检索结果-内蒙古大学图书馆

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Cao, Tong Pang, Qingle Wang, Yangjie Sun, Jingyang Zhou, Tai Chai, Mengya Qingdao University of Technology Dept. School of Information and Control Engineering Qingdao China

ISBN: (纸本)9798350399059

Microgrids, as self-contained energy systems, possess great potential in facilitating renewable energy consumption and optimizing energy structures. This paper introduces a model for energy dispatch in microgrids that incorporates demand-side response, utilizing a sigmoid continuum and the chaotic seagull optimization algorithm (SCCSOA). The objective is to tackle the multi-constrained and non-linear operational characteristics of microgrids. The enhanced algorithm leverages a chaotic sequence to initialize the seagull population, while employing the sigmoid function to guide the seagull search process. This approach significantly improves the algorithm's global search capability. Furthermore, a golden sine mechanism is introduced to enhance the local search efficiency in the later stages of the algorithm. The effectiveness of the improved algorithm in microgrid systems is verified through arithmetic simulations that analyze optimization results for different scheduling strategies, thus demonstrating its adaptability. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Fault Location Method for Distribution Network Based on Fusion of Transient Energy and Polarity Value Comparison 6

Fault Location Method for Distribution Network Based on Fusi...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Sun, Jingyang Pang, Qingle Cao, Tong Wang, Yangjie Qingdao University of Technology Dept. School of Information and Control Engineering Qingdao China

ISBN: (纸本)9798350399059

The widespread application of distributed generator (DG) in distribution networks can improve the quality of electrical energy and ensure the stability of power supply, but at the same time, it raises the electricity network's complexity and fault rate, which has a significant impact on the power network's ability to operate safely, reliably, and effectively. Consequently, in order to assure the safety, dependable, and effective functioning of distribution network systems, it is crucial to minimize the hazards that DG pose to their operation. To successfully use DG to address the issue of single-phase ground fault location in distribution networks, this paper elucidates the transient energy and the polarity value comparison fault location method, proposes a distribution network fault location method based on fusion of transient energy and polarity value comparison. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Automated Symptom Tracking And Prediction Of Angioedema Disease Using Machine Learning

Automated Symptom Tracking And Prediction Of Angioedema Dise...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Arunkumar, M. Palanisamy, M. Viknesh, K. Mugilarasan, M. Abinesh, B. Ifet College Of Engineering Dept. Of Information Technology Tamilnadu Villupuram India Dhanalakshmi Srinivasan Engineering College Dept. Of Information Technology Tamilnadu Perambalur India Ifet College Of Engineering Dept. Of Information Technology Tamilnadu Villupuram India

ISBN: (纸本)9798350352689

The timely and precise identification of skin diseases is essential to optimizing therapy effectiveness and attaining favorable patient outcomes. However depending solely on visual examination and conventional diagnostic techniques adds subjectivity and might take a long time, which increases the risk of misdiagnosis or postponed treatment. This research aims to develop a machine-learning model to detect angioedema disease, a potentially fatal illness marked by sudden swelling of the skin and mucous membranes. Using several feature extraction techniques, the proposed model extracts texture, color, and intensity information from skin photographs. These extracted attributes are then integrated into a transfer learning framework to enhance overall performance, utilizing data from previously trained models. The shortcomings of traditional machine learning methods, such the need for huge datasets or protracted training cycles, are addressed by this innovative methodology The created approach has the potential to help medical practitioners make well-informed diagnoses, especially in areas with limited resources. The methodology has the potential to greatly improve patient outcomes and save healthcare costs by enabling early diagnosis and permitting proactive treatment actions. This development is especially helpful for increasing access to precise diagnoses in a variety of healthcare environments, guaranteeing that patients receive prompt and effective therapy. © 2024 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Solution to Mitigate the Disadvantages in the Design of LLC Resonant Converters for Electric Vehicle Fast Chargers with High Output Power and Wide Output Voltage Range

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第2期74卷 316-325页

作者： Park, Ha-Min Lee, Hyung-Woo Park, Chan-Bae Guo, Youguang Lee, Jae-Bum Dept. of Railway Vehicle & Operation System Engineering Korea National University of Transportation Korea Republic of Dept. of Electrical and Data Engineering University of Technology Sydney Australia Dept. of Railroad Electrical and Information Engineering Korea National University of Transportation Korea Republic of

As the number of electric vehicles grows, the development of fast chargers is advancing rapidly. A DC-DC converter that can deliver high output power, a fixed input voltage, and a wide output voltage range is critical for electric vehicle fast chargers. While the LLC resonant converter is commonly used in these converters, it requires a low magnetizing inductance, which increases the transformer air gap, causing additional AC losses in the windings due to the fringing effect. To mitigate these issues, this study explores design solutions in LLC resonant converters. By using two transformers per module, with the primary sides connected in series and the secondary sides in parallel, the number of primary turns can be reduced, minimizing the air gap. This reduction also allows for structural changes in the windings, improving heat dissipation. Magnetic field analysis and circuit simulations were conducted to validate the proposed DC-DC converter design. Copyright © The Korean Institute of Electrical Engineers.

关键词： Transformer windings

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive Target Detection with Optimal Transportation for Different Satellite SAR Images 15

Domain Adaptive Target Detection with Optimal Transportation...

引用

15th European Conference on Synthetic Aperture Radar, EUSAR 2024

作者： Qin, Jiang Zou, Bin Zhang, Lamei Qiu, Yu Dept. of Information Engineering Harbin Institute of Technology China

ISBN: (纸本)9783800762873

Satellite-borne SAR image target detection is widely used across various fields. However, there are different data distributions among SAR images from different satellite sensors and different imaging conditions. This makes it challenging for deep learning based detectors to achieve performance generalization for different data domains with distributional discrepancies. In this paper, an Optimal Transport based domain Adaptive target Detection (OTAD) method is proposed to improve target detection performance under the data distributional discrepancies in the realistic scenarios. OTAD utilizes geometry-aware clustering assignment to estimate prototypes corresponding to different geometries. Subsequently, unbalanced optimal transport is employed to map target features to source prototypes corresponding to their respective geometries. In this way, OTAD accomplishes feature adaptation between source and target domains, reducing feature distributional discrepancies while preserving intra-domain structures. Two cross-domain target detection tasks are constructed using Gaofen-3 and Sentinel-1 SAR data in the experiments. The cross-domain detection results demonstrate that OTAD effectively reduces feature distributional discrepancies and improves target detection performance for different satellite SAR images. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Fast Method for Water and Airport Segmentation in SAR Images 15

A Lightweight and Fast Method for Water and Airport Segmenta...

引用

15th European Conference on Synthetic Aperture Radar, EUSAR 2024

作者： Qiu, Yu Zou, Bin Zhang, Lamei Dept. of Information Engineering Harbin Institute of Technology China

ISBN: (纸本)9783800762873

In large scene SAR images, the extraction of regions of interest is crucial for improving the accuracy of target detection. Airports and water bodies within these scenes often contain aircraft and ships, which are primary targets for detection. SAR images exhibit similar scattering characteristics for airport runways and water bodies. In light of this, our paper presents a lightweight and fast segmentation method applicable to both airport and water regions(LFSAW). Firstly, we construct a lightweight and efficient concatenate module (LECM) for rapid feature extraction. Subsequently, we create a specialized module for SAR images that extracts edge information (DIEM) from ground truth and utilizes it for supervision while simultaneously enhancing the segmentation performance by extracting detailed information. Finally, we employ a multi-task loss function to jointly supervise the edge detail and segmentation information. Furthermore, to facilitate simultaneous segmentation of airport and water regions, we build a dataset comprising 7931 image slices designed specifically for airport-water body segmentation tasks. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

IoT Based Night Patrol Robot Leveraging Voice technology for Superior Surveillance

IoT Based Night Patrol Robot Leveraging Voice Technology for...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Libina, M. Dhevendhiran, R. Praveenkumar, B. Ifet College of Engineering Dept. of Information Technology Villupuram India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

It designs and implements an IoT-based night patrol robot that has improved surveillance capabilities by combining voice technology. The patrol robot system is remote-controlled, patrols designated areas at night, and provides real-time monitoring through onboard sensors and live video feed. This robot provides an easy interface to human operators that can give voice commands. There is no need for physical interactions in terms of remote control or status updates that can run on the desired location from instructions from the control room. The night patrol human risks lead to reduced awareness, vulnerabilities, physical health, and work-life balance. Motion detection, along with the sensing of environmental conditions, and secure wireless communication ensure real-time alerts for suspicious activities in areas like cities, critical areas, and construction sites. The patrol robot is efficient, scalable, and cost-effective in enhancing traditional security systems. The robot can run in a crucial area that human patrol cannot do, ensuring reliability, flexibility, and adaptability to the environment it roams. It includes technologies like motion detection, location tracking, and voice controls that can reduce human intervention while providing improvements in safety in high-risk environments. The robot can increase the emergency patrol assistant by monitoring live video streaming to control rooms. The results from prototype testing indicate effectiveness in performing patrol duties and in responding to voice-based instructions in varying environmental conditions. © 2025 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Asymmetric Key Cryptographic Algorithms in Image Encryption

Comparative Study of Asymmetric Key Cryptographic Algorithms...

引用

2025 International Conference on Computer, Electrical and Communication engineering, ICCECE 2025

作者： Maiti, Pubali Paul, M. Atanu Kumar Acharya, Meenakshi Government College of Engineering and Ceramic Technology Dept. of Information Technology Kolkata India

ISBN: (纸本)9798331513894

In the realm of information security, ensuring the confidentiality and integrity of image communication has become a critical concern, especially in the context of modern technological advancements. This paper presents an in-dept. analytical study of image encryption using asymmetric key cryptography algorithms such as RSA, ElGamal, Elliptic Curve Cryptography (ECC), and LUC. The study explores the encryption and decryption mechanisms of these algorithms, assesses their computational efficiency, and evaluates their strengths and weaknesses in the context of secure image transmission. The paper concludes with a detailed comparison of these algorithms, identifying the most suitable ones for practical application in secure communication systems. Finally, the study highlights the need for algorithms that are not only secure but also capable of efficiently handling the growing challenges, ensuring minimal computation overhead and no compromise in encryption and decryption speeds. © 2025 IEEE.

关键词： Decryption EIGamal Elliptic Curve Cryptography (ECC) Encryption LUC Rivest-Shamir-Adleman (RSA)

来源：评论

学校读者我要写书评

暂无评论

Offline-Online Actor-Critic for Partially Observable Markov Decision Process

Offline-Online Actor-Critic for Partially Observable Markov ...

引用

2023 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2023

作者： Xuesong, Wang Diyuan, Hou Yuhu, Cheng China University of Mining and Technology Dept. School of Information and Control Engineering Xuzhou China

ISBN: (纸本)9798350309003

Offline-online reinforcement learning combines the advantages of offline learning in terms of sample efficiency and online learning in terms of exploration and trial-and-error. On the other hand, the partial observability of the environment is a challenging issue in reinforcement learning. This paper proposes a Partially Observable Offline-Online Actor-Critic (PO3AC) algorithm. In PO3AC, during both the offline and online training phases, different weighted behavior cloning regularization terms are considered to alleviate the distribution shift. During training, the actor and critic are trained separately, and a recurrent neural network is used to train a state prediction model that predicts the mapping of observation to belief states. Experimental results conducted on the PyBullet physics engine demonstrate that the proposed algorithm outperforms existing algorithms. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An AI-driven GPT Model for Automated Detection of Heart Disease using ECG Dataset

An AI-driven GPT Model for Automated Detection of Heart Dise...

引用

2025 AI-Driven Smart Healthcare for Society 5.0, AdSoc5.0 2025

作者： Pati, Kingshuk Banik, Shubhayu Md Sahil, S.K. Srimani, Abhrodip Ghosh, Sima Dasgupta, Sudakshina Dept. of Information Technology Government College Of Engineering and Textile Technology Serampore India

ISBN: (纸本)9798331536336

Globally, heart disease is the major ingredient of mortality. Heart attacks are frequently caused by Coronary Artery Disease (CAD) due to the unavailability of the oxygenated blood to the heart muscles. Medical professionals find it challenging to forecast since it demands experiences and a deeper level of predictive knowledge. The healthcare industry has a wealth of information, but it not only lacks understandability of the data, but also has insufficient tools for analyzing the data to find the hidden patterns. Automated Electrocardiogram (ECG) analysis may prove to be a beneficial tool in smart healthcare systems. An automated diagnosis method based on machine learning offers a dependable, cost-effective, and efficient means of detecting cardiac disease. It requires a huge number of data which is hard to be analyzed and interpreted by traditional techniques. The intention is to identify an appropriate interpretable automated method for heart disease prediction with maximum accuracy and efficiency. © 2025 IEEE.

关键词： Electrocardiography

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：