检索结果-内蒙古大学图书馆

31st Symposium of Advanced Database Systems, SEBD 2023

作者： Ferraro, Antonino Galli, Antonio Gatta, Valerio La Moscato, Vincenzo Postiglione, Marco Sperlì, Giancarlo Moscato, Francesco Department of Electrical Engineering and Information Technology University of Naples Federico II Italy Department of Information Engineering Electrical Engineering and Applied Mathematics University of Salerno Italy

This paper represent an extended abstract of a recent proposal ([1]), in which the authors present a new methodology for unsupervised anomaly detection in predictive maintenance using sound data. In particular, the methodology leverages LSTM and CNN-based autoencoders to process continuous audio streams from different audio sources in real-world factories based on a customized sliding window. The novelties of the proposed approach include a general methodology for unsupervised anomaly detection, machine ID encoding using one-hot encoding, and conditioning an autoencoder by jointly analyzing the relationships between the mel-spectrogram and the machine ID to compute an anomaly score. The methodology achieves good performances in terms of effectiveness and in addition low inference time and memory requirements. © 2023 CEUR-WS. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Transfer learning in breast mass detection and classification

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第10期15卷 3587-3602页

作者： Ryspayeva, Marya Bria, Alessandro Marrocco, Claudio Tortorella, Francesco Molinara, Mario Department of Electrical and Information Engineering University of Cassino and Southern Lazio Viale dell’Università Cassino03043 Italy Department of Computer Engineering Astana IT University Mangilik El block C.1 Astana010000 Kazakhstan Department of Electrical Information Engineering and Applied Mathematics University of Salerno Via Giovanni Paolo II 132 Fisciano84084 Italy

Covid-19 infection influenced the screening test rate of breast cancer worldwide due to the quarantine measures, routine procedures reduction, and delay of early diagnosis, causing high mortality risk and severity of the disease. X-ray mammography is the gold standard for diagnosing early signs of breast cancer, and Artificial Intelligence enables the detection of suspicious lesions and classifying them in terms of malignancy. This paper aimed to investigate mass detection and classification in a large-scale OPTIMAM dataset with 6000 cases and extracted 3524 images with masses in the mammograms of the Hologic manufacturer. The methodology of the detection step is to train the RetinaNet architecture of ResNet50, ResNet101, and ResNet152 backbones with three types of initializations by ImageNet and COCO weights and from scratch. The dataset was pre-processed to generate two types of input with entire mammograms and patches, which are stated as the first and the second approaches. The results show that in the first approach, RetinaNet of ResNet50 backbone with ImageNet and COCO weights and ResNet152 with the same weights performed 0.91 True Positive Rate at 0.78 False Positive Per Image, respectively. In contrast, in the second approach, ResNet152 with ImageNet weights reached 0.88 TPR at 0.78 FPPI. In the classification step, the Transfer Learning approach was applied with fine-tuning by adding L2-regularization and class weights to balance class distribution in the datasets. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Translation of a sphere towards a rigid plane in an Oldroyd-B fluid

引用

Physical Review Fluids 2024年第8期9卷 083303页

作者： Tachin Ruangkriengsin Rodolfo Brandão Bimalendu Mahapatra Evgeniy Boyko Howard A. Stone Program in Applied and Computational Mathematics Department of Mechanical and Aerospace Engineering Faculty of Mechanical Engineering

We analyze the low-Reynolds-number translation of a sphere towards or away from a rigid plane in an Oldroyd-B fluid under two scenarios: prescribing the sphere's translational velocity, and prescribing the force on the sphere. Leveraging the lubrication approximation and a perturbation expansion in powers of the Deborah number, we develop a comprehensive theoretical analysis that yields analytical approximations for velocity fields, pressures, and forces acting on the sphere. Our framework aids in understanding temporal microstructural changes as the particle-wall gap evolves over time. In particular, we show that alterations in the polymer conformation tensor in response to geometric changes induce additional forces on the sphere. For cases with prescribed velocity, we present a theoretical approach for calculating resistive forces at any order in the Deborah number and utilize a reciprocal theorem to obtain higher-order corrections based on velocity fields in the previous orders. When the sphere translates with a constant velocity, the fluid viscoelasticity decreases the resistive force at the first order. However, at the second-order correction, the direction of the sphere's movement determines whether viscoelasticity increases or decreases the resistive force. For cases with prescribed force, we show that understanding the influence of viscoelasticity on the sphere's translational velocity necessitates a more intricate analysis even at low Deborah numbers. Specifically, we introduce an ansatz for constant force scenarios, and we derive solution forms for general prescribed forces using the method of multiple scales. We find that when a sphere undergoes sedimentation due to its own weight, the fluid viscoelasticity results in a slower settling process, reducing the leading-order sedimentation rate.

关键词： Complex fluids Low Reynolds number flows Lubrication theory Polymer conformation changes Rheology

来源：评论

学校读者我要写书评

暂无评论

UAV longitudinal autopilot design using SLC and TECS controllers

引用

CEAS Aeronautical Journal 2024年第2期15卷 351-362页

作者： Ghelem, Nourddine Boudana, Djamel Bouchhida, Ouahid Laboratory of Process Control LCP Department of Engineering Control Systems and Applied Mathematics National Polytechnic School ENP of Algiers 10 St Hacen Badi El Harrach Algiers Algeria Department of Electrical Engineering LREA Laboratory University of Medea Medea Algeria

UAVs are becoming increasingly prevalent in a wide range of fields, including surveillance, photography, agriculture, transportation, and communications. Hence, research institutions have developed a range of linear and non-linear controllers that can enhance the stability and efficiency of these UAVs while performing their assigned tasks. In this paper, we present a longitudinal autopilot design for the Sky Sailor solar UAV using two different control techniques. The first technique is a classic controller known as SLC (Successive Loop Closure), which is based on consecutive closed loops using a PID controller. The second technique is the TECS (Total Energy Control System) controller, which uses the specified total energy rate and energy distribution rate to regulate the airspeed and altitude of the UAV. After detailing the working principle of each controller and calculating the tuning parameters for each one, we applied the two techniques to the non-linear model that describes the behavior of the Sky Sailor UAV using MATLAB Simulink. The simulation results showed that the TECS controller is superior to the SLC controller in terms of stability and energy efficiency. As such, this technique is an excellent choice for solar drones, as it can increase their endurance. © Deutsches Zentrum für Luft- und Raumfahrt e.V. 2024.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Integrating local binary patterns and convolutional neural networks with a balanced gray encoded pooling mechanism

引用

Multimedia Tools and Applications 2025年 1-27页

作者： Lai, Cheng-Ling Tseng, Ling-Shen Chang, Chih-Hung Chen, Yi-Han Wu, Chih-Hung Department of Electrical Engineering National University of Kaohsiung 700 Kaohsiung University Rd Nanzih District Kaohsiung81148 Taiwan Department of Applied Mathematics National University of Kaohsiung 700 Kaohsiung University RdNanzih District Kaohsiung81148 Taiwan

Local binary pattern (LBP) is a commonly adopted method for texture description in image analysis applications. However, when used in deep convolutional neural networks (CNNs), standard LBP often fails to retain crucial feature uniformity and diversity during dimensionality reduction, which limits its effectiveness in complex image classification tasks. To address these issues, a novel LBP encoding method utilizing balanced Gray code (BGC) is introduced. In this method, similar LBP features are re-ordered as neighbors to maximally preserve feature integrity and diversity through the pooling process. This approach improves the compatibility of LBP with CNN architectures, enhancing both accuracy and robustness. An efficient algorithm is designed that integrates BGC transformation, LBP counting, and sum pooling for dimensionality reduction without sacrificing key feature characteristics. Several LBP-embedded network architectures based on ResNet have been developed and tested, demonstrating significant performance improvements in the proposed method. The experimental results reveal that our proposed method outperforms typical CNN models with a 15% accuracy improvement for classifying the STL-10 benchmark images. Additionally, our proposed method demonstrates greater robustness to illumination variations, highlighting the potential of this method for enhanced feature representation in deep learning. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Detecting Persian Signatures in Realistic Images using the YOLO Algorithm 20

Detecting Persian Signatures in Realistic Images using the Y...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Jafarian, Shiva Shabaninia, Elham Nezamabadi-Pour, Hossein Shahid Bahonar University of Kerman Department of Electrical Engineering Kerman Iran Graduate University of Advanced Technology Department of Applied Mathematics Kerman Iran

ISBN: (纸本)9798350383942

While crucial for document forensics and security, detecting Persian signatures in real-world scenarios poses a considerable challenge due to the distinctive features of Persian signatures - characterized by complex combinations of shapes and letters instead of conventional names - along with issues like noise, cluttered backgrounds, and more. Furthermore, the scarcity of annotated datasets complicates signature detection in natural settings. This paper addresses these challenges by introducing a new dataset for Persian documents, merging publicly available signatures with diverse backgrounds to create semi-realistic images reflecting real-world conditions. Additionally, the proposed method leverages the YOLOv5 architecture for signature detection. The experimental findings illustrate that, under various lighting conditions, background complexities, and signature distortions, this approach effectively and accurately detects Persian signatures. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Enhancing Farsi Text Recognition via Iteratively Using a Language Model 20

Enhancing Farsi Text Recognition via Iteratively Using a Lan...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Afkari-Fahandari, Ali Asadi-Zeydabadi, Fatemeh Shabaninia, Elham Nezamabadi-Pour, Hossein Shahid Bahonar University of Kerman Department of Electrical Engineering Kerman Iran Graduate University of Advanced Technology Department of Applied Mathematics Kerman Iran

ISBN: (纸本)9798350383942

In the present era, there is a growing demand for a reliable Farsi text recognition system, that addresses the needs of both industrial and individual users. The process of text recognition is typically accompanied by a subsequent post-processing step, which aims to tailor the text to specific language constraints. However, the iterative use of post-correction offers valuable insights for enhancing the precision of the recognized text. Meanwhile, building upon the recent successes of Transformer-based approaches in natural language processing and computer vision, we propose a Farsi text recognition model. This model seamlessly integrates a decoupled convolutional Transformer-based vision model for initial predictions and a Transformer-based language model for refining the obtained predictions. Evaluation of well-known Farsi OCR datasets, including Iranshahr, Sadri, and Shotor, demonstrates the model's superior performance, surpassing existing literature with recognition accuracies of 97.59%, 99.25%, and 99.97% on Iranshahr, Sadri, and Shotor datasets, respectively. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Farsi Handwritten Text Recognition via a Lightweight Attention-Driven Sequence Recognition Network 19

Farsi Handwritten Text Recognition via a Lightweight Attenti...

引用

19th Iranian Conference on Intelligent Systems, ICIS 2024

ISBN: (纸本)9798331507565

In today's digital age, there's a growing demand for a dependable system that can recognize handwritten text. This demand comes from various industries as well as individual users, highlighting the importance of a system that can quickly convert, store, and enhance the accessibility of handwritten documents. Encoder-decoder models have proven their effectiveness in various sequence learning tasks, such as machine translation, image captioning, action recognition, and optical character recognition. However, these models have encountered difficulties in achieving competitive results in the specific context of Farsi handwritten text recognition. This paper introduces an innovative lightweight attention-driven encoder-decoder model designed to address the challenges associated with Farsi handwritten text recognition. To evaluate the proposed model, two well-known Farsi handwritten text datasets, Sadri and Iranshahr, are utilized. Additionally, to potentially enhance recognition accuracy, two different convolutional backbones-ResNet34 and MobileNetV3-Are explored. Through experimental analysis, our best-performing model surpasses existing CNN-based and CRNN-based methods, achieving recognition accuracies of 94.79% on the Iranshahr dataset and 98.99% on the Sadri dataset. Additionally, our model offers faster inference speeds and a lower computational burden compared to recent Transformer-based approaches. These results demonstrate the effectiveness of our attention-driven encoder-decoder model in addressing the challenges of lightweight Farsi handwritten text recognition. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Retinal Blood Vessel Tracking and Diameter Estimation via Gaussian Process With Rider Optimization Algorithm

引用

IEEE Journal of Biomedical and Health Informatics 2024年第3期28卷 1173-1184页

作者： Ahmad, Nehal Lai, Kuan-Ting Tanveer, M. Indian Institute of Technology Indore Simrol Department of Mathematics Indore453552 India National Taipei University of Technology Department of International Program of Electrical Engineering and Computer Science Taipei106 Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei106 Taiwan

Retinal blood vessels structure analysis is an important step in the detection of ocular diseases such as diabetic retinopathy and retinopathy of prematurity. Accurate tracking and estimation of retinal blood vessels in terms of their diameter remains a major challenge in retinal structure analysis. In this research, we develop a rider-based Gaussian approach for accurate tracking and diameter estimation of retinal blood vessels. The diameter and curvature of the blood vessel are assumed as the Gaussian processes. The features are determined for training the Gaussian process using Radon transform. The kernel hyperparameter of Gaussian processes is optimized using Rider Optimization Algorithm for evaluating the direction of the vessel. Multiple Gaussian processes are used for detecting the bifurcations and the difference in the prediction direction is quantified. The performance of the proposed Rider-based Gaussian process is evaluated with mean and standard deviation. Our method achieved high performance with the standard deviation of 0.2499 and mean average of 0.0147, which outperformed the state-of-the-art method by 6.32%. Although the proposed model outperformed the state-of-the-art method in normal blood vessels, in future research, one can include tortuous blood vessels of different retinopathy patients, which would be more challenging due to large angle variations. We used Rider-based Gaussian process for tracking blood vessels to obtain the diameter of retinal blood vessels, and the method performed well on the 'STrutred Analysis of the REtina (STARE) Database' accessed on Oct. 2020 (https://***/~ahoover/stare/). To the best of our knowledge, this experiment is one of the most recent analysis using this type of algorithm. © 2013 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

A roulette wheel-based pruning method to simplify cumbersome deep neural networks

引用

Neural Computing and Applications 2024年第22期36卷 13915-13933页

作者： Chan, Kit Yan Yiu, Ka Fai Cedric Guo, Shan Jiang, Huimin School of Electrical Engineering Computing and Mathematics Sciences Curtin University Bentley Australia Department of Applied Maths The Hong Kong Polytechnic University Hong Kong School of Business Macau University of Science and Technology China

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept;large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches. © The Author(s) 2024.

关键词： Deep neural networks

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：