Jui-Tang Wang

The emergence of 6 G networks introduces unprecedented demands for deterministic, ultra-reliable, and low-latency communication (URLLC) across diverse service domains such as autonomous mobility, industrial automation, and immersive applications. Achieving these requirements within the disaggregated and multi-vendor Open Radio Access Network (O-RAN) architecture remains a major challenge, particularly due to the dynamic nature of radio conditions and transport-layer variability. This paper proposes a proactive, AI-native latency control framework for O-RAN-based 5G/6G networks, targeting deterministic ultrareliable low-latency communication (URLLC) under heterogeneous traffic conditions. Unlike prior reactive or slice-static approaches, the proposed architecture embeds predictive latency modeling and semantic policy reasoning directly within the near-real-time RAN Intelligent Controller (RIC), enabling anticipation and mitigation of end-to-end delay violations before they occur. Through an experimental testbed based on the O-RAN Software Community (OSC) stack, srsRAN, and an open 5G core, the proposed approach demonstrates a consistent reduction in tail latency and hybrid automatic repeat request (HARQ) deadline violations compared to conventional O-RAN scheduling. The results confirm that embedding network intelligence and semantic control within the O-RAN control loop can achieve reliable sub-5 ms communication performance, offering a practical pathway toward AI-native, latency-deterministic 6 G systems.

The growing demand for ultra-reliable and low-latency communication (URLLC) in private 5G environments, such as smart campuses and industrial networks, has highlighted the limitations of conventional Wireline access gateway function (W-AGF) architectures that depend heavily on centralized 5G core (5GC) processing. This paper introduces a novel Centralized Unit (CU)-based Zone-Access Gateway Function (Z-AGF) architecture designed to enhance handover performance and enable Local Breakout (LBO) within Non-Public Networks (NPNs) for non-5G capable (N5GC) devices. The proposed design integrates W-AGF functionalities with the Open Radio Access Network (O-RAN) framework, leveraging the F1 Application Protocol (F1AP) as the primary interface between Z-AGF and CU. By performing local breakout (LBO) locally at the Z-AGF, latency-sensitive traffic is processed closer to the edge, reducing the backhaul load and improving end-to-end latency, throughput, and jitter performance. The experimental results demonstrate that Z-AGF achieves up to 45.6% latency reduction, 69% packet loss improvement, 85.6% reduction of round-trip time (RTT) for local communications under LBO, effective local offloading with quantified throughput compared to conventional W-AGF implementations. This study provides a scalable and interoperable approach for integrating wireline and wireless domains, supporting low-latency, highly reliable services within the O-RAN ecosystem and accelerating the adoption of localized next-generation 5G services.

Introduction: The main challenge in using building information modelling (BIM) is the centralised collaborative framework in the various design software (e.g., AutoCAD, Revit, RHINO, and ArchiCAD) used by professionals across various disciplines, which causes difficulties during data exchange. Methods: The existing framework may increase the project lead time, require more effort, and result in design conflicts and misunderstandings. Thus, this paper has proposed a dynamic information storage with blockchain system (DISBS) using a physical curtain wall project for practical implementation. In addition, this paper has further discussed the linkages and verified and analysed the effectiveness of the proposed methodology. Results: Through the DISBS proposed in this research, the characteristics and achievable functions of blockchain technology are presented. Various applications for the field of construction engineering are highly developable within this research. Conclusion: The DISBS can improve not only the management quality of construction projects, but also promote mutual trust in the construction industry and optimize architecture, engineering, and construction (AECO) productivity.

A 5G network can provide more comprehensive bandwidth connectivity for the industry 4.0 environment, which requires faster and tremendous data transmission. This study demonstrates the 5G network performance evaluation with MEC, without MEC, WiFi 6, and Ethernet networks. Usually, a 5G network engages with Multi-access Edge Computing, providing the computing functions dedicated to the users on edge nodes. The MEC network architecture presents significant facilities, a network schematic, and data transmission routers. The field test performs high-definition streaming video and heavy-traffic load testing to evaluate the performance based on different protocols by comparing throughput, latency, jitter, and packet loss rate. MEC network performance, streaming video performance, and load test evaluation results reveal that the 5G network working with MEC achieved better performance than when it was working without MEC. The MEC can improve data transmission efficiency by dedicated configuration but is only accessible with authentication from mobile network operators (MNOs). Therefore, MNOs should offer industrial private network users partial authentication for accessing MEC functionality to improve network feasibility and efficiency. In conclusion, this work illustrates the 5G network implementation and performance measurement for constructing a smart factory.

Artificial intelligence, particularly machine learning, is the fastest-growing research trend in educational fields. Machine learning shows an impressive performance in many prediction models, including psychosocial education. The capability of machine learning to discover hidden patterns in large datasets encourages researchers to invent data with high-dimensional features. In contrast, not all features are needed by machine learning, and in many cases, high-dimensional features decrease the performance of machine learning. The feature selection method is one of the appropriate approaches to reducing the features to ensure machine learning works efficiently. Various selection methods have been proposed, but research to determine the essential subset feature in psychosocial education has not been established thus far. This research investigated and proposed methods to determine the best feature selection method in the domain of psychosocial education. We used a multi-criteria decision system (MCDM) approach with Additive Ratio Assessment (ARAS) to rank seven feature selection methods. The proposed model evaluated the best feature selection method using nine criteria from the performance metrics provided by machine learning. The experimental results showed that the ARAS is promising for evaluating and recommending the best feature selection method for psychosocial education data using the teacher’s psychosocial risk levels dataset.

In the past few years, Peer-to-Peer lending (P2P lending) has grown rapidly in the world. The main idea of P2P lending is disintermediation and removing the intermediaries like banks. For a small business and some individuals without enough credit or credit history, P2P lending is a good way to apply for a loan. However, the fundamental problem of P2P lending is information asymmetry in this model, which may not correctly estimate the default risk of lending. Lenders only determine whether or not to fund the loan by the information provided by borrowers, causing P2P lending data to be imbalanced datasets which contain unequal fully paid and default loans. Imbalanced datasets are quite common in the real worlds, such as credit card fraud in transactions, bad products in the plant and so on. Unfortunately, the imbalanced data are unfriendly to the normal machine learning schemes. In our scenario, models without any adaptive methods would focus on learning the normal repayment. However, the characteristic of the minority class is critical in the loaning business. In this study, we utilize not only several machine learning schemes for predicting the default risk of P2P lending but also re-sampling and cost-sensitive mechanisms to process imbalanced datasets. Furthermore, we use the datasets from Lending Club to validate our proposed scheme. The experiment results show that our proposed scheme can effectively raise the prediction accuracy for default risk.