Browse Articles

In this study, the authors investigate the disinfectant potential of many household spices and minerals. More specifically, they test whether these compounds can be used to disinfect mobile phones after daily use with the hope of identifying environmentally-friendly cleaning options.

The electronic health record (EHR), along with its mobile application, has demonstrated the ability to improve the efficiency and accuracy of health care delivery. This study included data from 874 health care providers over a 12-month period regarding their usage of mobile phone (EPIC® Haiku) and tablet (EPIC® Canto) mEHR. Ambulatory and inpatient care providers had the greatest usage levels over the 12-month period. Awareness of workflow allows for optimization of mEHR design and implementation, which should increase mEHR adoption and usage, leading to better health outcomes for patients.

Plant diseases can cause up to 50% crop yield loss for the popular tomato plant. A mobile device-based method to identify diseases from photos of symptomatic leaves via computer vision can be more effective due to its convenience and accessibility. To enable a practical mobile solution, a “shallow” convolutional neural networks (CNNs) with few layers, and thus low computational requirement but with high accuracy similar to the deep CNNs is needed. In this work, we explored if such a model was possible.

One of the greatest challenges we face today is the sustainable production, storage, and distribution of electrical power. One emerging technology with great promise in this area is that of metal-air fuel cells—a long-term and reusable electricity storage system made from a reactive metal anode and a saline solution. In this study the authors tested several different types of metal to determine which was the most suitable for this application. They found that a fuel cell with a magnesium anode was superior to fuel cells made from aluminum or zinc, producing a voltage and current sufficient for real-world applications such as charging a mobile phone.

Osteosarcoma is a type of bone cancer that affects young adults and children. Early diagnosis of osteosarcoma is crucial to successful treatment. The current methods of diagnosis, which include imaging tests and biopsy, are time consuming and prone to human error. Hence, we used deep learning to extract patterns and detect osteosarcoma from histological images. We hypothesized that the combination of two different technologies (transfer learning and data augmentation) would improve the efficacy of osteosarcoma detection in histological images. The dataset used for the study consisted of histological images for osteosarcoma and was quite imbalanced as it contained very few images with tumors. Since transfer learning uses existing knowledge for the purpose of classification and detection, we hypothesized it would be proficient on such an imbalanced dataset. To further improve our learning, we used data augmentation to include variations in the dataset. We further evaluated the efficacy of different convolutional neural network models on this task. We obtained an accuracy of 91.18% using the transfer learning model MobileNetV2 as the base model with various geometric transformations, outperforming the state-of-the-art convolutional neural network based approach.

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.

Here, recognizing the need to improve the efficiency of the conversion of solar energy to electrical energy, the authors used MATLAB to mathematically simulate a multi-layered thin film with an without an antireflective coating. They found that the use of alternating ZnO-SiO₂ multilayers enhanced the transmission of light into the solar cell, increasing its efficiency and reducing the reflectivity of the Si-Air interface.

Skin cancer is a common and potentially deadly form of cancer. This study’s purpose was to develop an automated approach for early detection for skin cancer. We hypothesized that convolutional neural network-based models using transfer learning could accurately differentiate between benign and malignant moles using natural images of human skin.

Globally, the cultivation of 77.8 million tons of grapes each year underscores their significance in both diets and agriculture. However, grapevines face mounting threats from diseases such as black rot, Esca, and leaf blight. Traditional detection methods often lag, leading to reduced yields and poor fruit quality. To address this, authors used machine learning, specifically deep learning with Convolutional Neural Networks (CNNs), to enhance disease detection.

While 75% of waste in the United States is stated to be recyclable, only about 34% truly is. This project takes a stance to combat the pillars of mismanaged waste through a modern means of convenience: the TracedWaste app. The purpose of this study was to identify how individuals' waste disposal habits improved and knowledge increased (i.e. correctly disposing of waste, understanding negative incorrect waste disposal) due to their use of an informational waste management app as measured by a survey using a 1-5 Likert Scale. The results showed that the TracedWaste app helped conserve abundant resources such as energy and wood, decrease carbon emissions, and minimize financial toll all through reducing individual impact.