Global Journal on Innovation, Opportunities and Challenges in Applied Artificial Intelligence and Machine Learning [ISSN: 2581-5156 (online)]

Interpretable Deep Learning Models for Medical Diagnosis: A Case Study on Cardiac Arrhythmia Classification

Rajasrikar Punugoti, Aradhya Pokhriyal, Ronak Duggar

An in-depth study on the creation of interpretable deep learning models for precise classification of cardiac arrhythmias is presented here. In this study, cutting-edge deep learning techniques are used to the well-known MIT-BIH Arrhythmia Database. These techniques include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their hybrid architecture. The electrocardiogram (ECG) recordings in this dataset have been annotated, making it possible for models to learn complicated patterns and categorise a wide variety of cardiac arrhythmias. To aid in the interpretation of ECG signals, attention mechanisms are integrated. The suggested hybrid CNN-RNN model performs exceptionally well, with an accuracy of 94.56%. In addition to enhancing the model's interpretability, visualising the attention weights reveals useful insights into the decision-making procedure. The use of interpretable deep learning models and the illumination of the mechanisms driving accurate predictions are two major contributions of this thesis to the field of cardiac arrhythmia classification. This study demonstrates the promise of such models to improve healthcare by assisting physicians in making accurate diagnoses and crafting effective treatment plans.

AI and Story of Snow White: Concepts for AI Governance

Rujittika Mungmunpuntipantip, Viroj Wiwanitkit

This paper explores the intersection of artificial intelligence (AI) and the classic fairy tale of Snow White, with a particular focus on the concepts of AI governance. By analyzing the story of Snow White through the lens of AI, this study aims to draw insights and lessons that can inform the development of effective governance frameworks for AI technologies. The paper begins by examining key themes in Snow White, such as power dynamics, ethical decision-making, and the consequences of technological advancements. It then applies these themes to the context of AI governance, highlighting the importance of transparency, accountability, and fairness in regulating AI systems. Furthermore, the study delves into various AI governance models and frameworks proposed by scholars and policymakers. It evaluates their strengths and weaknesses, drawing parallels with the characters and events in Snow White. Through this analysis, the paper seeks to identify best practices and principles that can guide the responsible development and deployment of AI technologies. The findings of this research underscore the significance of establishing robust AI governance mechanisms that address the potential risks and ethical challenges associated with AI. By leveraging insights from the story of Snow White, policymakers and stakeholders can gain a deeper understanding of the complexities involved in governing AI and develop strategies to ensure its responsible and beneficial use. Ultimately, this study contributes to the ongoing discourse on AI governance by providing conceptual frameworks and thought-provoking insights derived from the timeless tale of Snow White. It serves as a foundation for further research and discussions aimed at fostering a harmonious relationship between AI technologies and society.

Evolution of AI Image Generation: The Role of Stable Diffusion, Leonardo AI, and Image Prompts

Rujittika Mungmunpuntipantip, Viroj Wiwanitkit

This article explores the advancements in AI image generation and the various techniques utilized in the process. We delve into the significance of Stable Diffusion and Leonardo AI in generating lifelike images. Furthermore, we shed light on the usage of image prompts as basic instructions to generate desired visuals. We also examine the importance of selecting appropriate models and employing the image to image technique. Additionally, we discuss the integration of Dall-E with Bing Image Creator and the potential implications of copyright for generated AI images.

Generation of Fake content using Machine Learning RNN Technique

Rahul Jakhar, Vanshika Choudhary, Nishchay ., Gautam ., Kartik .

A wider audience is being exposed to fake news than ever before. The proliferation of social networking sites and direct messaging systems is the primary culprit. The problem at hand is developing an algorithm using deep learning that can discern between real and fake news articles. In order to accomplish this, this research first examines a few datasets that allow for the coexistence of fake and true news. Then we review some of the existing research on deep learning algortihms and algorithms which are applied in fake news classification. This paper focuses on implementing an RNN algorithm with the minimum data preprocessing possible and achieving maximum accuracy.

A Short Review on AI based Solar Power System

Koushik Sarkar, Debojyoti Ghosh

Modern, advanced society cannot function without a steady and reliable source of electricity. Much of the work being done on control framework research has moved away from the formal scientific demonstration system, which emerged from the fields of task analysis, control hypothesis, and numerical analysis, and toward the less rigorous and labour-intensive approaches of artificial intelligence (AI). These techniques are used to address a range of control framework, scheduling, forecasting, control, and arrangement. These tactics are able to handle challenging tasks that applications in today's vast power frameworks, which have significantly more interconnections added to satisfy the expanding load requirement, look for. This paper's actual objective is to demonstrate how computerized reasoning processes could play a crucial role in forecasting and illustrating the operation of solar-powered energy frameworks. Through a way for displaying different problems in the many orders of sun-based vitality designing, the paper outlines an understanding of how expert systems and neural systems function.

Next-Gen Data Engineering: The AI Revolution

Shubhodip Sasmal

In the era of rapid technological advancement, data engineering stands at the forefront of innovation, with artificial intelligence (AI) emerging as a transformative force. This research paper explores the paradigm shift in data engineering ushered in by the integration of AI technologies. The study delves into the multifaceted impact of AI on traditional data engineering methodologies, addressing the evolution of data processing, storage, and analysis in the next generation.

The paper begins by elucidating the current landscape of data engineering, emphasizing the challenges and limitations faced by conventional approaches. It then navigates through the key pillars of AI that are revolutionizing the field, namely machine learning, natural language processing, and computer vision. These technologies are examined in the context of their applications in data engineering, shedding light on their ability to enhance automation, scalability, and adaptability.

A significant portion of the research focuses on the synergies between AI and big data, illustrating how machine learning algorithms can harness vast datasets to derive meaningful insights. The discussion extends to the role of AI in optimizing data pipelines, reducing latency, and improving the overall efficiency of data processing workflows. Furthermore, the paper explores the implications of AI-driven data governance and security measures, emphasizing the importance of responsible AI deployment to mitigate potential risks.

The study also considers the transformative impact of AI on data integration and interoperability, exploring how intelligent systems facilitate seamless communication between disparate data sources. The emergence of AI-powered data lakes and warehouses is discussed, highlighting their ability to consolidate diverse datasets for enhanced analytics and decision-making.

In conclusion, this research paper posits that the integration of AI into data engineering practices represents a watershed moment, propelling the field into a new era of possibilities. As organizations strive to leverage data as a strategic asset, understanding the implications and opportunities presented by the AI revolution in data engineering is paramount. The insights gleaned from this study contribute to a deeper understanding of the evolving landscape, offering valuable perspectives for researchers, practitioners, and industry stakeholders navigating the complex intersection of AI and data engineering.