Future Digital Technologies and Artificial Intelligence

Mapping the spatial-temporal evolution of imagery in Tang poetry: a computer vision and GIS-based approach

Zhuanghao Si — Mon, 27 Oct 2025 00:00:00 +0000

This study uses computer analysis and mapping technology to examine the changes in the locations and times mentioned in poetry images from the Tang Dynasty (618–907 CE). Tang poetry from this era of Chinese history contains a wealth of cultural and geographic details that are suitable for computer analysis. Using tools for location mapping and automatic image sorting, we examined 2,800 poems written by 485 poets. With an accuracy of 89% for natural images, 85% for cultural images, and 82% for emotional images, the computer vision system produced good results. Three distinct regional groups — centered on northwest political areas, central cultural corridors, and southern literary regions — were identified through the successful mapping of 1,247 location mentions across Tang Dynasty China using geographic analysis. Time analysis revealed the distinct shift in poetic activity from northwestern centers to southern regions, centered by the An Lushan Rebellion (755-763 CE). In the Late Tang analysis, the lines of separation show, with some degree of real evidence, matching the recorded population changes affecting large populations. This method gives digital humanities researchers a tool for constructing number-based frameworks that are founded in accepted literary history views. These findings furnish practical needs in matters of cultural heritage protection and in educational programs linking literature with historical geography.

Self-healing IoT infrastructure for intelligent transportation systems: a multi-city comparative analysis

Si Liu, Midhun Chakkaravarthy — Fri, 20 Mar 2026 00:00:00 +0000

Intelligent transportation systems critically depend on reliable real-time data from thousands of distributed IoT sensors, yet current management frameworks lack autonomous recovery mechanisms to maintain service continuity during device failures or network disruptions. This paper presents a self-healing infrastructure architecture specifically designed for the transportation domain, where service interruptions can cascade into traffic congestion and safety hazards. The architecture integrates three complementary mechanisms: predictive health monitoring, which uses time-series anomaly detection to identify failing devices before complete failure; preemptive workload migration, which redistributes critical sensing tasks to neighboring devices based on predicted failures; and distributed consensus protocols, which enable rapid reconfiguration without centralized coordination. Unlike existing reactive approaches that respond to failures after service degradation occurs, our proactive strategy maintains service quality by anticipating and preventing disruptions. A key innovation lies in the domain-specific failure prediction models trained on operational patterns unique to transportation applications, incorporating factors such as vehicle vibration exposure, environmental stress, and communication interference patterns. Comparative analysis of multiple metropolitan transportation networks with varying levels of infrastructure maturity reveals that self-healing capabilities significantly reduce the frequency of service interruptions and recovery time compared to operator-managed systems. The findings demonstrate that transportation authorities can deploy larger sensor networks with fewer maintenance personnel by leveraging autonomous resilience mechanisms. This work provides practical guidelines for deploying fault-tolerant IoT systems in mission-critical urban services where reliability directly impacts public safety and urban mobility.

Lightweight security architecture for resource-constrained IoT devices: design patterns and implementation trade-offs

Si Liu, Midhun Chakkaravarthy — Fri, 27 Mar 2026 00:00:00 +0000

Securing large-scale IoT deployments poses fundamental challenges as traditional cryptographic protocols impose computational overhead that resource-constrained devices cannot sustain while maintaining real-time responsiveness. This paper systematically analyzes the design space of lightweight security architectures for IoT management systems, identifying critical tradeoffs between protection strength, computational efficiency, and operational scalability. Through iterative prototype development and performance profiling across heterogeneous device platforms, we derive a set of validated design patterns that balance security requirements with resource constraints. The proposed architecture employs stratified security policies in which protection mechanisms adapt to device capabilities—resource-rich gateways handle computationally intensive operations, while resource-constrained sensors implement optimized authentication protocols. A novel contribution is a distributed authentication framework that uses Merkle-DAG structures to achieve high transaction throughput without incurring blockchain consensus overhead, thereby enabling real-time coordination among thousands of devices. The paper also introduces a taxonomy of attack vectors specific to collaborative IoT management and evaluates defensive mechanisms through systematic penetration testing. Implementation guidelines address practical considerations, including key distribution in dynamic device populations, secure firmware updates over unreliable networks, and privacy-preserving data aggregation at edge nodes. Experimental results from laboratory testbeds and pilot deployments demonstrate that carefully optimized classical cryptographic primitives can provide adequate security for current IoT systems without incurring prohibitive overhead, while the modular architecture supports future migration to post-quantum algorithms as hardware capabilities improve. This work provides system architects with evidence-based design principles for implementing security in resource-constrained distributed systems where traditional approaches prove infeasible.

Value co-creation in smart transportation new infrastructure projects: the mechanism of AI-enhanced corporate culture and advertising on strategic niche construction for Shandong SMEs

Hui Yan, Rozaini Binti Rosli — Sat, 25 Apr 2026 00:00:00 +0000

Small and medium-sized enterprises (SMEs) in China's smart-transportation new-infrastructure sector face persistent difficulties in constructing durable strategic niches, yet existing research relies on survey-based methods that overlook the textual signals firms produce through public-facing documents. This study proposes a three-stage analytical framework that integrates NLP feature extraction, machine-learning prediction, and PLS-SEM mediation testing. Drawing on 323 SMEs in Shandong Province and a corpus of 12,864 enterprise text segments, the NLP pipeline extracts culture-sentiment, advertising-sentiment, topic-proportion, and AI-keyword-density features through BERT-wwm-ext, LDA, and TF-IDF. XGBoost achieves the best prediction of strategic niche construction (R² = 0.63), and SHAP analysis identifies culture-sentiment as the top-ranked feature (mean |SHAP| = 0.42), outperforming all survey-derived variables. PLS-SEM validates that value co-creation partially mediates both paths from AI-enhanced organizational capabilities to niche construction (VAF = 29.3% and 31.7%). The findings indicate that text-derived indicators capture strategic positioning signals that conventional questionnaires miss, offering a replicable mixed-methods paradigm for AI-management crossover research.