Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Empowering Diabetic Eye Disease Detection: Leveraging Differential Evolution for Optimized Convolution Neural Networks
Get PDFDiabetic eye detection has become a major concern across the globe, which could be effectively addressed by automated detection using a deep convolutional neural network (DCNN). CNN models have better detection and classification accuracy than other state-of-theart models. In this paper, a differential evolution (DE)-optimized CNN has been proposed for the single-step classification of diabetic retinopathy (DR) and glaucoma images. DE has been used to find out the optimized values of four hyper-parameters of CNN, i.e., the number of filters in the first layer, the filter size, the number. of convolution layers, and the number of strides. Simulation has been done using three publicly available datasets, and the accuracy obtained is 87.8%, 92.3%, and 88.7%, respectively, which outperforms other models. No other state-of-the-art model has used DE for hyper-parameter tuning in CNN models. Also, no other additional segmentation approach or handcrafted features have been used. The model has been kept simple to reduce computational costs
Development of a Deep Learning Model for the Prediction of Ventilator Weaning
Get PDFThe issue of failed weaning is a critical concern in the intensive care unit (ICU) setting. This scenario occurs when a patient experiences difficulty maintaining spontaneous breathing and ensuring a patent airway within the first 48 hours after the withdrawal of mechanical ventilation. Approximately 20% of ICU patients experience this phenomenon, which has severe repercussions on their health. It also has a substantial impact on clinical evolution and mortality, which can increase by 25% to 50%. To address this issue, we propose a medical support system that uses a convolutional neural network (CNN) to assess a patient’s suitability for disconnection from a mechanical ventilator after a spontaneous breathing test (SBT). During SBT, respiratory flow and electrocardiographic activity were recorded and after processed using time-frequency analysis (TFA) techniques. Two CNN architectures were evaluated in this study: one based on ResNet50, with parameters tuned using a Bayesian optimization algorithm, and another CNN designed from scratch, with its structure also adapted using a Bayesian optimization algorithm. The WEANDB database was used to train and evaluate both models. The results showed remarkable performance, with an average accuracy 98 ± 1.8% when using CNN from scratch. This model has significant implications for the ICU because it provides a reliable tool to enhance patient care by assisting clinicians in making timely and accurate decisions regarding weaning. This can potentially reduce the adverse outcomes associated with failed weaning events
A Systematic Investigation on Botnet Intrusion Detection Using Various Machine Learning Techniques
Get PDFThe Internet of Things (IoT) is growing rapidly in an exponential manner due to its versatility in technology. This has led to many challenges in securing the IoT environment. Devices in IoT environments are vulnerable to various cyberattacks. Botnet-based attacks are predominant and widespread in nature. Due to insufficient memory and computational power, the IoT environment cannot handle the botnet attack that affects security. Identifying intrusions in IoT environments is another challenge for researchers. Finding unknown patterns in the data generated through IoT networks helps improve security in the IoT environment. Machine learning (ML) is a platform that helps identify patterns in the provided data. In this study, we present our research on classifying incoming data from the IoT as malicious or benign using machine learning techniques. We propose an ML-based botnet attack detection framework for nine commercial IoT devices that primarily target BASHLITE and Mirai botnet attacks. Rigorous pragmatic research was conducted on the N-BaIoT dataset, which was extracted from realtime IoT devices connected to a network. Using this framework, the results have been depicted, which can efficiently detect botnet attacks and can also be applied to any other types of attacks
XAI-PhD: Fortifying Trust of Phishing URL Detection Empowered by Shapley Additive Explanations
Get PDFThe rapid growth of the Internet has led to an increased demand for online services. However, this surge in online activity has also brought about a new threat: phishing attacks. Phishing is a type of cyberattack that utilizes social engineering techniques and technological manipulations to steal crucial information from unsuspecting individuals. Consequently, there is a rising necessity to create dependable phishing URL detection models that can effectively identify phishing URLs with enhanced accuracy and reduced prediction overhead. This study introduces XAI-PhD, an innovative phishing detection method that utilizes machine learning (ML) and Shapley additive explanation (SHAP) capabilities. Specifically, XAI-PhD utilizes SHAP to thoroughly analyze the significance of each feature in influencing the decision-making process of the classifier. By selectively incorporating input characteristics based on their SHAP values, only the most crucial attributes are assessed, enabling the development of a highly adaptable and generalized model. XAI-PhD utilizes a lightweight gradient boosting machine as its classifier, and a series of rigorous tests are conducted to assess its performance compared to established baseline methods. The empirical findings unequivocally demonstrate the exceptional effectiveness of XAI-PhD, as evidenced by its remarkable accuracy and F1-score of 99.8% and 99%, respectively. Moreover, XAI-PhD exhibits high computational efficiency, requiring only 1.47 milliseconds and 18.5 microseconds per record to generate accurate predictions
The Importance of Soft Skills for Academic Performance and Career Development—From the Perspective of University Students
Get PDFIn the present era, the importance of soft skills as a crucial element for personal and professional success is widely acknowledged. When hiring new employees, these soft skills are highly valued by employers. However, many students are unaware of the crucial role those soft skills play in their education and career success, hindering their progress in developing these skills. This study aims to assess students’ perceptions of the importance of soft skills for academic performance and career development. A questionnaire-based online survey was conducted, involving 968 undergraduate students from eight universities in Vietnam, to gather data. The findings showed that most respondents recognized the significance of soft skills in fostering positive relationships, career advancement, and securing desirable employment. However, students did not believe that these skills had a substantial impact on their academic performance. Communication, teamwork, collaboration, and time management skills were identified as the most critical soft skills for enhancing academic performance, while teamwork, collaboration, leadership, and problem-solving skills were considered pivotal for career development. Moreover, a significant portion of students perceived their soft skills level to be below the desired threshold, showing more confidence in skills they considered to be more important. Similarly, students tended to prioritize the development of soft skills that they perceived as essential to their personal goals
Physics XP: Integration of ChatGPT and Gamification to Improve Academic Performance and Motivation in Physics 1 Course
Get PDFThe understanding of the physics course (PC) at the university level faces many challenges, highlighting the gap in mathematical knowledge and conceptual phenomenological analysis that affect the assimilation of more advanced physical concepts. The synergistic integration of artificial intelligence (AI) and gamification into the teaching and learning process transforms this process into an engaging and collaborative experience, improving interaction and personalization of learning and incorporating game elements to increase student participation and motivation. The objective of this research was to measure the influence of the integration of ChatGPT, AI, and gamification on the academic results and motivation of students in the physics 1 course. A total of 188 students participated in this study: 98 students in the experimental group and 90 students in the control group. The grades obtained in the standardized evaluations were compared in both the partial exam and the final exam of the physics 1 course, and a Likert-type questionnaire was used for motivation. The results show a better academic performance (AP) of the students in the experimental group than the control group, which is statistically evidenced (p < 0.01). It also shows that students who developed the course using ChatGPT AI and gamification developed a more positive attitude towards interest, usefulness, self-efficacy, active participation, and personal satisfaction in the physics 1 course
A Comprehensive Analysis of Faculty Adoption of Cloud Computing E-Learning in Ghanaian Technical Universities
Get PDFCloud-based e-learning is a technology used to enhance teaching and learning in universities. However, its adoption in technical universities is low, and research into the factors influencing teacher adoption is limited. To address this situation, a study was conducted at Ghanaian technical universities to examine the determinants of teachers’ adoption of cloud-based e-learning. The study involved 1258 respondents, the majority of whom were male (853, or 67.8%), aged between 30 and 40 (47%), and 79.1% had a master’s degree. The results showed that individuals with a master’s degree had a higher level of knowledge of cloud-based e-learning compared to those with a bachelor’s, doctorate, or another master’s degree in technology. The study identified seven factors influencing the use of cloud-based e-learning, including pedagogical innovation, e-infrastructure readiness, cloud-based e-learning security, university location, the usefulness of cloud-based e-learning, and provider support. Interestingly, the cost of cloud-based e-learning had no significant impact
Teaching of Physics in Engineering from Problem-Based and Project-Based Learning Approaches
Get PDFWithin the scope of this research, an evaluation was conducted on the problem-based learning (PBL) and project-based learning (PrBL) methods in teaching physics to mechanical and electrical engineering students at a public university in Peru. Two groups, each consisting of 15 and 16 students, were carefully selected to ensure uniformity in academic, socioeconomic, and emotional aspects. The measurement of academic performance was conducted both at the beginning and the end of the period. The statistical analysis using the t-student test revealed that the PrBL method was significantly more effective than PBL. These findings underscore the association between the choice of learning methods and the specific scientific area being taught, emphasizing the superiority of the PrBL approach in this educational context. This discovery suggests that implementing learning strategies that incorporate a project-based approach can be a valuable option to enhance academic performance in scientific disciplines
Social Networks as Technology-Enhanced Learning Environments for Second Language Teaching in Higher Education
Get PDFIn the post-pandemic era, the Digital 2023 Report highlights a rapid expansion in the global user base of social networking sites (SNSs). Despite the lack of formal integration of SNSs in second language (L2) education, which could enhance real-time creation, collaboration, and communication in the target language and culture, L2 learners still actively use these technologies outside of educational settings. This exploratory study utilizes a descriptive survey research design with a purposefully selected sample of 239 undergraduate and graduate students in their first and second years of language studies. These students pursue commonly taught languages, such as Spanish, as well as less commonly taught ones, such as Arabic, Persian, Slavic (Bosnian-Croatian-Serbian, Russian, and Polish), Turkic (Turkish and Uyghur), and Uralic (Estonian, Finnish, and Hungarian), in addition to others, such as Mongolian. The diverse range of languages enables a thorough investigation of the use of SNSs among college-level L2 learners in the United States, including both widely taught and less commonly taught languages. The findings of this study show that the target age group exhibits distinct preferences in their choice of social platforms for personal use compared to those used in L2 classrooms. Furthermore, the outcomes underscore the significant impact of age, gender, and the method of course delivery on the usage patterns of social networking sites
Analysis of Abstractive and Extractive Summarization Methods
Get PDFThis paper explains the existing approaches employed for (automatic) text summarization. The summarizing method is part of the natural language processing (NLP) field and is applied to the source document to produce a compact version that preserves its aggregate meaning and key concepts. On a broader scale, approaches for text-based summarization are categorized into two groups: abstractive and extractive. In abstractive summarization, the main contents of the input text are paraphrased, possibly using vocabulary that is not present in the source document, while in extractive summarization, the output summary is a subset of the input text and is generated by using the sentence ranking technique. In this paper, the main ideas behind the existing methods used for abstractive and extractive summarization are discussed broadly. A comparative study of these methods is also highlighted