scholarly journals Nutrient Estimation from 24-Hour Food Recalls Using Machine Learning and Database Mapping: A Case Study with Lactose

Nutrients ◽  
2019 ◽  
Vol 11 (12) ◽  
pp. 3045 ◽  
Author(s):  
Elizabeth L. Chin ◽  
Gabriel Simmons ◽  
Yasmine Y. Bouzid ◽  
Annie Kan ◽  
Dustin J. Burnett ◽  
...  
Keyword(s):  
Machine Learning ◽  
Assessment Tool ◽  
Dietary Assessment ◽  
Learning Models ◽  
Dietary Recall ◽  
Manual Curation ◽  
The Status ◽  
Food Recalls ◽  
Recall System ◽  
Machine Learning Models

The Automated Self-Administered 24-Hour Dietary Assessment Tool (ASA24) is a free dietary recall system that outputs fewer nutrients than the Nutrition Data System for Research (NDSR). NDSR uses the Nutrition Coordinating Center (NCC) Food and Nutrient Database, both of which require a license. Manual lookup of ASA24 foods into NDSR is time-consuming but currently the only way to acquire NCC-exclusive nutrients. Using lactose as an example, we evaluated machine learning and database matching methods to estimate this NCC-exclusive nutrient from ASA24 reports. ASA24-reported foods were manually looked up into NDSR to obtain lactose estimates and split into training (n = 378) and test (n = 189) datasets. Nine machine learning models were developed to predict lactose from the nutrients common between ASA24 and the NCC database. Database matching algorithms were developed to match NCC foods to an ASA24 food using only nutrients (“Nutrient-Only”) or the nutrient and food descriptions (“Nutrient + Text”). For both methods, the lactose values were compared to the manual curation. Among machine learning models, the XGB-Regressor model performed best on held-out test data (R2 = 0.33). For the database matching method, Nutrient + Text matching yielded the best lactose estimates (R2 = 0.76), a vast improvement over the status quo of no estimate. These results suggest that computational methods can successfully estimate an NCC-exclusive nutrient for foods reported in ASA24.

scholarly journals Print-and-Play Fabrication

2021 ◽  
Author(s):  
Carlos E. Tejada
Keyword(s):  
Machine Learning ◽  
Three Dimensional ◽  
Digital Fabrication ◽  
Learning Models ◽  
Fluid Behavior ◽  
The Status ◽  
Physical Shape ◽  
Dimensional Models ◽  
Three Dimensional Models ◽  
Machine Learning Models

In recent years, it has become increasingly accessible to create interactive applications on screen-based devices. Contrary to this ease, and despite their numerous benefits, creating tangible interactive devices is a task reserved for experts, requiring extensive knowledge on electronics, and manual assemblies. While digital fabrication equipment holds promise to alleviate this situation, the majority of research exploring this avenue still present significant barriers for non-experts, and other-domain experts to construct tangible devices, often requiring assembly of electronic circuits and printed parts, prohibitive fabrication pipelines, or intricate calibration of machine learning models. This thesis introduces Print-and-Play Fabrication: a digital fabrication paradigm where tangible interactive devices are printed, rather than assembled. By embedding interior structures inside three-dimensional models that leverage distinct properties of fluid behavior, this thesis presents a variety of techniques to construct tangible devices that can sense, process, and respond to user’s interactions without requiring assembly of parts, circuits, or calibration of machine learning models. Chapter 2 provides an overview of the fabrication of tangible devices literature through the lens of Print-and-Play Fabrication. This chapter highlights the post-print activities required to enable each of the efforts in the literature, and reflects on the status of the field. Chapters 3 and 4 introduce two novel techniques for constructing tangible devices that can sense user’s interactions. AirTouch uses basic principles of fluid behavior to enable the construction of touch-sensing devices, capable of detecting interactions in up to 12 locations, with an accuracy of up to 98%. Blowhole builds on this concept by employing principles of acoustic resonance to construct tangible devices that can detect where they are gently blown on. Blowhole-enabled devices can enable up to seven interactive locations, with an accuracy of up to 98%. Conversely, in Chapter 6 I introduce a technique to encapsulate logic computation into 3D-printed objects. Inspired by concepts from the Cold War era, I embed structures capable of representing basic logic operations using interacting jets of air into three-dimensional models. AirLogic takes the form of a toolkit, enabling non-expert designers to add a variety of input, logic processing, and output mechanisms to three-dimensional models. Continuing, Chapter 5 describes a toolkit for fabricating objects capable of changing their physical shape using pneumatic actuation. MorpheesPlug introduces a design environment, a set of pneumatically actuated widgets, and a control module that, in tandem, enable non[1]experts to construct devices capable of changing their physical shape in order to provide output. Last, I conclude with reflections on the status of Print-and-Play Fabrication, and possible directions for future work.

Improving XGBoost with Imagination Sampling

2020 ◽  
Vol 2 (1) ◽  
pp. 3-6
Author(s):  
Eric Holloway
Keyword(s):  
Machine Learning ◽  
General System ◽  
Learning Models ◽  
Starting Point ◽  
Machine Learning Models

Imagination Sampling is the usage of a person as an oracle for generating or improving machine learning models. Previous work demonstrated a general system for using Imagination Sampling for obtaining multibox models. Here, the possibility of importing such models as the starting point for further automatic enhancement is explored.

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Utilizing Blockchain Technology in Social Media Bot Identification

2020 ◽  
Author(s):  
Shreya Reddy ◽  
Lisa Ewen ◽  
Pankti Patel ◽  
Prerak Patel ◽  
Ankit Kundal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Gold Standard ◽  
The Internet ◽  
Learning Models ◽  
Current Time ◽  
Machine Learning Methods ◽  
Blockchain Technology ◽  
Modern Age ◽  
Machine Learning Models

<p>As bots become more prevalent and smarter in the modern age of the internet, it becomes ever more important that they be identified and removed. Recent research has dictated that machine learning methods are accurate and the gold standard of bot identification on social media. Unfortunately, machine learning models do not come without their negative aspects such as lengthy training times, difficult feature selection, and overwhelming pre-processing tasks. To overcome these difficulties, we are proposing a blockchain framework for bot identification. At the current time, it is unknown how this method will perform, but it serves to prove the existence of an overwhelming gap of research under this area.<i></i></p>

Sign in / Sign up

Export Citation Format

Share Document