Machine learning assisted fast prediction of inertial lift in microchannels

Lab on a Chip ◽  
2021 ◽  
Author(s):  
Jinghong Su ◽  
Xiaodong Chen ◽  
Yongzheng Zhu ◽  
Guoqing Hu
Keyword(s):  
Machine Learning ◽  
Microfluidic Devices ◽  
Particle Migration ◽  
Inertial Effect ◽  
Microfluidic Platforms ◽  
Precise Prediction ◽  
Fast Prediction

Inertial effect has been extensively used in manipulating both engineered particles and biocolloids in microfluidic platforms. The design of inertial microfluidic devices largely relies on precise prediction of particle migration...

scholarly journals Disposable Voltammetric Immunosensors Integrated with Microfluidic Platforms for Biomedical, Agricultural and Food Analyses: A Review

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4124 ◽  
Author(s):  
Fabiana Felix ◽  
Alexandre Baccaro ◽  
Lúcio Angnes
Keyword(s):  
Quality Management ◽  
Signal Amplification ◽  
Screen Printing ◽  
Point Of Care ◽  
Microfluidic Devices ◽  
Strong Interactions ◽  
Point Of Care Testing ◽  
Microfluidic Platforms ◽  
Broad Variety ◽  
Interesting Alternative

Disposable immunosensors are analytical devices used for the quantification of a broad variety of analytes in different areas such as clinical, environmental, agricultural and food quality management. They detect the analytes by means of the strong interactions between antibodies and antigens, which provide concentration-dependent signals. For the herein highlighted voltammetric immunosensors, the analytical measurements are due to changes in the electrical signals on the surface of the transducers. The possibility of using disposable and miniaturized immunoassays is a very interesting alternative for voltammetric analyses, mainly, when associated with screen-printing technologies (screen-printed electrodes, SPEs), and microfluidic platforms. The aim of this paper is to discuss a carefully selected literature about different examples of SPEs-based immunosensors associated with microfluidic technologies for diseases, food, agricultural and environmental analysis. Technological aspects of the development of the voltammetric immunoassays such as the signal amplification, construction of paper-based microfluidic platforms and the utilization of microfluidic devices for point-of-care testing will be presented as well.

Better Performance with Transformer: CPPFormer in precise prediction of cell-Penetrating Peptides

2021 ◽  
Vol 28 ◽  
Author(s):  
Yuyang Xue ◽  
Xiucai Ye ◽  
Lesong Wei ◽  
Xin Zhang ◽  
Tetsuya Sakurai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Cell Penetrating Peptides ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Practical Applications ◽  
Deep Model ◽  
Cell Penetrating ◽  
Precise Prediction ◽  
Transformer Model

: With its superior performance, the Transformer model, which is based on the 'Encoder-Decoder' paradigm, has become the mainstream in natural language processing. On the other hand, bioinformatics has embraced machine learning and made great progress in drug design and protein property prediction. Cell-penetrating peptides (CPPs) are one kind of permeable protein that is convenient as a kind of 'postman' in drug penetration tasks. However, a small number of CPPs have been discovered by research, let alone practical applications in drug permeability. Therefore, correctly identifying the CPPs has opened up a new way to take macromolecules into cells without other potentially harmful materials in the drug. Most of the previous work only uses trivial machine learning techniques and hand-crafted features to construct a simple classifier. In CPPFormer, we learn from the idea of implementing the attention structure of Transformer, rebuilding the network based on the characteristics of CPPs according to its short length, and using an automatic feature extractor with a few manual engineered features to co-direct the predicted results. Compared to all previous methods and other classic text classification models, the empirical result has shown that our proposed deep model-based method has achieved the best performance of 92.16% accuracy in the CPP924 dataset and has passed various index tests.

Skin-interfaced microfluidic devices with one-opening chambers and hydrophobic valves for sweat collection and analysis

Lab on a Chip ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 2635-2645 ◽  
Author(s):  
Yingxue Zhang ◽  
Yao Chen ◽  
Jielong Huang ◽  
Yangchengyi Liu ◽  
Jinfeng Peng ◽  
...  
Keyword(s):  
Microfluidic Devices ◽  
Microfluidic Platforms ◽  
Sweat Loss ◽  
Essential Insight ◽  
Insight Into ◽  
Sweat Collection

Soft, skin-interfaced microfluidic platforms are capable of capturing, storing, and assessing sweat chemistry and total sweat loss, which provides essential insight into human physiological health.

scholarly journals Agricultural loan delinquency prediction using machine learning methods

2021 ◽  
pp. 1-16
Author(s):  
Jian Chen ◽  
Ani L. Katchova ◽  
Chenxi Zhou
Keyword(s):  
Machine Learning ◽  
Deposit Insurance ◽  
Agricultural Sector ◽  
Financial Stress ◽  
Economic Downturn ◽  
Bayes Classifier ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Precise Prediction ◽  
Federal Deposit Insurance

The recent economic downturn in the agricultural sector that started in 2013 has caused some concerns for farmers’ repayment capacity, which raises the need for precise prediction of financial stress in the agricultural sector. Machine learning has been shown to improve predictions with large financial data, however, its application remains limited in the agricultural sector. In this study, we approximate financial stress by agricultural loan delinquency, and predict it by employing a logistic regression and several machine learning methods. The main datasets include the Call Reports and Summary of Deposits from the Federal Deposit Insurance Corporation (FDIC). Our results show that ensemble learning methods have the best performance in prediction accuracy, with improvement of 26 percentage points at most and that the Naïve Bayes classifier is the best method to maintain the lowest cost from false predictions when the failure of identifying potentially high-risk loans is very costly. From the perspective of banks, while there are important benefits to using machine learning, the bank-level costs are also important considerations that may lead to different choices of machine learning methods.

scholarly journals Machine learning model for fast prediction of the natural frequencies of protein molecules

RSC Advances ◽  
2020 ◽  
Vol 10 (28) ◽  
pp. 16607-16615
Author(s):  
Zhao Qin ◽  
Qingyi Yu ◽  
Markus J. Buehler
Keyword(s):  
Machine Learning ◽  
Natural Frequencies ◽  
Protein Structures ◽  
Learning Model ◽  
Natural Vibrations ◽  
Existing Structures ◽  
Machine Learning Model ◽  
Protein Molecules ◽  
Fast Prediction

Natural vibrations and resonances are intrinsic features of protein structures and can be learnt from existing structures.

Microtiter Plate-Based Microfluidic Platforms: Sealing, Leakage Testing, and Performance of a 96-Well SPRI Device

2006 ◽  
Author(s):  
D. S. Park ◽  
M. Hupert ◽  
J. Guy ◽  
P. Datta ◽  
J.-B. Lee ◽  
...  
Keyword(s):  
High Throughput ◽  
Mold Insert ◽  
Microfluidic Devices ◽  
Microtiter Plate ◽  
Thickness Variation ◽  
Large Area ◽  
Microfluidic Platforms ◽  
Effective Manner ◽  
Micro Molding ◽  
Microtiter Plate Format

Highly parallelized biochemical analysis is a significant step toward achieving high throughput processing of patient samples for diagnosis and treatment monitoring. The standard microtiter plate is used to carry out multiple reactions for high throughput screening. By incorporating polymer microfluidic devices at each well in the microtiter plate format, the capability of the format could be significantly enhanced for high throughput processing of large numbers of biochemical samples in a cost-effective manner. Low cost replication of the microtiter plates is done using micro molding techniques, so microfabrication technology for making large area mold inserts (LAMIs) containing microfluidic devices at each well of a microtiter plate format is needed. A large area mold insert (LAMI) in the footprint of the standard microtiter plate was fabricated using an SU-8 based UV-LIGA technique. Excellent lithography results, with vertical sidewalls, were obtained by utilizing flycutting to minimize SU-8 film thickness variation and a UV filter for attenuating high absorbance UV wavelengths. Overplating of nickel in the SU-8 polymeric molds was used to make high quality metallic mold inserts with vertical sidewalls. Micro molding of polycarbonate (PC) was done using hot embossing, resulting in good replication fidelity over the large surface area. Thermal fusion bonding of the molded PC chips yielded good sealing results and the developed polymer microfluidic platforms showed good fluidic uniformity.

Sign in / Sign up

Export Citation Format

Share Document