检索结果-内蒙古大学图书馆

Genetic programming with surrogate evaluation for the electric vehicle routing problem

Swarm and Evolutionary Computation 2025年 96卷

作者： Gil-Gala, Francisco J. Đurasević, Marko Jakobović, Domagoj Varela, Ramiro Department of Computer Science University of Oviedo Gijón33271 Spain Faculty of Electrical Engineering and Computing University of Zagreb Zagreb10000 Croatia

The focus on environmental sustainability has made the Electric Vehicle Routing Problem (EVRP) an important area of research. Routing Policies (RPs) offer a simple and efficient approach to solving VRPs, providing advantages over methods like metaheuristics by quickly generating solutions. However, designing efficient RPs manually can be time-consuming. Therefore, there is a need to explore hyper-heuristic approaches, particularly Genetic Programming (GP), to automate the design of RPs. However, population-based evolutionary algorithms like GP often require a significant amount of computational resources, especially for fitness calculation. Therefore, surrogate evaluation is essential in enhancing efficiency, especially in GP, where multiple problem instances need to be solved to evaluate each chromosome. In this study, we employ surrogate models within GP to design RPs for EVRP with hard time windows. The experiments show that the RPs designed by GP with surrogate models outperform those produced by standard GP approaches while still requiring less computational time to be generated. Moreover, the RPs designed with GP using surrogate models are also smaller, and consequently, they are also more efficient and easier to interpret. © 2025

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Designing Lookahead Relocation Rules for the Container Relocation Problem with Genetic Programming 28th

Designing Lookahead Relocation Rules for the Container Rel...

引用

28th European Conference on Genetic Programming, EuroGP 2025, Held as Part of EvoStar 2025

作者： Đurasević, Marko Đumić, Mateja Gil-Gala, Francisco Javier Jakobović, Domagoj Faculty of Electrical Engineering and Computing University of Zagreb Zagreb10000 Croatia School of Applied Mathematics and Informatics J. J. Strossmayer University of Osijek Osijek31000 Croatia Department of Computing University of Oviedo Gijón Spain

ISBN: (纸本)9783031899904

The container relocation problem is an important combinatorial optimisation problem commonly found in warehouses and container ports. The goal of this problem is to retrieve all of the containers from the yard with the fewest container relocations between the stacks. Since the problem is NP-hard, various heuristics have been proposed to solve it, among which are relocation rules (RRs), simple constructive heuristics that incrementally construct the solution. However, it is quite difficult to design such RRs manually, so genetic programming has been applied to design new RRs automatically. A significant problem with RRs, whether manually or automatically designed, is that they usually have a limited view of the problem. This means that they will often make decisions that can negatively influence the future, meaning that the current decision would cause additional relocations. Therefore, this study investigates different relocation schemes that can be used within RRs to obtain rules with lookahead ability. These rules will enable containers to be relocated based on future information and, consequently, arranged better in the yard. For that purpose, three novel relocation schemes for automatically designed RRs are defined and evaluated on an existing problem set. The results demonstrate that integrating additional elements to evolve lookahead RRs can significantly improve the results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Reactive Navigation of the Ackermann Steering Robot in Unknown Environments

Reactive Navigation of the Ackermann Steering Robot in Unkno...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： ANA ŠELEK IVAN HRABAR SAŠA ŠTEKOVIĆ Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Autegra D.O.O. Zagreb Croatia

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

Mobile robots are now widely used in numerous real-world applications that have complex navigation requirements, especially in environments used by humans. This requires highly accurate navigation that can be performed in realtime. In this paper, a method for generating a smooth motion of nonholonomic mobile robots is proposed. It enables robots to move optimally toward the desired goal and allows fast path replanning when encountering unknown or dynamic obstacles. The method generates smooth, collision-free trajectories based on clothoids, ensuring high computational efficiency and suitability for realtime path planning. By applying a smoothing algorithm, the proposed method improves the robot's efficiency in terms of travel time and trajectory length from start to goal, as demonstrated by a comparison with model predictive control.

关键词： Smoothing methods Navigation Dynamics Real-time systems Trajectory Computational efficiency Mobile robots Collision avoidance Testing Predictive control

来源：评论

学校读者我要写书评

暂无评论

Power Line Following Based on Measurements of the Magnetic Field

Power Line Following Based on Measurements of the Magnetic F...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Goran Vasiljević Dean Martinović Stjepan Bogdan Faculty of Electrical Engineering and Computing Laboratory for Robotics and Intelligent Control Systems Unska 3 University of Zagreb Zagreb Croatia

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

In this paper, we present a method to control the UAV to follow the power line with a specific position and orientation based only on the measurement of the magnetic field generated by the current flow in the power line. In this way, it is possible to localize the UAV with respect to the power line without the need for additional sensors, even in poor visibility conditions. The measurements from four magnetometers attached to the UAV are used to solve an optimization problem that involves determining the relative pose of the UAV with respect to the power line. Based on the relative pose, the UAV is controlled to follow the power line in a predefined position and orientation. Experiments in a test setup have confirmed that the method is applicable in a realistic environment.

关键词： Location awareness Visualization Power measurement Magnetic field measurement Magnetometers Current measurement Position measurement Autonomous aerial vehicles Magnetic fields Optimization

来源：评论

学校读者我要写书评

暂无评论

Pose-independent 3D Anthropometry from Sparse Data

arXiv

引用

arXiv 2025年

作者： Bojanić, David Wuhrer, Stefanie Petković, Tomislav Pribanić, Tomislav University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Inria centre University Grenoble Alpes Grenoble France

3D digital anthropometry is the study of estimating human body measurements from 3D scans. Precise body measurements are important health indicators in the medical industry, and guiding factors in the fashion, ergonomic and entertainment industries. The measuring protocol consists of scanning the whole subject in the static A-pose, which is maintained without breathing or movement during the scanning process. However, the A-pose is not easy to maintain during the whole scanning process, which can last even up to a couple of minutes. This constraint affects the final quality of the scan, which in turn affects the accuracy of the estimated body measurements obtained from methods that rely on dense geometric data. Additionally, this constraint makes it impossible to develop a digital anthropometry method for subjects unable to assume the A-pose, such as those with injuries or disabilities. We propose a method that can obtain body measurements from sparse landmarks acquired in any pose. We make use of the sparse landmarks of the posed subject to create pose-independent features, and train a network to predict the body measurements as taken from the standard A-pose. We show that our method achieves comparable results to competing methods that use dense geometry in the standard A-pose, but has the capability of estimating the body measurements from any pose using sparse landmarks only. Finally, we address the lack of open-source 3D anthropometry methods by making our method available to the research community at ***/DavidBoja/pose-independent-anthropometry. Copyright © 2025, The Authors. All rights reserved.

关键词： Entertainment industry

来源：评论

学校读者我要写书评

暂无评论

Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach

arXiv

引用

arXiv 2025年

作者： Sternak, Tvrtko Runje, Davor Granoša, Dorian Wang, Chi Faculty of Electrical Engineering and Computing University of Zagreb Croatia SplxAI Google DeepMind United Kingdom

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage—the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to secure LLM deployment and introduce a framework for testing the robustness of LLMs using agentic teams. Leveraging AG2 (formerly AutoGen), we implement a multi-agent system where cooperative agents are tasked with probing and exploiting the target LLM to elicit its prompt. Guided by traditional definitions of security in cryptography, we further define a prompt leakage-safe system as one in which an attacker cannot distinguish between two agents: one initialized with an original prompt and the other with a prompt stripped of all sensitive information. In a safe system, the agents’ outputs will be indistinguishable to the attacker, ensuring that sensitive information remains secure. This cryptographically inspired framework provides a rigorous standard for evaluating and designing secure LLMs. This work establishes a systematic methodology for adversarial testing of prompt leakage, bridging the gap between automated threat modeling and practical LLM security. You can find the implementation of our prompt leakage probing on GitHub: https://***/sternakt/prompt-leakage-probing © 2025, CC BY-NC-ND.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Modeling of Open Dielectric Structures with Glide and Broken Mirror Symmetries

Modeling of Open Dielectric Structures with Glide and Broken...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Dubravko Tomić Francisco Mesa Zvonimir Šipuš Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Departamento de Física Aplicada 1 Universidad de Sevilla Sevilla Spain

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

The increased interest in exploiting the higher symmetries in the design of microwave components necessitates the development of efficient and reliable analysis methods. Analysis of dispersion properties of open structures with commercial solvers is a non-trivial problem that requires a physical insight in distinguishing between guided modes and spurious solutions. This paper presents an analytical model based on Rigorous Cou-pled Wave Analysis and derives the dispersion equation, which accounts for presence of glide or broken mirror symmetries. GRATING

关键词： Europe Reliability engineering Microwave theory and techniques Harmonic analysis Antennas and propagation Mathematical models Dielectrics Mirrors Gratings Dispersion

来源：评论

学校读者我要写书评

暂无评论

Modified Huygens Source for Maximum Gain of Implanted Antenna

Modified Huygens Source for Maximum Gain of Implanted Antenn...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Jiajun Li Zvonimir Šipuš Anja K. Skrivervik Microwaves and Antennas Group École Polytechnique Fédérale de Lausanne Lausanne Switzerland Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

Implanted antennas are a key part of wireless implanted medical devices. However, the lossy nature of the surrounding body tissue significantly reduces their radiation efficiency and gain. Therefore, it is important to maximize the power reaching free space from the implanted antenna. The fundamental modes TE10 and TM10 are of great interest as they have lower near-field losses compared to higher order modes. A Huygens source antenna that combines two first modes, TE10 and TM10, is thus a good candidate for an efficient implanted antenna. However, because the losses for TE and TM modes differ in the implanted scenario, the optimal power distribution between the two modes will vary from that in free space.. Hence, in this contribution we study the theoretical maximum gain and the corresponding optimal power distribution of a Huygens source antenna in a deeply implanted scenario. The encapsulation size and implantation depth, the key parameters affecting the near-field efficiency, are investigated in detail. The Ohmic losses of the electric and magnetic dipole are also discussed for practical design considerations.

关键词： Wireless communication Encapsulation Medical devices Dipole antennas Antenna theory Power distribution Europe Propagation losses Bioelectric phenomena

来源：评论

学校读者我要写书评

暂无评论

I/O Circuit and Sub-5V ESD Protection for Advanced Bonding Interfaces

I/O Circuit and Sub-5V ESD Protection for Advanced Bonding I...

引用

Annual International Symposium on Reliability Physics

作者： M. Krilcic A. Baric S.-H. Lin T. Markovic N. Pantano M. Simicic Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia IMEC Leuven Belgium Dept. of Electronics and Informatics Vrije Universiteit Brussel Brussel Belgium Dept. of Electrical Engineering (ESAT) KU Leuven Leuven Belgium

ISBN: (数字)9798331504779

ISBN: (纸本)9798331504786

This study investigates the impact of electrostatic discharge (ESD) protection on the performance of I/O circuits in 2.5D-chiplet and 3D integrated architectures, focusing on 12-nm FinFET devices. Using 1-ns-pulse ESD stress measurements and S-parameter analysis, it assesses trade-offs between ESD protection effectiveness and the corresponding capacitance and layout area penalties. The findings highlight the challenges of optimizing chiplet interconnects while meeting evolving protection standards. However, as ESD protection capacitance exceeds interconnect capacitance, it introduces severe RC delay penalties, making further reductions in protection levels essential for maintaining system efficiency and integration feasibility.

关键词： Electrostatic discharge protection Three-dimensional displays Transmitters Chiplets Layout Circuits Integrated circuit interconnections Capacitance FinFETs Testing

来源：评论

学校读者我要写书评

暂无评论

A redescription mining framework for post-hoc explaining and relating deep learning models

arXiv

引用

arXiv 2025年

作者： Mihelčić, Matej Grubišić, Ivan Keber, Miha Department of Mathematics Faculty of Science University of Zagreb Bijenička cesta 30 Zagreb10000 Croatia Ruđer Bošković Institute Bijenička cesta 54 Zagreb10000 Croatia Faculty of Electrical Engineering and Computing University of Zagreb Unska cesta 3 Zagreb10000 Croatia

Deep learning models (DLMs) achieve increasingly high performance both on structured and unstructured data. They significantly extended applicability of machine learning to various domains. Their success in making predictions, detecting patterns and generating new data made significant impact on science and industry. Despite these accomplishments, DLMs are difficult to explain because of their enormous size. In this work, we propose a novel framework for post-hoc explaining and relating DLMs using redescriptions. The framework allows cohort analysis of arbitrary DLMs by identifying statistically significant redescriptions of neuron activations. It allows coupling neurons to a set of target labels or sets of descriptive attributes, relating layers within a single DLM or associating different DLMs. The proposed framework is independent of the artificial neural network architecture and can work with more complex target labels (e.g. multi-label or multi-target scenario). Additionally, it can emulate both pedagogical and decompositional approach to rule extraction. The aforementioned properties of the proposed framework can increase explainability and interpretability of arbitrary DLMs by providing different information compared to existing explainable-AI approaches. © 2025, CC BY-NC-ND.

关键词： Adversarial machine learning

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：