Browse Articles

Collaboration beats heterogeneity: Improving federated learning-based waste classification

Chong et al. | Jul 18, 2023

Collaboration beats heterogeneity: Improving federated learning-based waste classification

Based on the success of deep learning, recent works have attempted to develop a waste classification model using deep neural networks. This work presents federated learning (FL) for a solution, as it allows participants to aid in training the model using their own data. Results showed that with less clients, having a higher participation ratio resulted in less accuracy degradation by the data heterogeneity.

Read More...

Comparing the Effectiveness of Popular Treatments for Swelling and Scarring

Benavides et al. | Jul 08, 2020

Comparing the Effectiveness of Popular Treatments for Swelling and Scarring

Numerous specialty treatments claim to reduce swelling and scarring; however, it is unknown if these treatments are more effective than less expensive treatments. In an attempt to determine if one outperforms the other, treatments were applied to the same subject following bilateral orthopedic foot surgery. No difference was found the specialty treatments compared to more cost-effective treatments.

Read More...

Exploring a Possible Link Between ADHD and Inattentional Blindness

Younger et al. | Dec 21, 2020

Exploring a Possible Link Between ADHD and Inattentional Blindness

Attention Deficit Hyperactivity Disorder (ADHD) is characterized by impulsivity, hyperactivity, and inattention. The authors hypothesized that people with ADHD would display more inattentional blindness in perceptually simple tasks and less inattentional blindness in perceptually complex tasks. The results indicate that there is no significant correlation between ADHD and inattentional blindness in either type of task.

Read More...

Similarity Graph-Based Semi-supervised Methods for Multiclass Data Classification

Balaji et al. | Sep 11, 2021

Similarity Graph-Based Semi-supervised Methods for Multiclass Data Classification

The purpose of the study was to determine whether graph-based machine learning techniques, which have increased prevalence in the last few years, can accurately classify data into one of many clusters, while requiring less labeled training data and parameter tuning as opposed to traditional machine learning algorithms. The results determined that the accuracy of graph-based and traditional classification algorithms depends directly upon the number of features of each dataset, the number of classes in each dataset, and the amount of labeled training data used.

Read More...

Wind Resistance and Automobile Shapes

Neelakantan et al. | Jan 25, 2019

Wind Resistance and Automobile Shapes

Energy efficiency is becoming more important as we struggle to find better, more sustainable energy sources to power our planet; the car industry is no exception. In this article, the authors examine the effect of shape on automobile aerodynamics By finding the shape that makes cars less resistant to wind, and therefore more energy efficient, can help the automobile industry make better, more eco-friendly cars that are also cheaper to operate.

Read More...

Machine Learning Algorithm Using Logistic Regression and an Artificial Neural Network (ANN) for Early Stage Detection of Parkinson’s Disease

Kar et al. | Oct 10, 2020

Machine Learning Algorithm Using Logistic Regression and an Artificial Neural Network (ANN) for Early Stage Detection of Parkinson’s Disease

Despite the prevalence of PD, diagnosing PD is expensive, requires specialized testing, and is often inaccurate. Moreover, diagnosis is often made late in the disease course when treatments are less effective. Using existing voice data from patients with PD and healthy controls, the authors created and trained two different algorithms: one using logistic regression and another employing an artificial neural network (ANN).

Read More...

The association between hunting and the feeding and vigilance times of American bison in North Dakota and Montana

McCandless et al. | Mar 30, 2022

The association between hunting and the feeding and vigilance times of American bison in North Dakota and Montana

This study hypothesized that feeding times of bison in the hunted populations would be significantly shorter than that of bison in the nonhunted population and vigilance times would be significantly longer than that of bison in the nonhunted population. Notably, the results found significant differences in feeding and vigilance times of bison in the hunted and non-hunted populations. However, these differences did not support the original hypothesis; bison in hunted populations spent more time feeding and less time vigilant than bison in the non-hunted population. Future studies investigating the association between hunting and bison behaviors could use populations of bison that are hunted more frequently, which may provide different results.

Read More...

Search Articles

Search articles by title, author name, or tags

Clear all filters

Popular Tags

Browse by school level