Medical machine learning algorithms are typically evaluated based on accuracy vs. a clinician-defined ground truth, a reasonable initial choice since trained clinicians are usually better classifiers than ML models. However, this metric does not fully capture the actual clinical task: it neglects the fact that humans, even with perfect accuracy, are subject to non-trivial error from the Poisson statistics of rare events, because clinical protocols often specify a relatively small sample size. For example, to quantitate malaria on a thin blood film a clinician examines only 2000 red blood cells (0.0004 uL), which can yield large Poisson variation in the actual number of parasites present, so that a perfect human's count can differ substantially from the true average load. In contrast, an ML system may be less accurate on an object level, but it may also have the option to examine more blood (e.g. 0.1 uL, or 250x). Then while its parasite identification error is higher, the Poisson variability of its estimate is lower due to larger sample size. To qualify for clinical deployment, an ML system's performance must match current standard of care, typically a very demanding target. To achieve this, it may be possible to offset the ML system's lower accuracy by increasing its sample size to reduce Poisson error, and thus attain the same net clinical performance as a perfectly accurate human limited by smaller sample size. In this paper, we analyse the mathematics of the relationship between Poisson error, classification error, and total error. This mathematical toolkit enables teams optimizing ML systems to leverage a relative strength (larger sample sizes) to offset a relative weakness (classification accuracy). We illustrate the methods with two concrete examples: diagnosis and quantitation of malaria on blood films.

Almost all classification methods such as XGBoost [1], Random Forest [2], Logistic Regression [3] are able to produce probability estimates. Output thresholding is a process to tune the decision threshold which is later used to assign class predictions based on a model's probability estimates for instances during inference [4]. For binary classification tasks, instances with probability estimates higher than or equal to the threshold are assigned positives class, otherwise as negative which is depicted in Table 1. Adjusting the threshold is particularly important for imbalanced classification problems where the train datasets have a smaller number of samples in the minority classes compared to the other classes. Output thresholding is one of the methods to address class imbalance problem [5]. Since the distribution of classes is skewed and probability estimates often favor the majority class, using a default classification threshold of 0.5 may not be the most effective approach for such problems [6]. Therefore it is essential to perform a search for the threshold to use during inference. Output thresholding is also considered to address class imbalance problem for convolutional neural networks [7].

Forests are crucial for ecological balance, but wildfires, a major cause of forest loss, pose significant risks. Fire weather indices, which assess wildfire risk and predict resource demands, are vital. With the rise of sensor networks in fields like healthcare and environmental monitoring, semantic sensor networks are increasingly used to gather climatic data such as wind speed, temperature, and humidity. However, processing these data streams to determine fire weather indices presents challenges, underscoring the growing importance of effective forest fire detection. This paper discusses using Apache Spark for early forest fire detection, enhancing fire risk prediction with meteorological and geographical data. Building on our previous development of Semantic Sensor Network (SSN) ontologies and Semantic Web Rules Language (SWRL) for managing forest fires in Monesterial Natural Park, we expanded SWRL to improve a Decision Support System (DSS) using a Large Language Models (LLMs) and Spark framework. We implemented real-time alerts with Spark streaming, tailored to various fire scenarios, and validated our approach using ontology metrics, query-based evaluations, LLMs score precision, F1 score, and recall measures.

In this paper, we propose a novel feature weighting method to address the limitation of existing feature processing methods for tabular data. Typically the existing methods assume equal importance across all samples and features in one dataset. This simplified processing methods overlook the unique contributions of each feature, and thus may miss important feature information. As a result, it leads to suboptimal performance in complex datasets with rich features. To address this problem, we introduce Tabular Feature Weighting with Transformer, a novel feature weighting approach for tabular data. Our method adopts Transformer to capture complex feature dependencies and contextually assign appropriate weights to discrete and continuous features. Besides, we employ a reinforcement learning strategy to further fine-tune the weighting process. Our extensive experimental results across various real-world datasets and diverse downstream tasks show the effectiveness of TFWT and highlight the potential for enhancing feature weighting in tabular data analysis.

In the e-commerce domain, the accurate extraction of attribute-value pairs from product listings (e.g., Brand: Apple) is crucial for enhancing search and recommendation systems. The automation of this extraction process is challenging due to the vast diversity of product categories and their respective attributes, compounded by the lack of extensive, accurately annotated training datasets and the demand for low latency to meet the real-time needs of e-commerce platforms. To address these challenges, we introduce GenToC, a novel two-stage model for extracting attribute-value pairs from product titles. GenToC is designed to train with partially-labeled data, leveraging incomplete attribute-value pairs and obviating the need for a fully annotated dataset. Moreover, we introduce a bootstrapping method that enables GenToC to progressively refine and expand its training dataset. This enhancement substantially improves the quality of data available for training other neural network models that are typically faster but are inherently less capable than GenToC in terms of their capacity to handle partially-labeled data. By supplying an enriched dataset for training, GenToC significantly advances the performance of these alternative models, making them more suitable for real-time deployment. Our results highlight the unique capability of GenToC to learn from a limited set of labeled data and to contribute to the training of more efficient models, marking a significant leap forward in the automated extraction of attribute-value pairs from product titles. GenToC has been successfully integrated into India's largest B2B e-commerce platform, IndiaMART.com, achieving a significant increase of 21.1% in recall over the existing deployed system while maintaining a high precision of 89.5% in this challenging task.

The classification of statements provided by individuals during police interviews is a complex and significant task within the domain of natural language processing (NLP) and legal informatics. The lack of extensive domain-specific datasets raises challenges to the advancement of NLP methods in the field. This paper aims to address some of the present challenges by introducing a novel dataset tailored for classification of statements made during police interviews, prior to court proceedings. Utilising the curated dataset for training and evaluation, we introduce a fine-tuned DistilBERT model that achieves state-of-the-art performance in distinguishing truthful from deceptive statements. To enhance interpretability, we employ explainable artificial intelligence (XAI) methods to offer explainability through saliency maps, that interpret the model's decision-making process. Lastly, we present an XAI interface that empowers both legal professionals and non-specialists to interact with and benefit from our system. Our model achieves an accuracy of 86%, and is shown to outperform a custom transformer architecture in a comparative study. This holistic approach advances the accessibility, transparency, and effectiveness of statement analysis, with promising implications for both legal practice and research.

In this work, we explore idiomatic language processing with Large Language Models (LLMs). We introduce the Idiomatic language Test Suite IdioTS, a new dataset of difficult examples specifically designed by language experts to assess the capabilities of LLMs to process figurative language at sentence level. We propose a comprehensive evaluation methodology based on an idiom detection task, where LLMs are prompted with detecting an idiomatic expression in a given English sentence. We present a thorough automatic and manual evaluation of the results and an extensive error analysis.

Text classification is a fundamental task in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field. This paper introduces the Smart Expert System, a novel approach that leverages LLMs as text classifiers. The system simplifies the traditional text classification workflow, eliminating the need for extensive preprocessing and domain expertise. The performance of several LLMs, machine learning (ML) algorithms, and neural network (NN) based structures is evaluated on four datasets. Results demonstrate that certain LLMs surpass traditional methods in sentiment analysis, spam SMS detection and multi-label classification. Furthermore, it is shown that the system's performance can be further enhanced through few-shot or fine-tuning strategies, making the fine-tuned model the top performer across all datasets. Source code and datasets are available in this GitHub repository: https://github.com/yeyimilk/llm-zero-shot-classifiers.

We introduce a heuristic to test the significance of fit of Self-Validated Ensemble Models (SVEM) against the null hypothesis of a constant response. A SVEM model averages predictions from nBoot fits of a model, applied to fractionally weighted bootstraps of the target dataset. It tunes each fit on a validation copy of the training data, utilizing anti-correlated weights for training and validation. The proposed test computes SVEM predictions centered by the response column mean and normalized by the ensemble variability at each of nPoint points spaced throughout the factor space. A reference distribution is constructed by refitting the SVEM model to nPerm randomized permutations of the response column and recording the corresponding standardized predictions at the nPoint points. A reduced-rank singular value decomposition applied to the centered and scaled nPerm x nPoint reference matrix is used to calculate the Mahalanobis distance for each of the nPerm permutation results as well as the jackknife (holdout) Mahalanobis distance of the original response column. The process is repeated independently for each response in the experiment, producing a joint graphical summary. We present a simulation driven power analysis and discuss limitations of the test relating to model flexibility and design adequacy. The test maintains the nominal Type I error rate even when the base SVEM model contains more parameters than observations.

The behavior of neural networks (NNs) on previously unseen types of data (out-of-distribution or OOD) is typically unpredictable. This can be dangerous if the network's output is used for decision-making in a safety-critical system. Hence, detecting that an input is OOD is crucial for the safe application of the NN. Verification approaches do not scale to practical NNs, making runtime monitoring more appealing for practical use. While various monitors have been suggested recently, their optimization for a given problem, as well as comparison with each other and reproduction of results, remain challenging. We present a tool for users and developers of NN monitors. It allows for (i) application of various types of monitors from the literature to a given input NN, (ii) optimization of the monitor's hyperparameters, and (iii) experimental evaluation and comparison to other approaches. Besides, it facilitates the development of new monitoring approaches. We demonstrate the tool's usability on several use cases of different types of users as well as on a case study comparing different approaches from recent literature.