Using agent-based social simulations can enhance our understanding of urban planning, public health, and economic forecasting. Realistic synthetic populations with numerous attributes strengthen these simulations. The Wasserstein Generative Adversarial Network, trained on census data like EU-SILC, can create robust synthetic populations. These methods, aided by external statistics or EU-SILC weights, generate spatial synthetic populations for agent-based models. The increased access to high-quality micro-data has sparked interest in synthetic populations, which preserve demographic profiles and analytical strength while ensuring privacy and preventing discrimination. This study uses national data from Finland and Greece for Helsinki and Thessaloniki to explore balanced spatial synthetic population generation. Results show challenges related to balancing data with or without aggregated statistics for the target population and the general under-representation of fringe profiles by deep generative methods. The latter can lead to discrimination in agent-based simulations.
Art curatorial practice is characterized by the presentation of an art collection in a knowledgeable way. Machine processes are characterized by their capacity to manage and analyze large amounts of data. This paper envisages AI curation and audience interaction to explore the implications of contemporary machine learning models for the curatorial world. This project was developed for the occasion of the 2023 Helsinki Art Biennial, entitled New Directions May Emerge. We use the Helsinki Art Museum (HAM) collection to re-imagine the city of Helsinki through the lens of machine perception. We use visual-textual models to place indoor artworks in public spaces, assigning fictional coordinates based on similarity scores. We transform the space that each artwork inhabits in the city by generating synthetic 360 art panoramas. We guide the generation estimating depth values from 360 panoramas at each artwork location, and machine-generated prompts of the artworks. The result of this project is an AI curation that places the artworks in their imagined physical space, blurring the lines of artwork, context, and machine perception. The work is virtually presented as a web-based installation
The Helsinki Speech Challenge 2024 (HSC2024) invites researchers to enhance and deconvolve speech audio recordings. We recorded a dataset that challenges participants to apply speech enhancement and inverse problems techniques to recorded speech data. This dataset includes paired samples of AI-generated clean speech and corresponding recordings, which feature varying levels of corruption, including frequency attenuation and reverberation. The challenge focuses on developing innovative deconvolution methods to accurately recover the original audio. The effectiveness of these methods will be quantitatively assessed using a speech recognition model, providing a relevant metric for evaluating enhancements in real-world scenarios.
Large urban special events significantly contribute to a city's vibrancy and economic growth but concurrently impose challenges on transportation systems due to alterations in mobility patterns. This study aims to shed light on mobility patterns by utilizing a unique, comprehensive dataset collected from the Helsinki public transport mobile application and Bluetooth beacons. Earlier methods, relying on mobile phone records or focusing on single traffic modes, do not fully grasp the intricacies of travel behavior during such events. We focus on the Vappu festivities (May 1st) in the Helsinki Metropolitan Area, a national holiday characterized by mass gatherings and outdoor activities. We examine and compare multi-modal mobility patterns during the event with those during typical non-working days in May 2022. Through this case study, we find that people tend to favor public transport over private cars and are prepared to walk longer distances to participate in the event. The study underscores the value of using comprehensive multi-modal data to better understand and manage transportation during large-scale events.
NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary step into the direction of designing smaller sub-networks and components with specialized functionality. In this paper, we present the MAMMOTH toolkit: a framework designed for training massively multilingual modular machine translation systems at scale, initially derived from OpenNMT-py and then adapted to ensure efficient training across computation clusters. We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information. The toolkit is publicly available online.
Spatiotemporal distribution of urban population is crucial to understand the structure and dynamics of cities. Most studies, however, have focused on the microscopic structure of cities such as their few most crowded areas. In this work, we investigate the macroscopic structure of cities such as their clusters of highly populated areas. To do this, we analyze the spatial distribution of urban population and its intraday dynamics in Seoul and Helsinki with a percolation framework. We observe that the growth patterns of the largest clusters in the real and randomly shuffled population data are significantly different, and highly populated areas during the daytime are denser and form larger clusters than highly populated areas during the nighttime. An analysis of the cluster-size distributions at percolation criticality shows that their power-law exponents during the daytime are lower than those during the nighttime, indicating that the spatial distributions of urban population during daytime and nighttime fall into different universality classes. Finally measuring the area-perimeter fractal dimension of the collection of clusters demonstrates that the fractal dimensions during the da
This article presents the algorithms developed by the Core Imaging Library (CIL) developer team for the Helsinki Tomography Challenge 2022. The challenge focused on reconstructing 2D phantom shapes from limited-angle computed tomography (CT) data. The CIL team designed and implemented five reconstruction methods using CIL (https://ccpi.ac.uk/cil/), an open-source Python package for tomographic imaging. The CIL team adopted a model-based reconstruction strategy, unique to this challenge with all other teams relying on deep-learning techniques. The CIL algorithms showcased exceptional performance, with one algorithm securing the third place in the competition. The best-performing algorithm employed careful CT data pre-processing and an optimization problem with single-sided directional total variation regularization combined with isotropic total variation and tailored lower and upper bounds. The reconstructions and segmentations achieved high quality for data with angular ranges down to 50 degrees, and in some cases acceptable performance even at 40 and 30 degrees. This study highlights the effectiveness of model-based approaches in limited-angle tomography and emphasizes the importa
Detailed understanding of multi-modal mobility patterns within urban areas is crucial for public infrastructure planning, transportation management, and designing public transport (PT) services centred on users' needs. Yet, even with the rise of ubiquitous computing, sensing urban mobility patterns in a timely fashion remains a challenge. Traditional data sources fail to fully capture door-to-door trajectories and rely on a set of models and assumptions to fill their gaps. This study focuses on a new type of data source that is collected through the mobile ticketing app of HSL, the local PT operator of the Helsinki capital region. HSL's dataset called TravelSense, records anonymized travelers' movements within the Helsinki region by means of Bluetooth beacons, mobile phone GPS, and phone OS activity detection. In this study, TravelSense dataset is processed and analyzed to reveal spatio-temporal mobility patterns as part of investigating its potentials in mobility sensing efforts. The representativeness of the dataset is validated with two external data sources - mobile phone trip data (for demand patterns) and travel survey data (for modal share). Finally, practical perspectives t
In this paper we present a bilevel optimization scheme for the solution of a general image deblurring problem, in which a parametric variational-like approach is encapsulated within a machine learning scheme to provide a high quality reconstructed image with automatically learned parameters. The ingredients of the variational lower level and the machine learning upper one are specifically chosen for the Helsinki Deblur Challenge 2021, in which sequences of letters are asked to be recovered from out-of-focus photographs with increasing levels of blur. Our proposed procedure for the reconstructed image consists in a fixed number of FISTA iterations applied to the minimization of an edge preserving and binarization enforcing regularized least-squares functional. The parameters defining the variational model and the optimization steps, which, unlike most deep learning approaches, all have a precise and interpretable meaning, are learned via either a similarity index or a support vector machine strategy. Numerical experiments on the test images provided by the challenge authors show significant gains with respect to a standard variational approach and performances comparable with those
Understanding the mobility patterns of commuter train passengers is crucial for developing efficient and sustainable transportation systems in urban areas. Traditional technologies, such as Automated Passenger Counters (APC) can measure the aggregated numbers of passengers entering and exiting trains, however, they do not provide detailed information nor passenger movements beyond the train itself. To overcome this limitation we investigate the potential combination of traditional APC with an emerging source capable of collecting detailed mobility demand data. This new data source derives from the pilot project TravelSense, led by the Helsinki Regional Transport Authority (HSL), which utilizes Bluetooth beacons and HSL's mobile phone ticket application to track anonymous passenger multimodal trajectories from origin to destination. By combining TravelSense data with APC we are able to better understand the structure of train users' journeys by identifying the origin and destination locations, modes of transport used to access commuter train stations, and boarding and alighting numbers at each station. These insights can assist public transport planning decisions and ultimately help
Using several lines of evidence we show that the scale values of the geomagnetic variometers operating in Helsinki in the 19th century were not constant throughout the years of operation 1844-1897. Specifically, the adopted scale value of the Horizontal Force variometer appears to be too low by ~30% during the years 1866-1874.5 and the adopted scale value of the Declination variometer appears to be too low by a factor of ~2 during the interval 1885.8-1887.5. Reconstructing the Heliospheric Magnetic Field strength from geomagnetic data has reached a stage where a reliable reconstruction is possible using even just a single geomagnetic data set of hourly or daily values. Before such reconstructions can be accepted as reliable, the underlying data must be calibrated correctly. It is thus mandatory that the Helsinki data be corrected. Such correction has been satisfactorily carried out and the HMF strength is now well constrained back to 1845.
This paper describes the submission from the University of Helsinki to the shared task on cross-lingual dependency parsing at VarDial 2017. We present work on annotation projection and treebank translation that gave good results for all three target languages in the test set. In particular, Slovak seems to work well with information coming from the Czech treebank, which is in line with related work. The attachment scores for cross-lingual models even surpass the fully supervised models trained on the target language treebank. Croatian is the most difficult language in the test set and the improvements over the baseline are rather modest. Norwegian works best with information coming from Swedish whereas Danish contributes surprisingly little.
These are short notes of three introductory lectures on recently proposed matrix models of Superstrings and M theory given at 5th Nordic Meeting on Supersymmetric Field and String Theories in Helsinki (March 10-12, 1997). Contents: M(atrix) theory of BFSS, From IIA to IIB with IKKT, The NBI matrix model.
In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English. This year, we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German, we trained both sentence-level transformer models and compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches, and we also included a rule-based system for English-Finnish.
The 15-minute city is a powerful planning concept to counter car-dependence by promoting active mobility to amenities and fostering inclusive urban environments. However, this policy has challenges in amenity-poor urban peripheries. Public transport remains underexplored in this discourse despite its role in distant access. Here, we propose a framework that incorporates public transport into the 15-minute city model using openly available data. By comparing Helsinki, Madrid, and Budapest, we demonstrate that multimodal mobility substantially increases access to amenities and enhances socio-spatial integration within a 15-minute reach. Although urban periphery benefit significantly from radial or high-speed public transport lines in their social mixing potential, such lines alone do not improve their access to amenities. These findings underscore the need to optimize polycentric public transport networks that can improve inclusive urban accessibility and complement active mobility in polycentric cities.
Developing accurate and generalizable epileptic seizure prediction models from electroencephalography (EEG) data across multiple clinical sites is hindered by patient privacy regulations and significant data heterogeneity (non-IID characteristics). Federated Learning (FL) offers a privacy-preserving framework for collaborative training, but standard aggregation methods like Federated Averaging (FedAvg) can be biased by dominant datasets in heterogeneous settings. This paper investigates FL for seizure prediction using a single EEG channel across four diverse public datasets (Siena, CHB-MIT, Helsinki, NCH), representing distinct patient populations (adult, pediatric, neonate) and recording conditions. We implement privacy-preserving global normalization and propose a Random Subset Aggregation strategy, where each client trains on a fixed-size random subset of its data per round, ensuring equal contribution during aggregation. Our results show that locally trained models fail to generalize across sites, and standard weighted FedAvg yields highly skewed performance (e.g., 89.0% accuracy on CHB-MIT but only 50.8% on Helsinki and 50.6% on NCH). In contrast, Random Subset Aggregation sig
In this paper, we compare pricing and non-pricing mechanisms for implementing demand-side management (DSM) mechanisms in a neighborhood in Helsinki, Finland. We compare load steering based on peak load-reduction using the profile steering method, and load steering based on market price signals, in terms of peak loads, losses, and device profiles. We found that there are significant differences between the two methods; the peak-load reduction control strategies contribute to reducing peak power and improving power flow stability, while strategies primarily based on prices result in higher peaks and increased grid losses. Our results highlight the need to potentially move away from market-price-based DSM to DSM incentivization and control strategies that are based on peak load reductions and other system requirements.
This is the story of the first Fields Medal awarded to Lars Ahlfors. It was smuggled out of Finland in 1944, pawned in Sweden during World War II, and returned to Helsinki in 2004. This article is based on an interview with Ahlfors' second daughter Vanessa Gruen, and established biographical sources.
The visual appeal of urban environments significantly impacts residents' satisfaction with their living spaces and their overall mood, which in turn, affects their health and well-being. Given the resource-intensive nature of gathering evaluations on urban visual appeal through surveys or inquiries from residents, there is a constant quest for automated solutions to streamline this process and support spatial planning. In this study, we applied an off-the-shelf AI model to automate the analysis of urban visual appeal, using over 1,800 Google Street View images of Helsinki, Finland. By incorporating the GPT-4 model with specified criteria, we assessed these images. Simultaneously, 24 participants were asked to rate the images. Our results demonstrated a strong alignment between GPT-4 and participant ratings, although geographic disparities were noted. Specifically, GPT-4 showed a preference for suburban areas with significant greenery, contrasting with participants who found these areas less appealing. Conversely, in the city centre and densely populated urban regions of Helsinki, GPT-4 assigned lower visual appeal scores than participant ratings. While there was general agreement b
This paper addresses the reconstruction of audio signals from degraded measurements. We propose a lightweight model that combines the discrete Fourier transform with a Convolutional Autoencoder (FFT-ConvAE), which enabled our team to achieve second place in the Helsinki Speech Challenge 2024. Our results, together with those of other teams, demonstrate the potential of neural-network-free approaches for effective speech signal reconstruction.