检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Fei Lin, Xi Wang, Zhenkun Yao, Shunyu Tong, Xialiang Yuan, Mingxuan Zhang, Qingfu Department of Computer Science City University of Hong Kong Hong Kong School of System Design and Intelligent Manufacturing the Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China Huawei Noah’s Ark Lab Canada

Multiobjective evolutionary algorithms (MOEAs) are major methods for solving multiobjective optimization problems (MOPs). Many MOEAs have been proposed in the past decades, of which the search operators need a carefully handcrafted design with domain knowledge. Recently, some attempts have been made to replace the manually designed operators in MOEAs with learning-based operators (e.g., neural network models). However, much effort is still required for designing and training such models, and the learned operators might not generalize well on new problems. To tackle the above challenges, this work investigates a novel approach that leverages the powerful large language model (LLM) to design MOEA operators. With proper prompt engineering, we successfully let a general LLM serve as a black-box search operator for decomposition-based MOEA (MOEA/D) in a zero-shot manner. In addition, by learning from the LLM behavior, we further design an explicit white-box operator with randomness and propose a new version of decomposition-based MOEA, termed MOEA/D-LO. Experimental studies on different test benchmarks show that our proposed method can achieve competitive performance with widely used MOEAs. It is also promising to see the operator only learned from a few instances can have robust generalization performance on unseen problems with quite different patterns and settings. The results reveal the potential benefits of using pre-trained LLMs in the design of MOEAs. To foster reproducibility and accessibility, the source code is https://***/FeiLiu36/LLM4MOEA. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Room Temperature Detection Using Bioelectric Potential of Plant Data

SSRN

引用

SSRN 2024年

作者： Tahyudin, Imam Rozaq, Hasri Akbar Awal Nambo, Hidetaka Department of Information System Faculty of Computer Science Amikom Purwokerto University Jl. Letjendpol Soemarto Banyumas Purwanegara 53127 Indonesia Graduate School of Informatics Faculty of Computer Science Gazi Üniversitesi Ankara Yenimahalle Turkey Graduate School of NST Division of Electrical Engineering and Computer Science Kanazawa University Kakumamachi Ishikawa Kanazawa920-1192 Japan

Plants are living things that have many secrets in them. One that is very interesting is how plants can communicate with the surrounding environment through the activities of the plants themselves. Then, from this communication activity, plants produce electricity, which we can use to study further the behavior of these plants, commonly known as bioelectric potential. This study has aim to analyze the ability of bioelectric potential of plant to response a room temperature in different condition. This research is analyzed using a deep learning algorithm, namely Long-Short Term Memory (LSTM). The data was recording using a modified amplifier and the output is signal data. The signal obtained is an analog signal which is then converted into a digital signal. The data that has been obtained is then transformed first before being analyzed using the Wavelet Transform method. The algorithm will be evaluated between the baseline and hyperparameter tuning models. The result showed that hyperparameter tuning has the smallest RMSE. Therefore, it is better than baseline model. © 2024, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Effect Analysis of Image Translation by Controlling Size of Dataset and Adjusting Parameters for CycleGAN 3

Effect Analysis of Image Translation by Controlling Size of ...

引用

3rd IEEE International Conference on Communications, Information system and computer engineering, CISCE 2021

作者： Xu, Keang Zhou, Ziyu Wei, Lesi School of Computing and Information System University of Melbourne Wuhan China School of Computer Science and Engineering University of New South Wales Shantou China Faculty of Engineering Computer and Mathematical Sciences University of Adelaide Adelaide Australia

ISBN: (纸本)9780738112152

Image translation can be achieved effectively by CycleGAN. However, it is not clear whether the dataset size and parameter adjustment would influence the performance of CycleGAN. Therefore, this paper uses the different kinds of dataset and different dataset sizes to evaluate the performance of the model. Furthermore, parameters are adjusted in CycleGAN to further evaluate the performance of the CycleGAN-based method for image translation. The experimental results show that with the increases of the size of the dataset, except for some special situations, the loss of the model will decrease when different loss shows different descending amplitude which means small size of dataset would lead to overfitting. In addition, this cycle GAN model is more suitable for the 'horse to zebra' dataset, because this dataset has the least loss. Cycle consistency or its weight, hyper parameters adjusting can achieve the better unpaired image resolution than the original image, which shows this model can do a fairly good translation. Our research is of great significance to explore the best parameter settings and dataset size of image translation optimization based on CycleGAN. © 2021 IEEE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Empowered Human-computer Interaction with Domain Adaptation Network

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xu, Xu Fu, Chong Chen, Junxin Northeastern University School of Computer Science and Engineering Shenyang110004 China Dalian University of Technology China The School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110004 China Dalian University of Technology School of Software Dalian116621 China

Multi-modal emotion recognition plays a vital role in the human-computer interaction (HCI) for consumer electronics. Nowadays, many studies have developed multi-modal fusion algorithms for this ***, two challenging issues remain unsolved, i.e., inefficient multi-modal feature fusion and unclear distance in feature *** this end, we develop a novel framework, namely LAFDA-Net, for cross-subject emotion recognition using EEG and eye movement *** is based on low-rank fusion and domain adaptation *** specifically, the multi-modal signals are input into the feature extraction branch in parallel to generate ***, these features are fused by the low-rank fusion branch, reducing complexity and avoiding ***, the fused features are flattened and sent to the classification branch to determine the emotion *** training, these features are input into the domain adaptive branch to bridge the gap between the source domain and target *** benchmark datasets, i.e., SEED, SEED-IV, and SEED-V, are employed for performance *** results demonstrate that the proposed LAFDA-Net is robust, effective, and has advantages over peer methods. © 1975-2011 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Development the Numerical Method to Solve the Inverse Initial Value Problem for the Thermal Conductivity Equation of Composite Materials

Development the Numerical Method to Solve the Inverse Initia...

引用

2020 Ibn Al-Haitham International Conference for Pure and Applied sciences, IHICPS 2020

作者： Al-Mahdawi, H.K. Department of System Programming School of Electronic Engineering and Computer Science South Ural State University Lenina 76 Chelyabinsk454080 Russia

In this paper, the heat conduction equation for composite materials posed and solved. This problem is known as an inverse initial value problem for the heat conduction equation. In order to solve and formulate this inverse problem, the function spaces must be defined and represented. By studying and solving the direct problem for the heat equation in composite materials, it is possible to determine the function spaces and solve the inverse initial value problem. Scientific methods used: the separation of variables method used to solve the direct problem for the heat equation. It found that method separation of variables does not completely lead to the solution of the inverse initial value problem, since this method leads to a divergent series of solutions and rather massive errors. The heat conduction problem can be formulated as Fredholm integral first kind equations. The discretization algorithm applied to reformulated the problem as linear operator problem as matrix and vectors form. Then, Tikhonov's regularization inversion method has been used to find an approximation solution. Finally, as shown in the numerical example the regularized approximate solutions obtained. © Published under licence by IOP Publishing Ltd.

关键词： Initial value problems

来源：评论

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

引用

International Conference on Software engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Encoder Cross-Shape Transformer Network for Medical Image Segmentation in Internet of Medical Things for Consumer Health

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhao, Yawu Wang, Shudong Zhang, Yulin Ren, Yande Zhang, Yuanyuan Pang, Shanchen the School of Computer Science and Technology China University of Petroleum Shandong Qingdao China the College of Mathematics and System Science Shandong University of Science and Technology Shandong Qingdao China the Department of Medical Imaging Center the Affiliated Hospital of Qingdao University Shandong Qingdao China the School of Information and Control Engineering Qingdao University of Technology Shandong Qingdao China

In emerging consumer healthcare, high-performance and robust medical image segmentation methods are essential for personalized diagnosis and treatment. Thus, early screening of aneurysms reduces the risk of aneurysm rupture and provides therapeutic and preventive measures. However, uncontrollable factors such as uncertainty in the size and location shape of tumors in medical images a significant challenge to medical image segmentation. These factors make extracting high-quality features from aneurysm images difficult, resulting in poor segmentation. Then, we designed a dual encoder cross-shape transform network (DECSTNet) to capture aneurysm feature information. The dual encoder structure can extract aneurysm feature information at different scales, the adaptive dynamic feature fusion module can fuse features at different scales between the encoders, and the cross-shape window transform layer can compute the width and height of the image in parallel for local self-attention, which enhances the interactive capability of the telematic information while realizing the complementarity of the local information. Through extensive experiments, we demonstrate the excellent segmentation performance of DECSTNet on the private and three public datasets. Noteworthy our method has significant segmentation performance and fewer parameters, making it well-suited to be deployed on IoMT diagnostic platforms for medical image segmentation to promote healthy patient consumption. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unit-Level AC Induced Magnetic Behavior in the Low-Frequency Regime: Measurement and Characterization

Unit-Level AC Induced Magnetic Behavior in the Low-Frequency...

引用

2022 ESA Workshop on Aerospace EMC, Aerospace EMC 2022

作者： Spantideas, Sotirios T. Giannopoulos, Anastasios E. Baklezos, Anargyros T. Nikolopoulos, Christos D. Nicoletto, Marco Marziali, Ilario Boschetti, Demis Capsalis, Christos N. National Technical University of Athens School of Electrical and Computer Engineering 15780 Greece Hellenic Mediterranean University Department of Electronic Engineering Crete73133 Greece Thales Alenia Space Italia Domain Exploration and Science: Electrical System and EMC Turin10146 Italy

ISBN: (纸本)9789082684742

In this paper, the measurement and characterization of the unit-level, low-frequency induced magnetic response for purposes of magnetic cleanliness is presented. Firstly, we concretely describe the test measurement procedure, including the configuration of the measurement setup and the specifications required to accurately obtain the weak induced magnetic signature of a unit. Furthermore, the post-processing pipeline of the measured data for denoising purposes is illustrated through measurements of representative spacecraft equipment (RF Switch unit). Finally, the frequency domain characterization of the induced unit magnetization is performed based on dipole fitting modeling and the induced magnetization tensor is calculated as a linear combination for different orientations of the applied magnetic field. © 2022 ESA ESTEC.

关键词： Magnetization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Dimension Measurement system for Industrial Part Inspection

Deep Learning-Based Dimension Measurement System for Industr...

引用

2024 China Automation Congress, CAC 2024

作者： Li, Xiao-Di Fan, Xing-Rong Zhang, Xian-Ming Zhang, Han-Zhi Huang, Chun-Jie Xu, Cheng Chongqing Engineering Laboratory for Detection Control and Integrated System School of Artificial Intelligence Chongqing Technology and Business University Chongqing China Engineering Research Centre for Waste Oil Recovery Technology and Equipment Ministry of Education Chongqing Key Laboratory Chongqing Technology and Business University Chongqing China School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing China Chongqing Intelligent Supply Chain Engineering & Technology Research Center Chongqing Jiaotong University Chongqing China Chongqing Aerospace Bashan Motorcycle Manufacturing Co. Ltd. Chongqing China

ISBN: (纸本)9798350368604

This paper develops a deep learning-based system for the dimension measurement of industrial parts. The system employs a general self-supervised image segmentation network to perform dichotomous image segmentation (DIS) on the parts, effectively extracting binary images of the target components from complex backgrounds without requiring preprocessing steps such as filtering or denoising. Following segmentation, contour detection, and dimension measurement are executed. The system utilizes a CMOS area scan camera and was tested on a computer equipped with a GTX1050 graphics card. The tests, conducted on two typical thrust ball bearing components (i.e., the ball retainer and the shaft ring) ü yielded ten measurements per part. Comparison with a vernier caliper as the reference standard reveals that under normal operating conditions, the maximum standard deviation is 0.007 mm and the maximum absolute error is 0.017 mm. © 2024 IEEE.

关键词： Ball bearings

来源：评论

学校读者我要写书评

暂无评论

3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations

arXiv

引用

arXiv 2024年

作者： Wu, Xuecheng Xue, Junxiao Fu, Liangyu Nie, Jiayu Huang, Danlei Yin, Xinyi School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Research Center for Space Computing System Zhejiang Lab Hangzhou China School of Software Northwestern Polytechnical University Xi’an China School of Cyber Science and Engineering Zhengzhou University Zhengzhou China

Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention mechanisms to construct a more discriminative YOLO head which is enriched with more useful intermediate features. To tackle this gap, this work aims to leverage multiple attention mechanisms to hierarchically enhance the triple discriminative awareness of the YOLO detection head and complementarily learn the coordinated intermediate representations, resulting in a new series detectors denoted 3A-YOLO. Specifically, we first propose a new head denoted TDA-YOLO Module, which unifiedly enhance the representations learning of scale-awareness, spatial-awareness, and task-awareness. Secondly, we steer the intermediate features to coordinately learn the inter-channel relationships and precise positional information. Finally, we perform neck network improvements followed by introducing various tricks to boost the adaptability of 3A-YOLO. Extensive experiments across COCO and VOC benchmarks indicate the effectiveness of our detectors. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

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：