In this paper, error estimates of classification Random Forests are quantitatively assessed. Based on the initial theoretical framework built by Bates et al. (2023), the true error rate and expected error rate are theoretically and empirically investigated in the context of a variety of error estimation methods common to Random Forests. We show that in the classification case, Random Forests' estimates of prediction error is closer on average to the true error rate instead of the average prediction error. This is opposite the findings of Bates et al. (2023) which were given for logistic regression. We further show that this result holds across different error estimation strategies such as cross-validation, bagging, and data splitting.

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory demands. In addition, the efficiency of a deep ensemble is related to diversity among the ensemble members which is challenging for large, over-parameterized deep neural networks. Moreover, ensemble learning has not yet seen such widespread adoption, and it remains a challenging endeavor for self-supervised or unsupervised representation learning. Motivated by these challenges, we present a novel self-supervised training regime that leverages an ensemble of independent sub-networks, complemented by a new loss function designed to encourage diversity. Our method efficiently builds a sub-model ensemble with high diversity, leading to well-calibrated estimates of model uncertainty, all achieved with minimal computational overhead compared to traditional deep self-supervised ensembles. To evaluate the effectiveness of our approach, we conducted extensive experiments across various tasks, including in-distribution generalization, out-of-distribution detection, dataset corruption, and semi-supervised settings. The results demonstrate that our method significantly improves prediction reliability. Our approach not only achieves excellent accuracy but also enhances calibration, surpassing baseline performance across a wide range of self-supervised architectures in computer vision, natural language processing, and genomics data.

Software development projects rely on issue tracking systems at the core of tracking maintenance tasks such as bug reports, and enhancement requests. Incoming issue-reports on these issue tracking systems must be managed in an effective manner. First, they must be labelled and then assigned to a particular developer with relevant expertise. This handling of issue-reports is critical and requires thorough scanning of the text entered in an issue-report making it a labor-intensive task. In this paper, we present a unified framework called MaintainoMATE, which is capable of automatically categorizing the issue-reports in their respective category and further assigning the issue-reports to a developer with relevant expertise. We use the Bidirectional Encoder Representations from Transformers (BERT), as an underlying model for MaintainoMATE to learn the contextual information for automatic issue-report labeling and assignment tasks. We deploy the framework used in this work as a GitHub application. We empirically evaluate our approach on GitHub issue-reports to show its capability of assigning labels to the issue-reports. We were able to achieve an F1-score close to 80\%, which is comparable to existing state-of-the-art results. Similarly, our initial evaluations show that we can assign relevant developers to the issue-reports with an F1 score of 54\%, which is a significant improvement over existing approaches. Our initial findings suggest that MaintainoMATE has the potential of improving software quality and reducing maintenance costs by accurately automating activities involved in the maintenance processes. Our future work would be directed towards improving the issue-assignment module.

A vast number of systems across the world use algorithmic decision making (ADM) to (partially) automate decisions that have previously been made by humans. When designed well, these systems promise more objective decisions while saving large amounts of resources and freeing up human time. However, when ADM systems are not designed well, they can lead to unfair decisions which discriminate against societal groups. The downstream effects of ADMs critically depend on the decisions made during the systems' design and implementation, as biases in data can be mitigated or reinforced along the modeling pipeline. Many of these design decisions are made implicitly, without knowing exactly how they will influence the final system. It is therefore important to make explicit the decisions made during the design of ADM systems and understand how these decisions affect the fairness of the resulting system. To study this issue, we draw on insights from the field of psychology and introduce the method of multiverse analysis for algorithmic fairness. In our proposed method, we turn implicit design decisions into explicit ones and demonstrate their fairness implications. By combining decisions, we create a grid of all possible "universes" of decision combinations. For each of these universes, we compute metrics of fairness and performance. Using the resulting dataset, one can see how and which decisions impact fairness. We demonstrate how multiverse analyses can be used to better understand variability and robustness of algorithmic fairness using an exemplary case study of predicting public health coverage of vulnerable populations for potential interventions. Our results illustrate how decisions during the design of a machine learning system can have surprising effects on its fairness and how to detect these effects using multiverse analysis.

Emergency department (ED) crowding is a significant threat to patient safety and it has been repeatedly associated with increased mortality. Forecasting future service demand has the potential patient outcomes. Despite active research on the subject, several gaps remain: 1) proposed forecasting models have become outdated due to quick influx of advanced machine learning models (ML), 2) amount of multivariable input data has been limited and 3) discrete performance metrics have been rarely reported. In this study, we document the performance of a set of advanced ML models in forecasting ED occupancy 24 hours ahead. We use electronic health record data from a large, combined ED with an extensive set of explanatory variables, including the availability of beds in catchment area hospitals, traffic data from local observation stations, weather variables, etc. We show that N-BEATS and LightGBM outpeform benchmarks with 11 % and 9 % respective improvements and that DeepAR predicts next day crowding with an AUC of 0.76 (95 % CI 0.69-0.84). To the best of our knowledge, this is the first study to document the superiority of LightGBM and N-BEATS over statistical benchmarks in the context of ED forecasting.

Worldwide, many millions of people die suddenly and unexpectedly each year, either with or without a prior history of cardiovascular disease. Such events are sparse (once in a lifetime), many victims will not have had prior investigations for cardiac disease and many different definitions of sudden death exist. Accordingly, sudden death is hard to predict. This analysis used NHS Electronic Health Records (EHRs) for people aged $\geq$50 years living in the Greater Glasgow and Clyde (GG\&C) region in 2010 (n = 380,000) to try to overcome these challenges. We investigated whether medical history, blood tests, prescription of medicines, and hospitalisations might, in combination, predict a heightened risk of sudden death. We compared the performance of models trained to predict either sudden death or all-cause mortality. We built six models for each outcome of interest: three taken from state-of-the-art research (BEHRT, Deepr and Deep Patient), and three of our own creation. We trained these using two different data representations: a language-based representation, and a sparse temporal matrix. We used global interpretability to understand the most important features of each model, and compare how much agreement there was amongst models using Rank Biased Overlap. It is challenging to account for correlated variables without increasing the complexity of the interpretability technique. We overcame this by clustering features into groups and comparing the most important groups for each model. We found the agreement between models to be much higher when accounting for correlated variables. Our analysis emphasises the challenge of predicting sudden death and emphasises the need for better understanding and interpretation of machine learning models applied to healthcare applications.

Minimizing error in prevalence estimates and diagnostic classifiers remains a challenging task in serology. In theory, these problems can be reduced to modeling class-conditional probability densities (PDFs) of measurement outcomes, which control all downstream analyses. However, this task quickly succumbs to the curse of dimensionality, even for assay outputs with only a few dimensions (e.g. target antigens). To address this problem, we propose a technique that uses empirical training data to classify samples and estimate prevalence in arbitrary dimension without direct access to the conditional PDFs. We motivate this method via a lemma that relates relative conditional probabilities to minimum-error classification boundaries. This leads us to formulate an optimization problem that: (i) embeds the data in a parameterized, curved space; (ii) classifies samples based on their position relative to a coordinate axis; and (iii) subsequently optimizes the space by minimizing the empirical classification error of pure training data, for which the classes are known. Interestingly, the solution to this problem requires use of a homotopy-type method to stabilize the optimization. We then extend the analysis to the case of impure training data, for which the classes are unknown. We find that two impure datasets suffice for both prevalence estimation and classification, provided they satisfy a linear independence property. Lastly, we discuss how our analysis unifies discriminative and generative learning techniques in a common framework based on ideas from set and measure theory. Throughout, we validate our methods in the context of synthetic data and a research-use SARS-CoV-2 enzyme-linked immunosorbent (ELISA) assay.

A covariance matrix estimator using two bits per entry was recently developed by Dirksen, Maly and Rauhut [Annals of Statistics, 50(6), pp. 3538-3562]. The estimator achieves near minimax rate for general sub-Gaussian distributions, but also suffers from two downsides: theoretically, there is an essential gap on operator norm error between their estimator and sample covariance when the diagonal of the covariance matrix is dominated by only a few entries; practically, its performance heavily relies on the dithering scale, which needs to be tuned according to some unknown parameters. In this work, we propose a new 2-bit covariance matrix estimator that simultaneously addresses both issues. Unlike the sign quantizer associated with uniform dither in Dirksen et al., we adopt a triangular dither prior to a 2-bit quantizer inspired by the multi-bit uniform quantizer. By employing dithering scales varying across entries, our estimator enjoys an improved operator norm error rate that depends on the effective rank of the underlying covariance matrix rather than the ambient dimension, thus closing the theoretical gap. Moreover, our proposed method eliminates the need of any tuning parameter, as the dithering scales are entirely determined by the data. Experimental results under Gaussian samples are provided to showcase the impressive numerical performance of our estimator. Remarkably, by halving the dithering scales, our estimator oftentimes achieves operator norm errors less than twice of the errors of sample covariance.

Cyclostationarity involves periodic statistical variations in signals and processes, commonly used in signal analysis and network security. In the context of attacks, cyclostationarity helps detect malicious behaviors within network traffic, such as traffic patterns in Distributed Denial of Service (DDoS) attacks or hidden communication channels in malware. This approach enhances security by identifying abnormal patterns and informing Network Intrusion Detection Systems (NIDSs) to recognize potential attacks, enhancing protection against both known and novel threats. This research focuses on identifying cyclostationary malware behavior and its detection. The main goal is to pinpoint essential cyclostationary features used in NIDSs. These features are extracted using algorithms such as Boruta and Principal Component Analysis (PCA), and then categorized to find the most significant cyclostationary patterns. The aim of this article is to reveal periodically changing malware behaviors through cyclostationarity. The study highlights the importance of spotting cyclostationary malware in NIDSs by using established datasets like KDD99, NSL-KDD, and the UGRansome dataset. The UGRansome dataset is designed for anomaly detection research and includes both normal and abnormal network threat categories of zero-day attacks. A comparison is made using the Random Forest (RF) and Support Vector Machine (SVM) algorithms, while also evaluating the effectiveness of Boruta and PCA. The findings show that PCA is more promising than using Boruta alone for extracting cyclostationary network feature patterns. Additionally, the analysis identifies the internet protocol as the most noticeable cyclostationary feature pattern used by malware. Notably, the UGRansome dataset outperforms the KDD99 and NSL-KDD, achieving 99% accuracy in signature malware detection using the RF algorithm and 98% with the SVM.

Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We established an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculated an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies.