Vol. 1 No. 2 (2024)

We are delighted to present to you the second issue of the IJETAA. This issue encapsulates a diverse range of research articles that delve into cutting-edge advancements in various domains of analytics and artificial intelligence.

In this issue, we feature five insightful articles that contribute significantly to the advancement of analytical methodologies and applications:

1. Spatial Distribution Analysis of Urban Retail Industry Using POI Big Data: This article explores the spatial distribution patterns of urban retail industries by leveraging Point of Interest (POI) big data. The research sheds light on the dynamics of retail establishments in urban environments, offering valuable insights for urban planners and businesses alike.

2. YOLOLayout: Multi-Scale Cross Fusion Former for Document Layout Analysis: Presenting YOLOLayout, a novel approach for document layout analysis that utilizes a multi-scale cross fusion former. This research addresses the challenge of accurately extracting structural information from diverse document layouts, thereby facilitating automated document processing systems.

3. Joint Information Extraction Model Based on Feature Sharing: Introducing a joint information extraction model that leverages feature sharing to enhance performance. This model demonstrates the efficacy of collaborative learning in information extraction tasks, paving the way for improved text mining and knowledge discovery.

4. Interpretable DeepFake Detection Based on Frequency Spatial Transformer: Delving into the realm of deepfake detection, this article proposes an interpretable approach based on a frequency spatial transformer. By analyzing frequency-based features, the proposed method enhances the interpretability of deepfake detection models, thus bolstering trust and reliability in content authentication systems.

5. Prompt Optimization Methods for Large Language Models with Long Text Input: Addressing the challenges associated with large language models and long text inputs, this research presents prompt optimization methods to improve model performance. By optimizing prompts for specific tasks and inputs, this approach enhances the effectiveness and efficiency of large language models in diverse applications.

Each of these articles contributes to the growing body of knowledge in advanced analytics and artificial intelligence, offering innovative solutions to real-world challenges. We extend our gratitude to the authors for their valuable contributions and to our reviewers for their meticulous evaluation.

We hope that the articles featured in this issue will inspire further research and spark meaningful discussions in the field of advanced analytics. We invite you to delve into the depth of knowledge presented in these articles and explore the possibilities they unfold.