A neural network system has been developed on a personal computer to identify 1129 infrared spectra. The system is composed of two steps of networks. The first step classifies 1129 spectra into 40 categories, and each unit of the output layer is connected to one of the 40 networks in the second step, which identify each spectrum. Each network is composed of three layers. The input, intermediate, and output layers are composed of 250, 40, and 40 units, respectively. Intensity data at 250 wavenumber points between 1800 and 550 cm−1 of the infrared spectra are entered into the input layer of each network. The training of the networks was carried out with the spectral data of 1129 compounds stored in the SDBS system, and thus the networks were successfully constructed. On the basis of the results, the system has been developed by preparing pre- and post-processing programs. The system can identify each unknown spectrum within 0.1 s, and is quite efficient for identifying infrared spectra on a personal computer.
Structure identification of chemical substances from infrared spectra can be done with various approaches: a theoretical method using quantum chemistry calculations, an inductive method using standard spectral databases of known chemical substances, and an empirical method using rules between spectra and structures. For various reasons, it is difficult to definitively identify structures with these methods. The relationship between structures and infrared spectra is complicated and nonlinear, and for problems with such nonlinear relationships, neural networks are the most powerful tools. In this study, we have evaluated the performance of a neural network system that mimics the methods used by specialists to identify chemical structures from infrared spectra. Neural networks for identifying over 100 functional groups have been trained by using over 10 000 infrared spectral data compiled in the integrated spectral database system (SDBS) constructed in our laboratory. Network structures and training methods have been optimized for a wide range of conditions. It has been demonstrated that with neural networks, various types of functional groups can be identified, but only with an average accuracy of about 80%. The reason that 100% identification accuracy has not been achieved is discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.