Browse Articles

The authors design and test an easy-to-use and cost-effective mobile app-based alert system to help senior citizens rapidly communicate with caregivers in emergencies or when in need of assistance.

The authors develop a method for detecting fake AI-generated images from real images.

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.

Recent advances in generative AI have made it increasingly hard to distinguish real images from AI-generated ones. Traditional detection models using CNNs or U-net architectures lack precision because they overlook key spatial and frequency domain details. This study introduced a hybrid model combining Convolutional Neural Networks (CNN) with Fast Fourier Transform (FFT) to better capture subtle edge and texture patterns.

The authors investigate how well AI-detection machine learning models can detect real versus AI-generated art across different art styles.

Here, the authors investigated methods to reduce noise in audio composed of real-word sounds. They specifically used two spectral subtraction noise reduction algorithms: stationary and non-stationary finding notable differences in noise improvements depending on the noise sources.

The authors looked at the ability of machine learning algorithms to interpret language given their increasing use in moderating content on social media. Using an explainable model they were able to achieve 81% accuracy in detecting fake vs. real news based on language of posts alone.

Powered by the sociological framework that exposure to television bleeds into social biases, limiting media representation of women and minority groups may lead to real-world implications and manifestations of racial and gender disparities. To address this phenomenon, the researchers in this article take a look at primetime fictional representation of minorities and women as lawyers and physicians and compare television representation to census data of the same groups within real-world legal and medical occupations. The authors maintain the hypothesis that representation of female and minority groups as television lawyers and doctors is lower than that of their white male counterparts relative to population demographics - a trend that they expect to also be reflected in actual practice. With fictional racial and gender inequalities and corresponding real-world trends highlighted within this article, the researchers call for address towards representation biases that reinforce each other in both fictional and non-fictional spheres.

In their attempt to evoke a greater emotional connection with viewers, animators have strived to replicate human movements in their animations. However, animation movements still appear distinct from human movements. With a focus on walking, we hypothesized that animations, unaffected by real external forces (e.g. gravity), would move with a universally distinct, gliding gait that is discernible from humans.

Zoos offer educational and scientific advantages but face high maintenance costs and challenges in animal care due to diverse species' habits. Challenges include tracking animals, detecting illnesses, and creating suitable habitats. We developed a deep learning framework called SmartZoo to address these issues and enable efficient animal monitoring, condition alerts, and data aggregation. We discovered that the data generated by our model is closer to real data than random data, and we were able to demonstrate that the model excels at generating data that resembles real-world data.