Digital twin (DT) technology enables real-time simulation, prediction, and optimization of physical systems, but its practical deployment often faces challenges related to high data requirements, proprietary data constraints, and limited adaptability to evolving system conditions. This work introduces DDD-GenDT, a dynamic data-driven generative digital twin framework grounded in the Dynamic Data-Driven Application Systems (DDDAS) paradigm. The proposed architecture comprises of the Physical Twin Observation Graph (PTOG) for representing operational states of the physical twin (PT), an Observation Window Extraction process for capturing relevant temporal state sequences, a Data Preprocessing Pipeline within an LLM-Based Behavior Prediction Engine for sensor data structuring and filtering, and an LLM ensemble that performs zero-shot predictive inference. By leveraging generative artificial intelligence, DDD-GenDT reduces the need for extensive historical datasets, enabling DT construction in data-scarce environments while maintaining privacy for proprietary industrial processes. The DDDAS-driven feedback mechanism allows the DT to autonomically adapt its predictive behavior in alignment with PT-specific wear and degradation patterns, thereby supporting DT-aging, which is the progressive synchronization of the DT with the evolving physical system. The proposed framework is validated using the NASA CNC milling dataset, with spindle motor current as the monitored variable. In a zero-shot prediction setting, the GPT-4-based DT achieves an average RMSE of 0.479 A (4.79% of the maximum 10 A spindle current), accurately modeling both nonlinear process dynamics and changes arising from PT aging without retraining. These results demonstrate that DDD-GenDT provides a generalizable, data-efficient, and adaptive DT modeling approach, bridging the generative AI capabilities with the performance and reliability requirements of industrial DT applications.

Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for women's mental and physical health, especially affecting female reproductive systems. Exploiting weakly supervised learning and explainable AI techniques are crucial for fast, accurate, and robust automatic marker detection, efficient prevention, and primary treatment of gynecological tumors. Methods: With respect to the PRIMSA methodology, weakly supervised learning schemes and deep learning-based schemes are investigated in the cross-subject fields of clinical diagnostic imaging and explainable AI technology. Related methods, opening research problems, and challenging subjects are explored in the screening and treatment of gynecological tumors and performing cancer image diagnosis in the latest study. Results: Keynote approaches combining ultrasound medicine, explainable AI, and clinical imaging technology are summarized. In combination with learning-based methods with medical imaging, prospective insights are put forward for refreshed concepts on treatments in the area of gynecological oncology, with a feasible range of applications for their corresponding AI techniques. Conclusions: Explainable AI and deep learning-based approaches are capable of performing accurate classification between benign and malignant tumors, yielding a pathway to care for women's health, improving the survival rate of patients, pacing with disease prediction, and matching the strategic goal of "Healthy China 2030".

The aviation sector relies on cooperative surveillance systems such as Automatic Dependent Surveillance-Broadcast (ADS-B) and Remote Identification (RID) to enhance safety and efficiency. However, their open, unencrypted communication protocols make them vulnerable to various cyberattacks. This survey examines the current state of knowledge on attacks, detection techniques, and countermeasures for both ADS-B and RID, addressing a gap in the literature by analyzing them side by side. It categorizes attacks, including emerging threats, reviews detection methods from traditional to modern AI-based approaches and discusses existing countermeasures. Furthermore, this paper provides a list of simulation tools and open-access datasets and identifies current research challenges and future directions.

As Cyber-Physical Systems (CPS) such as water treatment and distribution systems grow in scale and complexity, their operational technology becomes computationally heterogeneous, spanning from resource-abundant cloud platforms to resource-constrained edge devices. This fundamental diversity challenges the deployment of a single, effective anomaly detection solution, creating a significant architectural dilemma for critical infrastructure operations. Deep learning methods achieve strong anomaly detection capability, but they are often too heavy for resource-constrained edge devices. Although lightweight models can reduce the demand for computing resources, their detection capability also decreases. To address these issues, this paper proposes Transformer-based Anomaly Behavior Analysis for Cyber-Physical Systems (TABA-CPS), a holistic architecture designed to address this conflict through its flexible dual-mode deployment strategy. At its core is a novel Expectation-Maximization Anomaly Transformer (EM-AT) model, an extension of the Anomaly Transformer (AT) that automatically sets the detection threshold, eliminating manual inspection. TABA-CPS offers a flexible, dual-mode deployment strategy: a Performance mode for environments with enough computational resources, which maximizes anomaly detection accuracy and enables Large Language Model (LLM)-based anomaly behavior investigation; and a Computational Resource-constrained Edge (CRCE) mode for resource-constrained devices (e.g., Raspberry Pi), which utilizes model quantization and the ExecuTorch runtime to deliver efficient, low-latency inference. Additionally, the architecture introduces the Green-Water System Anomaly Detection Evaluation (Green-WSADE) framework, inspired by the Green AI idea, to evaluate overall performance on different devices. Experiment results show that Performance mode achieves F₁ scores of 96.32% and 92.47% on Secure Water Treatment (SWaT) and Water Distribution(WADI) datasets, respectively, surpassing leading methods. CRCE mode significantly lowers computational resource consumption, including a 41% reduction in average inference power with only a marginal F₁ score drop (about 0.14% on SWaT, 0.11% on WADI). Moreover, the CRCE mode consistently achieves a computational resource efficiency grade of 1 to 3 across heterogeneous edge devices under the Green-WSADE framework, achieving superior resource efficiency compared to Performance mode on identical resource-constrained hardware. The results demonstrate that TABA-CPS delivers accurate and rapid on-site anomaly detection at the network edge while lowering resource usage, supporting long-term, reliable operation in water treatment and distribution systems.

Artificial intelligence (AI) is applied at a pace that challenges the verification of its suitability to the domains of application. This situation arises from the proliferation of AI development being conducted from a data science point of view rather than a software engineering approach. The situation leads to the question of whether software development course curricula are addressing the necessary educational needs for graduates to respond to the challenges of applying AI development in emerging domains. The challenge has two parts: the first is the use of AI in developing software systems, and the second is the development of AI systems. By looking at the first part of this challenge, we propose a pedagogy for introducing AI tools in software engineering education and structuring a methodology for AI application development to establish software engineering principles. This article is exploratory. We reviewed the existing literature to identify the commonalities of approaches to select a required set of topics, course outcomes, and structure for a curriculum on AI in software development.