International Journal of Education and Management Engineering @ijeme
Статьи журнала - International Journal of Education and Management Engineering
Все статьи: 655
Optimal and Appropriate Job Allocation Algorithm for Skilled Agents under a Server Constraint
Статья научная
In a combinatorial auction, there has a server, some agents, and some jobs which can be used to reach efficient resource and job allocations among the agents. In our paper, we have shown how any server can achieve maximum throughput as well as maximum profit based on some server constraints where each agent has one or more skills to perform those jobs on a priority basis which can be executed in a whole or partial. This algorithm can effectively distribute the appropriate job allocation among skilled agents with proper acknowledgment to the server after a certain period.
Бесплатно
Optimization of Curriculum Content Using Data Mining Methods
Статья научная
The purpose of this article is to search and extract the necessary content, identifying curriculum topics. Classification and clustering of text documents are challenging artificial intelligence tasks. Therefore, an important objective of this study is to propose and implement a tool for analyzing textual information. The study used Data Mining methods to analyze text data and generate educational content. The work used methods for classifying text information, namely, support vector machines (SVM), Naive Bayes classifier, decision tree, K-nearest neighbor (kNN) classifier. These methods were used in developing the curriculum for the specialty “Cybersecurity” for the Faculty of Information and Telecommunication Technologies. About 48 curricula in this specialty were analyzed, topics and sections in disciplines were identified, and the content of the academic program was improved. It is expected that the results obtained can be used by specialists, managers and teachers to improve educational activities.
Бесплатно
Статья научная
Scrum and Kanban are some of the most common methodologies that are used in software development because of flexibility and focus on the team. Nevertheless, applying Agile at a project level and within large IT projects including workforce distributed across different areas, manages some remarkable difficulties, for example, coordination, communication, or resources. This paper examines ideas on how to improve the implementation of Agile system to increase the performance of the team and results of the projects. The study focuses on four key goals: proving Agile improvements in practice via pilot surveys, applying best-practice structures, such as defence-grade SAFe or LeSS at the scale, encouraging organizations-wide Agile mindset, and using collaboration and automation technologies when working in remote environments. These issues serve as the focus of this research with the intention of preserving Agile’s principles of flexibility and practicability across various size and scale projects. It presents suggestions for further research and informs practitioners and organizations wishing to obtain the most out of Agile methodologies in real environments.
Бесплатно
Optimizing Student Performance Prediction via K-Means and k-NN Integration
Статья научная
This study explores the integration of two methods, namely K-Means and k-NN. K-means is used to identify categories of learning outcome data, while k-NN is used to predict students' learning outcomes into relevant categories. Through the calculation of the Elbow method, it was established that the optimal number of clusters for grouping is three. The learning outcome data, which include Arithmetic and Statistics scores, are processed to produce a mapping that differentiates students into three categories: Adequate, Moderate, and Good. In the 12th iteration, the clustering results using K-Means achieved convergence, with 64 students in the Adequate category (C1), 60 students in the Moderate category (C2), and 59 students in the Good category (C3). This indicates that the students in each group are evenly distributed based on their mathematical and statistical abilities. The prediction results using k-NN for a student with an Arithmetic score of 85 a Statistics score of 75, and a k-value of 61, found that 7 data fell into Category 1 (Adequate), 3 data into Category 2 (Moderate), and dominant 51 data in Category 3 (Good). Thus, the prediction results are placed in Category 3, indicating a 'Good' rating in their academic performance. By using data mining techniques to enhance understanding of student learning outcomes, this study provides a significant contribution to the field of education. It demonstrates substantial progress toward a data-driven learning approach that can be tailored to specific needs and improve student learning outcomes.
Бесплатно
Orphan Adoption Management System using Machine Learning Approach
Статья научная
According to UNICEF, the latest estimate states that there are about 2.7 million children in orphanages. Orphanage is a residence for people who are without parental support or any moral support from anyone. Such orphans require help from people who are in a good financial state to donate them. Generally, in orphanage records are usually maintained for future reference, retrieval, and easy management. The objective of this paper is to help the orphans from different orphanages to get help from the donors who wish to donate them by using our web application. The proposed system helps the staff in reducing manual paper work and enhances tidiness in record keeping since the existing one uses manual keeping, i.e., the use of files and papers. The system allows the orphanage owner to add and modify the orphan records. The system provides suggestions for assignment of these orphans to the caretakers/donors by using SVM (Support Vector Machine) algorithm. Donor can select the orphan and request for adoption from the orphanage owner. The Orphanage owner can accept or reject help from the donor. The proposed system is aimed to facilitate donors with the details of an orphan and providing fund specifically to that orphan.
Бесплатно
Performance Analysis for Heterogeneous & Reconfigurable Computing Based on Scheduling
Статья научная
Right now, heterogeneous & reconfigurable computing is a research hot in the area of high performance computing. Due to the heterogeneity of application tasks and reconfigurability of system architecture, performance analysis for heterogeneous & reconfigurable computing becomes rather difficult. Unfortunately, the existing techniques and methods are no longer suitable for use. This paper presents a performance analysis method based on task scheduling. It builds on system architecture model and task model of heterogeneous & reconfigurable computing. By making use of heterogeneity matching matrix and reconfigurability coupling matrix we achieve optimal selection and matching between computational tasks and processing units. Through task scheduling algorithm, the completion time of application task run on heterogeneous & reconfigurable computing system can be calculated. Finally, we carry out case study.
Бесплатно
Performance with Eloquent and Query Builder in Crowdfunding System with Laravel Framework
Статья научная
Performance is a point of interest that is quite interesting for application owners, how could it not, besides being rich in features and following what they want, there are things that are no less important, namely the issue of the speed of use of an application that must be considered for developers. Because the speed level will affect the user experience in using it. Many factors influence the performance of an application, especially in the website category, one of which is the developer's ability to minimize large amounts of data load. This is the importance of being able to categorize which large data loads need to be considered and which are not. There is a system crowdfunding website that is currently operating using the laravel framework, but there are several obstacles faced where some of the processes in it are rather slow in the process. In this research, how do we choose which process uses process eloquence and which one needs to use the query builder. So that combining eloquent and query builder can be optimal
Бесплатно
Personality Trait Identification Using Unconstrained Cursive and Mood Invariant Handwritten Text
Статья научная
Identification of Personality is a complex process. Personality traits are stable over time .Individual's behavior naturally varies from occasion to occasion. But there is a core consistency which defines the true nature. The paper addresses this issue of behavior. Graphology is normally a technique used to identify the traits. Accuracy of this technique depends on how skilled the analyst is. Although human intervention in handwriting analysis has been effective, but it is costly and prone to fatigue. An automation of handwritten text is proposed. Basically we have considered three important features in the direction of orientation of the lines :(i) up hill (ii) down hill (iii) constant line. Edge histogram and bounding boxes was used for feature extraction .Known classifiers like SVM & ANN are used for training and the results were compared. The results were about 98% for SVM & 70% with ANN. The analysis was done using single line.
Бесплатно
Personalized Search Recommender System: State of Art, Experimental Results and Investigations
Статья научная
Personalized recommender system has attracted wide range of attention among researchers in recent years. These recommender systems suggest products or services depending upon user's personal interest. There has been a huge demand for development of web search apps for gaining knowledge pertaining to user's choice. A strong knowledge base, type of approach for search and several other factors make it accountable for a good personalized web search engine. This paper presents the state of art, challenges and other issues in this context, thereby providing the need for an improved personalized system. The study carried out in this paper reports the overview of existing technologies for building a personalized recommender systems in social networking platforms. Study reported in this article seems to be promising and provides possibilities of research directions, pros & cons and other alternatives.
Бесплатно
Physical and soft sensor technologies for wastewater quality management
Статья научная
Physical sensors are used mostly to detect sludge and odour in wastewater. Black box modelling or data-derived model using the correlation of input-output parameters is the preferred method as we have assessed. This is due to the non-complex approach of such models as opposed to model-driven, mechanistic models. The latter is hard to be adopted for soft-sensor development due to the inherent complexities and uncertainties. The commonest methods for soft sensor model development are ANN and ANFIS. Many other improvements of these methods are achieved by combining with other techniques to enhance the prediction performance of the soft sensors. Accuracy and precision of data collected for soft sensor modelling has become a vital concern at present to ensure the reliability of wastewater quality indices predicted by the soft sensors. Reduction of the level of reliability of the sensor system in monitoring and controlling of WWTPs would lead to serious lapses in the wastewater quality management. In this backdrop we recommend SEVA soft sensor as one of the best potential solutions which could be offered by the existing technologies.
Бесплатно
Policy Model in the Desktop Management System
Статья научная
By studying the policy and desktop management systems theories, referencing the Internet Engineering Task Force (IETF) policy model, this paper proposed a policy model that can be applied in specific desktop management system. It mainly explains the whole system framework and its implementation mechanisms, and it discusses the problems and solutions that the policy model uses in the desktop management system.
Бесплатно
Potato Leaf Disease Detection Using Image Processing
Статья научная
The economics of a nation is significantly influenced by agricultural productivity. Finding plant leaf disease is crucial since it significantly reduces agricultural productivity. Traditional detection methods like observing with the naked eye can lead to time-consuming and less accurate results. Farmers can’t always tell the difference between leaf diseases because sometimes they look the same. That’s why researchers have started using automation techniques to accurately detect the main diseases and their symptoms. This research proposed potato leaf disease detection using an image processing technique where the dataset was obtained online. In the proposed method, several image pre-processing techniques are used including data augmentation, gaussian smoothing, image normalization, dimensionality reduction and one hot encoding. CNN, KNN and SVC were used as classifiers. CNN gives the best result with an overall accuracy of 97%. Previous works with different classifiers had several limitations and using CNN the researchers didn’t get satisfying result. For this research a new hybrid model is introduced which can utilize the best of CNN classifier and it will be much more reliable and effective.
Бесплатно
Practical Teaching Staff Construction under New Situation
Статья научная
The practical teaching is a very important component of higher education. It is a special platform which not only integrates abstract and concrete, but also integrates theory and practice. And it is the main channel to cultivate talents with innovative spirit and practical ability. Therefore, the reform of practice education is necessarily the most important work in the present teaching work. In order to achieve the anticipated results, universities should establish diversified mechanism of performance assessment on teacher, establish multi-type mechanism of cultivation on teacher and construct practical teaching teacher staff with reasonable structure.
Бесплатно
Статья научная
The study was aimed to create a predictive model for predicting students’ academic performance based on a neural network algorithm. This is because recently, educational data mining has become very helpful in decision making in an educational context and hence improving students’ academic outcomes. This study implemented a Neural Network algorithm as a data mining technique to extract knowledge patterns from student’s dataset consisting of 480 instances (students) with 16 attributes for each student. The classification metric used is accuracy as the model quality measurement. The accuracy result was below 60% when the Adam model optimizer was used. Although, after applying the Stochastic Gradient Descent optimizer and dropout technique, the accuracy increased to more than 75%. The final stable accuracy obtained was 76.8% which is a satisfactory result. This indicates that the suggested NN model can be reliable for prediction, especially in social science studies.
Бесплатно
Prediction of Mental Health Problems among Higher Education Student Using Machine Learning
Статья научная
Today, mental health problems become serious issues in Malaysia. In generally, mental health problems are health issues that effects on how a person feels, thinks, behaves, and communicate with others. According to National Health and Morbidity Survey (NHMS) 2017, one in five people in Malaysia is depression. Then, two in five people is anxiety and one in ten people is having stress. Higher education student also one of communities that have high risk to face mental health problems. The difficulties in identifying factors of mental health problems become a challenges and obstacle to help the person with mental health problem. Objectives of this paper are (1) review mental health problem among higher education student, (2) the contributing factors and (3) review the existing machine learning to analyse and predict mental health problem among higher education student. Finding of the paper will be used for other study to further discussion on mental health problems for implementation using computational modelling.
Бесплатно
Статья научная
Diabetes has since become global pandemic – which must be diagnosed early enough if the patients are to survive a while longer. Traditional means of detection has its limitations and defects. The adoption of data mining tools and adaptation of machine intelligence is to yield an approach of predictive diagnosis that offers solution to task, which traditional means do not proffer low-cost-effective results. The significance thus, is to investigate data feats rippled with ambiguities and noise as well as simulate model tractability in order to yield a low-cost and robust solution. Thus, we explore a deep learning ensemble for detection of diabetes as a decision support. Model achieved a 95-percent accuracy, with a sensitivity of 0.98. It also agrees with other studies that age, obesity, environ-conditions and family relation to the first/second degrees are critical factors to be watched for type-I and type-II management. While, mothers with/without previous case of gestational diabetes is confirmed if there is: (a) history of babies with weight above 4.5kg at birth, (b) resistant to insulin showing polycystic ovary syndrome, and (c) have abnormal tolerance to insulin.
Бесплатно
Статья научная
Chronic Kidney Disease (CKD) is considered a leading cause of high morbidity and mortality. Therefore, it needs early detection to allow timely intervention aimed at the enhancement of the patient outcome. The current study presents a Transparent CKD ML which combines the predictive power of efficient ML methods with the eXplainable AI techniques for transparent interpretibility of the prediction. This study has conducted an in-depth performance evaluation of the predictive power of the following eight machine learning algorithms: Logistic Regression, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, CatBoost, XGBoost, and AdaBoost on the 'Chronic Kidney Disease' dataset provided by UCI Machine Learning Repository. As a further study on algorithm performance, performance measures of accuracy, precision, recall, and F1 score were calculated; it was determined that Logistic Regression, Random Forest, and AdaBoost were performing very well and achieved 100% score in all metrics. This study further combined the ML models with eXplainable AI ( XAI) techniques to increase the transparency of the models. SHapley Additive exPlanations (SHAP) an XAI technique was used to provide critical insights into the causality that dictates the predictions of CKD. Thus, this combination ensures the best performance of the model, increasing the trust in AI within clinical practice. The present study, therefore, unleashes the transformational potential of AI technologies in radically renovating the management of CKD and improving patient outcomes across the world.
Бесплатно
Principle of Satellite Navigation Orbit and Positioning
Статья научная
We first have studied the principle of satellite navigation orbit and positioning. Then we have taken GPS and Transit satellite navigation system for example, and have discussed them importantly. We also have introduced GLonass globe satellite navigation system of Russia and Navsat navigation satellite system which studied by ESA.
Бесплатно
Problem Solving, Computer Technology, and Students’ Motivation in Learning Mathematics
Статья
In recent years, more and more attentions are given to developing problem solving skills and using computer technology in the teaching and learning of mathematics. Case studies, independent projects, and examples of applications of mathematics are used more and more frequently in mathematics classes in order to enhance students’ development in mathematical thinking and problem solving skills. Two examples of such studies are presented in this paper.
Бесплатно
Статья научная
The purpose of the scientific article is to identify a possible solution to the problem of improving students’ training effectiveness through the combined usage of active forms and methods of teaching students among the dependent learning parameters set. The authors came to this hypothetical opinion based on the comparative analysis results of previous studies, which confirm that the usage of active forms and methods of teaching students is the right vector for solving the lifelong problem of learning improving the effectiveness. It has been established that the available psychological and pedagogical literature does not provide specific solutions for modern students - cyber-socialised youth, which would help to substantiate the best ways to intensify students' learning and cognitive activity. Previous scientific studies have confirmed that the group of people who are most addicted to computer games, as practice shows, is difficult to motivate to study using traditional approaches when there is a distracting and, to some extent, gambling factor. Based on these circumstances, the proposed research is obviously logical from the need to improve the theory and methodology of vocational education through the usage of active forms and methods of teaching students. New circumstances have determined the subject of the study, which is a professional business game. It has been experimentally determined that during a professional business game students will use simulation models to solve professional problems. To organise and conduct a professional business game, teachers define game and functional goals. In the above variant of the professional business game structural scheme, the goal of accelerating the discipline development through students' learning activation is achieved. Organising and conducting a professional business game as an active teaching method involves preparation of both students and teachers for it, and also requires the methodological materials and technical means availability, which helps to increase the classes effectiveness conducted in a game form and to form professional competencies in students. The article provides practical steps for preparing participants of a professional business game.
Бесплатно
