检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

ISBN: (纸本)157735897X

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Goldilocks Framework: Towards Selecting the Optimal Approach to Conducting AI Projects 22

The Goldilocks Framework: Towards Selecting the Optimal Appr...

引用

1st International Conference on AI engineering - Software engineering for AI, CAIN 2022

作者： Dzhusupova, Rimman Bosch, Jan Olsson, Helena Holmstrom Control & Safety Systems McDermott Dept. of Electrical & Instrumentation The Hague Netherlands Chalmers University of Technology Department of Computer Science and Engineering Gothenburg Sweden Malmö University Department of Computer Science and Media Technology Malmö Sweden

ISBN: (纸本)9781450392754

Artificial intelligence is increasingly becoming important to businesses since many companies have realized the benefits of applying Machine Learning (ML) and Deep Learning (DL) into their operations. Nevertheless, ML/DL technologies' industrial development and deployment examples are still rare and generally confined within a small cluster of large international companies who are struggling to apply ML more broadly and deploy their use cases at a large scale. Meanwhile, current AI market has started offering various solutions and services. Thus, organizations must understand how to acquire AI technology based on their business strategy and available resources. This paper discusses the industrial experience of developing and deploying ML/DL use cases to support organizations in their transformation towards AI. We identify how various factors, like cost, schedule, and intellectual property, can be affected by the choice of approach towards ML/DL project development and deployment within large international engineering corporations. As a research result, we present a framework that covers the trade-offs between those various factors and can support engineering companies to choose the best approach based on their long-term business strategies and, therefore, would help to accomplish their ML/DL project deployment successfully. © 2022 ACM.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Biomass Fuel Classification from Agricultural Residues Using Machine Learning

Biomass Fuel Classification from Agricultural Residues Using...

引用

IEEE Region 10 Humanitarian Technology Conference (R10-HTC)

作者： Nikhil Pachauri Himanshu Gupta Om Prakash Verma Sushil Kumar Singh Deepak Verma Ravikumar RN Department of Mechatronics Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Jalandhar India Department of Computer Engineering of Computer Engineering Marwadi University Rajkot Gujarat India Dept. of Computer Engineering Marwadi University Rajkot Gujarat India

ISBN: (数字)9798350340204

ISBN: (纸本)9798350340211

This work incorporates an adaptive learning-based boosting (ADboost) ML classifier to classify four types of fuel: agricultural residue, coals, wood, and produced biomass. Further, the ADboost’s hyperparameters, such as learning rate, maximum number of splits, and minimum leaf size are adjusted using teaching learning-based optimization (TLBO), resulting in TADboost. The performance of TADboost is compared against various popular ML (NN, BAG, NB, and SVM) models. Simulated result reveals that the suggested classifiers outperform other compared ML classifiers for fuel classification with the classification accuracy, precision, recall, F1-score, and kappa as 0.9659, 0.9671, 0.9449, 0.9558, and 0.9482, respectively.

关键词： Training Support vector machines Accuracy Biological system modeling Simulation Coal Linear programming Biomass Security Optimization

来源：评论

学校读者我要写书评

暂无评论

Federated-Boosting: A Distributed and Dynamic Boosting-Powered Cyber-Attack Detection Scheme for Security and Privacy of Consumer IoT

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Khan, Izhar Ahmed Pi, Dechang Kamal, Shaharyar Alsuhaibani, Mohammed Alshammari, Bandar Mzel Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China University of Chile Department of Electrical Engineering Chile Qassim University College of Computer Department of Computer Science Buraydah Saudi Arabia Technology Control Company Riyadh Saudi Arabia

Consumer Internet of Things (CIoT) is an emerging technology that took the traditional consumer electronics to next level with smarter devices and higher connectivity. However, the rapid boom of this technology has captured a great deal of hacker's attention in the past decade. Due to resource restricted nature of CIoT devices and limited computational abilities, security professionals are unable to strengthen the security and privacy measures. Since the existing security methods suffers from data imbalance and overfitting issues, this paper proposes a distributed and dynamic weighted boosting method named Federated-Boosting for the accurate and timely detection of cyber-Attacks in CIoT. Specifically, a weighting strategy is designed to overcome the data imbalance issue by dynamically adjusting the weights of weaker class samples. Additionally, a regularized loss function is designed that helps in controlling the overfitting of the model and provide enhance performance and generalization. Finally, a time-based and performance-based dynamic aggregation scheme is designed using distributed training model that keeps the privacy of the CIoT devices intact to the local server. Extensive experiments on two real-world datasets validates the superior performance of Federated-Boosting model against state-of-The-Art detection models. © 1975-2011 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Texture Analysis of Breast US Images Using Morphological Transforms, Hausdorff Dimension and Bagging Ensemble Method 32

Texture Analysis of Breast US Images Using Morphological Tra...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Tabacaru, Gigi Moldovanu, Simona Barbu, Marian 'Dunarea de Jos' University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Automatic Control and Electrical Engineering Romania 'Dunarea de Jos' University of Galati Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Romania Dunarea de Jos University of Galati The Modelling & Simulation Laboratory Galati800008 Romania

ISBN: (纸本)9798350395440

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer. © 2024 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Trajectory control and Fair Communications for Multi-UAV Networks: A Federated Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE Transactions on Wireless Communications 2025年

作者： Tarekegn, Getaneh Berie Tesfaw, Belayneh Abebe Juang, Rong-Terng Saha, Dola Tarekegn, Robel Berie Lin, Hsin-Piao Tai, Li-Chia Nycu Department of Electrical and Computer Engineering 1001 University Road Hsinchu300 Taiwan Nycu Institute of Electrical and Control Engineering 1001 University Road Hsinchu300 Taiwan National Taipei University of Technology Department of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Institute of Aerospace and System Engineering Taipei10608 Taiwan University at Albany Suny Department of Electrical and Computer Engineering AlbanyNY12222 United States

Due to their highly flexible deployment and agility features, unmanned aerial vehicles (UAVs) serving as aerial base stations are increasingly being used in challenging environments, including emergency communication, traffic offloading, and failures of existing communications infrastructure. A reliable and effective communication service requires 3D deployment and autonomous UAV trajectory optimization in each time slot. While most prior approaches focus on trajectory design that maximizes communication coverage or network throughput without considering fairness as well as computation time. This paper presents a multi-UAV trajectory control and fair communication (TCFC) scheme that maximizes ground user data rate and communication coverage while ensuring service fairness in a UAV-aided wireless communications system. The proposed TCFC scheme employs a two-stage learning approach. Firstly, it develops a gated recurrent unit-based link quality estimation model to assess each user's link quality over time. Then, a federated multi-agent deep reinforcement learning (FedMADRL) algorithm is utilized to continuously adjust the trajectory of the UAVs, optimizing communication performance. We evaluated our proposed system using real channel measurement data, i.e., amplitude and phase signal information. The results show that the proposed TCFC scheme reduces computation time by 26.91% and provides comparable network performance with the baseline methods while improving DRL agents' privacy. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Some Use Cases of Security Constrained Economic Dispatch Problem for Outage Work Planning Collaboration System 13

Some Use Cases of Security Constrained Economic Dispatch Pro...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Toyoshima, Ichiro Tatekoji, Takashi Mizutani, Ryota Sato, Hiroaki Toshiba Energy Systems & Solutions Corporation Infrastructure Service Development & Design Department Tokyo Japan Toshiba Energy Systems & Solutions Corporation Power Grid System Solutions Engineering Depattment Kawasaki Japan Toshiba Energy Systems & Solutions Corporation Power Control Computer Systems Department Tokyo Japan

ISBN: (纸本)9798350355079

Outage work planning has been essential to maintain the power grid system. For the operators, the planning is troublesome. It is caused by too complex process. The past few years, we have been developing Outage Work planning Collaboration System (OWCS) with some mathematical optimization techniques. Especially, Security Constrained Economic Dispatch(SCED) is extened in some ways to handle various power grid situations. © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

RISense: 6G-Enhanced Human Activity Recognition System with RIS and Deep LDA 25

RISense: 6G-Enhanced Human Activity Recognition System with ...

引用

25th IEEE International Conference on Mobile Data Management, MDM 2024

作者： Rizk, Hamada Hashima, Sherief Osaka University Graduate School of Information Science and Technology Suita565-0871 Japan Tanta University Computer and Control Engineering Department Tanta31733 Egypt RIKEN-AIP Computational Learning Theory Team Fukuoka819-0395 Japan Egyptian Atomic Energy Authority Engineering Dept Cairo13759 Egypt

ISBN: (纸本)9798350374551

Human Activity Recognition (HAR) systems hold great potential in aiding disabled and elderly individuals to live independently. Various approaches have been suggested for identifying human activities, including sensors, cameras, wearables, and contactless microwave sensing. This latter method is gaining significant attention due to its ability to address privacy concerns arising from cameras and alleviate discomfort caused by wearables. However, current microwave sensing techniques have a key limitation, requiring controlled and ideal conditions to achieve accurate activity detection. In this paper, we propose RISense, a deep learning-aided system for HAR using Re-configurable Intelligent Surface (RIS). RISense introduces novel modules designed to generate a human activity representational space that ensures separability between activity classes, even in the presence of noisy and distorted Channel State Information (CSI) measurements. These representations are then fed into a Recurrent Neural Network (RNN), which learns the sequential changes in features to accurately estimate the user activity. The evaluation of RISense across two realistic settings, encompassing both non-line-of-sight and multi-floor scenarios, showcases its efficacy. Specifically, RISense achieves an activity recognition accuracy of 98.7%. This performance overcomes the accuracy of state-of-the-art systems by over 15%. These findings highlight the superior efficacy of the proposed methodologies, including integrating RIS and advanced learning techniques. © 2024 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Enhancing Transformer Tracking Using NF-ResNet and ResNeXT Backbones 1

引用

1st International Conference on Machine Intelligence for Research and Innovations, MAiTRI 2023

作者： Verma, Sourabh Singla, Rajesh Verma, Om Prakash Sharma, Richa Gupta, Himanshu Sharma, Tarun Muthanna, Ammar Department of Instrumentation and Control Engineering Dr. B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India Department of Computer Science—Internet of Things ABES Institute of Technology Ghaziabad India University Meerut India Saint-Petersburg State University of Telecommunications Saint Petersburg Russia

ISBN: (数字)9789819981359

ISBN: (纸本)9789819981342

Residual networks play a foremost role in the domain of tracking, specifically in the extraction of features. The residual networks are using a simple technique of skipping connections to overcome the problem of vanishing gradient. Also, it is using batch normalization after each layer of convolution to accelerate the training by reducing the dependency over the parameters. Though, we have tried to solve these issues by introducing ResNeXt and NF-ResNet one by one into the TransT tracker as feature extractors in the place of ResNet. Finally, we present a ResNeXt-based TransT tracker (named as TransT_NeXt) and NF-Net-based TransT tracker (named as TransT_NFNet). We have evaluated proposed trackers on three large-scale benchmark datasets and four small-scale benchmark datasets but unfortunately, our trackers haven’t performed well. At last, we have discussed about the future work on the basis of this study. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Perimeter Defense Using a Turret with Finite Range and Startup Time

Perimeter Defense Using a Turret with Finite Range and Start...

引用

American control Conference (ACC)

作者： Shivam Bajaj Shaunak D. Bopardikar Alexander Von Moll Eric Torng David W. Casbeer Department of Electrical and Computer Engineering Michigan State University Control Science Center Air Force Research Laboratory Department of Computer Science and Engineering Michigan State University

We consider a perimeter defense problem in a planar conical environment comprising a turret that has a finite range and non-zero startup time. The turret seeks to defend a concentric perimeter against N ≥ 2 intruders. Upon release, each intruder moves radially towards the perimeter with a fixed speed. To capture an intruder, the turret's angle must be aligned with that of the intruder's angle and must spend a specified startup time at that orientation. We address offline and online versions of this optimization problem. Specifically, in the offline version, we establish that in general parameter regimes, this problem is equivalent to solving a Travelling Repairperson Problem with Time Windows (TRP-TW). We then identify specific parameter regimes in which there is a polynomial time algorithm that maximizes the number of intruders captured. In the online version, we present a competitive analysis technique in which we establish a fundamental guarantee on the existence of at best (N – 1)-competitive algorithms. We also design two online algorithms that are provably 1 and 2-competitive in specific parameter regimes.

关键词：

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：