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.

Humans have a natural ability to recognize emotional cues from the facial expressions of others, as a crucial evolutionary trait to navigate social interactions. This ability likely develops through normal development and social experience, but it is unclear how much influence age and sex have in emotional facial recognition (EFR). In this study, the authors investigate EFR in children and teenagers, and look at whether accurate emotional recognition does occur more in males or females.

Here, seeking to better understand how facial features provide important visual cues to help convey emotions, the authors evaluated the accuracy and reaction time of participants in regards to experimental photographs where a person's eyebrows were obscured and ones where they were not. Their findings revealed that removing eyebrows resulted in a significant decrease in a participant's ability to recognize anger, with adolescents most likely to misidentify emotions.

In this study, the authors tested the ability and accuracy of a neural net to identify patterns in complex number matrices.

In this study the authors develop an app for faster chess game entry method to help chess learners improve their game. This culminated in the Augmented Reality Chess Analyzer (ARChessAnalyzer) which uses traditional image and vision techniques for chess board recognition and Convolutional Neural Networks (CNN) for chess piece recognition.

Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

Modern artificial neural networks have been remarkably successful in various applications, from speech recognition to computer vision. However, it remains less clear whether they can implement abstract concepts, which are essential to generalization and understanding. To address this problem, the authors investigated the above vs. below task, a simple concept-based task that honeybees can solve, using a conventional neural network. They found that networks achieved 100% test accuracy when a visual target was presented below a black bar, however only 50% test accuracy when a visual target was presented below a reference shape.

The impact of age on mental health is a crucial yet understudied aspect of public health. While mental health is gaining recognition as a vital component of overall well-being, its correlation with age remains largely unexplored. In Canada, where the median age has risen significantly over the past half-century, understanding this relationship becomes increasingly pertinent. Researchers hypothesized that older adults would exhibit lower rates of mental health disorders and report better perceived mental health due to increased emotional stability and maturity.

The mountain chain of the Western Ghats on the Indian peninsula, a UNESCO World Heritage site, is home to about 200 frog species, 89 of which are endemic. Distinctive to each frog species, their vocalizations can be used for species recognition. Manually surveying frogs at night during the rain in elephant and big cat forests is difficult, so being able to autonomously record ambient soundscapes and identify species is essential. An effective machine learning (ML) species classifier requires substantial training data from this area. The goal of this study was to assess data augmentation techniques on a dataset of frog vocalizations from this region, which has a minimal number of audio recordings per species. Consequently, enhancing an ML model’s performance with limited data is necessary. We analyzed the effects of four data augmentation techniques (Time Shifting, Noise Injection, Spectral Augmentation, and Test-Time Augmentation) individually and their combined effect on the frog vocalization data and the public environmental sounds dataset (ESC-50). The effect of combined data augmentation techniques improved the model's relative accuracy as the size of the dataset decreased. The combination of all four techniques improved the ML model’s classification accuracy on the frog calls dataset by 94%. This study established a data augmentation approach to maximize the classification accuracy with sparse data of frog call recordings, thereby creating a possibility to build a real-world automated field frog species identifier system. Such a system can significantly help in the conservation of frog species in this vital biodiversity hotspot.

Molecules which bind to proteins that aggregate abnormally in neurodegenerative diseases could be promising drugs for these diseases. In this study, Zhang, Wu, Zhang, and Dang simulate the binding behavior of various molecules to screen for candidates which could be promising candidates for drug development.