检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zhiqiang Chen Hongbo Chen Yuhua Qi Shipeng Zhong Dapeng Feng Jin Wu Weisong Wen Ming Liu School of Systems Science and Engineering Sun Yatsen University Guangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Aeronautical and Aviation Engineering Hong Kong Polytechnic University Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

LiDAR-based localization is valuable for applications like mining surveys and underground facility maintenance. However, existing methods can struggle when dealing with uninformative geometric structures in challenging scenarios. This paper presents RELEAD, a LiDAR-centric solution designed to address scan-matching degradation. Our method enables degeneracy-free point cloud registration by solving constrained ESIKF updates in the front end and incorporates multisensor constraints, even when dealing with outlier measurements, through graph optimization based on Graduated Non-Convexity (GNC). Additionally, we propose a robust Incremental Fixed Lag Smoother (rIFL) for efficient GNC-based optimization. RELEAD has undergone extensive evaluation in degenerate scenarios and has outperformed existing state-of-the-art LiDAR-Inertial odometry and LiDAR-Visual-Inertial odometry methods.

关键词： Degradation Location awareness Surveys Laser radar Current measurement Pose estimation Sensors

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Trained Stacking Model for Univariate Time Series Forecasting 25th

Two-Stage Trained Stacking Model for Univariate Time Series...

引用

25th International Conference on Web Information systems engineering, WISE 2024

作者： Wang, Haoyu Wang, Bin Liu, Sitong Yang, Xiaochun Wang, Jiahe Yu, Shiyu School of Computer Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China Ministry of Education Shenyang China Finance College NanKai University Tianjin China Department of Family Medicine Sheng Jing Hospital China Medical University Liaoning Shenyang China China Mobile Group Liaoning Company Limited Shenyang China

ISBN: (纸本)9789819605781

The stacking ensemble model is widely used in the forecasting of univariate time series data. It works by combining the predictions of multiple models. It has been applied across fields such as economics, energy, and healthcare, where data often fluctuates frequently and comes in diverse forms. First, a set of base models is trained on the dataset to make initial predictions. These predictions are then used as input features for the training of a meta-model. Finally, in subsequent forecasts, the trained meta-model merges the new predictions of the base models to provide a more accurate forecast. However, most stacking models directly use all available data to train the base models once and stack their predictions to train the meta-model. This may lead to overfitting because they train the base models on the entire dataset, including the part of the actual labels for training the meta-model, potentially causing target leakage for the meta-model. To address this issue, we propose a two-stage trained stacking model. The input data is divided into training and label parts. In the first stage, the base models are trained on the training part, and the predictions of the base models are combined with the label part to train the meta-model. In the second stage, the base models are retrained with all input data, and the meta-model trained in the first stage is used for the final prediction. This approach helps mitigate overfitting in the prediction phase caused by target leakage during the training process. We test our model on three different types of datasets. Experimental results show that our stacking ensemble model outperforms the individual base models on all datasets in terms of MAE and MSE, demonstrating not only good generalizability but also improved performance across various scenarios. Additionally, we compared our two-stage trained stacking model with a basic stacking ensemble model framework. The results suggest our model provides more accurate predictions for

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Framework for Intra-Class Imbalance Medical Image Segmentation

Dual-Path Framework for Intra-Class Imbalance Medical Image ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Xiaolu Lin Bing Yang Yfan Zhou Risa Higashita Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Tomey Corporation Japan

The intra-class imbalance usually occurs in medical images due to external influences, such as noise interference and changes in camera angle. It leads to complex textures and varied appearances within the target object region and makes segmentation task challenging. To deal with this kind of problem, we proposed a dual-path framework in this paper. Considering that the object consists of two subclasses (majority- and minority-subclass), a deep learning model is adopted to separate them. We constructed two weighted maps for the dual paths, related to majority- and minority-subclass respectively. A fusion module was designed to generate the final output according to the results from the dual paths. The experimental results on two datasets shew our approach's validity and superiority for medical image segmentation compared with other competing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GiantScope: A simulation microscopy for middle school biological experiment education

GiantScope: A simulation microscopy for middle school biolog...

引用

作者： Zhang, Haoyang Zhang, Mingmin Pan, Zhigeng Cao, Mingliang Li, Yongheng Zhong, Yong Chen, Ganglin Liu, Xin Foshan University Foshan China College of Computer Science and Technology Zhejiang University Hangzhou China Virtual Reality and Intelligent Systems Research Institute Nanjing University of Information Science and Technology Nanjing China School of Computer and Information Engineering Guangdong Polytechinc of Industry and Commerce Guangzhou China

We present a simulation microscope device called GiantScope, which combines virtual microscope, cloud computing, and embedded technologies. Users can complete most of the microscope-based experiments in biology courses by operating our device, while learning the operating skills of microscopes at the same time. Our device supports most of the operation functions of optical microscopes, including quasifocus screw adjustment, slide movement recognition and so on, and also has auxiliary enhancement functions including manual measurement, annotation and so on. In addition, we have built a cloud-based digital slide database, which enables users to select experimental observations through digital slides, including static cell specimens or dynamic cell activities. After user study, we found that using GiantScope for biological experiments has better learning efficiency and user experience than traditional microscopes. © 2022 John Wiley & Sons, Ltd.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Deduplicating and Ranking Solution Programs for Suggesting Reference Solutions

arXiv

引用

arXiv 2023年

作者： Shirafuji, Atsushi Watanobe, Yutaka Graduate Department of Computer and Information Systems University of Aizu Aizu-Wakamatsu Japan Department of Computer Science and Engineering University of Aizu Aizu-Wakamatsu Japan

Referring to solution programs written by other users is helpful for learners in programming education. However, current online judge systems just list all solution programs submitted by users for references, and the programs are sorted based on the submission date and time, execution time, or user rating, ignoring to what extent the programs can be helpful to be referenced. In addition, users struggle to refer to a variety of solution approaches since there are too many duplicated and near-duplicated programs. To motivate learners to refer to various solutions to learn better solution approaches, in this paper, we propose an approach to deduplicate and rank common solution programs in each programming problem. Inspired by the nature that the many-duplicated program adopts a more common approach and can be a general reference, we remove the near-duplicated solution programs and rank the unique programs based on the duplicate count. The experiments on the solution programs submitted to a real-world online judge system demonstrate that the number of programs is reduced by 60.20%, whereas the baseline only reduces by 29.59% after the deduplication, meaning that users only need to refer to 39.80% of programs on average. Furthermore, our analysis shows that top-10 ranked programs cover 29.95% of programs on average, indicating that users can grasp 29.95% of solution approaches by referring to only 10 programs. The proposed approach shows the potential of reducing the learners’ burden of referring to too many solutions and motivating them to learn a variety of solution approaches. © 2023, CC BY.

关键词： Online systems

来源：评论

学校读者我要写书评

暂无评论

An Improved Flocking Model for UAVs in Constrained Environments 8

An Improved Flocking Model for UAVs in Constrained Environme...

引用

8th International Conference on Big Data and Information Analytics, BigDIA 2022

作者： Zhang, Xiaoyu Yuan, Yutong Zhang, Fan College of Intelligence Science and Technology National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China College of Computer Science National University of Defense Technology Changsha China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

The research of UAV flocking is getting more and more popular these days. Some flocking model is established on the commonly used environment and complex environment with narrow paths and broad barriers will reduce the performance of the model. In this paper, we design a complex environment which includes narrow paths and broad barriers. We propose a mission that UAVs move at the start point and move into the expected area after crossing barriers and walls. We propose a evaluation function which contains the mission execution time and collisions. Then we conducted a simulation experiment, using a single-objective genetic algorithm to optimize the parameters of the model. We proof that the performance of the optimized model is superior to the performance of the original model and we get better mission execution time and the number of collisions. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Heuristic Assisted Memetic Algorithm for Efficient Inter-Satellite Link Scheduling in the BeiDou Navigation Satellite System

引用

IEEE/CAA Journal of Automatica Sinica 2021年第11期8卷 1800-1816页

作者： Yonghao Du Ling Wang Lining Xing Jungang Yan Mengsi Cai College of Systems Engineering National University of Defense TechnologyChangsha 410073China Leiden Institute of Advanced Computer Science Leiden UniversityLeiden 2332 CAThe Netherlands Department of Automation Tsinghua UniversityBeijing 100083China

Inter-satellite link(ISL)scheduling is required by the BeiDou Navigation Satellite System(BDS)to guarantee the system ranging and communication *** the BDS,a great number of ISL scheduling instances must be addressed every day,which will certainly spend a lot of time via normal metaheuristics and hardly meet the quick-response requirements that often occur in real-world *** address the dual requirements of normal and quick-response ISL schedulings,a data-driven heuristic assisted memetic algorithm(DHMA)is proposed in this paper,which includes a high-performance memetic algorithm(MA)and a data-driven *** normal situations,the high-performance MA that hybridizes parallelism,competition,and evolution strategies is performed for high-quality ISL scheduling solutions over *** in quick-response situations,the data-driven heuristic is performed to quickly schedule high-probability ISLs according to a prediction model,which is trained from the high-quality MA *** main idea of the DHMA is to address normal and quick-response schedulings separately,while high-quality normal scheduling data are trained for quick-response *** addition,this paper also presents an easy-to-understand ISL scheduling model and its NP-completeness.A seven-day experimental study with 10080 one-minute ISL scheduling instances shows the efficient performance of the DHMA in addressing the ISL scheduling in normal(in 84 hours)and quick-response(in 0.62 hour)situations,which can well meet the dual scheduling requirements in real-world BDS applications.

关键词： BeiDou Navigation Satellite System(BDS) data-driven heuristic inter-satellite link(ISL)scheduling memetic algorithm metaheuristic quick-response

来源：评论

学校读者我要写书评

暂无评论

Optimizing Random Forest Classifier for Detection of Alzheimer's Using OASIS

Optimizing Random Forest Classifier for Detection of Alzheim...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Karri Sai Sanjana Reddy Kishor Kumar Reddy C. Srinath Doss Kari Lippert Dept. of Computer Science and Engineering Stanley College of Engineering and Technology for Women Hyderabad India Faculty of Engineering and Technology Botho University Botswana Dept. of Systems Engineering University of South Alabama Alabama USA

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

Alzheimer's disease (AD) is a progressive brain disorder impacting behavior, memory, and cognition, with over a million cases reported annually in India. The risk significantly increases beyond age 65. Early diagnosis and treatment can result in better recovery. We propose a predictive model using the Random Forest algorithm and the OASIS dataset for early AD diagnosis, leveraging MRI data, clinical notes, genetic markers, and cognitive test results. Our model was evaluated against several others, including Decision Tree, AdaBoost, SVM, and Logistic Regression. With a 97.3% accuracy and a 2.7% error rate, our Random Forest Classifier o utperformed t he others, demonstrating superior predictive power for early AD diagnosis and potentially improving patient care.

关键词： Training Accuracy Transfer learning Predictive models Prediction algorithms Genetics Classification algorithms Alzheimer's disease Random forests Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Automatic 3D Printer Anomaly Detection during the Printing Process 3

Deep Learning-based Automatic 3D Printer Anomaly Detection d...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Lalitha, T. Anushkannan, N.K Shreepad, Sarange Sasireka, S. Anandaram, Harishchander Razia, Shaik Vellore Institute of Technology Department of Computer Science and Engineering Tamil Nadu Vellore632014 India Kathir College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore641062 India Ajeenkya Dy Patil School of Engineering Department of Mechanical Maharashtra Pune412105 India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Tamil Nadu Coimbatore641202 India Amrita VishwaVidyapeetham Centre for Excellence in Computational Engineering and Networking Tamil Nadu Coimbatore641112 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522302 India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

3D printing is a technology which is expected to be one of the most used technologies in the upcoming time. This technology allows to print out products that are designed using 3D modeling software. Though this is an effective technology, it also has its disadvantages. The disadvantages include anomalies. Anomaly is a defect that is often found when the printer finishes the printing process. Thus, it cannot be rectified when found during the process. To resolve this issue, this study aims in developing a deep learning model using the UNet algorithm. A dataset of pictures of various possible anomalies is gathered from Kaggle. The Kaggle data is then preprocessed using three different methods. The images are initially applied using the target format. The images are then multiplied and shrunk to keep the balance. The UNet method is employed to create a deep learning model. The preprocessed dataset is then used to train the model. To guarantee improved performance, the trained model is subsequently put to the test to assess the model's final accuracy and loss. In all three instances, the model's output is determined to be satisfactory. The model produced an accuracy of 98% during the testing and produced a loss value of 0.54%. This loss value is so small that it can be neglected. The model developed is found to be one of the best algorithms that can be used in anomaly detection. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Deep Network for Semantic Segmentation of Building in Very High Resolution Imagery

Multi-Task Deep Network for Semantic Segmentation of Buildin...

引用

2021 International Conference of Technology, science and Administration, ICTSA 2021

作者： Moghalles, Khaled Li, Heng-Chao Al-Huda, Zaid Hezzam, Essa Abdullah Southwest Jiaotong University School of Computer Science and Technology Chengdu China Taibah University College of Computer Science and Engineering Department of Information Systems Medina Saudi Arabia

ISBN: (纸本)9781665428620

Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. The automatic generation of buildings from satellite images presents a considerable challenge due to the complexity of building shapes. Compared with the traditional building extraction approaches, deep learning networks have shown outstanding performance in this task by using both high-level and low-level feature maps. Recently, many deep networks derived from U-Net has been extensively used in various buildings segmentation tasks. However, in most of the cases, U-net produce coarse and non-smooth segmentations with lots of discontinuities. To improve and refine the performance of U-Net network, we propose a deep end-to-end network, which use a single encoder and two parallel decoders along with performing the mask predictions also perform distance map estimation. The distance map aid in ensuring smoothness in the segmentation predictions. We also propose a new joint loss function for the proposed architecture. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only (RGB) images demonstrated that the proposed framework can significantly improve the quality of building segmentation. © 2021 IEEE.

关键词： Feature extraction

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：