检索结果-内蒙古大学图书馆

Best Selection of Generative Adversarial Networks Hyper-Parameters Using Genetic Algorithm

SN computer Science 2021年第4期2卷 283页

作者： Alarsan, Fajr Ibrahem Younes, Mamoon Informatics and Decision Supporting Systems Higher Institute for Applied Sciences and Technology Damascus Syrian Arab Republic Faculty of Computer and Automation Engineering Damascus University Damascus Syrian Arab Republic

Generative adversarial networks (GANs) are most popular generative frameworks that have achieved compelling performance. They follow an adversarial approach where two deep models generator and discriminator compete with each other. In this paper, we propose a Generative Adversarial Network with best hyper-parameters selection to generate fake images for digit numbers 1–9 with generator and train discriminator to decide whereas the generated images are fake or true. Genetic algorithm (GA) technique was used to adapt GAN hyper-parameters, the resulted algorithm is named GANGA: generative adversarial network with genetic algorithm. The resulted algorithm has achieved high performance;it was able to get zero value of loss function for the generator and discriminator separately. Anaconda environment with tensorflow library facilitates was used;python as programming language was adapted with needed libraries. The implementation was done using MNIST dataset to validate the work. The proposed method is to let genetic algorithm choose best values of hyper-parameters depending on minimizing a cost function such as a loss function or maximizing accuracy function used to find best values of learning rate, batch normalization, number of neurons and a parameter of dropout layer. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Discriminator Generative adversarial networks (GAN) Generator Genetic algorithm Image synthesis MNIST dataset

来源：评论

学校读者我要写书评

暂无评论

TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules

arXiv

引用

arXiv 2025年

作者： Zhang, Ruoyu Wang, Lulu He, Yi Pan, Tongling Yu, Zhengtao Li, Yingna Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650504 China Key Laboratory of Computer Technologies Application Kunming650504 China Hongyun Honghe Group Honghe Cigarette Factory Kunming650202 China

Recent advancements in large language models (LLMs) have significantly enhanced the fluency and logical coherence of image captioning. Retrieval-Augmented Generation (RAG) is widely adopted to incorporate external knowledge into LLMs;however, existing RAG-based methods rely on separate retrieval banks, introducing computational overhead and limiting the utilization of LLMs’ inherent zero-shot capabilities. To address these limitations, we propose TPCap, a novel trigger-augmented and multi-modal purification framework for zero-shot image captioning without external retrieval libraries. TPCap consists of two key components: trigger-augmented (TA) generation and multi-modal purification (MP). The TA module employs a trigger projector with frozen and learnable projections to activate LLMs’ contextual reasoning, enhance visual-textual alignment, and mitigate data bias. The MP module further refines the generated entity-related information by filtering noise and enhancing feature quality, ensuring more precise and factually consistent captions. We evaluate TPCap on COCO, NoCaps, Flickr30k, and WHOOPS datasets. With only 0.82M trainable parameters and training on a single NVIDIA RTX 4090 GPU, TPCap achieves competitive performance comparable to state-of-the-art models. Copyright © 2025, The Authors. All rights reserved.

关键词： Information filtering

来源：评论

学校读者我要写书评

暂无评论

Radar emitter signal recognition based on convolutional neural network and main ridge coordinate transformation of ambiguity function 4

Radar emitter signal recognition based on convolutional neur...

引用

4th IEEE Advanced Information Management, Communicates, Electronic and automation Control Conference, IMCEC 2021

作者： Pu, Yunwei Liu, Taotao Wu, Haixiao Guo, Jiang Kunming University of Science and Thechnology Faculty of Information Engineering and Automation Kunming650500 China Computer Center Kunming University of Science and Thechnology Kunming650500 China

ISBN: (纸本)9781728185347

Aiming at the time-consuming and inconspicuous features of artificially extracting radar emitter signal features, a recognition method based on deep learning convolutional neural network and ambiguity function main ridge coordinate transformation is proposed. The method extracts the main ridge of the ambiguity function of the signal through fast discrete fractional Fourier transform, and then uses the two-dimensional time-frequency diagram of the main ridge polar coordinate domain of the ambiguity function as the input of the convolutional neural network to realize the sorting and recognition of different radar signals. Experiments show that the method in this paper not only maintains a 100% recognition rate above 0dB, but also stabilizes the recognition accuracy rate above 90% at -6dB. Compared with traditional radar signal recognition methods and other deep learning model recognition methods, the proposed method has greatly improved recognition rate and robustness, and has certain engineering application value. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating FACTS technologies into renewable energy systems: potential and challenges

引用

International Journal of Ambient Energy 2024年第1期45卷

作者： Nazir, Muhammad Shahzad Ullah, Hayat Larik, Nauman Ali Chu, Zhang Tian, Peng Sohail, Hafiz M. Raute, Reiko Faculty of Automation Huaiyin Institute of Technology Huai’an China Gina Cody School of Engineering and Computer Science Concordia University Montreal Canada Concordia University Montreal Canada School of Electrical Power South China University of Technology Guangzhou China School of Economics and Management South China Normal University Guangzhou China Department of Electrical Engineering Faculty of Engineering University of Malta Msida Malta

The proliferation of renewable energy systems into smart grids is becoming increasingly vital as the globe continues to shift toward sustainable energy sources. However, renewable energy’s intermittent nature can cause power quality complications such as voltage swings and frequency irregularities. Interestingly, FACTS technologies can provide improved control facilities for power flow and voltage regulation. The global FACTS market worthed $1.18 billion in 2020 and is predicted to be $1.91 billion by 2026, expanding at 7.5%. This study entertains FACTS technologies and their integration into renewable energy systems. This study deliberates the function of several FACTS devices, including Static Var Compensators, Static Synchronous Compensators, and Unified Power Flow Controllers, in enhancing power quality. The study also expanded to the problems and opportunities that come with integrating FACTS technologies into renewable energy systems. This study offers the current state of FACTS technologies and their prospective applications for improving power quality integrated renewable energy systems issues. The review will be an interesting useful source for industry and academia researchers in power systems and renewable energy. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： FACTS technologies power quality green energy utilisation clean energy smart grid renewable energy sources

来源：评论

学校读者我要写书评

暂无评论

Review of recent designs, performance, and configurations for the pyramid solar still

引用

International Journal of Energy and Water Resources 2025年第2期9卷 1145-1176页

作者： Hussein, A. Kadhim Rashid, F. Lafta Abed, A.M. Sultan, H.S. Togun, H. Attia, M. El Hadi Manokar, A. Muthu Hamida, M. Bechir Ben Ali, B. Younis, O. Khutar, N. Murad Mechanical Engineering Department College of Engineering University of Babylon Babylon City Hilla Iraq Petroleum Engineering Department College of Engineering University of Kerbala Karbala Iraq Air Conditioning and Refrigeration Techniques Engineering Department Al-Mustaqbal University College Babylon 51001 Iraq College of Engineering University of Warith Al-Anbiyaa Karbalaa 56001 Iraq Biomedical Engineering Department University of Thi-Qar Nassiriya 64001 Iraq Physics Department Faculty of Exact Sciences University of El Oued El Oued 3900 Algeria Department of Mechanical Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu Chennai 600048 India Department of Chemical Engineering College of Engineering Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Research Laboratory of Ionized Backgrounds and Reagents Studies (EMIR) Preparatory Institute for Engineering Studies of Monastir (IPEIM) University of Monastir Monastir City Tunisia Higher School of Sciences and Technology of Hammam Sousse Department of Physics University of Sousse Sousse Tunisia School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen 518055 China Department of Mechanical Engineering College of Engineering in Wadi Addwasir Prince Sattam Bin Abdulaziz University Al-Kharj 11942 Saudi Arabia Department of Mechanical Engineering Faculty of Engineering University of Khartoum Khartoum Sudan Department of Computer Technical Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq

Fresh water is essential for day-to-day survival. The primary issue facing undeveloped nations is the continuous scarcity of clean water, and drinking contaminated water to survive may harm one’s health. Due to population expansion, there is less fresh water available. Boring wells, rainwater, and water from rivers or lakes are among the potential water sources. For isolated, arid, and semiarid regions, solar distillation is appropriate. Where there is a severe drinking water deficit and intense solar radiation. With free energy, straightforward, affordable technology, and a clean atmosphere, solar still (SS) partly meets man’s demand for drinking water, especially in distant locations. This review focuses on pyramid solar stills (PSS), highlighting their potential to meet drinking water demands with free, clean energy and simple technology. This paper comprehensively reviews numerical, experimental, and combined (numerical and experimental), discussing various setups, parameters, and results. Key advancements, performance improvements, and future research directions are outlined, emphasizing the importance of innovative designs and optimization for enhanced efficiency and freshwater production. © The Author(s), under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2024.

关键词： Comprehensive review Pyramid solar still Remote regions Water desalination

来源：评论

学校读者我要写书评

暂无评论

A Study to Compare YOLO Family Models for Metal Surface Anomaly Detection

A Study to Compare YOLO Family Models for Metal Surface Anom...

引用

IEEE International Conference on Big Data

作者： Abdüsselam Koç Özlem Albayrak Yaşar Kurt Perin Ünal Faculty of Computer Engineering TED University Ankara Turkey Research & Development TEKNOPAR Industrial Automation Ostim Technical University Graduation School of Engineering and Sciences Ankara Turkey Graduation School of Engineering and Sciences Ostim Technical University

Anomaly detection is an important process that needs to be automated. Metal is an essential material that is heavily used in manufacturing of many different products. Automated detection of anomalies on metal surfaces is a topic that has been widely studied both by the researchers in the academia and by the practitioners. In the recent years, many studies have been conducted that apply deep learning for anomaly detection on metal surfaces. In this study, using NEU-DET data set, we have applied YOLO family models (YOLOv4, YOLOv5, YOLOv6, YOLOv7 and YOLOv8) in order to classify defects of images of steel. The results presented that with respect to mAP50 YOLOv8 has outperformed the other models. In the short term, we aim to utilize real images taken from home appliances products and perform a replication study. As for the long-term research we aim to develop and test our model based on real data set belonging to a Horizon Europe project. YOLOv8 has presented the best performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Contextual Representation and Multi-modality for End-to-end Autonomous Driving

引用

engineering Applications of Artificial Intelligence 2024年 135卷

作者： Azam, Shoaib Munir, Farzeen Kyrki, Ville Kucner, Tomasz Piotr Jeon, Moongu Pedrycz, Witold Department of Electrical Engineering and Automation Aalto University Espoo Finland Finnish Center for Artificial Intelligence Finland School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2V4 Canada Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Systems Research Institute Polish Academy of Sciences Warsaw01-447 Poland

Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often lack global environmental context. Humans, when driving, naturally employ neural maps that integrate various factors such as historical data, situational subtleties, and behavioral predictions of other road users to form a rich contextual understanding of their surroundings. This neural map-based comprehension is integral to making informed decisions on the road. In contrast, even with their significant advancements, autonomous systems have yet to fully harness this depth of human-like contextual understanding. Motivated by this, our work draws inspiration from human driving patterns and seeks to formalize the sensor fusion approach within an end-to-end autonomous driving framework. We introduce a framework that integrates three cameras (left, right, and center) to emulate the human field of view, coupled with top-down bird-eye-view semantic data to enhance contextual representation. The sensor data is fused and encoded using a self-attention mechanism, leading to an auto-regressive waypoint prediction module. We treat feature representation as a sequential problem, employing a vision transformer to distill the contextual interplay between sensor modalities. The efficacy of the proposed method is experimentally evaluated in both open and closed-loop settings. Our method achieves displacement error by 0.67m in open-loop settings, surpassing current methods by 6.9% on the nuScenes dataset. In closed-loop evaluations on CARLA's Town05 Long and Longest6 benchmarks, the proposed method enhances driving performance, route completion, and reduces infractions. © 2024 The Authors

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Efficient Visual Recognition:A Survey on Recent Advances and Brain-inspired Methodologies

引用

Machine Intelligence Research 2022年第5期19卷 366-411页

作者： Yang Wu Ding-Heng Wang Xiao-Tong Lu Fan Yang Man Yao Wei-Sheng Dong Jian-Bo Shi Guo-Qi Li Applied Research Center Laboratory Tencent Platform and Content Group Shenzhen 518057China School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi′an Jiaotong UniversityXian710049China School of Artificial Intelligence Xidian UniversityXi'an 710071China Division of Information Science Nara Institute of Science and TechnologyNara 6300192Japan Peng Cheng Laboratory Shenzhen 518000China Department of Computer and Information Science University of PennsylvaniaPhiladelphia PA19104-6389USA Institute of Automation Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100190China

Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial *** has great fundamental importance and strong industrial needs,particularly the modern deep neural networks(DNNs)and some brain-inspired methodologies,have largely boosted the recognition performance on many concrete tasks,with the help of large amounts of training data and new powerful computation *** recognition accuracy is usually the first concern for new progresses,efficiency is actually rather important and sometimes critical for both academic research and industrial ***,insightful views on the opportunities and challenges of efficiency are also highly required for the entire *** general surveys on the efficiency issue have been done from various perspectives,as far as we are aware,scarcely any of them focused on visual recognition systematically,and thus it is unclear which progresses are applicable to it and what else should be *** this survey,we present the review of recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related and brain-inspired visual recognition approaches,including efficient network compression and dynamic brain-inspired *** investigate not only from the model but also from the data point of view(which is not the case in existing surveys)and focus on four typical data types(images,video,points,and events).This survey attempts to provide a systematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners working on visual recognition problems.

关键词： Visual recognition deep neural networks(DNNS) brain-inspired methodologies network compression dynamic inference survey

来源：评论

学校读者我要写书评

暂无评论

Research on the Structural Design and Basin Characteristics of Pilot Electromagnetic Valves for New Energy Wastewater Treatment Systems

Research on the Structural Design and Basin Characteristics ...

引用

Advanced Electrical and Energy Systems (AEES), International Conference on

作者： Na Wang Yueyang Dong Xiaofei Zhen Ruonan Jiao Haoran Fu Yuying Chen School of Mechatronic Engineering Lanzhou Jiaotong University Lanzhou China School of New Energy and Power Engineering Lanzhou Jiaotong University Lanzhou China Faculty of Engineering Computer and Mathematical Sciences The University of Adelaide Adelaide Australia Academy of Electrical and Automation Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9798331517724

ISBN: (纸本)9798331517731

Pilot-operated solenoid valves have the advantage of fast response times and can meet high pressure and large diameter requirements through their structural characteristics, making them widely used in various fields. The pilot-operated solenoid valve discussed in this article is applied in a new energy system a sewage treatment system based on solar photovoltaic and solar thermal technology. The pilot-operated solenoid valve designed in this paper controls the flow rate and velocity of the sewage. This article uses Fluent to calculate the flow coefficient of pilot-type solenoid valves at various openings, exploring the flow characteristics of these valves. Based on computational fluid dynamics, simulations of the cavitation flow field were performed for pilot-type solenoid valve models at different openings, resulting in pressure contour plots and liquid velocity vector diagrams within the pilot valve. The study investigated the effects of the valve opening and the pressure difference at the inlet and outlet on the cavitation conditions within the valve. This provides a foundation for subsequent analysis of the vibration characteristics and structural optimization of solenoid pilot valves. The results indicate that negative pressure occurs within the solenoid pilot valve at all openings, leading to cavitation phenomena. When the opening is greater than or equal to 0.5, significant negative pressure appears near the valve port of the valve sleeve, with more pronounced cavitation phenomena, which can easily lead to cavitation bubbles and deformation.

关键词： Vibrations Analytical models Deformation Computational modeling Valves Vectors Time factors Solenoids Wastewater treatment Optimization

来源：评论

学校读者我要写书评

暂无评论

Cross-Guided Attention and Combined Loss for Optimizing Gastrointestinal Visual Question Answering

Cross-Guided Attention and Combined Loss for Optimizing Gast...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qian Yang Lijun Liu Xiaobing Yang Li Liu Wei Peng Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming P. R. China Yunnan Key Laboratory of Computer Technology Application Kunming China P. R. China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Medical Visual Question Answering (Med-VQA) aims at answering clinical questions related to medical imaging, providing important reference for medical imaging diagnosis. Gastrointestinal visual question answering can deeply understand and analyze gastrointestinal medical images, provides supporting information to answer questions about the diagnostic process, and improves diagnostic accuracy and efficiency. However, most existing Med-VQA can only handle simple and general questions, struggling to tackle visual question answering related to complex diseases. Therefore, this paper proposes a Med-VQA model called CACL, which uses cross-guidance and improved combined loss. The model focuses on gastrointestinal image analysis and achieves efficient and accurate feature extraction for gastrointestinal images. A cross-guided attention module is also designed to enhance the model’s reasoning ability when dealing with complex cross-modal tasks. In addition, a multi-task composite loss function is designed to balance the loss of segmentation task and classification task, and improve the overall performance. Experimental results show that the proposed method can effectively improve the accuracy of gastrointestinal visual question answering.

关键词： Visualization Image segmentation Accuracy Image analysis Feature extraction Multitasking Gastrointestinal tract Question answering (information retrieval) Medical diagnostic imaging Diseases

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：