Abstract
We discuss chemical information processing considering dataset classifiers formed with a network of interacting droplets. Our arguments are based on computer simulations of droplets in which a photosensitive variant of the Belousov-Zhabotinsky (BZ) reaction proceeds. By applying optical control we can adjust the time evolution of individual droplets and prepare the network to perform a specific computational task. We demonstrate that chemical classifiers made of droplets can be designed in computer simulations based on evolutionary algorithms. The mutual information between the dataset and the observed time evolution of droplets in the network is taken as the fitness function in the optimization process. We show that a classifier of the Wisconsin Breast Cancer Dataset made of a relatively small number of droplets can distinguish between malignant and benign forms of cancer with an accuracy exceeding 97%. The reliability of the optimized chemical classifiers of this dataset as a function of optimization time, number of droplets involved in data processing and the method of extracting the output information is discussed.
Highlights
Semiconductors have the dominant position in modern information processing applications, their physical properties impose restrictions on the environments in which they can operate
In this paper we focus our attention on information processing with a photosensitive, ruthenium-catalyzed variant of the Belousov–Zhabotinsky (BZ) reaction.[11]
We study the time evolution of a network of droplets in the time interval [0,tsim] and relate the output information to the number of excitations observed at a selected droplet within this time interval
Summary
Semiconductors have the dominant position in modern information processing applications, their physical properties impose restrictions on the environments in which they can operate. If the medium is spatially distributed a local excitation can expand in space via diffusion of the activator and propagate in the form of an excitation pulse (a spike). Each binary logic operation can be regarded as a classification problem for the dataset composed of M = 4 records. In this paper we present the construction of a classifier for the Wisconsin Breast Cancer Dataset[38] from the Proben[1] collection.[39] This dataset contains M = 699 records (cases) composed of 10 predictors with the cancer type (benign or malignant) as the output class. We demonstrate that a high accuracy classification algorithm of such a dataset can be executed by a network containing a relatively small number of BZ droplets (r25). The described evolutionary algorithm is general and can be applied for finding the conditions at which the network performs the required classification task in the optimal way
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.