The success of foundation models in natural language processing and computer vision has motivated similar approaches for general time series analysis. While these models are effective for a variety of tasks, their applicability in medical domains with limited data remains largely unexplored. To address this, we investigate the effectiveness of foundation models in medical time series analysis involving electroencephalography (EEG). Through extensive experiments on tasks such as age prediction, seizure detection, and the classification of clinically relevant EEG events, we compare their diagnostic accuracy with that of specialised EEG models. Our analysis shows that foundation models extract meaningful EEG features, outperform specialised models even without domain adaptation, and localise task-specific biomarkers. Moreover, we demonstrate that diagnostic accuracy is substantially influenced by architectural choices such as context length. Overall, our study reveals that foundation models with general time series understanding eliminate the dependency on large domain-specific datasets, making them valuable tools for clinical practice.

In natural language processing and computer vision, self-supervised pre-training on large datasets unlocks foundational model capabilities across domains and tasks. However, this potential has not yet been realised in time series analysis, where existing methods disregard the heterogeneous nature of time series characteristics. Time series are prevalent in many domains, including medicine, engineering, natural sciences, and finance, but their characteristics vary significantly in terms of variate count, inter-variate relationships, temporal dynamics, and sampling frequency. This inherent heterogeneity across domains prevents effective pre-training on large time series corpora. To address this issue, we introduce OTiS, an open model for general time series analysis, that has been specifically designed to handle multi-domain heterogeneity. We propose a novel pre-training paradigm including a tokeniser with learnable domain-specific signatures, a dual masking strategy to capture temporal causality, and a normalised cross-correlation loss to model long-range dependencies. Our model is pre-trained on a large corpus of 640, 187 samples and 11 billion time points spanning 8 distinct domains, enabling it to analyse time series from any (unseen) domain. In comprehensive experiments across 15 diverse applications - including classification, regression, and forecasting - OTiS showcases its ability to accurately capture domain-specific data characteristics and demonstrates its competitiveness against state-of-the-art baselines. Our code and pre-trained weights are publicly available at https://github.com/oetu/otis. Self-supervised pre-training paradigms are designed to account for the specific properties of language (Radford et al., 2018; Touvron et al., 2023; Chowdhery et al., 2023) or imaging (Zhou et al., 2022; Cherti et al., 2023; Oquab et al., 2024), unlocking foundational model capabilities that apply to a wide range of domains and downstream tasks. This potential, however, remains largely unrealised in time series due to the lack of self-supervised pre-training paradigms that account for the heterogeneity of time series across domains.

And now, some investors hope, Pokémon and Mario. For investors willing to make risky bets, the next big "Gamestonk" could be a vintage copy of Pokémon Yellow. Companies like Rally and Otis (founded in 2016 and 2018, respectively) allow their customers to buy shares of these niche assets, which have been fetching astronomically high prices at auction: A copy of Super Mario Bros. sold for $114,000 in July 2020, and in November, a copy of Super Mario Bros. 3 was auctioned off at $156,000, making it the most expensive game ever sold. A combination of rarity and old-fashioned financial speculation continues to drive prices higher, which in turn attracts more and more interest from investors. The current record is about to be smashed by another rare copy of Super Mario Bros. up for auction now, which is set to sell at over $310,000.

A combination of analytics and sensor technologies identify any deviations from what would be considered a normal ride, from a slight temperature change in the shafts to a slow-closing door. When such anomalies are detected, the system sends alerts to hand-held devices carried by maintenance personnel. The setup helps Schindler analyze problems faster, said Chief Technology Officer Karl-Heinz Bauer. "We can do the jobs in a shorter period of time and with higher quality," he said. The transformation of elevators from just a mechanically efficient way to go up and down into data-spewing devices is helping Schindler, as well as rivals Otis Elevator Co. and Thyssenkrupp AG, predict and diagnose elevator problems and better attune rides with expected foot traffic.

Nearly 165 years ago, Elisha Otis created the world's first safe elevator and founded a company with one goal in mind--to move people safely to their upward destination. Today as a part of United Technologies, we are bolstering our legacy with the latest in technology to introduce a completely new digital service ecosystem. This innovative system connects our teams and customers to each other, providing the information they want and expect in today's digital age. Let me offer a potentially real-world scenario: You're to give an important presentation at an office building thirty minutes away. You leave early, but traffic causes you to arrive with just five minutes to spare.

Everything we experience is filtered through thick veils of of personal baggage, self-interest and delusion, constantly skewing the world into the most comforting state possible. Universes of fragile concepts stand between what you think happened and what actually happened. It's an interactive crime drama that allows the audience to shift perspectives among three characters at will, telling a single story from disparate points of view. In the free online prototype, viewers press A, S or D on the keyboard to instantly swap perspectives among a babysitter, a father and a man intent on robbing their house. Otis doesn't pause when the perspective changes; the story carries on for all three characters.

As technologies such as artificial intelligence (AI) and machine learning (ML) mature, innovation is no longer the sole domain of consumer-facing businesses. With the democratisation of technology, organisations in the business-to-business (B2B) space -- traditionally deemed as slow adopters -- are enthusiastically embracing AI technology. The objective is to offer advanced and responsive products and services to clients. For example, with the help of AI and ML, Otis is developing smart elevators capable of communicating with passengers, building managers, service staff and other building systems. The elevator manufacturer is transforming its service business to incorporate smart, connected technology that delivers proactive, quick and effective diagnostics and repair.