检索结果-内蒙古大学图书馆

Retinal disorder diagnosis based on hybrid deep learning models

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Cerebral ischemia detection using deep learning techniques

引用

Health Information Science and systems 2025年第1期13卷 1-19页

作者： Pastor-Vargas, Rafael Antón-Munárriz, Cristina Haut, Juan M. Robles-Gómez, Antonio Paoletti, Mercedes E. Benítez-Andrades, José Alberto Communications and Control Systems Computer Engineering Science Faculty UNED Calle Juan del Rosal 16 Madrid 28040 Spain Radiology area Hospital Universitario de Navarra Navarra Spain School of Technology University of Extremadura Extremadura Cáceres Spain ALBA Research Group Department of Electric Systems and Automatics Engineering University of Leon Campus of Vegazana s/n Castilla y León León 24071 Spain

Cerebrovascular accident (CVA), commonly known as stroke, stands as a significant contributor to contemporary mortality and morbidity rates, often leading to lasting disabilities. Early identification is crucial in mitigating its impact and reducing mortality. Non-contrast computed tomography (NCCT) remains the primary diagnostic tool in stroke emergencies due to its speed, accessibility, and cost-effectiveness. NCCT enables the exclusion of hemorrhage and directs attention to ischemic causes resulting from arterial flow obstruction. Quantification of NCCT findings employs the Alberta Stroke Program Early Computed Tomography Score (ASPECTS), which evaluates affected brain structures. This study seeks to identify early alterations in NCCT density in patients with stroke symptoms using a binary classifier distinguishing NCCT scans with and without stroke. To achieve this, various well-known deep learning architectures, namely VGG3D, ResNet3D, and DenseNet3D, validated in the ImageNet challenges, are implemented with 3D images covering the entire brain volume. The training results of these networks are presented, wherein diverse parameters are examined for optimal performance. The DenseNet3D network emerges as the most effective model, attaining a training set accuracy of 98% and a test set accuracy of 95%. The aim is to alert medical professionals to potential stroke cases in their early stages based on NCCT findings displaying altered density patterns. © The Author(s) 2025.

关键词： Cerebral ischemia Computed tomography Deep learning Ictus dataset Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adaptive Filter for Head Tracking in Augmented Reality (AR)-based Flight Simulators

引用

IEEE Transactions on computers 2025年

作者： Nwobodo, Onyeka J. Kuaban, Godlove Suila Nkemeni, Valery Wereszczynski, Kamil Cyran, Krzysztof A. Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Polish Academy of Sciences Institute of Theoretical and Applied Informatics Poland University of Buea Laboratory of Electrical Engineering and Computing Faculty of Engineering and Technology Buea Cameroon

This paper presents a novel approach for head tracking in augmented reality (AR) flight simulators using an adaptive fusion of Kalman and particle filters. This fusion dynamically balances the strengths of both algorithms, leveraging Kalman filters for computational efficiency and particle filters for handling non-linearities based on real-time factors such as sensor noise and head movement patterns. Our method demonstrates superior tracking precision and reduced latency, making it particularly effective for immersive pilot training in AR-based flight simulations. While focused on flight simulation, our approach holds high potential for broader applications in other AR and virtual reality (VR) environments where precise, real-time head tracking is crucial. These results provide actionable design guidance for developers optimizing tracking systems in environments that require fast response times and high accuracy. Future extensions of this research could explore the generalization of our approach across diverse AR applications, including human-computer interaction (HCI), medical simulations, and gaming. © 1968-2012 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

Charging Load Prediction Method for Electric Vehicles using CNN-GRU-Attention model with SSA optimization strategy

Charging Load Prediction Method for Electric Vehicles using ...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Xinyu Fan Galaktion V. Shvedov Chuqiao Cai Electrical Power Systems Department National Research University “MPEI” Moscow Russian Federation Information Processing and Management Systems Department Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

This paper proposes a CNN-GRU-Attention model for short-term charging load prediction at electric vehicle (EV) charging stations. The model leverages the strengths of Convolutional Neural Networks (CNN) for feature extraction and dimensionality reduction, while Gated Recurrent Units (GRU) enhance temporal sequence learning. The attention mechanism assigns dynamic weights to the extracted features, improving the prediction accuracy. Hyperparameters are optimized using the Sparrow Search Algorithm (SSA), and an improved version, ISSA, further enhances model performance. Experimental results demonstrate that the CNN-GRU-Attention model outperforms baseline models, including CNN, GRU, LSTM (Long Short-Term Memory), and BiLSTM (Bidirectional Long Short-Term Memory), with higher prediction accuracy and fewer trainable parameters. The model's predictive capabilities enable optimization of power supply strategies in smart grids. However, it faces challenges in long-term load prediction and computational resource demands during hyperparameter optimization.

关键词： Adaptation models Accuracy Computational modeling Predictive models Hyperparameter optimization Feature extraction Smart grids Convolutional neural networks Optimization Load modeling

来源：评论

学校读者我要写书评

暂无评论

Impact of diameter on D-shaped POF sensors for salt detection

Impact of diameter on D-shaped POF sensors for salt detectio...

引用

International Laser Technology and Optics Symposium 2024, iLATOS2024

作者： Khan, Abdul Ali Thirunavakkarasu, Punithavathi M. bte Saidin, Norazlina Noor, Ahmad Shukri Muhammad Waqas, Nawaf Communication Technology Section Universiti Kuala Lumpur British Malaysian Institute Kuala lumpur53100 Malaysia Faculty of I.C.T BUITEMS Quetta87100 Pakistan Department of Electrical and Computer Engineering International Islamic University Malaysia Kuala Lumpur53100 Malaysia Department of Computer and Communication Systems Engineering Faculty of Engineering Universiti Putra Malaysia Selangor Malaysia Department of Instrumentation and Control Engineering Universiti Kuala Lumpur British Malaysian Institute Bt. 8 Jalan Sungai Pusu Selangor Gombak53100 Malaysia

This study investigates the relationship between the diameter of a D-shaped plastic optical fiber (POF) sensor and its optical response as a function of varying salt concentrations. A simple and efficient dry etching polishing technique was employed to create D-shaped POF sensors with a range of diameters. All the fabricated sensors were carefully developed to maintain a consistent length of 20 cm with a sensing region of 1cm. To evaluate the optical intensity response, each sensor, with its respective diameter, was examined with the salt concentration ranging from (0 to 5%) examination utilizing a spectrometer. The sensor response was characterized by quantifying the variations observed in the intensity of the optical signal propagating through the sensing region. The sensors having a diameter of 500 μm, 700 μm, and 900 μm had a sensitivity of 149 A.U/%salt, 66 A.U/%salt, and 11.2 A.U/%salt respectively. The sensitivity of the 500 μm diameter sensor increased 13 times approximately as compared to the sensor having diameter of 900 μm. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Dry etching

来源：评论

学校读者我要写书评

暂无评论

HFSA: hybrid feature selection approach to improve medical diagnostic system

引用

PeerJ computer Science 2025年 11卷 e2764-e2764页

作者： Rabie, Asmaa H. Aldawsari, Mohammed Saleh, Ahmed I. Saraya, M.S. Rashad, Metwally Computer and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Computer Engineering and Information Department College of Engineering in Wadi Alddawasir Prince Sattam Bin Abdulaziz University Al Kharj Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt

Thanks to the presence of artificial intelligence methods, the diagnosis of patients can be done quickly and accurately. This article introduces a new diagnostic system (DS) that includes three main layers called the rejection layer (RL), selection layer (SL), and diagnostic layer (DL) to accurately diagnose cases suffering from various diseases. In RL, outliers can be removed using the genetic algorithm (GA). At the same time, the best features can be selected by using a new feature selection method called the hybrid feature selection approach (HFSA) in SL. In the next step, the filtered data is passed to the naive Bayes (NB) classifier in DL to give accurate diagnoses. In this work, the main contribution is represented in introducing HFSA as a new selection approach that is composed of two main stages;fast stage (FS) and accurate stage (AS). In FS, chi-square, as a filtering methodology, is applied to quickly select the best features while Hybrid Optimization Algorithm (HOA), as a wrapper methodology, is applied in AS to accurately select features. It is concluded that HFSA is better than other selection methods based on experimental results because HFSA can enable three different classifiers called NB, K-nearest neighbors (KNN), and artificial neural network (ANN) to provide the maximum accuracy, precision, and recall values and the minimum error value. Additionally, experimental results proved that DS, including GA as an outlier rejection method, HFSA as feature selection, and NB as diagnostic mode, outperformed other diagnosis models. © (2025), (PeerJ Inc.). All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Energy-Based Trajectory Tracking for Underactuated Mechanical systems: Velocity-Free and Disturbance Rejection Methods

引用

International Journal of Robust and Nonlinear control 2025年

作者： Javanmardi, N. Borja, P. van der Schaft, A.J. Yazdanpanah, M.J. Scherpen, J.M.A. Jan C. Willems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen Groningen Netherlands Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Engineering Computing and Mathematics University of Plymouth Plymouth United Kingdom Jan C. Willems Center for Systems and Control Bernoulli Institute Faculty of Science and Engineering University of Groningen Groningen Netherlands

This work investigates three energy-shaping control approaches to address the trajectory-tracking problem for specific classes of underactuated mechanical systems. In particular, the notions of contractive systems and dynamic extensions are utilized to solve the trajectory-tracking problem while addressing implementation issues such as the lack of velocity sensors and the presence of constant disturbances. To this end, a first tracking controller is developed without the need for velocity measurements. A second controller is introduced, solving the trajectory-tracking problem while rejecting matched constant disturbances. Then, a third approach establishes conditions to combine both mentioned controllers. It is shown that the proposed design methods guarantee exponential convergence of closed-loop systems for specific classes of underactuated mechanical systems. The third method is illustrated with an example. © 2025 The Author(s). International Journal of Robust and Nonlinear control published by John Wiley & Sons Ltd.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Rational Gaussian wavelets and corresponding model driven neural networks

arXiv

引用

arXiv 2025年

作者： Ámon, Attila Miklós Fenech, Kristian Kovács, Péter Dózsa, Tamás Eötvös Loránd University Faculty of Informatics Department of Numerical Analysis Hungary Eötvös Loránd University Faculty of Informatics Department of Artificial Intelligence Hungary HUN-REN Institute for Computer Science and Control Systems and Control Laboratory Hungary University of Győr Hungary

In this paper we consider the continuous wavelet transform using Gaussian wavelets multiplied by an appropriate rational term. The zeros and poles of this rational modifier act as free parameters and their choice highly influences the shape of the mother wavelet. This allows the proposed construction to approximate signals with complex morphology using only a few wavelet coefficients. We show that the proposed rational Gaussian wavelets are admissible and provide numerical approximations of the wavelet coefficients using variable projection operators. In addition, we show how the proposed variable projection based rational Gaussian wavelet transform can be used in neural networks to obtain a highly interpretable feature learning layer. We demonstrate the effectiveness of the proposed scheme through a biomedical application, namely, the detection of ventricular ectopic beats (VEBs) in real ECG *** Codes 65D15 © 2025, CC BY.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Vehicle type recognition based on audio data 58

Vehicle type recognition based on audio data

引用

58th Hawaii International Conference on System Sciences, HICSS 2025

作者： Kobiela, Dariusz Hajdasz, Michał Erezman, Mateusz Nurzyńska, Karolina Zaporowski, Szymon Kurowski, Adam Weichbroth, Paweł Department of Software Engineering Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk 80-233 Poland Department of Multimedia Systems Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk 80-233 Poland Department of Algorithmics and Software Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice 44-100 Poland

ISBN: (纸本)9780998133188

Identifying different vehicle types can help manage traffic more efficiently, reduce congestion, and improve public safety. This study aims to create a classification model that can recognize vehicle types based on the sound of passing vehicles. To achieve this, a database of raw audio files containing 1763 samples from two sources was assembled. The time-domain signals were converted to a time-frequency representation using the short-time Fourier transform to generate Mel Spectrograms. Mel-frequency Cepstral Coefficients (MFCCs) were also generated using the discrete cosine transform. In our experiments we compared these approaches. Since the data was imbalanced we applied online augmentation. Based on the literature review, we chose a Convolutional Neural Network (CNN) classifier because it is particularly well suited for analyzing large datasets due to its automatic feature extraction, parameter sharing and sparsity. The results showed that Mel Spectrograms were more effective for audio data preprocessing in this particular use case, achieving the highest accuracy of 0.875 and the highest f1-score of 0.877 compared to MFCCs. © 2025 IEEE computer Society. All rights reserved.

关键词： acoustics mel-frequency cepstral coefficient mfcc sound spectrogram vehicle type detection vehicle type recognition

来源：评论

学校读者我要写书评

暂无评论

Bridging research gaps in breast cancer detection: An ensemble approach informed by bibliometric analysis

引用

Biomedical Signal Processing and control 2025年 109卷

作者： ZainEldin, Hanaa Bamaqa, Amna Farsi, Mohammed Badawy, Mahmoud Elhosseini, Mostafa A. Computers and Control Systems Engineering Department Mansoura University Faculty of Engineering Mansoura 35516 Egypt Department of Computer Science and Information Applied College Taibah University Madinah 42353 Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Yanbu 46421 Saudi Arabia

One of the leading causes of cancer-related death for women is still breast cancer, which highlights the importance of early and precise diagnosis techniques. Despite medical imaging and deep learning advances, current models fail to combine innovative object identification and classification methods, limiting their diagnostic performance. A bibliometric study of 1145 research articles identified key gaps, including the lack of integration between advanced object detection models like YOLOv9 and YOLOv10 with high-performance classification architectures such as EfficientNet B7, as well as the limited utilization of diverse imaging modalities. This study proposes a novel ensemble model for Breast Cancer Classification and Detection by combining YOLOv9, YOLOv10, and EfficientNet B7 (BC²D-Y/EN) to address these gaps. The proposed model combines the advanced object detection capabilities of YOLOv9 and YOLOv10 with the high-performance classification power of EfficientNet B7. This method aims to improve detection accuracy and computational efficiency in breast cancer identification. The proposed approach is validated using four publicly available datasets: CBIS-DDSM, CBIS-DDSM RGB breast cancer dataset, The Breast1 MRI dataset, and the Breast Ultrasound Tumor Object Detection dataset, all containing expert-annotated cases of benign and malignant tumors. The experimental findings indicate that the suggested model surpasses other models, achieving precision rates of 98.56% with EfficientNet B7, 98.3% with YOLOv9, and 100% with YOLOv9. These findings highlight the advantages of advanced models and diverse imaging methodologies to enhance diagnostic accuracy and effectiveness in breast cancer detection. © 2025 Elsevier Ltd

关键词： Breast cancer detection (BCD) Classification Deep learning (DL) EfficientNet B7 YOLOv10 YOLOv9

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：