检索结果-内蒙古大学图书馆

Semi-supervised learning for real-time anomaly detection in pulsed transfer wire arc additive manufacturing

JOURNAL OF MANUFACTURING PROCESSES 2024年 128卷 84-97页

作者： Mattera, Giulio Polden, Joseph Caggiano, Alessandra Nele, Luigi Pan, Zengxi Norrish, John Univ Naples Federico II Dept Chem Mat & Ind Prod Engn Naples Italy Univ Wollongong Sch Mech Mat Mechatron & Biomed Engn Wollongong NSW Australia Univ Naples Federico II Fraunhofer Joint Lab Excellence Adv Prod Technol F Naples Italy Univ Naples Federico II Ctr Adv Metrol Technol Serv CeSMA Naples Italy

In Wire-Arc Additive Manufacturing (WAAM), ensuring the quality and integrity of components is of key importance and performing anomaly detection during production is an efficient strategy for preventing defects and maintaining an acceptable quality with lower costs compared to the development of complex supervised learning techniques. This paper presents an approach based on semi-supervised learning for real-time anomaly detection in the production of Inconel 718 components via the Pulsed Transfer WAAM process. The workflow is based on the use of training data obtained by employing established process parameters, similar to what is done in Welding Procedure Qualification Records (WPQRs), to develop a semi-supervised anomaly detection application. The proposed approach involves depositing material using the already established process parameters and collecting the corresponding welding data in terms of welding current and voltage sensor signals. The collected data are then employed to train an unsupervised algorithm by using solely good deposition data to learn hidden complex patterns of normality and hence detect anomalies based on deviations from these patterns. With this aim, global and local features are extracted from the welding current and voltage sensor signals in both time and time-frequency domains via Wavelet Transform technique and a deep learning approach based on a residual convolutional autoencoder. To showcase the effectiveness of the proposed approach, a case study involving wire arc additive manufacturing of Inconel 718 components was conducted. The proposed algorithm was tested and achieved an F-score of 0.895, representing a 30 % improvement over state-of-the-art methods that rely on time domain features for anomaly detection. This research work contributes to the improvement of anomaly detection methodologies, offering substantial advantages over alternative techniques for quality control and reliability of additive manufacturing processes such

关键词： Wire arc additive manufacturing Anomaly detection Machine learning Frequency domain image processing

来源：评论

学校读者我要写书评

暂无评论

FAKE CURRENCY DETECTION USING CONVOLUTIONAL NEURAL NETWORK AND image processing 15

FAKE CURRENCY DETECTION USING CONVOLUTIONAL NEURAL NETWORK A...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Srilatha, Boddu Ithvika, C.H. Meenakshi, Patil Pradhan, Sasmita Kumari Rani, K. Pushpa Jayanth, M. Department of Computer Science and Engineering MLR Institute of Technology Hyderabad500043 India Department of Computer Science and Engineering AVN Institute of Engineering and Technology Hyderabad500043 India Department of of CSE-CyS DS and AI&DS VNR VJIET Bachupally Hyderabad India

ISBN: (纸本)9798350370249

The increased use of modern printing and scanning technologies has led to a significant rise in counterfeit currency production, posing a serious threat to global economies. To tackle this growing issue, our project, titled "Fake currency detection using Convolutional Neural Networks and image processing," introduces an innovative solution that utilizes artificial intelligence (AI) and machine learning for efficient counterfeit detection. Financial institutions, banks, and businesses are facing heightened vulnerability to counterfeit currency, resulting in considerable financial losses and a decrease in the value of genuine money. Current currency detection systems often rely on time-consuming traditional methods and manual inspection, which are prone to human error. Even the counterfeit detection machines in use have limitations when it comes to identifying sophisticated counterfeit notes. Our project addresses these challenges by proposing an advanced system that integrates convolutional neural networks (CNNs) and image processing techniques. Given the advancements in printing and scanning technologies, counterfeiting has evolved into a more sophisticated and widespread problem. Traditional currency detection methods, rooted in hardware and image processing, have proven to be inefficient and time-consuming. Hence, there is a critical need for a more robust and rapid solution to detect counterfeit currency. Our proposed approach employs a transfer-learned CNN, a deep learning model trained on a dataset comprising real and fake currency images. The CNN learns the intricate features of both genuine and counterfeit banknotes, allowing it to accurately identify fake currency in real-time. The transfer learning process enables the CNN to leverage knowledge gained from a diverse dataset, improving its ability to recognize subtle patterns associated with counterfeit notes. The primary components of our project include a diverse dataset with images of real and fake currenc

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Patient-specific cerebral 3D vessel model reconstruction using deep learning

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2024年第10期62卷 3225-3232页

作者： Koizumi, Satoshi Kin, Taichi Shono, Naoyuki Kiyofuji, Satoshi Umekawa, Motoyuki Sato, Katsuya Saito, Nobuhito Univ Tokyo Hosp Dept Neurosurg 7-3-1 Bunkyo Ku Tokyo 1138655 Japan Univ Tokyo Grad Sch Med Dept Med Informat Engn Tokyo Japan

Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10 mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.

关键词： deep learning Medical image processing Magnetic resonance angiography Aneurysm Segmentation

来源：评论

学校读者我要写书评

暂无评论

Detection of False Data Injection Attacks in Distribution Networks: A Vertical Federated learning Approach

引用

IEEE TRANSACTIONS ON SMART GRID 2024年第6期15卷 5952-5964页

作者： Kesici, Mert Pal, Bikash Yang, Guangya Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Tech Univ Denmark Dept Wind & Energy Syst DK-2800 Kongens Lyngby Denmark

This paper proposes a collaborative learning framework based on vertical federated learning for detecting false data injection attacks in distribution networks. The proposed framework empowers entities that are responsible for a sub-network to collaboratively construct an FDIA detection model, effectively addressing issues associated with data sharing and enabling the utilization of various measurements from each sub-network. The proposed framework enables real-time collaboration between the server and the grid edge-side by allocating the two models created through the split learning approach applied to the proposed attention-based hybrid deep learning model. The grid edge-side is tasked with extracting spatial features, while the server is responsible for extracting temporal features from the data processed by the grid edge-side. The edge-side model is designed by adopting an attention module integrated into a deep learning model while the server-side model is designed based on the Bi-LSTM model. The effectiveness of the proposed framework is demonstrated on the IEEE 123 and IEEE 37 node test systems.

关键词： Feature extraction Distribution networks Data models Federated learning real-time systems Particle measurements image edge detection False data injection attack vertical federated learning cyber attack detection state estimation split learning

来源：评论

学校读者我要写书评

暂无评论

RT-SNDETR: real-time supernova detection via end-to-end image transformers

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2024年第1期534卷 726-737页

作者： Pan, Zhi-Ren Qiu, Bo Li, Guang-Wei Hebei Univ Technol Sch Elect & Informat Engn Tianjin 300401 Peoples R China Tianfu Yongxing Lab Chengdu 610213 Peoples R China Univ Sci & Technol Beijing Sch Intelligence Sci & Technol Beijing 100083 Peoples R China Natl Astron Observ CAS Key Lab Opt Astron Beijing 100101 Peoples R China

In large-scale astronomical surveys, traditional supernova detection pipelines rely on complex and relatively inefficient image differencing techniques. This paper proposes an end-to-end deep-learning supernova detection network, the real-time SuperNova DEtection TRansformer (RT-SNDETR). This network partially replaces traditional pipelines by integrating image differencing, source detection, and real-bogus classification, achieving a speed 51.49 times that of the fastest image differencing method, SFFT. Additionally, it remains competitive with methods like YOLO v8, offering a well-balanced trade-off between speed and accuracy. Experimental results highlight RT-SNDETR's superior performance, with an average precision(AP) of 96.30 per cent on synthetic samples and 76.60 per cent on real supernova samples. It significantly outperforms other detection networks, including RT-DETR (+5.6 per cent AP on synthetic/+5.1 per cent AP on real samples) and Cascade R-CNN (+8.9 per cent AP on synthetic/ +28.6 per cent AP on real samples). The incorporation of CycleGAN-based data generation methods plays a significant role in enhancing RT-SNDETR's performance. These methods simulate realistic PSF variations, enabling the object detection network to learn more robust features and improving its generalization to real supernovae data. Additionally, by integrating unsupervised domain adaptation techniques, RT-SNDETR achieves an AP of 81.70 per cent on real SDSS supernova survey samples. This study demonstrates RT-SNDETR's potential to significantly enhance both the speed and accuracy of supernova detection, making it a highly effective solution for large-scale astronomical surveys.

关键词： methods: data analysis techniques: image processing techniques: photometric transients: supernovae

来源：评论

学校读者我要写书评

暂无评论

A real-time Demonstrator for image Classification using FPGA-based Logic Neural Networks

A Real-time Demonstrator for Image Classification using FPGA...

引用

Conference on real-time processing of image, Depth, and Video Information

作者： Concha, David Garcia-Espinosa, Francisco J. Ramirez, Ivan Alberto Aranda, Luis Univ Rey Juan Carlos CAPO Res Grp Madrid 28933 Spain

ISBN: (纸本)9781510673199;9781510673182

real-time image processing is a key area of focus, but computationally intensive. Neural networks effectively address classification tasks, but they are not always a viable option, particularly in environments where high power consumption or computational requirements are limiting factors. Hardware devices such as Field-Programmable Gate Arrays (FPGAs) offer significant parallelization capabilities that can be fully exploited when the implemented circuit is composed solely of logic gates. In addition, FPGAs are also interesting alternatives to traditional GPU-based implementations in terms of power consumption and reconfiguration capabilities. They can be used as a demonstration platform to validate a hardware design that can be later manufactured, creating the final Application-Specific Integrated Circuit (ASIC). This paper introduces a practical demonstration platform based on an FPGA that highlights the great capabilities of logic neural networks, a type of neural network constructed exclusively with logic gates. By harnessing FPGA parallelization and logic gates, we have achieved a balance between computational power and real-time performance. This approach ensures that image classification occurs at speeds on the order of nanoseconds. This ultra-fast processing is well-suited for real-time image analysis applications across various domains. Industries that rely on quality control, such as manufacturing, will benefit from rapid and precise assessments. In the field of medical image processing, where quick diagnoses are crucial, this technology promises transformative advancements. The demonstration platform developed serves as a proof of concept for logic neural networks, offering a solution to the challenge of real-time image processing and representing the first step towards the implementation of future architectures of logic networks in hardware.

关键词： deep learning Field-Programmable Gate Array (FPGA) Logic Neural Network (LNN) real-time image Classification

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Apple Identification Method via the Collaboration of YOLOv5 Algorithm and Fast-Guided Filter Theory

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2024年第11期33卷 2450188-2450188页

作者： Zhang, Eryue Zhang, He Coll Mech & Elect Engn Henan Vocat Coll Appl Technol Zhengzhou 450000 Peoples R China Henan Coll Surveying & Maping Dept Surveying & Mapping Engn Zhengzhou 450000 Peoples R China

Apple-picking robot can promote the development of smart agriculture, and accurate object recognition in complex natural environments using deep learning algorithms is critical. However, research has shown that changes in illumination and object occlusion remain significant challenges for recognition. In order to improve the accuracy of apple apple-picking robot's identification and positioning of apples in natural environment, a method using YOLOv5 (You Only Look Once, YOLO) combined with fast-guided filter is proposed. By introducing a fast-guided filtering module, the ability to extract image features is improved, and the problem of inaccurate occlusion targets and edge detection is solved;K-means clustering algorithm is introduced in improving YOLOv5, which can realize automatic adjustment of image size and step size;BiFPN structure is introduced in Neck network to add weighted feature fusion to highlight the detailed features. The results show that the algorithm proposed in this paper can well remove noise information such as occlusion edge blurring in apple images in a natural light environment. In the real orchard environment, the apple recognition accuracy rate reached 97.8%, the recall rate was 97.3% and the recognition rate was about 26.84fps. The results show that this research based on YOLOv5 and fast-guided filtering can realize fast and accurate identification of apple fruits in natural environment, and meet the practical application requirements of real-time target detection.

关键词： Object recognition deep learning YOLOv5 fast-guided filter image processing

来源：评论

学校读者我要写书评

暂无评论

Hybrid-supervised deep learning for domain transfer 3D protoacoustic image reconstruction

引用

PHYSICS IN MEDICINE AND BIOLOGY 2024年第8期69卷 085007-085007页

作者： Lang, Yankun Jiang, Zhuoran Sun, Leshan Xiang, Liangzhong Ren, Lei Univ Maryland Dept Radiat Oncol Phys Baltimore MD 21201 USA Duke Univ Dept Radiat Oncol Durham NC 27710 USA Univ Calif Irvine Dept Biomed Engn & Radiol Irvine CA 92617 USA

Objective. Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which impairs its accuracy for dose verification. In this study, we developed a hybrid-supervised deep learning method for protoacoustic imaging to address the limited view issue. Approach. We proposed a Recon-Enhance two-stage deep learning method. In the Recon-stage, a transformer-based network was developed to reconstruct initial pressure maps from raw acoustic signals. The network is trained in a hybrid-supervised approach, where it is first trained using supervision by the iteratively reconstructed pressure map and then fine-tuned using transfer learning and self-supervision based on the data fidelity constraint. In the enhance-stage, a 3D U-net is applied to further enhance the image quality with supervision from the ground truth pressure map. The final protoacoustic images are then converted to dose for proton verification. Main results. The results evaluated on a dataset of 126 prostate cancer patients achieved an average root mean squared errors (RMSE) of 0.0292, and an average structural similarity index measure (SSIM) of 0.9618, out-performing related start-of-the-art methods. Qualitative results also demonstrated that our approach addressed the limit-view issue with more details reconstructed. Dose verification achieved an average RMSE of 0.018, and an average SSIM of 0.9891. Gamma index evaluation demonstrated a high agreement (94.7% and 95.7% for 1%/3 mm and 1%/5 mm) between the predicted and the ground truth dose maps. Notably, the processing time was reduced to 6 s, demonstrating its feasibility for online 3D dose verification for prostate proton therapy. Significance. Our study achieved start-of-the-art performance in the challenging task of direct reconstruction from radiofrequency signals, demonstrating the great promise of PA imaging as a high

关键词： proton therapy dose verification protoacoustic reconstruction self-supervised deep learning

来源：评论

学校读者我要写书评

暂无评论

IoT-based control and monitoring system for hydroponic plant growth using image processing and mobile applications

引用

PEERJ COMPUTER SCIENCE 2025年 11卷 e2763-e2763页

作者： Rofiansyah, Wizman Zalianty, Fayza Rizka La Ito, Firman Ahmad Wijayanto, Inung Ryanu, Harfan Hian Irawati, Indrarini Dyah Telkom Univ Sch Elect Engn Bandung West Java Indonesia Telkom Univ Sch Appl Sci Bandung West Java Indonesia

The HydroFarm project presents an innovative IoT-based control and monitoring system for hydroponic plant growth, integrating advanced image processing techniques and mobile applications to enhance urban farming practices. This system addresses critical challenges faced by urban farmers, such as limited space and the need for precise environmental management. By employing a comprehensive approach that combines various sensors (DHT22, DS18B20, pH, TDS) with an ESP32 microcontroller, HydroFarm enables real-time monitoring of essential parameters like temperature, humidity, pH, and nutrient levels. A significant novelty of this project lies in its use of a convolutional neural network (CNN) for plant health assessment through image processing. This technique allows for accurate detection of plant conditions, categorizing leaves as healthy or unhealthy based on visual data captured via a mobile application. The application, developed in Kotlin, not only facilitates user interaction but also provides automated and manual control over nutrient delivery systems based on real-time sensor data. Testing results indicate that the HydroFarm system achieves a high accuracy rate of 96% in detecting plant health conditions, with the sensors providing accurate and consistent data to maintain effective control over hydroponic parameters. The system usability scale (SUS) evaluation yielded an impressive score of 81.875, categorizing the application as excellent and user-friendly. Overall, HydroFarm represents a significant advancement in hydroponic farming technology by integrating IoT capabilities with deep learning for enhanced decision-making and operational efficiency in urban agriculture. The findings underscore the potential for scaling this model to improve food security and promote sustainable agricultural practices in densely populated areas.

关键词： Urban farming Hydroponics Controlling Monitoring Mobile applications image processing Internet of Things Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

real-time social distance monitoring and face mask detection based Social-Scaled-YOLOv4, deepSORT and DSFD&MobileNetv2 for COVID-19

引用

MULtimeDIA TOOLS AND APPLICATIONS 2024年第10期83卷 30613-30639页

作者： Mokeddem, Mohammed Lakhdar Belahcene, Mebarka Bourennane, Salah M Khider Univ RB IAIM LI3C Biskra Algeria Ecole Cent GSM Fresnel Inst Marseille France

COVID-19 has spread rapidly worldwide, despite the availability of vaccines, the fear of the World Health Organization continues due to the mutation of the Coronavirus. This is what prompted us to propose this work of social distance and wearing a face mask to fight against this pandemic to save lives. In this work, we propose a real-time four-stage model with monocular camera and deep learning based framework for automating the task of monitoring social distancing and face mask detection using video sequences. This work based on Scaled-You Only Look Once (Scaled-YOLOv4) object detection model, Simple Online and real-time Tracking with a deep association metric approach to tracking people. The perspective transformation is used to approximate the three-dimensional coordinates with Euclidean metric to compute distance between boxes. The Dual Shot Face Detector (DSFD) and MobileNetv2 face mask model used to detect faces of people who violate or cross the social distance. Accuracy of 56.2% and real-time performance of 32 frames per second are achieved by the Social-Scaled-YOLOv4 (Social-YOLOv4-P6) model trained on the MS COCO dataset and Google-Open-image dataset. The results are compared with other popular state-of-the-art models in terms of Mean-Average-Precision, frame rate and loss of values. The DSFD&MobileNetv2 facemask detectors trained on Wider Face and real Face mask dataset achieves an accuracy of 99.3%. The proposed approach is validated on indoor/outdoor public images and video sequences such as wider face dataset, Oxford Town Center dataset and open access sequences.

关键词： COVID-19 Detection and Localization deep learning Social Distancing Scaled-YOLOv4 Tracking

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：