Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
The Impact of Using DPSK Modulation on the Performance of Transdermal Optical Wireless Communications under Pointing Errors
Get PDFThe current paper explores the impact of misalignment between transceivers (referred to as pointing error (PE)) on the performance of transdermal optical wireless (TOW) technology, as indicated by average signal-to-noise ratio (SNR), outage probability (OP), outage rate (OR), and average ergodic capacity (AEC). This study was inspired by the effectiveness of differential phase shift keying (DPSK) in enhancing the reliability of the link in free-space optical communications (FSO). Furthermore, this enhancement was studied and analyzed in consideration of the impact of pointing errors. In particular, this paper presents a mathematical analysis that considers certain characteristics of the channel, limitations within the body, the pointing errors (PEs) between the transceivers, and other specific aspects of the optical unit. The results demonstrate the significant impact of PEs on the reliability of the TOW link and highlight the improvement provided by the DPSK technique. i.e., 3 dB better performance compared to the on-off keying (OOK) modulation technique. Finally, this research demonstrates the practical application of wireless optical technology in the medical field within the wavelength range of 800–1300 nm, with optimal performance observed around 1100 nm
Web Attack Intrusion Detection System Using Machine Learning Techniques
Get PDFWeb attacks often target web applications because they can be accessed over a network and often have vulnerabilities. The success of an intrusion detection system (IDS) in detecting web attacks depends on an effective traffic classification system. Several previous studies have utilized machine learning classification methods to create an efficient IDS with various datasets for different types of attacks. This paper utilizes the Canadian Institute for Cyber Security’s (CIC-IDS2017) IDS dataset to assess web attacks. Importantly, the dataset contains 80 attributes of recent assaults, as reported in the 2016 McAfee report. Three machine learning algorithms have been evaluated in this research, namely random forests (RF), k-nearest neighbor (KNN), and naive bayes (NB). The primary goal of this research is to propose an effective machine learning algorithm for the IDS web attacks model. The evaluation compares the performance of three algorithms (RF, KNN, and NB) based on their accuracy and precision in detecting anomalous traffic. The results indicate that the RF outperformed the NB and KNN in terms of average accuracy achieved during the training phase. During the testing phase, the KNN algorithm outperformed others, achieving an average accuracy of 99.4916%. However, RF and KNN achieved 100% average precision and recall rates compared to other algorithms. Finally, the RF and KNN algorithms have been identified as the most effective for detecting IDS web attacks
Therapy and Emotional Support through a Chatbot
Get PDFIn the context of advancing technological development, chatbots have emerged as an innovative tool in the field of mental health, offering new possibilities to provide therapy and emotional support in an accessible and convenient manner. The aim of this study was to develop and evaluate a chatbot implemented in a web application designed to provide emotional support to an adult population, specifically targeting young people and adults over the age of 18. The research focused on user satisfaction with the chatbot experience. Using a qualitative approach and non-random convenience sampling, we collected feedback on the chatbot’s performance from 15 users through an online questionnaire. The results showed a positive assessment, with an average satisfaction score of 4.09 on a scale of 1 to 5. The participants expressed their approval of the emotional support provided by the chatbot, emphasizing the sense of understanding and trust generated by the therapeutic interventions and emotional support. In conclusion, this study successfully assessed user satisfaction with the emotional support chatbot, emphasizing its significance in the realm of digital mental health. The scope of this study was solely focused on user satisfaction. For future research, it is recommended to expand the scope to investigate the correlation between user satisfaction and therapeutic outcomes. Additionally, there is a need to tailor these systems to meet the specific emotional requirements of diverse user groups and enhance the efficacy of mental health patient care
Comprehensive Cardiac Ischemia Classification Using Hybrid CNN-Based Models
Get PDFThis study addresses the critical issue of classifying cardiac ischemia, a disease with significant global health implications that contributes to the global mortality rate. In our study, we tackle the classification of ischemia using six diverse electrocardiogram (ECG) datasets and a convolutional neural network (CNN) as the primary methodology. We combined six separate datasets to gain a more comprehensive understanding of cardiac electrical activity, utilizing 12 leads to obtain a broader perspective. A discrete wavelet transform (DWT) preprocessing was used to eliminate irrelevant information from the signals, aiming to improve classification results. Focusing on accuracy and minimizing false negatives (FN) in ischemia detection, we enhance our study by incorporating various machine learning models into our base model. These models include multilayer perceptron (MLP), support vector machines (SVM), random forest (RF), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM), allowing us to leverage the strengths of each algorithm. The CNN-BiLSTM model achieved the highest accuracy of 99.23% and demonstrated good sensitivity of 98.53%, effectively reducing false negative cases in the overall tests. The CNN-BiLSTM model demonstrated the ability to effectively identify abnormalities, misclassifying only 25 out of 1,673 ischemic cases in the test set as normal. This is due to the BiLSTM’s efficiency in capturing long-range dependencies and sequential patterns, making it suitable for tasks involving time-series data such as ECG signals. In addition, CNNs are well-suited for hierarchical feature learning and complex pattern recognition in ECG data
Improvements of EEG Signal Quality: A Hybrid Method of Blind Source Separation and Variational Mode Destruction to Reduce Artifacts
Get PDFThe electroencephalogram (EEG) is a crucial tool for studying brain activity; yet it frequently encounters artifacts that distort meaningful neural signals. This paper addresses the challenge of artifact removal through a unique hybrid method, combining Variational Mode Decomposition (VMD) techniques with Blind Source Separation (BSS) algorithms. VMD, recognized for its adaptability to non-linear and non-stationary EEG data, as well as its ability to alleviate mode mixing and the “endpoint effect,” which serves as an effective preprocessing step. The paper evaluates the performance of two integrated BSS algorithms, AMICA and AMUSE, across various criteria. Comparisons across metrics such as Euclidean distance, Spearman correlation coefficient, and Root Mean Square Error reveal similar performance between AMICA and AMUSE. However, a distinct divergence is evident in the Signal to Artifact Ratio (SAR). When employed with VMD, AMICA demonstrates superiority in effectively discerning and segregating brain signals from artifacts, which gives a mean value of 1.0924. This study introduces a potent hybrid VMDBSS approach for enhancing EEG signal quality. The findings emphasize the notable impact of AMICA, particularly in achieving optimal results in artifact removal, as indicated by its superior performance in SAR. The abstract concludes by underlining the significance of these results, emphasizing AMICA’s pivotal role in achieving the highest measurable evaluation value, making it a compelling choice for researchers and practitioners in EEG signal processing
Lean Construction Strategies Supported by Artificial Intelligence Techniques for Construction Project Management—A Review
Get PDFThis paper analyzes the application of artificial intelligence (AI) techniques in lean construction (LC) and their potential to enhance project management (PM) for improved cost and schedule efficiency. The PRISMA methodology is used to select relevant articles in four steps. Furthermore, a bibliometric analysis of keywords and their occurrences is conducted. The study emphasizes the different methods of utilizing lean tools and AI techniques to attain optimal results in the construction industry. By combining a variety of tools and techniques, it is possible to create an environment that fosters improved project outcomes while minimizing risks and inefficiencies. According to the articles reviewed, the LC methodology and its tools are becoming increasingly relevant in general practice (GP). Machine learning (ML) techniques, particularly artificial neural networks (ANN), have been extensively researched as a tool to enhance construction projects by minimizing delays, fostering collaboration, cutting costs, saving time, and boosting productivity. Combining LC with ML can enhance profitability and align with lean principles, leading to successful outcomes for construction projects
Revolutionizing Brain Tumor Analysis: A Fusion of ChatGPT and Multi-Modal CNN for Unprecedented Precision
Get PDFIn this study, we introduce an innovative approach to significantly enhance the precision and interpretability of brain tumor detection and segmentation. Our method ingeniously integrates the cutting-edge capabilities of the ChatGPT chatbot interface with a state-of-the-art multi-modal convolutional neural network (CNN). Tested rigorously on the BraTS dataset, our method showcases unprecedented performance, outperforming existing techniques in terms of both accuracy and efficiency, with an impressive Dice score of 0.89 for tumor segmentation. By seamlessly integrating ChatGPT, our model unveils deep-seated insights into the intricate decision-making processes, providing researchers and physicians with invaluable understanding and confidence in the results. This groundbreaking fusion holds immense promise, poised to revolutionize the landscape of medical imaging, with far-reaching implications for clinical practice and research. Our study exemplifies the transformative potential achieved through the synergistic combination of multi-modal CNNs and natural language processing, paving the way for remarkable advancements in brain tumor detection and segmentation
An Application of Computer Vision Techniques to Study the Relationship between Mental Stress and Pupil Diameter among Student Population
No full textStress is a state of mental tension, which helps us to cope with challenges in our life. It makes us progressive when it is positive, but excessive negative stress that perseveres for a long time leads to a state of depressiveness. Longer stressed stage of a human being changes the size, functionality and frequency of response of many internal and external body parameters. By applying computer vision techniques, these changes of body parameters can be tracked to get useful information about the mental stress for a stress affected person. Many studies show the pupil diameter varies significantly with the effect of stress. Our work is based on the study of variation of pupil diameters of stress affected and not affected university students. With the application of different supervised machine learning algorithms, we have observed that the pupil dilates more in case of stress affected students than non-stressed students. We have also found that the pupils of the students dilates more when they were in positive emotional states than their negative emotional states. This work will be helpful for researchers who are working in the field of emotion detection and recognition and affective disorder analysis
Enhancing Psychological Well-being in Higher Education Post-Covid-19 Pandemic. The Role of AI-Based Support Systems—Bibliometric Reviews
Get PDFPsychological well-being is a cornerstone of student success in higher education. However, many students struggle with mental health challenges like stress, anxiety, and depression during and even after the Covid-19 pandemic. These challenges, often stemming from academic, personal, social, or career concerns, negatively impact student learning and development. This underscores the need for robust support systems within higher education (HE). Artificial intelligence (AI) emerges as a promising field in educational technology, offering students readily available guidance on their path to well-being. This research, guided by the PRISMA Statement 2015, provides an overview of AI applications in higher education through a systematic review. From an initial pool of 270 publications identified between year 2021 and 2023, finally, 24 articles met our inclusion criteria and were analyzed for the final synthesis. This paper revealed three key areas where AI-based systems can support student well-being: i) AI’s Advancement and Potential: Exploring the evolving capabilities and promise of AI in this context. ii) Building Effective AI Systems: Identifying crucial components for successful AI-based well-being interventions. iii) Barriers to Implementing AI in Higher Education: Addressing ethical considerations and challenges unique to academic settings. The conclusions and the road ahead from this research is the critical need for ethical, well-designed AI-based systems to overcome existing barriers and deliver exceptional student well-being support services. By prioritizing student mental health and providing them with the necessary tools and resources, we can empower them to achieve their full potential and thrive in their academic endeavors
Harnessing Machine Learning for Quantifying Vesicoureteral Reflux: A Promising Approach for Objective Assessment
Get PDFIn this study, we evaluated the performance of various machine-learning models on multiple datasets labeled GR1, GR2, GR3, GR4, and GR5. We assessed the models using a range of evaluation metrics, including AUC, CA, F1, precision, recall, MCC, specificity, and log loss. The models examined were logistic regression, decision tree, kNN, random forest, gradient boosting, neural network, AdaBoost, and stochastic gradient descent. The results indicate that all models consistently demonstrated outstanding performance across all datasets, with most achieving perfect scores in all metrics. The models exhibited high accuracy and effectiveness in accurately classifying instances. Although random forests displayed slightly lower scores in some metrics, theyi still maintained an overall high level of accuracy. The findings highlight the models’ ability to effectively learn the underlying patterns within the data and make accurate predictions. The low log loss values further confirmed the models’ precise estimation of probabilities. Consequently, these models possess strong potential for practical applications in various domains, offering reliable and robust classification capabilities