检索结果-内蒙古大学图书馆

Accurate prediction of five-axis machining cycle times with deep neural networks using Bi-LSTM

CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY 2024年 48卷 28-41页

作者： Chien, Shih-Hsuan Sencer, Burak Ward, Rob Oregon State Univ Sch Mech Ind & Mfg Engn Corvallis OR 97331 USA Univ Sheffield Adv Mfg Res Ctr Rotherham S60 5TZ England Univ Sheffield Dept Automat Control & Syst Engn Sheffield S1 3JD England

This paper presents a novel machine learning (ML) based approach to predict machining cycle (part program running) times for complex 5-axis machining. Typical 5-axis machining toolpaths consist of short-segmented discrete linear cutter location lines (CL-lines) with simultaneously varying tool center point (TCP) and orientation vectors (ORI). As the 5-axis machine tool NC (numerical control) system tries to interpolate such part programs smoothly, the TCP motion decelerates and accelerates repeatedly causing the actual feedrate to fluctuate. The actual observed (resultant) feedrate can be approximately 30 % lower than the user commanded one. Furthermore, if the toolpath requires the 5-axis machine tool to travel closer to its singular point, or if the workpiece placement on the table is not optimal, actual feedrate is even lowered further. This paper presents two ML-based approaches to accurately predict 5-axis machining toolpaths. The first strategy uses a bidirectional long short-term memory (Bi-LSTM) network to model the machine tool behavior and generates a direct final cycle time estimation for any given part program. This approach only uses the toolpath geometry to predict the cycle time, and for training it only needs the "final" cycle times of similar part programs making it practical on today's shop floors. The second strategy requires individual CL-line processing times for training. In return, it can provide highly accurate cycle time predictions. Both strategies can capture the interpolation dynamics of 5-axis machine tool NC systems accurately. Simulation studies and experimental validations are conducted on modern 5-axis machine tools with varying workpiece placements and interpolation parameters. Proposed approaches have shown to predict cycle times with 90-95 % accuracy on real-life complex 5-axis machining toolpaths.

关键词： Cycle -time prediction 5 -Axis machining Machine learning

来源：评论

学校读者我要写书评

暂无评论

deep Cardiac MRI Reconstruction with ADMM 14th

Deep Cardiac MRI Reconstruction with ADMM

引用

14th International Workshop on Statistical Atlases and Computational Modelling of the Heart (STACOM)

作者： Yiasemis, George Moriakov, Nikita Sonke, Jan-Jakob Teuwen, Jonas Netherlands Canc Inst Amsterdam Netherlands Univ Amsterdam Amsterdam Netherlands Radboud Univ Nijmegen Med Ctr Nijmegen Netherlands

ISBN: (纸本)9783031524479;9783031524486

Cardiac magnetic resonance imaging (CMR) is a valuable non-invasive tool for identifying cardiovascular diseases. For instance, Cine MRI is the benchmark modality for assessing the cardiac function and anatomy. On the other hand, multi-contrast (T1 and T2) mapping has the potential to assess pathologies and abnormalities in the myocardium and interstitium. However, voluntary breath-holding and often arrhythmia, in combination with MRI's slow imaging speed, can lead to motion artifacts, hindering real-time acquisition image quality. Although performing accelerated acquisitions can facilitate dynamic imaging, it induces aliasing, causing low reconstructed image quality in Cine MRI and inaccurate T1 and T2 mapping estimation. In this work, inspired by related work in accelerated MRI reconstruction, we present a deep learning-based method for accelerated cine and multi-contrast reconstruction in the context of dynamic cardiac imaging. We formulate the reconstruction problem as a least squares regularized optimization task, and employ vSHARP, a state-of-the-art deep learning-based inverse problem solver, which incorporates half-quadratic variable splitting and the alternating direction method of multipliers (ADMM) with neural networks. We treat the problem in two setups;a 2D reconstruction and a 2D dynamic reconstruction task, and employ 2D and 3D deep learning networks, respectively. Our method optimizes in both the image and k-space domains, allowing for high reconstruction fidelity. Although the target data is undersampled with a Cartesian equispaced scheme, we train our deep neural network using both Cartesian and simulated non-Cartesian undersampling schemes to enhance generalization of the model to unseen data, a key ingredient of our method. Furthermore, our model adopts a deep neural network to learn and refine the sensitivity maps of multi-coil k-space data. Lastly, our method is jointly trained on both, undersampled cine and multi-contrast data.

关键词： Accelerated Cardiac MRI deep MRI Reconstruction Dynamic Cardiac MRI Reconstruction Cine Reconstruction T1-T2 Reconstruction

来源：评论

学校读者我要写书评

暂无评论

VISUAL QUESTION ANSWERING FOR WISHART H-ALPHA CLASSIFICATION OF POLARIMETRIC SAR imageS

VISUAL QUESTION ANSWERING FOR WISHART H-ALPHA CLASSIFICATION...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Aghababaei, Hossein Stein, Alfred Univ Twente Fac Geoinformat Sci & Earth Observat Enschede Netherlands

ISBN: (纸本)9798350360332;9798350360325

Polarimetric Synthetic Aperture Radar (PolSAR) images offer a rich repository of information, crucial for diverse applications ranging from classification to target identification. In the domain of PolSAR image classification, the Wishart classifier emerged as a prominent and widely employed technique. This classifier is often used to articulate the properties of polarimetric scattering types in images, providing valuable insight into various types of targets. With the growing interest in multidisciplinary Artificial Intelligence (AI) research, especially in computer vision and Natural Language processing (NLP), our goal is to integrate this enthusiasm into polarimetric image analysis. We propose extending the Wishart classifier framework to include a free-form and open-ended Visual Question Answering (VQA) model. This model is designed to answer natural language questions related to PolSAR images, covering pixel details and scattering patterns. The objective is to provide accurate natural language responses that reflect real-world scenarios, such as assisting the visually impaired. Both questions and answers in this context are intentionally left open-ended to capture the complexity of inquiries in the polarimetric SAR images domain.

关键词： Polarimetric SAR image Classification Visual Question Answering deep learning Natural Language Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

Efficient super-resolution of phase images encoded with random phase mask by machine learning techniques

引用

APPLIED OPTICS 2025年第7期64卷 B6-B12页

作者： Yamada, Yu Okamoto, Atsushi Tomita, Akihisa Hokkaido Univ Grad Sch Informat Sci & Technol N14 W9Kita Ku Sapporo 0600814 Japan

In the field of optics, a random phase mask (RPM) is used to efficiently encode and decode spatial complex amplitude distribution information of measurement targets into phase information. By encoding spatial complex amplitude distribution into a phase using an RPM, this distribution can be processed by modulating only the phase, which is efficient in computational terms. However, when encoding and decoding spatial complex amplitude distribution using an RPM, the resolution of optical devices such as a spatial light modulator (SLM) and charge-coupled device (CCD) becomes a bottleneck, resulting in decreased encoding and decoding accuracy. To address this issue, we propose a super-resolution method for phase images encoded with spatial complex amplitude distribution. This method uses a convolutional neural network (CNN) and a vision transformer (ViT), which are machine learning techniques widely used in computer vision. Through this super-resolution processing, we demonstrated that complex amplitude information can be encoded and decoded into phase images beyond the resolution of optical devices such as an SLM and CCD. Evaluation of the test images using peak signal-to-noise ratio (PSNR) showed improvements of 2.37 dB with the CNN and 1.86 dB with the ViT. Furthermore, we applied the proposed method to virtual phase conjugation based optical tomography (VPC-OT). The simulation results of measuring a microscopic target with a four-layer structure showed noise reduction at all depth positions and an improvement in the measurement accuracy of approximately 6-13 dB. (Details are shown in Fig. 7 and Table 2.) By applying the proposed method, measurement accuracy is improved with minimal computational operations, and without requiring additional optical systems or increasing the number of measurements. In addition, we examined the appropriate size of the machine learning model by observing the input image size (number of parameters) and loss progression. (c) 2024 Optica Pu

关键词： Confocal laser scanning microscopy Machine vision Neural networks Phase imaging real time imaging Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Control System with Ambulance Detection Using image processing

Smart Traffic Control System with Ambulance Detection Using ...

引用

2023 Intelligent Computing and Control for Engineering and Business Systems, ICCEBS 2023

作者： Nalini, M. Sandhya, S. Shiwani, S. Charumathi, S. Maharajothi, G. Sri Sairam Engineering College Dept of Electronics and Instrumenation Chennai India

ISBN: (纸本)9798350394580

In densely populated urban environments, the rapid and efficient passage of emergency vehicles, such as ambulances, is paramount to saving lives. This abstract introduces a cutting-edge approach to enhance traffic management and emergency response by leveraging image processing techniques for real-time ambulance detection and priority routing. The system we suggest consists of a network of sharp cameras placed at crucial crossroads and along major thoroughfares. These cameras record live video feeds of the traffic situation continuously. The video frames are processed using advanced computer vision algorithms, including object detection and tracking. Specifically, a deep neural network is employed to identify and track ambulance vehicles based on their unique visual characteristics, such as flashing lights, sirens, and distinctive vehicle markings. Upon ambulance detection, the system promptly triggers a series of actions to ensure swift and unimpeded passage. First, nearby traffic signals are dynamically adjusted to give the ambulance a green light, thereby expediting its route. Simultaneously, notifications are sent to connected vehicles via a dedicated communication network, advising them to make way for the approaching emergency vehicle. This communication can take various forms, such as in-car alerts, smartphone notifications, or even messages displayed on electronic road signs. To ensure the system's reliability and responsiveness, it operates in real-time, with minimal latency. Additionally, machine learning models are continuously trained and updated to improve ambulance detection accuracy, adapt to changing environmental conditions, and reduce false positives. By utilizing image processing and intelligent traffic management, our solution contributes to safer, more efficient urban transportation systems and ultimately plays a crucial role in saving lives during critical emergencies. © 2023 IEEE.

关键词： deep neural networks image processing Machine learning real time monitoring

来源：评论

学校读者我要写书评

暂无评论

FNBUI-NET: A multi-task model for fetal nasal bone ultrasound image defect detection and classification

引用

BIOMEDICAL SIGNAL processing AND CONTROL 2025年 104卷

作者： Li, Yapeng Liu, Zhonghua Zhang, Jiansong Zeng, Pan Fan, Yuling Feng, Longxiang Liu, Peizhong Lyu, Guorong Wu, Xiuming Huaqiao Univ Sch Med Quanzhou 362021 Peoples R China Fujian Med Univ Dept Ultrasound Quanzhou Hosp 1 Quanzhou 362000 Peoples R China Huaqiao Univ Coll Engn Quanzhou 362021 Peoples R China Quanzhou Med Coll Quanzhou 362011 Peoples R China Fujian Med Univ Affiliated Hosp 2 Dept Ultrasound Quanzhou 362000 Peoples R China

In prenatal ultrasound diagnosis, the accurate identification and timely assessment of the fetal nasal bone are crucial for monitoring the growth and development of the fetus's face. However, the small size and complex anatomy of the fetal nasal bone make it difficult for doctors to determine if there are any defects. Motivated by this critical and intricate ultrasound task, a multi-task deep learning model, FNBUI Network (FNBUI-NET), was designed to detect fetal nasal bone defects and classify fetal nasal bone ultrasound images (FNBUI) in real-time. The model reconsiders and balances the relationship between inference speed and computational accuracy in object detection algorithms, innovatively proposing the integration of the ShuffleNetV2 (Shuffle_Block) network with the Content-Aware ReAssembly of Features (CARAFE) module to process data tensors of varying sizes from clinical settings, and employed Coordinate Attention (CA) for feature compression encoding to extract consistency constraints within chaotic feature distributions. The FNBUI dataset is also proposed to support the research on fetal nasal bone detection and classification, which 1104 ultrasound images with three objects (i.e., normal, dysplasia, absence) of fetal nasal bones from 731 mid-pregnancy women for training and testing the performance of FNBUI-NET. The experiments show that FNBUI-NET can accurately classify fetal ultrasound images and detect nasal bone defects, achieving an mAP@0.5 of 0.985 in nasal bone detection and an accuracy of 0.981 in classification, outperforming 18 popular current methods. It provides a valuable tool for less experienced and younger sonologists, assisting them in the examination and diagnosis of fetal nasal bone defects.

关键词： Prenatal ultrasound diagnosis Fetal nasal bone ultrasound images Multi-task deep learning model Detect fetal nasal bone defect Classify

来源：评论

学校读者我要写书评

暂无评论

A conditional registration network for continuous 4D respiratory motion synthesis

引用

MEDICAL PHYSICS 2023年第7期50卷 4379-4387页

作者： Sang, Yudi Ruan, Dan Univ Calif Los Angeles Dept Bioengn Los Angeles CA USA Univ Calif Los Angeles Dept Radiat Oncol Los Angeles CA USA Univ Calif Los Angeles Los Angeles CA 90095 USA

BackgroundFour-dimensional computed tomography (4DCT) provides an important physiological information for diagnosis and treatment. On the other hand, its acquisition could be challenged by artifacts due to motion sorting/binning, time and effort bandwidth in image quality QA, and dose considerations. A 4D synthesis development would significantly augment the available data, addressing quality and consistency issues. Furthermore, the high-quality synthesis can serve as an essential backbone to establish a feasible physiological manifold to support online reconstruction, registration, and downstream analysis from real-time x-ray imaging. PurposeOur study aims to synthesize continuous 4D respiratory motion from two extreme respiration phases. MethodsA conditional image registration network is trained to take the end-inhalation (EI) and end-exhalation (EE) as input, and output arbitrary breathing phases by varying the conditional variable. A volume compensation and calibration post-processing is further introduced to improve intensity synthesis accuracy. The method was tested on 20 4DCT scans with a four-fold cross-testing scheme and compared against two linear scaling methods and an image translation network. ResultsOur method generated realistic 4D respiratory motion fields that were spatiotemporally smooth, achieving a root-mean-square error of (70.1 +/- 33.0) HU and structural similarity index of (0.926 +/- 0.044), compared to the ground-truth 4DCT. A 10-phase synthesis takes about 2.85 s. ConclusionsWe have presented a novel paradigm to synthesize continuous 4D respiratory motion from end-inhale and end-exhale image pair. By varying the conditional variable, the network can generate the motion field for an arbitrary intermediate breathing phase with precise control.

关键词： deep learning image registration image synthesis

来源：评论

学校读者我要写书评

暂无评论

Low-cost and precise traditional Chinese medicinal tree pest and disease monitoring using UAV RGB image only

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-23页

作者： Guo, Haoran Cheng, Yuhua Liu, Jun Wang, Zhihu Hunan Univ Chinese Med Sch Informat Changsha Peoples R China

Accurate and timely pest and disease monitoring during the cultivation process of traditional Chinese medicinal materials is crucial for ensuring optimal growth, increased yield, and enhanced content of effective components. This paper focuses on the essential requirements for pest and disease monitoring in a planting base of Cinnamomum Camphora var. Borneol (CCB) and presents a solution using unmanned aerial vehicle (UAV) images to address the limitations of real-time and on-site inspections. In contrast to existing solutions that rely on advanced sensors like multispectral or hyperspectral sensors mounted on UAVs, this paper utilizes visible light sensors directly. It introduces an ensemble learning approach for pest and disease monitoring of CCB trees based on RGB-derived vegetation indices and a combination of various machine learning algorithms. By leveraging the feature extraction capabilities of multiple algorithms such as RF, SVM, KNN, GBDT, XGBoost, GNB, and ELM, and incorporating morphological filtering post-processing and genetic algorithms to assign weights to each classifier for optimal weight combination, a novel ensemble learning strategy is proposed to significantly enhance the accuracy of pest and disease monitoring of CCB trees. Experimental results validate that the proposed method can achieve precise pest and disease monitoring with reduced training samples, exhibiting high generalization ability. It enables large-scale pest and disease monitoring at a low cost and high precision, thereby contributing to improved precision in the cultivation management of traditional Chinese medicinal materials.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal image Understanding and Audio Description System for the Visually Impaired People 10

A Multi-Modal Image Understanding and Audio Description Syst...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Preetham, Monisha Krishnan, Meena Monta Vista High School CA United States Cisco United States

ISBN: (纸本)9798350384369

A significant challenge in the field of computer vision is to develop algorithms that are capable of producing captions for images. Ensuring image accessibility is crucial for individuals who have visual impairments. Audio descriptions provide detailed explanations of displayed events, such as bodily movements and expressive gestures in the images. Producing top-notch audio reports necessitates a substantial amount of personal effort in generating descriptions. To overcome this barrier to accessibility, this paper developed a novel multi-modal system that examines the graphical elements of an image and produces audio. The proposed technique extracts the features from the images by applying the transfer learning strategy. The captions undergo pre-processing to generate the tokens. The attention mechanism-encoder-decoder model receives as inputs the tokens and the image features that have been extracted. The model undergoes testing to create captions for the images, and its performance is assessed using the Bilingual Evaluation Understudy (BLEU) score. The average score on the test dataset is 73.864. The produced captions are transformed into audio format to cater to individuals with visual impairments. The real-time implementation of this technology can provide significant benefits to visually impaired individuals, enabling them to comprehend and analyze visual information in real time. © 2024 IEEE.

关键词： Multicarrier modulation

来源：评论

学校读者我要写书评

暂无评论

Non-invasive method for the prediction of micronutrient deficiency using sequential learning techniques

引用

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION 2023年第6期11卷 2322-2332页

作者： Devi, T. Kalavathi Baluprithviraj, K. N. Mohan, M. Madhan Devi, S. Uma Sakthivel, P. Rajeshwari, P. Vinodha, B. Kongu Engn Coll Dept EIE Perundurai India VIT Univ Sch Nano Sci Chennai India Vellalar Coll Engn & Technol Dept EEE Erode India Inst Rd Transport Perundurai Med Coll Dept Pathol Erode India

Study data from World Health Organization indicate that 2.8% of the disease around the world is caused by micronutrient insufficiency due to improper consumption of a balanced diet. The micronutrient deficiency is detected from the individual's blood sample which is an invasive technique. Such techniques are quite in comfort for the persons and also painful. This proposed method involves the micronutrient deficiency identification using the non-invasive method of image processing. In this work, images of the anterior conjunctiva of eye, tongue and nail bed are used to detect the deficiency. Convolutional neural network models are used in the proposed deep learning model to extract the features of the parts of eye, nail and tongue. CNN-LSTM and CNN-GRU architectures are used to predict the deficiency in the images by extracting the features and perform the classification. A collection of 140 images were used as a dataset in this system. The real-time images are used to train the model, which is then validated with sample images for increased accuracy. The simulation of the CNN network with CNN-GRU has very low MSEs with 0.22%, results show that the proposed system achieved an accuracy of 99.6%, specificity of 99.7% and sensitivity of 99.4%.

关键词： sequential image processing vitamin iron micronutrient deficiency

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：