Learned pseudo-random number generator: WGAN-GP for generating statistically robust random numbers.

Pseudo-random number generators (PRNGs) are software algorithms generating a sequence of numbers approximating the properties of random numbers. They are critical components in many information systems that require unpredictable and nonarbitrary behaviors, such as parameter configuration in machine learning, gaming, cryptography, and simulation. A PRNG is commonly validated through a statistical test suite, such as NIST SP 800-22rev1a (NIST test suite), to evaluate its robustness and the randomness of the numbers. In this paper, we propose a Wasserstein distance-based generative adversarial network (WGAN) approach to generating PRNGs that fully satisfy the NIST test suite. In this approach, the existing Mersenne Twister (MT) PRNG is learned without implementing any mathematical programming code. We remove the dropout layers from the conventional WGAN network to learn random numbers distributed in the entire feature space because the nearly infinite amount of data can suppress the overfitting problems that occur without dropout layers. We conduct experimental studies to evaluate our learned pseudo-random number generator (LPRNG) by adopting cosine-function-based numbers with poor random number properties according to the NIST test suite as seed numbers. The experimental results show that our LPRNG successfully converted the sequence of seed numbers to random numbers that fully satisfy the NIST test suite. This study opens the way for the "democratization" of PRNGs through the end-to-end learning of conventional PRNGs, which means that PRNGs can be generated without deep mathematical know-how. Such tailor-made PRNGs will effectively enhance the unpredictability and nonarbitrariness of a wide range of information systems, even if the seed numbers can be revealed by reverse engineering. The experimental results also show that overfitting was observed after about 450,000 trials of learning, suggesting that there is an upper limit to the number of learning counts for a fixed-size neural network, even when learning with unlimited data.

Growth control of leaf lettuce with exposure to underwater ultrasound and dissolved oxygen supersaturation.

The growth rate of vegetables in plant factories can be regulated by environmental factors including light, temperature, and chemicals, which might give rise to mutation in leaf health. Here, we aim to devise a new way that allows for controlling the growth rate of plants in hydroponics as well as maintaining the product quality; we apply underwater ultrasound and dissolved oxygen supersaturation as external stimuli to plants. As an example, we examine the growth of leaf lettuce in hydroponics with exposure to 28-kHz ultrasound and dissolved oxygen supersaturation up to 36 mg/L at 20 °C. Our results show that exposure to the ultrasound of peak-to-peak pressure at 20 kPa or larger works as the growth inhibitor of the leaves and the roots, while the oxygen supersaturation as the growth promoter, without any degradation of chlorophyll in the leaves. This suggests that these external stimuli can be used in the growth control system of plant factories.