检索结果-内蒙古大学图书馆

7th International Conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Shen, Jiachen Wang, Wenxuan Chen, Chen Jiao, Jianbo Liu, Jing Zhang, Yan Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States School of Computer Science University of Birmingham United Kingdom Institute of Automation Chinese Academy of Sciences China

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs. Thus, it is of increasing importance to fine-tune pre-trained models for medical volumetric segmentation tasks in a both effective and parameter-efficient manner. In this paper, we introduce a new framework named Med-Tuning to realize parameter-efficient tuning (PET) for medical volumetric segmentation task and an efficient plug-and-play module named Med-Adapter for task-specific feature extraction. With a small number of tuned parameters, our framework enhances the 2D baselines’s precision on segmentation tasks, which are pre-trained on natural images. Extensive experiments on three benchmark datasets (CT and MRI modalities) show that our method achieves better results than previous PET methods on volumetric segmentation tasks. Compared to full FT, Med-Tuning reduces the fine-tuned model parameters by up to 4×, with even better segmentation performance. Our project webpage is at https://***/Med-Tuning/. © 2024 CC-BY 4.0, J. Shen, W. Wang, C. Chen, J. Jiao, J. Liu, Y. Zhang, S. Song & J. Li.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Enhancing Bird Migration Studies: Detecting Birdsong in Audio Files Using Convolutional Neural Networks

Enhancing Bird Migration Studies: Detecting Birdsong in Audi...

引用

作者： Honsor, Oksana Gonsor, Yuriy Institute of Computer Technologies Automation and Metrology Lviv Polytechnic National University Lviv79013 Ukraine Institute of Computer Science and Information Technology Lviv Polytechnic National University Lviv79013 Ukraine

Monitoring climate threats and global environmental changes is a crucial issue worldwide. To achieve this, it is important to continuously study these changes using non-standard approaches. One such approach is studying bird migration. It is crucial for analyzing environmental factors that cover large areas of land, such as temperature, air pollution, and water pollution. This article presents a machine-learning model that accurately identifies birdsong in audio files to study bird migration in specific areas. This model uses a convolutional neural network to classify audio files based on images of their spectrograms. The study involves collecting and analyzing audio files that can be used to identify characteristics according to which the sound in the file will be identified as bird sound. The study investigated the effectiveness of using STFT and Mel-spectrograms in a convolutional neural network to classify files based on the presence of bird sounds. The model trained on Mel spectrograms achieved an accuracy of 80%, which is 17% higher than the model trained on STFT spectrograms. This accuracy value is completely sufficient to claim the presence of bird sounds in the audio file. Particular attention is given to the efficiency and accuracy of the CNN model because these indicators enable the comparison and selection of the best classifier for a given file type and model. Although the classification accuracy of the chosen method was lower than expected when building the classification model, the model can predict an audio file in less than 0,5 s, which is a significant achievement. The obtained results may aid in the development of systems for monitoring bird migration across vast territories. To enhance the technique, multiple sets of audio files can be utilized to classify the presence of birds in the environment, improving the accuracy of the method and model. However, the simultaneous complex processing of numerous audio files may reduce processing speed. This

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Fully Sparse Detector with Cascade Heads for LiDAR-based 3D Object Detection 13

A Fully Sparse Detector with Cascade Heads for LiDAR-based 3...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Chen, Junnan Zhang, Gang Hu, Xiaolin Zeng, Zhigang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science and Technology Institute for AI BNRist THU-Bosch JCML Center Tsinghua Universigy Beijing China

ISBN: (纸本)9798331516147

LiDAR-based 3D object detection is a critical component of perception systems in autonomous driving. Existing detectors typically rely on dense feature maps for 3D object prediction. However, as the perception range expands, the computational overhead associated with dense feature maps increases quadratically, creating significant challenges for scaling to long-range detection scenarios. To address this issue, fully sparse detectors have recently been proposed, but they often suffer from suboptimal performance or excessively complex architectures. In this paper, we present CHNet, a fully sparse detector designed to overcome these limitations by introducing a cascade head module, which consists of two sequential heads. By generating coarse object predictions, creating new feature points based on centers of the predicted objects, and aggregating features of the entire object to these new center points, CHNet enhances the qualities of object feature representations, achieving higher detection performance. Notably, CHNet effectively addresses the center feature missing problem in LiDAR-based 3D object detection by adding at most a hundred new feature points, offering a potential avenue for future research. On the widely used Waymo Open and Argoverse2 datasets, CHNet achieves impressive results without any additional embellishments. © 2025 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Unloading method in coordinated harvesting

引用

International Journal of Agricultural and Biological Engineering 2025年第2期18卷 45-54页

作者： Xiaoxiong Wang Zhihong Man Zhuo Wang Xiaoping Bai Jian Wang Zhikang Ge Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110016China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China School of Software and Electrical Engineering Swinburne University of TechnologyMelbourneVIC3122Australia

In this study,a novel unloading method was developed for the operation of the unloading spout during the loading process in a master-slave automatic harvesting *** demonstrated that uniform and full loading in the grain tank can be achieved by uninterrupted unloading with the motion of the unloading ***,the overflow algorithm is proposed to divide the loading process into multiple loading *** each round,a specific loading area and target loading height are assigned to achieve better ***,complete coverage path planning and transfer path planning algorithms are developed to guide the motion of the unloading spout during different loading *** the motion of the unloading spout,loading can be carried out accurately to maximize the capacity utilization of the grain tank,which can reduce the round-trip frequency of the transport vehicle and improve the energy and time efficiency of the harvesting *** results are provided to validate the excellent performance of the presented unloading method.

关键词： coordinated harvesting loading uniformity overflow algorithm path planning

来源：评论

学校读者我要写书评

暂无评论

Sample Efficient Reinforcement Learning Using Graph-Based Memory Reconstruction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 751-762页

作者： Kang, Yongxin Zhao, Enmin Zang, Yifan Li, Lijuan Li, Kai Tao, Pin Xing, Junliang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

Reinforcement learning (RL) algorithms typically require orders of magnitude more interactions than humans to learn effective policies. Research on memory in neuroscience suggests that humans' learning efficiency benefits from associating their experiences and reconstructing potential events. Inspired by this finding, we introduce a human brainlike memory structure for agents and build a general learning framework based on this structure to improve the RL sampling efficiency. Since this framework is similar to the memory reconstruction process in psychology, we name the newly proposed RL framework as graph-based memory reconstruction (GBMR). In particular, GBMR first maintains an attribute graph on the agent's memory and then retrieves its critical nodes to build and update potential paths among these nodes. This novel pipeline drives the RL agent to learn faster with its memory-enhanced value functions and reduces interactions with the environment by reconstructing its valuable paths. Extensive experimental analyses and evaluations in the grid maze and some challenging Atari environments demonstrate GBMRs superiority over traditional RL methods. We will release the source code and trained models to facilitate further studies in this research direction. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Collection of Robotics Problems for Benchmarking Evolutionary Computation Methods 26th

A Collection of Robotics Problems for Benchmarking Evoluti...

引用

26th International Conference on Applications of Evolutionary Computation, EvoApplications 2023, held as part of EvoStar 2023

作者： Kůdela, Jakub Juříček, Martin Parák, Roman Institute of Automation and Computer Science Brno University of Technology Technicka 2 Brno621 00 Czech Republic

ISBN: (纸本)9783031302282

The utilization of benchmarking techniques has a crucial role in the development of novel optimization algorithms, and also in performing comparisons between already existing methods. This is especially true in the field of evolutionary computation, where the theoretical performance of the method is difficult to analyze. For these benchmarking purposes, artificial (or synthetic) functions are currently the most widely used ones. In this paper, we present a collection of real-world robotics problems that can be used for benchmarking evolutionary computation methods. The proposed benchmark problems are a combination of inverse kinematics and path planning in robotics that can be parameterized. We conducted an extensive numerical investigation that encompassed solving 200 benchmark problems by seven selected metaheuristic algorithms. The results of this investigation showed that the proposed benchmark problems are quite difficult (multimodal and non-separable) and that they can be successfully used for differentiating and ranking various metaheuristics. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Industrial Control Anomaly Detection Based on Distributed Linear Deep Learning

引用

computers, Materials & Continua 2025年第1期82卷 1129-1150页

作者： Shijie Tang Yong Ding Huiyong Wang School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin541004China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin541004China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic TechnologyGuilin541004China Institute of Cyberspace Technology HKCT Institute for Higher EducationHong Kong999077China School of Mathematics&Computing Science Guilin University of Electronic TechnologyGuilin541004China

As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are *** key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time *** address this issue,we propose an anomaly detection method based on distributed deep *** method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete *** use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation *** method can not only detect abnormal attacks but also locate the sensors that cause *** conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public *** experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.

关键词： Anomaly detection CPS deep learning MLP(multi-layer perceptron)

来源：评论

学校读者我要写书评

暂无评论

Multirange Breathing Rate Estimation With Deep Learning Using FMCW Radar

引用

IEEE Sensors Journal 2025年第11期25卷 20015-20023页

作者： Fusco, Alessandra Lavronenko, Kostiantyn Sakharov, Sviatoslav Hazra, Souvik Servadei, Lorenzo Wille, Robert Technical University of Munich School of Computation Information and Technology Chair for Design Automation Munich80333 Germany Infineon Technologies AG Neubiberg85579 Germany RWTH Aachen University Faculty of Mathematics Computer Science and Natural Sciences Aachen52062 Germany Technical University of Munich Munich80333 Germany

Frequency-modulated continuous wave (FMCW) radar is a promising technology for noninvasive monitoring of vital signs, such as breathing rate (BR). A key challenge lies in selecting the correct range bin corresponding to the human target, particularly in dynamic environments and resource-constrained systems. This article introduces a resource-efficient deep learning (DL) method for multirange BR estimation that significantly enhances accuracy while maintaining low computational and memory requirements, making it suitable for embedded systems. We benchmark our method against two alternative single-bin approaches: energy-based and spatial phase coherency (SPC) range bin selection, both integrated with DL for BR estimation. Performance is evaluated on an experimental dataset comprising recordings from 25 subjects, with 17 used for training and eight for testing. Recordings were conducted under diverse conditions, spanning various distances, angles, sensor mounting heights, and static and dynamic background scenarios, including individuals walking in the background. Our method achieves a root-mean-square error (RMSE) of 1.88 breaths per minute (bpm) and a Spearman correlation coefficient of 0.83, outperforming state-of-the-art methods that typically report higher RMSEs on smaller datasets. With a minimal memory footprint of approximately 25 KB, the proposed approach is well-suited for resource-constrained embedded systems. This advancement underscores the potential of lightweight DL for reliable and accurate noninvasive vital sign monitoring in healthcare applications. © 2001-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping

TreeSwap: Data Augmentation for Machine Translation via Depe...

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Nagy, Attila Lakatos, Dorina Barta, Botond Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Hungary

ISBN: (纸本)9789544520922

Data augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method, which generates new sentences by swapping objects and subjects across bisentences. This is performed simultaneously based on the dependency parse trees of the source and target sentences. We name this method TreeSwap. Our results show that TreeSwap achieves consistent improvements over baseline models in 4 language pairs in both directions on resource-constrained datasets. We also explore domain-specific corpora, but find that our method does not make significant improvements on law, medical and IT data. We report the scores of similar augmentation methods and find that TreeSwap performs comparably. We also analyze the generated sentences qualitatively and find that the augmentation produces a correct translation in most cases. Our code is available on Github1. © 2023 Incoma Ltd. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Water Quality Prediction With Multimodal Low-Rank Fusion and Localized Attention

引用

IEEE Internet of Things Journal 2025年第12期12卷 21158-21169页

作者： Bi, Jing Li, Yibo Yuan, Haitao Wang, Mengyuan Wang, Ziqi Zhang, Jia Zhou, Mengchu Beijing University of Technology College of Computer Science Beijing Laboratory of Smart Environmental Protection Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Beihang University School of Energy and Power Engineering Beijing100191 China Southern Methodist University Department of Computer Science DallasTX75206 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

Water quality prediction methods forecast the short- or long-term trends of its changes, providing proactive advice for preventing and controlling water pollution. Existing water quality prediction methods typically fail to capture water quality’s nonlinear characteristics accurately and only consider historical time series data. However, meteorology and other factors also significantly impact water quality indicators. Therefore, considering only historical data of water quality time series is not feasible. To solve this problem, this work proposes a hybrid water quality prediction model called CMLIP, which integrates convNeXt V2, multimodal bottleneck transformer, low-rank multimodal fusion, iTransformer, and PatchTST. CMLIP inputs water quality time series and meteorological remotely sensed rainfall images into a multimodal fusion module before prediction. Specifically, CMLIP integrates the model of ConvNeXt V2 to extract image features. Its multimodal fusion module combines a multimodal bottleneck transformer and the low-rank multimodal fusion to fuse the time series and images. Furthermore, CMLIP combines iTransformer and PatchTST to form an improved prediction module that realizes the prediction of fused features. Experimental results with real-life water quality time series and remotely sensed rainfall images demonstrate that CMLIP when fusing meteorological data, achieves an average improvement of 17% in water quality forecasting accuracy compared to forecasts using only water quality time series. Moreover, CMLIP outperforms other state-of-the-art algorithms in both data fusion and prediction, with an average enhancement of 6% in fusion effectiveness and an average improvement of 22% in prediction accuracy. © 2014 IEEE.

关键词： Rain

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：