Handbook of Intelligent Computing and Optimization for Sustainable Development - Группа авторов

Скачать книгу

is capable of solving computational, reasoning and classification problems [15–19]. The intention of this chapter is to theoretically build the backbone of DNA computer which is necessary to take a leap toward the shift in paradigm. The major findings of this chapter are listed below:

       • Demonstration to develop the models of DNA ANN using DNA oligonucleotides.

       • Use of DNA sequences as input and output signal to constructs the basic architecture of the neuron.

       • Illustration of the design strategy of DNA logic gates using the hybridization of the strands and the conformational deviations of the DNA secondary structures.

       • Design strategy of DNA logic circuit to develop and control nano-scale DNA devices.

       • Applications of nano-DNA-devices which can be designed using DNA ANN, DNA logic gates and logic circuit.

      DNA computation is the successful amalgamation of computer science and biological science. This emerging way of computation has the capability to revolutionize the technological perspective of coming era if the following limitations can be resolved.

       • As the algorithms of DNA computing involves a huge amount of DNA sequences and data as well, the probability of error exponentially increases.

       • The steps of the methodologies using DNA oligonucleotides need human and mechanical assistance which often claim a long time.

       • Biological experiments are very expensive. Thus, the implementation problem of DNA computation algorithms is one of the major limitations.

      The present advent of DNA computing cannot allow it to replace classical silicon-based computation as now DNA computers are not easily programmable. But several research works are being conducted globally and scientists are dedicated in development of more systematic and error-tolerant protocols.

      In this chapter, we have discussed the design strategy of artificial molecular machines which can efficiently replace traditional silicon-based computation. Computers and other electronic devices have made human being technologically more efficient than hundred years ago. Likewise, the development of DNA ANN and DNA logic gates are making human technologically capable to build molecular devices which will be more accomplished and more responsible toward the environment in coming era. In DNA computing, the mathematical and logical operations are replaced by the unique DNA chemistry and the Boolean bits are replaced by four nucleotides, i.e., Adenine (A), Guanine (G), Cytosine (C), and Thymine (T). Though the biochemical operations followed in DNA computation are much slower than conventional computing, the parallelism and storage capacity of DNA molecules are exponentially greater.

      We are hardly in the first generation of artificial intelligence in the domain of silicon computing. But gradually AI is evolving and scientists are trying to make DNA-based artificial intelligence more applicable in near future, specifically for health protection. DNA computing deals with a large amount of DNA sequences, and thus, the probability of error increases exponentially. In near future, it may be conceivable to design DNA-silicon hybrid architecture or incorporate DNA computing to develop software as it has more adaptability than hardware. DNA computers may successfully replace traditional computing system if automation can be involved in this technology to reduce human or machine interference.

      The first author, M. Mondal, acknowledges the financial support received as Research Associate fellowship from Council of Scientific & Industrial Research: Human Resource Development Group (CSIR: HRDG), Government of India.

      1. McCulloch, W. and Pitts, W., A Logical Calculus of Ideas Immanent in Nervous Activity. Bull. Math. Biophys., 5, 4, 115–133, 1943.

      2. Rosenblatt, F., The Perceptron - a perceiving and recognizing automaton, Report 85-460-1, Cornell Aeronautical Laboratory, Buffalo, New York, USA, 1957.

      3. Hebb, D.O., The organization of behavior; a neuropsychological theory, Wiley, New York, USA, 1949.

      4. Mills, P.A., Jr, Gene expression profiling diagnosis through DNA molecular computation. Trends Biotechnol., 20, 4, 137–140, 2002.

      5. Liu, W., Sun, S., Guo, Y., A DNA Computing Model of Perceptron. Pacific-Asia Conference on Circuits, Communications and Systems, pp. 726–729, 2009.

      6. Macdonald, J. and Stefanovic, D., Deoxyribozymes performing logic operations and simple computations. Scholarpedia J., 7, 6, 10021, 2012.

      7. Ray, K.S. and Mondal, M., Reasoning with disposition using DNA tweezers. Int. J. Bio-inspired Comput., 4, 5, 302–318, 2012.

      9. Hirose, R., Kobayashi, S., Komiya, K., DNA Logic Circuits with a DNA Polymerase and a Nicking Enzyme, in: Proceedings of The 2011 International Conference on Parallel and Distributed Processing Techniques and Applications, pp. 713–719, Las Vegas, Nevada, USA, 2011.

      10. Qian, L., Winfree, E., Bruck, J., Neural network computation with DNA strand displacement cascades. Nature, 475, 368–372, 2011.

      11. Cherry, K.M. and Qian, L., Scaling up molecular pattern recognition with DNA-based winnertake-all neural networks. Nature, 559, 370–376, 2018.

      12. Stojanovic, M.N. and Stefanovic, D., A Deoxyribozyme-Based Molecular Automaton. Nat. Biotechnol., 21, 1069–1074, 2003.

      13. Macdonald, J., Li, Y., Sutovic, M., Lederman, H., Pendri, K., Lu, W., Andrews, B.L., Stefanovic, D., Stojanovic, M.L., Medium Scale Integration of Molecular Logic Gates in an Automaton. Nano Lett., 6, 2598–603, 2006.

      14. Pei, R., Taylor, S.K., Stefanovic, D., Rudchenko, S., Mitchell, T.E., Stojanovic, M.N., Behavior of polycatalytic assemblies in a substrate-displaying matrix. J. Am. Chem. Soc, 128, 39, 12693– 12699, 2006.

      15. Adleman, L., Molecular computation of solutions to combinatorial problems. Science, 266, 1021–1024, 1994.

      16. Winfree, E., Liu, F., Wenzler, L.A., Seeman, N.C., Design and self-assembly of two-dimensional DNA crystals. Nature, 394, 539–544, 1998.

      17. Benenson, Y., Paz-Elizur, T., Adar, R., Keinan, E., Livneh, Z., Shapiro, E., Programmable and autonomous computing machine made of biomolecules. Nature, 414, 430–434, 2001.

      18. Ray, K.S. and Mondal, M., Classification of SODAR data by DNA computing. New Math. Nat. Comput., 7, 3, 413–432, 2011.

      19. Ray, K.S. and Mondal, M., Logical inference by DNA strand algebra. New Math. Nat. Comput., 12, 1, 29–44, 2016.

      1 *Corresponding author: [email protected]

      3

      Intelligent Garment Detection Using Deep Learning

       Aniruddha Srinivas Joshi*, Savyasachi Gupta, Goutham Kanahasabai and Earnest Paul Ijjina†

       Department of Computer Science and Engineering, National Institute of Technology, Warangal, India

       Abstract

      Garment detection is a complex image processing task that has a multitude of applications in the industry such as retrieval of similar garments, Artificial Intelligence–powered fashion recommendation models, and automatic labeling of catalogs. Retailers of fashion stores can benefit from knowing vital information about the

Скачать книгу