International Journal of Modern Education and Computer Science @ijmecs
Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1123
Статья научная
Cognitive Load Theory (CLT) is an instructional design theory that aligns with human cognitive architecture for creating instructional materials, through the design guidelines of its 17 instructional effects. However, the Self-Management effect suggests that students can be instructed to manage their learning. The Collective Working Memory effect highlights how a group of students working together can foster a more effective learning environment than an individual student, resulting in better learning outcomes. This research explored applying the Self-Management effect of CLT alongside the Collective Working Memory effect learning data structures in basic programming and measuring their effectiveness regarding essential knowledge acquisition in declarative knowledge, knowledge transfer (near transfer) in procedural knowledge, and developing self-management skills. Cognitive load was measured to determine the difference between groups and to determine the correlation with learning outcomes. The study was carried out through a quasi-experimental design with homogeneous groups, involving students from the Autonomous University of Aguascalientes. The results suggest positive findings in knowledge transfer as well as the development of self-management skills. The cognitive load between the participating groups does not show any significant statistical difference, nor does it show any correlation with the learning results.
Бесплатно
Статья научная
The increasing use of e-mail in the world because of its simplicity and low cost, has led many Internet users are interested in developing their work in the context of the Internet. In the meantime, many of the natural or legal persons, to sending e-mails unrelated to mass. Hence, classification and identification of spam emails is very important. In this paper, the combined Particle Swarm Optimization algorithms and Artificial Neural Network for feature selection and Support Vector Machine to classify and separate spam used have and finally, we compared the proposed method with other methods such as data classification Self Organizing Map and K-Means based on criteria Area Under Curve. The results indicate that the Area Under Curve in the proposed method is better than other methods.
Бесплатно
Emerging Themes and Research Directions in MOOCs and Micro-credentials
Статья научная
Massive Open Online Courses (MOOCs) and micro-credentials have emerged as key innovations in modern education, offering scalable, flexible access to learning and skill development. Despite their potential, challenges such as low learner engagement, high dropout rates, and uncertainty over the value of digital credentials remain. This study analyzes 3,743 publications from 1970 to 2024 using bibliometric and text analytics to uncover research trends, influential studies, and dominant themes in the field. Results show a surge in research from 2014 to 2020 driven by digital technology adoption and the COVID-19 pandemic followed by a decline as hybrid learning models became normalized. Key themes include learner motivation, engagement strategies, digital badges, and ethical concerns tied to data-driven education. While advancements in learning analytics and personalization show promise, the study underscores the need for standardized credentialing, scalable engagement frameworks, and ethical governance in online education. Critical gaps remain, particularly in evaluating the long-term impact of micro-credentials on employability and understanding adoption differences across regions and socio-economic groups. Limitations include reliance on the Web of Science and author-provided keywords, which may narrow the scope. Despite this, the study provides a systematic overview and offers practical insights for improving MOOCs and micro-credentials as tools for lifelong learning and global educational equity.
Бесплатно
Emotion Classification Utilizing Transformer Models with ECG Signal Data
Статья научная
In recent years, there has been growing interest in leveraging physiological signals, such as Electrocardiogram (ECG) data, for emotion classification tasks. This study explores the efficacy of utilizing Transformer models, a state-of-the-art architecture in natural language processing, for emotion classification using ECG signal data. The proposed methodology involves preprocessing the ECG signals, extracting relevant features, and model architecture consists of DistilBERT model, Pooling Layer to obtain a fixed-size representation of the ECG signal, Dropout Layer to prevent overfitting, Fully Connected Layer for classification. Experiments are conducted on publicly available dataset, demonstrating the effectiveness of the proposed approach compared to traditional machine learning methods. The results suggest that DistilBERT Transformer model can effectively capture complex temporal dependencies within ECG signals, thereby achieving notable performance of 76% accuracy in emotion classification tasks. This research contributes to the growing body of literature exploring the intersection of physiological signals and deep learning techniques for affective computing applications.
Бесплатно
Emotional Design in Multimedia Learning: How Emotional Intelligence Moderates Learning Outcomes
Статья научная
This study is designed as a preliminary study to explore the effects of emotional intelligence (EI) on achievement, perceived intrinsic motivation and perceived satisfaction when expose to an emotional designed Multimedia Learning Environment (MLE) that was designed to induce either positive, neutral or negative emotions. All three designs had similar content and narration but differed in visual element such as colour, font size, font style and images. Based on the findings, it was reported that students performed better in the design used to induce negative emotion (NegD design) followed by the positive (PosD) and Neutral (NeuD). There is no significant difference in levels of emotional intelligence towards these learning outcomes; however, students with Low EI performed better overall. EI only qualified perceived satisfaction when using a MLE designed to induce emotions and it was found that students with Low EI preferred the design that induces positive emotions. In addition, High EI students favored designs with emotionality (positive or negative) compared to neutral design.
Бесплатно
Empirical Analysis of Bagged SVM Classifier for Data Mining Applications
Статья научная
Data mining is the use of algorithms to extract the information and patterns derived by the knowledge discovery in databases process. Classification maps data into predefined groups or classes. It is often referred to as supervised learning because the classes are determined before examining the data. The feasibility and the benefits of the proposed approaches are demonstrated by the means of data mining applications like intrusion detection, direct marketing, and signature verification. A variety of techniques have been employed for analysis ranging from traditional statistical methods to data mining approaches. Bagging and boosting are two relatively new but popular methods for producing ensembles. In this work, bagging is evaluated on real and benchmark data sets of intrusion detection, direct marketing, and signature verification in conjunction with as the base learner. The proposed is superior to individual approach for data mining applications in terms of classification accuracy.
Бесплатно
Empirical Analysis of HPC Using Different Programming Models
Статья научная
During the last decade, Heterogeneous systems are emerging for high performance computing [1]. In order to achieve high performance computing (HPC), existing technologies and programming models aims to see rapid growth toward intra-node parallelism [2]. The current high computational system and applications demand for a massive level of computation power. In last few years, Graphical processing unit (GPU) has been introduced an alternative of conventional CPU for highly parallel computing applications both for general purpose and graphic processing. Rather than using the traditional way of coding algorithms in serial by single CPU, many multithreading programming models has been introduced such as CUDA, OpenMP, and MPI to make parallel processing by using multicores. These parallel programming models are supportive to data driven multithreading (DDM) principle [3]. In this paper, we have presented performance based preliminary evaluation of these programming models and compared with the conventional single CPU serial processing system. We have implemented a massive computational operation for performance evaluation such as complex matrix multiplication operation. We used data driven multithreaded HPC system for performance evaluation and presented the results with a comprehensive analysis of these parallel programming models for HPC parallelism.
Бесплатно
Статья научная
The main aim of this paper is to avoid hot-spot problem in wireless sensor network with uniform energy dissipation among cluster heads in the network. It proposes an energy efficient unequal clustering mechanism to form limited and equivalent number of clusters across different levels of wireless sensor network to enable invariable energy consumption among them. Concentrated cluster formation near base station ensures minimum relay burden on cluster heads to avoid hot-spot problem in multi-hop data forwarding model. Equivalent number of clusters at each level ensures in-common network load on each cluster head among different data forwarding routes. In addition, a simple disjoint multi-hop routing technique is proposed for smooth data forwarding process. Simulation results evidence that the proposed unequal clustering algorithm overcomes hot-spot problem with invariable energy dissipation among cluster heads across the network and elevates sensor network lifetime.
Бесплатно
Energy saving VM placement in cloud
Статья научная
The tremendous gain owing to the ubiquitous acceptance of the cloud services across the globe results in more complexity for the cloud providers by way of resource maintenance. This has a direct effect on the cost economy for them if the resources are not efficiently utilized. Most of the allocation strategies follow mechanisms involving direct allotment of VMs onto the servers based on their capabilities. This paper presents a VM allocation strategy that looks at VM placement by allowing server capacity to be partitioned into different classes. The classes are mainly based on the RAM and processing abilities which would be matched with VMs need. When the match is found the servers from this category are provisioned for the task executions. Based on the experimentation for various datacenter scenarios, it has been found that the proposed mechanism results in significant energy savings with reduced response time compared to the traditional VM allocation policies.
Бесплатно
English Pronunciation Practice Method with CG Animations Representing Mouth and Tongue Movements
Статья научная
Method for English pronunciation practice utilizing Computer Graphics: CG animation representing tongue movements together with mouse movements is proposed. Pronunciation practice system based on personalized CG animation of mouth movement model is proposed. The system enables a learner to practice pronunciation by looking at personalized CG animations of mouth movement model , and allows him/her to compare them with his/her own mouth movements. In order to evaluate the effectiveness of the system by using personalized CG animation of mouth movement model, Japanese vowel and consonant sounds were read by 8 infants before and after practicing with the proposed system, and their pronunciations were examined. Remarkable improvement on their pronunciations is confirmed through a comparison to their pronunciation without the proposed system based on identification test by subjective basis. In addition to the mouth movement, tongue movement is represented by CG animation. Experimental results show 20 to 40 % improvement is confirmed by adding tongue movements for pronunciations of "s" and "th".
Бесплатно
Статья научная
The Recurrent Neural Network (RNN) is well suited for emotional speech recognition because its uses constantly time shifting property. Even though RNN gives better results GRU, LSTM and BILSTM solves the gradient problem and overfitting problem joins the path to reduces the efficiency. Hence in this paper five deep learning architecture is designed in order to overcome the major issues using data augmentation and spatial feature. Five different architectures like: Enhanced Deep Hierarchal LSTM & GRU (EDHLG), EDHBG, EDHGL, EDHGB & EDHGG are developed with dropout layers. The raw data learned from LSTM will be given as the input to GRU layer for deepest learning. Thus, the gradient problem is reduced, and accuracy of each emotion was increased. Also, to enhance the accuracy level spatial features were concatenated with MFCC. Thus, in all models, the experimental evaluation with the Tamil emotional dataset yielded the best results. EDHLG has a 93.12% accuracy, EDHGL has a 92.56 percent accuracy, EDHBG has a 95.42 percent accuracy, EDHGB has a 96 percent accuracy, and EDHGG has a 94 percent accuracy. Furthermore, the average accuracy rate of a single individual LSTM layer is 74%, while BILSTM is 77%. EDHGB outperforms almost all other systems, by an optimal system of 94.27 percent and then a maximum overall accuracy of 95.99 percent. For the Tamil emotion data, emotional states such as happy, fearful, angry, sad, and neutral have a 100% prediction accuracy, while disgust has a 94 percent efficiency rate and boredom has an 82 percent accuracy rate. Also, the training time and evaluation time utilized by EDHGB is 4.43 mins and 0.42 mins which is less when compared with other models. Hence by changing the LSTM, BILSTM and GRU layers large analysis of experiment on Tamil dataset is done and EDHGB is superior to other models, and when compared with basic models LSTM and BILSTM around 26% more efficiency is gained.
Бесплатно
Enhanced Learning with Abacus and its Analysis Using BCI Technology
Статья научная
Although technology is successfully being used these days as a tool to improve education at all levels, its improper usage is curbing the imagination of the student community, leading to a diminution in their thinking capacity and ability to focus and concentrate. As attention is a vital cognitive feature of any learning process, students these days are not coping well with this process. This study attempts to analyse the focusing capacity of students from two different backgrounds; students who have undergone training in mental arithmetic and usage of the abacus and students without any formal mental arithmetic training. The analysis is done through a simple Electroencephalogram (EEG) based gaming software, which measures the time needed for the players to focus and reach a specific attention level. An EEG device measures brain invoked potentials. Due to the availability of low cost commercial grade EEG devices, usage of these devices today, is not confined only to research and clinical purposes, but is being used beyond these applications. This study is an attempt to apply Brain Computer Interface (BCI) Technology to assess cognition. The performance of the first category was found to be better than the second set of students.
Бесплатно
Статья научная
With the outgrowth of cloud computing, a large amount of private information is stored over cloud servers, which is in encrypted format. But searching over encrypted data is very difficult. Earlier search schemes were based on Boolean search through keywords. But don't consider relevance of files. After that ranked search comes into its role, which uses searchable symmetric encryption (SSE). To achieve more practical and efficient design method was further modified to "Order preserving symmetric encryption" (OPSE), which uses primitives and indexed metadata files used in ranked SSE. In this proposed work further enhancements are done to reduce storage space for encrypted metadata using Porter Stemming method. Improvements in retrieval time are also done by using Boyer Moore's searching algorithm.
Бесплатно
Enhanced Ring Signatures Schemes for Privacy Preservation in Wireless Sensor Networks
Статья научная
Advancements in the domains of low-data-rate wireless networking and micro-electro-mechanical systems enabled the inception of a new networking domain, called wireless sensor network. These ad-hoc kind of networks have diversified applications in battlefield surveillance, disaster monitoring, intrusion detection etc. These networks consist plethora of sensor nodes which are severely resource constrained. As the application of the wireless sensor network is increasing, there is an emerging need for the security and privacy scheme which makes the network secure from various attacks and hide the ongoing activities in the network from a non-network entity. Privacy in wireless sensor network is yet a challenging domain to work on. Lot of work has been done to ensure privacy in the network. These relate to provide privacy in terms of the network entity and the privacy of the sensed information. Most of the solutions till date is based upon routing in the network layer, random walk based flooding, dummy data injection and cross layer solutions. Each of the schemes induce some overhead in the network. A light weight scheme is always desired for resource constraint wireless sensor networks. In this work we will propose a scheme which assures the privacy of the nodes in the network along with the privacy of the event generated in the network through a self organizing scheme. Through various simulation results the validity of our scheme among different network scenarios will be shown. We will also prove through graphical results that our proposed scheme enhances network lifetime quite satisfactorily.
Бесплатно
Enhancement of energy aware hierarchical cluster-based routing protocol for WSNs
Статья научная
Wireless sensor networks are present almost everywhere because of their extensive variety of utilization. However, sensor nodes are battery constrained. Therefore, proficient utilization of power turns into testing issues. Aggregated data at the base station, by individual nodes cause a flood of information which results in greater power consumption. To avoid or minimize this issue a new technique of data aggregation has been proposed. In this paper, we proposed enhanced novel energy aware hierarchical cluster-based (ENEAHC) routing protocol with the aim to: minimizing as much as total energy consumption and to enhance the performance of the energy efficient protocol by using inter-cluster based data aggregation. LZW based data aggregation likewise connected to the Cluster head (CH) to improve more results. Performance results show ENEAHC scheme reduce the end-to-end energy consumption and prolong the lifetime of the network compared to well known clustering algorithms i.e. LEACH and NEAHC. We design the actual relay node selecting issue like a non-linear programming issue and make use of property of compress sensing to find the optimal solution. The results are evaluated at the end of this paper through simulation.
Бесплатно
Статья научная
This research study aims to compare the learning achievements of first-year students in an algorithm and programming course before and after participating in cooperative blended learning activities focused on variables, expressions, and control commands. By utilizing problem-based learning methods, the researchers sought to meticulously analyze the profound impact of these activities on students’ academic advancement. The research tools deployed encompassed satisfaction questionnaires and achievement tests. The research cohort encompassed seven experienced specialists within higher education institutions, each endowed with a minimum of ten years of pedagogical experience, along with twenty-five participating students. Employing rigorous statistical analysis via T-tests, the study conclusively revealed a statistically noteworthy enhancement in student achievement post the program, underscoring the affirmative influence of cooperative blended learning activities. Moreover, the overall satisfaction level among learners engaging in the proposed learning activities was remarkably elevated, evident through an average satisfaction rating of 4.54 and a standard deviation of 0.73. These empirical insights succinctly underscore the demonstrable effectiveness of assimilating cooperative blended learning methods within algorithm and programming education, thereby accentuating the pivotal role of these pedagogical approaches in shaping contemporary educational practices.
Бесплатно
Статья научная
Customer attrition is a major issue that affects the telecom industry as it reduces the company’s revenues and the overall customer base. Solving this problem involves the use of accurate prediction models that utilize CRM data and machine learning algorithms. Though several research papers have been written and published on CCP in the telecom industry, the existing models lack reliability and accuracy. The use of sophisticated data mining and machine learning techniques has been widely practised for improving predictive models. Churn prediction models that exist have their problems in terms of accuracy and errors. It is still important to develop more sophisticated models that can work well with large data and give accurate predictions. Therefore, this work aims to offer the OKMSVM model for multiclass cancer-type classification. The method applied for the dimensionality reduction pre-process is Kernel Principal Component Analysis (KPCA) and the feature selection pre-process is done using Ant Lion Optimization (ALO). This combination assists in improving the chance of the prediction and also the reduction of probable errors. The performance of the proposed OKMSVM model was compared with some of the most common churn prediction models such as HTLSVM, DNN, ICPCSF and other ML models. It was seen that the OKMSVM model outperformed other models with an accuracy of 91. 5%, an AUC of 85. Accurate, with a correlation coefficient of 0. 838. It further shows that this model is better than the current models in the market in estimating customer churn.
Бесплатно
Enhancing Efficient Study Plan for Student with Machine Learning Techniques
Статья научная
This research aims to enhance the achievement of the students on their study plan. The problem of the students in the university is that some students cannot design the efficient study plan, and this can cause the failure of studying. Machine Learning techniques are very powerful technique, and they can be adopted to solve this problem. Therefore, we developed our techniques and analyzed data from 300 samples by obtaining their grades of students from subjects in the curriculum of Computer Science, Faculty of Science and Technology, Sakon Nakhon Rajabhat University. In this research, we deployed CGPA prediction models and K-means models on 3rd-year and 4th-year students. The results of the experiment show high performance of these models. 37 students as representative samples were classified for their clusters and were predicted for CGPA. After sample classification, samples can inspect all vectors in their clusters as feasible study plans for next semesters. Samples can select a study plan and predict to achieve their desired CGPA. The result shows that the samples have significant improvement in CGPA by applying self-adaptive learning according to selected study plan.
Бесплатно
Enhancing Emotion Detection with Adversarial Transfer Learning in Text Classification
Статья научная
Emotion detection in text-based content, such as opinions, comments, and textual interactions, holds pivotal significance in enabling computers to comprehend human emotions. This symbiotic understanding between machines and human languages, powered by technological advancements like Natural Language Processing and artificial intelligence, has revolutionized the dynamics of human-computer interaction. The complexity of emotion detection, although challenging, has surged in importance across diverse domains, encompassing customer service, healthcare, and surveillance of social media interactions. Within the realm of text analysis, the quest for accurate emotion detection necessitates a profound exploration of cutting-edge methodologies. This pursuit is further intensified by the imperative to fortify models against adversarial attacks, a pressing concern in deep learning-based approaches. To address this critical challenge, this paper introduces a pioneering technique—adversarial transfer learning—specifically tailored for emotion classification in text analysis. By infusing adversarial training into the model architecture, the proposed approach emerges a solution that not only mitigates the vulnerabilities of existing methods but also fortifies the model against adversarial intrusions. In realizing the potential of the proposed approach, a diverse array of datasets is harnessed for comprehensive training. The empirical results vividly demonstrate the efficacy of this approach, showcasing its superior performance when compared to state-of-the-art methodologies. Notably, the suggested approach yields in advancements in classification accuracy. In particular, the deployment of the Adversarial transfer learning methodology has increased in accuracy of 17.35%. This study, therefore, encapsulates a dual achievement: the introduction of an innovative approach that leverages adversarial transfer learning for emotion classification, and the subsequent empirical validation of its unparalleled efficiency. The implications reverberate across multiple sectors, extending the horizons of accurate emotion detection and laying a foundation for the next stride in human-computer interaction and emotion analysis.
Бесплатно
Enhancing Information Systems Students' Soft Skill – a Case Study
Статья научная
Information Systems (IS) curricula should provide students with both technical and non-technical (soft) skills. The technical aspects are covered by various courses. However, soft skills like teamwork, interpersonal communication, presentation delivery, and others are hardly covered. Employers, who consider both technical and soft skills to be equally important, search for professional Information Systems employees possessing both sets of skills. These employers often complain that finding an IS graduate with both types of skills is quite difficult. The IS 2010 Model Curriculum refers to both types of skills, considering them an essential part of the graduate knowledge base. However, in many cases the soft skills are not sufficiently addressed, and even if they are, it is not necessarily in the context of software development projects. The Systems Analysis and Design (SAD) course provides an important foundation for the IS profession. This is especially true due to the emerging role of the programmer-analyst who is responsible not only for programming but also for some analysis work. In order to strengthen the soft skills in the context of system analysis and design, we suggest a workshop structure emphasizing these soft skills while students analyze and design a complete information system. Our SAD workshop includes some face to face lectures and team-based collaborations. The students undertake many online activities, including teamwork, interviews with simulated clients, team-based peer reviews, presentation delivery, and so forth. The workshop employs a grade difference calculation mechanism that revealed, along with the students' reflections, that the workshop structure enhanced the students' ability to cope with the workshop assignments while strengthening their soft skills and preparing them for their future analysis and design challenges.
Бесплатно
