检索结果-内蒙古大学图书馆

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Radojičić, Veljko Rapaić, Milan R. University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798331515799

This paper investigates reinforcement learning (RL) as a practical framework for achieving optimal adaptive control across several simple dynamical system models. All experiments were conducted using the Proximal Policy Optimization (PPO) algorithm, implemented within the MATLAB Reinforcement Learning Toolbox. The primary focus of this study is to explore how the learning process can be empirically designed to sufficiently excite the system dynamics and obtain a sufficiently robust controller. © 2025 IEEE.

关键词： Self adjusting control systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating Extended Kalman Filter and Unscented Kalman Filter for accurate trajectory estimation

Evaluating Extended Kalman Filter and Unscented Kalman Filte...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Anastasija Golić Mirna Radović Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This paper evaluates two common methods for trajectory estimation: the Extended Kalman Filter (EKF), the Unscented Kalman Filter (UKF). The EKF and UKF are well-established recursive filtering techniques commonly used for nonlinear state *** performance of these methods is compared through their implementation on a standard trajectory estimation problem, with a focus on assessing their accuracy.

关键词： Accuracy Linear approximation Trajectory Computational efficiency Kalman filters Reliability Nonlinear systems State estimation Tuning Standards

来源：评论

学校读者我要写书评

暂无评论

Optimal control of Systems with Fractional Dynamics and Algebraic Constraints 24

Optimal Control of Systems with Fractional Dynamics and Alge...

引用

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Živanović, Nikolina Jeličič, Zoran D. University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798331515799

This study investigates optimal control problems described by fractional differential equations, with the control vector components subject to algebraic constraints. Two case studies are analyzed: an illustrative example designed to test the algorithm's effectiveness and a biologically significant model of acute myeloid leukemia (AML), which applies optimal control theory to design therapeutic strategies under medical constraints. The methodology transforms fractional differential equations into equivalent ordinary differential equations using the framework of Atanacković and Stanković. L.S. Pontryagin's maximum principle is then applied to derive control functions that satisfy the algebraic constraints, followed by numerical optimization of the Hamiltonian function. We formally parsed the problem of dynamic optimization into a static optimization problem using the Forward-Backward Sweep Method (FBSM). The approach is validated through comprehensive numerical simulations, demonstrating its robustness and applicability to real-world problems. © 2025 IEEE.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Evaluating Extended Kalman Filter and Unscented Kalman Filter for accurate trajectory estimation 24

Evaluating Extended Kalman Filter and Unscented Kalman Filte...

引用

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Golić, Anastasija Radović, Mirna University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798331515799

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Accidental Centralization: Pitfalls of Blockchain-Based Project Architectures

Accidental Centralization: Pitfalls of Blockchain-Based Proj...

引用

Electrical, Electronic and computing Engineering (IcETRAN), International Conference on

作者： Veljko B. Petrović Dinu Dragan Dušan B. Gajlć Control and Computing Department Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798350386998

ISBN: (纸本)9798350387001

Making use of blockchain in complex projects in ways which scale and keep costs down can lead to very complex architectural patterns. The problem with such patterns is that it is very easy to set up a system that only seems decentralized but, in fact, operates under a degraded trust model or is even centralized in practice. Using a blockchain to implement a centralized system represents a grotesque waste of computational resources for no benefit at all. This paper analyzes several cases of such architectural malfunction and shows how degraded trust can occur, how to detect it, and how to respond to this issue.

关键词： Privacy Costs Computational modeling Design methodology Computer architecture Trustless services Blockchains

来源：评论

学校读者我要写书评

暂无评论

A review of the approaches for enhancing driver safety through camera-based monitoring

A review of the approaches for enhancing driver safety throu...

引用

Zooming Innovation in Consumer Electronics International Conference (ZINC)

作者： Maksim Egelja Bogdan Pavkovic Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798350349153

ISBN: (纸本)9798350349160

Road accidents caused by human error continue to result in a rising number of serious injuries and fatalities each year. Automated Driving Assistance Systems (ADAS) offer a promising approach by continuous monitoring of drivers to promptly identify and address unsafe behaviors. A further technical challenge is solely relying on camera sensors to determine crucial human deficiencies such as drowsiness and distraction. In our research, we provide a review of relevant papers from the field of computer vision for driver monitoring. Most of these approaches rely on Machine Learning (ML) algorithms and Convolutional Neural Networks (CNNs) for both image processing and driver state classification. Our findings indicate that Hidden Markov Models (HMMs) and CNNs consistently outperform other techniques in terms of accuracy. In conclusion, we present our perspective on the essential features that a comprehensive driver monitoring system (DMS) should include.

关键词： Computer vision Technological innovation Reviews Hidden Markov models Cameras Sensors Proposals

来源：评论

学校读者我要写书评

暂无评论

Security enhancement of LSB-based audio steganography method

Security enhancement of LSB-based audio steganography method

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Jezdimirovic, Jovana Pekez, Nenad Kovacevic, Jelena University of Novi Sad Faculty of Technical Sciences Computing and Control Engineering Department Novi Sad Serbia Systems LLC RT-RK Institute for Computer Based Novi Sad Serbia

ISBN: (纸本)9798350347722

The rapid development of digital technology has brought about the challenge of ensuring information security. Cryptography and steganography are among the various techniques available to address this challenge. These techniques come in different forms and provide reliable means of securing information and communication. Despite the existence of numerous options, new variations are still emerging. This paper concentrates on Least Significant Bit (LSB) coding, which is one of the most widely recognized and frequently utilized steganography techniques. The advantages of LSB-based coding methods are high capacity and low complexity. However, predictability is an issue. Audio files' sizes and data redundancy make audio data perfect for steganography, as it is possible to embed large amounts of secret information and easily transmit the signal via various communication channels. However, the use of LSB coding in audio steganography has a drawback due to the extreme sensitivity of the human auditory system (HAS). This means that any noise added to the audio with data embedded in the LSBs can be detected by the HAS, which is dependent on the number of LSBs used. This work presents an improvement of the LSB-based approach, the XORing of LSBs method, with an emphasis on enhanced security. The method achieves this by randomly picking the pairs of bits to be XOR'd while preserving the characteristics of classic LSB methods. To verify the method, it has been implemented on the Cirrus Logic DSP, proving that it may be efficiently used in a real-Time audio environment without interfering with HAS sensitivity levels. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Deep Forest-Based Fall Detection in Internet of Medical Things Environment

引用

Computer Systems Science & Engineering 2023年第6期45卷 2377-2389页

作者： Mohamed Esmail Karar Omar Reyad Hazem Ibrahim Shehata College of Computing and Information Technology Shaqra UniversityP.O.Box 33Shaqra11961Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Computer Science Department Faculty of Computers and Artificial IntelligenceSohag UniversitySohag82524Egypt Department of Computer and Systems Engineering Faculty of EngineeringZagazig UniversityZagazig44519Egypt

This article introduces a new medical internet of things(IoT)framework for intelligent fall detection system of senior people based on our proposed deep forest *** cascade multi-layer structure of deep forest classifier allows to generate new features at each level with minimal hyperparameters compared to deep neural ***,the optimal number of the deep forest layers is automatically estimated based on the early stopping criteria of validation accuracy value at each generated *** suggested forest classifier was successfully tested and evaluated using a public SmartFall dataset,which is acquired from three-axis accelerometer in a *** includes 92781 training samples and 91025 testing samples with two labeled classes,namely non-fall and *** results of our deep forest classifier demonstrated a superior performance with the best accuracy score of 98.0%compared to three machine learning models,i.e.,K-nearest neighbors,decision trees and traditional random forest,and two deep learning models,which are dense neural networks and convolutional neural *** considering security and privacy aspects in the future work,our proposed medical IoT framework for fall detection of old people is valid for real-time healthcare application deployment.

关键词： Elderly population fall detection wireless sensor networks internet of medical things deep forest

来源：评论

学校读者我要写书评

暂无评论

YOLOv8n-CGW: A novel approach to multi-oriented vehicle detection in intelligent transportation systems

引用

Multimedia Tools and Applications 2025年第7期84卷 3809-3840页

作者： Berwo, Michael Abebe Fang, Yong Sarwar, Nadeem Mahmood, Jabar Aljohani, Mansourah Elhosseini, Mostafa School of Information and Engineering Chang’an University Shaanxi Xi’an710064 China Department of Computer Science Bahria University Lahore Campus Punjab Lahore54600 Pakistan Department of Information Technology Faculty of Computing and Information Technology University of Sialkot Punjab Sialkot51040 Pakistan College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

In the context of Intelligent Transportation Systems (ITS), the role of vehicle detection and classification is indispensable for streamlining transportation management, refining traffic control, and conducting in-depth accident analyses. However, the intricate task of accurately detecting multi-oriented vehicles in diverse scenarios remains a challenge, even with the advancements in ITS. Factors such as vehicle morphology, design, road conditions, structural details, and climatic variables provide a significant part in the detection. To address this, our study introduces an advanced YOLOv8n model, specifically the YOLOv8n-CGW, which is built upon pre-trained deep learning frameworks. This model is meticulously tailored to enhance the detection capabilities for multi-oriented vehicles. Comprehensive evaluations on esteemed datasets like MtV, MERGED, Custom dataset, DAWN, WEDGE, and UA-DETRAC underscore the superiority of our approach over existing models. Notably, our YOLOv8n-CGW model achieves a remarkable mAP of 83.3% and boasts a swift inference time of 0.0019s, setting a new benchmark in the domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DEGAS - Deformation Estimation based on Magnetic Gradient Tensor Contraction for Soft Robot Shape Servoing

DEGAS - Deformation Estimation based on Magnetic Gradient Te...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Jelena Vuletić Bruno Marić Matko Orsag LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

This work proposes the first derivation, implementation, and experimental validation of magnetic-based proprioceptive sensing method for soft robotic applications. In our proposed approach, the magnetic sensing system measures gradient tensor contractions that can be directly related to the shape of a deformable plastering tool. Custom-designed and 3D-printed plastering tool embeds two identical permanent magnets that generate a non-symmetric magnetic field tracked by the proposed sensor. Seamless real-time control is enabled with the sensor sampling rate of 1 kHz. Classical linear control is synthesized for the scraper bending angle and orientation control. The tool, sensor, and the proposed control system are validated on robotic plastering and painting tasks.

关键词： Magnetic field measurement Tensors Deformation Shape Propioception Estimation Bending Soft robotics Sensors Painting

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：