Nowadays, machine learning (ML) plays a vital role in many aspects of our daily life. In essence, building well-performing ML applications requires the provision of high-quality data throughout the entire life-cycle of such applications. Nevertheless, most of the real-world tabular data suffer from different types of discrepancies, such as missing values, outliers, duplicates, pattern violation, and inconsistencies. Such discrepancies typically emerge while collecting, transferring, storing, and/or integrating the data. To deal with these discrepancies, numerous data cleaning methods have been introduced. However, the majority of such methods broadly overlook the requirements imposed by downstream ML models. As a result, the potential of utilizing these data cleaning methods in ML pipelines is predominantly unrevealed. In this work, we introduce a comprehensive benchmark, called REIN1, to thoroughly investigate the impact of data cleaning methods on various ML models. Through the benchmark, we provide answers to important research questions, e.g., where and whether data cleaning is a necessary step in ML pipelines. To this end, the benchmark examines 38 simple and advanced error detection and repair methods. To evaluate these methods, we utilized a wide collection of ML models trained on 14 publicly-available datasets covering different domains and encompassing realistic as well as synthetic error profiles.

The goal of this study is to assess the feasibility of airway geometry as a biomarker for ASD. Chest CT images of children with a documented diagnosis of ASD as well as healthy controls were identified retrospectively. 54 scans were obtained for analysis, including 31 ASD cases and 23 age and sex-matched controls. A feature selection and classification procedure using principal component analysis (PCA) and support vector machine (SVM) achieved a peak cross validation accuracy of nearly 89% using a feature set of 8 airway branching angles. Sensitivity was 94%, but specificity was only 78%. The results suggest a measurable difference in airway branchpoint angles between children with ASD and the control population. Under review at Scientific Reports

Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments.

Recent progress in end-to-end Imitation Learning approaches has shown promising results and generalization capabilities on mobile manipulation tasks. Such models are seeing increasing deployment in real-world settings, where scaling up requires robots to be able to operate with high autonomy, i.e. requiring as little human supervision as possible. In order to avoid the need for one-on-one human supervision, robots need to be able to detect and prevent policy failures ahead of time, and ask for help, allowing a remote operator to supervise multiple robots and help when needed. However, the black-box nature of end-to-end Imitation Learning models such as Behavioral Cloning, as well as the lack of an explicit state-value representation, make it difficult to predict failures. To this end, we introduce Behavioral Cloning Value Approximation (BCVA), an approach to learning a state value function based on and trained jointly with a Behavioral Cloning policy that can be used to predict failures. We demonstrate the effectiveness of BCVA by applying it to the challenging mobile manipulation task of latched-door opening, showing that we can identify failure scenarios with with 86% precision and 81% recall, evaluated on over 2000 real world runs, improving upon the baseline of simple failure classification by 10 percentage-points.

Recent advancements in artificial intelligence (AI) have seen the emergence of smart video surveillance (SVS) in many practical applications, particularly for building safer and more secure communities in our urban environments. Cognitive tasks, such as identifying objects, recognizing actions, and detecting anomalous behaviors, can produce data capable of providing valuable insights to the community through statistical and analytical tools. However, artificially intelligent surveillance systems design requires special considerations for ethical challenges and concerns. The use and storage of personally identifiable information (PII) commonly pose an increased risk to personal privacy. To address these issues, this paper identifies the privacy concerns and requirements needed to address when designing AI-enabled smart video surveillance. Further, we propose the first end-to-end AI-enabled privacy-preserving smart video surveillance system that holistically combines computer vision analytics, statistical data analytics, cloud-native services, and end-user applications. Finally, we propose quantitative and qualitative metrics to evaluate intelligent video surveillance systems. The system shows the 17.8 frame-per-second (FPS) processing in extreme video scenes. However, considering privacy in designing such a system results in preferring the pose-based algorithm to the pixel-based one. This choice resulted in dropping accuracy in both action and anomaly detection tasks. The results drop from 97.48 to 73.72 in anomaly detection and 96 to 83.07 in the action detection task. On average, the latency of the end-to-end system is 36.1 seconds.

Remote Patient Monitoring (RPM) is an emerging technology paradigm that helps reduce clinician workload by automated monitoring and raising intelligent alarm signals. High sensitivity and intelligent data-processing algorithms used in RPM devices result in frequent false-positive alarms, resulting in alarm fatigue. This study aims to critically review the existing literature to identify the causes of these false-positive alarms and categorize the various interventions used in the literature to eliminate these causes. That act as a catalog and helps in false alarm reduction algorithm design. A step-by-step approach to building an effective alarm signal generator for clinical use has been proposed in this work. Second, the possible causes of false-positive alarms amongst RPM applications were analyzed from the literature. Third, a critical review has been done of the various interventions used in the literature depending on causes and classification based on four major approaches: clinical knowledge, physiological data, medical sensor devices, and clinical environments. A practical clinical alarm strategy could be developed by following our pentagon approach. The first phase of this approach emphasizes identifying the various causes for the high number of false-positive alarms. Future research will focus on developing a false alarm reduction method using data mining.

Manual segmentation of medical images (e.g., segmenting tumors in CT scans) is a high-effort task that can be accelerated with machine learning techniques. However, selecting the right segmentation approach depends on the evaluation function, particularly in medical image segmentation where we must deal with dependency between voxels. For instance, in contrast to classical systems where the predictions are either correct or incorrect, predictions in medical image segmentation may be partially correct and incorrect simultaneously. In this paper, we explore this expressiveness to extract the useful properties of these systems and formally define a novel multi-modal evaluation (MME) approach to measure the effectiveness of different segmentation methods. This approach improves the segmentation evaluation by introducing new relevant and interpretable characteristics, including detection property, boundary alignment, uniformity, total volume, and relative volume. Our proposed approach is open-source and publicly available for use. We have conducted several reproducible experiments, including the segmentation of pancreas, liver tumors, and multi-organs datasets, to show the applicability of the proposed approach.

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests that training using the (rescaled) square loss is often superior in terms of the classification accuracy. In this paper we propose the "squentropy" loss, which is the sum of two terms: the cross-entropy loss and the average square loss over the incorrect classes. We provide an extensive set of experiments on multi-class classification problems showing that the squentropy loss outperforms both the pure cross entropy and rescaled square losses in terms of the classification accuracy. We also demonstrate that it provides significantly better model calibration than either of these alternative losses and, furthermore, has less variance with respect to the random initialization. Additionally, in contrast to the square loss, squentropy loss can typically be trained using exactly the same optimization parameters, including the learning rate, as the standard cross-entropy loss, making it a true "plug-and-play" replacement. Finally, unlike the rescaled square loss, multiclass squentropy contains no parameters that need to be adjusted.

Model evaluation is a critical component in supervised machine learning classification analyses. Traditional metrics do not currently incorporate case difficulty. This renders the classification results unbenchmarked for generalization. Item Response Theory (IRT) and Computer Adaptive Testing (CAT) with machine learning can benchmark datasets independent of the end-classification results. This provides high levels of case-level information regarding evaluation utility. To showcase, two datasets were used: 1) health-related and 2) physical science. For the health dataset a two-parameter IRT model, and for the physical science dataset a polytonomous IRT model, was used to analyze predictive features and place each case on a difficulty continuum. A CAT approach was used to ascertain the algorithms' performance and applicability to new data. This method provides an efficient way to benchmark data, using only a fraction of the dataset (less than 1%) and 22-60x more computationally efficient than traditional metrics. This novel metric, termed Machine Learning Capability (MLC) has additional benefits as it is unbiased to outcome classification and a standardized way to make model comparisons within and across datasets. MLC provides a metric on the limitation of supervised machine learning algorithms. In situations where the algorithm falls short, other input(s) are required for decision-making.

Generalized Zero-Shot Learning (GZSL) and Open-Set Recognition (OSR) are two mainstream settings that greatly extend conventional visual object recognition. However, the limitations of their problem settings are not negligible. The novel categories in GZSL require pre-defined semantic labels, making the problem setting less realistic; the oversimplified unknown class in OSR fails to explore the innate fine-grained and mixed structures of novel categories. In light of this, we are motivated to consider a new problem setting named Zero-Knowledge Zero-Shot Learning (ZK-ZSL) that assumes no prior knowledge of novel classes and aims to classify seen and unseen samples and recover semantic attributes of the fine-grained novel categories for further interpretation. To achieve this, we propose a novel framework that recovers the clustering structures of both seen and unseen categories where the seen class structures are guided by source labels. In addition, a structural alignment loss is designed to aid the semantic learning of unseen categories with their recovered structures. Experimental results demonstrate our method's superior performance in classification and semantic recovery on four benchmark datasets.