Browse Articles

This study investigates how the hyperparameters epochs and batch size affect the classification accuracy of a convolutional neural network (CNN) trained on pulsar candidate data. Our results reveal that accuracy improves with increasing number of epochs and smaller batch sizes, suggesting that with optimized hyperparameters, high accuracy may be achievable with minimal training. These findings offer insights that could help create more efficient machine learning classification models for pulsar signal detection, with the potential of accelerating pulsar discovery and advancing astrophysical research.

Detecting cervical spondylosis using deep learning

The authors studied the impact of AI face-tracking technology on the immersiveness of videogames as an alternative to virtual reality gaming.

The authors looked at the importance of different point breakdowns needed to win in a game of tennis.

The authors studied the ability of deep learning models to predict droughts in the midwestern United States.

Here the authors introduce pressing filtration as a novel, efficient, and low-energy method for extracting dietary fiber from cabbage, which successfully retains heat-sensitive nutrients and achieves a high fiber yield. The study demonstrates the scalability and economic viability of this technique for commercial use, highlighting that the resulting high-fiber cabbage powder can be incorporated into familiar foods like hamburger buns and beef patties without compromising taste or sensory quality.

The study explored converting Gracilaria seaweed waste—known for releasing toxic hydrogen sulfide when decomposed—into biochar as a sustainable solution for waste management and soil improvement.

The authors looked at if there was any correlation between the phase of the moon and admissions for psychiatric concerns.

The authors looked at energy efficient ways to generate small nitrogenous compounds.

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.