检索结果-内蒙古大学图书馆

Realization of Memristive State machine for Smart Edge Detector applications

IETE JOURNAL OF RESEARCH 2023年第3期69卷 1249-1259页

作者： Ganganaik, Priyanka B. Abhijith, G. Raj, P. Michael Preetam Renuka, H. Rao, B. v. v. S. N. Prabhakar Kundu, Souvik Birla Inst Technol & Sci BITS Pilani Dept Elect & Elect Engn Hyderabad Campus Hyderabad 500078 India

In this work, an oxide memristor was utilized for analog computing, which exhibited controllable transitions within its stable resistive states. The memristive ON and OFF states were considered to be logic 1 and logic 0, respectively, whereas the intermediate memristances represent the possible resistive states within the memristive state machine (MSM). This MSM was sprucely tailored to perform tunable edge detection. In contrast to other software based conventional edge detection systems such as Canny, Sobel, and Prewitt, the proposed MSM system performed better with around 8% improvement in accuracy of edge detection. With the level of simplicity and accuracy, the proposed system exhibits potential to be an efficient alternative to the conventional systems for edge detection and laid a concrete path for future low hardware based smart system design due to the suppression of analog-to-digital conversion.

关键词： Memristor Memristive state machine State transitions Edge detection image processing Multi-level logic

来源：评论

学校读者我要写书评

暂无评论

Enhancing metal additive manufacturing training with the advanced vision language model: A pathway to immersive augmented reality training for non-experts

引用

JOURNAL OF MANUFACTURING SYSTEMS 2024年 75卷 257-269页

作者： Fan, Haolin Zhang, Hongji Ma, Changyu Wu, Tongzi Fuh, Jerry Ying Hsi Li, Bingbing Natl Univ Singapore Dept Mech Engn Singapore 117575 Singapore Calif State Univ Northridge Auton Res Ctr STEAHM ARCS Northridge CA 91330 USA

This paper introduces an innovative training system for the Renishaw AM400 metal printer, leveraging the synergy of the advanced vision Language Model (vLM) with Augmented Reality (AR) within the Digital Twins (DT) framework. Aimed at overcoming the limitations of conventional training methods in metal additive manufacturing (AM), our system integrates AR to provide an immersive learning environment, enhancing the real-world experience with interactive digital overlays. The core of the system lies in its use of vLM, which, pre-trained on diverse datasets, excels in processing multi-modal data, thereby offering nuanced and contextually relevant guidance for trainees. Key experiments demonstrate the system's effectiveness, particularly highlighting the usage of vLM as an Artificial Intelligence (AI) agent to integrate external tools like YOLO-v7 for valve state classification and CRAFT for control panel text recognition. This approach significantly improves recognition accuracy, operational understanding, and human-machine interaction, especially for nonexpert users, making complex metal AM operations more accessible. The research not only showcases the potential of AR and vLM in industrial training but also sets a new standard for smart manufacturing practices, indicating broader applications in various industrial domains.

关键词： Metal additive manufacturing vision language model Augmented reality Non-expert training Digital twins

来源：评论

学校读者我要写书评

暂无评论

Design and development of universal soft robotic end effector through machine learning on the IRB 360 robot

引用

INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND applications 2024年第3期8卷 671-691页

作者： Sethuramalingam, Prabhu Uma, M. Darshan, v. Sumesh, K. S. SRM Inst Sci & Technol Kattankulathur Dept Mech Engn Chennai 603203 India SRM Inst Sci & Technol Dept Computat Intelligence Chennai 603203 India

The end effector (gripper) is an important part of a robotic system that is used for industrial and domestic tasks like grasping, carrying, manipulating, assembling, painting, and so on. For handling different types of objects hard as well as soft, require different types of the gripper. The employment of compliant soft-robotic grasping systems, which are characterized by high flexibility in terms of workpiece shape, dimension, and anatomy, is a good method to incorporate greater flexibility into production. The study's major goal is to build and analyses the soft-robotic grippers in terms of repeatability with large payload capacities. End effector (soft gripper) control is crucial for precision work by applying different gripping forces according to the object going to pick. The selection of suitable gripping force for a particular object is done by the process of machine learning (ML). The soft gripper is designed, fabricated, and tested using Industrial Robot (IRB 360) flex picker robot. The virtual environment is created to move the linear path using Robot studio software with rapid programming language. The accuracy, precision, recall, and receiver operating characteristic curve (ROC) curve are analyzed and predict the gripper force accurately with 94% when compared with experimental value. The gripper is working effectively from 1.4 to 2.8 bars with a maximum payload of 500 g. The soft flexible gripper angle is measured based on the pressure using an image processing edge detection technique. The optimized best possible gripping force is predicted using different objects and control action is done to supply exact force to the gripper.

关键词： IRB 360 robot Gripping force machine learning Logistic regression Soft gripper image processing

来源：评论

学校读者我要写书评

暂无评论

Non-Destructive Post-Harvest Tomato Mass Estimation Model Based on Its Area via Computer vision and Error Minimization Approaches

引用

IEEE ACCESS 2022年 10卷 100247-100256页

作者： Bucio, F. J. Isaza, C. Gonzalez, E. Zavala De Paz, J. P. Rizzo Sierra, J. A. Anaya Rivera, E. K. Univ Politecn Queretaro Santiago De Queretaro 76240 Mexico Univ Politecn Tulancingo Tulancingo 43629 Hidalgo Mexico

Tomato commercialization in Mexican and Latin-American markets is economically affected by three main physical aspects of the fruit: ripening time, size, and mass. Digital image processing combined with mathematical models and machine learning approaches allows the development of prediction models to minimize fruit waste, among other applications. Particularly crossed validation, linear and non-linear adjustment by quadratic mean least error approximation, and digital image processing are used to obtain a post-harvest mass loss estimation model based upon the fruit's area. A database for fruit characterization of 97,200 images and mass (kg) and area (cm2) measurement entries over a continuous post-harvest timeline of 54 days was considered in the methodology. Results from the linear (polynomial) adjustment model presented an efficiency of 94.65%, while the non-linear (exponential and potential) adjustment models gave in their turn efficiencies of 99.21 and 99.82%, respectively. It was concluded that the best mass loss estimation model was the potential adjustment one, with an approximation error of just 0.18% between actual and estimated data.

关键词： Mathematical models Digital images Biological system modeling Crops Economics Predictive models machine learning Commercialization Computer vision Agricultural engineering Estimation Error analysis Agricultural engineering digital images estimation error linear approximation machine learning prediction models

来源：评论

学校读者我要写书评

暂无评论

Development and Application of Self-Supervised machine Learning for Smoke Plume and Active Fire Identification from the Fire Influence on Regional to Global Environments and Air Quality Datasets

引用

REMOTE SENSING 2025年第7期17卷 1267-1267页

作者： LaHaye, Nicholas Easley, Anastasija Yun, Kyongsik Lee, Hugo Linstead, Erik Garay, Michael J. Kalashnikova, Olga v. Spatial Informat Grp LLC Pleasanton CA 94566 USA CALTECH Jet Prop Lab Pasadena CA 91101 USA Univ Calif Berkeley Coll Letters & Sci Dept Math Berkeley CA 94720 USA Chapman Univ Fowler Sch Engn Orange CA 92866 USA Chapman Univ Machine Learning & Assist Technol Lab MLAT Orange CA 92866 USA

Fire Influence on Regional to Global Environments and Air Quality (FIREX-AQ) was a field campaign aimed at better understanding the impact of wildfires and agricultural fires on air quality and climate. The FIREX-AQ campaign took place in August 2019 and involved two aircraft and multiple coordinated satellite observations. This study applied and evaluated a self-supervised machine learning (ML) method for the active fire and smoke plume identification and tracking in the satellite and sub-orbital remote sensing datasets collected during the campaign. Our unique methodology combines remote sensing observations with different spatial and spectral resolutions. With as much as a 10% increase in agreement between our produced masks and high-certainty hand-labeled pixels, relative to evaluated operational products, the demonstrated approach successfully differentiates active fire pixels and smoke plumes from background imagery. This enables the generation of a per-instrument smoke and active fire mask product, as well as smoke and fire masks created from the fusion of selected data from independent instruments. This ML approach has the potential to enhance operational active wildfire monitoring systems and improve decision-making in air quality management through fast smoke plume identification and tracking and could improve climate impact studies through fusion data from independent instruments.

关键词： FIREX-AQ active fire and smoke detection big data applications clustering computer vision image segmentation self-supervised deep learning multi-modal data fusion

来源：评论

学校读者我要写书评

暂无评论

Multiple image Augmentations for Enhanced YOLO-based Traffic Sign Detection 2

Multiple Image Augmentations for Enhanced YOLO-based Traffic...

引用

2nd International Conference on image processing, Computer vision and machine Learning, ICICML 2023

作者： Long, Pinzhuang Hu, Yichen University of Nottingham Ningbo China Electrical and Electronic Engineering Ningbo315100 China University of Nottingham Mechanical Manufacturing and Material Engineering NottinghamNG7 2RD United Kingdom

ISBN: (纸本)9798350331417

The rapid growth of the automotive industry necessitates the implementation of robust passenger safety measures, especially in the domain of traffic sign recognition for autonomous driving. This study introduces an effective approach to enhance traffic sign detection, with a specific emphasis on the You Only Look Once (YOLO) architecture. The paper addresses the challenges associated with accurately localizing traffic signs by employing diverse image augmentation techniques, including flipping, color inversion, Gaussian blur, affine transformation, and brightness adjustment. Despite computational challenges, particularly in light of YOLOv5's superior accuracy and efficiency, there is still room for further refinement to meet the stringent requirements of autonomous driving research. This research underscores the potential of image augmentation in advancing traffic sign recognition, demonstrating its pivotal role in the development of intelligent transportation systems. In comparison to existing algorithms as YOLO-v3 and YOLO-v5, the proposed technique might successfully reach higher accuracy and less computational power and processing time. © 2023 IEEE.

关键词： Autonomous driving Data augment Traffic signs detection YOLO architecture Introduction

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of froth surface monitoring as an aid for grade and recovery prediction of flotation process. Part A: structural features

引用

ENERGY SOURCES PART A-RECOvERY UTILIZATION AND ENvIRONMENTAL EFFECTS 2023年第1期45卷 2587-2605页

作者： Nakhaei, Fardis Irannajad, Mehdi Mohammadnejad, Sima Amirkabir Univ Technol Dept Min & Met Engn Tehran Iran Tarbiat Modares Univ Dept Min Engn Tehran Iran

Digital image processing system is a promising technology for obtaining process-related information and well accepted in mineral processing industries as a fast, non-invasive and low-cost tool for quality evaluation of flotation process. The structural, textural and dynamic features of froth surface appearance include vital information about process status, which can be employed as a useful index for the evaluation of the flotation performance. A large number of features extraction techniques have been proposed over the last years and understanding digital imaging and selecting a proper technique for the desired application are very important. The goal of this two-part series is to compile an up-to-date review regarding the most common techniques of features extraction from froth images and to present their major advantages, limitations, and applications in flotation process, with particular focus on prediction of concentrate grade and recovery. Part 1 of this review focusses on the structural features of froth images (bubble shape and size distribution) and the relationship between them and process conditions, while Part 2 presents textural and dynamic features. Also, Part 2 discusses estimation methods of concentrate grade and recovery with the froth surface measurable attributes. This work can make significant contributions toward the development of on-line control systems on the basis of machine vision.

关键词： Froth flotation image analysis features extraction bubble size froth shape grade recovery control

来源：评论

学校读者我要写书评

暂无评论

Convolution-Enhanced Evolving Attention Networks

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2023年第7期45卷 8176-8192页

作者： Wang, Yujing Yang, Yaming Li, Zhuo Bai, Jiangang Zhang, Mingliang Li, Xiangtai Yu, Jing Zhang, Ce Huang, Gao Tong, Yunhai Peking Univ Key Lab Machine Percept MOE Sch Intelligence Sci & Technol Beijing 100871 Peoples R China Peking Univ Dept Comp Sci & Technol Engn Res Ctr Microprocessor & Syst Beijing 100871 Peoples R China Chinese Acad Sci Inst Informat Engn Beijing 100045 Peoples R China Swiss Fed Inst Technol CH-8092 Zurich Switzerland Tsinghua Univ Dept Automat Beijing 100190 Peoples R China

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps are crucial as they encode semantic dependencies between input tokens. However, most existing attention networks perform modeling or reasoning based on representations, wherein the attention maps of different layers are learned separately without explicit interactions. In this paper, we propose a novel and generic evolving attention mechanism, which directly models the evolution of inter-token relationships through a chain of residual convolutional modules. The major motivations are twofold. On the one hand, the attention maps in different layers share transferable knowledge, thus adding a residual connection can facilitate the information flow of inter-token relationships across layers. On the other hand, there is naturally an evolutionary trend among attention maps at different abstraction levels, so it is beneficial to exploit a dedicated convolution-based module to capture this process. Equipped with the proposed mechanism, the convolution-enhanced evolving attention networks achieve superior performance in various applications, including time-series representation, natural language understanding, machine translation, and image classification. Especially on time-series representation tasks, Evolving Attention-enhanced Dilated Convolutional (EA-DC-) Transformer outperforms state-of-the-art models significantly, achieving an average of 17% improvement compared to the best SOTA. To the best of our knowledge, this is the firstwork that explicitly models the layer-wise evolution of attention maps. Our implementation is available at https://***/pkuyym/EvolvingAttention.

关键词： Transformers Task analysis Convolution Neural networks machine translation Time series analysis Computational modeling Evolving attention image classification machine translation network architecture natural language understanding representation learning time series

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Deep Learning Models for image Captioning of Satellite images 4th

Comparative Evaluation of Deep Learning Models for Image Cap...

引用

4th International Conference on Innovations in Computational Intelligence and Computer vision, ICICv 2024

作者： Shree, Aishwary Sharma, Rohit Singla, Jai Gopal Dhaka, vijaypal Singh verma, Sourabh Singh Malik, Arnav Manipal University Jaipur Jaipur303007 India Space Applications Centre ISRO Ahmedabad380015 India Jayshree Periwal Global School Jaipur302026 India

ISBN: (纸本)9789819769940

In our investigation, we present a thorough comparative examination of contemporary models aimed at generating descriptive narratives based on satellite image analysis, leveraging a fusion of methodologies such as computer vision (Cv), natural language processing (NLP), and machine learning (ML). Employing an array of cutting-edge neural network architectures including vGG-19, ResNet-50, DenseNet-201, EfficientNet B7, UNet, and Inception v3, we meticulously analyze intricate features within satellite images to extract essential patterns and information. These features are subsequently integrated into a Long Short-Term Memory (LSTM) network, a robust variant of Recurrent Neural Network (RNN), thereby enhancing our capacity to efficiently interpret and analyze satellite image data. Through exhaustive experimentation on established benchmark datasets such as the Sydney Dataset and RSIC Dataset, we conduct a comprehensive comparative analysis to assess the efficacy of diverse models. The notable advancements achieved by our model in the realm of satellite image captioning hold significant promise for practical applications in domains such as image interpretation. The observed milestones represent a substantive progression within the field, showcasing adaptable utility across diverse sectors. Particularly noteworthy is the superior performance attained through the pairing of EfficientNet B7 (ENet) with LSTM, yielding accuracy rates exceeding 90% across both the Sydney Dataset and RSIC Dataset. This underscores the effectiveness of synergizing ENet with LSTM architectures for satellite image captioning tasks, thereby emphasizing its potential for real-world deployment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Agry: a comprehensive framework for plant diseases classification via pretrained EfficientNet and convolutional neural networks for precision agriculture

引用

MULTIMEDIA TOOLS AND applications 2024年第24期83卷 64813-64851页

作者： Saleki, Sheida Tahmoresnezhad, Jafar Urmia Univ Technol Fac Informat Technol & Comp Engn Orumiyeh Iran

Diagnosing plant diseases is a vital issue in maintaining and developing of agricultural products. These diseases occur with changes in the tissue of different parts of plants. While the previous researches have only been conducted on certain species of plants and specific parts, we propose a comprehensive approach that has reached a high accuracy in diagnosing and classifying the disease of offending plant species by examining their different parts, including leaves, fruits, tree trunks, and seeds. We extract features from different layers of pre-trained AlexNet, ResNet50, vGG16, EfficientNetB0, EfficientNetB3 and EfficientNetB7 deep models with a spatial attention module to classify samples with an SvM classifier with RBF kernel. In order to automate the detection of plant diseases by manned or unmanned agricultural machines, our proposed Agry requires only 0.04089 seconds for image processing and decision making in real time. Also, due to the use of transfer learning, the cost of building the proposed model, including time and resources, is minimized. The results of the tests show a significant improvement compared to the previous works, and in most cases the classification is done without errors.

关键词： Precision agriculture Plant disease machine vision Deep learning Transfer learning Deep convolutional neural networks Pre-trained models

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：