检索结果-内蒙古大学图书馆

A Survey of Artificial Hummingbird Algorithm and Its Variants: Statistical Analysis, Performance Evaluation, and Structural Reviewing

引用

Archives of Computational Methods in engineering 2025年第1期32卷 269-310页

作者： Hosseinzadeh, Mehdi Rahmani, Amir Masoud Husari, Fatimatelbatoul Mahmoud Alsalami, Omar Mutab Marzougui, Mehrez Nguyen, Gia Nhu Lee, Sang-Woong Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Communication and Computer Engineering Faculty of Engineering Cihan University-Erbil Kurdistan Region Iraq Department of Electrical Engineering College of Engineering Taif University Taif21944 Saudi Arabia Department of Computer Engineering College of Computer Science King Khalid University Abha61413 Saudi Arabia School of Computer Science Duy Tan University Da Nang Viet Nam Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam13120 Korea Republic of

In the last few decades, metaheuristic algorithms that use the laws of nature have been used dramatically in numerous and complex optimization problems. The artificial hummingbird algorithm (AHA) is one of the metaheuristic algorithms that was invented in 2022 based on the foraging and migration behavior of the hummingbird for modeling and solving optimization problems. The algorithm initially starts with an initial random population of solutions. It then uses iterative processes and hummingbird position updates to balance exploration and exploitation toward the most optimal solutions. This paper has a detailed and extensive review of the AHA algorithm considering the aspects of hybrid, improved, binary, multi-objective, and optimization problems. In addition, a wide range of applications of AHA in various fields such as feature selection, image processing, scheduling, Internet of Things, classification, clustering, financial and economic issues, forecasting, wireless sensor networks, and many engineering challenges are explored. The statistical and numerical results showed that the AHA algorithm with deep learning methods, Levy flight, and opposition-based learning had the best performance. Also, the AHA algorithm is most widely used in solving multimodal optimization problems and continuous functions. © The Author(s) under exclusive licence to International Center for Numerical Methods in engineering (CIMNE) 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Extrinsic and Temporal Calibration of Automotive Radar and 3-D LiDAR in Factory and On-Road Calibration Settings

IEEE Open Journal of Intelligent Transportation Systems

引用

IEEE Open Journal of Intelligent Transportation systems 2023年 4卷 708-719页

作者： Lee, Chia-Le Hou, Chun-Yu Wang, Chieh-Chih Lin, Wen-Chieh Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu300 Taiwan Industrial Technology Research Institute Mechanical and Mechatronics Systems Research Laboratories Hsinchu31040 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan

While automotive radars are widely used in ADAS and autonomous driving, extrinsic and temporal calibration of automotive radars with other sensors is still daunting due to the sparsity, uncertainty, and missing elevation angles of automotive radar measurements. We propose a target-based calibration approach of 3D automotive radar and 3D LiDAR that performs extrinsic and temporal calibration in both factory and on-road settings. In factory calibration settings, a map is built with precise target poses;target trajectories are estimated based on map-based target localization in which the accuracy of both nearby and faraway target pose estimates can be ensured. The spatial and temporal relationships between radar and LiDAR measurements are established with target trajectories to accomplish extrinsic and temporal calibration. The proposed data collection procedure provides sufficient motion for analyzing time delay between sensors and can significantly reduce the data collection effort and time. There is 52.3% distance error reduction after time delay compensation in the experiment, which shows the improvements of temporal calibration. In on-road calibration settings, the metal objects with semantic labels, such as traffic signs, are selected as calibration targets. Although there could be insufficient correspondences to infer the missing dimension of planar radar for six DoF extrinsic calibration as demonstrated in factory calibration settings, the three extrinsic parameters and the time delay are shown still to be accurate. We validated the proposed method using the nuScenes datasets, which provide sensor measurements, poses, and HD map. With twenty-two data logs, each has over 1000 correspondences, the result of extrinsic parameters reaches centimeter-level accuracy compared with the offered benchmark. The time delay compensation improves 1 meter error for radar tracking in a 20 m/s vehicle case and improves mapping quality in real world data. © 2020 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Classification of Cotton Fabric, Pineapple Fabric and Cotton Pineapple Blend Fabric with VGG16 using Keras 15

Classification of Cotton Fabric, Pineapple Fabric and Cotton...

引用

15th IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2023

作者： Villaverde, Jocelyn F. Ferrer, Marlou D. MacAbeo, Julia Alexandra T. Masilungan-Manuel, Joanna Tess Mapua University Department of Electrical Electronics and Computer Engineering Manila Philippines Philippine Textile Research Institute Research and Development Division Department of Science and Technology Taguig City Philippines

ISBN: (纸本)9798350381177

Plant leaves represent valuable raw materials for fabric production, offering an eco-friendly alternative to traditional textiles. Converting these leaves into fibers opens opportunities for versatile textile applications. Traditionally, fabric classification relied heavily on manual, time-consuming microscopic analysis of fiber composition and texture, imposing limitations on efficiency and scalability. To address this challenge, the researchers developed a robust computer Vision System on Raspberry Pi, capable of accurately classifying cotton, pineapple, and pineapple-cotton fabrics. Leveraging the powerful machine learning libraries, Tensorflow and Keras, the researchers utilized the VGG16 model, training and fine-tuning it for specialized fabric classification tasks. Notably, the VGG16 model came pretrained with weights from the ImageNet dataset, further enhancing its performance. The dataset comprised 300 images, with equal representation from cotton, pineapple, and cotton-pineapple blend fabrics. These images underwent comprehensive image pre-preprocessing, utilizing techniques such as flipping, adjusting brightness and contrast, and color augmentation. The results of this study are highly promising, with the system achieving an impressive overall accuracy rate of 91.11%. This research not only showcases the system's proficiency in fabric classification but also highlights its potential for practical applications in real-world fabric classification scenarios. © 2023 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Automating Maritime Risk Data Collection and Identification Leveraging Large Language Models 24

Automating Maritime Risk Data Collection and Identification ...

引用

24th IEEE International Conference on Data Mining Workshops, ICDMW 2024

作者： Huang, Donghao Fu, Xiuju Yin, Xiaofeng Pen, Haibo Wang, Zhaoxia Singapore Management University School of Computing and Information Systems Singapore Mastercard Research and Development Singapore Agency for Science Technology and Research Institute of High Performance Computing Singapore Tianjin University School of Electrical and Information Engineering China

ISBN: (纸本)9798331530631

Maritime risk research is crucial yet challenging for improving safety, efficiency, and sustainability in maritime operations. This paper presents an innovative method for automating the collection and identification of risk data related to global maritime risks from news sources, addressing the limitations of traditional manual methods. To evaluate the proposed method, different learning-based models, including conventional machine learning approaches and advanced Large Language Models (LLMs) such as GPT-4 and LLaMA-3.1, are comprehensively studied for comparison. In addition, not only do we use popular evaluation metrics to assess the proposed method, but we also introduce a new evaluation metric, called the "Ratio of Valid Categories (RVC),"to evaluate model reliability. The merits of the proposed method are demonstrated across different evaluation metrics. The research results show that the proposed LLM-based methods, particularly the GPT-4-based method, consistently outperform traditional models, significantly improving both the efficiency and accuracy of maritime risk data collection and identification. Our findings contribute to the expanding literature on LLM applications in risk management, demonstrating their potential to transform data collection and identification practices. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Deep Learning for Segmenting Ultrasound Images of Breast Tumours

Uncertainty-Aware Deep Learning for Segmenting Ultrasound Im...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Munia, Afsana Ahmed Hossain, Ibrahim Jalali, Seyed Mohammad Tabarisaadi, Pegah Rahman, Ashikur Nahavandi, Saeid Deakin University Institute for Intelligent Systems Research and Innovation VIC3216 Australia Bangladesh University of Engineering and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350337020

Precise image segmentation is one of the dominant factors in disease diagnosis. A typical application is the segmentation of breast ultrasound images, allowing radiologists to suggest what to do next. After emerging deep learning technology especially convolutional neural networks (CNNs), the image segmentation model achieved state-of-the-art performance in various medical applications such as cancer detection and classification, lung node segmentation, cell segmentation and so on. However, despite these successes, a big question arises: to what extent is the model certain about the predicted result? Generally, most deep learning models focus on high accuracy but not on uncertainty of predicted results, which is not enough to make a critical real-life decision such as a disease diagnosis, where a wrong decision can be life-threatening. Hence for making a crucial decision, it is essential that the predicted result will provide not only accuracy but also estimate model uncertainty. Our contribution to this research is to build a system that predicts pixel-wise semantic segmentation and provides uncertainty estimation of the predicted results. It is achieved by adding a dropout layer during training and using Monte Carlo dropout in inference. We evaluate our model with the breast ultrasound image dataset (BUSI) and compare the results with a few other state-of-the-art methods where our method outperforms others in terms of IoU. © 2023 IEEE.

关键词： Breast cancer Deep learning Semantic segmentation Ultrasound images Uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Oct Image Blind Despeckling Based on Gradient Guided Filter with Speckle Statistical Prior 48

Oct Image Blind Despeckling Based on Gradient Guided Filter ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Sanqian Xiong, Muxing Yang, Bing Zhang, Xiaoqing Higashita, Risa Liu, Jiang Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Shenzhen China Tomey Corporation Japan

ISBN: (纸本)9781728163277

Optical coherence tomography (OCT) imaging technique has been widely used for ocular disease diagnosis. However, speckles occur in OCT images due to the property of coherent imaging, inevitably affecting the visual quality and clinical analysis. To alleviate this problem, we propose a novel gradient-guided speckle image filtering method (GGSF) with structure enhancement for directly removing speckles in OCT images. Specifically, the multiplicative characteristic of speckle noise is incorporated into the guided filtering processing for modeling raw OCT images. To avoid getting trapped in image distortions, we further employ gradient regularization to integrate the structure prior information into the guided speckle image filtering procedure. Additionally, we introduce the statistical property of speckle noise obeying a gamma distribution into the least square method solver for the resulting non-convex GGSF model. Experimental results on the AS-OCT dataset demonstrate the effectiveness of GGSF for OCT image despeckling compared with competitive methods. Furthermore, we validate the benefits of GGSF for subsequent clinical analysis with the CM-OCT dataset. © 2023 IEEE.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Effective solutions to prevent digital fraud by introducing electronic signature of PDF files 24

Effective solutions to prevent digital fraud by introducing ...

引用

24th International Conference on Control systems and computer Science, CSCS 2023

作者： Anghel, Ionut Petrisor Radulescu, Dragos Marinescu, Ion Alexandru Polytechnic University of Bucharest Computer Science and Engineering Department Bucharest Romania National Institute for Research and Development in Informatics Digital Transformation and Governance Bucharest Romania

ISBN: (纸本)9798350313390

With the exponential growth of digital transactions, the creation and verification of electronic signatures contributes decisively to the creation of a safer environment for business development and innovation, based on security factors such as confidentiality, integrity, authenticity or non-repudiation. Implementing electronic signatures in PDF files can improve the prevention of digital fraud by providing an additional level of security and authenticity. For this reason, in addition to choosing a reliable electronic signature provider, it is necessary to establish clear signing procedures in order to minimize the risk of fraud. For this purpose, a software solution intended mainly for the academic environment is presented, which facilitates the electronic signature with legal value of PDF documents using a digital certificate. This application offers the possibility of simultaneously signing of multiples files in a folder, thus streamlining the process of digital signature and avoiding the use of third-party applications. © 2023 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Reward-Based Energy-Aware Routing Protocols in Wireless Sensor Networks

Reward-Based Energy-Aware Routing Protocols in Wireless Sens...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Salama, Ramiz Alturjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Cyprus Artificial Intelligence Software and Information Systems Engineering Departments AI and Robotics Institute Near East University Nicosia Cyprus

ISBN: (纸本)9783031782756

Smart cities, industrial automation, healthcare, and environmental monitoring are just a few of the industries that have seen revolutionary changes as a result of Wireless Sensor Networks’ (WSNs) explosive growth. WSNs are significantly hampered by the limited energy resources of their sensor nodes, which are usually battery-powered and placed in inaccessible locations, despite their wide-ranging applications. As a result, energy efficiency is now a crucial component of these networks’ operation and design. Though these protocols frequently fail to adjust to the dynamic and unpredictable nature of WSNs, traditional energy-aware routing methods have been created to decrease energy consumption by choosing the best paths for data transfer. By allowing sensor nodes to learn from their surroundings and make wise routing decisions, the machine learning field of reinforcement learning (RL) provides a viable answer to these problems. In contrast to conventional techniques, RL-based protocols provide continuous energy optimization by dynamically modifying their routing strategies in response to real-time feedback. This paper investigates how to include RL methods—specifically, Q-learning and SARSA—into WSN energy-aware routing protocols. The suggested method creates a more distributed and scalable solution by enabling each node to independently learn and modify its routing choices. The effectiveness of RL-based routing protocols is compared to traditional methods through comprehensive simulations. The findings show that by slowing down the rate at which energy is being used up by each node, RL not only increases energy efficiency but also lengthens the network's operational life. In particular, Q-learning demonstrates a notable improvement in sustaining data delivery rates and network connectivity under various circumstances. Although a little more computationally demanding, the SARSA algorithm offers greater flexibility in situations where network topology changes often. Th

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Using Gamification to Increase Healthcare Professionals’ Cybersecurity Awareness

Using Gamification to Increase Healthcare Professionals’ Cy...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Salama, Ramiz Alturjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Cyprus Artificial Intelligence Software Information Systems Engineering Departments AI and Robotics Institute Near East University Nicosia Cyprus

ISBN: (纸本)9783031782756

Cybersecurity knowledge is essential in today’s increasingly digital healthcare environment to protect sensitive patient data and guarantee the integrity of healthcare systems. But conventional cybersecurity training approaches frequently fail to hold healthcare professionals’ attention, which results in inadequate application and retention of the material. In order to increase cybersecurity awareness among healthcare professionals, this study investigates the use of gamification—a technological technique that incorporates game design aspects into non-gaming contexts—as an innovative method. A mixed-methods research methodology is used in the study to assess the effectiveness of a cybersecurity training program that is gamified. To encourage user involvement and motivation, the program incorporates aspects like leaderboards, interactive scenarios, badges, and points. The study included a total of 100 healthcare professionals from various departments, offering a thorough understanding of the program’s effects across a range of positions and experience levels. Pre- and post-training surveys were used to gather quantitative data on participant changes in knowledge, attitudes, and behaviors pertaining to cybersecurity procedures. Furthermore, semi-structured interviews yielded qualitative insights that further elucidated the participants’ perspectives and experiences with the gamified training method. Comparing gamification to conventional training approaches, the results show that gamification dramatically improves engagement and knowledge retention. The willingness of the participants to acquire and use cybersecurity techniques in their daily lives has reportedly increased. Additionally, the gamified components strengthened the training objectives by fostering a competitive yet cooperative learning environment. The potential of gamification as a game-changing instrument for cybersecurity education in healthcare settings is highlighted by this study. Healthcare busines

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A robust deformed convolutional neural network(CNN)for image denoising

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 331-342页

作者： Qi Zhang Jingyu Xiao Chunwei Tian Jerry Chun‐Wei Lin Shichao Zhang School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina School of Computer Science Central South UniversityChangshaChina School of Software Northwestern Polytechnical UniversityXi'anShaanxiChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina Yangtze River Delta Research Institute Northwestern Polytechnical UniversityTaicangChina Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergenNorway

Due to strong learning ability,convolutional neural networks(CNNs)have been developed in image ***,convolutional operations may change original distributions of noise in corrupted images,which may increase training difficulty in image *** relations of surrounding pixels can effectively resolve this *** by that,we propose a robust deformed denoising CNN(RDDCNN)in this *** proposed RDDCNN contains three blocks:a deformable block(DB),an enhanced block(EB)and a residual block(RB).The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture,according to relations of surrounding *** EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers,batch normalisation(BN)and ReLU,which can enhance the learning ability of the proposed *** address long-term dependency problem,the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean ***,we implement a blind denoising *** results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative *** can be obtained at https://***/hellloxiaotian/RDDCNN.

关键词： blind denoising CNN deformed block enhanced block

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：