检索结果-内蒙古大学图书馆

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： S.P. Ramesh Ali Hadi Abdulwahid Afsana Anjum N. Venkatesh Rajesh Singh M. Kalyan Chakravarthi Department of Computer Science and Engineering AMET University Kanathur Tamil Nadu Department of Control &Automation Southern Technical University Engineering Technical College Basra Iraq Department of Information Technology & Security Jazan University Jazan KSA School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Uttaranchal Institute of Technology Uttaranchal University India School of Electronics Engineering VIT-AP University Amaravathi India

The demand on healthcare is growing as a result of the expanding global population, rising demands for successful treatment, and an underlying improvement in life quality. Consequently, healthcare remains one of the most significant social and economic problems in the world, necessitating the development of new and more sophisticated scientific and technological treatments.E-health services are provided via personalised healthcare systems to meet the medical and support needs of the ageing population. An important development in the Big Data age is the Internet of Things, which facilitates several real-time engineering solutions through improved services. Healthcare systems are now using analytics over IoT data streams as a stream of user data to find new information, forecast rapid recognition, and make decisions on life-threatening situations. In this study, researchers have carried out a thorough review of the hottest recent revolutionary technologies in bespoke healthcare systems, with a focus on hypervisor, cloud infrastructure, big data analytic, the Web of Things, and smartphone apps. In order to make early disease detection and diagnosis possible, it is important to develop a better healthcare system. We have examined these problems and suggested potential solutions while offering secure e-health services. The purpose of this study is to design a smart and secure remote monitoring and warning system using the latest emerging technologies in 21 st century such as big data analytics and Internet of Things (IoT) ecosystems. In this study the researchers discussed a detailed research methodology to meet the outcomes of the reerach. All the relevant findings and analysis are explained in descriptive manner. Moreover, this study highlights the constantly expanding requirements for better medical systems in the present and offers potential directions for future research.

关键词： Industries Patient monitoring Ecosystems Sociology Medical services Big Data Alarm systems

来源：评论

学校读者我要写书评

暂无评论

EDF-SSD: An Improved Feature Fused SSD for Object Detection

EDF-SSD: An Improved Feature Fused SSD for Object Detection

引用

IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)

作者： Tanvir Ahmad Xiaona Chen Ali Syed Saqlain Yinglong Ma School of Control and Computer Engineering North China Electric Power University Beijing China

Single Shot Multibox Detector (SSD), which is considered one of the top prominent algorithms for object detection in terms of speed and accuracy. However, in the feature pyramid, conventional SSD uses every layer individualistically and ignores the background information of the objects by taking only the fine-grained details of the objects into account, which drops its accuracy in certain cases especially in heavy occlusion, objects overlapping and small objects. It is a known fact that if the number of feature maps is increased, the efficiency of a deep network is considered to be increased, but just simply rising the number of feature maps will not bring any improvement. Regarding the lack of feature complementarity in conventional SSD feature layers and its low accuracy in certain circumstances, this paper proposed a multi-scale strategy to combine feature maps of a low-level feature with the deconvolutional layers on conventional SSD to improve the efficiency, for simplicity, we called the proposed method EDF-SSD (Enhanced Deconvolution Feature Fused SSD). The proposed EDF-SSD is evaluated on MS COCO and PASCAL VOC 2007 datasets, the experiment results show that EDF-SSD has achieved higher mAP on both datasets by comparing with that of conventional SSD.

关键词： Cloud computing Deconvolution Conferences Object detection Detectors Big Data Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks

arXiv

引用

arXiv 2023年

作者： Ledda, Emanuele Fumera, Giorgio Roli, Fabio Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Via Dodecaneso 35 Genova16146 Italy Department of Electric and Electronic Engineering University of Cagliari Via Marengo 3 Cagliari09100 Italy

Among Bayesian methods, Monte-Carlo dropout provides principled tools for evaluating the epistemic uncertainty of neural networks. Its popularity recently led to seminal works that proposed activating the dropout layers only during inference for evaluating uncertainty. This approach, which we call dropout injection, provides clear benefits over its traditional counterpart (which we call embedded dropout) since it allows one to obtain a post hoc uncertainty measure for any existing network previously trained without dropout, avoiding an additional, time-consuming training process. Unfortunately, no previous work compared injected and embedded dropout;therefore, we provide the first thorough investigation, focusing on regression problems. The main contribution of our work is to provide guidelines on the effective use of injected dropout so that it can be a practical alternative to the current use of embedded dropout. In particular, we show that its effectiveness strongly relies on a suitable scaling of the corresponding uncertainty measure, and we discuss the trade-off between negative log-likelihood and calibration error as a function of the scale factor. Experimental results on UCI data sets and crowd counting benchmarks support our claim that dropout injection can effectively behave as a competitive post hoc uncertainty quantification technique. © 2023, 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

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

arXiv

引用

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Quantum Circuit engineering for Correcting Coherent Noise

arXiv

引用

arXiv 2021年

作者： Ahsan, Muhammad Naqvi, Syed Abbas Zilqurnain Anwar, Haider Department of Mechatronics and Control Engineering University of Engineering and Technology Lahore Pakistan Department of Computer Science Namal Institute

Crosstalk and several sources of operational interference are invisible when qubit or a gate is calibrated or benchmarked in isolation. These are unlocked during the execution of full quantum circuit applying entangling gates to several qubits simultaneously. Unwanted Z-Z coupling on superconducting cross-resonance CNOT gates, is a commonly occurring unitary crosstalk noise that severely limits the state fidelity. This work presents (1) method of tracing unitary errors, which exploits their sensitivity to the arrangement of CNOT gates in the circuit and (2) correction scheme that modifies original circuit by inserting carefully chosen compensating gates (single- or two-qubit) to possibly undo unitary errors. On two vastly different types of IBMQ processors offering quantum volume 8 and 32, our experimental results show up to 25% reduction in the infidelity of [[7, 1, 3]] code |+i state. Our experiments aggressively deploy forced commutation of CNOT gates to obtain low noise state-preparation circuits. Encoded state initialized with fewer unitary errors marks an important step towards successful demonstration of fault-tolerant quantum computers. Copyright © 2021, The Authors. All rights reserved.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Model Checking of Cooperative Tripping Based on Timed Automata

Model Checking of Cooperative Tripping Based on Timed Automa...

引用

Electrical engineering (CIYCEE), IEEE China International Youth Conference on

作者： Xiong Haijun Wang Yao Jiang He Ye Xingyu School of Control and Computer Engineering North China Electric Power University Baoding China

ISBN: (纸本)9781665400657

Networked collaborative tripping can effectively reduce the construction complexity of the backup protection system, but there is still a lack of research on the reachability and real-time verification of the tripping algorithm. In this paper, the networked cooperative trip system is regarded as a reactive real-time system, and a method for verifying the cooperative characteristics of the protection system based on a timed automata is proposed. First, the timed automata are used to give the calculation model of the protection IED, the circuit breaker XCBR and the overall protection system, and then UPPAAL is used to model the model, and the description method of time characteristics is given, and the UPPAAL tool is used to verify the model. The algorithm model in the bus 12node system has been effectively verified. This method can complete the accessibility and real-time evaluation of the tripping algorithm, which is of great significance for reducing the hidden dangers in the system design.

关键词： Electrical engineering Conferences Automata Collaboration Model checking Real-time systems Delays

来源：评论

学校读者我要写书评

暂无评论

Robust Frequency Regulation for Dual-Area Interconnected Grids Using Hybrid controller: A Comparative Study

Robust Frequency Regulation for Dual-Area Interconnected Gri...

引用

Smart Technologies for Power, Energy and control (STPEC), IEEE International Conference on

作者： Awadh Ba Wazir Abdullah A. Alhussainy Abdulraheem H. Alobaidi Aatif Altaf Anil Kumar Mahendra Kumar Sultan Alghamdi Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz University Jeddah Saudi Arabia Instrumentation and Control Engineering Department Dr. B R Ambedkar National Institute of Technology Jalandhar Jalandhar Punjab India

This paper introduces a robust controller designed for load frequency control in a dual-area integrated power grid. Here, the suggested controller is a blend of a fuzzy logic controller with an integral controller. The parameters of the integral controller and frequency bias settings are optimized to enhance the dynamic response of the proposed controller. To attain this, three distinct optimization algorithms are employed, i.e., genetic algorithm, simulated annealing, and pattern search. A new objective function using settling time, settling-max, and settling-min with a suitable weight factor is used to improve the parameters estimation process. A comparative analysis is performed using the proposed approach and classical-I controller under two cases considering several load disturbance scenarios. Furthermore, the suggested hybrid controller is evaluated and compared with similar models in the literature. As expected, the proposed controller exhibits superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A WAVELET GUIDED ATTENTION MODULE FOR SKIN CANCER CLASSIFICATION WITH GRADIENT-BASED FEATURE FUSION

arXiv

引用

arXiv 2024年

作者： Roy, Ayush Sarkar, Sujan Ghosal, Sohom Kaplun, Dmitrii Lyanova, Asya Sarkar, Ram Department of Electrical Engineering Jadavpur University Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Electronics and Communication Engineering International Institute of Information Technology Chhattisgarh Naya Raipur India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University"LETI" Saint Petersburg Russia

Skin cancer is a highly dangerous type of cancer that requires an accurate diagnosis from experienced physicians. To help physicians diagnose skin cancer more efficiently, a computer-aided diagnosis (CAD) system can be very helpful. In this paper, we propose a novel model, which uses a novel attention mechanism to pinpoint the differences in features across the spatial dimensions and symmetry of the lesion, thereby focusing on the dissimilarities of various classes based on symmetry, uniformity in texture and color, etc. Additionally, to take into account the variations in the boundaries of the lesions for different classes, we employ a gradient-based fusion of wavelet and soft attention-aided features to extract boundary information of skin lesions. We have tested our model on the multi-class and highly class-imbalanced dataset, called HAM10000, and achieved promising results, with a 91.17% F1-score and 90.75% accuracy. The code is made available at: https://***/AyushRoy2001/ WAGF-Fusion. © 2024, CC BY.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

An Optimal Scheduling Strategy of Spinning Reserve Considering Coordination Between Source and Load for Power System

An Optimal Scheduling Strategy of Spinning Reserve Consideri...

引用

IEEE Asia Power and Energy engineering Conference (APEEC)

作者： Zhaoguo Yu Ziqiu Song Yang Hu Hanyu Feng School of Control and Computer Engineering North China Electric Power University Beijing China

Due to large-scale wind power integration, the operation and reserve of power system has been seriously affected. It is necessary to utilize other resources to replace conventional generators to provide reserve capacity for power system. Taking multiple types of reserve resources into account, an optimal scheduling strategy of spinning reserve considering coordination between source and load for power system is proposed. Firstly, according to the mode and operation constraints of reserve resources, the reserve models of conventional generators, wind farm and demand response are established. Secondly, with the objective function of minimizing the operation cost and reserve cost of power system, the optimal scheduling model of spinning reserve based on source load coordination is constructed. Finally, a case of 6-machine 30 bus system is carried out to prove that the economy of power system is improved obviously, and the effectiveness of the proposed optimal scheduling strategy is verified. Furthermore, the impact of wind farm and demand response reserve cost on the system spinning reserve capacity allocation is analyzed respectively, and it has a certain reference significance for reserve resource bidding mechanism of power system.

关键词： Biological system modeling Optimal scheduling Wind power generation Wind farms Load management Generators Power systems

来源：评论

学校读者我要写书评

暂无评论

Motion Planning for Tractor-Trailer System

Motion Planning for Tractor-Trailer System

引用

control Conference (ICC), 2019 Sixth Indian

作者： Tanuj Thakkar Arpita Sinha Computer Science & Engineering Charotar University of Science & Technology India System and Control Engineering IIT BombayIndia

ISBN: (纸本)9781665409797

Motion planning for a tractor-trailer system is a challenging problem due to the nonholonomic constraints and highly nonlinear nature of the system. In this paper, we present a motion planning approach based on the Hybrid A* algorithm which produces smooth, collision-free, and kinematically feasible paths for a tractor-trailer system in a known environment. Kinematic model based on the on-axle hitching configuration of the tractor-trailer system is used for node expansion. Voronoi graph is used to compute sub-goals that guide the search towards the goal faster. A pure pursuit controller is employed to track the generated trajectory. The planning approach is evaluated over a number of Monte-Carlo simulation runs, and the experimental results indicate a perfect accuracy.

关键词： Adaptation models Monte Carlo methods Tracking Computational modeling Kinematics Planning Trajectory

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：