Division of Science and Engineering Penn State Abington AbingtonPA19001 United States The College of Arts and Architecture Penn State University ParkPA16802 United States

We acquired 3D volumetric data of artworks with an OCT-based hybrid scanning platform. The data is then exported into standard 3D data formats that can be 3D printed, shared, and viewed in VR and AR. © 2021 The A... 详细信息

ISBN: (纸本)9781557528209

关键词： Volumetric analysis

来源：评论

学校读者我要写书评

暂无评论

Fall Detection System for Elderly (FDS-E) using Low-cost Camera Based on LSTM and OpenPose

Fall Detection System for Elderly (FDS-E) using Low-cost Cam...

引用

IEEE Instrumentation and Measurement technology Conference

作者： Herti Miawarni Tri Arief Sardjono Eko Setijadi Wijayanti Mauridhi Hery Purnomo Dept. of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Electrical Engineering Dept. of Biomedical Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Architecture Faculty of Engineering Universitas Diponegoro Semarang Indonesia Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember University Center of Excellence on Artificial Intelligence for Healthcare and Society (UCE AIHeS) Surabaya Indonesia

Recently, many countries have been dealing with an increasing amount of elderly who are living alone. Unfortunately, fall incidents in the elderly tend to happen, and without proper dependable care would lead to fatal injuries. The elderly must be closely monitored under constant observation. Accidental falls are a leading cause of injury, mortality, and mobility limitations in the elderly. The expenses of national healthcare systems are also significantly impacted by accidental falls. These findings highlight the importance of investing heavily in the study and advancement of fall detection and intervention technologies. It is essential to recognize them early and provide fast assistance by developing technologies that can simultaneously improve the standard and the safety of the elderly's living environment. In this paper, we present a computer vision algorithm for falling incident detection using a low-cost camera and deep learning model. Ultimately, this algorithm can be used for the cases of elderly, in which falling risk is high and fatal. Furthermore, one self-developed dataset was used to validate the suggested approach experimentally. We used an OpenPose-based feature using a low-cost camera input and then classified each event or activity as either fall or non-fall. Classification tasks are carried out by Long Short-Term Memory (LSTM) with multiple validation metrics. The LSTM in this work is also optimized using Bayesian method. Finally, our approach to recognize falls has accuracy of 99.5%, which is distinct from other past works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Paratuberculosis in Histopathological Images Based on Explainable Artificial Intelligence and Deep Learning

arXiv

引用

arXiv 2022年

作者： Yiǧit, Tuncay Şengöz, Nilgün Özmen, Özlem Hemanth, Jude Işik, Ali Hakan Dept. of Computer Engineering Faculty of Engineering Süleyman Demirel University Isparta32260 Turkey Dept. of Pathology Faculty of Veterinary Medicine Burdur Mehmet Akif Ersoy University Burdur15030 Turkey Karunya Institute of Technology & Sciences Coimbatore641114 India Dept. of Computer Engineering Faculty of Engineering and Architecture Burdur Mehmet Akif Ersoy University Burdur15030 Turkey

Artificial intelligence holds great promise in medical imaging, especially histopathological imaging. However, artificial intelligence algorithms cannot fully explain the thought processes during decision-making. This situation has brought the problem of explainability, i.e., the black box problem, of artificial intelligence applications to the agenda: an algorithm simply responds without stating the reasons for the given images. To overcome the problem and improve the explainability, explainable artificial intelligence (XAI) has come to the fore, and piqued the interest of many researchers. Against this backdrop, this study examines a new and original dataset using the deep learning algorithm, and visualizes the output with gradient-weighted class activation mapping (Grad-CAM), one of the XAI applications. Afterwards, a detailed questionnaire survey was conducted with the pathologists on these images. Both the decision-making processes and the explanations were verified, and the accuracy of the output was tested. The research results greatly help pathologists in the diagnosis of *** Codes 68T07 © 2022, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Recommendation System Towards Residential Energy Saving Based on Anomaly Detection

Recommendation System Towards Residential Energy Saving Base...

引用

International Conference on Signal Processing and Information Security (ICSPIS)

作者： Shadi Atalla Yassine Himeur Wathiq Mansoor Abbes Amira Fodil Fadli Abigail Copiaco Shahab Saquib Sohail College of Engineering and IT University of Dubai Dubai UAE Department of Computer Science University of Sharjah Sharjah UAE Dept. of Architecture & Urban Planning Qatar University Doha 2713 Qatar School of Engineering Sciences & Technology Jamia Hamdard New Delhi 110062 India

ISBN: (纸本)9781665492669

This paper presents a recommender system to promote energy consumption reduction behaviors in residential buildings. The system exploits data stream processing methods jointly with machine learning algorithms on real-time residential data. Specifically, the data stream includes disaggregated power consumption, context, and weather conditions data. Internally the system converts time-series data streams into discrete ordered data points, which serve as inputs for training ML models. This method is used to predict power consumption anomalies. Gradually, the system helps to shape its users’ activities into more energy-efficient ones. The experimental evaluation on real and simulated datasets demonstrates the promising performance of the proposed method, primarily when the K-neighbors neighbors’ algorithm is used to classify the features extracted with interleaving current with the previous data points. The performance assessment of the machine learning algorithms shows the suitability of our implementation for Edge and Fog platforms in terms of accuracy, latency, and model size.

关键词： Training Power demand Machine learning algorithms Shape Signal processing algorithms Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Emotion detection in infants using an ensemble classifier with a novel member selection technique

Emotion detection in infants using an ensemble classifier wi...

引用

2020 Summer computer Simulation Conference, SCSC 2020, Held at the 2020 Summer Simulation Multi-Conference, SummerSim 2020

作者： Fahmy, Hesham Ahmed Fahmy, Sherif Fadel Del Barrio García, Alberto A. Juan, Guillermo Botella Dept. of Electronics and Communications Dept. of Computer Engineering Arab Academy for Science Technology and Maritime Transport 2401 Smart Village Campus Giza12577 Egypt Dept. of Computer Architecture and Automation Complutense University of Madrid Ciudad Universitaria C/ Jose Santesmases 9 Madrid28040 Spain

ISBN: (纸本)9781713819462

In this paper, we develop a method for detecting infant emotion from images using machine learning techniques. It is important to develop automatic infant emotion detection algorithms as they can become part of an integrated system that monitors the well-being of infants at home and in institutional settings. In particular, we develop an ensemble classifier that combines the results from diverse individual classifiers to produce better classification results. We present a novel method for selecting members of the ensemble that is based on the Pearson correlation coefficient of the location of the errors in the classifiers. The results show that the ensemble classifier outperforms individual classifiers by at least 1.4 times, and outperforms a state-of-the-art open-source algorithm for adult emotion detection by a larger margin. The results also indicate that Pearson Correlation among classifiers at a certain number of classifier count is a good criterion for selecting ensemble members. ©2020 Society for Modeling & Simulation (SCS) International

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：