Drone footage has captured a group of polar bears living inside an abandoned research station on Russia's Kolyuchin Island. Travel blogger, Vadim Makhorov, shared video that shows several bears inside the scattered building, looking through windows and walking around the island. A bear could be seen trying to catch the blogger's drone as it approached. The Kolyuchin weather station was abandoned in the early 1990s, after the collapse of the Soviet Union. Russian Alexey Molchanov breaks his own 2024 world record in one of the most technically challenging freediving events.

Russian freediver Alexey Molchanov plunged 126m (413ft) in a single breath to set a new world record at the AIDA Freediving World Championships in Limassol, Cyprus. He descended deep below the Mediterranean Sea with nothing but a headlight, two fins and a rope as a guide, in a feat considered one of the most technically challenging freedive categories. Mr Molchanov broke his own 2024 world record of 125m, during which he held his breath for a staggering four minutes and 32 seconds. The BBC's Russia editor, Steve Rosenberg, reports from joint manoeuvres by Russia and Belarus, as part of the Zapad 2025 (West 2025) military drills. 'Looks like a toy, but it's real': BBC examines a downed Russian drone Drones like this one were shot down over Polish airspace in the early hours of Wednesday.

Notre-Dame's iconic towers reopen six years after fire The iconic Medieval towers of Notre-Dame Cathedral in Paris have reopened to the public, six years after a massive fire ravaged parts of the historical landmark and forced its closure. The central part of the cathedral was reopened in December 2024, but it has taken longer for Notre-Dame's twin towers to be accessible once again for visitors. A huge restoration project has taken place over the past few years to bring the cathedral back to its former glory after parts of it were substantially damaged during 2019's fire. French President Emmanuel Macron on Friday reopened the newly-restored towers to the public. The BBC's Russia editor, Steve Rosenberg, reports from joint manoeuvres by Russia and Belarus, as part of the Zapad 2025 (West 2025) military drills.

'Looks like a toy, but it's real': BBC examines a downed Russian drone At least three Russian drones were shot down in Poland's airspace during attacks on Ukraine, the Polish prime minister said on Wednesday. The BBC's Sarah Rainsford has been looking at the exact type of Russian drone that flew into Poland, and is proving a massive challenge for Ukraine's territorial defence forces. The BBC's Sarah Rainsford says Sunday's attack caused a huge amount of damage. One of Kyiv's main government buildings was hit in overnight missile and drone strikes by Russia. 'The hit was very hard': Eyewitness in second carriage shares video of crash moment The incident in Lisbon's funicular has left 16 dead and multiple injured.

Ukraine's main government building in Kyiv was hit for the first time since Russia's full-scale invasion of the country on Sunday, officials said. The BBC's Sarah Rainsford visited the scene, where she observed a huge amount of damage. Local media reports suggest a cable came loose along the railway's route, causing it to lose control - a national day of mourning is being observed Actor Julia Roberts makes her Venice Film Festival debut promoting her new movie After The Hunt. The helicopter was attempting to collect water to fight wildfires at the time of the crash. 'Give it a go!': Tips from a top rate tree hugger Top tree hugger Hannah Willow explains why she loves the sport so much.

Water reuse is a key point when fresh water is a commodity in ever greater demand, but which is also becoming ever more available. Furthermore, the return of clean water to its natural environment is also mandatory. Therefore, wastewater treatment plants (WWTPs) are essential in any policy focused on these serious challenges. WWTPs are complex facilities which need to operate at their best to achieve their goals. Nowadays, they are largely monitored, generating large databases of historical data concerning their functioning over time. All this implies a large amount of embedded information which is not usually easy for plant managers to assimilate, correlate and understand; in other words, for them to know the global operation of the plant at any given time. At this point, the intelligent and Machine Learning (ML) approaches can give support for that need, managing all the data and translating them into manageable, interpretable and explainable knowledge about how the WWTP plant is operating at a glance. Here, an eXplainable Artificial Intelligence (XAI) based methodology is proposed and tested for a real WWTP, in order to extract explainable service knowledge concerning the operation modes of the WWTP managed by AQUAVALL, which is the public service in charge of the integral water cycle in the City Council of Valladolid (Castilla y León, Spain). By applying well-known approaches of XAI and ML focused on the challenge of WWTP, it has been possible to summarize a large number of historical databases through a few explained operation modes of the plant in a low-dimensional data space, showing the variables and facility units involved in each case.

The study proposes an advanced machine learning approach to predict spine surgery outcomes by incorporating oversampling techniques and grid search optimization. A variety of models including GaussianNB, ComplementNB, KNN, Decision Tree, and optimized versions with RandomOverSampler and SMOTE were tested on a dataset of 244 patients, which included pre-surgical, psychometric, socioeconomic, and analytical variables. The enhanced KNN models achieved up to 76% accuracy and a 67% F1-score, while grid-search optimization further improved performance. The findings underscore the potential of these advanced techniques to aid healthcare professionals in decision-making, with future research needed to refine these models on larger and more diverse datasets.

Time series data, defined by equally spaced points over time, is essential in fields like medicine, telecommunications, and energy. Analyzing it involves tasks such as classification, clustering, prototyping, and regression. Classification identifies normal vs. abnormal movements in skeleton-based motion sequences, clustering detects stock market behavior patterns, prototyping expands physical therapy datasets, and regression predicts patient recovery. Deep learning has recently gained traction in time series analysis due to its success in other domains. This thesis leverages deep learning to enhance classification with feature engineering, introduce foundation models, and develop a compact yet state-of-the-art architecture. We also address limited labeled data with self-supervised learning. Our contributions apply to real-world tasks, including human motion analysis for action recognition and rehabilitation. We introduce a generative model for human motion data, valuable for cinematic production and gaming. For prototyping, we propose a shape-based synthetic sample generation method to support regression models when data is scarce. Lastly, we critically evaluate discriminative and generative models, identifying limitations in current methodologies and advocating for a robust, standardized evaluation framework. Our experiments on public datasets provide novel insights and methodologies, advancing time series analysis with practical applications.

Low-Light Image Enhancement (LLIE) is a key task in computational photography and imaging. The problem of enhancing images captured during night or in dark environments has been well-studied in the image signal processing literature. However, current deep learning-based solutions struggle with efficiency and robustness in real-world scenarios (e.g. scenes with noise, saturated pixels, bad illumination). We propose a lightweight neural network that combines image processing in the frequency and spatial domains. Our method, FLOL+, is one of the fastest models for this task, achieving state-of-the-art results on popular real scenes datasets such as LOL and LSRW. Moreover, we are able to process 1080p images under 12ms. Code and models at https://github.com/cidautai/FLOL

White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. There is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences.