检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and communication Networks (CICN)

作者： Turja Bhattacharhee Syed Ali Hussain Pradyut Kumar Sanki Pranab Mandol Dept. of Computer Science And Engineering SRM University Guntur AP India Dept. of Electronics and Communication Engineering SRM University Guntur AP India Dept. of Physics SRM University Guntur AP India

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

This extensive research delves into the intersection of MRI imaging and deep learning, in the task of identifying and categorizing brain tumors. In addition to models like VGG16 and ResNet101 a designed Convolutional Neural Network (CNN) was developed and thoroughly evaluated showcasing a range of techniques utilized. Augmentation methods were purposefully applied to enrich the dataset, enhancing the models' robustness and adaptability. Evaluation metrics, including the F1 score, recall, accuracy, and precision gave a general picture of the model's performance. Furthermore, leveraging Explainable AI (XAI) techniques such as LIME unveiled insights, into the decision-making processes underlying the models enhancing their interpretability and trustworthiness. The study findings ultimately underscore the potential of learning in revolutionizing automated brain tumor diagnosis and classification poised to enhance patient care pathways and medical diagnostic capabilities significantly. Index Terms-MRI image, deep learning, VGG16, ResNET101, CNN, LIME

关键词： Deep learning Adaptation models Magnetic resonance imaging Computational modeling Brain tumors Brain modeling Robustness Convolutional neural networks Medical diagnosis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Equilibrium Models Meet Federated Learning

Deep Equilibrium Models Meet Federated Learning

引用

European Signal Processing Conference (EUSIPCO)

作者： Alexandros Gkillas Dimitris Ampeliotis Kostas Berberidis Dept. of Computer Engineering and Informatics University of Patras Greece Dept. of Digital Media and Communication Ionian University Greece

In this study the problem of Federated Learning (FL) is explored under a new perspective by utilizing the Deep Equilibrium (DEQ) models instead of conventional deep learning networks. We claim that incorporating DEQ models into the federated learning framework naturally addresses several open problems in FL, such as the communication overhead due to the sharing large models and the ability to incorporate heterogeneous edge devices with significantly different computation capabilities. Additionally, a weighted average fusion rule is proposed at the server-side of the FL framework to account for the different qualities of models from heterogeneous edge devices. To the best of our knowledge, this study is the first to establish a connection between DEQ models and federated learning, contributing to the development of an efficient and effective FL framework. Finally, promising initial experimental results are presented, demonstrating the potential of this approach in addressing challenges of FL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Ensemble Learning Approach to Predict Eye Diseases from OCT Images

A Novel Deep Ensemble Learning Approach to Predict Eye Disea...

引用

Sustainable Technologies for Industry 4.0 (STI), International Conference on

作者： Nazim Uddin Md Sajib Mia Mohammed Nasir Uddin Prince Mahmud Dept. of Information and Communication Technology Chandpur Science and Technology University Bangladesh Dept. of Computer Science and Engineering Sylhet Engineering College Bangladesh Dept. of Computer Science and Engineering Jagannath University Bangladesh Dept. of Computer Science and Engineering Chandpur Science and Technology University Bangladesh

As the world advances in technology, the classification of eye diseases is thought to have clinical applications since it evaluates and analyzes the results. Optometrists research and diagnose age-related eye problems such as Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and Drusen using optical coherence tomography (OCT) of the human eye. Because their symptoms are similar, identifying these diseases is challenging and requires hours of expert analysis. The requirements for eye illness classification should be straightforward in nature, structure, and evaluation. Deep Learning Convolutional Neural Network Classification can create a hierarchical representation of images to differentiate between normal and diseased eye patterns for diagnostic purposes. Therefore, this paper aims to implement and define deep learning to classify and identify eye diseases. Using a four-class classification problem, this work investigates the automatic detection of Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Drusen, and Normal in Optical Coherence Tomography (OCT) pictures. Multi-transfer learning architecture was used in the suggested deep learning Ensemble classification model. The most incredible accuracy of our proposed Ensemble model for multi- class classification was 83%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Hybrid Algorithm for Smooth AUV Path Generation

An Intelligent Hybrid Algorithm for Smooth AUV Path Generati...

引用

Industrial Electronics: Developments & Applications (ICIDeA), IEEE International Conference on-

作者： Paramjeet Singh Bhaskar Jyoti Talukdar Rudra Narayan Dash Bikramaditya Das Dept. of Computer Science and Engineering BPUT Rourkela Odisha India Dept. of Electronics and Telecommunication Engineering VSSUT Burla Odisha India School of Electrical Engineering KIIT Deemed to be University Bhubaneswar India Dept. of Electronics and Communication Engineering BPUT Rourkela Odisha India

ISBN: (数字)9798331533205

ISBN: (纸本)9798331533212

The development of effective multi-objective optimization strategies for Autonomous Underwater Vehicles (AUVs) operating in uncharted territories constitutes a considerable challenge. This endeavor necessitates the simultaneous minimization of travel time, reduction of path length, enhancement of navigational safety, and smoothing of trajectories. In light of these challenges, this research presents an innovative real-time path planning framework that seamlessly integrates Particle Swarm Optimization (PSO) with Simulated Annealing (SA), thereby enhancing AUV navigation within static environments. The PSO algorithm is utilized to generate optimal temporary waypoints across the scenarios examined, by balancing the crucial optimization parameters. Subsequently, an optimal path is formulated, informed by both the initial and terminal points. The efficacy of the proposed methodology is assessed through simulations conducted across three distinct maps. Each obstacle map demonstrates varying densities of obstacles. The outcomes of these simulations emphasize the robustness and adaptability of the proposed strategy, highlighting its ability to formulate optimal paths within complex underwater environments, irrespective of the arrangement of obstacles. The AUVs display remarkable agility in maneuvering through intricate underwater landscapes, adept.y avoiding debris and obstacles while preserving operational efficiency. This enhanced path planning technique not only elevates the responsiveness of the AUVs during critical missions—such as search and rescue operations and structural assessments—but also significantly bolsters their overall navigational safety. Through this research, we introduce a formidable tool for enhancing AUV capabilities in practical applications, ultimately facilitating more efficient underwater exploration and intervention.

关键词： Adaptation models Smoothing methods Navigation Simulation Urban areas Simulated annealing Trajectory Scattering parameters Collision avoidance Optimization

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Technology in Peruvian Higher Education: Influence of University Tenure 13

Virtual Reality Technology in Peruvian Higher Education: Inf...

引用

13th International Conference on Virtual Campus, JICV 2023

作者： Vergara-Rodriguez, Diego Solis, Ronald Melgarejo Anton-Sancho, Alvaro Depaz, Carlos Edmundo Navarro Fernandez-Arias, Pablo Samala, Agariadne Dwinggo Ávila Spain Web Digital School University Department of Virtual Education Lima Peru San Marcos University Dept. System Engineering and Computer Science Lima Peru Universitas Negeri Padang Facuity of Engineering West Sumatera Padang Indonesia

ISBN: (纸本)9798350343441

The use of virtual reality (VR) technologies in higher education has been growing in recent years due to their didactic potential in the most diverse areas of knowledge. However, the implementation of VR in universities is affected by several factors, including the level of digitization of the country or the tenure, private or public, of the universities. In this paper, a quantitative, descriptive and correlational research is carried out on the assessments of a group of professors in Peru about the use of VR in their lectures and on the differences in these perceptions according to the tenure of the university of the participants. For this purpose, a validated questionnaire was used, and its responses were statistically analyzed. The results reveal that professors express high ratings for the use of VR but show insufficient levels of digital skills for its use. In addition, professors from private universities give higher ratings of the didactic and usability aspects of VR. It is suggested that VR equipment and faculty training should be strengthened. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Deep Equilibrium Models Meet Federated Learning

arXiv

引用

arXiv 2023年

作者： Gkillas, Alexandros Ampeliotis, Dimitris Berberidis, Kostas Dept. of Computer Engineering and Informatics University of Patras Greece Dept. of Digital Media and Communication Ionian University Greece

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential: ML vs. DL in Network Security with Explainable AI (XAI) Insights

Exploring the Potential: ML vs. DL in Network Security with ...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Md. Tohidul Islam Md. Khalid Syfullah Jabbarul Islam H.M. Sazzad Quadir Md. Golam Rashed Dipankar Das Dept. of Information and Communication Engineering University of Rajshahi Rajshahi Bangladesh Dept. of Electrical and Computer Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh

The increasing complexity and diversity of cyber threats have driven the widespread adoption of Machine Learning (ML) and Deep Learning (DL) techniques for Network Intrusion Detection systems (NIDSs) due to their capacity to effectively adapt and detect evolving threats. However, the inherent black-box nature of ML and DL-powered NIDSs has raised concerns surrounding explainability, transparency, and interpretability. This challenge has led to a prevailing sense of distrust in these systems. In this paper, we propose an improved Network Intrusion Detection system (NIDS) and introduce a ML and a DL-based classifier to detect malicious network traffics. To overcome the explainibility and trust issues, we innovatively integrate advanced Explainable Artificial Intelligence (XAI) techniques, such as SHAP, LIME, and ELI5, with our proposed ML and DL classifiers. These techniques provide vital insights and detailed explanations behind the decision-making processes of the NIDS. This approach is pivotal for multiple reasons, including ensuring that the classifiers are fair and unbiased, articulating the rationale behind their outcomes, or for debugging the models when they make mistakes. Furthermore, we evaluate and compare the performance of ML and DL classifiers using a variety of metrics such as Accuracy, Precision, Recall, F1-score, ROC AUC curve, PR AUC, Training time, Confusion matrix, and also compare the explainability the classifiers. The need to compare ML and DL-based classifiers stems from the aim to optimize network security measures, improve threat detection, ensure that resources are used efficiently in the face of evolving cyber threats, and understanding the differences in their decision-making processes. In this study, the ML Classifier (Accuracy 94.5%) outperformed the DL Classifier (Accuracy 93.5%).

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid APF Approach for Obstacle Avoidance in a 3D Environment

A Hybrid APF Approach for Obstacle Avoidance in a 3D Environ...

引用

Industrial Electronics: Developments & Applications (ICIDeA), IEEE International Conference on-

作者： Amrita Saini Bhaskar Jyoti Talukdar Rudra Narayan Dash D Chandrasekhar Rao Bikramaditya Das Dept. of Computer Science and Engineering BPUT Rourkela Odisha India Dept. of Electronics and Telecommunication Engineering VSSUT Burla Odisha India School of Electrical Engineering KIIT Deemed to be University Bhubaneswar India Dept. of Electronics and Communication Engineering BPUT Rourkela Odisha India

ISBN: (数字)9798331533205

ISBN: (纸本)9798331533212

This study's main objective is to look at strategies, for avoiding underwater collisions and planning trajectories while navigating around static obstacles. Traditional Artificial Potential Fields (APF) face challenges such as getting stuck in local minima, which diminishes the path's optimality. Additionally, conventional APF often results in trajectories characterized by sharp turns or sudden changes in direction, particularly in environments populated with numerous obstacles. These obstacles can significantly hinder Autonomous Underwater Vehicles (AUVs) that depend on smooth trajectories for maintaining stability and control. To address these drawbacks, we present the Hybrid A* - Artificial Potential Field (HA-APF) algorithm. When using AUVs for collision avoidance duties, adherence to safety procedures is crucial. We propose an enhanced HA-APF algorithm to address this issue for efficient path planning and collision avoidance. Additionally, the A* algorithm, which has been altered to mitigate the innate problems with local optimality in the conventional APF approach, is used in conjunction with the improved APF technique. Finally, validations are conducted in three different regions with different beginning and finishing positions. These tests show how feasible and successful the suggested algorithm is in assisting AUVs in avoiding collisions while also carrying out path-planning duties. Through this work, we provide a robust tool for advancing AUV capabilities in real-world applications, ultimately allowing for more effective underwater exploration and intervention.

关键词： Three-dimensional displays Navigation Stability analysis Hybrid power systems Trajectory Planning Safety Collision avoidance Faces Finishing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid APF Approach for Obstacle Avoidance in a 3D Environment 3

A Hybrid APF Approach for Obstacle Avoidance in a 3D Environ...

引用

3rd IEEE International Conference on Industrial Electronics: Developments and Applications, ICIDeA 2025

作者： Saini, Amrita Talukdar, Bhaskar Jyoti Dash, Rudra Narayan Rao, D Chandrasekhar Das, Bikramaditya BPUT Dept. of Computer Science and Engineering Odisha Rourkela India VSSUT Dept. of Electronics and Telecommunication Engineering Odisha Burla India School of Electrical Engineering KIIT Deemed to be University Bhubaneswar India BPUT Dept. of Electronics and Communication Engineering Odisha Rourkela India

ISBN: (纸本)9798331533205

This study's main objective is to look at strategies, for avoiding underwater collisions and planning trajectories while navigating around static obstacles. Traditional Artificial Potential Fields (APF) face challenges such as getting stuck in local minima, which diminishes the path's optimality. Additionally, conventional APF often results in trajectories characterized by sharp turns or sudden changes in direction, particularly in environments populated with numerous obstacles. These obstacles can significantly hinder Autonomous Underwater Vehicles (AUVs) that depend on smooth trajectories for maintaining stability and control. To address these drawbacks, we present the Hybrid A∗ - Artificial Potential Field (HA-APF) algorithm. When using AUVs for collision avoidance duties, adherence to safety procedures is crucial. We propose an enhanced HA-APF algorithm to address this issue for efficient path planning and collision avoidance. Additionally, the A∗ algorithm, which has been altered to mitigate the innate problems with local optimality in the conventional APF approach, is used in conjunction with the improved APF technique. Finally, validations are conducted in three different regions with different beginning and finishing positions. These tests show how feasible and successful the suggested algorithm is in assisting AUVs in avoiding collisions while also carrying out path-planning duties. Through this work, we provide a robust tool for advancing AUV capabilities in real-world applications, ultimately allowing for more effective underwater exploration and intervention. © 2025 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Highly Interpretable Deep Equilibrium Network for Hyperspectral Image Deconvolution

A Highly Interpretable Deep Equilibrium Network for Hyperspe...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Alexandros Gkillas Dimitris Ampeliotis Kostas Berberidis Dept. of Computer Engineering & Informatics University of Patras Greece Dept. of Digital Media and Communication Ionian University Greece

In this paper, a novel technique for the hyperspectral image deconvolution problem is developed. First, considering the highly ill-posed nature of the examined problem, it is imperative to incorporate proper priors (regularizers) to capture the strong spectral and spatial dependencies of the hyperspectral images. Then, in light of this, a novel optimization problem is proposed by employing a convolutional neural network to act as a regularizer, which is learnt to reflect the properties of the signals of interest. To solve the proposed optimization problem, we use the half quadratic splitting methodology, thus designing an efficient iterative solver (iteration map). Based on the Deep Equilibrium (DEQ) modeling, which aims to express the proposed iterative solver as an equilibrium (fixed-point) computation, a highly interpretable deep learning-based network is derived, which can be trained endto-end. Extensive numerical results using two publicly available datasets illustrate that the proposed method markedly outperforms other state-of-the-art approaches.

关键词： Deep learning Deconvolution Signal processing algorithms Signal processing Numerical models Iterative methods Convolutional 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：