To make the test automation process go faster, we needed to harness innovation. So how do we do this? So the first strategy was to figure out how we could leverage AI to speed up the test development cycle. The second strategy involved developing a test automation care package.

This paper presents a cloud-edge digital twin frame- work designed to enhance battery lifecycle management within electric vehicles, contributing to sustainable transportation and advanced battery system engineering. The architecture integrates a static state-of-health (SOH) model trained offline with a dynamically retrained state-of-charge (SOC) model updated peri- odically via cloud-based machine learning.

This paper introduces a data-driven anomaly detection framework designed to enhance the safety and reliability of lithium-ion battery packs deployed in large-scale electric transport systems. Leveraging principal component analysis (PCA) and cumulative sum (CUSUM) control charts, the method monitors mean-based residuals of voltage and temperature across cell groups to detect early-stage faults such as internal short circuits, sensor failures, and thermal irregularities.

The rapid development arena of Artificial Intelligence (AI), especially from Large Language Models (LLMs), has prompted a drastic change in the way data engineering is practised. This paper provides an in-depth overview of AI-powdered data engineering, and discusses how modern AI techniques are re-shaping the conventional development, profiling/optimisation, and maintenance process of the data pipeline. We then study recent paradigms in so-called pipeline automation with LLMs, the growing use of machine learning to optimise database query execution, and ponder over risks and governance that should be considered when allowing AI-driven data flows.

This paper discusses the potential contribution of Artificial Intelligence (AI) to Cybersecurity: How can it be useful for securing healthcare patient data? ML, NLP, AD(shell 2017) for defending cyber threats AI techniques such as machine learning and natural language processing (NLP), anomaly detection are the best helpful in detecting and protecting from cyber threats. [1] [8] The work evaluates these technologies for their suitability in the context of real-time threat discovery, automated incident response and data confidentiality protection.

Agentic AI systems that autonomously retrieve patient data, invoke external tools, and maintain cross-session memory introduce safety challenges that extend beyond traditional model-level evaluation. Existing benchmarks assess trust, privacy, and security in isolation, overlooking critical interactions: retrieval strategies influence both answer accuracy and what Protected Health Information (PHI) enters the model context, while memory configurations affect longitudinal reasoning as well as adversarial exposure.

Manual cleaning of underground drainage systems is grossly inadequate and one of the world's most dangerous occupations that expose sewage workers to toxic gases, oxygen deficiency, structural collapse and fatal accidents. The deaths are mostly due to inhalation of toxic gases such as methane (CH₄), hydrogen sulfide (H₂S), ammonia (NH₃) and carbon monoxide (CO) that can be found in the mines.

Coal mining ranks among the most dangerous job, with workers operating in underground conditions replete with toxic gases, higher-than-average temperatures, heavy machinery and unstable working environments. Workers are routinely exposed to dangers such as methane leaks, carbon-monoxide poisoning, explosions and sudden building collapses. To keep miners safe, smart mines need to continuously track environmental factors and monitor worker health condition.

An AI-based Key Performance Indicator (KPI) framework is developed for monitoring and controlling ventilation quality using embedded devices.The system integrates real-time data from MQ-02 and MQ-135 gas sensors, processed through machine learning algorithms to generate predictive outputs that guide ventilation control decisions. These streamlined models are designed specifically for embedded deployment, continuously monitoring critical KPIs related to air quality index, ventilation efficiency and response time to ensure smart order situational adaptive ventilation.

The rapid expansion of medical data within the National Health Service (NHS) presents both opportunities and challenges in leveraging healthcare analytics for improved patient outcomes and research. However, disparate data sources, inconsistent formats, and the lack of standardized integration mechanisms hinder effective data utilization. This study proposes a novel framework for standardizing and integrating NHS medical data by addressing structural heterogeneity, semantic in- consistencies, and interoperability gaps.