Title: PREDICTING MATERNAL OUTCOMES USING TREE-BASED METHODS IN MACHINE LEARNING
Department of Computer Science, Faculty of Science, University of Uyo, Nigeria
Maternal health, with its global significance for maternal mortality rates, is a paramount concern. This study focuses on leveraging tree-based algorithms to aid healthcare providers in informed decision-making for expectant mothers. Analyzing 4,000 antenatal care records in Nigeria's Niger Delta area (2018-2022) identified 15 critical features using Principal Component Analysis (PCA) to predict outcomes like stillbirth, full-term birth, preterm birth, miscarriage, placenta previa, and maternal mortality. Decision Tree (DT) prioritizes Hemoglobin Level (HL), Random Forest (RF) includes HL, Pulse Rate (PR), and Packed Cell Volume Level (PCVL). AdaBoost (ADA) emphasizes HL, Maternal Weight (MW), and Preeclampsia (PREE). Gradient Boosted Trees (GBT) consistently prioritize HL, PREE, and MW, with Extreme Gradient Boosting (XGB) aligning with these features. A bar chart illustrates precision scores, with XGBoost leading at 0.95, GBT at 0.93, Random Forest at 0.92, AdaBoost at 0.91, and DT at 0.90. These findings offer valuable insights for healthcare professionals and researchers aiming to enhance maternal health outcomes. Future research avenues include exploring the synergy of tailored logistic regression models with gradient-boosted algorithms to enhance discrimination and calibration. Additionally, combining gradient-boosted tree algorithms with SHAP (Shapley Additive Explanations) could provide deeper insights into the importance of features and predictive performance improvements. Keywords: Maternal health, Maternal outcomes, Tree-based algorithms, Pregnancy, Maternal mortality.
Title: Cultural Bridges in Digital Education: Humanized Training for Indigenous Teachers
Universidade Federal Fluminense - Brazil
We will explore a theme of great relevance in the contemporary educational context: the challenges in implementing digital activities in indigenous communities. This study that I present focused on the final stages of an Initial and Continuing Education Course in Computing, Technologies and Educational Robotics for Basic Education. Using a qualitative methodology, we conducted semi-structured interviews with indigenous community members who participated in the course. In addition, we carried out a thorough documentary analysis, evaluating records and feedback from those involved in the activities. The results that emerged from the study are revealing. We identified significant challenges such as limited connectivity, which poses barriers to access and use of digital resources. Cultural adaptation also proved to be an obstacle, highlighting the need for materials and methods that respect the cultural particularities of these communities. Furthermore, the participants' prior training was found to be insufficient, suggesting the need for more robust training. One of the most critical points identified was linguistic diversity. The lack of materials adapted to local languages hinders full comprehension and participation by community members. This leads us to reflect on the importance of pedagogical strategies that are not only effective but also sensitive to the cultural and linguistic nuances of these groups. In the final considerations, we highlight the urgency of educational strategies that are culturally appropriate and consider the specific conditions of indigenous communities. We propose practical measures such as additional training for educators, personalisation of teaching materials, and the establishment of closer partnerships with communities.
Title: Harmony in Progress: Navigating Latest Technical Trends and Ethical Horizons in Artificial Intelligence and Machine Learning
Associate Professor in the EE&CS Department at Alabama A&M University, USA
In the ever-evolving realm of Artificial Intelligence (AI) and Machine Learning (ML), rapid technological progress is reshaping the landscape. This keynote speech delves into the latest advancements and trends in AI and ML. It also sheds light on the intricate balance between emerging technologies and ethical considerations in this dynamic field. This talk is divided into two parts. In the first part of the presentation, the speaker will delve into state-of-the-art technical trends, providing a comprehensive discussion on the dynamic evolution of AI and ML across diverse sectors. For instance, in healthcare, these technologies contribute significantly to enhancing tasks such as medical image analysis and predictive analytics. The finance industry stands to benefit from applications like algorithmic trading and fraud detection, while the automotive sector leverages ML for real-time decision-making in autonomous vehicles. Thus, the speaker will elucidate the latest advancements and future trends, positioning AI and ML as dynamic and transformative forces across multiple domains. However, the pursuit of technical excellence must be accompanied by a profound understanding of the ethical considerations inherent in AI and ML applications. As we push the boundaries of technological advancements, ethical dilemmas emerge, necessitating a delicate balance between progress and responsibility. The second part of the speech will address the ethical dimensions of AI, including issues of bias, transparency, and accountability, offering a roadmap for ethical decision-making in the AI-driven era. The speaker is enthusiastic not only about sharing technical knowledge but also believes that attending the conference in person will extend beyond the enrichment of technical insights. It presents an opportunity to foster potential international collaborations and unparalleled networking opportunities, serving as a platform for initiatives like faculty and student exchanges, as well as collaborative research endeavors. This talk holds value for various stakeholders, including faculty, students, researchers, business professionals, government representatives, and more. Together, let's contribute to shaping the future of AI and ML in an era characterized by both progress and responsibility.
Title: Future Of Artificial Intelligence In Agriculture
Department of Computer Science, Mata Gujri Khalsa College Kartarpur
The future of artificial intelligence (AI) in agriculture is poised to revolutionize the industry in numerous ways, offering solutions to challenges such as climate change, resource scarcity, and increasing global food demand. Here are some key aspects of AI's role in the future of agriculture: Precision farming, crop monitoring and management, Predictive analysis, Robotics and automation, sustainable growth, Overall, the future of AI in agriculture holds tremendous potential to transform the industry, making it more efficient, sustainable, and resilient in the face of evolving challenges. However, it's essential to address issues such as data privacy, cybersecurity, and equitable access to technology to ensure that the benefits of AI are realized by all stakeholders in the agricultural ecosystem