Enhancing Fusion Teaching based Research from the Student Perspective

Anita; Aditi; F. Abdul Munaim Al; Rama Devi

doi:https://doi.org/10.54216/FPA.120209

Journal of Cognitive Human-Computer Interaction | 2023

ActivBench: Leveraging Human Activity Inference from Smartphone Sensors for Human Computer Interactions

Human activity recognition (HAR) from smartphone sensors has gained significant attention due to its potential to enhance user experience (UX) and human computer interaction (HCI) in various domains, HAR can enable personalized, context-aware, and adaptive interfaces that improve accessibility and promote health and wellness in various applications such as healthcare, smart homes, fitness tracking, and context-aware systems. However, evaluating the performance of different machine learning (ML) algorithms on activity recognition tasks remains challenging, primarily due to the lack of standardized benchmark datasets and evaluation protocols. In this paper, we presented ActivBench, an end-to-end computational intelligence benchmark designed to facilitate the evaluation and comparison of ML algorithms for human activity inference from smartphone sensors. We addressed the challenges in benchmarking activity recognition systems by providing a unified evaluation protocol and standardized performance metrics. Through extensive experiments using various state-of-the-art algorithms, we demonstrated the effectiveness of ActivBench in assessing the strengths and limitations of different approaches. The benchmark results provide valuable insights into the strengths and limitations of different algorithms, facilitating the development of robust and accurate activity recognition systems that can enhance human computer interaction in various applications. ActivBench is serving as a valuable resource for researchers and practitioners in human activity recognition and human-computer interaction, enabling fair comparisons and fostering advancements in the field. It also serves as a catalyst for advancements in the field, enabling the exploration of novel algorithms, feature engineering techniques, and sensor modalities.

groups

Basma K. Eldrandaly mail

link https://doi.org/10.54216/JCHCI.050205

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Prediction Of Diseases in Smart Healthcare System Using Machine Learning

Smart healthcare systems rely heavily on disease prediction because it paves the way for early detection and prompt action, both of which enhance patient outcomes. In this research, we present a machine learning (ML) method for identifying data patterns that might be used to foretell the occurrence of cardiac disease. Our approach entails cleaning the data used for predicting cardiac issues and then using a Support Vector Machine (SVM). Age, sex, chest pain type, blood pressure, cholesterol, and exercise-induced angina are only few of the attributes included in the dataset. Insights into the distributional analysis of categorical and numeric variables, as well as potential connections and trends, are gained through exploratory data analysis (EDA). Cross-validation results show that the SVM model performs exceptionally well, with higher accuracy and AUC than competing models. By utilizing ML methods, our research aids in the development of intelligent healthcare systems. These results add to our understanding of how to forecast diseases and show how machine learning may transform healthcare systems to improve patient outcomes.

groups

Nadjem Bailek mail -

Mohamed Saber mail

link https://doi.org/10.54216/JAIM.030205

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Tapping into Knowledge: Ontological Data Mining Approach for Detecting Cardiovascular Disease Risk Causes Among Diabetes Patients

The prevalence of cardiovascular disease (CVD) is a serious public health issue, and it is of particular concern for people with diabetes because of the increased risk of cardiovascular problems that these people experience. In this study, we suggest a novel method of Ontological Data Mining (ODM) for identifying the origins of CVD risk in diabetic patients. We want to improve the readability and precision of prediction models by incorporating domain knowledge and semantic linkages into the data mining process. In this work, we examine a large dataset consisting of 70,000 patient records with 11 attributes, all of which are derived through a thorough clinical history and physical examination. As part of our methodology, we use decision trees, support vector machines (SVMs), and gradient boosting (GB). The distribution patterns of critical variables with respect to CVD outcomes can be better understood through the use of visual representations such as box plots, distributional plots, and pie charts. Finding significant connections and causal relationships between risk factors and CVD outcomes is made possible by the suggested ODM method. Our research has promising implications for bettering the treatment of patients with diabetes, facilitating targeted interventions, and enhancing risk assessment and preventative methods for cardiovascular disease.

groups

Hussein Alkattan mail -

S. K. Towfek mail -

M. Y. Shams mail

link https://doi.org/10.54216/JAIM.040101

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Bridging the Gap: An Explainable Methodology for Customer Churn Prediction in Supply Chain Management

Customer churn prediction is a critical task for businesses aiming to retain their valuable customers. Nevertheless, the lack of transparency and interpretability in machine learning models hinders their implementation in real-world applications. In this paper, we introduce a novel methodology for customer churn prediction in supply chain management that addresses the need for explainability. Our approach take advantage of XGBoost as the underlying predictive model. We recognize the importance of not only accurately predicting churn but also providing actionable insights into the key factors driving customer attrition. To achieve this, we employ Local Interpretable Model-agnostic Explanations (LIME), a state-of-the-art technique for generating intuitive and understandable explanations. By utilizing LIME to the predictions made by XGBoost, we enable decision-makers to gain intuition into the decision process of the model and the reasons behind churn predictions. Through a comprehensive case study on customer churn data, we demonstrate the success of our explainable ML approach. Our methodology not only achieves high prediction accuracy but also offers interpretable explanations that highlight the underlying drivers of customer churn. These insights supply valuable management for decision-making processes within supply chain management.

groups

Adel Oubelaid mail -

Abdelhameed Ibrahim mail -

Ahmed M. Elshewey mail

link https://doi.org/10.54216/JAIM.040102

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Interpreting the Incomprehensible: Benchmarking Visual Explanation Methods for Deep Convolutional Networks

Deep Convolutional Networks (CNNs) have revolutionized various fields, including computer vision, but their decision-making process remains largely opaque. To address this interpretability challenge, numerous visual explanation methods have been proposed. However, a comprehensive evaluation and benchmarking of these methods are essential to understand their strengths, limitations, and comparative performance. In this paper, we present a systematic study that benchmarks and compares various visual explanation techniques for deep CNNs. We propose a standardized evaluation framework consisting of benchmark explain ability methods. Through extensive experiments, we analyze the effectiveness, and interpretability of popular visual explanation methods, including gradient-based methods, activation maximization, and attention mechanisms. Our results reveal nuanced differences between the methods, highlighting their trade-offs and potential applications. We conduce a comprehensive evaluation of visual explanation methods on different deep CNNs, the results demonstrate the ability to achieve informed selection and adoption of appropriate techniques for interpretability in real-world applications.

groups

Wei Hong Lim mail -

Marwa M. Eid mail

link https://doi.org/10.54216/JAIM.040103

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Visualizing the Unseen: Exploring GRAD-CAM for Interpreting Convolutional Image Classifiers

Mathematical programming can express competency concepts in a well-defined mathematical model for a particular. Convolutional Neural Networks (CNNs) and other deep learning models have shown exceptional performance in image categorization tasks. However, questions about their interpretability and reliability are raised by their intrinsic complexity and black-box nature. In this study, we explore the visualization method of Gradient-Weighted Class Activation Mapping (GRAD-CAM) and its application to understanding how CNNs make decisions. We start by explaining why tools like GRAD-CAM are necessary for deep learning and why interpretability is so important. In this article, we provide a high-level introduction to CNN architecture, focusing on the significance of convolutional layers, pooling layers, and fully connected layers in the context of image categorization. Using the Xception model as an illustration, we describe how to generate GRAD-CAM heatmaps to highlight key areas in a picture. We highlight the benefits of GRAD-CAM in terms of localization accuracy and interpretability by comparing it to other visualization techniques like Class Activation Mapping (CAM) and Guided Backpropagation. We also investigate GRAD-CAM's potential uses in other areas of image classification, such as medical imaging, object recognition, and fine-grained classification. We also highlight the disadvantages of GRAD-CAM, such as its vulnerability to adversarial examples and occlusions, along with its advantages. We conclude by highlighting extensions and changes planned to address these shortcomings and strengthen the credibility of GRAD-CAM justifications. As a result of the work presented in this research, we can now analyze and improve Convolutional Image Classifiers with greater accuracy and transparency.

groups

Sunil Kumar mail -

Abdelaziz A. Abdelhamid mail -

Zahraa Tarek mail

link https://doi.org/10.54216/JAIM.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Mining Sematic Association Rules from RDF Data

Many fields rely heavily on the accurate and consistent portrayal of structured data. In order to effectively express and link information on the Semantic Web, RDF (Resource Description Framework) data is essential. Here, we present a process for extracting semantic association rules from RDF data. For our method, we employ the Apriori algorithm to mine the RDF triples for hidden connections between ideas and relationships. Using metrics such as confidence, support, and lift, we examine how well our model performs. We also give visual representations, like as scatter plots and clustered matrices, to make the correlations easier to understand and analyse. The findings validate our model's potential to unearth significant relationships, which in turn reveal important details about the RDF data's underlying semantics. Our findings are discussed, and suggestions for further study are provided.

groups

Nima Khodadadi mail -

M. G. El-Mahgoub mail -

Rokaia M. Zaki mail

link https://doi.org/10.54216/JAIM.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2023

Analysis of Fusion of Machine Learning Tools in Education

In this modern world, artificial intelligence has revolutionized human life in multiple ways. Like other fields, education industry is also transforming with the influence of AI with its smart learning platform and automation of tasks. The introduction of fusion of machine learning tools (FMLT) in the field of education helps to predict learning outcomes and identify challenges in learning. The objective of this paper is to study the fusion of application of machine learning tools in education. This paper highlights the role of data driven FMLT in teaching and learning and also analyzes students and teachers’ experiences as well as challenges faced during the implementation of FMLT system. This article discusses various machine learning tools that can be fused into academics. The experiment is conducted on students at graduate level and the results reveal an increase of 88% in terms of learning efficiency for the proposed FMLT system compared to traditional methods, which reflects high positive impact of the contributions of FMLT in academics. Results of the findings also reveal that FMLT applications facilitate thinking, creativity, class engagement and quality teaching inside and outside classrooms. The feedback findings express mixed attitudes concerning the use of machine learning tools in classrooms.

groups

Anita Venugopal mail -

Mukesh Madanan mail -

Thangadurai kadarkarai mail

link https://doi.org/10.54216/FPA.120207

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2023

Potential Pitfalls of Data Fusion Digitalization in Microfinance Context

The current era of socio-economic development is featured by rapidly increasing fusion of technology and rapid data fusion digitalization of human activities. While most of these advancements are promising to bring various positive aspects, such as reductions in cost and time, there are potential pitfalls that should be considered. In this paper, we aim to measure potential challenges that data fusion data fusion digitalization could bring in the microfinance context. First, we provide the set of stylized facts and trends in data fusion digitalization using three measures: mobile cell users, internet provision, and mobile-money-service provision. The trends in data fusion digitalization are provided across groups of countries by different income levels. Secondly, using pair-wise correlations we analyze how the set of five microfinance financial and five social indicators are correlated with the digital ranking of countries. Our results demonstrate that while there are increasing patterns in data fusion digitalization in most of the developing countries, negative correlations are observed. We explain the negative implications of data fusion digitalization due to increasing moral hazard and asymmetric information. Our findings call for further research on the long-term implications of digitalization in other areas of social sciences so that to better cope with potential challenges.  

groups

Maxbuba Ismailova mail -

Nargiza Alimukhamedova mail

link https://doi.org/10.54216/FPA.120208

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2023

Enhancing Fusion Teaching based Research from the Student Perspective

There has been a growing need for fusion based research studies on the relations between university teaching and research. The higher educational universities of the current generation believe in and focus on the teaching-research nexus in academics. To improve teaching methodology there is more emphasis given to the fusion teaching by enabling the information fusing concept through pedagogy. Many discussions have been carried out to evaluate the contribution of teaching–research nexus from the student's point of view. The current study highlights teaching through research where the learners are taught with a special focus on research activities at the same time. The objective of this work is to promote fusion of research related activities into the teaching and learning process to achieve positive impact on enhancing students’ interest towards learning. In view of this and to support this, various opportunities were provided for students and teachers to conduct research and a strategic approach was implemented to achieve this objective. We explore a) student involvement in different scholarly activities b) analyse research skill acquisition of the experimental group c) collect feedback to find students satisfaction level on FTBR approach.The findings demonstrate (mean score 3.09) the positive contribution of the fusion research-teaching towards achieving academic excellence.The strategies discussed in the methodology and results of the study may be used to broaden the fusion teaching-research at the graduate and undergraduate levels.

groups

Anita Venugopal mail -

Aditi Sharma mail -

F. Abdul Munaim Al Rawas mail -

Rama Devi S. mail

link https://doi.org/10.54216/FPA.120209

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new