A novel genetic algorithm for curriculum sequence optimization

2021 ◽  
pp. 1-17
Author(s):  
Ouissem Benmesbah ◽  
Mahnane Lamia ◽  
Mohamed Hafidi
Keyword(s):  
Optimization Problem ◽  
Random Search ◽  
Personalized Learning ◽  
The Other ◽  
Optimal Learning ◽  
Swarm Optimization ◽  
Learning Content ◽  
Learning Path ◽  
Dynamic Generation ◽  
Search Approach

A curriculum sequence represents a match between learners’ preferences, needs, and surroundings from one side, and the learning content characteristics and the pedagogical requirements from the other side. The curriculum sequence adaptation problem (CSA) is considered as an important issue in adaptive and personalized learning field. It concerns the dynamic generation of a personal optimal learning path for a specific learner. This problem has gained an increased research interest in the last decade, and heuristics and meta-heuristics are usually used to solve it. In this direction, this paper summarizes existing works and presents a novel GA-based approach modeled as an objective optimization problem to deal with this problem. The experimental results from simulations showed that the proposed GA could outperform particle swarm optimization (PSO) and a random search approach in many simulated datasets. Moreover, from a pedagogical perspective, positive learners’ feedback and high acceptance towards the proposed approach is indicated.

scholarly journals The swarm intelligence algorithms and their application for the educational data analysis

2019 ◽  
Vol 23 (5) ◽  
pp. 33-43
Author(s):  
Y. Yu. Dyulicheva
Keyword(s):  
Data Analysis ◽  
Swarm Intelligence ◽  
Learning Objects ◽  
Ant Algorithm ◽  
First Year ◽  
Optimal Learning ◽  
First Year Students ◽  
Learning Content ◽  
Learning Path ◽  
Level Of Knowledge

The purpose of the paper is the investigation of the modern approaches and prospects for the application of swarm intelligence algorithms for educational data analysis, as well as the possibility of using of ant algorithm modifications for organizing educational content in adaptive systems for conducting project seminars.Materials and methods. The review of the modern articles on the educational data analysis based on swarm intelligence algorithms is provided; the approaches to solving problem of the optimal learning path construction (optimal organization of the learning objects) based on the algorithm and its modifications taking into account the students’ performance in the process of the optimal learning path construction are investigated; the application of particle swarm optimization and its modification based on Roccio algorithm for the reduction of curse dimension in the problem of the auto classifying questions; the application of ant algorithm, bee colony algorithm and bat algorithm for recommender system construction are studied; the prediction of students’ performance based on particle swarm optimization is researched in the article. The modification of ant algorithm for optimal organization of learning objects at projects seminars is proposed.Results. The modern approaches based on swarm intelligence algorithms to problem solving in educational data analysis are investigated. The various approaches to pheromones updating (their evaporation) when building the optimal learning path based on students’ performance data and search of group with “similar" students are studied; the abilities of the hybrid swarm intelligence algorithms for recommendation construction are investigated.Based on the modification of ant algorithm, the approach to the learning content organization at project seminars with individual preferences and students’ level of basic knowledge is proposed. The python classes are developed: the class for statistical data processing; the classfor modifica -tion of ant algorithm, taking into account the current level of knowledge and interest of student in studying a specific topic at the project seminar; the class for optimal sequence of the project seminars ’ topics for students. The developed classes allow creating the adaptive system that helps first year students with a choice of topics of project seminars.Conclusion. According to the results of the study, we can conclude about the effectiveness of swarm intelligence algorithms usage to solve a wide range of tasks connected with learning content and students’ data analysis in the e-learning systems and perspectives to hybrid approaches development based on swarm intelligence algorithms for realizing the adaptive learning systems on the paradigm of “demand learning".The results can be used to automate the organization of learning content during project seminars for the first-year students, when it is important to understand the basic level of knowledge and students’ interest in learning new technologies.

Particle swarm optimization neural network for research on artificial intelligence college English classroom teaching framework

2020 ◽  
pp. 1-13
Author(s):  
Dong Juan ◽  
Yu Hong Wei
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Personalized Learning ◽  
Particle Swarm Algorithm ◽  
Swarm Optimization ◽  
College English ◽  
Learning Path ◽  
English Classroom

This paper based on the algorithm of particle swarm optimization neural network, the university English classroom training framework with artificial intelligence is researched and designed, and a personalized learning path based on an improved binary particle swarm algorithm based on the non-linear increase of inertial weights and the exploration of unknown space is proposed. The recommendation method improves the algorithm’s convergence speed and convergence accuracy. It is easy to jump out of the local optimum through the improvement of the algorithm, thereby solving the problem of low recommendation accuracy of the personalized learning path and improving the recommendation efficiency. To verify the recommended effect of the model and algorithm, this paper designs a simulation experiment and a learning platform that take the college English course as an example to verify the running performance and practical application effect of the proposed method. The above experiments show that the proposed method can improve the matching degree of the personalized learning path and the needs of learners, and improve the accuracy of application in personalized learning path recommendation.

A new algorithm for finding CRM-model coefficients

2019 ◽  
Vol 5 (3) ◽  
pp. 164-185 ◽  
Author(s):  
Alexander D. Bekman ◽  
Sergey V. Stepanov ◽  
Alexander A. Ruchkin ◽  
Dmitry V. Zelenin
Keyword(s):  
Approximate Solution ◽  
Optimization Problem ◽  
Optimal Solution ◽  
Complex Form ◽  
Approximate Solutions ◽  
The Other ◽  
Programming Algorithm ◽  
Stochastic Algorithms ◽  
Large Set ◽  
Flow Rates

The quantitative evaluation of producer and injector well interference based on well operation data (profiles of flow rates/injectivities and bottomhole/reservoir pressures) with the help of CRM (Capacitance-Resistive Models) is an optimization problem with large set of variables and constraints. The analytical solution cannot be found because of the complex form of the objective function for this problem. Attempts to find the solution with stochastic algorithms take unacceptable time and the result may be far from the optimal solution. Besides, the use of universal (commercial) optimizers hides the details of step by step solution from the user, for example&nbsp;— the ambiguity of the solution as the result of data inaccuracy.<br> The present article concerns two variants of CRM problem. The authors present a new algorithm of solving the problems with the help of “General Quadratic Programming Algorithm”. The main advantage of the new algorithm is the greater performance in comparison with the other known algorithms. Its other advantage is the possibility of an ambiguity analysis. This article studies the conditions which guarantee that the first variant of problem has a unique solution, which can be found with the presented algorithm. Another algorithm for finding the approximate solution for the second variant of the problem is also considered. The method of visualization of approximate solutions set is presented. The results of experiments comparing the new algorithm with some previously known are given.

scholarly journals Time Saving Students’ Formative Assessment: Algorithm to Balance Number of Tasks and Result Reliability

2021 ◽  
Vol 11 (13) ◽  
pp. 6048
Author(s):  
Jaroslav Melesko ◽  
Simona Ramanauskaite
Keyword(s):  
Formative Assessment ◽  
Item Response ◽  
Item Difficulty ◽  
Classical Test Theory ◽  
Personalized Learning ◽  
Test Theory ◽  
Time Saving ◽  
Learning Path ◽  
Crucial Component

Feedback is a crucial component of effective, personalized learning, and is usually provided through formative assessment. Introducing formative assessment into a classroom can be challenging because of test creation complexity and the need to provide time for assessment. The newly proposed formative assessment algorithm uses multivariate Elo rating and multi-armed bandit approaches to solve these challenges. In the case study involving 106 students of the Cloud Computing course, the algorithm shows double learning path recommendation precision compared to classical test theory based assessment methods. The algorithm usage approaches item response theory benchmark precision with greatly reduced quiz length without the need for item difficulty calibration.

scholarly journals A Modified Niching Crow Search Approach to Well Placement Optimization

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 857
Author(s):  
Jahedul Islam ◽  
Md Shokor A. Rahaman ◽  
Pandian M. Vasant ◽  
Berihun Mamo Negash ◽  
Ahshanul Hoqe ◽  
...  
Keyword(s):  
Optimization Problem ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Multimodal Optimization ◽  
Test Functions ◽  
Well Placement ◽  
Suggested Approach ◽  
Placement Optimization ◽  
Well Placement Optimization ◽  
Search Approach

Well placement optimization is considered a non-convex and highly multimodal optimization problem. In this article, a modified crow search algorithm is proposed to tackle the well placement optimization problem. This article proposes modifications based on local search and niching techniques in the crow search algorithm (CSA). At first, the suggested approach is verified by experimenting with the benchmark functions. For test functions, the results of the proposed approach demonstrated a higher convergence rate and a better solution. Again, the performance of the proposed technique is evaluated with well placement optimization problem and compared with particle swarm optimization (PSO), the Gravitational Search Algorithm (GSA), and the Crow search algorithm (CSA). The outcomes of the study revealed that the niching crow search algorithm is the most efficient and effective compared to the other techniques.

PSS with SVC Damping Controllers Coordinated Design and Real-Time Implementation in Multi-Machine Power System Using Advanced Adaptive PSO

2013 ◽  
Vol 14 (5) ◽  
pp. 487-498
Author(s):  
Rajendraprasad Narne ◽  
P.C. Panda
Keyword(s):  
Power System ◽  
Real Time ◽  
Optimization Problem ◽  
Test System ◽  
Swarm Optimization ◽  
Damping Controllers ◽  
Control Schemes ◽  
Controller Performance ◽  
Adaptive Pso ◽  
System Stabilizer

Abstract This article proposed coordinated tuning and real-time implementation of power system stabilizer (PSS) with static var compensator (SVC) in multi-machine power system. The design of proposed coordinated damping controller is formulated as an optimization problem, and the controller gains are optimized instantaneously using advanced adaptive particle swarm optimization. Here, PSS with SVC installed in multi-machine system is examined. The coordinated tuning among the damping controllers is performed on the non-linear power system dynamic model. Finally, the proposed coordinated controller performance is discussed with time-domain simulations. Different loading conditions are employed on the test system to test the robustness of proposed coordinate controller, and the simulation results are compared with four different control schemes. To validate the proposed controller, the test power system is also implemented on real-time (OPAL-RT) simulator, and acceptable results are reported for its verifications.

scholarly journals Optimal Location and Design of TCSC controller For Improvement of Stability

2011 ◽  
pp. 210-215
Author(s):  
Swathi Kommamuri ◽  
P. Sureshbabu
Keyword(s):  
Power System ◽  
Optimization Problem ◽  
Low Frequency ◽  
System Stability ◽  
Simulation Environment ◽  
Swarm Optimization ◽  
Stability Performance ◽  
Low Frequency Oscillations ◽  
Simulation Results ◽  
The Stability

Power system stability improvement by a coordinate Design ofThyristor Controlled Series Compensator (TCSC) controller is addressed in this paper.Particle Swarm Optimization (PSO) technique is employed for optimization of the parameterconstrained nonlinear optimization problem implemented in a simulation environment. The proposed controllers are tested on a weakly connected power system. The non-linear simulation results are presented. The eigenvalue analysis and simulation results show the effectiveness and robustness of proposed controllers to improve the stability performance of power system by efficient damping of low frequency oscillations under various disturbances.

scholarly journals Comparison of the effectiveness of the Map-Reduce approach and the actor model in solving problems with high connectivity of inp data on the example of the optimization problem for a swarm of particles

2021 ◽  
pp. 049-055
Author(s):  
Larin V.O. ◽  
◽  
Provotar O.I. ◽  
Keyword(s):  
Optimization Problem ◽  
Map Reduce ◽  
Actor Model ◽  
Swarm Optimization ◽  
Memory Efficiency ◽  
Order Of Magnitude ◽  
High Connectivity ◽  
Memory Support ◽  
Bounded Input ◽  
Spark Framework

The paper defines the notion of distributed problems with bounded input components. Particle Swarm Optimization problem is shown to be an example of such a class. Such a problem's implementation based on the Map-Reduce model (implemented on the Spark framework) and an implementation based on an actor model with shared memory support (implemented on Strumok DSL) is provided. Both versions' performance assessment is conducted. The hybrid actor model is shown to be an order of magnitude more effective in time and memory efficiency than Map-Reduce implementation. Additional optimization for the hybrid actor model solution is proposed. The prospects of using the hybrid actor model for other similar problems are given

Sign in / Sign up

Export Citation Format

Share Document