Accuracy is crucial for success in machine learning, but how do developers measure it? Several mathematical testing methods can reveal how accurate a machine learning model is and what types of predictions it is struggling with. The foundation of machine learning accuracy is the confusion matrix. The confusion matrix is used to compare the predictions of a machine-learning model with reality. True positives and true negatives are predictions that match reality, while false negatives and false positives are incorrect predictions.

Missing data is common in applied data science, particularly for tabular data sets found in healthcare, social sciences, and natural sciences. Most supervised learning methods only work on complete data, thus requiring preprocessing such as missing value imputation to work on incomplete data sets. However, imputation alone does not encode useful information about the missing values themselves. For data sets with informative missing patterns, the Missing Indicator Method (MIM), which adds indicator variables to indicate the missing pattern, can be used in conjunction with imputation to improve model performance. While commonly used in data science, MIM is surprisingly understudied from an empirical and especially theoretical perspective. In this paper, we show empirically and theoretically that MIM improves performance for informative missing values, and we prove that MIM does not hurt linear models asymptotically for uninformative missing values. Additionally, we find that for high-dimensional data sets with many uninformative indicators, MIM can induce model overfitting and thus test performance. To address this issue, we introduce Selective MIM (SMIM), a novel MIM extension that adds missing indicators only for features that have informative missing patterns. We show empirically that SMIM performs at least as well as MIM in general, and improves MIM for high-dimensional data. Lastly, to demonstrate the utility of MIM on real-world data science tasks, we demonstrate the effectiveness of MIM and SMIM on clinical tasks generated from the MIMIC-III database of electronic health records.

In many domains, there are many examples and far fewer labels for those examples; e.g. we may have access to millions of lines of source code, but access to only a handful of warnings about that code. In those domains, semi-supervised learners (SSL) can extrapolate labels from a small number of examples to the rest of the data. Standard SSL algorithms use ``weak'' knowledge (i.e. those not based on specific SE knowledge) such as (e.g.) co-train two learners and use good labels from one to train the other. Another approach of SSL in software analytics is potentially use ``strong'' knowledge that use SE knowledge. For example, an often-used heuristic in SE is that unusually large artifacts contain undesired properties (e.g. more bugs). This paper argues that such ``strong'' algorithms perform better than those standard, weaker, SSL algorithms. We show this by learning models from labels generated using weak SSL or our ``stronger'' FRUGAL algorithm. In four domains (distinguishing security-related bug reports; mitigating bias in decision-making; predicting issue close time; and (reducing false alarms in static code warnings), FRUGAL required only 2.5% of the data to be labeled yet out-performed standard semi-supervised learners that relied on (e.g.) some domain-independent graph theory concepts. Hence, for future work, we strongly recommend the use of strong heuristics for semi-supervised learning for SE applications. To better support other researchers, our scripts and data are on-line at https://github.com/HuyTu7/FRUGAL.

These automated decision frameworks have demonstrated various unwanted consequences as a result of biased data [11, 66-68, 84, 86, 109]. Oftentimes these systems are trained on samples (datasets) from a larger population. Biased results can arise if the sample does not accurately represent the target population, or if there is a lack of sufficient representation for subgroups within the data. While the literature of data bias in machine Learning and artificial intelligence (AI) systems is rich [99], there exists only limited work on the connections between data representativity and AI systems. Terms like representative sample are used ubiquitously in the literature, often without further specification on the details or effects of this representativity. This paper analyzes and surveys data representativity in scientific literature relating to machine learning and AI systems by investigating how different notions of representativity are used and what effects adhering to different notions of data representativity has in relation to appropriate inference. The term representative sample is an overloaded term and a generally accepted definition of what constitutes a representative sample (subset of observations) is hard to find in the literature. A few examples demonstrate that at least a couple of definitions of representative sample exist. The most general definition we found is from D'Excelle (2014) and states ""Representative sampling" is a type of statistical sampling that allows us to use data from a sample to make conclusions that are representative for the population from which the sample is taken."

A plethora of recent research has proposed several automated methods based on machine learning (ML) and deep learning (DL) to detect cybersickness in Virtual reality (VR). However, these detection methods are perceived as computationally intensive and black-box methods. Thus, those techniques are neither trustworthy nor practical for deploying on standalone VR head-mounted displays (HMDs). This work presents an explainable artificial intelligence (XAI)-based framework VR-LENS for developing cybersickness detection ML models, explaining them, reducing their size, and deploying them in a Qualcomm Snapdragon 750G processor-based Samsung A52 device. Specifically, we first develop a novel super learning-based ensemble ML model for cybersickness detection. Next, we employ a post-hoc explanation method, such as SHapley Additive exPlanations (SHAP), Morris Sensitivity Analysis (MSA), Local Interpretable Model-Agnostic Explanations (LIME), and Partial Dependence Plot (PDP) to explain the expected results and identify the most dominant features. The super learner cybersickness model is then retrained using the identified dominant features. Our proposed method identified eye tracking, player position, and galvanic skin/heart rate response as the most dominant features for the integrated sensor, gameplay, and bio-physiological datasets. We also show that the proposed XAI-guided feature reduction significantly reduces the model training and inference time by 1.91X and 2.15X while maintaining baseline accuracy. For instance, using the integrated sensor dataset, our reduced super learner model outperforms the state-of-the-art works by classifying cybersickness into 4 classes (none, low, medium, and high) with an accuracy of 96% and regressing (FMS 1-10) with a Root Mean Square Error (RMSE) of 0.03.

To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth, existing multi-camera methods often generate multiple bounding boxes along a ray of depth direction for difficult small objects such as pedestrians, resulting in an extremely low recall. Furthermore, directly applying depth prediction modules to existing multi-camera methods, generally composed of large network architectures, cannot meet the real-time requirements of self-driving applications. To address these issues, we propose Cross-view and Depth-guided Transformers for 3D Object Detection, CrossDTR. First, our lightweight depth predictor is designed to produce precise object-wise sparse depth maps and low-dimensional depth embeddings without extra depth datasets during supervision. Second, a cross-view depth-guided transformer is developed to fuse the depth embeddings as well as image features from cameras of different views and generate 3D bounding boxes. Extensive experiments demonstrated that our method hugely surpassed existing multi-camera methods by 10 percent in pedestrian detection and about 3 percent in overall mAP and NDS metrics. Also, computational analyses showed that our method is 5 times faster than prior approaches. Our codes will be made publicly available at https://github.com/sty61010/CrossDTR.

In machine learning, the selection of a promising model from a potentially large number of competing models and the assessment of its generalization performance are critical tasks that need careful consideration. Typically, model selection and evaluation are strictly separated endeavors, splitting the sample at hand into a training, validation, and evaluation set, and only compute a single confidence interval for the prediction performance of the final selected model. We however propose an algorithm how to compute valid lower confidence bounds for multiple models that have been selected based on their prediction performances in the evaluation set by interpreting the selection problem as a simultaneous inference problem. We use bootstrap tilting and a maxT-type multiplicity correction. The approach is universally applicable for any combination of prediction models, any model selection strategy, and any prediction performance measure that accepts weights. We conducted various simulation experiments which show that our proposed approach yields lower confidence bounds that are at least comparably good as bounds from standard approaches, and that reliably reach the nominal coverage probability. In addition, especially when sample size is small, our proposed approach yields better performing prediction models than the default selection of only one model for evaluation does.

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training protocols. In this work, we develop FiLM Transfer (FiT) which fulfills these requirements in the image classification setting by combining ideas from transfer learning (fixed pretrained backbones and fine-tuned FiLM adapter layers) and meta-learning (automatically configured Naive Bayes classifiers and episodic training) to yield parameter efficient models with superior classification accuracy at low-shot. The resulting parameter efficiency is key for enabling few-shot learning, inexpensive model updates for personalization, and communication efficient federated learning. We experiment with FiT on a wide range of downstream datasets and show that it achieves better classification accuracy than the leading Big Transfer (BiT) algorithm at low-shot and achieves state-of-the art accuracy on the challenging VTAB-1k benchmark, with fewer than 1% of the updateable parameters. Finally, we demonstrate the parameter efficiency and superior accuracy of FiT in distributed low-shot applications including model personalization and federated learning where model update size is an important performance metric.

Early detection of many life-threatening diseases (e.g., prostate and breast cancer) within at-risk population can improve clinical outcomes and reduce cost of care. While numerous disease-specific "screening" tests that are closer to Point-of-Care (POC) are in use for this task, their low specificity results in unnecessary biopsies, leading to avoidable patient trauma and wasteful healthcare spending. On the other hand, despite the high accuracy of Magnetic Resonance (MR) imaging in disease diagnosis, it is not used as a POC disease identification tool because of poor accessibility. The root cause of poor accessibility of MR stems from the requirement to reconstruct high-fidelity images, as it necessitates a lengthy and complex process of acquiring large quantities of high-quality k-space measurements. In this study we explore the feasibility of an ML-augmented MR pipeline that directly infers the disease sidestepping the image reconstruction process. We hypothesise that the disease classification task can be solved using a very small tailored subset of k-space data, compared to image reconstruction. Towards that end, we propose a method that performs two tasks: 1) identifies a subset of the k-space that maximizes disease identification accuracy, and 2) infers the disease directly using the identified k-space subset, bypassing the image reconstruction step. We validate our hypothesis by measuring the performance of the proposed system across multiple diseases and anatomies. We show that comparable performance to image-based classifiers, trained on images reconstructed with full k-space data, can be achieved using small quantities of data: 8% of the data for detecting multiple abnormalities in prostate and brain scans, and 5% of the data for knee abnormalities. To better understand the proposed approach and instigate future research, we provide an extensive analysis and release code.

The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with the intention of providing a user-friendly tool to dermatologists to reduce the challenges encountered or associated with manual inspection. This article aims to provide a comprehensive literature survey and review of a total of 594 publications (356 for skin lesion segmentation and 238 for skin lesion classification) published between 2011 and 2022. These articles are analyzed and summarized in a number of different ways to contribute vital information regarding the methods for the development of CAD systems. These ways include relevant and essential definitions and theories, input data (dataset utilization, preprocessing, augmentations, and fixing imbalance problems), method configuration (techniques, architectures, module frameworks, and losses), training tactics (hyperparameter settings), and evaluation criteria. We intend to investigate a variety of performance-enhancing approaches, including ensemble and post-processing. We also discuss these dimensions to reveal their current trends based on utilization frequencies. In addition, we highlight the primary difficulties associated with evaluating skin lesion segmentation and classification systems using minimal datasets, as well as the potential solutions to these difficulties. Findings, recommendations, and trends are disclosed to inform future research on developing an automated and robust CAD system for skin lesion analysis.