The most important aspect of a genetic algorithm (GA) lies in the optimal solution found. The result obtained by a genetic algorithm can be evaluated according to the quality of this solution. It is important that this solution is optimal or close to optimal in relation to the defined performance criteria, usually the fitness value. This study addresses the problem of automated generation of assessment tests in education. In this paper, we present the design of a model of assessment test generation used in education using genetic algorithms. The assessment covers a series of courses taught over a period of time. The genetic algorithm presents an improvement or development, which consists of the initial population variation, obtained by the selection of a large fixed number of individuals from various populations, which are ordered by the fitness value using merge sort, chosen for the reason of the high number of individuals. The initial population variation can be seen as a specific modality for increasing the diversity and number of the initial population of a genetic algorithm, which influences the algorithm performance. This process increases the diversity and quality of the initial population, improving the algorithm’s overall performance. The development/novelty brought about by this paper is related to its application to a specific issue (educational assessment test generation) and the specific methodology used for population variation. This development can be applied for large sets of individuals, the variety, and the large number of generated individuals leading to higher odds to increase the performance of the algorithm. Experimental results demonstrate that the proposed method outperforms traditional GA implementations in terms of solution quality and convergence speed, showing its effectiveness for large-scale test generation tasks.

The educational assessment is an essential task within the educational process. The generation of right and correct assessment content is a determinant process within the assessment. The creation of an automated method of generation similar to a human experienced operator (teacher) deals with a complex series of issues. This paper presents a compiled set of methods and tools used to generate educational assessment content in the form of assessment tests. The methods include the usage of various structures (e.g., trees, chromosomes and genes, and genetic operators) and algorithms (graph-based, evolutionary, and genetic) in the automated generation of educational assessment tests. This main purpose of the research is developed in the context of the existence of several requirements (e.g., degree of difficulty, item topic), which gives a higher degree of complexity to the issue. The paper presents a short literature review related to the issue. Next, the description of the models generated in the authors’ previous research is presented. In the final part of the paper, the results related to the implementations of the models are presented, as well as results and performance. Several conclusions were drawn based on this compilation, the most important of them being that tree and genetic-based approaches to the issue have promising results related to performance and assessment content generation.

This paper investigates the optimization of an irrigation system distributed over an agricultural area discretized into unit cells, using evolutionary algorithms for the control of water irrigation points (taps). The model simulates the distribution of water through strategically placed irrigation points, considering the individual requirements of each cell. The main objective is to minimize the difference between the amount of water needed and delivered, while reducing the total consumption. The dynamics of fitness over generations are analyzed, as well as the average behavior of deficit, surplus, and relative humidity. The results highlight a relatively uniform distribution of delivered water and a stable convergence of the fitness function, demonstrating the efficiency of the proposed method in managing water resources in a sustainable way. In this matter, compared to the full-activation scenario, the presented model reduced total water use by more than 50%, achieving zero deficit, minimal surplus, and a 46% improvement in overall fitness. Although the approach demonstrates promising results in simulated scenarios, it does not currently incorporate real-time sensor data or field validation, which are planned for future development. The study provides a solid basis for the development of smart irrigation systems, adaptable to the variability of soil and climatic conditions.

The growing sophistication of cyber threats has heightened the need for enhanced security measures in distributed web systems. This paper explores the potential of genetic algorithms to reinforce these systems by improving their adaptability to emerging vulnerabilities. Genetic algorithms, rooted in evolutionary principles, provide a mechanism to optimize security parameters, such as threat detection, intrusion response, and anomaly identification. Unlike traditional methods, these algorithms offer dynamic solutions capable of evolving with changing attack patterns. The study delves into various ways genetic algorithms can be incorporated into security frameworks for distributed systems, focusing on how these adaptive strategies could increase system resilience and robustness. Key considerations include the efficiency of configuration optimization, the ability to manage diverse security scenarios, and the scalability of algorithmic integration across multiple nodes within a system. By analyzing theoretical models and current advancements in evolutionary computing, we provide a comprehensive evaluation of the algorithm's potential impact on distributed security infrastructures. This research highlights the importance of innovative, adaptive approaches to maintaining the security of increasingly interconnected web systems in the face of evolving cyber risks.

The Food Loss and Waste (FLW) phenomenon is an important issue in the current development of economy as a whole. This phenomenon is emerging in all economic contexts, starting from food production and processing, known as food loss (FL), to the consuming stages, known as food waste (FW). In this matter, identifying key causes and quantifying the impact of FLW is essential. The current paper is an integrated summative description of several research results related to FLW obtained by the authors and elaborated in previous papers. Thus, the paper includes a bird-eye view of the entire model alongside the agri-food chain, taking into account modalities of measuring the FL during its components and a specific measurement of FW on the consuming component. The approach takes into account methodologies and instruments from various domains, such as statistics, data processing, automated learning (e.g., machine learning), System Dynamics or networks. The expected results are the description of the model and the resulted data. Conclusions can be used further to study and challenge the FLW phenomenon causes effects for any interested stakeholders.

This paper presents an interdisciplinary assessment method using items grouped according to the disciplines targeted to identify student competencies. For each subject, a weight is used depending on the requirements of the assessor. The model we present uses different databases, one for each subject used for assessment, and the selection of items for assessment is done using genetic algorithms. The model implementation is done using the Python language. Based on the results, the genetic algorithm efficiently optimizes the generation of multidisciplinary tests and its performance can be improved by dynamically adapting parameters and diversifying solutions to avoid stagnation.

This paper examines the usage of genetic algorithms for performance analysis and optimization in distributed web systems. The selected system for distributed systems performance analysis pertains to educational assessment domains. Genetic algorithms (GA) offer a promising approach for automating the optimization process. In this study, the GA is used to generate educational assessment tests within an educational framework. The assessment tests are formed of items stored in data structures and used in the generation process. This process is delimited by several requirements of the assessment objectives, such as the degree of difficulty or solving time. A typical GA approach leads to optimised sequences of items or tests, whereas the usage of distribution within the process can surpass usual GA issues, such as local optimisation. The distribution consists in the generation of the assessment tests on several nodes within a network, where each node has generative tasks. Moreover, they have been successfully applied and solved a wide range of problems, including scheduling, routing, and load balancing in distributed systems. This article also presents a comparative analysis of GA performance: centralized GA and distributed GA. Centralized GAs run on a single computer, while distributed GAs run on multiple computers. This work represents an important step in the understanding and application of genetic algorithms in the context of distributed web systems, providing a solid foundation for future research in this area. The conclusions of this paper demonstrate the effectiveness of genetic algorithms in developing the performance of distributed systems.

Economic markets can be modeled using a system -based approach. In an economic system, agents have complex behavioural patterns, two of the most important being concurrency and cooperation. In this paper, we present a model of an economic system that integrates the dual characteristic of economic system. On one hand, the concurrent characteristic is modeled using Petri nets and focuses on determining the agent behavioural patterns in the system related to the resources distribution and market share. On the other hand, the cooperation characteristic is related to the determination of an agent that can influence the market behaviour, using a model based on Leader Election. In this matter, the concurrency between agents is integrated with market coordination, useful in contexts as quality standard establishment or collective issues. The context of the model related to distribution can be further developed, especially related to agrifood chains in economic markets, by establishing a classification of the agents of the economic market, useful for a vertical integration of the market.

The addition of the performance characteristic to an implementation is a crucial step in delivering the best results. In this matter, the current paper presents a description of a model which uses concepts related to web distribution systems in order to improve the performance and scalability of an implementation of a system that will be used in educational assessment and which generates assessment tests using genetic algorithms. The distributed systems could be used as a modality of implementing parallel operations for the genetic algorithm, such as mutation or crossover, but also for specific parts of the implementation, such as the selection process of the items within the assessment test. This paper has the aim to describe an improved model for this system, in order to be used for implementation and results.

The generation of assessment test is a vast area within the educational assessment design process. In this matter, the type of the question is one of the most important parameters of this process, due to its impact on the development of the assessment implementation phase. This paper presents a development of a model of an assessment test generation using genetic algorithms with an additional type of item which is dynamically generated. The item has a form of a parametric structure, e.g. the quadratic function for a given set of parameters. The purpose of this paper is to present the schema of the additional part of the model and its integration within the assessment model developed and described in previous papers.

The most important aspect of an educational assessment is related to the closeness of the results to the actual knowledge level of the assessee. In this way, the fidelity of the assessment is ensured. In this matter, this paper presents the description and potential results of a model that determines a recognition of a detailed knowledge report related to the assessment topic, including the situation of partial knowledge. Thus, a model that details the usage of genetic algorithms (GAs) for establishing a method of partial scoring using fuzzy logic and weights given to specific parts of the assessment items is presented in this paper. Shortly, assessment items such as MCQ (multiple-choice) or cloze questions are given as examples of situations where this method of partial scoring can be applied. The genetic algorithm is used to generate the optimal scoring weights to the option of the assessment items related to a given value of entropy or scoring equilibrium between the scores chosen for the items. The purpose of this analysis is to obtain an optimal score configuration for an item which can offer chosen score equilibrium between the options score and which could give the opportunity of partial scoring, which has multiple benefits for the assessment process.

Food loss and waste (FLW) is a primary focus topic related to all human activity. This phenomenon has a great deal of importance due to its effect on the economic and social aspects of human systems. The most integrated approach to food waste analysis is based on the study of FLW alongside the agrifood chain, which has also been performed in previous studies by the authors. This paper presents a modality of determination of food loss and waste effects with an emphasis on consumer segments in agrifood chains in the form of a predictive model based on statistical data collected based on specific methods in Romania. The determination is made comparatively, using two predictive machine learning-based methods and separate instruments (software), in order to establish the best model that fits the collected data structure. In this matter, a Decision Tree Approach (DTA) and a Neural Network Approach (NNA) will be developed, and common methodologies of the approaches will be applied. The results will determine predictive outcomes for a specific food waste (FW) agent (e.g., consumer) based on pattern recognition of the collected data. The results showed relatively high-accuracy predictions, especially for the NN approach, with lower performances using the DTA. The effects of the application of this predictive model will be expected to improve the food loss prevention measures within economic contexts when applied to real-life scenarios.

This paper focuses on presenting a methodology for designing an assessment test that takes into account the degree of difficulty of the items and the overall test structure in an integrated academic environment. This integrated approach allows for the collection of assessment items at an academic consortium level, making them applicable to similar faculties within a group of institutions. The proposed model consists of two main components: the item collector and the test generator. The item collector gathers assessment items from various academic institutions within the consortium. These items are then utilized by the test generator, which automatically generates tests using a combination of evolutionary algorithms (genetic-based) and machine learning (ML) techniques. The genetic-based algorithm and ML methods play a key role in determining the composition and structure of the assessment tests.

The design of a good assessment is related to compliance with several requirements. A good design ensures the validity and correctness of the assessment process within education. This paper presents a modality of designing an assessment test in respect of the degree of difficulty of the items and the test in an integrated academic environment, meaning that the items used for assessment are collected at an academic consortium level and they can be used in an integrated way for all the similar faculties from the academic group of institutions. The presented model is composed of two main components: the item collector and the test generator. The generation of tests is made automatically, by using evolutionary algorithms (genetic-based) and machine learning (ML) methods. An implementation of the model for the genetic-based algorithm is also presented.

The introduction of the image-based assessment can lead to a better outcome related to the general purpose of the assessment. In this matter, this paper presents a modality of generating assessment tests, also referred as sequences of items, that are formed of questions, also referred as items, which base their solving process on images and their content. In this matter, the paper will present the description of the general model of assessment, taking into consideration the inclusion of the image-based type of items. The general model of the assessment comprises a wider number of types of items, the most studied of them being the multiple-choice text-based items. Thus, the purpose of the paper is the inclusion within this general assessment model of the new approach related to item types (image-based) and their impact on the assessment outcomes.

The analysis of the performance of the educational process is one of the essential aspects of the contempo-rary approach of the educational system. Technology has permitted the analysis of various components of the learning process, which has developed in the process of learning analytics. This paper presents the model and implementation of a concept that uses learning analytics to determine the outcome of an educational process and its performance. Its performance refers to the group understanding of a specific concept measured using the results to systematic evaluation during a period of time. The model, called Course Item Management Generation (CIM-GET), is part of a larger model that is centered on the educational assessment process and which uses machine learning-based techniques and evolutionary algorithms to generate assessment tests used for learning purposes. The current model uses statistical and item response analysis parameters in order to create a report regarding the items within the tests that are given over a period of time to specific students within a faculty of university. In the first part, the CIM-GET model will be presented in the context of the larger model called Dynamic Model for Assessment and Interpretation of Results (DMAIR), then several results obtained after the technical and statistical implementation will be presented. The CIM-GET model uses items from an item dataset, extracted using machine learning-based tools by the defining keywords of the item, which also represent the topics of an item, which form an optimal test using a generation algorithm (e.g., genetic algorithm). After the test is given to students, the results are stored in a database, a report is output and a list of topics that need to be revised is generated. In this matter, the practical results of the presented model will be shown, in order to show the practical importance of the results.

Learning management systems are rapidly evolving as independent platforms for supporting an entire assessment and even educational process. However, these are bounded by the lack of human interaction and task solving for intricate or more complex educational systems. Thus, developments can be made in the direction of building such systems which will increase the number and quality of solutions given to issues regarding online education. In this paper, we present the construction of an example of such a system which serves as an aid for the teacher to assess the students enrolled at a certain course. In the form of a web application, the system will generate variants of tests that can be given to students following restrictions of difficulty and time. This would ease the assessment process within the course and would create an automated tool for an equitable evaluation of all students.

The determination of the influences of the management on the economic performance of an agricultural holding can be an important process for the farm manager, as a source of information which can consist in a valuable component needed in the decisional process. In this matter, the analysis is useful during a specific period of time, which also comprises future predictions. In this paper, we will present a study of the connection between the farm management approach, represented by several characteristics of the farm and the farmer, and the farm economic performance, represented by the financial result of the farm activity. This study is presented as a comparative analysis of two methods that establish the existence and intensity of the mentioned connection, the first one being based on statistical methods and instruments and the second one being based on machine-learning based tools, specifically supervised learning. This study aims to find alternative means of studying causal implications of the management type on the economic activity within a farm, based on digital-based tools. The obtained results for the mentioned research showed that the methods based on supervised learning can be an important tool of analysis, being complementary with the traditional statistical methods regarding the analysis of the microeconomic agricultural environment and performance, providing supplementary key data regarding the economic indicators.

This paper presents a method of estimating the independent component analysis model with a training algorithm based on a mixed learning algorithm of genetic algorithms with a neural network algorithm. The mixed training algorithm is applied to optimize the objective function negentropy used to estimate the ICA model. The proposed estimation algorithm improves the training scheme based on genetic algorithms by using for crossover the most suitable chromosomes evaluated by the objective function with the parameters calculated calculated accordingly by a multilayer neural network algorithm. The results produced by the proposed algorithm were compared with the results of applying standard methods for estimating independent components such as FastICA variants based on the standard Newton method or the secant method. The experimental results were established in blind source separation applications by using unidimensional and bidimensional signals.

Technology is being increasingly used in domains such as education, where a large part of the teacher’s or mentor’s time is wasted in drafting up informal tests for classroom use. In this paper, we will present a genetic algorithm-based program which can automatically generate optimized exam tests from a data bank of categorized questions. The user can select the number of questions included in a test and the categories relevant to the test. In the final part of the paper we show relevant performance tests results obtained with a Java implementation of this algorithm.