|
Batch-to-batch optimization with model adaptation leveraging Gaussian processes: the case of optogenetically assisted microbial consortia |
|
Sebastian Espinel Rios(Princeton University, United States), Rudolph Kok(Otto von Guericke University Magdeburg, Germany), Steffen Klamt(Max Planck Institute for Dynamics of Complex Technical Systems, Germany), Jose L. Avalos(Princeton University, United States), Rolf Findeisen(TU Darmstadt, Germany) |
| We propose to perform open-loop optimization with batch-to-batch model adaptation based on Gaussian processes for maximizing bioproduction by optogenetically assisted consortia. The proposed approach enables knowledge transfer from existing to new models, improving predictability and optimization performance in each batch while avoiding costly and time-consuming modeling experiments. Compared to closed-loop optimization, this strategy is easier to implement as it does not rely on online monitoring, contributing to the state of the art in optimizing bioproduction by microbial consortia. We outline the applicability of the approach using simulation experiments. |
|
|
Corpuscular volume estimation using a small amount of blood via microscope images |
|
Jegyeong Ryu(Seoul National University, Korea), Dahyun Nam(Yonsei University, Korea), Junghyun John Son(Korea Institute of Science and Technology, Korea), Amy Kyungwon Han(Seoul National University, Korea), Deukhee Lee(Korea Institute of Science and Technology, Korea) |
| Blood is an analysis serves as a valuable diagnostic tool that can easily and simply diagnose health. In this study, we present a methodology to make the simple and quick blood analysis. This method uses a microscope image of a small amount of blood, without drying the blood sample. To assess the validity and accuracy of the proposed method, an investigation is conducted to examine its correlation with the Sysmex XN-1000; we show that the correlation coefficients are higher than 0.88. By developing this method, it will
be possible to establish a simple quick blood analysis method using microscope images, decreasing a time consumed for
the health checkup. |
|
|
Compensating for Size Effect in Shear Wave Elastography using Deep Neural Networks |
|
Seungyeop Lee, Jae Youn Hwang, Yongsoon Eun(DGIST, Korea) |
| In ultrasound shear wave elastography (USWE), the elasticity of a small lesion is underestimated due to the wave reflection inside the lesion. This phenomenon is referred to as size effect. This paper proposes using a deep neural network to compensate for the size effect without explicit size information. |
|
|
Novel design of DNA constant-signal generator towards an experimental feasibility |
|
Takeru Fujimura, TAKASHI NAKAKUKI(Kyushu Institute of Technology, Japan) |
| Recent advances in nanotechnology have accelerated the development of various molecular systems driven by the chemical principles of operation. Because intelligent “molecular robots” with sensors and actuators designed at the molecular level can be developed, there is an increasing demand for molecular circuits that perform complicated information processing, such as feedback controllers.
In this study, we developed a constantsignal generator that outputs a designated concentration for DNA circuits.
Because our circuit is based on DNA strand displacement reactions, which are commonly used in the design of DNA circuits, it is applicable and connectable to a variety of DNA circuits. |
|