Online computer science (CS) courses have broadened access to CS education, yet inclusivity barriers persist for minoritized groups in these courses. One problem that recent research has shown is that often inclusivity biases (“inclusivity bugs”) lurk within the course materials themselves, disproportionately disadvantaging minoritized students. To address this issue, we investigated how a faculty member can use AID—an Automated Inclusivity Detector tool—to remove such inclusivity bugs from a large online CS1 (Intro CS) course and what is the impact of the resulting inclusivity fixes on the students’ experiences. To enable this evaluation, we first needed to (Bugs): investigate inclusivity challenges students face in 5 online CS courses; (Build): build decision rules to capture these challenges in courseware (“inclusivity bugs”) and implement them in the AID tool; (Faculty): investigate how the faculty member followed up on the inclusivity bugs that AID reported; and (Students): investigate how the faculty member’s changes impacted students’ experiences via a before-vs-after qualitative study with CS students. Our results from (Bugs) revealed 39 inclusivity challenges spanning courseware components from the syllabus to assignments. After implementing the rules in the tool (Build), our results from (Faculty) revealed how the faculty member treated AID more as a “peer” than an authority in deciding whether and how to fix the bugs. Finally, the study results with (Students) revealed that students found the after-fix courseware more approachable - feeling less overwhelmed and more in control in contrast to the before-fix version where they constantly felt overwhelmed, often seeking external assistance to understand course content.

This paper proposes a novel data-driven technique, namely Online Learning for sensor Fault diagnosis Analysis (OLFA), to perform real-time fault analysis for autonomous cars. Considering the non-stationary properties of real-time sensor faults and the mapping relationship between sensors and feature variables, the proposed method decomposes the sensor fault diagnosis analysis problem into an online data stream classification and feature ranking problems. To detect and identify faults, a clustering-based data stream classification approach is developed to continuously capture and classify non-stationary sensor faults for autonomous cars with little intervention from human experts. An effective active learning method is extended and embedded into the proposed framework to minimize the need for prior knowledge about faults and enable the continual learning capability to adapt to and handle the non-stationary properties of sensor faults. Moreover, the proposed framework addresses the parameter optimization issue of existing machine learning based fault analysis techniques and employs feature ranking analysis to systematically analyze the possible source(s) of sensor faults. CAR Learning to Act (CARLA), a well-known realistic autonomous driving simulator, is used as the benchmark to perform the sensor fault injection and online data stream collection to evaluate the efficacy of OLFA. Analysis of the collected faulty datasets and experimental results, and comparison between OLFA and several state-of-the-art clustering-based approaches for fault classification, demonstrated the efficacy of the proposed framework in the domain of autonomous cars.

The non-stationary nature of data streams strongly challenges traditional machine learning techniques. Although some solutions have been proposed to extend traditional machine learning techniques for handling data streams, these approaches either require an initial label set or rely on specialized design parameters. The overlap among classes and the labeling of data streams constitute other major challenges for classifying data streams. In this paper, we proposed a clustering-based data stream classification framework to handle non-stationary data streams without utilizing an initial label set. A density-based stream clustering procedure is used to capture novel concepts with a dynamic threshold and an effective active label querying strategy is introduced to continuously learn the new concepts from the data streams. The sub-cluster structure of each cluster is explored to handle the overlap among classes. Experimental results and quantitative comparison studies reveal that the proposed method provides statistically better or comparable performance than the existing methods.

Standard Convolutional Neural Network (CNN) designs rarely focus on the importance of explicitly capturing diverse features to enhance the network’s performance. Instead, most existing methods follow an indirect approach of increasing or tuning the networks’ depth and width, which in many cases significantly increase the computational cost. Inspired by biological visual system, we proposes a Diverse and Adaptive Attention Convolutional Network (DA2-Net), which enables any feed-forward CNNs to explicitly capture diverse features and adaptively select and emphasize the most informative features to efficiently boost the network’s performance. DA2-Net incurs negligible computational overhead and it is designed to be easily integrated with any CNN architecture. We extensively evaluated DA2-Net on benchmark datasets, including CIFAR100, SVHN, and ImageNet, with various CNN architectures. The experimental results show DA2-Net provides a significant performance improvement with very minimal computational overhead.

Feature selection methods are widely used to address the high computational overheads and curse of dimensionality in classifying high-dimensional data. Most conventional feature selection methods focus on handling homogeneous features, while real-world datasets usually have a mixture of continuous and discrete features. Some recent mixed-type feature selection studies only select features with high relevance to class labels and ignore the redundancy among features. The determination of an appropriate feature subset is also a challenge. In this paper, a supervised feature selection method using density-based feature clustering (SFSDFC) is proposed to obtain an appropriate final feature subset for mixed-type data. SFSDFC decomposes the feature space into a set of disjoint feature clusters using a novel density-based clustering method. Then, an effective feature selection strategy is employed to obtain a subset of important features with minimal redundancy from those feature clusters. Extensive experiments as well as comparison studies with five state-of-the-art methods are conducted on SFSDFC using thirteen real-world benchmark datasets and results justify the efficacy of the SFSDFC method.