Fusing Swarm Intelligence and Self-Assembly for Optimizing Echo State Networks

Computational Intelligence and Neuroscience ◽

10.1155/2015/642429 ◽

2015 ◽

Vol 2015 ◽

pp. 1-15 ◽

Cited By ~ 2

Author(s):

Charles E. Martin ◽

James A. Reggia

Keyword(s):

Self Assembly ◽

Effective Means ◽

Optimality Criteria ◽

Difficult Problem ◽

Benchmark Problems ◽

Objective Functions ◽

Echo State Networks ◽

And Topology ◽

Interacting Networks

Optimizing a neural network’s topology is a difficult problem for at least two reasons: the topology space is discrete, and the quality of any given topology must be assessed by assigning many different sets of weights to its connections. These two characteristics tend to cause very “rough.” objective functions. Here we demonstrate how self-assembly (SA) and particle swarm optimization (PSO) can be integrated to provide a novel and effective means ofconcurrentlyoptimizing a neural network’s weights and topology. Combining SA and PSO addresses two key challenges. First, it creates a more integrated representation of neural network weights and topology so that we have just a single, continuous search domain that permits “smoother” objective functions. Second, it extends the traditional focus of self-assembly, from the growth of predefinedtarget structures, to functional self-assembly, in which growth is driven by optimality criteria defined in terms of the performance of emerging structures on predefinedcomputational problems. Our model incorporates a new way of viewing PSO that involves a population of growing, interacting networks, as opposed to particles. The effectiveness of our method for optimizing echo state network weights and topologies is demonstrated through its performance on a number of challenging benchmark problems.

Download Full-text

A Brief Look at Multi-Criteria Problems: Multi-Threshold Optimization versus Pareto-Optimization

Multicriteria Optimization - Pareto-Optimality and Threshold-Optimality ◽

10.5772/intechopen.91169 ◽

2020 ◽

Author(s):

Nodari Vakhania ◽

Frank Werner

Keyword(s):

Optimization Problems ◽

Optimality Criteria ◽

General Notion ◽

Objective Functions ◽

Objective Criterion ◽

Solution Quality ◽

Pareto Optimal Set ◽

Threshold Optimization ◽

Feasible Solutions

Multi-objective optimization problems are important as they arise in many practical circumstances. In such problems, there is no general notion of optimality, as there are different objective criteria which can be contradictory. In practice, often there is no unique optimality criterion for measuring the solution quality. The latter is rather determined by the value of the solution for each objective criterion. In fact, a practitioner seeks for a solution that has an acceptable value of each of the objective functions and, in practice, there may be different tolerances to the quality of the delivered solution for different objective functions: for some objective criteria, solutions that are far away from an optimal one can be acceptable. Traditional Pareto-optimality approach aims to create all non-dominated feasible solutions in respect to all the optimality criteria. This often requires an inadmissible time. Besides, it is not evident how to choose an appropriate solution from the Pareto-optimal set of feasible solutions, which can be very large. Here we propose a new approach and call it multi-threshold optimization setting that takes into account different requirements for different objective criteria and so is more flexible and can often be solved in a more efficient way.

Download Full-text

Urban stormwater: the analysis of the failure of the alternative techniques and the management of quality

Water Science & Technology ◽

10.2166/wst.1995.0009 ◽

1995 ◽

Vol 32 (1) ◽

pp. 33-39

Author(s):

E. Alfakih ◽

S. Barraud ◽

Y. Azzout ◽

B. Chocat

Keyword(s):

Stormwater Management ◽

Difficult Problem ◽

Management Approach ◽

Alternative Technique ◽

Urban Stormwater ◽

Urban Stormwater Management ◽

Porous Pavement ◽

Alternative Techniques ◽

Design Construction

The implementation of alternative techniques in urban stormwater management is a difficult problem in terms of choice, design, construction, and operating. We applied a quality management approach to try and have a better understanding of these techniques. The quality of an alternative technique in urban stormwater management is defined; the factors that lead to failures were identified and analysed. In order to reduce these factors, tools were developed, and measures that allow the achievement of the necessary standard of quality are suggested. In this article, all the illustrations refer to the porous pavement technique.

Download Full-text

Multi-Task Optimization and Multi-Task Evolutionary Computation in the Past Five Years: A Brief Review

Mathematics ◽

10.3390/math9080864 ◽

2021 ◽

Vol 9 (8) ◽

pp. 864

Author(s):

Qingzheng Xu ◽

Na Wang ◽

Lei Wang ◽

Wei Li ◽

Qian Sun

Keyword(s):

Evolutionary Computation ◽

Explicit Knowledge ◽

Optimization Problems ◽

Effective Means ◽

Typical Application ◽

The Past ◽

Current State ◽

Evolution Algorithms ◽

Application Fields

Traditional evolution algorithms tend to start the search from scratch. However, real-world problems seldom exist in isolation and humans effectively manage and execute multiple tasks at the same time. Inspired by this concept, the paradigm of multi-task evolutionary computation (MTEC) has recently emerged as an effective means of facilitating implicit or explicit knowledge transfer across optimization tasks, thereby potentially accelerating convergence and improving the quality of solutions for multi-task optimization problems. An increasing number of works have thus been proposed since 2016. The authors collect the abundant specialized literature related to this novel optimization paradigm that was published in the past five years. The quantity of papers, the nationality of authors, and the important professional publications are analyzed by a statistical method. As a survey on state-of-the-art of research on this topic, this review article covers basic concepts, theoretical foundation, basic implementation approaches of MTEC, related extension issues of MTEC, and typical application fields in science and engineering. In particular, several approaches of chromosome encoding and decoding, intro-population reproduction, inter-population reproduction, and evaluation and selection are reviewed when developing an effective MTEC algorithm. A number of open challenges to date, along with promising directions that can be undertaken to help move it forward in the future, are also discussed according to the current state. The principal purpose is to provide a comprehensive review and examination of MTEC for researchers in this community, as well as promote more practitioners working in the related fields to be involved in this fascinating territory.

Download Full-text

Investigation of the Preparation of Anodized Nanoporous Alumina Array

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.887-888.766 ◽

2014 ◽

Vol 887-888 ◽

pp. 766-769 ◽

Cited By ~ 1

Author(s):

Huey Ling Chang ◽

Chih Ming Chen ◽

Chin Huang Sun ◽

Jin Shyong Lin

Keyword(s):

Anodic Oxidation ◽

Self Assembly ◽

Aluminum Surface ◽

Nanostructured Film ◽

Oxidation Treatment ◽

Anodic Aluminum ◽

Nanoporous Template ◽

Anodic Oxidation Treatment ◽

Stable Control

This study produced a regularly arranged membrane, called anodic aluminum oxide (referred AAO), by mean of anodic oxidation treatment. The structure of AAO can be molecular self-assembly and its pore size is consistent. Also, the manufacturing process cost is low. These properties make the AAO be a nanotemplate material. This study further created a high quality of nanostructured film by electrochemical mould with the design of electrolyzer. In addition, a uniform nanothin film was grown on the aluminum surface in the stable control of current and temperature according to the conditions of different anode treatment. This film can form a nanopore array which the diameter can be controlled the size ranging from 15 nm to 400 nm. As results, the study can produce nanoporous template for various aperture by mean of anodic oxidation.

Download Full-text

Neurotechnology as a factor of the educational process transformation

Vocational education and labour market ◽

10.52944/port.2021.47.4.007 ◽

2021 ◽

pp. 98-13

Author(s):

Л.Д. Александрова ◽

Р.А. Богачева ◽

Т.А. Чекалина ◽

М.В. Максимова ◽

В.И. Тимонина

Keyword(s):

Effective Means ◽

Individual Characteristics ◽

Educational Process ◽

Special Equipment ◽

Research Areas ◽

Long Time ◽

Mental Abilities ◽

The Individual ◽

And Control

Изучение возможностей мозга для повышения качества обучения находится в центре внимания педагогической науки уже много лет. Развитие цифровизации позволило использовать в исследованиях специальное оборудование, с помощью которого можно оценивать и контролировать работу мозга, развивать умственные способности, познавательные функции и т. п. Нейротехнологии стали эффективным средством, позволяющим трансформировать образовательный процесс за счет подбора специального учебного контента с учетом индивидуальных особенностей обучающихся. Вместе с тем возникает необходимость в конкретизации терминологии и определении актуальных направлений исследований в данной области. For a long time, the study of the brain capabilities for the improvement of the quality of education has been an urgent direction in pedagogical science. Due to the development of digitalization, new areas of research have emerged related to the use of special equipment that makes it possible to assess and control brainwork, develop mental abilities, cognitive functions, etc. One of them is neurotechnology, which is an effective means of transforming the educational process: it offers educational content based on the individual characteristics of students. Thus, a need to concretize the terminology and determine the current research areas arises. The article aims to attempt to fill this gap with the help of a representative analysis of publications on neurotechnologies, as well as the essence of neuroeducation.

Download Full-text

An open-source R-package and web application for high-quality probabilistic predictions in hydrology

10.5194/egusphere-egu21-8549 ◽

2021 ◽

Author(s):

Jason Hunter ◽

Mark Thyer ◽

Dmitri Kavetski ◽

David McInerney

Keyword(s):

Open Source ◽

Web Application ◽

R Package ◽

Error Model ◽

Objective Functions ◽

High Quality ◽

Wide Range ◽

Probabilistic Error

Probabilistic predictions provide crucial information regarding the uncertainty of hydrological predictions, which are a key input for risk-based decision-making. However, they are often excluded from hydrological modelling applications because suitable probabilistic error models can be both challenging to construct and interpret, and the quality of results are often reliant on the objective function used to calibrate the hydrological model.We present an open-source R-package and an online web application that achieves the following two aims. Firstly, these resources are easy-to-use and accessible, so that users need not have specialised knowledge in probabilistic modelling to apply them. Secondly, the probabilistic error model that we describe provides high-quality probabilistic predictions for a wide range of commonly-used hydrological objective functions, which it is only able to do by including a new innovation that resolves a long-standing issue relating to model assumptions that previously prevented this broad application. &#160;We demonstrate our methods by comparing our new probabilistic error model with an existing reference error model in an empirical case study that uses 54 perennial Australian catchments, the hydrological model GR4J, 8 common objective functions and 4 performance metrics (reliability, precision, volumetric bias and errors in the flow duration curve). The existing reference error model introduces additional flow dependencies into the residual error structure when it is used with most of the study objective functions, which in turn leads to poor-quality probabilistic predictions. In contrast, the new probabilistic error model achieves high-quality probabilistic predictions for all objective functions used in this case study.The new probabilistic error model and the open-source software and web application aims to facilitate the adoption of probabilistic predictions in the hydrological modelling community, and to improve the quality of predictions and decisions that are made using those predictions. In particular, our methods can be used to achieve high-quality probabilistic predictions from hydrological models that are calibrated with a wide range of common objective functions.

Download Full-text

Research on intervention methods of nosocomial infection in neurosurgery

Reports in Clinical Studies and Medicine ◽

10.18282/rcsm.v2.i1.782 ◽

2020 ◽

Vol 2 (1) ◽

pp. 5

Author(s):

Sung-Won Kim

Keyword(s):

Risk Factors ◽

Drug Resistance ◽

Infection Rate ◽

Effective Means ◽

Severe Trauma ◽

High Infection Rate ◽

Intervention Measures ◽

Bacterial Drug Resistance ◽

High Infection

The proportion of critically ill patients from neurosurgery wards in hospitals is significantly higher than that from other departments. These patients suffer from low immune. At the same time, because of the severe trauma after surgery and the complexity of pathogens in patients, antibiotics are frequently used. However, the of bacterial drug resistance is relatively high because of the particularity of hospitals, which is a major reason for the high infection rate of neurosurgery patients. Therefore, regarding to these risk factors, intervention measures should be actively explored in hospitals, so as to control the infection rate, reduce the possibility of infection in neurosurgery patients, improve the rehabilitation efficiency of patients, and reduce unnecessary suffering of patients caused by infection. This is also an effective means to improve the quality of hospital medical care.

Download Full-text

An evolutionary-based optimization algorithm for truss sizing design

Vietnam Journal of Mechanics ◽

10.15625/0866-7136/7476 ◽

2016 ◽

Vol 38 (4) ◽

pp. 307-317

Author(s):

Pham Hoang Anh

Keyword(s):

Local Search ◽

Objective Function ◽

Optimization Algorithm ◽

Optimization Problems ◽

Optimal Solution ◽

The Other ◽

Truss Structures ◽

Benchmark Problems ◽

Discrete Variables ◽

Objective Functions

In this paper, the optimal sizing of truss structures is solved using a novel evolutionary-based optimization algorithm. The efficiency of the proposed method lies in the combination of global search and local search, in which the global move is applied for a set of random solutions whereas the local move is performed on the other solutions in the search population. Three truss sizing benchmark problems with discrete variables are used to examine the performance of the proposed algorithm. Objective functions of the optimization problems are minimum weights of the whole truss structures and constraints are stress in members and displacement at nodes. Here, the constraints and objective function are treated separately so that both function and constraint evaluations can be saved. The results show that the new algorithm can find optimal solution effectively and it is competitive with some recent metaheuristic algorithms in terms of number of structural analyses required.

Download Full-text

THE EFFECT OF PHYSICAL EXERCISE ON THE REHABILITATION QUALITY OF HUMAN WAIST DYSFUNCTION

Revista Brasileira de Medicina do Esporte ◽

10.1590/1517-8692202127032021_0084 ◽

2021 ◽

Vol 27 (3) ◽

pp. 315-318

Author(s):

Fanfan Li

Keyword(s):

Quality Of Life ◽

Effective Means ◽

Training Group ◽

Abdominal Muscle ◽

Motor Dysfunction ◽

Control Group ◽

Treatment Results ◽

Level Of Evidence ◽

Human Motor

ABSTRACT Introduction Human motor dysfunction can affect the quality of life, especially waist dysfunction. And an effective means to improve muscle strength during exercise. Object This article compares and analyzes the effectiveness of human muscle exercise on the decline in quality of life caused by motor dysfunction. Method The article divides patients with motor dysfunction into trunk isokinetic training group (experimental group) and waist and abdominal muscle functional training group (control group), and comparative analysis of related indicators before and after treatment. Results Before treatment, the specific indicators of the two were different (P>0.05). After treatment, the patients’ quality of life indicators and motor function indicators were significantly different (P<0.05). Conclusion Exercise has an obvious curative effect for patients with human motor dysfunction, and it is worthy of clinical promotion. Level of evidence II; Therapeutic studies - investigation of treatment results.

Download Full-text