Conecte-se

Bibliografias temáticas / Genetic Algorthim

Índice

Artigos de revistas
Teses / dissertações
Capítulos de livros
Trabalhos de conferências

Literatura científica selecionada sobre o tema "Genetic Algorthim"

Autor: Grafiati

Publicado: 8 de fevereiro de 2025

Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos

Selecione um tipo de fonte:

Consulte a lista de atuais artigos, livros, teses, anais de congressos e outras fontes científicas relevantes para o tema "Genetic Algorthim".

Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.

Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.

Artigos de revistas sobre o assunto "Genetic Algorthim"

1

Yani, Ahmad, Junaidi Junaidi, M. Irwanto e A. H. Haziah. "Optimum reactive power to improve power factor in industry using genetic algortihm". Indonesian Journal of Electrical Engineering and Computer Science 14, n.º 2 (1 de maio de 2019): 751. http://dx.doi.org/10.11591/ijeecs.v14.i2.pp751-757.

Texto completo da fonte

Resumo:

<span>Capacitor bank is a collection of power tools in the form of a capacitor that serves as a tool that can reduce or improve reactive power into the power grid. The load on the electricity network in general is an inductive load. If the average power factor (cos ϴ) is less than 0.85, the State Electricity Company will provide the reactive power in KVAR fines usage charges on customers. An effort should be done to reduce the reactive power. An installation of bank capacitor is suitable to be implemented in an industry AC loads. It will reduce the reactive power and improve the power factor. In the case of 380 V, 50 Hz, 500 kW AC loads are improved the power factor from 0.7 to 0.93 using genetic algorithm, thus the AC loads current and reactive power will be decreased. It is suitable that the AC loads current is inversely proportional to the power factor, and the reactive power is proportional to the AC loads current.</span>

Estilos ABNT, Harvard, Vancouver, APA, etc.

2

Nurdin, Hardisal, Muhammad Zarlis e Erna Budhiarti Nababan. "Teknik Watermarking Adaptif Menggunakan Micro Genetic Algorithm". Jurnal Inotera 1, n.º 1 (27 de julho de 2017): 64. http://dx.doi.org/10.31572/inotera.vol1.iss1.2016.id9.

Texto completo da fonte

Resumo:

Citra digital sangat rentan terhadap perlakuan pengolahan kembali, seperti pemampatan, penyaringan, pengaburan, dan sebagainya. Pada citra yang mengandung watermark, pengolahan kembali tentunya dapat merusak eksistensi watermark di dalamnya. Kekukuhan watermark dalam citra asli dapat ditingkatkan melalui pemilihan teknik-teknik penyisipan yang tepat. Salah satunya dengan menggunakan teknik transformasi citra seperti discrete wavelete transform atau DWT. Namun penentuan skala penyisipan (gain) bagi watermark menjadi sangat krusial, karena dengan nilai gain yang besar akan membuat kualitas visual citra dapat berkurang. Sebaliknya, nilai gain yang terlalu kecil membuat watermark akan sukar untuk dideteksi. Penggunaan teknik cerdas seperti micro genetic algorthm dapat memberika solusi dalam menentukan nilai penskalaan ini. Sehingga kualitas visual citra dapat dijaga dan watermark di dalamnya dapat dipertahankan.

Estilos ABNT, Harvard, Vancouver, APA, etc.

3

Alsuwaiket, M. A. "Feature Extraction of EEG Signals for Seizure Detection Using Machine Learning Algorthims". Engineering, Technology & Applied Science Research 12, n.º 5 (2 de outubro de 2022): 9247–51. http://dx.doi.org/10.48084/etasr.5208.

Texto completo da fonte

Resumo:

Epilepsy is a central nervous system disorder in which brain activity becomes abnormal and causes periods of unusual behavior and sometimes loss of awareness. Epilepsy is a disease that may affect males or females of all ethnic groups and ages. Detecting seizures is challenging due to the difference in human behaviors and brain signals. This paper aims to automate the extraction of electroencephalogram (EEG) signals without referring to doctors using two feature extraction methods, namely Wavelet Packet decomposition (WPD) and Genetic Algorithm-Based Frequency-Domain Feature Search (GAFDS). Three machine learning algorithms were applied, namely Conventional Neural Networks (CNNs), Support Vector Machine (SVM), and Random Forest (RF) to diagnose epileptic seizures. The results achieved from the classifiers show a higher accuracy rate using CNNs as a classifier and GAFDS as feature extraction reaching 97.93% accuracy while the accuracy rate of the SVM and RF was 94.49% and 88.03% respectively.

Estilos ABNT, Harvard, Vancouver, APA, etc.

4

Nugroho, Herminarto, Muhammad Akram Saputra e Muhammad Fadil Anwar. "Optimasi Daya Generator Angin Melalui Pitch Angle Control dengan Particle Swarm Optimization dan Genetic Algortihm". PETIR 16, n.º 1 (25 de abril de 2023): 100–108. http://dx.doi.org/10.33322/petir.v16i1.1704.

Texto completo da fonte

Resumo:

In optimizing the power of the wind turbine generator (WTG) due to fluctuating wind speed, the pitch angle control is used on WTG. The pitch angle has a great influence towards the rotational speed change of the WTG. The pitch angle value is in the range of 0-90 degrees. The optimal value of the pitch angle can produce the maximum power output from the wind turbine generator. Because the pitch angle value changes with wind speed, the optimization method is carried out using Particle Swarm Optimization (PSO) method and Genetic Algorithm (GA) optimization method. By using these two methods optimally, the optimal pitch angle will be obtained dependant on changes in wind speed.

Estilos ABNT, Harvard, Vancouver, APA, etc.

5

Sari, Sri Novida, Roberto Kaban, Abdul Khaliq e Ayu Andari. "SISTEM PENJADWALAN MATA PELAJARAN SEKOLAH MENGGUNAKAN METODE HYBRID ARTIFICIAL BEE COLONY (HABC)". Jurnal Nasional Teknologi Komputer 2, n.º 1 (1 de fevereiro de 2022): 20–32. http://dx.doi.org/10.61306/jnastek.v2i1.21.

Texto completo da fonte

Resumo:

scheduling is very closely related to teaching and learning activities in a school that aims to support, facilitate, enhance the quality of education and improve discipline in the process of teaching and learning activities. The problem faced in making a schedule of subjects is time, the process of making a schedule takes quite a long time in the process of processing the schedule. Of the algorithms used in scheduling problems, algortima Artificial Bee Colony is an algorithm inspired by the behavior of honeybee colonies that work based on the way bees forage for food. Algortima Artificial Bee Colony is known to have advantages over other optimization algorithms that are very efficient in finding optimal solutions. But the Artificial Bee Colony algorithm has its drawbacks that, if the dimensions of the problem increase, the exchange of information is still limited to one dimension. The weakness of Artificial Bee Colony is what makes the opportunity to develop ABC, namely, Hybrid Artificial Bee Colony (HABC) by adding a crossover operator of genetic algorithms. Genetics algorithm's crossover operator inserted into ABC algorithm to improve exchange of information between bees. It can be concluded that the application of HABC methods can do the optimization process quite well in scheduling issues with fairly low schedule clashing results. Based on the results of trials conducted five times, the results that scheduling applications using the HABC Algorithm can produce a schedule of subjects by clashing to a minimum with an average accuracy percentage rate of 98.03%

Estilos ABNT, Harvard, Vancouver, APA, etc.

6

Utami, Dwi Yuni, Elah Nurlelah e Noer Hikmah. "Attribute Selection in Naive Bayes Algorithm Using Genetic Algorithms and Bagging for Prediction of Liver Disease". JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING 4, n.º 1 (20 de julho de 2020): 76–85. http://dx.doi.org/10.31289/jite.v4i1.3793.

Texto completo da fonte

Resumo:

Liver disease is an inflammatory disease of the liver and can cause the liver to be unable to function as usual and even cause death. According to WHO (World Health Organization) data, almost 1.2 million people per year, especially in Southeast Asia and Africa, have died from liver disease. The problem that usually occurs is the difficulty of recognizing liver disease early on, even when the disease has spread. This study aims to compare and evaluate Naive Bayes algorithm as a selected algorithm and Naive Bayes algorithm based on Genetic Algorithm (GA) and Bagging to find out which algorithm has a higher accuracy in predicting liver disease by processing a dataset taken from the UCI Machine Learning Repository database (GA). University of California Invene). From the results of testing by evaluating both the confusion matrix and the ROC curve, it was proven that the testing carried out by the Naive Bayes Optimization algorithm using Algortima Genetics and Bagging has a higher accuracy value than only using the Naive Bayes algorithm. The accuracy value for the Naive Bayes algorithm model is 66.66% and the accuracy value for the Naive Bayes model with attribute selection using Genetic Algorithms and Bagging is 72.02%. Based on this value, the difference in accuracy is 5.36%.Keywords: Liver Disease, Naïve Bayes, Genetic Agorithms, Bagging.

Estilos ABNT, Harvard, Vancouver, APA, etc.

7

Li, Mouwei. "Mended genetic algorthms and application to profile parameters optimization of tandem cold strip mill". Chinese Journal of Mechanical Engineering (English Edition) 13, supp (2000): 123. http://dx.doi.org/10.3901/cjme.2000.supp.123.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

8

Yanto, Eri, e Ramalia Noratama Putri. "APPLICATION OF GENETIC ALGORITHM IN TOURISM ROUTE OPTIMIZATION IN PEKANBARU CITY". Journal of Applied Business and Technology 1, n.º 1 (20 de janeiro de 2020): 41–50. http://dx.doi.org/10.35145/jabt.v1i1.22.

Texto completo da fonte

Resumo:

The number of tourist attractions that are not yet well known, reinforced by the release of Pekanbaru City Government data that the tourism sector only accounts for about 0.9% of the national tourism sector. Therefore, this study aims to optimize the determination of Pekanbaru city tourist travel routes by using genetic algorithms or Genetic Algorithms. Genetic algortima process generally consists of several stages, starting from the initial generation, determination of fitness, crossover stage, mutation to the generation of advanced stages. With an accuracy rate of the best offered solutions reaching around 88% and an average solution search of about 19 seconds per iteration on a constant 100x trial, the results of this study can be used to help general users or Tour & Travel businesses in determining travel routes more optimal travel and a better travel experience.

Estilos ABNT, Harvard, Vancouver, APA, etc.

9

Li, Li. "Research on daylighting optimization of building space layout based on parametric design". Sustainable Buildings 7 (2024): 3. http://dx.doi.org/10.1051/sbuild/2024003.

Texto completo da fonte

Resumo:

Excellent daylighting in buildings is beneficial to protect the physical and mental health of users. After introducing the daylighting of the building, this paper used the genetic algorithm (GA) optimized by co-evolution to optimize the daylighting. Then, a one-story L-shaped accommodation house in Zhengzhou, Henan Province was taken as a case for analysis. The effectiveness of the Daysim software used for calculating the building lighting indicator was tested. Then, the performance of the improved GA with different daylighting indicators as fitness values was compared. Finally, the optimization performance of the particle swarm optimization (PSO) algorithm, the traditional GA, and the improved GA were compared. The results showed that the daylighting indicators simulated by Daysim were significantly correlated with the measured data, suggesting its effectiveness. The improved GA using dynamic daylighting indicators as fitness values had better optimization performance. Compared with the other two algortihms, the improved GA had better optimization performance.

Estilos ABNT, Harvard, Vancouver, APA, etc.

10

Rohman, Ramdhan Saepul, Rizal Amegia Saputra e Dasya Arif Firmansaha. "Komparasi Algoritma C4.5 Berbasis PSO Dan GA Untuk Diagnosa Penyakit Stroke". CESS (Journal of Computer Engineering, System and Science) 5, n.º 1 (31 de janeiro de 2020): 155. http://dx.doi.org/10.24114/cess.v5i1.15225.

Texto completo da fonte

Resumo:

Abstrak— Stroke merupakan gangguan fungsi otak baik lokal maupun menyeluruh yang disebabkan karena pasokan darah ke otak terganggu yang terjadi secara cepat dan berlangsung lebih dari 24 jam atau berakhir dengan kematian. Stroke Merupakan 1 dari 10 jenis penyakit yang paling mematikan di Indonesia. Hal ini berdasarkan pada data yang dikumpulkan dari sampel yang mewakili Indonesia, meliputi 41.590 kematian sepanjang 2014 dan pada semua kematian itu dilakukan autopsi verbal, sesuai pedoman Badan Kesehatan Dunia. Pentingnya mengetahui gejala sejak dini merupakan langkah awal dalam mencegahan terjadinya stroke. Maka itu, dilakukan penelitian untuk menganalisa data terkait dengan penyebab stroke. Adapun atribut yang terlibat dalam penyebab terjadinya stroke yakni, usia, jenis kelamin, kadar glukosa, riwayat penyakit jantung, hipertensi, tipe pekerjaan, tipe tempat tinggal, status merokok, index masa tubuh dan status pernikahan. Diperlukan suatu algortima tertentu untuk mengklasifikasikan semua atribut tersebut. C45 merupakan Algoritma yang paling banyak digunakan, dalam kasus ini akurasi dari algoritma C4.5 sebesar 99.07%. Selanjutnya Algoritma C4.5 dioptimasi dengan menggunakan Particle Swarm Optimization sehingga memperoleh akurasi sebesar 99.28% dan Algorittma C4.5 juga dioptimasi dengan menggunakan Genetic Algorithm sehingga memperoleh akurasi sebesar 99.38%.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mais fontes

Teses / dissertações sobre o assunto "Genetic Algorthim"

1

Yuret, Deniz. "From genetic algorthms to efficient optimization". Thesis, Massachusetts Institute of Technology, 1994. http://hdl.handle.net/1721.1/37727.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

2

Vaikkathe, Ananthakrishnan. "Optimization of Synchromodal Container Transportation". Electronic Thesis or Diss., Normandie, 2024. http://www.theses.fr/2024NORMLH40.

Texto completo da fonte

Resumo:

Cette thèse explore la mise en œuvre de la synchromodalité dans le transport de conteneurs en arrière-pays. La synchromodalité, une forme avancée de transport multimodal, offre une flexibilité et une résilience accrues pour le transport de fret conteneurisé. Bien que le transport routier ait traditionnellement dominé ce secteur, la synchromodalité vise à promouvoir un transfert modal stratégique vers des modes de transport plus durables, tels que le rail et les voies navigables intérieures. Le principal défi opérationnel réside dans la détermination de l’itinéraire optimal pour le transport des marchandises entre les terminaux d’origine et de destination. Dans la première partie de cette thèse, un modèle mathématique est développé pour identifier les meilleurs itinéraires de transport, en minimisant à la fois les émissions de carbone et la durée de transit. Compte tenu de la complexité NP-difficile de ce problème de chemin le plus court capacitaire, un algorithme génétique est proposé pour résoudre des instances de grande taille. Ces instances sont basées sur le corridor de fret de l’Axe Seine en France. Les résultats montrent qu’un transfert modal du camion vers le rail et les voies navigables intérieures peut permettre de réduire les émissions de carbone jusqu’à 80 %. La deuxième partie étend le modèle mathématique en intégrant des impacts environnementaux supplémentaires, appelés coûts externes. Un cadre d’optimisation multi-objectifs basé sur la métaheuristique NSGA-II est mis en œuvre pour résoudre efficacement le problème à grande échelle. Dans la troisième partie, le modèle prend en compte les incertitudes liées aux temps de trajet et de transport. Pour y faire face, une approche d’optimisation robuste basée sur une formulation min-max est employée, permettant de résoudre le problème de transport multimodal dans des conditions incertaines
This thesis explores the implementation of synchromodality in hinterland container transportation. Synchromodality, an advanced form of multimodal transportation, offers enhanced flexibility and resilience for containerized freight movement. While road transport has traditionally dominated this sector, synchromodality aims to promote a strategic modal shift toward more sustainable modes of transportation, such as rail and inland waterways. The primary operational challenge lies in determining the optimal route for transporting shipments between origin and destination terminals. In the first part of this thesis, a mathematical model is developed to identify the best transportation routes, minimizing both carbon emissions and transit duration. Given the NP-hard complexity of this capacitated shortest path problem, a genetic algorithm is proposed to solve large-scale problem instances. These instances are based on the Seine Axis freight corridor in France. The results demonstrate that a modal shift from truck to rail and inland waterways can achieve up to an 80% reduction in carbon emissions. The second part extends the mathematical model to incorporate additional environmental impacts, known as external costs. A multi-objective optimization framework using the NSGA-II metaheuristic is implemented to solve the problem for large-scale scenarios effectively. In the third part, the model accounts for uncertainties in travel and transportation times. To address this, a robust optimization approach based on a min-max formulation is employed, enabling the solution of the multimodal transportation problem under uncertain conditions

Estilos ABNT, Harvard, Vancouver, APA, etc.

3

Leigh, Ryan E. "Using genetic algorithms to create believable agents". abstract and full text PDF (free order & download UNR users only), 2006. http://0-gateway.proquest.com.innopac.library.unr.edu/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:1438914.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

4

Quiroz, Juan C. "Interactively evolving user interfaces". abstract and full text PDF (free order & download UNR users only), 2007. http://0-gateway.proquest.com.innopac.library.unr.edu/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:1442877.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

5

Uritu, Doina. "A genetic algorithm for freight rail transport scheduling (FRTS)". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.

Encontre o texto completo da fonte

Resumo:

Sono sempre di più le città alla ricerca di uno sviluppo sostenibile delle politiche e degli strumenti volti a garantire un’efficiente ed efficace mobilità urbana per passeggeri e merci. Oggigiorno, il veicolo maggiormente utilizzato per il trasporto merci è il camion, il quale influisce sull’aumento del traffico urbano, sul numero di incidenti e sull’emissione di sostanze inquinanti. In questo testo si propone un metodo alternativo per il trasporto della merce, utilizzando la rete ferroviaria urbana come soluzione potenziale per decrementare l’inquinamento atmosferico e per ridurre il flusso stradale spostandolo su quello ferroviario. Il problema trattato si chiama Freight Rail Transport Scheduling (FRTS), ovvero la pianificazione del trasporto della merce per ferrovia. Si tratta della condivisione comune della rete ferroviaria urbana per trasportare i passeggeri e la merce. In particolare, si tratta di assegnare le domande dei clienti a treni appartenenti ad una linea ferroviaria, dove ogni stazione può essere utilizzata come piattaforma per lo scarico/carico della merce. L’obiettivo è la minimizzazione del tempo totale d’attesa delle merci nelle stazioni per massimizzare il turnover della merce. Poiché il problema è di tipo NP-difficile, si propone un Algoritmo Genetico (AG) come metodo risolutivo. L’algoritmo è costituito da una lista di individui, identificati da una serie di domande ordinate in base alla priorità di assegnazione ai treni. La soluzione ricercata è una lista di treni a cui sono state assegnate le domane dei clienti. Gli operatori principali dell’algoritmo sono il crossover e la mutazione, i quali permettono di trovare la soluzione ottima o sub-ottima. In aggiunta, verrà presentato un caso pratico di implementazione dell’algoritmo per trasportare pacchi nella città di Parigi, utilizzando la linea 14 della metropolitana. Le emissioni di CO2 verranno poi calcolate e valutate per l’attuale e per l'alternativo modo di trasporto

Estilos ABNT, Harvard, Vancouver, APA, etc.

6

Všetečka, Martin. "Optimalizace dopravní sítě". Doctoral thesis, Vysoké učení technické v Brně. Fakulta stavební, 2015. http://www.nusl.cz/ntk/nusl-390237.

Texto completo da fonte

Resumo:

The thesis proposes an optimization algorithm used a genetic algorithm. Optimization problem is demonstrated on issues of left turn which meets the requirements for systematic optimization - complexity of the problem, which can not be solved analytically, and the possibility of using templates, which enable automation of design and calculation of all variants.

Estilos ABNT, Harvard, Vancouver, APA, etc.

7

Svobodová, Jitka. "Neuronové sítě a evoluční algoritmy". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-218221.

Texto completo da fonte

Resumo:

Objective of this master's thesis is optimizing of neral network topology using some of evolutionary algorithms. The backpropagation neural network was optimized using genetic algorithms, evolutionary programming and evolutionary strategies. The text contains an application in the Matlab environment which applies these methods to simple tasks as pattern recognition and function prediction. Created graphs of fitness and error functions are included as a result of this thesis.

Estilos ABNT, Harvard, Vancouver, APA, etc.

8

Alam, Sameer Information Technology &amp Electrical Engineering Australian Defence Force Academy UNSW. "Evolving complexity towards risk : a massive scenario generation approach for evaluating advanced air traffic management concepts". Awarded by:University of New South Wales - Australian Defence Force Academy, 2008. http://handle.unsw.edu.au/1959.4/38966.

Texto completo da fonte

Resumo:

Present day air traffc control is reaching its operational limits and accommodating future traffic growth will be a challenging task for air traffic service providers and airline operators. Free Flight is a proposed transition from a highly-structured and centrally-controlled air traffic system to a self-optimized and highly-distributed system. In Free Flight, pilots will have the flexibility of real-time trajectory planning and dynamic route optimization given airspace constraints (traffic, weather etc.). A variety of advanced air traffc management (ATM) concepts are proposed as enabling technologies for the realization of Free Flight. Since these concepts can be exposed to unforeseen and challenging scenarios in Free Flight, they need to be validated and evaluated in order to implement the most effective systems in the field. Evaluation of advanced ATM concepts is a challenging task due to the limitations in the existing scenario generation methodologies and limited availability of a common platform (air traffic simulator) where diverse ATM concepts can be modeled and evaluated. Their rigorous evaluation on safety metrics, in a variety of complex scenarios, can provide an insight into their performance, which can help improve upon them while developing new ones. In this thesis, I propose a non-propriety, non-commercial air traffic simulation system, with a novel representation of airspace, which can prototype advanced ATM concepts such as conflict detection and resolution, airborne weather avoidance and cockpit display of traffic information. I then propose a novel evolutionary computation methodology to algorithmically generate a massive number of conflict scenarios of increasing complexity in order to evaluate conflict detection algorithms. I illustrate the methodology in detail by quantitative evaluation of three conflict detection algorithms, from the literature, on safety metrics. I then propose the use of data mining techniques for the discovery of interesting relationships, that may exist implicitly, in the algorithm's performance data. The data mining techniques formulate the conflict characteristics, which may lead to algorithm failure, using if-then rules. Using the rule sets for each algorithm, I propose an ensemble of conflict detection algorithms which uses a switch mechanism to direct the subsequent conflict probes to an algorithm which is less vulnerable to failure in a given conflict scenario. The objective is to form a predictive model for algorithm's vulnerability which can then be included in an ensemble that can minimize the overall vulnerability of the system. In summary, the contributions of this thesis are: 1. A non-propriety, non-commercial air traffic simulation system with a novel representation of airspace for efficient modeling of advanced ATM concepts. 2. An Ant-based dynamic weather avoidance algorithm for traffic-constrained enroute airspace. 3. A novel representation of 4D air traffic scenario that allows the use of an evolutionary computation methodology to evolve complex conflict scenarios for the evaluation of conflict detection algorithms. 4. An evaluation framework where scenario generation, scenario evaluation and scenario evolution processes can be carried out in an integrated manner for rigorous evaluation of advanced ATM concepts. 5. A methodology for forming an intelligent ensemble of conflict detection algorithms by data mining the scenario space.

Estilos ABNT, Harvard, Vancouver, APA, etc.

9

Beji, Hamdi. "Machine learning et algorithme évolutionnaire : prédiction et optimisation du comportement mécanique et thermique de composites via l'homogénéisation de leurs microcrostuctures". Electronic Thesis or Diss., Université de Lille (2022-....), 2024. http://www.theses.fr/2024ULILN023.

Texto completo da fonte

Resumo:

Ce travail concerne la prédiction et l'optimisation, par approches bio-inspirées, du comportement mécanique et thermique de matériaux composites via l'homogénéisation de leurs microstructures.Une chaine de simulation numérique, par Eléments Finis, a permis l'analyse de VER (Volumes Elémentaires Représentatifs) pour diverses formes d'inclusions, avec prise en compte de leurs positions et orientations, et avec variations des contrastes et fractions volumiques. Cette première étape a abouti à la génération d'un ensemble de bases de données portant sur les réponses (en termes de caractéristiques linéaires thermo-élastiques) de microstructures composites.Ces données ont ensuite été utilisées pour alimenter des modèles d'apprentissage automatique, intégrant des approches de Machine Learning et de Deep Learning, dont l'évaluation repose sur le MAE et le RMSE, démontrant ainsi une excellente précision de prédiction.Dès lors, l'étude a porté sur la recherche de microstructures optimisées : le couplage de ces outils numériques de prédiction avec un algorithme génétique a ainsi permis l'obtention, par analyse inverse, l'obtention de VER correspondants à des valeurs prescrites de caractéristiques thermo-élastiques.Afin de rendre ces outils novateurs plus accessibles, une interface Web, a été développée, mettant en avant leurs fonctionnalités interactives et dynamiques. Cette plateforme facilite l'exploration et l'exploitation intuitive des résultats obtenus
This work focuses on the prediction and optimization, using bio-inspired approaches, of the mechanical and thermal behavior of composite materials through the homogenization of their microstructures. A numerical simulation chain, using Finite Elements, enabled the analysis of Representative Volume Elements (RVEs) for various forms of inclusions, considering their positions and orientations, as well as variations in contrasts and volume fractions. This initial step led to the generation of a database set covering the responses (in terms of thermoelastic linear characteristics) of composite microstructures.These data were then used to feed machine learning models, integrating both Machine Learning and Deep Learning approaches, with evaluation based on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), demonstrating excellent prediction accuracy. Subsequently, the study focused on the search for optimized microstructures: coupling these numerical prediction tools with a genetic algorithm enabled the inverse analysis to obtain RVEs corresponding to prescribed values of thermoelastic characteristics.To make these innovative tools more accessible, a web interface was developed, highlighting their interactive and dynamic functionalities. This platform facilitates the exploration and intuitive exploitation of the obtained results

Estilos ABNT, Harvard, Vancouver, APA, etc.

10

Sigrist, Zoé. "Contribution à l'identification de systèmes non-linéaires en milieu bruité pour la modélisation de structures mécaniques soumises à des excitations vibratoires". Thesis, Bordeaux 1, 2012. http://www.theses.fr/2012BOR14655/document.

Texto completo da fonte

Resumo:

Cette thèse porte sur la caractérisation de structures mécaniques, au travers de leurs paramètres structuraux, à partir d'observations perturbées par des bruits de mesure, supposés additifs blancs gaussiens et centrés. Pour cela, nous proposons d'utiliser des modèles à temps discret à parties linéaire et non-linéaire séparables. La première permet de retrouver les paramètres recherchés tandis que la seconde renseigne sur la non-linéarité présente. Dans le cadre d'une modélisation non-récursive par des séries de Volterra, nous présentons une approche à erreurs-dans-les-variables lorsque les variances des bruits ne sont pas connues ainsi qu'un algorithme adaptatif du type LMS nécessitant la connaissance de la variance du bruit d'entrée. Dans le cadre d'une modélisation par un modèle récursif polynomial, nous proposons deux méthodes à partir d'algorithmes évolutionnaires. La première inclut un protocole d'arrêt tenant compte de la variance du bruit de sortie. Dans la seconde, les fonctions fitness sont fondées sur des fonctions de corrélation dans lesquelles l'influence du bruit est supprimée ou compensée
This PhD deals with the caracterisation of mechanical structures, by its structural parameters, when only noisy observations disturbed by additive measurement noises, assumed to be zero-mean white and Gaussian, are available. For this purpose, we suggest using discrete-time models with distinct linear and nonlinear parts. The first one allows the structural parameters to be retrieved whereas the second one gives information on the nonlinearity. When dealing with non-recursive Volterra series, we propose an errors-in-variables (EIV) method to jointly estimate the noise variances and the Volterra kernels. We also suggest a modified unbiased LMS algorithm to estimate the model parameters provided that the input-noise variance is known. When dealing with recursive polynomial model, we propose two methods using evolutionary algorithms. The first includes a stop protocol that takes into account the output-noise variance. In the second one, the fitness functions are based on correlation criteria in which the noise influence is removed or compensated

Estilos ABNT, Harvard, Vancouver, APA, etc.

Capítulos de livros sobre o assunto "Genetic Algorthim"

1

Gabr, B., e M. Ahmed. "Assessment of Genetic Algorthim in Developing Bathymetry Using Multispectral Landsat Images". In APAC 2019, 393–400. Singapore: Springer Singapore, 2019. http://dx.doi.org/10.1007/978-981-15-0291-0_55.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Trabalhos de conferências sobre o assunto "Genetic Algorthim"

1

Nuradis, Jemal, e Frezewud Lemma. "Hybrid Bat and Genetic Algorthim Approach for Cost Effective SaaS Placement in Cloud Environment". In 2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC). IEEE, 2019. http://dx.doi.org/10.1109/i-smac47947.2019.9032665.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

2

Shea, Peter J., John Peterson, Kathleen Alexander e Alcino Azevedo. "Force aggregation using genetic algortihms". In Optical Science and Technology, SPIE's 48th Annual Meeting, editado por Oliver E. Drummond. SPIE, 2003. http://dx.doi.org/10.1117/12.506449.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

3

Demir, Muhammet Selim, Omer Faruk Gemici e Murat Uysal. "Genetic algortihm based resource allocation technique for VLC networks". In 2017 25th Signal Processing and Communications Applications Conference (SIU). IEEE, 2017. http://dx.doi.org/10.1109/siu.2017.7960526.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

4

Su, Jianhai, e Timothy C. Havens. "Fuzzy community detection in social networks using a genetic algortihm". In 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2014. http://dx.doi.org/10.1109/fuzz-ieee.2014.6891611.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

5

Zubi, H. M., R. W. Dunn, F. V. P. Robinson e M. H. El-werfelli. "Passive filter design using genetic algorthims for adjustable speed drives". In Energy Society General Meeting. IEEE, 2010. http://dx.doi.org/10.1109/pes.2010.5589799.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

6

Faelden, Gerard Ely U., Jose Martin Z. Maningo, Reiichiro Christian S. Nakano, Argel A. Bandala e Elmer P. Dadios. "Blind localization method for quadrotor-unmanned aerial vehicle (QUAV) utilizing genetic algortihm". In 2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM). IEEE, 2014. http://dx.doi.org/10.1109/hnicem.2014.7016214.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

7

Bentaleb, Ali, e Ahmed Ettalbi. "Toward Cloud SaaS for web service composition optimization based on genetic algortihm". In 2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech). IEEE, 2016. http://dx.doi.org/10.1109/cloudtech.2016.7847692.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

8

Russell, Alex, Garrick Orchard e Ralph Etienne-Cummings. "Configuring of Spiking Central Pattern Generator Networks for Bipedal Walking Using Genetic Algorthms". In 2007 IEEE International Symposium on Circuits and Systems. IEEE, 2007. http://dx.doi.org/10.1109/iscas.2007.378701.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

9

Zulvia, Ferani E., R. J. Kuo e Tung-Lai Hu. "Solving CVRP with time window, fuzzy travel time and demand via a hybrid ant colony optimization and genetic algortihm". In 2012 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2012. http://dx.doi.org/10.1109/cec.2012.6252922.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Oferecemos descontos em todos os planos premium para autores cujas obras estão incluídas em seleções literárias temáticas. Contate-nos para obter um código promocional único!