检索结果-内蒙古大学图书馆

Machine Learning for Predictive Modeling and Personalized Treatment in Magnesium-based Biomedical Applications 8

Machine Learning for Predictive Modeling and Personalized Tr...

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Jnyanadeep, Bandaru Sahana, S. Suresh, Rohit Roopa, T.S. Angadi, Gangadhar Bengaluru India Rv College of Engineering® Department of Computer Science and Engineering Bengaluru India Rv College of Engineering® Department of Mechanical Engineering Bengaluru India

ISBN: (纸本)9798331505462

This paper explores the integration of machine learning (ML) techniques with magnesium-based biomedical applications, focusing on predictive modeling and personalized treatment strategies. Magnesium's biocompatibility and biodegradability make it an attractive material for various medical applications, including implants and drug delivery systems. However, optimizing its use for individual patients remains challenging. In this paper it is proposed that ML can bridge this gap by enabling more accurate predictions of treatment outcomes and facilitating personalized approaches. Through a comprehensive review of existing literature and analysis of case studies, it is demonstrated that how supervised learning, unsupervised learning, and deep learning techniques can be applied to improve patient outcomes in magnesium-based treatments. The paper also addresses challenges such as data privacy and model interpretability, proposing solutions for integrating ML into clinical workflows. Our findings suggest that the synergy between ML and magnesium-based biomedical applications has the potential to significantly advance personalized medicine, opening new avenues for research and clinical practice. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing flexural properties in PP/Sisal/PMA bio-composites by response surface methodology

引用

Interactions 2024年第1期245卷 1-14页

作者： Vadivel, M. Musrif, Pramod G. Satishkumar, P. Nasrulla, S. Mohamed Saminathan, Rajasekaran Vijayan, Vinesh Department of Civil Engineering Nehru Institute of Technology Coimbatore India Institute of Information Technology AISSMS Maharashtra Shivajinagar Pune India Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India Department of Mechanical Engineering PSNA College of Engineering & ampTechnology Tamilnadu Dindigul India Department of Mechanical Engineering College of Engineering and Computer Science Jazan University Jizan Saudi Arabia Rathinam Technical Campus Tamilnadu Coimbatore India

Applying the response surface methodology, this work aims to examine the flexural characteristics of bio composites composed of polypropylene (PP)/sisal fiber (Sisal)/polypropylene-grafted maleic anhydride (PMA). To predict the modulus behavior and flexural strength of the natural fiber bio-composite, mathematical models have been developed as a function of Sisal load, PMA, and fiber length compatibilizer content. These models are based on a three-factor, three-level Box-Behnken design (BBD), a subset of the response surface methodology (RSM). Sisal fiber (15–35 wt%), fiber length (4–12 mm), and PMA (2–6% wt%) were the three levels that were selected for the factors that were taken into consideration. The utilize of contour plots and response surface methodology allowed for the determination of optimal compositions with respect to improved flexural properties. According to the results produced from the design expert software, the flexural modulus (FM) is 1625.09 MPa and the ideal flexural strength (FS) is 46.3954 MPa. A high degree of agreement between the experimental data and the model’s predictions was indicated by the R2 values and normal probability maps. The specimens were then examined utilizing scanning electron microscopy (SEM) to determine their morphology. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Bending strength

来源：评论

学校读者我要写书评

暂无评论

Enhancing Trajectory Tracking of Quadrotor Using Feedback Linearization with MPC-LPV and LQI-LPV under Variable Disturbances 3

Enhancing Trajectory Tracking of Quadrotor Using Feedback Li...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Chowdhury, Raian Haider Imtiaz Ferdous, Ahmed Hossain, Amreen Rahman, Kazi Arafat Bangladesh University of Engineering and Technology Department of Mechanical Engineering Dhaka Bangladesh Brac University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

The deployment of Unmanned Aerial Vehicles (UAVs) has markedly improved industrial efficiency. Optimizing control algorithms for precise path tracking is essential for enhancing the reliability and performance of these systems. This paper presents a comparative analysis of Model Predictive Controller (MPC) and Linear Quadratic Integral (LQI) controller, combined with the Linear Parameter Varying (LPV) approach, for quadrotor trajectory tracking under variable disturbances. The quadrotor is modeled using Newton-Euler equations for a six-degrees-of-freedom system. The control architecture includes an outer loop position controller using Feedback Linearization (FL) and an inner loop attitude controller implemented as either MPC-LPV or LQI-LPV. Disturbances are modeled using a custom sinusoidal model. Numerical simulations are done to evaluate controller performance for six different trajectories. The results for the helical trajectory indicate that under variable disturbances, the MPC-LPV+FL outperforms the LQI-LPV+FL. The MPC-LPV+FL achieves a steady-state error of 0.1934 m compared to 0.6611 m for the LQI-LPV+FL. Additionally, the MPC-LPV+FL reaches the minimum error in 3.1 seconds, compared to 3.8 seconds for the LQI-LPV+FL, resulting in a 22.58% faster response. Therefore, MPC-LPV+FL is the superior choice based on accuracy, stability, and speed of response under adverse conditions. © 2024 IEEE.

关键词： Feedback linearization

来源：评论

学校读者我要写书评

暂无评论

Implementation of Hector SLAM Algorithm for Mapping Indoor Environments with Obstacles 3

Implementation of Hector SLAM Algorithm for Mapping Indoor E...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hossain, Amreen Chowdhury, Raian Haider Brac University Department of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Engineering and Technology Department of Mechanical Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

Autonomous navigation in obstacle-rich indoor environments is crucial for both industrial and domestic robotic applications. A central aspect of this process is Simultaneous Localization and Mapping (SLAM). This paper presents a comprehensive methodology for implementing Hector SLAM, a widely used SLAM algorithm that operates without relying on external odometry and pose data from wheel encoders or Inertial Measurement Unit (IMU) sensors. The experimental setup involves a custom-built two-wheeled mobile robotic platform, equipped with essential components including a 2D Light Detection and Ranging (LiDAR) sensor, wheel encoders, IMU, motor drivers, an Arduino UNO, and a Raspberry Pi 4B, with Robot Operating System (ROS) serving as the primary software framework. The robot navigates within a predefined rectangular indoor environment, where real-time mapping results are captured at different time intervals to assess mapping accuracy. Additionally, a randomly placed object is introduced to test the obstacle detection capability during operation. Results indicate that Hector SLAM demonstrates high accuracy, achieving precision within a few centimeters, particularly in environments with distinct structural features. © 2024 IEEE.

关键词： Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Blockchain architecture in upcoming digital world 4th

Blockchain architecture in upcoming digital world

引用

4th Annual International Conference on Data science, Machine Learning and Blockchain Technology, AICDMB 2023

作者： Promod Kumar, B.M. Manoj Gowda, K.S. Heemashree, S.S. Siddesh Kumar, N.M. Tejas, S. Haran, Pranadhi Vikas, C.M. Department of Computer Science and Engineering PES College of Engineering Mandya India Department of Information Science and Engineering PES College of Engineering Mandya India Department of Mechanical Engineering PES College of Engineering Mandya India

ISBN: (纸本)9781032426853

Blockchain architecture is a multi-layered system with various components that work together to ensure stability, security, and efficiency. The bottom layer, the Data Layer, holds transactions and data, while the Consensus Layer ensures accuracy and validates transactions. The Network Layer manages communication and data transmission, and the Application Layer provides user access. The Contract Layer executes smart contracts and defines rules, and the Security Layer protects the system from attacks. Blockchain architecture is widely used in various industries including finance, healthcare, supply chain, and voting systems, providing secure, transparent, and immutable data. The combination of blockchain and AI technology results in secure, decentralized and automated execution of agreements, transforming industries such as finance, supply chain and healthcare. © 2024 The Author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning model with knowledge distillation for pulmonary diseases detection in chest X-rays

引用

Multimedia Tools and Applications 2025年第15期84卷 14885-14913页

作者： Asham, Mohammed A. Al-Shargabi, Asma A. Al-Sabri, Raeed Meftah, Ibrahim School of Computer Science and Engineering Central South University Hunan Changsha410083 China Department of Information Technology Collage of Computer Qassim University Buraydah51452 Saudi Arabia College of Mechanical and Electrical Engineering Central South University Changsha410017 China

Accurate and timely diagnosis of pulmonary diseases is critical in the field of medical imaging. While deep learning models have shown promise in this regard, the current methods for developing such models often require extensive computing resources and complex procedures, rendering them impractical. This study focuses on the development of a lightweight deep-learning model for the detection of pulmonary diseases. Leveraging the benefits of knowledge distillation (KD) and the integration of the ConvMixer block, we propose a novel lightweight student model based on the MobileNet architecture. The methodology begins with training multiple teacher model candidates to identify the most suitable teacher model. Subsequently, KD is employed, utilizing the insights of this robust teacher model to enhance the performance of the student model. The objective is to reduce the student model's parameter size and computational complexity while preserving its diagnostic accuracy. We perform an in-depth analysis of our proposed model's performance compared to various well-established pre-trained student models, including MobileNetV2, ResNet50, InceptionV3, Xception, and NasNetMobile. Through extensive experimentation and evaluation across diverse datasets, including chest X-rays of different pulmonary diseases such as pneumonia, COVID-19, tuberculosis, and pneumothorax, we demonstrate the robustness and effectiveness of our proposed model in diagnosing various chest infections. Our model showcases superior performance, achieving an impressive classification accuracy of 97.92%. We emphasize the significant reduction in model complexity, with 0.63 million parameters, allowing for efficient inference and rapid prediction times, rendering it ideal for resource-constrained environments. Outperforming various pre-trained student models in terms of overall performance and computation cost, our findings underscore the effectiveness of the proposed KD strategy and the integration of the Conv

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Entropy-Boosted Adversarial Patch for Concealing Pedestrians in YOLO Models

引用

IEEE Access 2024年 12卷 32772-32779页

作者： Lin, Chih-Yang Huang, Tun-Yu Ng, Hui-Fuang Lin, Wei-Yang Farady, Isack National Central University Department of Mechanical Engineering Taoyuan32001 Taiwan Hsinchu310401 Taiwan Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia National Chung Cheng University Department of Computer Science and Information Engineering Chiayi62102 Taiwan

In recent years, rapid advancements in hardware and deep learning technologies have paved the way for the extensive integration of image recognition and object detection into daily applications. As reliance on deep learning grows, so do concerns about the vulnerabilities of deep neural networks, emphasizing the need to address potential security issues. This research unveils the Entropy-boosted Loss, a novel loss function tailored to generate adversarial patches resembling potted plants. Specifically designed for the YOLOV2, YOLOV3, and YOLOV4 object detectors, these patches obscure the detectors' ability to identify individuals. By enhancing the uncertainty in class probability, a person wearing an adversarial patch crafted using our proposed loss function becomes less identifiable by YOLO detectors, achieving the desired adversarial effect. This underscores the significance of comprehending the vulnerabilities of YOLO models to adversarial attacks, particularly for individuals aiming to obscure their presence from camera detection. Our experiments, conducted using the INRIA person dataset and under real-time network camera conditions, confirm the effectiveness of our method. Moreover, our technique demonstrates substantial success in virtual try-on environments. © 2013 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Reliability Analysis of Correlated Competitive and Dependent Components Considering Random Isolation Times

引用

computers, Materials & Continua 2023年第9期76卷 2763-2777页

作者： Shuo Cai Tingyu Luo Fei Yu Pradip Kumar Sharma Weizheng Wang Lairong Yin School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Department of Computing Science University of AberdeenAberdeenUK School of Automotive and Mechanical Engineering Changsha University of Science and TechnologyChangsha410114China

In the Internet of Things(IoT)system,relay communication is widely used to solve the problem of energy loss in long-distance transmission and improve transmission *** Body Sensor Network(BSN)systems,biosensors communicate with receiving devices through relay nodes to improve their limited energy *** the relay node fails,the biosensor can communicate directly with the receiving device by releasing more transmitting ***,if the remaining battery power of the biosensor is insufficient to enable it to communicate directly with the receiving device,the biosensor will be isolated by the ***,a new combinatorial analysis method is proposed to analyze the influence of random isolation time(RIT)on system reliability,and the competition relationship between biosensor isolation and propagation failure is *** approach inherits the advantages of common combinatorial algorithms and provides a new approach to effectively address the impact of RIT on system reliability in IoT systems,which are affected by competing ***,the method is applied to the BSN system,and the effect of RIT on the system reliability is analyzed in detail.

关键词： BSN Internet of Things reliability analysis random isolation time

来源：评论

学校读者我要写书评

暂无评论

Electronic structure prediction of multimillion atom systems through uncertainty quantification enabled transfer learning

引用

npj Computational Materials 2024年第1期10卷 1423-1437页

作者： Shashank Pathrudkar Ponkrshnan Thiagarajan Shivang Agarwal Amartya S.Banerjee Susanta Ghosh Department of Mechanical Engineering-Engineering Mechanics Michigan Technological UniversityHoughtonMIUSA Department of Electrical and Computer Engineering University of CaliforniaLos AngelesCA90095USA Department of Materials Science and Engineering University of CaliforniaLos AngelesCA90095USA Faculty member of the Center for Data Sciences Michigan Technological UniversityHoughtonMIUSA

The ground state electron density—obtainable using Kohn-Sham Density Functional Theory(KSDFT)simulations—contains a wealth of material information,making its prediction via machine learning(ML)models ***,the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation,making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system ***,we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data,while comprehensively sampling systemconfigurations using *** ML models are less reliant on heuristics,and being based on Bayesian neural networks,enable uncertainty *** show that our models incur significantly lower data generation costs while allowing confident—and when verifiable,accurate—predictions for a wide variety of bulk systems well beyond training,including systems with defects,different alloy compositions,and at multi-million-atom ***,such predictions can be carried out using only modest computational resources.

关键词： alloy prediction transfer

来源：评论

学校读者我要写书评

暂无评论

Classifying aquatic organism via evolving residual convolutional neural networks by optimized random vector functional link

引用

Multimedia Tools and Applications 2025年第1期84卷 221-243页

作者： Zhou, Zhiyu Wen, Jingqi Liu, Mingxuan Yang, Junyi School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China School of Mechanical Engineering Hangzhou Dianzi University Hangzhou310018 China

Aquatic organisms serve as crucial indicators of ecosystem health and water quality conditions. Accurate classification and monitoring of aquatic organisms facilitate the timely detection of ecological environmental changes, which is of significant importance for the conservation of biodiversity and environmental protection. Pointing at the issues of fuzzy images and difficult classification caused by the poor lighting conditions of aquatic organisms and many impurities around, we put forward a novel classification model of aquatic organisms with convolution neural network, feedforward network and optimization algorithm. The model first abstracts the traits of aquatic organisms, and then classifies the abstracted features. Through migration learning of ResNet101 neural network on Fish4Knowledge dataset and ISLVRC2012 and some data sets related to aquatic organisms, a network that will be used to abstract features is obtained. The model put forward in the paper firstly uses ResNet101 to abstract the aquatic organism image’s characteristics, and then uses the Golden Eagle optimization algorithm (GEO) optimized by chaos mapping optimization and the RVFL neural network optimized by L2,1 regularization to classify aquatic organisms. The algorithm is compared with other RVFL algorithms optimized by Ant Lion Optimizer (ALO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Harris Hawks Optimization (HHO) and Dragonfly Algorithm (DA). The findings indicate that the methodology introduced in this paper exhibits an improvement over the original ResNet101, with increases of 1.58%, 2.57%, 0.22% and 0.93% in particularity rate, accuracy rate, recall rate and F1 score on ILSVRC2012, respectively. The efficiency and accuracy of this method significantly contribute to the advancement of aquatic organism monitoring and environmental protection efforts. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image classification

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：