检索结果-内蒙古大学图书馆

bio-inspired algorithm for outliers detection

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第24期76卷 25659-25677页

作者： Forestiero, Agostino Natl Res Council Italy Inst High Performance Comp & Networking CNR ICAR Via Pietro Bucci 7-11 C I-87036 Arcavacata Di Rende CS Italy

An essential activity to obtain valuable information to identify, for example, intrusions, faults, system failures, etc, is outliers detection. This paper proposes a bio-inspired algorithm able to detect anomaly data in distributed systems. Each data object is associated with a mobile agent that follows the well-known bio-inspired algorithm of flocking. The agents are randomly disseminated onto a virtual space where they move autonomously in order to form one or more flocks. Through a tailored similarity function, the agents associated with similar objects join in the same flock, whereas, the agents associated with dissimilar objects do not join in any flock. The objects associated with isolated agents or associated with agents grouped into flock with a number of entities lower than a given threshold, represent the outliers. Experimental results on synthetic and real data sets confirm the validity of the approach.

关键词： Outliers detection Data streams bio-inspired algorithm Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

bio-inspired algorithm for QoS Optimization in Information-Centric Networking 5

Bio-Inspired Algorithm for QoS Optimization in Information-C...

引用

5th International Conference on Computing, Engineering, and Design (ICCED)

作者： Safitri, Cutifa Yamada, Yoshihide Goudarzi, Shidrokh Mantoro, Teddy Ayu, Media Anugerah Univ Teknol Malaysia Malaysia Japan Int Inst Technol Kuala Lumpur Malaysia Univ Teknol Malaysia Adv Informat Sch Kuala Lumpur Malaysia Sampoerna Univ Dept Comp Sci Jakarta Indonesia

ISBN: (纸本)9781728120942

Information-Centric Networking (ICN) is a paradigm shift for Future Internet Architecture to eliminate issues in current implemented network. To date mobile communication still bring challenges due to diversity of network access characteristics. To achieve high Quality of Service (QoS), an intelligent services and mechanism is primly essential. Hence, the problem with ICN is articulated as an optimization problem to sustain the desired Quality of Service (QoS). These requirements motivate this study to improve the mobile QoS by hybridization of bio-inspired algorithm in the communication architecture. The proposed intelligent algorithm comprised of mutation, migration and crossover stages. For this, a cost function is designed and adopted in the selected bio-inspired algorithms to evaluate their performance in QoS optimization process. The statistical findings display the superiority of bioGeography Based Optimization scheme in comparison to the other algorithms.

关键词： Information-Centric Networking ICN bio-inspired algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic segmentation of gallbladder using bio-inspired algorithm based on a spider web construction model

引用

JOURNAL OF SUPERCOMPUTING 2019年第6期75卷 3158-3183页

作者： Muneeswaran, V Rajasekaran, M. Pallikonda Kalasalingam Acad Res & Educ Dept Instrumentat & Control Engn Srivilliputur Post 626126 Tamil Nadu India Kalasalingam Acad Res & Educ Dept Elect & Commun Engn Srivilliputur Post 626126 Tamil Nadu India

In medical image processing, an accurate segmentation and classification are very important and this field still needs an effective computer-based algorithm for accomplishing the task. In gallbladder segmentation, only few automatic segmentation methodologies have been presented. The accuracy is very important in medical image processing for accurate diagnosis of the disease. In this paper, by exploiting the basic web building behavior of spiders, we developed a bio-inspired algorithm based on the spider web construction process for image segmentation process in medical images. The aim of this paper is to detect the shape of the gallbladder and to segment the gallstones and polyps located inside the gallbladder using a computer-based algorithm. It is necessary to apply a suitable preprocessing method in order to eliminate the irregularities presenting in the ultrasound scan images. In the preprocessing stage, histogram equalization and DooG filter are applied to enhance the contrast of the image. After that, the proposed spider web algorithm is applied in the segmentation process. The performance metrics of the proposed method are evaluated by implementing the proposed method to test the input dataset of 60 patients and it is compared with the results obtained from conventional segmentation methods. The values of DSC, OF, OV and PE for images with no lesions are 0.873167, 0.8389, 0.81705 and 0.81452.

关键词： Gallbladder segmentation Gallstone segmentation bio-inspired algorithm Spider web construction

来源：评论

学校读者我要写书评

暂无评论

Recognition of archaic Lanna handwritten manuscripts using a hybrid bio-inspired algorithm

引用

MEMETIC COMPUTING 2015年第1期7卷 3-17页

作者： Thammano, Arit Pravesjit, Sakkayaphop King Mongkuts Inst Technol Ladkrabang Fac Informat Technol Bangkok 10520 Thailand

This paper proposes a new character recognition system for archaic Lanna handwritten characters. The proposed system consists of two main processes: the segmentation process and the recognition process. The segmentation process decomposes the touching or overlapping characters, commonly found in Lanna manuscripts, into isolated characters. In the recognition process, the proposed system uses the self-organizing map to divide the input images into several clusters. The clonal selection algorithm of the artificial immune system is then used to build a recognition model for each cluster created by the self-organizing map. Finally, the particle swarm optimization is employed as a local search mechanism. The proposed system was evaluated and compared to several state-of-the-art approaches. The experimental results demonstrate that the proposed system is very effective in recognizing not only Lanna characters but also the handwritten numerals of the five most popular scripts.

关键词： Archaic manuscript bio-inspired algorithm Character recognition Hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

A bio-inspired algorithm for a classical water resources allocation problem based on Adleman-Lipton model

引用

DESALINATION AND WATER TREATMENT 2020年第0期185卷 168-174页

作者： Deng, Anjun Wang, Zhaocai Liu, Haifeng Wu, Tunhua China Inst Water Resources & Hydropower Res State Key Lab Simulat & Regulat River Basin Water Beijing 100048 Peoples R China Shanghai Ocean Univ Coll Informat Shanghai 201306 Peoples R China Wenzhou Med Univ Affiliated Hosp 1 Wenzhou 325035 Peoples R China

The shortage of water resources has always been one of the difficult problems that plagued world economic development and social stability. The imbalance and uneven distribution of water resources between regions exacerbate this contradiction. Therefore, the optimal economical and reasonable water resource design method has become the hope for solving the problem of water resource shortage. As a classic resource allocation and scheduling problem, the rural postman problem has been widely used in practice. The problem includes finding the minimum cost tour after traversing all edges in the required edge subset at least once in an undirected graph, but so far, there is no effective algorithm to solve this problem. Based on bio-heuristic computing model and deoxyribonucleic acid (DNA) molecular operations, a parallel bio-computing algorithm for rural postman problem is proposed in the paper. We use a DNA algorithm to solve the rural postman problem with n vertices in O(n(2)) time complexity. Then, we prove the feasibility of the algorithm in theory and verify the authenticity of the algorithm in the simulation experiment. Compared with previous algorithms, DNA computing algorithm not only has higher computational efficiency and lower error rate but also has huge storage capacity and parallel computing ability, which makes the algorithm has better applicability in dealing with large-scale problems.

关键词： Water resources dispatching Rural postman problem Adleman-Lipton model bio-inspired algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed Synchronization Technique for OFDMA-Based Wireless Mesh Networks Using a bio-inspired algorithm

引用

SENSORS 2015年第8期15卷 18287-18301页

作者： Kim, Mi Jeong Maeng, Sung Joon Cho, Yong Soo Chung Ang Univ Sch Elect & Elect Engn Seoul 156756 South Korea

In this paper, a distributed synchronization technique based on a bio-inspired algorithm is proposed for an orthogonal frequency division multiple access (OFDMA)-based wireless mesh network (WMN) with a time difference of arrival. The proposed time- and frequency-synchronization technique uses only the signals received from the neighbor nodes, by considering the effect of the propagation delay between the nodes. It achieves a fast synchronization with a relatively low computational complexity because it is operated in a distributed manner, not requiring any feedback channel for the compensation of the propagation delays. In addition, a self-organization scheme that can be effectively used to construct 1-hop neighbor nodes is proposed for an OFDMA-based WMN with a large number of nodes. The performance of the proposed technique is evaluated with regard to the convergence property and synchronization success probability using a computer simulation.

关键词： wireless mesh network OFDMA bio-inspired algorithm distributed synchronization time difference of arrival time synchronization frequency synchronization

来源：评论

学校读者我要写书评

暂无评论

Global Maximum Power Point Tracking of Photovoltaic Systems Using bio-inspired algorithm-Based MPPT and One-Cycle Control

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2024年第5期49卷 6799-6814页

作者： Nisha, R. Sheela, K. Gnana APJ Abdul Kalam Technol Univ Dept Elect & Elect Engn TIST Thiruvananthapuram 695016 Kerala India APJ Abdul Kalam Technol Univ TIST Thiruvananthapuram 695016 Kerala India

The clean and abundant nature of photovoltaic technology makes it eminent among other renewable energy sources and to obtain the best benefit from these sources, an efficient maximum power point tracking technique is needed that can produce the required output even under varying environmental conditions. This work deals with the development of a global maximum power point tracking technique combining bio-inspired algorithms and one-cycle control which helps in effective tracking even under partial shading conditions. This technique generates signals for the KY converter from the duty cycle obtained from bio-inspired algorithms. The voltage at the output of the photovoltaic panel is fed to the load through KY converter. The analysis of the system is carried out using resistive load under different patterns of the photovoltaic array using particle swarm optimization, flower pollination and flying squirrel search optimization algorithms through simulation and experimentation. The performance indices like tracking speed, tracking efficiency and steady-state oscillations are taken for comparison with the existing systems without one-cycle control, and the results indicate its capability in GMPP tracking with an average efficiency and tracking time of 99.1% and 0.13 s, respectively.

关键词： bio-inspired algorithm Global maximum power point Partial shading Particle swarm optimization One-cycle control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Social Media Profile Authenticity Detection: A bio-inspired algorithm Approach 1

引用

6th International Conference on Machine Learning for Networking (MLN)

作者： Mahammed, Nadir Klouche, Badia Saidi, Imene Khaldi, Miloud Fahsi, Mahmoud Ecole Super Informat Sidi Bel Abbes LabRI SBA Lab PO 73 Sidi Bel Abbes 22016 Algeria Univ Djillali Liabes Sidi Bel Abbes EEDIS Lab PO 89 Sidi Bel Abbes 22000 Algeria

ISBN: (数字)9783031599330

ISBN: (纸本)9783031599323;9783031599330

In the contemporary digital landscape, the pervasive and far-reaching impact of online social networks is indisputable. Prominent platforms such as Instagram, Facebook, and Twitter frequently grapple with the persistent challenge of distinguishing between registered profiles and genuinely engaged users, resulting in a noticeable surge in the prevalence of counterfeit or dormant accounts. This situation underscores the compelling necessity to accurately differentiate between authentic and misleading user profiles. The primary objective of this investigation is to introduce an innovative approach to profile validation. This unique method astutely leverages state-of-the-art bio-inspired algorithms while circumventing traditional machine learning techniques. The empirical results are notably convincing, consistently achieving a high level of accuracy in classification tests conducted on the provided datasets.

关键词： Online social network Fake profile detection bio-inspired algorithm Machine learning Instagram Facebook Twitter Simulation

来源：评论

学校读者我要写书评

暂无评论

Barnacles Mating Optimizer: A bio-inspired algorithm for Solving Optimization Problems 19

Barnacles Mating Optimizer: A Bio-Inspired Algorithm for Sol...

引用

19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)

作者： Sulaiman, Mohd Herwan Mustaffa, Zuriani Saari, Mohd Mawardi Daniyal, Hamdan Daud, Mohd Razali Razali, Saifudin Mohamed, Amir Izzani Univ Malaysia Pahang Fak Kejuruteraan Elekt & Elekt Pekan Malaysia Univ Malaysia Pahang Fak Sistem Komputer & Kejuruteraan Perisian Kuantan Malaysia

ISBN: (纸本)9781538658895

A novel bio-inspired optimization algorithm is proposed in this paper namely barnacles mating optimizer (BMO) algorithm. The main inspiration of BMO is originated from the mating behavior of barnacles in nature. Barnacles are hermaphroditic micro-organisms which have both male and female sex reproductions. To create new off-springs, they must be fertilized by a neighbor. They are well-known for their long penises, about seven times the length of their bodies to cope with the changing tides and sedentary lifestyle. In BMO, the selection of barnacle's parents is decided randomly by the length of barnacle's penis to create new off-springs. The exploitation and exploration processes are the generation of new off-springs inspired by the Hardy- Weinberg principle and sperm cast situation, respectively. The effectiveness of proposed BMO is tested through a set of benchmark multi-dimensional functions which the global and local minimum are known. Comparisons with other recent algorithms also will be presented in this paper.

关键词： barnacles mating optimizer benchmark functions bio-inspired algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Web Services Clustering using a bio-inspired algorithm 26

Web Services Clustering using a Bio-inspired Algorithm

引用

26th International Workshop on Database and Expert Systems Applications (DEXA)

作者： Mora, Roman Santillan-Perez, Saul Bravo, Maricela UAM Azcapotzalco Dept Syst Azcapotzalco DF Mexico

ISBN: (纸本)9781467375818

In this work we describe a bio-inspired algorithm for Web service clustering, in particular we present an adaptation of the Ant Colony Optimization (ACO) algorithm which is applied over a collection of Web service descriptions. The adapted ACO uses input and output parameter definitions to calculate semantic similarity measures between all the different Web services. A set of experiments were carried out with promising results that show the benefits of the ACO algorithm for Web services clustering.

关键词： Web services clustering bio-inspired algorithm Ant-based Clustering

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：