Coffee is one of the most valuable primary commodities. Despite this, the common selection technique of green coffee beans relies on personnel visual inspection, which is labor-intensive and subjective. Therefore, an efficient way to evaluate the quality of beans is needed. In this paper, we demonstrate a site-independent approach to find site-specific color features of the seed coat in qualified green coffee beans. We then propose two evaluation schemes for green coffee beans based on this site-specific color feature of qualified beans. Due to the site-specific properties of these color features, machine learning classifiers indicate that compared with the existing evaluation schemes of beans, our evaluation schemes have the advantages of being simple, having less computational costs, and having universal applicability. Finally, this site-specific color feature can distinguish qualified beans from different growing sites. Moreover, this function can prevent cheating in the coffee business and is unique to our evaluation scheme of beans.
Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to leak tokens generated by an LLM. By co-locating an attack process on the same hardware as the victim model, we flush and reload embedding vectors from the embedding layer, where each token corresponds to a unique embedding vector. When accessed during token generation, it results in a cache hit detectable by our attack on shared lower-level caches. A significant challenge is the massive size of LLMs, which, by nature of their compute intensive operation, quickly evicts embedding vectors from the cache. We address this by balancing the number of tokens monitored against the amount of information leaked. Monitoring more tokens increases potential vocabulary leakage but raises the chance of missing cache hits due to eviction; monitoring fewer tokens improves detection reliability but limits vocabulary coverage. Through extensive experimentation, we demonstrate the feasibility of leaking tokens from LLMs via cache side-channels. Our findings reveal a ne
Amidst growing food production demands, early plant disease detection is essential to safeguard crops; this study proposes a visual machine learning approach for plant disease detection, harnessing RGB and NIR data collected in real-world conditions through a JAI FS-1600D-10GE camera to build an RGBN dataset. A two-stage early plant disease detection model with YOLOv8 and a sequential CNN was used to train on a dataset with partial labels, which showed a 3.6% increase in mAP compared to a single-stage end-to-end segmentation model. The sequential CNN model achieved 90.62% validation accuracy utilising RGBN data. An average of 6.25% validation accuracy increase is found using RGBN in classification compared to RGB using ResNet15 and the sequential CNN models. Further research and dataset improvements are needed to meet food production demands.
Abeans [1] (wide-interface accelerator Java beans developed at JSI) have in the past been used with great success in control applications at ANKA and ESO and on test cases at the SLS and Riken. At DESY, TINE [2] is used as the principal control system for HERA as well as the intercommunication protocol among the HERA experiments. To date, most TINE-based client-side applications have been written using ACOP [3] (a narrow-interface accelerator component) in Visual Basic (VB), which has provided a remarkably powerful developing environment for generating professional control applications. Currently, however, VB control applications can only run on Windows-based desktop machines and consoles. As it is often desirable to provide certain control applications on non-Windows platforms (or indeed over the Web), we have created an equally powerful developing environment based on Java and the next release of Abeans, where an ACOP-like narrow-interface bean has been developed. Like ACOP, the Abean itself accepts plugs from various communication protocols, but was brought to fruition at DESY using the TINE Java class. Details concerning matching Abeans and TINE, as well as the pros and cons of
The use of machine learning (ML) based techniques has become increasingly popular in the field of bioacoustics over the last years. Fundamental requirements for the successful application of ML based techniques are curated, agreed upon, high-quality datasets and benchmark tasks to be learned on a given dataset. However, the field of bioacoustics so far lacks such public benchmarks which cover multiple tasks and species to measure the performance of ML techniques in a controlled and standardized way and that allows for benchmarking newly proposed techniques to existing ones. Here, we propose BEANS (the BEnchmark of ANimal Sounds), a collection of bioacoustics tasks and public datasets, specifically designed to measure the performance of machine learning algorithms in the field of bioacoustics. The benchmark proposed here consists of two common tasks in bioacoustics: classification and detection. It includes 12 datasets covering various species, including birds, land and marine mammals, anurans, and insects. In addition to the datasets, we also present the performance of a set of standard ML methods as the baseline for task performance. The benchmark and baseline code is made publicl
Plant breeders and agricultural researchers can increase crop productivity by identifying desirable features, disease resistance, and nutritional content by analysing the Dry Bean dataset. This study analyses and compares different Support Vector Machine (SVM) classification algorithms, namely linear, polynomial, and radial basis function (RBF), along with other popular classification algorithms. The analysis is performed on the Dry Bean Dataset, with PCA (Principal Component Analysis) conducted as a preprocessing step for dimensionality reduction. The primary evaluation metric used is accuracy, and the RBF SVM kernel algorithm achieves the highest Accuracy of 93.34%, Precision of 92.61%, Recall of 92.35% and F1 Score as 91.40%. Along with adept visualization and empirical analysis, this study offers valuable guidance by emphasizing the importance of considering different SVM algorithms for complex and non-linear structured datasets.
With advances in the field of machine learning, precisely algorithms for recommendation systems, robot assistants are envisioned to become more present in the hospitality industry. Additionally, the COVID-19 pandemic has also highlighted the need to have more service robots in our everyday lives, to minimise the risk of human to-human transmission. One such example would be coffee shops, which have become intrinsic to our everyday lives. However, serving an excellent cup of coffee is not a trivial feat as a coffee blend typically comprises rich aromas, indulgent and unique flavours and a lingering aftertaste. Our work addresses this by proposing a computational model which recommends optimal coffee beans resulting from the user's preferences. Specifically, given a set of coffee bean properties (objective features), we apply different supervised learning techniques to predict coffee qualities (subjective features). We then consider an unsupervised learning method to analyse the relationship between coffee beans in the subjective feature space. Evaluated on a real coffee beans dataset based on digitised reviews, our results illustrate that the proposed computational model gives up to
Take a large bag of black and white beans, with all possible proportions considered initially equally likely, and imagine to make random extractions with reintroduction. Twenty consecutive observations of black make us highly confident that the next bean will be black too. On the contrary, the observation of 1010 black beans and 990 white ones leads us to judge the two possible outcomes about equally probable. According to C.S. Peirce this reasoning violates what he called "rule of balancing reasons", because the difference of "arguments" in favor and against the outcome of black is 20 in both cases. Why? (I.e. why does that rule not apply here?)
Effects of a third rank permeability term in chiral solids are studied. Fluid flow through such materials acquires vorticity upon emergence from the material. Materials of interest include chiral surface lattices such as the gyroid, chiral rib lattices, and granular materials comprised of sugar crystals, quartz sand, wheat or beans. A characteristic length scale is associated with the chirality. The length scale can be obtained by several methods. Contacts with nonlocal permeability, elasticity and piezoelectricity are explored.
Automated bioacoustic analysis is essential for biodiversity monitoring and conservation, requiring advanced deep learning models that can adapt to diverse bioacoustic tasks. This article presents a comprehensive review of large-scale pretrained bioacoustic foundation models and systematically investigates their transferability across multiple bioacoustic classification tasks. We overview bioacoustic representation learning by analysing pretraining data sources and benchmarks. On this basis, we review bioacoustic foundation models, dissecting the models' training data, preprocessing, augmentations, architecture, and training paradigm. Additionally, we conduct an extensive empirical study of selected models on the BEANS and BirdSet benchmarks, evaluating generalisability under linear and attentive probing. Our experimental analysis reveals that Perch~2.0 achieves the highest BirdSet score (restricted evaluation) and the strongest linear probing result on BEANS, building on diverse multi-taxa supervised pretraining; that BirdMAE is the best model among probing-based strategies on BirdSet and second on BEANS after BEATs$_{NLM}$, the encoder of NatureLM-audio; that attentive probing is
This study focuses on the coffee chain of Sultan Kudarat - the coffee capital of the Philippines, where most of the farmers are smallholders. Coffee farmers in this area allocate their harvested cherries as fresh cherries, dried cherries, and green coffee beans to five market outlets: Nestle Philippines, local traders, association, direct selling, and other markets not mentioned (e.g., coffee shops and hotels). Hence, a supply chain network design (SCND) model and simulation are developed to investigate the changes in the profits of coffee farmers as they market their products, whether to be sold as fresh cherries, dried cherries, or processed into green coffee beans before marketing to the market outlets mentioned above, based on the average annual costs affecting the production, primary processing, and market prices of coffee products. Assuming that the annual coffee yield per tree and the average prices of coffee products in different markets are constant, the simulations show that farmers can gain a positive annual profit if they sell all dried cherries. However, results show that if farmers decide to produce and sell all green coffee beans, the farmers gain a negative profit d
Accurate and resource-efficient automated diagnosis is a cornerstone of modern agricultural expert systems. While Convolutional Neural Networks (CNNs) have established benchmarks in plant pathology, their ability to capture long-range spatial dependencies is often limited by standard pooling layers, and their high memory footprint hinders deployment on portable devices. This paper proposes a lightweight hybrid CNN-LSTM system for bean leaf disease classification. By integrating an LSTM layer to model the spatial-sequential relationships within feature maps, our hybrid architecture achieves a 94.38% accuracy while maintaining an exceptionally small footprint of 1.86 MB; a 70% reduction in size compared to traditional CNN-based systems. Furthermore, we provide a systematic evaluation of image augmentation strategies, demonstrating that tailored transformations are superior to generic combinations for maintaining the integrity of diagnostic patterns. Results on the $\textit{ibean}$ dataset confirm that the proposed system achieves state-of-the-art F1 scores of 99.22% with EfficientNet-B7+LSTM, providing a robust and scalable framework for real-time agricultural decision support in res
In recent years there have been growing concerns about the proper evaluation of physical properties of superconductors, in particular for quantities extracted from magnetic characterizations. Errors can and often do occur due to the following issues: i) several measurement instruments still use Gaussian & cgs-emu units instead of the preferable International System (SI) units; ii) there are decades of valuable publications where, however, equations were expressed in Gaussian & cgs-emu or other unit systems or where constants were normalized to unity, which requires proper understanding and unit conversion in order to correctly evaluate the measured physical quantities; iii) the conversion between unit systems sometimes appears challenging and may not be properly performed. In this paper we will describe how to properly convert physical quantities relevant for the evaluation of magnetic and other properties focusing on the still most used unit systems, SI and Gaussian & cgs-emu. We will provide examples of how to properly verify and understand the physical formulae. We will include examples for the correct method to determine the critical current density Jc of a supercon
In this study, we evaluate the efficacy of the Mamba architecture bioacoustics by introducing BioMamba, a Mamba-based audio representation model for wildlife sounds. We pre-train a BioMamba using self-supervised learning on a large audio corpus and evaluate it on the BEANS benchmark across diverse classification and detection tasks. Compared to the state-of-the-art Transformer-based model (AVES), BioMamba achieves comparable performance while significantly reducing VRAM consumption. Our results demonstrate Mamba's potential as a computationally efficient alternative for real-world environmental monitoring.
Cocoa bean quality assessment is essential for ensuring compliance with commercial standards, protecting consumer health, and increasing the market value of the cocoa product. The quality assessment estimates key physicochemical properties, such as fermentation level, moisture content, polyphenol concentration, and cadmium content, among others. This assessment has traditionally relied on the accurate estimation of these properties via visual or sensory evaluation, jointly with laboratory-based physicochemical analyses, which are often time-consuming, destructive, and difficult to scale. This creates the need for rapid, reliable, and noninvasive alternatives. Spectroscopy, particularly in the visible and near-infrared ranges, offers a non-invasive alternative by capturing the molecular signatures associated with these properties. Therefore, this work introduces a scalable methodology for evaluating the quality of cocoa beans by predicting key physicochemical properties from the spectral signatures of cocoa beans. This approach utilizes a conveyor belt system integrated with a VIS-NIR spectrometer, coupled with learning-based regression models. Furthermore, a dataset is built using
Backward error analysis offers a method for assessing the quality of numerical programs in the presence of floating-point rounding errors. However, techniques from the numerical analysis literature for quantifying backward error require substantial human effort, and there are currently no tools or automated methods for statically deriving sound backward error bounds. To address this gap, we propose Bean, a typed first-order programming language designed to express quantitative bounds on backward error. Bean's type system combines a graded coeffect system with strict linearity to soundly track the flow of backward error through programs. We prove the soundness of our system using a novel categorical semantics, where every Bean program denotes a triple of related transformations that together satisfy a backward error guarantee. To illustrate Bean's potential as a practical tool for automated backward error analysis, we implement a variety of standard algorithms from numerical linear algebra in Bean, establishing fine-grained backward error bounds via typing in a compositional style. We also develop a prototype implementation of Bean that infers backward error bounds automatically. Ou
Green Bean is a rare type of galaxy which represents a short-lived phase in the life cycle of active galactic nuclei (AGN), characterised by large-scale, powerful ionised clouds in the circumgalactic medium. Recent studies demonstrate that these extended ionised structures may reflect fading signatures of past AGN activity, often manifested in the form of large-scale ionisation cones. The analysis of their observational properties provides unique constraints on AGN lifetimes, feedback mechanisms, and transitions between radiative and kinetic modes of activity. In this paper we announce the first results of the project dedicated to the long-slit spectroscopic and scanning Fabry-Perot interferometric observations of Green Bean galaxies at the Russian 6-m telescope with SCORPIO-2 multi-mode instrument. We describe the data reduction and spectral fitting procedures that allow one to characterise ionisation conditions in extended gaseous regions of the galaxy SDSSJ095100.54+051026.7.
The geometry of a billiard boundary fundamentally governs its dynamics, ranging from integrable to mixed and fully chaotic regimes. Bean- and peanut-shaped billiards have varying curvature with both focusing and defocusing walls without a neutral segments. Particle dynamics inside these billiards show a strong correlation between classical and quantum dynamics in the chaotic regime also. This fundamental observation comes from our study of classical tools like Lyapunov exponent, Poincaré sections, flow trajectories in phase space and quantum tools that includes both statistical and dynamical measures. Statistical indicators include nearest-neighbour spacing distributions, level-spacing ratios, and the spectral staircase function, while dynamical measures include out-of-time-order correlators and spectral complexity. The dynamics in both of these billiard systems also exhibit eigenfunction scarring, an unexpected phenomenon observed in chaotic systems. Overall, our results provide a unified perspective on billiard systems with non-uniform curvature.
A matrix random walk is a stochastic process of the form $B_k = (I+A_1)\cdots(I+A_k)$ where $A_j$ are independent ``step'' matrices in $\mathrm{M}_N(\mathbb{C})$. With the right entry-covariance, a rescaled matrix random walk converges to Brownian motion $B(t)$ on a matrix Lie group. In this paper, we study the eigenvalues of such rescaled matrix random walks, as $N\to\infty$ and $k\to\infty$. The standard Brownian motion $W(t)$ on $\mathrm{M}_N(\mathbb{C})$ has independent Gaussian entries at each $t$. It is bi-invariant: mutiplying on the left or right by a unitary does not change the distribution. We prove that the empirical eigenvalue distribution of any matrix random walk $B_k$ with bi-invariant steps $A_j$ and initial distribution converges (for fixed $k$ as $N\to\infty$) to a probability measure on $\mathbb{C}$: the Brown measure of the free probability $\ast$-distribution limit $b_k$ of the random walk. If the steps $A_j$ are identically distributed with normalized Hilbert--Schmidt norm $\|A_j\|_2 = t$, the limit law of eigenvalues is supported on a compact ``lima bean'' shaped region. We explicitly compute the limit measure and region, and characterize their phase transiti
Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for transfer learning. In this new release, Perch 2.0, we expand from training exclusively on avian species to a large multi-taxa dataset. The model is trained with self-distillation using a prototype-learning classifier as well as a new source-prediction training criterion. Perch 2.0 obtains state-of-the-art performance on the BirdSet and BEANS benchmarks. It also outperforms specialized marine models on marine transfer learning tasks, despite having almost no marine training data. We present hypotheses as to why fine-grained species classification is a particularly robust pre-training task for bioacoustics.