检索结果-内蒙古大学图书馆

Proceedings of the 4th International Conference on Artificial Intelligence and Computer engineering

作者： Junyan Wang Ziyan Lian Feiyang Kang Jinkai Chen School of Internet Anhui University China School of Software Engineering University of Science and Technology of China China School of Advanced Technology University of Science and Technology of China China Department of Network management center China Mobile Communications Group Anhui Co. LTD China

ISBN: (纸本)9798400708831

Wood is an extremely important foundational building material. Rapid and accurate wood species recognition is crucial for the rational application of wood and for preventing economic losses caused by the misidentification of wood species. Current research primarily focuses on image preprocessing and the use of Convolutional Neural Networks (CNNs) for wood species recognition. Most of the existing methods employ non-lightweight CNN models, making it difficult for the models to achieve rapid recognition. Addressing the above issues, this paper introduces a hybrid model that combines Reparameterized CNN and Visual Transformer, which we refer to as RepCFT. We have designed a new module, RepLG, with strong local and global information extraction capabilities. RepCFT, constructed from RepLG, achieves a recognition accuracy of 98.7% without any data augmentation or training strategies, while using only 4.3 million parameters and 0.6 billion Multiply-Accumulate operations (MACs). Its performance is on par with ResNet50 and surpasses some existing lightweight models. At the same time, it achieves a recognition speed of up to 601.46 frames per second, effectively meeting the need for rapid and accurate recognition in wood species recognition tasks. All code and models have been uploaded to https://***/OnlyForWW/RepCFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Profiling and Imaging of RBC Using Coherent Gradient Sensing and Fourier Fringe Analysis

Profiling and Imaging of RBC Using Coherent Gradient Sensing...

引用

International Conference on Computational Mathematics in Nanoelectronics and Astrophysics, CMNA 2018

作者： Dhanotia, Jitendra Bande, Shivangi Bhatia, Vimal Prakash, Shashi Signals and Software Group Discipline of Electrical Engineering Indian Institute of Technology Indore Indore453552 India Photonics Laboratory Department of Electronics & Instrumentation Engineering Institute of Engineering & Technology Devi Ahilya University Khandwa Road Indore452017 India

ISBN: (纸本)9789811597077

In the present communication, profiling and imaging of red blood cell (RBC) using coherent gradient sensing (CGS) technique coupled with Fourier fringe analysis has been proposed. The RBC of a healthy person has a definite structure;it has been identified using double grating shearing interferometry and the direct phase determined using the Fourier transform method. Good accuracy and resolution in profiling have been achieved. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Interferometry

来源：评论

学校读者我要写书评

暂无评论

Mean Square Error-Based Approach for the Detection of Focal Position of a Lens

Mean Square Error-Based Approach for the Detection of Focal...

引用

International Conference on Computational Mathematics in Nanoelectronics and Astrophysics, CMNA 2018

作者： Bande, Shivangi Dhanotia, Jitendra Bhatia, Vimal Prakash, Shashi Photonics Laboratory Department of Electronics and Instrumentation Engineering Institute of Engineering and Technology Devi Ahilya University Khandwa Road Indore452017 India Signals and Software Group Discipline of Electrical Engineering Indian Institute of Technology Indore Indore453552 India

ISBN: (纸本)9789811597077

Determination of focal length of a lens is a common problem encountered in optical instrumentation;however, there exist very few solutions which are simple, inexpensive and yield automated output. In this paper, we present the results of investigation undertaken towards determining the focal length a test lens with high accuracy and precision by undertaking digital processing of self-images obtained at two Talbot planes using single linear grating. Light from a collimating lens is incident onto a test lens and mirror combination;the back-reflected light is incident onto a beam splitter to draw the beam for interferometric evaluation. Single CCD camera is used to capture self-images at the first and highest feasible Talbot plane for different positions of a given test lens. Self-images have been processed digitally to find mean square error (MSE) corresponding to each position of the lens. MSE is lowest when the lens is positioned at its focal length, for all other positions of lens MSE remains higher. Hence, focal position can be exactly differentiated from all other positions of lens. Also, it has been observed that MSE increases as the distance between Talbot planes increases. Hence, if the MSE is calculated for the first and the farthest Talbot plane, sensitivity is improved. To achieve high sensitivity, Talbot self-images at the first and till the eight Talbot planes (due to practical limitations) are analysed. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Liu, Yuze Liu, Tingjie Zhang, Tiehua Xia, Youhua Wang, Jinze Shen, Zhishu Jin, Jiong Yu, Fei Richard Ant Group Shanghai China Shenzhen China School of Computer Science and Technology Tongji University Shanghai China Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Large language models (LLMs) have demonstrated impressive success in a wide range of natural language processing (NLP) tasks due to their extensive general knowledge of the world. Recent works discovered that the performance of LLMs is heavily dependent on the input prompt. However, prompt engineering is usually done manually in a trial-and-error fashion, which can be labor-intensive and challenging in order to find the optimal prompts. To address these problems and unleash the utmost potential of LLMs, we propose a novel LLMsagnostic framework for prompt optimization, namely GRL-Prompt, which aims to automatically construct optimal prompts via reinforcement learning (RL) in an end-to-end manner. To provide structured action/state representation for optimizing prompts, we construct a knowledge graph (KG) that better encodes the correlation between the user query and candidate in-context examples. Furthermore, a policy network is formulated to generate the optimal action by selecting a set of in-context examples in a rewardable order to construct the prompt. Additionally, the embedding-based reward shaping is utilized to stabilize the RL training process. The experimental results show that GRL-Prompt outperforms recent state-ofthe- art methods, achieving an average increase of 0.10 in ROUGE-1, 0.07 in ROUGE-2, 0.07 in ROUGE-L, and 0.05 in BLEU. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Focal-UNet: Complex Image Semantic Segmentation Based on Focal Self-attention and UNet

Focal-UNet: Complex Image Semantic Segmentation Based on Foc...

引用

AI (ISAI), International Symposium on

作者： Haosong Gou Lei Xiang Xiaonian Chen Xin Tan Lei Lv School of Information and software Engineering in University of Electronic Science and Technology Chengdu China XinRun Information technology Co..LLC Ghuangzhou China China Mobile Group Sichuan Co. Ltd Chengdu China Chengdu Yunzhan Technology Co. Ltd Chengdu China

ISBN: (数字)9798350389074

ISBN: (纸本)9798350389081

Semantic segmentation is an important task in the field of computer vision and is widely used in fields such as medical image analysis and autonomous driving. However, when the recognized subject and the background are very similar and easily confused, it is more difficult to segment the target. This paper proposes an image segmentation algorithm based on Focal self-attention and UNet – Focal-UNet, which uses focal self-attention to capture local and global features and retain the most valuable information for edge recognition. At the same time, data enhancement methods are used to enhance the sensitivity of the model to surrounding local features during edge recognition. Experiments have proven that compared with traditional image segmentation algorithms, our algorithm achieves better segmentation results in scenes with complex backgrounds and high foreground similarities, and improves efficiency without losing more accuracy.

关键词： Accuracy Sensitivity Image analysis Target recognition Image edge detection Semantic segmentation Semantics Object segmentation Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

Densely packed object detection with transformer-based head and EM-merger

Densely packed object detection with transformer-based head ...

引用

作者： Zhong, Xiaojing Zhang, Ni Hu, Hao Li, Li Cen, Junhua Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China Pazhou Lab Guangzhou China Peng Cheng Laboratory Guangzhou China Zhongnan Building Materials Group Co. Ltd. Guangdong GW Guangzhou China Internet Technology Co. Ltd. Guangdong GW Guangzhou China

Due to the high density of objects and their varying sizes, detecting them accurately and without repetition in such scenarios is more challenging than traditional object detection methods. In this paper, we propose a YOLOv5-based object detection approach equipped with a Transformer-based Head and EM-Merger unit specifically designed for densely packed scenes. We incorporate the transformer architecture into the prediction heads to enable a self-attention mechanism that captures long-term dependencies between the densely packed objects. Additionally, we introduce an EM-Merger unit to resolve redundant object detections. Experimental results on the RebarDSC and SKU110K datasets demonstrate that our method significantly outperforms the baseline approach, achieving new state-of-the-art detection performance. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Raman Distributed Temperature Sensor By Piecewise Linear Compensation Algorithm 7

Performance Enhancement of Raman Distributed Temperature Sen...

引用

7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022

作者： Lu, Lidong Gao, Qinghao Wang, Qingshan Bu, Xiande Su, Xingchen Zhang, Chenglong Anhui University of Technology School of Electrical and Information Engineering Maanshan China Xuji Software Technology Co. Ltd Xuji Group Co.Ltd.1 Xuchang China State Grid Smart Grid Research Institute Co. Ltd Department of Information and Communication Nanjing China

ISBN: (纸本)9781665478571

As to the Raman scattering based distributed optical fiber temperature sensing system, the temperature demodulation algorithm has great influence on the temperature measurement accuracy. So, the data for the temperature demodulation need noise suppression and position correction. In addition, the walk-off effect of Raman Stokes and Raman anti-Stokes light and the fiber reference temperature calibration restrict the long-distance distributed temperature measurement, and corresponding signal processing algorithm should be adopted to solve the above problems. Based on the typical temperature demodulation theory that relies on the Raman Stokes and anti-Stokes data, an optical fiber attenuation compensation scheme for the fiber reference temperature calibration and a signal walk-off effect correction algorithm are proposed and experimentally demonstrated, and the measurement dynamic range obtained is larger than 20dB, and along an optical fiber with length of about 8km, it achieves measurement accuracy of 0.5 °C and 1m spatial resolution. © 2022 IEEE.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Methodology of Field-Oriented Control Design With Parameter Variation Analysis for Interior Permanent Magnet Synchronous Machine Drives

引用

IEEE Access 2025年 13卷 89524-89541页

作者： Tiago Davi Curi Busarello Abdullah Bubshait Oruganti V. S. R. Varaprasad Abdulhakeem Alsaleem Marcelo Godoy Simões Department of Control Automation and Computation Engineering Federal University of Santa Catarina Florianopolis Brazil Department of Electrical Engineering College of Engineering King Faisal University Al Ahsa Saudi Arabia Smart Transportation Electrification and Energy Research (STEER) Group Department of Electrical Computer and Software Engineering Faculty of Engineering and Applied Science Ontario Tech University Oshawa ON Canada Department of Electrical Engineering College of Engineering Qassim University Buraydah Saudi Arabia School of Technology and Innovations University of Vaasa Vaasa Finland

This paper proposes a comprehensive methodology for Field-Oriented Control (FOC) with parameter variation analysis for Interior Permanent Magnet Synchronous Machines (IPMSM). The modeling approach for an IPMSM is first presented, followed by a step-by-step procedure for designing a vector-controlled strategy. The formulation is based on a dq-rotating reference frame aligned with the rotor shaft position. A key distinction of this methodology from traditional approaches is that the current controller is designed in the time domain based on desired time constants, while the speed control is formulated within a frequency response domain framework. The proposed hybrid approach enables accurate tuning of the Proportional-Integrator (PI) controllers for both current and speed control loops. Additionally, a parameter variation analysis is conducted to enhance the proposed methodology. The validity region for the design procedure is presented, ensuring that for any wide speed variation of the machine, loop gains are properly tuned. One of the main advantages of the proposed methodology is that it provides a fast, reliable, and accurate technique for implementing IPMSM drive systems. Results from a Controller Hardware-in-the-Loop (C-HIL) setup with an external microcontroller are presented. The comprehensive design approach is validated under two different IPMSM parameter sets, demonstrating its effectiveness.

关键词： PI control Stators Tuning Mathematical models Velocity control Rotors Vectors Stator windings Robustness Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Efficient Test Case Prioritization Using the Rat Swarm Optimizer Algorithm

Efficient Test Case Prioritization Using the Rat Swarm Optim...

引用

Student Conference on Research and Development (SCOReD)

作者： Muhammad Afiq Bin Ariffin Mazidah Mat Rejab Rosziati Ibrahim Shahdatunnaim Binti Azmi Nor Amalina Mohd Sabri Nur Afiqah Sahadun Shelena Soosay Nathan Department of Software Engineering University Tun Hussein Onn Malaysia Batu Pahat Johor Malaysia ICT for Technology Humanization Focus Group Centter for Diploma Studies University Tun Hussein Onn Malaysia Johor Malaysia

ISBN: (数字)9798331510077

ISBN: (纸本)9798331510084

software testing is a critical phase in software development to ensure the reliability and quality of software systems. With the increasing complexity of software applications, the number of test cases can grow significantly, posing challenges in terms of execution time and resource utilization. Test Case Prioritization (TCP) has emerged as a crucial technique to optimize the order of test case execution, aiming to detect defects early in the testing process. This paper presents a novel approach to Test Case Prioritization by harnessing the power of Rat Swarm Optimization (RSO), an algorithm inspired by the collective behavior of rat colonies. Experimental results demonstrate the efficacy of our approach compared to another algorithm. This study evaluates the performance of the proposed method using the execution time taken and compared it with the others algorithm like Ant Colony Optimization (ACO), Artificial Bee Colony (ABC) algorithm, and Firefly algorithm. The results indicate that the Rat Swarm Optimizer (RSO) algorithm is notably more efficient in terms of execution time compared to the other tested algorithms. The results highlight the potential of RSO for applications requiring rapid test case prioritization, where minimizing execution time is critical. This paper underscores the potential of RSO as a viable and innovative solution for Test Case Prioritization, offering software developers and testers a valuable tool for enhancing the efficiency and effectiveness of software testing processes.

关键词： software testing software algorithms Rats software systems software reliability Complexity theory Resource management Particle swarm optimization Research and development software development management

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of deep learning models for predicting biocompatibility in tissue scaffold images

引用

Computers in Biology and Medicine 2025年第Pt A期192卷 110281-110281页

作者： Oncu, Emir Usta Ayanoglu, Kadriye Yasemin Ciftci, Fatih Faculty of Engineering Department of Biomedical Engineering Fatih Sultan Mehmet Vakıf University Istanbul Turkey BioriginAI Research Group Department of Biomedical Engineering Fatih Sultan Mehmet Vakif University Istanbul34015 Turkey Department of Tropiko Software and Consultancy Istanbul Turkey Department of Technology Transfer Office Fatih Sultan Mehmet Vakıf University Istanbul Turkey

Motivation: Bioprinting enables the creation of complex tissue scaffolds, which are vital for tissue engineering. However, predicting scaffold biocompatibility before fabrication remains a critical challenge, potentially leading to inefficiencies and resource wastage. Artificial Intelligence (AI) models, particularly Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs), offer promising predictive capabilities to address this issue. This study aims to compare the performance of ANN and CNN models to identify the most suitable approach for predicting scaffold biocompatibility using PrusaSlicer-generated designs. Description: Fifteen key design parameters influencing scaffold biocompatibility were modelled using ANN, while scaffold images were analyzed using CNN. PrusaSlicer was employed in designing scaffolds, with parameters influencing biocompatibility predictions. ANN models analyzed these parameters, while CNN models processed scaffold images. Data was standardized, and models were trained on an 80/20 split dataset. Performance evaluation metrics included accuracy, precision, recall, F1-Scores, and confusion matrices. Experimental validation involved biocompatibility tests on five scaffolds. Results: ANN model with 20 neurons and 100 epochs earned perfect (1.0) scores in F1-Score, Precision, and Recall, indicating the best possible model performance. A batch size of 56 for the Convolutional Neural Network model demonstrated balance in F1-Score (0.87), Precision (0.88), and Recall (0.9). Five scaffold tissues were tested for biocompatibility using these two models. ANN model predicted 5 scaffold tissues’ biocompatibilities correctly. While the ANN model accurately predicted biocompatibilities for all five scaffold samples, the CNN model misclassified one sample. Conclusion: This study demonstrates that ANN models are superior to CNN models in predicting scaffold biocompatibility from numerical design parameters. The findings underscore the val

关键词： Fiber bonding

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：