Motivated by canonical problems in medical diagnostics, we propose and study properties of an objective function that uniformly bounds uncertainties in quantities of interest extracted from classifiers and related data analysis tools. We begin by adopting a set-theoretic perspective to show how two main tasks in diagnostics -- classification and prevalence estimation -- can be recast in terms of a variation on the confusion (or error) matrix ${\boldsymbol {\rm P}}$ typically considered in supervised learning. We then combine arguments from conditional probability with the Gershgorin circle theorem to demonstrate that the largest Gershgorin radius $\boldsymbol ρ_m$ of the matrix $\mathbb I-\boldsymbol {\rm P}$ (where $\mathbb I$ is the identity) yields uniform error bounds for both classification and prevalence estimation. In a two-class setting, $\boldsymbol ρ_m$ is minimized via a measure-theoretic ``water-leveling'' argument that optimizes an appropriately defined partition $U$ generating the matrix ${\boldsymbol {\rm P}}$. We also consider an example that illustrates the difficulty of generalizing the binary solution to a multi-class setting and deduce relevant properties of the confusion matrix.

Multi-class classification annotations have significantly advanced AI applications, with truth inference serving as a critical technique for aggregating noisy and biased annotations. Existing state-of-the-art methods typically model each annotator's expertise using a confusion matrix. However, these methods suffer from two widely recognized issues: 1) when most annotators label only a few tasks, or when classes are imbalanced, the estimated confusion matrices are unreliable, and 2) a single confusion matrix often remains inadequate for capturing each annotator's full expertise patterns across all tasks. To address these issues, we propose a novel confusion-matrix-based method, PTBCC (ProtoType learning-driven Bayesian Classifier Combination), to introduce a reliable and richer annotator estimation by prototype learning. Specifically, we assume that there exists a set $S$ of prototype confusion matrices, which capture the inherent expertise patterns of all annotators. Rather than a single confusion matrix, the expertise per annotator is extended as a Dirichlet prior distribution over these prototypes. This prototype learning-driven mechanism circumvents the data sparsity and class imbalance issues, ensuring a richer and more flexible characterization of annotators. Extensive experiments on 11 real-world datasets demonstrate that PTBCC achieves up to a 15% accuracy improvement in the best case, and a 3% higher average accuracy while reducing computational cost by over 90%.

Machine learning (ML) has rapidly grown in popularity, becoming vital to many industries. Currently, the research on code smells in ML applications lacks tools and studies that address the identification and validity of ML-specific code smells. This work investigates suitable methods and tools to design and develop a static code analysis tool (MLpylint) based on code smell criteria. This research employed the Design Science Methodology. In the problem identification phase, a literature review was conducted to identify ML-specific code smells. In solution design, a secondary literature review and consultations with experts were performed to select methods and tools for implementing the tool. We evaluated the tool on data from 160 open-source ML applications sourced from GitHub. We also conducted a static validation through an expert survey involving 15 ML professionals. The results indicate the effectiveness and usefulness of the MLpylint. We aim to extend our current approach by investigating ways to introduce MLpylint seamlessly into development workflows, fostering a more productive and innovative developer environment.

The increase of IoT devices, driven by advancements in hardware technologies, has led to widespread deployment in large-scale networks that process massive amounts of data daily. However, the reliance on Edge Computing to manage these devices has introduced significant security vulnerabilities, as attackers can compromise entire networks by targeting a single IoT device. In light of escalating cybersecurity threats, particularly botnet attacks, this paper investigates the application of machine learning techniques to enhance security in Edge-Computing-Assisted IoT environments. Specifically, it presents a comparative analysis of Random Forest, XGBoost, and LightGBM -- three advanced ensemble learning algorithms -- to address the dynamic and complex nature of botnet threats. Utilizing a widely recognized IoT network traffic dataset comprising benign and malicious instances, the models were trained, tested, and evaluated for their accuracy in detecting and classifying botnet activities. Furthermore, the study explores the feasibility of deploying these models in resource-constrained edge and IoT devices, demonstrating their practical applicability in real-world scenarios. The results highlight the potential of machine learning to fortify IoT networks against emerging cybersecurity challenges.

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 including major pretraining data sources and benchmarks. On this basis, we review bioacoustic foundation models by thoroughly analysing design decisions such as model architecture, pretraining scheme, and training paradigm. Additionally, we evaluate selected foundation models on classification tasks from the BEANS and BirdSet benchmarks, comparing the generalisability of learned representations under both linear and attentive probing strategies. Our comprehensive experimental analysis reveals that BirdMAE, trained on large-scale bird song data with a self-supervised objective, achieves the best performance on the BirdSet benchmark. On BEANS, BEATs$_{NLM}$, the extracted encoder of the NatureLM-audio large audio model, is slightly better. Both transformer-based models require attentive probing to extract the full performance of their representations. ConvNext$_{BS}$ and Perch models trained with supervision on large-scale bird song data remain competitive for passive acoustic monitoring classification tasks of BirdSet in linear probing settings. Training a new linear classifier has clear advantages over evaluating these models without further training. While on BEANS, the baseline model BEATs trained with self-supervision on AudioSet outperforms bird-specific models when evaluated with attentive probing. These findings provide valuable guidance for practitioners selecting appropriate models to adapt them to new bioacoustic classification tasks via probing.

--Can we teach machines to assess the expertise of humans solving visual tasks automatically based on eye tracking features? This paper proposes AutoSIGHT, Automatic System for Immediate Grading of Human experTise, that classifies expert and non-expert performers, and builds upon an ensemble of features extracted from eye tracking data while the performers were solving a visual task. Results on the task of iris Presentation Attack Detection (PAD) used for this study show that with a small evaluation window of just 5 seconds, AutoSIGHT achieves an average average Area Under the ROC curve performance of 0.751 in subject-disjoint train-test regime, indicating that such detection is viable. Furthermore, when a larger evaluation window of up to 30 seconds is available, the Area Under the ROC curve (AUROC) increases to 0.8306, indicating the model is effectively leveraging more information at a cost of slightly delayed decisions. This work opens new areas of research on how to incorporate the automatic weighing of human and machine expertise into human-AI pairing setups, which need to react dynamically to nonstationary expertise distribution between the human and AI players ( e.g., when the experts need to be replaced, or the task at hand changes rapidly). Along with this paper, we offer the eye tracking data used in this study collected from 6 experts and 53 non-experts solving iris PAD visual task. As Artificial Intelligence (AI) systems become more commonplace in everyday tasks, companies and researchers alike understand that a lack of trust in a model or the validity of a model's decision is a major obstacle to wide-scale adoption [1]. This has led to the sub-field of Trustworthy Artificial Intelligence (T AI) that focuses on defining the core principles that AI systems should satisfy to increase trust and adoption. One such principle is that good models should generalize well to unseen data types (that is, operate well in an open set recognition regime). Another principle is that there should exist a seamless and effective collaboration between the AI and humans solving the tasks jointly, in which the capabilities of both sides are appropriately and automatically assessed, and incorporated into the decision-making process.

--Multimodal Large Language Models (MLLMs) have emerged as a promising solution for universal embedding tasks, yet adapting their generative nature for discriminative representation learning remains a significant challenge. The dominant paradigm of large-scale contrastive pre-training suffers from critical inefficiencies, including prohibitive computational costs and a failure to leverage the intrinsic, instruction-following capabilities of MLLMs. T o overcome these limitations, we propose an efficient framework for universal multimodal embeddings, which bridges this gap by centering on two synergistic components. First, our hierarchical embedding prompt template employs a two-level instruction architecture that forces the model to produce discriminative representations. Building on this strong foundation, our second component, self-aware hard negative sampling, redefines the fine-tuning process by leveraging the model's own understanding to efficiently mine challenging negatives while actively filtering out potential false negatives. Our comprehensive experiments show that our hierarchical prompt achieves zero-shot performance competitive with contrastively trained baselines and enhances the fine-tuning process by lifting a simple in-batch negative baseline by 4.8 points on the MMEB benchmark. Our work presents an effective and efficient pathway to adapt MLLMs for universal embedding tasks, significantly reducing training time. Embeddings [1], [2] are fixed-dimensional representations of inputs, encoded as semantic information within a continuous vector space, underpinning various downstream tasks such as clustering [3], [4], retrieval [5]-[8], and classification [9]. Following the success of instruction-based multi-task training methods [10], [11], the focus of research has shifted toward achieving universal embeddings [12]-[14], where a single model provides robust representations across diverse tasks and domains. The rapid growth of multimedia applications has further driven the need for universal multimodal embed-dings [15]-[18] capable of supporting both uni-modal and cross-modal retrieval.

Traditional machine learning met hods, such as support vector machines (SVM), artificial neural networks (ANN), and logistic regression, have been employed to classify dates based on morphological features like color, t exture, and shape. While effective, these approaches often lack the flexibility and comprehensive quality control needed in modern agricultural practices. To address these limitations, the SmartDate system represents a significant technological advancement by integrat ing deep learning with genetic algorithms and reinforcement learning. This AI-driven system not only excels in date fruit classification but also predicts expiration dates, filling a cruci al gap in existing solutions. SmartDate leverages multispectral and hyperspectral imaging, coupled with Visible-Near-Infrared (VisNIR) spectral sensors, to assess key quality indicators such as moisture c ontent, sugar levels, firmness, and internal defects. This allows for a more thorough evaluation of fruit quality compared to co nventional methods. Moreover, the inclusion of reinforcement learning e nables SmartDate to adapt in real-time to production envir onment changes, optimizing sorting accuracy and ensuring t hat only premium quality dates reach the market.

Image-based AI models are increasingly deployed across a wide range of domains, including healthcare, security, and consumer applications. However, many image datasets carry sensitive or proprietary content, raising critical concerns about unauthorized data usage. Data owners therefore need reliable mechanisms to verify whether their proprietary data has been misused to train third-party models. Existing solutions, such as backdoor watermarking and membership inference, face inherent trade-offs between verification effectiveness and preservation of data integrity. In this work, we propose HoneyImage, a novel method for dataset ownership verification in image recognition models. HoneyImage selectively modifies a small number of hard samples to embed imperceptible yet verifiable traces, enabling reliable ownership verification while maintaining dataset integrity. Extensive experiments across four benchmark datasets and multiple model architectures show that HoneyImage consistently achieves strong verification accuracy with minimal impact on downstream performance while maintaining imperceptible. The proposed HoneyImage method could provide data owners with a practical mechanism to protect ownership over valuable image datasets, encouraging safe sharing and unlocking the full transformative potential of data-driven AI.

Modern key-value stores rely heavily on Log-Structured Merge (LSM) trees for write optimization, but this design introduces significant read amplification. Auxiliary structures like Bloom filters help, but impose memory costs that scale with tree depth and dataset size. Recent advances in learned data structures suggest that machine learning models can augment or replace these components, trading handcrafted heuristics for data-adaptive behavior. In this work, we explore two approaches for integrating learned predictions into the LSM-tree lookup path. The first uses a classifier to selectively bypass Bloom filter probes for irrelevant levels, aiming to reduce average-case query latency. The second replaces traditional Bloom filters with compact learned models and small backup filters, targeting memory footprint reduction without compromising correctness. We implement both methods atop a Monkey-style LSM-tree with leveled compaction, per-level Bloom filters, and realistic workloads. Our experiments show that the classifier reduces GET latency by up to 2.28x by skipping over 30% of Bloom filter checks with high precision, though it incurs a modest false-negative rate. The learned Bloom filter design achieves zero false negatives and retains baseline latency while cutting memory usage per level by 70-80%. Together, these designs illustrate complementary trade-offs between latency, memory, and correctness, and highlight the potential of learned index components in write-optimized storage systems.