Imagine you are a dog behind a fence $Q$ and a hiker is passing by at constant speed along the hiking path $P$. In order to fulfil your duties as a watchdog, you desire to bark as long as possible at the human. However, your barks can only be heard in a fixed radius $ρ$ and, as a dog, you have bounded speed $s$. Can you optimize your route along the fence $Q$ in order to maximize the barking time with radius $ρ$, assuming you can run backwards and forward at speed at most $s$? We define the barking distance from a polyline $P$ on $n$ vertices to a polyline $Q$ on $m$ vertices as the time that the hiker stays in your barking radius if you run optimally along $Q$. This asymmetric similarity measure between two curves can be used to detect outliers in $Q$ compared to $P$ that other established measures like the Fréchet distance and Dynamic Time Warping fail to capture at times. We consider this measure in three different settings. In the discrete setting, the traversals of $P$ and $Q$ are both discrete. For this case we show that the barking distance from $P$ to $Q$ can be computed in $O(nm\log s)$ time. In the semi-discrete setting, the traversal of $Q$ is continuous while the one of
Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is straightforward and widely adopted, the relationship between RM accuracy and downstream policy performance remains under-explored. In this work, we conduct experiments in a synthetic setting to investigate how differences in RM measured by accuracy translate into gaps in optimized policy performance. Our findings reveal that while there is a weak positive correlation between accuracy and downstream performance, policies optimized towards RMs with similar accuracy can exhibit quite different performance. Moreover, we discover that the way of measuring accuracy significantly impacts its ability to predict the final policy performance. Through the lens of the Regressional Goodhart effect, we recognize that accuracy, when used for measuring RM quality, can fail to fully capture the potential RM overoptimization. This underscores the inadequacy of relying solely on accuracy to reflect their impact on policy optimization.
Takamura established a theory on splitting families of degenerations of complex curves. He introduced a powerful method for constructing a splitting family, called a barking family, in which there appear not only a singular fiber over the origin but also singular fibers over other points, called subordinate fibers. In this paper, for the case of degenerations of elliptic curves, we determine the types of these subordinate fibers.
Quantum weak measurements with states both pre- and postselected offer a window into a hitherto neglected sector of quantum mechanics. A class of such systems involves time dependent evolution with transitions possible. In this paper we explore two very simple systems in this class. The first is a toy model representing the decay of an excited atom. The second is the tunneling of a particle through a barrier. The postselection criteria are chosen as follows: at the final time, the "atom" remains in its initial excited state for the first example and the particle remains behind the barrier for the second. We then ask what weak values are predicted in the physical environment of the "atom" (to which no net energy has been transferred) and in the region beyond the barrier (to which the particle has not tunneled). Previous work suggests that very large weak values might arise in these regions for long durations between pre- and postselection times. Our calculations reveal some distinct differences between the two model systems.
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it. These instructions form a synthesis directed acyclic graph (DAG), describing how a large vocabulary of simple building blocks can be recursively combined through chemical reactions to create more complicated molecules of interest. In contrast, many current deep generative models for molecules ignore synthesizability. We therefore propose a deep generative model that better represents the real world process, by directly outputting molecule synthesis DAGs. We argue that this provides sensible inductive biases, ensuring that our model searches over the same chemical space that chemists would also have access to, as well as interpretability. We show that our approach is able to model chemical space well, producing a wide range of diverse molecules, and allows for unconstrained optimization of an inherently constrained problem: maximize certain chemical properties such that discovered molecules are synthesizable.
Environmental sounds like footsteps, keyboard typing, or dog barking carry rich information and emotional context, making them valuable for designing haptics in user applications. Existing audio-to-vibration methods, however, rely on signal-processing rules tuned for music or games and often fail to generalize across diverse sounds. To address this, we first investigated user perception of four existing audio-to-haptic algorithms, then created a data-driven model for environmental sounds. In Study 1, 34 participants rated vibrations generated by the four algorithms for 1,000 sounds, revealing no consistent algorithm preferences. Using this dataset, we trained Sound2Hap, a CNN-based autoencoder, to generate perceptually meaningful vibrations from diverse sounds with low latency. In Study 2, 15 participants rated its output higher than signal-processing baselines on both audio-vibration match and Haptic Experience Index (HXI), finding it more harmonious with diverse sounds. This work demonstrates a perceptually validated approach to audio-haptic translation, broadening the reach of sound-driven haptics.
Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery. Existing MEG- and EEG-based methods, while scalable, continue to suffer from high word error rates driven by relatively low signal-to-noise ratios compared to invasive recordings. We propose physiological noise augmentation (PNA), a data augmentation method that explicitly trains decoders to become invariant to task-agnostic artifacts (e.g. ocular and cardiac activity). PNA draws inspiration from automatic speech recognition systems, where environmental noise (e.g. dogs barking, city traffic) is added to clean speech to improve robustness. Analogously, we decompose brain recordings into clean data and noise artifacts using independent component analysis (ICA), before scaling and remixing to generate biophysically realistic, label-preserving training examples. We show that PNA approximates anisotropic regularization, penalizing decoder sensitivity along artifact-dominated directions. On MegNIST, a 12k-trial imagined-digit MEG dataset, PNA with 10-trial averaging improves EEGNet decoding accuracy by 4.7 percentage points (absolut
Ficus maxima (Moraceae, subgenus Pharmacosycea), known in Brazil as "caxinguba", occurs in northern Brazil and in Mato Grosso. Its leaves and fruits are important food sources for birds and mammals, and the species is traditionally used by Indigenous peoples of Central and South America to treat intestinal parasites, gingivitis, internal inflammation, and snakebites. Despite its medicinal relevance, studies on its chemistry and biological properties are still limited. This work aimed to characterize the chemical constituents of F. maxima leaves and stem bark using UPLC-MS-MS and to evaluate the antinociceptive activity and CYP1A inhibition of ethanolic extracts and fractions. Plant material collected in Abaetetuba, Para (October 2013), was extracted and fractionated by silica gel column chromatography. UPLC-MS-MS analyses in positive and negative ion modes enabled putative metabolite identification supported by MS/MS libraries and molecular networking on GNPS. A total of 45 metabolites were identified, including flavonoids, triterpenes, coumarins, polyunsaturated fatty acids, amino acids, and alkaloids. Major constituents in the leaf extract included triterpene 51, flavonoids 75 an
Speech quality and intelligibility are significantly degraded in noisy environments. This paper presents a novel transformer-based learning framework to address the single-channel noise suppression problem for real-time applications. Although existing deep learning networks have shown remarkable improvements in handling stationary noise, their performance often diminishes in real-world environments characterized by non-stationary noise (e.g., dog barking, baby crying). The proposed dual-input acoustic-image feature fusion using a hybrid ViT framework effectively models both temporal and spectral dependencies in noisy signals. Designed for real-world audio environments, the proposed framework is computationally lightweight and suitable for implementation on embedded devices. To evaluate its effectiveness, four standard and commonly used quality measurements, namely PESQ, STOI, Seg SNR, and LLR, are utilized. Experimental results obtained using the Librispeech dataset as the clean speech source and the UrbanSound8K and Google Audioset datasets as the noise sources, demonstrate that the proposed method significantly improves noise reduction, speech intelligibility, and perceptual qual
Standard classification of canine vocalisations is severely limited for assistance dogs, where sample data is sparse and variable across dogs and where capture of the full range of bark types is ethically constrained. We reframe this problem as a continuous regression task within a two-dimensional arousal-valence space. Central to our approach is an adjusted Siamese Network trained not on binary similarity, but on the ordinal and numeric distance between input sample pairs. Trained on a public dataset, our model reduces Turn-around Percentage by up to 50% on the challenging valence dimension compared to a regression baseline. Qualitative validation on a real-world dataset confirms the learned space is semantically meaningful, establishing a proof-of-concept for analysing canine barking under severe data limitations.
We perform Bayesian optimization using a Gaussian process perspective on Bayesian Additive Regression Trees (BART). Our BART Kernel (BARK) uses tree agreement to define a posterior over piecewise-constant functions, and we explore the space of tree kernels using a Markov chain Monte Carlo approach. Where BART only samples functions, the resulting BARK model obtains samples of Gaussian processes defining distributions over functions, which allow us to build acquisition functions for Bayesian optimization. Our tree-based approach enables global optimization over the surrogate, even for mixed-feature spaces. Moreover, where many previous tree-based kernels provide uncertainty quantification over function values, our sampling scheme captures uncertainty over the tree structure itself. Our experiments show the strong performance of BARK on both synthetic and applied benchmarks, due to the combination of our fully Bayesian surrogate and the optimization procedure.
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leveraging speaker assignment as an analytic tool for bias investigation. Unlike text-based models, which encode gendered associations implicitly, Speech-LLMs must produce a gendered voice, making speaker selection an explicit bias cue. We evaluate Bark, a Text-to-Speech (TTS) model, analyzing its default speaker assignments for textual prompts. If Bark's speaker selection systematically aligns with gendered associations, it may reveal patterns in its training data or model design. To test this, we construct two datasets: (i) Professions, containing gender-stereotyped occupations, and (ii) Gender-Colored Words, featuring gendered connotations. While Bark does not exhibit systematic bias, it demonstrates gender awareness and has some gender inclinations.
Aims: Over the past two decades, the rise of multidrug resistance (MDR) in bacteria has posed a significant threat to global health. The urgent need for new treatment alternatives has brought attention to the potential of plants, which harbor a wealth of unexplored phytochemicals with therapeutic properties. This study aims to evaluate the anti-bacterial efficacy of methanol and aqueous extracts from the leaves and bark of Horsfieldia iryaghedhi In vitro. Methodology: Aqueous and methanol extracts were obtained from the cold maceration method. In vitro anti-bacterial activity of methanol and aqueous leaf, bark, and combination extracts were determined against gram-negative bacteria Escherichia coli (ATCC 25922) and gram-positive bacteria Staphylococcus aureus (ATCC25923). The anti-bacterial assay for different concentrations of each extract was conducted through the well-diffusion method, with Gentamycin serving as the positive control. Results: Methanol leaf and combination extracts of Horsfieldia iryaghedhi have shown a positive anti-bacterial response at their highest concentrations of 1000mcg/mL and 500mcg/mL against grampositive bacteria Staphylococcus aureus while none of the
The precise identification of tree species is fundamental to forestry, conservation, and environmental monitoring. Though many studies have demonstrated that high accuracy can be achieved using bark-based species classification, these models often function as "black boxes", limiting interpretability, trust, and adoption in critical forestry applications. Attribution-based Explainable AI (XAI) methods have been used to address this issue in related works. However, XAI applications are often dependent on local features (such as a head shape or paw in animal applications) and cannot describe global visual features (such as ruggedness or smoothness) that are present in texture-dominant images such as tree bark. Concept-based XAI methods, on the other hand, offer explanations based on global visual features with concepts, but they tend to require large overhead in building external concept image datasets and the concepts can be vague and subjective without good means of precise quantification. To address these challenges, we propose a lightweight post-hoc method to interpret visual models for tree species classification using operators and quantifiable concepts. Our approach eliminates
Bark beetle infestations represent a serious challenge for maintaining the health of coniferous forests. This paper proposes a few-shot learning approach leveraging contrastive learning to detect bark beetle infestations using satellite PRISMA hyperspectral data. The methodology is based on a contrastive learning framework to pre-train a one-dimensional CNN encoder, enabling the extraction of robust feature representations from hyperspectral data. These extracted features are subsequently utilized as input to support vector regression estimators, one for each class, trained on few labeled samples to estimate the proportions of healthy, attacked by bark beetle, and dead trees for each pixel. Experiments on the area of study in the Dolomites show that our method outperforms the use of original PRISMA spectral bands and of Sentinel-2 data. The results indicate that PRISMA hyperspectral data combined with few-shot learning offers significant advantages for forest health monitoring.
This study accessed the antibacterial potential in vitro of hexane, chloroform and methanol extracts made from leaves, stem bark, flowers, seeds or roots of Sri Lankan grown Acronychia pedunculata plant against two Gram positive bacteria, Staphylococus aureus (ATCC 25923) and Bacilus cereus (ATCC 11778), and two Gram negative bacteria, Pseudomonas aeruginosa (ATCC 9027) and Escherichia coli (ATCC 35218), using agar disc diffusion bioassay technique. The results showed that none the of the extracts provoked an antibacterial action against the two Gram negative bacteria P. aeruginosa and E. coli. Conversely, compared to reference drug, Gentamicin, varying magnitudes of antibacterial activity (concentration: 300 mg/disc) ranging from zero to mild to moderate to strong antibacterial activity was evident with the three solvent systems made from different parts of the plant against the two Gram positive bacteria S. aureus and B. cereus. All the three flower extracts excerted marked antibacterial activity against both S. aureus and B. cereus. The highest antibacterial activity was exhibited by methanol flowers extract (inhibition zone: 13.8-0.32mm), with a Minimum inhibitory value of 32mg
Climate change has increased the vulnerability of forests to insect-related damage, resulting in widespread forest loss in Central Europe and highlighting the need for effective, continuous monitoring systems. Remote sensing based forest health monitoring, oftentimes, relies on supervised machine learning algorithms that require labeled training data. Monitoring temporal patterns through time series analysis offers a potential alternative for earlier detection of disturbance but requires substantial storage resources. This study investigates the potential of a Deep Learning algorithm based on a Long Short Term Memory (LSTM) Autoencoder for the detection of anomalies in forest health (e.g. bark beetle outbreaks), utilizing Sentinel-2 time series data. This approach is an alternative to supervised machine learning methods, avoiding the necessity for labeled training data. Furthermore, it is more memory-efficient than other time series analysis approaches, as a robust model can be created using only a 26-week-long time series as input. In this study, we monitored pure stands of spruce in Thuringia, Germany, over a 7-year period from 2018 to the end of 2024. Our best model achieved a d
Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas contextual visual cues from the surrounding environment have been overlooked: for example, when we see a dog bark, our brain has the innate ability to discern and filter out the barking noise. To this end, in this paper, we introduce a novel task, i.e. SAV-SE. To our best knowledge, this is the first proposal to use rich contextual information from synchronized video as auxiliary cues to indicate the type of noise, which eventually improves the speech enhancement performance. Specifically, we propose the VC-S$^2$E method, which incorporates the Conformer and Mamba modules for their complementary strengths. Extensive experiments are conducted on public MUSIC, AVSpeech and AudioSet datasets, where the results demonstrate the superiority of VC-S$^2$E over other competitive methods. We will make
Musical dynamics form a core part of expressive singing voice performances. However, automatic analysis of musical dynamics for singing voice has received limited attention partly due to the scarcity of suitable datasets and a lack of clear evaluation frameworks. To address this challenge, we propose a methodology for dataset curation. Employing the proposed methodology, we compile a dataset comprising 509 musical dynamics annotated singing voice performances, aligned with 163 score files, leveraging state-of-the-art source separation and alignment techniques. The scores are sourced from the OpenScore Lieder corpus of romantic-era compositions, widely known for its wealth of expressive annotations. Utilizing the curated dataset, we train a multi-head attention based CNN model with varying window sizes to evaluate the effectiveness of estimating musical dynamics. We explored two distinct perceptually motivated input representations for the model training: log-Mel spectrum and bark-scale based features. For testing, we manually curate another dataset of 25 musical dynamics annotated performances in collaboration with a professional vocalist. We conclude through our experiments that b
Attempting to apply deep learning methods to wood panels bark removal equipment to enhance the quality and efficiency of bark removal is a significant and challenging endeavor. This study develops and tests a deep learning-based wood panels bark removal equipment. In accordance with the practical requirements of sawmills, a wood panels bark removal equipment equipped with a vision inspection system is designed. Based on a substantial collection of wood panel images obtained using the visual inspection system, the first general wood panels semantic segmentation dataset is constructed for training the BiSeNetV1 model employed in this study. Furthermore, the calculation methods and processes for the essential key data required in the bark removal process are presented in detail. Comparative experiments of the BiSeNetV1 model and tests of bark removal effectiveness are conducted in both laboratory and sawmill environments. The results of the comparative experiments indicate that the application of the BiSeNetV1 segmentation model is rational and feasible. The results of the bark removal effectiveness tests demonstrate a significant improvement in both the quality and efficiency of bark