检索结果-内蒙古大学图书馆

International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

作者： Aphrodis Nduwamungu Tek Tjing Lie Ioannis Lestas Nirmal-Kumar C Nair Kosala Gunawardane Dept of Elect & Elec Engineering Auckland Univ. of Technology New Zealand Dept of Information Engineering Univ. of Cambridge United Kingdom Dept of Elect Computer & Software Engineering University of Auckland New Zealand School of Elect and Data Eng. Univ of Technology Sydney Australia

ISBN: (数字)9798350372786

ISBN: (纸本)9798350372793

For DC microgrids (MGs) with load variations and fixed operating points, the use of both linear and nonlinear droop controllers and their extensions is recommended. However, in future architectures with diverse loads ranging from light to heavy, including constant power loads, and fluctuating system parameters, this approach becomes impractical. Linear droop control, with a single droop coefficient, faces challenges in ensuring equitable current sharing due to cable resistance-induced voltage drops. Nonlinear droop control, with a high droop coefficient at heavy loads, may lead to suboptimal current sharing during light load conditions. To address these issues, an optimized piecewise linear droop control is proposed as an intermediary solution, demonstrating superior voltage regulation and current sharing in simulations, particularly under varying loads. Worst-case scenarios highlight the controller's dynamic adjustment of the droop coefficient for each load segment. Stability assessments of parallel buck converters have been conducted by varying critical parameters.

关键词： Buck converters Accuracy Power system dynamics Power system stability Load management Probabilistic logic Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Conv-Mamba-Hybrid Network for Medical Image Segmentation

A Novel Conv-Mamba-Hybrid Network for Medical Image Segmenta...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Sibo Qiao Zhiyuan Zhao Pengfei Xie Wenjing Yin Min Wang Yuanyuan Zhang Shanchen Pang The College of Software Tiangong University Tianjin China The College of Computer Science and Technology China University of Petroleum Qingdao China The Department of Electrical Engineering and Computer Science Khalifa University of Science and Technology Abu Dhabi United Arab Emirates The College of Life Sciences Tiangong University Tianjin China The College of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In the rapidly advancing landscape of intelligent medical technology, high-precision and widely applicable medical image segmentation techniques are pivotal in advancing personalized treatment plans and enhancing patient experiences. To address inherent obstacles, such as complex structures and features that are difficult to capture in segmentation tasks, we first propose a CMH module that merges convolutional neural networks (CNNs) with state space models (e.g., Mamba). This module hierarchically integrates CNN’s local priors into the Mamba layer, adeptly capturing specific details of target objects and broader contextual information from different perspectives. Subsequently, we introduce an information fusion module based on Mamba (MIH), aimed at dynamically fusing feature information from different paths and levels to enhance feature expression and discrimination. Building upon the abovementioned modules, we develop an unexplored segmentation model, CMHNet, capable of flexibly capturing feature maps of varying scales and angles from medical images. In the experiments, we present CMHNet’s distinguished performance in segmentation tasks through massive experiments on four medical datasets.

关键词： Image segmentation Sensitivity Anatomical structure Medical services Robustness Real-time systems Lesions Medical diagnostic imaging Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning

arXiv

引用

arXiv 2024年

作者： Liu, Fan Yao, Liang Zhang, Chuanyi Wu, Ting Zhang, Xinlei Jiang, Xiruo Zhou, Jun College of Computer Science and Software Engineering Hohai University Nanjing210098 China College of Artificial Intelligence and Automation Hohai University Nanjing210098 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Information and Communication Technology Griffith University NathanQLD4111 Australia

Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three lightweight detection frameworks on two benchmark datasets. Extensive experiments demonstrate that our approach can effectively improve model accuracy and achieve state-of-the-art (SoTA) performance on two datasets. Our code and dataset will be publicly available once the paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-II

arXiv

引用

arXiv 2024年

作者： Wu, Rixin Wang, Ran Hao, Jie Wu, Qiang Wang, Ping Niyato, Dusit The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing Jiangsu210038 China The Department of Electrical Engineering and Computer Science Lassonde School of Engineering York University M3J 1P3 Canada The School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

This paper proposes a weight-aware deep reinforcement learning (WADRL) approach designed to address the multiobjective vehicle routing problem with time windows (MOVRPTW), aiming to use a single deep reinforcement learning (DRL) model to solve the entire multiobjective optimization problem. The Non-dominated sorting genetic algorithm-II (NSGA-II) method is then employed to optimize the outcomes produced by the WADRL, thereby mitigating the limitations of both approaches. Firstly, we design an MOVRPTW model to balance the minimization of travel cost and the maximization of customer satisfaction. Subsequently, we present a novel DRL framework that incorporates a transformer-based policy network. This network is composed of an encoder module, a weight embedding module where the weights of the objective functions are incorporated, and a decoder module. NSGA-II is then utilized to optimize the solutions generated by WADRL. Finally, extensive experimental results demonstrate that our method outperforms the existing and traditional methods. Due to the numerous constraints in VRPTW, generating initial solutions of the NSGA-II algorithm can be time-consuming. However, using solutions generated by the WADRL as initial solutions for NSGA-II significantly reduces the time required for generating initial solutions. Meanwhile, the NSGA-II algorithm can enhance the quality of solutions generated by WADRL, resulting in solutions with better scalability. Notably, the weight-aware strategy significantly reduces the training time of DRL while achieving better results, enabling a single DRL model to solve the entire multiobjective optimization problem. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CovDNet: A Hybrid Multi - Level Densely Connected Neural Network for Improvised Analysis and Classification of COVID-19 Using Chest CT-Scans

CovDNet: A Hybrid Multi - Level Densely Connected Neural Net...

引用

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Deepa S Praveenkumar G D R Suguna Vivek Duraivelu C Jamunadevi S G Sundhar Department of Computer Technology-PG Kongu Engineering College Perundurai Erode Tamilnadu Department of computer science Vet institute of Arts and Science (Co-Education) College Erode Tamilnadu Department of Computer science and Engineering Bannari Amman Institute of Technology Sathyamangalam Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana Department of Computer Technology PG Kongu Engineering College Perundurai Erode Tamilnadu Final M.Sc(Software Systems) Kongu Engineering College Perundurai Erode Tamilnadu

COVID-19, caused by the new coronavirus SARS-Co V-2, has turned into a worldwide health emergency, needing speedy and precise diagnostic techniques. This abstract provides a thorough evaluation of research works focusing on COVID-19 identification using DenseNet, a cutting-edge convolutional neural network architecture. DenseNet is notable for its innovative design, which fosters feature reuse while relieving the vanishing gradient problem and enhancing network information flow. Researchers have created novel ways for COVID-19 identification using medical imaging, such as chest X-rays and CT scans, by harnessing the capabilities of DenseNet. The analyzed studies demonstrate DenseNet's efficiency in recognizing COVID-19-specific patterns and distinguishing them from other lung diseases. These investigations have shown remarkable accuracy, sensitivity, and precision, exceeding established machine learning approaches and even professional radiologists. This research study also highlights the difficulties and constraints experienced while using DenseNet to identify COVID-19. Issues such as dataset quantity, class imbalance, and model decision-making process interpretability are addressed. Furthermore, future research paths and prospective enhancements, such as multi-modal data integration and the development of explainable AI systems, are investigated. The experimental results indicate that the proposed approach achieves high accuracy, sensitivity, and precision in the identification of COVID - 19. The proposed methodology achieved an accuracy of 89.74%, sensitivity of 87.25 % , and precision of 79.56%, which outperforms the existing state-of-the-art methods. The proposed approach is robust and can effectively differentiate between COVID-19 positive and negative cases, which is essential for early detection and prompt treatment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifelong Scalable Generative System via Online Maximum Mean Discrepancy 39

Lifelong Scalable Generative System via Online Maximum Mean ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Fei Bors, Adrian G. School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of York YorkYO10 5GH United Kingdom

ISBN: (纸本)157735897X

Diffusion-based models have been recently shown to be high-quality data generators. However, their performance severely degrades when training on non-stationary changing data distributions in an online manner, due to the catastrophic forgetting. In this paper, we propose enabling the diffusion model with a novel Dynamic Expansion Memory Unit (DEMU) methodology that adaptively creates new memory buffers, to be added to a memory system, in order to preserve information deemed critical for training the model. Having a selective memory unit is essential for training diffusion networks, which are expensive to train, especially when deployed in resource-constrained environments. A Maximum Mean Discrepancy (MMD) based expansion mechanism, that evaluates probabilistic distances between each of the previously defined memory buffers and the newly given data, and uses them as expansion signals, is employed for ensuring the diversity of information learning. We propose a new model expansion mechanism to automatically add new diffusion models as experts in a mixture system, which enhances the multi-domain image generation performance. Also a novel memory compaction approach is proposed to automatically remove statistically overlapping memory units, through a graph relationship evaluation, preventing the limitless expansion of DEMU. Comprehensive results show that the proposed approach performs better than the state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Buffer storage

来源：评论

学校读者我要写书评

暂无评论

Motorbike Driving Activity Recognition Using Smartphone Motion Sensors

Motorbike Driving Activity Recognition Using Smartphone Moti...

引用

IEEE International Conference on Multi Topic

作者： Aasim Raheel Aamir Arsalan Sadam Hussain Noorani Sheharyar Khan Muhammad Ehatisham-Ul-Haq Zohaib Ali Department of Computer Engineering University of Engineering & Technology Taxila Pakistan Department of Software Engineering Fatima Jinnah Women University Rawalpindi Pakistan Department of Creative Technologies Air University Islamabad Pakistan Department of Computer Science Bahria University Islamabad Pakistan

Motorbike driving activity recognition plays a crucial role in various domains, including rider safety, vehicle diagnostics, and driver behavior analysis. Traditional methods for activity recognition often rely on dedicated sensors or on-board systems, which can be expensive, cumbersome, or limited in terms of availability. In recent years, the widespread use of smartphones with built-in motion sensors has opened up new possibilities for activity recognition in a more cost-effective and accessible manner. This paper presents a novel approach for motorbike driving activity recognition using smartphone motion sensors. Motorcyclist are inquired to take after a predefined way for recording accelerometer and gyroscope data. Twelve factual features are extricated to classify four driving events i.e., right turn, left turn, U-turn, and a straight path. Four machine learning classifiers i.e., Bayes Net, K-nearest neighbor, support vector machine, and random forest is utilized to classify motorbike driving events. The findings indicate that fusing of a gyroscope and accelerometer can significantly improve the detection of bike driving occurrences, achieving a noteworthy precision rate of 92.13%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessing the Linguistic Quality of REST APIs for IoT Applications

arXiv

引用

arXiv 2022年

作者： Palma, Francis Olsson, Tobias Wingkvist, Anna Gonzalez-Huerta, Javier Department of Computer Science and Media Technology Linnaeus University Sweden Department of Software Engineering Blekinge Institute of Technology Sweden

Internet of Things (IoT) is a growing technology that relies on connected 'things' that gather data from peer devices and send data to servers via APIs (Application Programming Interfaces). The design quality of those APIs has a direct impact on their understandability and reusability. This study focuses on the linguistic design quality of REST APIs for IoT applications and assesses their linguistic quality by performing the detection of linguistic patterns and antipatterns in REST APIs for IoT applications. Linguistic antipatterns are considered poor practices in the naming, documentation, and choice of identifiers. In contrast, linguistic patterns represent best practices to APIs design. The linguistic patterns and their corresponding antipatterns are hence contrasting pairs. We propose the SARAv2 (Semantic Analysis of REST APIs version two) approach to perform syntactic and semantic analyses of REST APIs for IoT applications. Based on the SARAv2 approach, we develop the REST-Ling tool and empirically validate the detection results of nine linguistic antipatterns. We analyse 19 REST APIs for IoT applications. Our detection results show that the linguistic antipatterns are prevalent and the REST-Ling tool can detect linguistic patterns and antipatterns in REST APIs for IoT applications with an average accuracy of over 80%. Moreover, the tool performs the detection of linguistic antipatterns on average in the order of seconds, i.e., 8.396 seconds. We found that APIs generally follow good linguistic practices, although the prevalence of poor practices exists. Copyright © 2022, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Algorithm for Prediction of Flood Severity

Application of Deep Learning Algorithm for Prediction of Flo...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： C Jamunadevi N Naveen M Manimaran M Janani Department of Computer Technology PG Kongu Engineering College Erode Department of IT Excel Engineering College Namakkal School of Computing Science and Engineering VIT Bhopal University Bhopal Madhya Pradesh India M.Sc (Software Systems) Kongu Engineering College Erode

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Natural disasters like floods have caused immense harm to lives and resources, underscoring the need for accurate prediction methods to mitigate their impact. Meteorological flood indices such as the standardized precipitation index help identify flood occurrences and severity levels, enabling proactive measures. While past research primarily used statistical methods like Least Square-Support Vector Machine (LS-SVM), these often lack accuracy for long-term forecasts. Advancements in machine learning, particularly artificial neural networks and deep neural networks, offer more accurate predictions over extended periods. Long Short-Term Memory (LSTM) models and Convolutional Neural Networks (CNN) are used to predict flood indices, handling real-time nonlinear data effectively. Benchmarking trials have shown that an LSTM and CNN configuration produced the best predictions, with an accuracy, prediction, MSE, and RMSE of 97.93,0.89, 0.01, and 0.10 respectively.

关键词： Accuracy Weather forecasting Predictive models Surfaces Data models Vectors Floods

来源：评论

学校读者我要写书评

暂无评论

Adaptive watermark generation mechanism based on time series prediction for stream processing

引用

Frontiers of computer Science 2021年第6期15卷 59-73页

作者： Yang SONG Yunchun LI Hailong YANG Jun XU Zerong LUAN Wei LI Sino-German Joint Software Institute Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854China College of Life Sciences and Bioengineering Beijing University of TechnologyBeijing 100083China

The data stream processing framework processes the stream data based on event-time to ensure that the request can be responded to in *** reality,streaming data usually arrives out-of-order due to factors such as network *** data stream processing framework commonly adopts the watermark mechanism to address the data *** is a special kind of data inserted into the data stream with a timestamp,which helps the framework to decide whether the data received is late and thus be *** watermark generation strategies are periodic;they cannot dynamically adjust the watermark distribution to balance the responsiveness and *** paper proposes an adaptive watermark generation mechanism based on the time series prediction model to address the above *** mechanism dynamically adjusts the frequency and timing of watermark distribution using the disordered data ratio and other lateness properties of the data stream to improve the system responsiveness while ensuring acceptable result *** implement the proposed mechanism on top of Flink and evaluate it with realworld *** experiment results show that our mechanism is superior to the existing watermark distribution strategies in terms of both system responsiveness and result accuracy.

关键词： data stream processing watermark time series based prediction dynamic adjustment

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：