Browse Articles

Algorithmic trading has been increasingly used by Americans. In this work, we tested whether including the opening, closing, and highest prices in three supervised learning models affected their performance. Indeed, we found that including all three prices decreased the error of the prediction significantly.

In this study, three models are used to test the hypothesis that data-centric artificial intelligence (AI) will improve the performance of machine learning.

Here, seeking a better solution to produce downforce that keeps a vehicle grounded at high speeds than wings which tend to result in degraded car performance due to increased air resistance, the authors considered using the Magnus effect as a replacement. The authors found that a spinning cylinder generated significantly more downforce through the Magnus effect than a standard wing at all wind speeds as simulated through the use of a leaf blower. They suggest that a cylinder could be a potential replacement for a wing when downforce is a priority.

Researching gun violence and mass shootings in the U.S. is difficult due to the lack of consistent data collection. Some studies have linked mass shootings to personal financial stress, but little formal research exists on the impact of broader economic conditions. This study hypothesized an inverse relationship between mass shootings and economic performance, using the S&P 500 and unemployment rate as indicators.

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.

Brain-Computer Interface (BCI) allows users, especially those with paralysis, to control devices through brain activity. This study explored using a custom transformer model to decode neural signals into handwritten text for individuals with limited motor skills, comparing its performance to a traditional RNN-based BCI.

Additive manufacturing (AM) is transforming the production of complex metal parts, but challenges like internal cracking can arise, particularly in critical sectors such as aerospace and automotive. Traditional methods to assess cracking susceptibility are costly and time-consuming, prompting the use of machine learning (ML) for more efficient predictions. This study developed a multi-model ML pipeline that predicts solidification cracking susceptibility (SCS) more accurately by considering secondary alloy properties alongside composition, with Random Forest models showing the best performance, highlighting a promising direction for future research into SCS quantification.

Rechargeable batteries are playing an increasingly prominent role in our lives due to the ongoing transition from fossil energy sources to green energy. The purpose of this study was to investigate variables that impact the effectiveness of rechargeable batteries. Alkaline (non-rechargeable) and rechargeable batteries share common features that are critical for the operation of a battery. The positive and negative electrodes, also known as the cathode and anode, are where the energy of the battery is stored. The electrolyte is what facilitates the transfer of cations and anions in a battery to generate electricity. Due to the importance of these components, we felt that a systematic investigation examining the surface area of the cathode and anode as well the impact of electrolytes with different properties on battery performance was justified. Utilizing a copper cathode and aluminum anode coupled with a water in salt electrolyte, a model rechargeable battery system was developed to test two hypotheses: a) increasing the contact area between the electrodes and electrolyte would improve battery capacity, and b) more soluble salt-based electrolytes would improve battery capacity. After soaking in an electrolyte solution, the battery was charged and the capacity, starting voltage, and ending voltage of each battery were measured. The results of this study supported our hypothesis that larger anode/cathodes surface areas and more ionic electrolytes such as sodium chloride, potassium chloride and potassium sulfate resulted in superior battery capacity. Incorporating these findings can help maximize the efficiency of commercial rechargeable batteries.

The advent of quantum computing will pose a substantial threat to the security of classical cryptographic methods, which could become vulnerable to quantum-based attacks. In response to this impending challenge, the field of post-quantum cryptography has emerged, aiming to develop algorithms that can withstand the computational power of quantum computers. This study addressed the pressing concern of classical cryptographic methods becoming vulnerable to quantum-based attacks due to the rise of quantum computing. The emergence of post-quantum cryptography has led to the development of new resistant algorithms. Our research focused on four quantum-resistant algorithms endorsed by America’s National Institute of Standards and Technology (NIST) in 2022: CRYSTALS-Kyber, CRYSTALS-Dilithium, FALCON, and SPHINCS+. This study evaluated the security, performance, and comparative attributes of the four algorithms, considering factors such as key size, encryption/decryption speed, and complexity. Comparative analyses against each other and existing quantum-resistant algorithms provided insights into the strengths and weaknesses of each program. This research explored potential applications and future directions in the realm of quantum-resistant cryptography. Our findings concluded that the NIST algorithms were substantially more effective and efficient compared to classical cryptographic algorithms. Ultimately, this work underscored the need to adapt cryptographic techniques in the face of advancing quantum computing capabilities, offering valuable insights for researchers and practitioners in the field. Implementing NIST-endorsed quantum-resistant algorithms substantially reduced the vulnerability of cryptographic systems to quantum-based attacks compared to classical cryptographic methods.

Given an association between nicotine addiction and gene expression, we hypothesized that expression of genes commonly associated with smoking status would have variable expression between smokers and non-smokers. To test whether gene expression varies between smokers and non-smokers, we analyzed two publicly-available datasets that profiled RNA gene expression from brain (nucleus accumbens) and lung tissue taken from patients identified as smokers or non-smokers. We discovered statistically significant differences in expression of dozens of genes between smokers and non-smokers. To test whether gene expression can be used to predict whether a patient is a smoker or non-smoker, we used gene expression as the training data for a logistic regression or random forest classification model. The random forest classifier trained on lung tissue data showed the most robust results, with area under curve (AUC) values consistently between 0.82 and 0.93. Both models trained on nucleus accumbens data had poorer performance, with AUC values consistently between 0.65 and 0.7 when using random forest. These results suggest gene expression can be used to predict smoking status using traditional machine learning models. Additionally, based on our random forest model, we proposed KCNJ3 and TXLNGY as two candidate markers of smoking status. These findings, coupled with other genes identified in this study, present promising avenues for advancing applications related to the genetic foundation of smoking-related characteristics.