检索结果-内蒙古大学图书馆

7th International Conference on Optimization and Learning

作者： Alizadeh, Sina Mouhoub, Malek Univ Regina Dept Comp Sci Regina SK Canada

ISBN: (纸本)9783031779404;9783031779411

Video game designers frequently employ different movement algorithms to give players the impression of the intelligent and unpredictable motions of non-player characters or enemy agents. This paper explores the application of metaheuristic biological algorithms in video games to enhance the unpredictability and realism of enemy characters, moving away from traditional pre-programmed NPC behaviors. Developing the bespoke game "Run and Catch" incorporates the utilization of Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) for directing the movement of non-player characters. We tackle the premature convergence challenge by introducing an adaptive Finder - Tracker agent approach. This mechanism maintains diversity in enemy movements to ensure responsiveness to real-time player character activities. The findings illustrate the adverse effects of early convergence on both immersion and the variety of non-player character movements within a 2D game environment. Moreover, the study underscores the success of ACO and PSO, equipped with the Finder- Tracker agent framework, in reshaping group movements of non-player characters and effectively dealing with the convergence challenge.

关键词： bio-inspired algorithms Video Games Non-Player Characters (NPCs)

来源：评论

学校读者我要写书评

暂无评论

bio-inspired machine learning: programmed death and replication

引用

NEURAL COMPUTING & APPLICATIONS 2023年第27期35卷 20273-20298页

作者： Grabovsky, Andrey Vanchurin, Vitaly Budker Inst Nucl Phys Novosibirsk 630090 Russia Novosibirsk State Univ Novosibirsk 630090 Russia Natl Ctr Biotechnol Informat NIH Bethesda MD 20894 USA Duluth Inst Adv Study Duluth MN 55804 USA

We analyze algorithmic and computational aspects of biological phenomena, such as replication and programmed death, in the context of machine learning. We use two different measures of neuron efficiency to develop machine learning algorithms for adding neurons to the system (i.e., replication algorithm) and removing neurons from the system (i.e., programmed death algorithm). We argue that the programmed death algorithm can be used for compression of neural networks and the replication algorithm can be used for improving performance of the already trained neural networks. We also show that a combined algorithm of programmed death and replication can improve the learning efficiency of arbitrary machine learning systems. The computational advantages of the bio-inspired algorithms are demonstrated by training feedforward neural networks on the MNIST dataset of handwritten images.

关键词： Machine learning Neural networks bio-inspired algorithms Neuron correlations Pruning algorithms Constructive algorithms Classification

来源：评论

学校读者我要写书评

暂无评论

Adaptive Chaotic Marine Predators Hill Climbing Algorithm for Large-Scale Design Optimizations

引用

IEEE ACCESS 2023年 11卷 39269-39294页

作者： Dehkordi, Amin Abdollahi Etaati, Bahareh Neshat, Mehdi Mirjalili, Seyedali Islamic Azad Univ Dept Comp Engn Najafabad Branch Najafabad Iran Univ Appl Sci Upper Austria Josef Ressel Ctr Symbol Regress A-4232 Hagenberg Austria Torrens Univ Australia Ctr Artificial Intelligence Res & Optimizat Brisbane Qld 4006 Australia Univ Technol Sydney Fac Engn & Informat Technol Ultimo NSW 2007 Australia

Meta-heuristic algorithms have been effectively employed to tackle a wide range of optimisation issues, including structural engineering challenges. The optimisation of the shape and size of large-scale truss structures is complicated due to the nonlinear interplay between the cross-sectional and nodal coordinate pressures of structures. Recently, it was demonstrated that the newly proposed Marine Predator Algorithm (MPA) performs very well on mathematical challenges. The MPA is a meta-heuristic that simulates the essential hunting habits of natural marine predators. However, this algorithm has some disadvantages, such as becoming locked in locally optimal solutions and not exhibiting high exploratory behaviour. This paper proposes two hybrid marine predator algorithms, Nonlinear Marine Predator (HNMPA) and Nonlinear-Chaotic Marine Predator Algorithm (HNCMPA), as improved variations of the marine predator algorithm paired with a hill-climbing (HC) technique for truss optimisation on form and size. The major advantage of these techniques is that they seek to overcome the MPA's disadvantages by using nonlinear values and prolonging the exploration phase with chaotic values;also, the HC algorithm has been used to avoid locally optimum solutions. In terms of truss optimisation performance, the proposed algorithm is compared to fourteen well-known meta-heuristics, including the Dragonfly Algorithm (DA), Henry Gas Solubility optimisation (HGSO), Arithmetic optimisation Algorithm (AOA), Generalized Normal Distribution Optimisation (GNDO), Salp Swarm Algorithm (SSA), Marine Predators Algorithm (MPA), Neural Network Algorithm (NNA), Water Cycle Algorithm (WCA), Artificial Gorilla Troops Optimiser (GTO), Gray Wolf Optimiser (GWO), Moth Flame Optimiser (MFO), Multi-Verse Optimiser (MVO), Equilibrium Optimiser (EO), and Cheetah Optimiser (CO). Furthermore, seven algorithms were chosen to test HNCMPA performance on benchmark optimisation sets, including MPA, MVO, PSO, MFO, SSA,

关键词： Optimization Metaheuristics Heuristic algorithms Convergence Genetic algorithms Search problems Particle swarm optimization bio-inspired algorithms hybrid algorithms marian predators algorithm meta-heuristics optimization method truss optimization

来源：评论

学校读者我要写书评

暂无评论

Last-Mile Delivery Optimization Using Mixed Electric Vehicles, UAVs and Full Truck Delivery Based on Artificial Intelligence algorithms 5th

Last-Mile Delivery Optimization Using Mixed Electric Vehicle...

引用

5th International Conference on Innovative Intelligent Industrial Production and Logistics

作者： Hanaa, Bouhia Benhra, Jamal Ed-dehbi, Wissal ESITH Casablanca Morocco Univ Hassan 2 ENSEM Casablanca Morocco

ISBN: (纸本)9783031807749;9783031807756

This paper presents the Electric Vehicle Routing Problem with Drones (EVRPD), a novel strategy aimed at enhancing last-mile delivery through the combined use of Electric Vehicles (EVs) and drones. The primary objective is to reduce energy usage and CO2 emissions while maintaining effective delivery operations. The proposed system employs a diverse fleet where EVs act as mobile bases, and drones handle the final leg of parcel delivery. Both EVs and drones can deliver packages, with drones being utilized for smaller, time-sensitive shipments. The system emphasizes optimal payload distribution to boost energy efficiency and drone endurance. Drones are resupplied on the EVs' rooftops via IoT technology. To address the routing challenge, the solution leverages bio-inspired algorithms, including Ant Colony Optimization (ACO) for EVs and Particle Swarm Optimization (PSO) for drones. This methodology enhances energy efficiency and drone autonomy, ensuring effective parcel delivery. By incorporating these advanced techniques, EVRPD presents a promising approach for a more sustainable and effective urban logistics network.

关键词： EVRPD Last-mile delivery Energy efficiency CO2 reduction EVs Drones bio-inspired algorithms ACO PSO

来源：评论

学校读者我要写书评

暂无评论

Expedited Machine-Learning-Based Global Design Optimization of Antenna Systems Using Response Features and Multi-fidelity EM Analysis 24th

Expedited Machine-Learning-Based Global Design Optimization ...

引用

24th International Conference on Computational Science (ICCS)

作者： Pietrenko-Dabrowska, Anna Koziel, Slawomir Leifsson, Leifur Gdansk Univ Technol Fac Elect Telecommun & Informat Narutowicza 11-12 PL-80233 Gdansk Poland Reykjavik Univ Engn Optimizat & Modeling Ctr Dept Engn Menntavegur 1 IS-102 Reykjavik Iceland Purdue Univ Sch Aeronaut & Astronaut W Lafayette IN 47907 USA

ISBN: (纸本)9783031637742;9783031637759

The design of antenna systems poses a significant challenge due to stringent performance requirements dictated by contemporary applications and the high computational costs associated with models, particularly full-wave electromagnetic (EM) analysis. Presently, EM simulation plays a crucial role in all design phases, encompassing topology development, parametric studies, and the final adjustment of antenna dimensions. The latter stage is especially critical as rigorous numerical optimization becomes essential for achieving optimal performance. In an increasing number of instances, global parameter tuning is necessary. Unfortunately, the use of nature-inspired algorithms, the prevalent choice for global design, is hindered by their poor computational efficiency. This article presents an innovative approach to cost-efficient global optimization of antenna input characteristics. Our methodology leverages response feature technology, ensuring inherent regularization of the optimization task by exploring the nearly-linear dependence between the coordinates of feature points and the antenna's dimensions. The optimization process is structured as a machine learning (ML) procedure, utilizing a kriging surrogate model rendering response features to generate promising candidate designs (infill points). This model is iteratively refined using accumulated EM simulation data. Further acceleration is achieved by incorporating multi-fidelity EM analysis, where initial sampling and surrogate model construction use low-fidelity EM simulations, and the ML optimization loop employs high-fidelity EM analysis. The multi-fidelity EM simulation data is blended into a single surrogate using co-kriging. Extensive verification of the presented algorithm demonstrates its remarkable computational efficiency, with an average running cost not exceeding ninety EM simulations per run and up to a seventy percent relative speedup over the single-fidelity procedure.

关键词： Antenna design global optimization computer-aided design response features bio-inspired algorithms variable-fidelity EM analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing the cryptographic key using sample entropy and whale optimization algorithm

引用

International Journal of Information Technology (Singapore) 2024年第3期16卷 1733-1741页

作者： Jawed, Md Saquib Sajid, Mohammad Department of Computer Science Aligarh Muslim University Aligarh India

Internet-of-Things (IoT) is one of the most rapidly developing technologies of the twenty-first century. With the invention of 5G technology and the support of the fog-cloud paradigm, IoT has boosted its growth exponentially. Billions of IoT devices exchange data every second, putting data security and privacy at risk and leading to the development of various cryptographic algorithms yearly. A cryptographic key is essential to any cryptographic algorithm, which should be highly randomized and unpredictable. This paper suggests a novel algorithm SampEn-WOA to generate cryptographic keys by utilizing sample entropy, V-Type transfer function, and whale optimization algorithm (WOA). The cryptographic keys of various lengths are generated for the state-of-the-art algorithms, namely advanced encryption standard (AES), SIMON, data encryption standard (DES), SPECK, 3DES, and PRESENT Ciphers. A comparison study is also performed to evaluate the strength of cryptographic keys of various lengths based on sample entropy and approximate entropy. The results are promising and suggest using SampEn-WOA for various state-of-the-art cryptographic algorithms. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Approximate entropy bio-inspired algorithms Cloud computing Cloud security Cryptography Internet-of-Things Sample entropy

来源：评论

学校读者我要写书评

暂无评论

Comprehensive performance metric for bio-inspired optimizers: a generation-wise population convergence approach toward global optimality

引用

Iran Journal of Computer Science 2025年 1-49页

作者： Thapliyal, Shivankur Kumar, Narender Doon University Dehradun India

Metaheuristic algorithms revolutionize optimization, offering flexibility, scalability, and problem-solving expertise. They excel in diverse domains due to adaptability, parallelism, and global exploration, making them essential in modern computing. Researchers have created numerous metaheuristics, necessitating benchmarking and comparisons to comprehend their capabilities and limitations, considering the “No Free Lunch Theorem”. Despite their prominence, the fundamental questions regarding performance difficulties are only partially answered due to a lack of in-depth analytical analysis. Due to the limitations of conventional metrics such as convergence rate and the quality of the final solution, which often do not provide a comprehensive understanding of an algorithm’s performance and can sometimes be confusing or challenging to interpret. This study introduces a new performance metric that monitors the algorithm’s behavior, including exploration, exploitation, and convergence, across iterations while considering data from all individuals in the population to rectify these limitations. The evaluation of the proposed matrices involves three stages. First, the performance of ten metaheuristic algorithms is analyzed using the proposed metric on 23 benchmark functions with dimensions of 30, 100, 500, and 1000, as well as 30 functions from IEEE CEC-2017 with dimensions of 30 and 15 functions from IEEE CEC-2015 with dimensions of 10. Second, the metric is applied to assess multi-layer perceptron adaptations on eight manifold datasets. Finally, graphical and statistical tools, including error trajectory plots, rating matrices, and Friedman ranking tests, are utilized to provide deeper insights. The results demonstrate the metric’s effectiveness in evaluating the exploration, exploitation, and convergence abilities of the algorithms. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Benchmark functions bio-inspired algorithms Metaheuristics Nature-inspired algorithms Optimization Particle swarm optimization Performance metric Swarm algorithms

来源：评论

学校读者我要写书评

暂无评论

Protection of data privacy from vulnerability using two-fish technique with Apriori algorithm in data mining

引用

JOURNAL OF SUPERCOMPUTING 2022年第16期78卷 17559-17593页

作者： Dhinakaran, D. Prathap, P. M. Joe Anna Univ Informat & Commun Engn Chennai Tamil Nadu India RMD Engn Coll Dept Informat Technol Kavaraipettai Tiruvallur India

The confidential data is mainly managed by creating passwords, tokens, and unique identifiers in an authorized manner. These records must be kept in a safe location away from the reach of unauthorized third parties. Both the client and server sides must be encrypted using the two-fish algorithm, which secures the distinction of private data. By gaining access to the user's information, a data miner may be able to steal it. To avoid such situations, both the data miner and the server must be encrypted. Further, the previous techniques faced several shortcomings in case of higher computational overhead, poor resource utilization, prone to single point failure, lower accuracy, noise, poor security, higher distortion, etc. In this study, both the client and server sides are encrypted using a two-fish algorithm to avoid information loss while transferring data to overcome these problems. The way the state-of-art techniques handled the privacy preservation issue often leads to privacy violations. This paper focuses on mining frequent itemsets present in the medical data by also ensuring privacy. Frequent itemset mining mainly aims to extract highly correlated items from the database and to achieve this novel fruitfly whale optimization algorithm (FWOA) combined with the Apriori algorithm. The Apriori heuristic and bio-inspired algorithms are integrated to solve the frequent itemset problem by reducing the low runtime performance when handling large datasets and also offering high-quality solutions. The adaptive k-anonymity approach is used for preserving data privacy by transforming the original data into an encrypted mode and offering privacy to the top-k frequent itemsets mining. The main advantage of the adaptive k-anonymity approach is that the confidential information disclosed by an individual user cannot be identified from at least k - 1 individuals. We ensure that the proposed methodology can offer data privacy in real time by the experiments conducted in a medica

关键词： Apriori algorithm Data miner Two-fish algorithm Privacy preservation bio-inspired algorithms Association rule mining Adaptive k-anonymity approach

来源：评论

学校读者我要写书评

暂无评论

Improved bees algorithm for the deployment of homogeneous and heterogeneous wireless sensor networks

引用

INTERNATIONAL JOURNAL OF SENSOR NETWORKS 2022年第4期38卷 254-262页

作者： Deghbouch, Hicham Debbat, Fatima Univ Mustapha Stambouli Mascara Dept Comp Sci Mascara Algeria

Nowadays, countless applications benefit from the services provided by wireless sensor networks (WSNs) in remote surveillance and data gathering. Coverage is considered an important quality of service (QoS) criterion for many of these applications. To ensure that the required QoS is achieved, the sensors must be placed in locations that optimise the area coverage and eliminate the coverage holes, especially when deploying sensors with heterogeneous sensing ranges. In this paper, a novel sensor deployment scheme based on the improved bees algorithm (IBA) for optimising the area coverage in both homogeneous and heterogeneous WSNs is proposed. The IBA includes a neighbourhood shrinking procedure that aims to improve the local search efficiency and a site abandonment procedure for preventing the algorithm from the entrapment in a local optimum. Experiments show that the IBA delivers high-quality solutions and optimises the area coverage effectively compared with four state-of-the-art methods in homogeneous and heterogeneous WSNs.

关键词： wireless sensor networks WSNs bio-inspired algorithms metaheuristics coverage redundancy area coverage simulation optimisation

来源：评论

学校读者我要写书评

暂无评论

Navigating the Intersections of Quantum Computing, DNA-Based Data Storage, and Geospatial Data Security: An Overview 8

Navigating the Intersections of Quantum Computing, DNA-Based...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Bhangale, Prajakta Vaikole, Shubhangi Fr.Conceicao Rodrigues College of Engineering Mumbai Univeristy India Datta Meghe College of Engineering Mumbai India Fr. Concicao Rodrigues Institute of Technology Deaprtment Information Technology Mumbai India

ISBN: (纸本)9798350391770

In recent years, the intersection of quantum computing and bioinformatics has emerged as a captivating frontier, promising to reshape the landscape of biological sequence analysis. DNA's ability to store vast information and its stability make it a candidate for secure geospatial data storage. Quantum computing, exemplified by QKD, transforms encryption, enhancing security. bio-inspired algorithms, emulating DNA sequences, optimise problem-solving. Combining these with quantum computing improves geospatial data security through protocol enhancements. Quantum bioinformatics explores quantum computing's potential in genetics and medicine, indirectly reinforcing data security. Integration of DNA-based storage with quantum encryption ensures highly secure data transmission. Geospatial data can be encoded in DNA sequences and encrypted for network transmission. This convergence promises enhanced data security, though implementation needs further research. Overall, these innovations hold potential for advancing geospatial data security. © 2024 IEEE.

关键词： bio-inspired algorithms Data transmission DNA-based data storage Genetic analysis Geospatial data security Personalized medicine Protocol optimization Quantum bioinformatics Quantum computing Quantum encryption

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：