Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Multi-Level Text Clustering in Subject Knowledge Library and its Visualization
Get PDFThe large-scale and complex data generated in the teaching field of business administration poses challenges for decision-makers and managers of companies, and how to effectively extract and manage the useful information contained in these data has become a problem to be solved. Currently available methods of subject knowledge library clustering and visualization struggle to handle the complexity and multi-hierarchies of such subject data effectively or meet users’ requirements for advanced semantic understanding and retrieval. In view of these matters, this study aims to probe deeper into the problem of multi-level text clustering in the subject knowledge library and its visualization. Firstly, an innovative strategy-based subject semantic representation method for knowledge libraries was proposed to better interpret and represent the semantic information of subject data. Secondly, a subject clustering model of the knowledge library was constructed based on an improved hierarchical Dirichlet polynomial distribution, enabling efficient and accurate clustering of subject data. Lastly, visualization technology was employed to display the cluster results, allowing users to gain a clear understanding of the internal relationships and structure of the subject data. The research findings of this study could provide valuable new tools and methods for solving the problem of subject knowledge library management and utilization, analyzing the subject data, and supporting decision-making. As a result, they hold both theoretical and practical significance
A Study on the Influence of Hybrid Teaching on Students’ Learning Attitude and Learning Confidence
Get PDFIntelligent terminal equipment is becoming extremely popular, and online learning has been increasingly accepted by people. In this context, it is particularly important to consider the ways of activating students’ interest in learning, improving their learning efficiency, and perception of network learning, as well as whether they can meet the requirements of the curriculum. The participants of this study are university students from China’s Fujian Province. According to the findings, it is suggested to improve the hybrid teaching resources, help teachers establish a correct outlook on learning, and improve their online learning management abilities
Developing a Mobile-Assisted Project-Based Learning Model for a Learning Media Course
Get PDFThe ability to create and use effective learning media is critical to students’ academic success. Therefore, a customized learning model for a learning media course needs to be developed to enhance learning effectiveness. The mobile-assisted project-based learning (PjBL) model was developed under the guidance of the Dick and Carey model to improve student learning outcomes in a learning media course. The validity test conducted for this model received a good score from expert validators, with an average score of 4.50 for usability and presentation, 4.56 for display, and 4.53 for language. The effectiveness test showed a high average n-gain of 0.83 in the one-to-one trial, 0.74 in the small group trial, and 0.73 in the large group trial. In addition, student feedback on the practicality of the mobile-assisted PjBL model was very good, with an average score of 4.31, or 86% of the ideal score. Based on these results, it is highly recommended to implement the mobile-supported PjBL model when teaching a learning media course
Cluster-Factors of Mobile Sensor Network Technology for Security Enhanced PEGASIS
Get PDFMobile wireless sensor networks (MWSNs) have been a hot topic of research, and numerous routing methods have been developed to increase energy efficiency and extend longevity. Nodes close to the sink often use more energy to transmit data from their neighbors to the sink, which causes them to run out of energy faster. These places are also referred to as rendezvous points, and choosing the best one is a hard task. The likelihood of choosing an ideal node as the rendezvous point will be extremely low because hierarchical algorithms only use their local information to select these places. The warm spot problem is addressed from four angles in this work using the Enhanced Power-Efficient Gathering in Sensor Information Systems (EPEGASIS) technique. In order to limit the amount of energy used during transmission, the ideal communication distance is first calculated. To balance the energy consumption among the nodes, mobile sink technology is employed once a threshold value is set to safeguard the dying nodes. The node can then modify its communication range based on how far away the sink node is from it. Thorough testing has been done to demonstrate that our suggested EPEGASIS works better in terms of longevity, drive usage, and web latency
Usability Evaluation of Tablet-Based Electronic Medical Record Interface in Supporting Elderly Medical Doctors
Get PDFRecently, tablet-based devices have become significantly more utilized platforms for electronic medical record (EMR) systems. EMR is the digital counterpart of the medical doctor’s office paper charts. EMR systems contain the medical and treatment histories of the patients in a unified practice. Nevertheless, statistics indicate that a considerable percentage of medical doctors are elderly, aged 60 and above. As using mobile handheld devices (including tablets) poses a well-recognized usability challenge for elderly users, the user interface (UI) usability of tablet-based EMR systems must be thoroughly assessed, considering the needs of elderly medical doctors. Accordingly, our objective is to address this need. Three expert evaluators implemented the heuristic evaluation (HE) approach to evaluate the UI usability of a commercial EMR system that is a tablet-based platform. Applying the HE approach helped identify usability problems that elderly medical doctors might encounter when utilizing a tablet-based EMR UI. In total, eight usability problems contributed to the seven heuristic violations discovered
Speech Recognition Algorithms based Cough Recognition System
Get PDFThis paper introduces an innovative technique for creating a cough detection system that relies on speech recognition algorithms. The strategy utilizes the Kaldi platform, which is open source and incorporates a hybrid system of Gaussian Mixture Model-based Hidden Markov Models (GMM-HMM) through a straightforward monophone training model. Additionally, the study examines the effectiveness of two different feature extraction approaches, Mel Frequency Cepstral Coefficient (MFCC) and Perceptual Linear Prediction (PLP). The proposed system can function as a collection tool for gathering natural and spontaneous cough data from conversations or continuous speech. The paper also compares the Kaldi and CMU Sphinx4 toolkits, concluding that Kaldi’s use of GMM-HMM outperforms CMU Sphinx4
Classification of Ocular Diseases Related to Diabetes Using Transfer Learning
Get PDFAlthough artificial intelligence enables the detection of abnormalities in medical images and is widely used as a computer vision technology, many researchers have focused on the detection of only one disease related to diabetes, which is diabetic retinopathy. In fact, patients face a significant risk of two other illnesses: cataract and glaucoma. In this article, we examined the diagnosis of these three eye diseases caused by diabetes and compared four approaches to classify these conditions. The proposed approaches are based on the transfer learning technique. We started by filtering, preparing, and augmenting the dataset, then applied transfer learning for feature extraction using two different architectures: VGG16 and RESNET50. We also investigated the impact of using contrast limited adaptive histogram equalization on the accuracy and precision of the models. This filter was used in a pre-training step for diabetic retinopathy diagnosis and in this paper proved its efficiency for glaucoma and cataract too. The final layers were replaced by Random Forest for classification. Models performed acceptable accuracies of 89.17% and 85.64% without operating contrast-limited adaptive histogram equalization and achieved better results when applying contrast-limited adaptive histogram equalization, with an accuracy of 97.48% and 96.66% for VGG16 and RESNET 50, respectively
Arrhythmia Detection Based on New Multi-Model Technique for ECG Inter-Patient Classification
Get PDFThis paper presents a novel model for arrhythmia detection based on a cascading technique that utilizes a combination of the One-Sided Selection (OSS) method, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms, this model denoted by (OWSK) model to classify four types of electrocardiogram (ECG) heartbeats following inter-patient scheme. The OWSK model consists of three stages. The first stage involves resampling using the One-Sided Selection (OSS) method to solve the imbalance problem and reduce data by removing noisy, borderline, and redundant samples. The second stage involves using Wavelet Transformation (WT) and Power Spectral Density (PSD) to extract the most relevant frequency domain features. The third stage involves a cascading process by constructing the classifier from SVM trained on the whole dataset to classify normal and abnormal beats. Then, KNN (K-Nearest Neighbors) is trained on only the three irregular minority classes to classify the three types of arrhythmias for the detection of ventricular ectopic beats, supraventricular ectopic beats, and fusion beats (V, S, and F). The performance of the proposed model is evaluated in terms of different metrics, including accuracy, recall, precision, and F1 score. The results show the superiority of the proposed model in medical diagnosis compared to the latest works, where it achieves 90%, 90%, 93%, and 91% for accuracy, recall, precision, and F1 score under the inter-patient paradigm and 98%, 98%, 98%, and 98% under the intra-patient paradigm
An Integrated Ensemble Learning Framework for Predicting Liver Disease
Get PDFThe liver disease has become a pressing global issue, with a sharp increase in cases reported worldwide. Detecting liver disease can be difficult as it often has few noticeable symptoms, which means that by the time it is detected, it may have already progressed to an advanced stage, resulting in many people dying without even realizing they had it. Early detection is crucial as it enables patients to begin treatment earlier, which can potentially save their lives. This study aimed to assess the efficacy of five ensemble machine learning (ML) models, namely RF, XGBoost, Extra Trees, bagging, and stacking methods, in predicting liver disease. It uses the ILPD dataset. To prevent overfitting and biases in the dataset, several pre-processing statistical techniques were employed to handle missing data, outliers, and data balancing. The study’s results underline the importance of using the RFE feature selection method, which allowed the use of only the most relevant features for the model, which may have improved the accuracy and efficiency of the model. The study found that the highest testing accuracy of 93% was achieved by the proposed model, which utilized an improved preprocessing approach and a stacking ensemble classifier with RFE feature selection. The use of ensemble ML has given promising results. Indeed, medical professionals can develop models better equipped to handle the complexity and variability of medical data, resulting in more accurate diagnoses, more effective treatment plans, and better patient outcomes
The Effectiveness of Multimedia and Virtual Environments in Light of the Conflict Strategy to Reduce Misconceptions in Mathematics among First-Year University Students
Get PDFThe roots of misconceptions in mathematics among first-year students at Hashemite University can be traced back to a flaw in the foundation of their previous mathematics knowledge acquired over the course of their academic years. This flaw presents a significant challenge for them during their studies. This study aimed to determine the effectiveness of multimedia and virtual environments in reducing misconceptions in mathematics among first-year students at Hashemite University, based on the conflict strategy. The study sample consisted of a random cluster sample of 109 male and female students from Hashemite University. The researcher observed the students and recorded their test scores. The researcher conducted face-to-face interviews to collect data for the study and performed statistical analysis using the t-test. The results showed that the percentage of misconceptions in mathematics among firstyear students at the Hashemite University for types 1, 2, 3, 4, and 5, respectively, amounted to 23%, 8%, 13.8%, 14.7%, and 0%. And 13.8%. The study examined the effectiveness of multimedia and virtual environments in reducing misconceptions in mathematics among first-year students at Hashemite University, based on the conflict strategy