Levy & Levy tackle the optimization of the coronary artery bypass graft, a life-saving surgical technique that treats artery blockage due to coronary heart disease. The authors develop a novel auto-suturing method that saves time, allows for an increased number of sutures, and improves graft quality over hand suturing. The authors also show that increasing the number of sutures from four to five with their new method significantly improves graft quality. These promising findings may help improve outcomes for patients undergoing surgery to treat coronary heart disease.

Here, recognizing the difficulty that visually impaired people may have differentiating United States currency, the authors sought to use artificial intelligence (AI) models to identify US currencies. With a one-stage AI they reported a test accuracy of 89%, finding that multi-level deep learning models did not provide any significant advantage over a single-level AI.

Over the last few decades, childhood stunting has persisted as a major global challenge. This study hypothesized that TPTO (Tree-based Pipeline Optimization Tool), an AutoML (automated machine learning) tool, would outperform all pre-existing machine learning models and reveal the positive impact of economic prosperity, strong familial traits, and resource attainability on reducing stunting risk. Feature correlation plots revealed that maternal height, wealth indicators, and parental education were universally important features for determining stunting outcomes approximately two years after birth. These results help inform future research by highlighting how demographic, familial, and socio-economic conditions influence stunting and providing medical professionals with a deployable risk assessment tool for predicting childhood stunting.

Reducing paint drying time is an important step in improving production efficiency and reducing costs. The authors hypothesized that decreased humidity would lead to faster drying, ultraviolet (UV) light exposure would not affect the paint colors differently, white light exposure would allow for longer wavelength colors to dry at a faster rate than shorter wavelength colors, and substrates with higher roughness would dry slower. Experiments showed that trials under high humidity dried slightly faster than trials under low humidity, contrary to the hypothesis. Overall, the paint drying process is very much dependent on its surrounding environment, and optimizing the drying process requires a thorough understanding of the environmental factors and their interactive effects with the paint constituents.

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.

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.

Buildings, which are responsible for the majority of electricity consumption in cities like Dubai, are often exclusively reliant on electrical lighting even in the presence of daylight to meet the illumination requirements of the building. This inefficient use of lighting creates potential to further optimize the energy efficiency of buildings by complementing natural light with electrical lighting. Prior research has mostly used ballasts (variable resistors) to regulate the brightness of bulbs. There has been limited research pertaining to the use of pulse width modulation (PWM) and the use of ‘triodes for alternating current’ (TRIACs). PWM and TRIACs rapidly stop and restart the flow of current to the bulb thus saving energy whilst maintaining a constant illumination level of a space. We conducted experiments to investigate the feasibility of using TRIACs and PWM in regulating the brightness of bulbs. We also established the relationship between power and brightness within the experimental setups. Our results indicate that lighting systems can be regulated through these alternate methods and that there is potential to save up to 16% of energy used without affecting the overall lighting of a given space. Since most energy used in buildings is still produced through fossil fuels, energy savings from lighting systems could contribute towards a lower carbon footprint. Our study provides an innovative solution to conserve light energy in buildings during daytime.

Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.

In this study the authors looked at the ability of artificial intelligence to detect tempo, rhythm, and intonation of a piece played on violin. Technology such as this would allow for students to practice and get feedback without the need of a teacher.

The sugar-rich modern diet underlies a suite of metabolic disorders, most common of which is diabetes. Accurately reporting the sugar content of pre-packaged food and drink items can help consumers track their sugar intake better, facilitating more cognisant and, eventually, moderate consumption of high-sugar items. In this article, the authors examine the effect of several variables on the accuracy of Fehling's reaction, a colorimetric reaction used to estimate sugar content.