The authors combine fine needle aspiration biopsy and machine learning algorithms to develop a breast cancer detection method suitable for resource-constrained regions that lack access to mammograms.
Read More...Applying machine learning to breast cancer diagnosis: A high school student’s exploration using R
The authors combine fine needle aspiration biopsy and machine learning algorithms to develop a breast cancer detection method suitable for resource-constrained regions that lack access to mammograms.
Read More...Tree-Based Learning Algorithms to Classify ECG with Arrhythmias
Arrhythmias vary in type and treatment, and ECGs are used to detect them, though human interpretation can be inconsistent. The researchers tested four tree-based algorithms (gradient boosting, random forest, decision tree, and extra trees) on ECG data from over 10,000 patients.
Read More...Comparing neural networks with a traditional method for identifying the vanishing points of surgical tools
Robot-assisted minimally invasive surgery (RMIS) benefits from increased precision and faster recovery, with force feedback from the surgical tool being critical for control. Researchers tested the use of neural networks for detecting the vanishing point of the tool, a key element for force feedback.
Read More...An exploration of western mosquitofish as the animal component in an aquaponic farming system
Aquaponics (the combination of aquatic plant farming with fish production) is an innovative farming practice, but the fish that are typically used, like tilapia, are expensive and space-consuming to cultivate. Medina and Alvarez explore other options test if mosquitofish are a viable option in the aquaponic cultivation of herbs and microgreens.
Read More...Assessing the possibility of using entomopathogenic fungi for mosquito control in Hawaii
Fungi that attack and kill insects have promise for targeting mosquitoes without the harmful environmental impacts of chemicals like DDT. To find out whether fungi might be effective in controlling mosquitoes in Hawaii, Jiang and Chan test the effects of Hawaiian fungal isolates on mosquito larvae.
Read More...Synthesis of sodium alginate composite bioplastic films
The authors looked at the development of biodegradable bioplastic and its features compared to PET packaging films. They were able to develop a biodegradable plastic with sodium alginate that dissolved in water and degrade in microbial conditions while also being transparent and flexible similar to current plastic films.
Read More...Alloferon improves the growth performance and developmental time of mealworms (Tenebrio molitor)
Mealworms (Tenebrio molitor) are important food sources for reptiles, birds, and other organisms, as well as for humans. However, the slow growth and low survival rate of mealworms cause problems for mass production. Since alloferon, a synthetic peptide, showed long-term immunological effects on mealworms, we hypothesized that alloferon would function as a growth promoter to maximize mealworm production. We discovered that the overall weight of the alloferon-containing gelatin diet group was 39.5-90% heavier, and the development time of the experimental group was shortened up to 20.6-39.6% than the control group.
Read More...The effect of an anthocyanin on the gut permeability of a Type 2 Diabetic Drosophila melanogaster
Anti-diabetic drugs like Metformin are known to increase gut permeability, and this has a negative impact on patient health. These authors hypothesized that this can be mitigated using purple sweet potato extract, which is high anthocyanin content, that feeds bacteria metabolism to decrease gut permeability.
Read More...Tomato disease identification with shallow convolutional neural networks
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.
Read More...A machine learning approach for abstraction and reasoning problems without large amounts of data
While remarkable in its ability to mirror human cognition, machine learning and its associated algorithms often require extensive data to prove effective in completing tasks. However, data is not always plentiful, with unpredictable events occurring throughout our daily lives that require flexibility by artificial intelligence utilized in technology such as personal assistants and self-driving vehicles. Driven by the need for AI to complete tasks without extensive training, the researchers in this article use fluid intelligence assessments to develop an algorithm capable of generalization and abstraction. By forgoing prioritization on skill-based training, this article demonstrates the potential of focusing on a more generalized cognitive ability for artificial intelligence, proving more flexible and thus human-like in solving unique tasks than skill-focused algorithms.
Read More...