T. Porntaveetus

3D-VRTGR: A novel 3D virtual relay tunnel-based geographic routing for flying ad hoc networks

Flying ad hoc networks (FANETs), composed of unmanned aerial vehicles (UAVs), are a key component of next-generation wireless networks that support various public safety and civilian applications in highly dynamic three-dimensional environments. However, high UAV mobility, highly dynamic topology, and limited energy and processing resources make efficient routing a challenging task. Traditional geographic routing protocols, such as GPSR, suffer from local minima, routing holes, unstable links, and high recovery overhead, reducing their effectiveness in FANETs. To address these challenges, this paper proposes a novel three-dimensional virtual relay tunnel-based geographic routing (3D-VRTGR) protocol. Unlike existing virtual tunnel-based routing approaches that use tunnels mainly as forwarding constraints, 3D-VRTGR employs a dynamically evolving virtual tunnel that continuously adapts to local network conditions and guides packet forwarding toward favorable regions. Therefore, the tunnel acts as a route-shaping mechanism rather than a simple filtering region. Specifically, the tunnel is reshaped using a distributed attraction-repulsion mechanism based on node density, residual energy, buffer status, geometric progress toward the destination, and void-history information. This mechanism guides the tunnel toward high-quality network regions while avoiding low-quality or potential void areas. Furthermore, a constant-time geometric pruning method provides efficient membership checking, and a bounded local self-repair mechanism addresses rare void-region scenarios without triggering perimeter recovery mode. Simulation results under varying UAV density, mobility, and traffic load demonstrate that 3D-VRTGR consistently outperforms GPSR, UF-GPSR, and A-Geo. The proposed protocol improves packet delivery ratio and throughput by up to 8.4% and 11.76%, respectively, while reducing latency, local minima occurrences, and link failures by up to 11.20%, 15.97%, and 14.54%, respectively. These results confirm the robustness and efficiency of 3D-VRTGR in highly dynamic FANET environments.

Intelligent Business Document Processing Using AI- and NLP-Based Techniques: A Systematic Literature Review

This systematic literature review examines the application of artificial intelligence (AI) and natural language processing (NLP) techniques in intelligent business document processing. The study systematically analyses 46 peer-reviewed articles published between 2014 and 2025 and indexed in the Scopus database. The reviewed literature was grouped into six core NLP-based analytical tasks: semantic search, question answering, summarisation, text data integration and matching, event extraction, and business process management. The findings show that AI- and NLP-based methods have significantly improved the automation, retrieval, interpretation, and structuring of business documents. Semantic search methods enhance information retrieval by moving beyond keyword matching, while question-answering systems and summarisation techniques support automated knowledge discovery and content reduction. Deep learning and transformer-based models have also improved entity matching, event extraction, and predictive business process monitoring. However, the review identifies several persistent limitations, including the continued dominance of extractive approaches, limited adoption of abstractive summarisation, insufficient integration of knowledge graphs, fragmented system development, limited enterprise-scale validation, and a lack of reusable code and shared resources. The findings further indicate that large language models (LLMs), particularly when combined with prompt engineering, retrieval-augmented generation, knowledge graphs, and agent-based architectures, offer promising opportunities to address these gaps. Overall, this review highlights both the progress and remaining challenges in developing scalable, explainable, and domain-adaptable AI-driven systems for intelligent business document processing.

ASGRR: Adaptive Swarm-Guided Graph Policy Routing for energy-efficient WSN-IoT networks

TLQ-Geo: a two-level q-learning-based geographic routing protocol for flying ad hoc networks

A two-level Q-learning-based geographic routing protocol called TLQ-Geo for FANETs, which significantly reduces convergence time and computational overhead and integrates hierarchical decision-making with adaptive reinforcement learning.