Browse Articles

The authors looked at ways that autonomous vehicles could be trained to better perform in adverse weather without the use of actual images taken during adverse weather events. They were able to improve performance, but models using actual images still perform the best.

Intelligent vehicles utilize a combination of video-enabled object detection and radar data to traverse safely through surrounding environments. However, since the most momentary missteps in these systems can cause devastating collisions, the margin of error in the software for these systems is small. In this paper, we hypothesized that a novel object detection system that improves detection accuracy and speed of detection during adverse weather conditions would outperform industry alternatives in an average comparison.

Here, seeking to better understand the control algorithms used in autonomous vehicles, the authors compared the Stanley and pure pursuit control algorithms along with a new version of each. Unexpectedly, they found that no control algorithm offered optimal performance, but rather resulted in tradeoffs between the various ideal results.

With the advance of technology, artificial intelligence (AI) is now applied widely in society. In the study of AI, machine learning (ML) is a subfield in which a machine learns to be better at performing certain tasks through experience. This work focuses on the convolutional neural network (CNN), a framework of ML, applied to an image classification task. Specifically, we analyzed the performance of the CNN as the type of neural activation function changes.

The authors develop a machine learning method to reduce misclassification of objects in safety-critical applications such as medical diagnosis.

Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

Autonomous drone imaging combined with machine learning offers a promising approach for early detection of invasive species. In this study, students built an autonomous drone and compared three models: CNN, SGDC, and XGBoost, to identify Brassica nigra from aerial footage. Their results show that CNNs most effectively recognize key visual features, demonstrating strong potential for supporting conservation and invasive plant management.

Here the authors present an autonomous drone air filtration system that uses a novel algorithm, the gradient ascent ML particle filter (GA/MLPF), to efficiently locate and mitigate outdoor air pollution. They demonstrate that their GA/MLPF algorithm is significantly more efficient than the conventional gradient ascent algorithm, reducing both the time and number of waypoints needed to find the source of pollution.

Natural selection shapes the evolution of all organisms, and one question of interest is whether natural selection will reach a "stopping point": a stable, ideal, value for any particular trait. Madhan and Kanagavel tackle this question by building a computer simulation of trait evolution in organisms.

The authors train a neural network to detect text-based emotions including joy, sadness, anger, fear, love, and surprise.