Résultats de recherche pour « Generative ML »

The COVID-19 pandemic and other ongoing health crises have underscored the need for prompt healthcare services worldwide. The traditional healthcare system, centered around hospitals and clinics, has proven inadequate in the face of such challenges. Intelligent wearable devices, a key part of modern healthcare, leverage Internet of Things technology to collect extensive data related to the environment as well as psychological, behavioral, and physical health. However, managing the substantial data generated by these wearables and other IoT devices in healthcare poses a significant challenge, potentially impeding decision-making processes. Recent interest has grown in applying data analytics for extracting information, gaining insights, and making predictions. Additionally, machine learning, known for addressing various big data and networking challenges, has seen increased implementation to enhance IoT systems in healthcare. This chapter focuses exclusively on exploring the hurdles encountered when integrating ML methods into the IoT healthcare sector. It offers a comprehensive summary of current research challenges and potential opportunities, categorized into three scenarios: IoT-based, ML-based, and the implementation of machine learning methodologies in the IoT-based healthcare industry. This compilation will assist future researchers, healthcare professionals, and government agencies by offering valuable insights into recent smart healthcare advancements.

In der Anwendung der aktuell diskutierten generativen KI-Systeme (ChatGPT, Midjourney etc.) werden nach schweizerischem Recht fremde Urheberrechte und verwandte Schutzrechte genutzt. Haben die Rechteinhaber oder ihre Rechteverwerter diesen Nutzungen nicht zugestimmt, so werden subjektive Rechte verletzt. Keine Hilfe bieten die Freiheit des Konsums und die Ausnahmen der Privatnutzung (Art. 19 URG) und der wissenschaftlichen Forschung (Art. 24d URG). Denn das Vervielfältigen und Bearbeiten durch die KI-Systeme geht über die gesetzlichen Zwecke hinaus. Was den Output generativer KI-Systeme betrifft (Texte, Bilder, Audios, Videos), so werden Rechte dann verletzt, wenn die konkrete Individualität eines Ursprungswerks erkennbar bleibt, das von Menschen geschaffen wurden. Das gleiche gilt aufgrund von Art. 2 Abs. 3bis URG, wenn eine fremde Fotografie ohne individuellen Charakter zugänglich gemacht wird. Mit dem Output können neue Rechte entstehen. Entweder trägt die anwendende Person oder die programmierende Person eine Individualität bei, die im Output erkennbar ist (geschütztes Werk gemäss Art. 2 URG), oder jemand lässt eine Audio- oder Videodateien entstehen (geschützte Ton- und Tonbildträger gemäss Art. 36 URG), woran möglicherweise auch eine Interpretin beteiligt sein kann, sofern namentlich ein Werk dargeboten wird (Art. 33 URG).

Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission. In this paper, we propose a general method to audit an ML model for the use of a data-owner's data in training, without prior knowledge of the ML task for which the data might be used. Our method leverages any existing black-box membership inference method, together with a sequential hypothesis test of our own design, to detect data use with a quantifiable, tunable false-detection rate. We show the effectiveness of our proposed framework by applying it to audit data use in two types of ML models, namely image classifiers and foundation models.

Machine learning (ML) transforms healthcare by enabling predictive analytics, personalized treatments, and improved patient outcomes. However, traditional ML workflows often require specialized skills, infrastructure, and resources, limiting accessibility for many healthcare professionals. This paper explores how BigQuery ML Cloud service helps healthcare researchers and data analysts to build and deploy models using SQL, without need for advanced ML knowledge. Our results demonstrate that the Boosted Tree model achieved the highest performance among the three models making it highly effective for diabetes prediction. BigQuery ML directly integrates predictive analytics into their workflows to inform decision-making and support patient care. We reveal this capability through a case study on diabetes prediction using the Diabetes Health Indicators Dataset. Our study underscores BigQuery ML's role in democratizing machine learning, enabling faster, scalable, and efficient predictive analytics that can directly enhance healthcare decision-making processes. This study aims to bridge the gap between advanced machine learning and practical healthcare analytics by providing detailed insights into BigQuery ML's capabilities. By demonstrating its utility in a real-world case study, we highlight its potential to simplify complex workflows and expand access to predictive tools for a broader audience of healthcare professionals.

oT ecosystems could be radically transformed by Generative Artificial Intelligence (GenAI), enabling intelligent data interpretation, automated decision-making, and human-AI cooperation in smart cities, healthcare, and industrial automation. However, cloud-centric deployments seriously jeopardize data sovereignty, model transparency, auditability, and service continuity—critical requirements in regulated and mission-critical domains. Large-scale IoT installations are not sustainable because to their high energy and thermal expenses.This work presents a sovereign, resilient, and energy-aware GenAI architecture that combines local data processing, local Large Language Models supported by Retrieval-Augmented Generation (RAG), and governance-by-design within a single edge-cloud continuum. At its core are machine learning agents that use deep reinforcement learning to discover optimal governance policies, adapting to dynamic privacy needs, evolving regulations, and fluctuating operational conditions while balancing privacy, compliance, service continuity, energy efficiency, and thermal constraints. Using the BIDMC PPG and Respiration Dataset and PubMedQA as case studies, we evaluate three configurations: cloud-only, conventional edge, and the proposed sovereign local framework with ML agent-based governance.Our architecture achieves 99% audit trace completeness (82% for cloud-only), reduces raw-data exposure from 100% to 4%, maintains 96% service availability during simulated outages, and reaches comparable accuracy (76.9% vs. 77.8%) at much lower latency (430 ms vs. 1840 ms, a 4.3x improvement). Additionally, compared to cloud-only implementation, it uses 92.7% less network traffic and 81% less energy per request. These results show that intelligent ML agents can deliver digital sovereignty without performance loss, providing a practical blueprint for sovereign and sustainable AI in real IoT settings.

Machine learning (ML) assets, such as models, datasets, and metadata, are central to modern ML workflows. Despite their explosive growth in practice, these assets are often underutilized due to fragmented documentation, siloed storage, inconsistent licensing, and lack of unified discovery mechanisms, making ML-asset management an urgent challenge. This tutorial offers a comprehensive overview of ML-asset management activities across its lifecycle, including curation, discovery, and utilization. We provide a categorization of ML assets, and major management issues, survey state-of-the-art techniques, and identify emerging opportunities at each stage. We further highlight system-level challenges related to scalability, lineage, and unified indexing. Through live demonstrations of systems, this tutorial equips both researchers and practitioners with actionable insights and practical tools for advancing ML-asset management in real-world and domain-specific settings.

The BigSMILES notation, a concise tool for polymer ensemble representation, is augmented here by introducing an enhanced version called generative BigSMILES. G-BigSMILES is designed for generative workflows, and is complemented by tailored software tools for ease of use. This extension integrates additional data, including reactivity ratios (or connection probabilities among repeat units), molecular weight distributions, and ensemble size. An algorithm, interpretable as a generative graph is devised that utilizes these data, enabling molecule generation from defined polymer ensembles. Consequently, the G-BigSMILES notation allows for efficient specification of complex molecular ensembles via a streamlined line notation, thereby providing a foundational tool for automated polymeric materials design. In addition, the graph interpretation of the G-BigSMILES notation sets the stage for robust machine learning methods capable of encapsulating intricate polymeric ensembles. The combination of G-BigSMILES with advanced machine learning techniques will facilitate straightforward property determination and in-silico polymeric material synthesis automation. This integration has the potential to significantly accelerate materials design processes and advance the field of polymer science.

Abstract This paper utilizes the concepts of fog computing, machine-learning and generative-AI to build accurate and efficient intrusion detection system IDS for the Internet of Things. It proposes a hybrid approach in which the machine learning classifier for the IDS system is built using both real data and synthetic data. The utilized real data will be information evaluated at the edge of the network and deemed to be non-sensitive and hence can be shipped to the cloud to build the generative-AI model. This model will then be used to generate the synthetic data used to augment the partial data. By doing so the security and privacy of the IoT environment is protected while still build an IDS with accepted accuracy. The evaluation shows that by applying techniques such as the light-weight privacy classification and principal component analysis PCA we are able to achieve good intrusion detection accuracy while minimizing the privacy risks to IoT raw data.