Browse Articles

The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.

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.

Here, seeking to identify an optimal method to classify tree species through remote sensing, the authors used a few machine learning algorithms to classify forest tree species through multispectral satellite imagery. They found the Random Forest algorithm to most accurately classify tree species, with the potential to improve model training and inference based on the inclusion of other tree properties.

Coral bleaching is a fatal process that reduces coral diversity, leads to habitat loss for marine organisms, and is a symptom of climate change. This process occurs when corals expel their symbiotic dinoflagellates, algae that photosynthesize within coral tissue providing corals with glucose. Restoration efforts have attempted to repair damaged reefs; however, there are over 360,000 square miles of coral reefs worldwide, making it challenging to target conservation efforts. Thus, predicting the likelihood of bleaching in a certain region would make it easier to allocate resources for conservation efforts. We developed a machine learning model to predict global locations at risk for coral bleaching. Data obtained from the Biological and Chemical Oceanography Data Management Office consisted of various coral bleaching events and the parameters under which the bleaching occurred. Sea surface temperature, sea surface temperature anomalies, longitude, latitude, and coral depth below the surface were the features found to be most correlated to coral bleaching. Thirty-nine machine learning models were tested to determine which one most accurately used the parameters of interest to predict the percentage of corals that would be bleached. A random forest regressor model with an R-squared value of 0.25 and a root mean squared error value of 7.91 was determined to be the best model for predicting coral bleaching. In the end, the random model had a 96% accuracy in predicting the percentage of corals that would be bleached. This prediction system can make it easier for researchers and conservationists to identify coral bleaching hotspots and properly allocate resources to prevent or mitigate bleaching events.

In this paper, we measured the privacy budgets and utilities of different differentially private mechanisms combined with different machine learning models that forecast traffic congestion at future timestamps. We expected the ANNs combined with the Staircase mechanism to perform the best with every value in the privacy budget range, especially with the medium high values of the privacy budget. In this study, we used the Autoregressive Integrated Moving Average (ARIMA) and neural network models to forecast and then added differentially private Laplacian, Gaussian, and Staircase noise to our datasets. We tested two real traffic congestion datasets, experimented with the different models, and examined their utility for different privacy budgets. We found that a favorable combination for this application was neural networks with the Staircase mechanism. Our findings identify the optimal models when dealing with tricky time series forecasting and can be used in non-traffic applications like disease tracking and population growth.

In this study, the authors developed and assessed the accuracy of a machine learning algorithm to identify skin cancers using images of biopsies.

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, recognizing the vastly different opinion held regarding device usage, the authors considered the effects of technology use on middle and high school students' learning effectiveness. Using an anonymous online survey they found partial support that device use at school increases learning effectiveness, but found strong support for a negative effect of technology use at home on learning effectiveness. Based on their findings they suggest that the efficacy of technology depends on environmental context along with other important factors that need consideration.

In this study, a deep learning model is used to classify post-traumatic stress disorder patients through novel markers to assist in finding candidate biomarkers for the disorder.

The authors compared the short-term effects of processed versus unprocessed food on spatial learning and survival in zebrafish, given the large public concern regarding processed foods. By randomly assigning zebrafish to a diet of brine shrimp flakes (processed) or live brine shrimp (unprocessed), the authors show while there is no immediate effect on a fish's decision process between the two diets, there are significant correlations between improved learning and stress response with the unprocessed diet.