检索结果-内蒙古大学图书馆

IEEE SSD International Multi-Conference on systems, Signals and Devices

作者： Taher Slimi Ahlem Djeha Anouar Ben Khalifa Université de Jendouba Institut National des Technologies et des Sciences du Kef Le Kef Tunisie LATIS-Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d'Ingénieurs de Sousse Sousse Tunisie

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

The challenge of enhancing ultrasound images while retaining essential features is vital in the medical field. Speckle noise significantly degrades image quality and can obscure important details. In this paper, we propose a new enhancement approach that integrates a Non-Subsampled Shearlet Transform (NSST) with a denoising autoencoder. By leveraging the capabilities of NSST for multi-scale and directional decomposition, our method effectively separates fine anatomical features from speckle noise. Our approach results in substantial speckle reduction while preserving critical details, thus enhancing the visual quality of ultrasound images. Experimental evaluations reveal the effectiveness of the proposed method in noise suppression and feature preservation, measured through various performance metrics. This innovative strategy represents a significant advancement in ultrasound image processing, with potential benefits for clinical diagnostics.

关键词： Image quality Visualization Ultrasonic imaging Ultrasonic variables measurement Noise Noise reduction Autoencoders Speckle Feature extraction Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Feature Attribution Explanation for Explainable Machine Learning

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第1期4卷 1-32页

作者： Wang, Ziming Huang, Changwu Li, Yun Yao, Xin Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Departmentof Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Advanced Cognitive Technology Lab Huawei Technologies Co. Ltd Shanghai201206 China School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

The feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model's output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although various metrics have been proposed to evaluate the explanation quality, no single metric could capture different aspects of the explanations. Different conclusions might be drawn using different metrics. Moreover, during the processes of generating explanations, existing FAE methods either do not consider any evaluation metric or only consider the faithfulness of the explanation, failing to consider multiple metrics simultaneously. To address this issue, we formulate the problem of creating FAE explainable models as a multi-objective learning problem that considers multiple explanation quality metrics simultaneously. We first reveal conflicts between various explanation quality metrics, including faithfulness, sensitivity, and complexity. Then, we define the considered multi-objective explanation problem and propose a multi-objective feature attribution explanation (MOFAE) framework to address this newly defined problem. Subsequently, we instantiate the framework by simultaneously considering the explanation's faithfulness, sensitivity, and complexity. Experimental results comparing with six state-of-The-Art FAE methods on eight datasets demonstrate that our method can optimize multiple conflicting metrics simultaneously and can provide explanations with higher faithfulness, lower sensitivity, and lower complexity than the compared methods. Moreover, the results have shown that our method has better diversity, i.e., it provides various explanations that achieve different tradeoffs between multiple conflicting explanation quality metrics. Therefore, it can provide tailored explanations to different stakeholders based on their specific requirements. © 2024 Copyright held by the owner/author(s). Publication rights licensed

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Triplet Vision Transformer for Word Image Retrieval in Historical Arabic Documents

SSRN

引用

SSRN 2023年

作者： Fathallah, Abir El Yacoubi, Mounim A. Ben Amara, Najoua Essoukri Université de Sousse Institut Supérieur de l’Informatique et des Techniques de Communication LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Télécom SudParis Institut Polytechnique de Paris 19 place Marguerite Perey Palaiseau91120 France Université de Sousse Ecole Nationale d’Ingénieurs de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

Deep learning techniques have become increasingly popular for word retrieval in historical documents. Extracting relevant information and learning representations for the image retrieval task has been widely spread by convolutional neural network architectures. These architectures usually face issues in extracting discriminative features due to the high complexity of historical writings and the poor quality of these documents. In this paper, we propose a novel end-to-end based triplet transformer approach to perform the word retrieval task. The suggested approach consists of three steps. First, a pre-processing phase based on generative models is provided in order to enhance the visual quality of historical documents. Then, a transformer-based triplet loss is applied to construct an embedding space that represents features as embedding vectors. Finally, to achieve high matching accuracy, similarity distances are used to measure the similarity between embedding vectors. To the best of our knowledge, this work unprecedentedly introduces the first approach including the transformer as a triplet network for word spotting in historical documents. To highlight the utility of our proposed approach, we use three challenging databases: George Washington, HADARA80P and VML-HD. The proposed approach shows improved performance over contemporary technologies currently being used in the word spotting research field. We achieve the best performance in word spotting in historical documents compared to the latest state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Imaging Enhancement Using Denoising AutoEncoders

Ultrasound Imaging Enhancement Using Denoising AutoEncoders

引用

IEEE SSD International Multi-Conference on systems, Signals and Devices

作者： Taher Slimi Radhia Ferjaoui Anouar Ben Khalifa Université de Jendouba Institut National des Technologies et des Sciences du Kef Le Kef Tunisie LATIS- Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d'Ingeniéurs de Sousse Sousse Tunisie

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

In ultrasound imaging, speckle noise is acknowledged as a major challenge, affecting visual clarity and compromising diagnostic accuracy. This degradation can lead to erroneous clinical evaluations, highlighting the urgent need to enhance denoising techniques. Various solutions have been proposed to tackle this issue. Convolutional Neural Network-based Denoising AutoEncoders (CNN-DAE) aim to mitigate this issue. However, this strategy suffers from potential loss of intricate details, excessive smoothing of images, and limited ability to adapt to different noise characteristics. In this research, we propose a CNN based Edge Detection Denoising AutoEncoders (CNN-EDDA). The proposed approach focuses on speckle denoising and enhancing the contours of anatomical structures, providing sharper and more precise definitions. This clarity enables the algorithm to effectively denoise the image by identifying regions with abrupt variations, allowing for the distinction of important details from speckle noise. By clarifying the edges, we preserve essential image details while reducing noise. This synergy between filtering and edge detection is crucial for ensuring reliable, high-quality results, facilitating more effective clinical interpretation. Our proposed CNN-EDDA method was evaluated according to subjective visual analyses as well as objective measurements, demonstrating better results than current state-of-the-art methods, with optimal performance metrics.

关键词： Deep learning Visualization Ultrasonic imaging Image edge detection Noise reduction Noise Autoencoders Anatomical structure Speckle Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breast Ultrasound Diagnostics Using GANs and Guided Filtering

Enhancing Breast Ultrasound Diagnostics Using GANs and Guide...

引用

IEEE SSD International Multi-Conference on systems, Signals and Devices

作者： Taher Slimi Anouar BEN Khalifa Université de Jendouba Institut National des Technologies et des Sciences du Kef Le Kef Tunisie LATIS- Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d'Ingénieurs de Sousse Sousse Tunisie

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

In ultrasound imaging, speckle noise presents a significant challenge, undermining image clarity and the accuracy of diagnostic interpretations. To address this critical issue, We develop a new method for improving the quality of ultrasound images using a Denoising Generative Adversarial Network complemented by a Guided Filter (DNGAN-GF). This method uses a neural network architecture to learn how to generate denoised images from noisy inputs while preserving important anatomical contours and details. Our innovative approach effectively transforms noisy images into remarkably clear visual representations. The DNGAN learns to capture the characteristics of clean image data, while the GF refines the results, ensuring the fidelity of anatomical structures. Qualitative assessments conducted by experts highlight the exceptional sharpness of contours and anatomical features, making anomaly interpretation more intuitive and accessible. This improvement not only assists radiologists in their evaluations but also has the potential to reduce diagnostic errors. Quantitative analyses reveal substantial increases in PSNR and SSIM metrics, confirming the superiority of our proposed DNGAN-GF method compared to conventional techniques. By significantly enhancing the visibility of anatomical details, our proposed solution can improve diagnostic accuracy and redefine standards in medical imaging, ultimately elevating the quality of patient care.

关键词： Visualization Ultrasonic imaging Accuracy Noise Noise reduction Transforms Speckle Breast Generative adversarial networks Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Performance Assessment of Double Line HVAC Circuit versus Bipolar HVDC Link in Presence of Large-Scale Solar Plant

Performance Assessment of Double Line HVAC Circuit versus Bi...

引用

International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM)

作者： Sirine Essallah Israa Ismael Hussein Adel Khedher LATIS- Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d’Ingénieurs de Sousse Sousse Tunisie

ISBN: (纸本)9781665451697

This paper presents a comparative study between the bipolar HVDC link and the double line HVAC circuit in the presence of a 1000 MW solar generating unit. The influence of the penetration of renewable power on system losses, voltage and transient stability is investigated. The research is performed on the Iraqi super-grid considering three types of faults are examined namely the line and the bus disturbances, and the line trip. The simulations were carried out for different transmission line length using the PSS/E software. The results showed that the bipolar HVDC link presents better results compared to the double line HVAC circuit in terms of stability, voltage improvement and power losses minimization.

关键词： Renewable energy sources HVAC HVDC transmission Voltage Power system stability Stability analysis Circuit stability

来源：评论

学校读者我要写书评

暂无评论

Robust WTE Sensorless Design based on Soft-VSI structure for Three-Phase IM Drive using Sliding Mode Observer Controller

Robust WTE Sensorless Design based on Soft-VSI structure for...

引用

International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM)

作者： Intissar Moussa Mouna Zerzeri Adel Khedher Ecole Nationale d’Ingénieurs de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Sousse Tunisie Institut Supérieur de Transport et de la Logistique de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Sousse Tunisie

ISBN: (纸本)9781665451697

In this paper, a Sliding Mode Observer (SMO) for flux and then speed-sensorless of three-phase Induction Motor (IM) as robust Wind Turbine Emulator (WTE) design is investigated. A Soft-Voltage Source Inverter (VSI) structure, which is controlled by a specific Space Vector Modulation (SVM), is applied to drive the IM. Hence, appropriate three vectors which synthesize the desired output voltage are selected to allow the proposed system to react as a real turbine considering the wind velocity, static and dynamic behaviors, and parametric variations. Mathematical models of each system part are described to highlight electrical, mechanical, and electromagnetic relations. Simulation results confirm that the presented control method provides good flux and speed estimations despite rotor resistance and load torque variations in terms of trajectory tracking.

关键词： Induction motors Transducers Trajectory tracking Wind speed Rotors Observers Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

Analysis of coupled axial-torsional vibration of drill-string with an inclination angle 41

Analysis of coupled axial-torsional vibration of drill-strin...

引用

第41届中国控制会议

作者： Jiahao Zhang Chengda Lu Hengyu Huang Jun Gao Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education CCTEG Xi'an Research Institute

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Drill-string vibration has a great negative influence on the safety and efficiency of geological *** that the influence of drill-string inclination is not well considered in the literature,this paper develops a novel drill-string vibration model for geological drilling with inclined ***,the correlation between the inclination angle of borehole and the axial and torsional forces on the drill-string is *** on this,a drill-string motion model with the parameters of inclination angle is ***,the bit-rock interaction is considered as two processes,axial cutting and torsional friction,and an axial-torsional coupled bit-rock interaction model with state-dependent time delay is *** combining the established drill-string motion model and bit-rock interaction model,a coupled axial-torsional vibration model of drill-string in inclined borehole is obtained with the effect of borehole wall friction taken into *** drill-string vibration model proposed in this paper is more general,and includes the existing coupled drill-string vibration model of vertical borehole,which is closer to the actual situation.

关键词： drill-string vibration drill-string inclination bit-rock interaction

来源：评论

学校读者我要写书评

暂无评论

A Finite-Time Posture Control Strategy for the Swarm Underactuated Robots 5th

A Finite-Time Posture Control Strategy for the Swarm Under...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2021

作者： Huang, Zixin Qin, Xiangyu Wei, Shaoqi Wang, Lejun Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430205 China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan430200 China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9789811939976

Under the background of industrial machinery automation. The swarm robots are required to cooperate to complete complex and accurate works in finite-time and create more relative residual value. Based on the inherent advantages of underactuated robot, the research of finite time posture control strategy has higher theoretical and practical value. Firstly, the dynamic model of a single Pendubot of planar swarm underactuated robots was built. However, the robots reach to the same objective from different initial states and keep being at the same posture, so it was necessary to plan a feasible trajectory. Then, the planned trajectory parameters are optimized to make the underactuated robots relized the objectives in finite time. Finally, an unified tracking controller is designed for the underactuated robots. Simulation results of the swarm underactuated robots demonstrated the effectiveness of the proposed control strategy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Energy landscape decomposition for cell differentiation with proliferation effect

引用

National Science Review 2022年第8期9卷 144-152页

作者： Jifan Shi Kazuyuki Aihara Tiejun Li Luonan Chen Research Institute of Intelligent Complex Systems Fudan University International Research Center for Neurointelligence The University of Tokyo Institutes for Advanced Study The University of Tokyo Key Laboratory of Mathematics and Its Applications (LMAM) and School of Mathematical Sciences Peking University Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Key Laboratory of Systems Health Science of Zhejiang Province Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences School of Life Science and Technology Shanghai Tech University Guangdong Institute of Intelligence Science and Technology

Complex interactions between genes determine the development and differentiation of cells. We establish a landscape theory for cell differentiation with proliferation effect, in which the developmental process is modeled as a stochastic dynamical system with a birth-death term. We find that two different energy landscapes, denoted U and V, collectively contribute to the establishment of non-equilibrium steady differentiation. The potential U is known as the energy landscape leading to the steady distribution, whose metastable states stand for cell types, while V indicates the differentiation direction from pluripotent to differentiated cells. This interpretation of cell differentiation is different from the previous landscape theory without the proliferation effect. We propose feasible numerical methods and a mean-field approximation for constructing landscapes U and V. Successful applications to typical biological models demonstrate the energy landscape decomposition's validity and reveal biological insights into the considered processes.

关键词： energy landscape cell differentiation stochastic systems

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：