Wilson Castro

Multilayer perceptron architecture optimization using parallel computing techniques

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time.

Evaluation of Expert Systems Techniques for Classifying Different Stages of Coffee Rust Infection in Hyperspectral Images

In this work, the use of expert systems and hyperspectral imaging in the determination of coffee rust infection was evaluated. Three classifiers were trained using spectral profiles from different stages of infection, and the classifier based on a support vector machine provided the best performance. When this classifier was compared to visual analysis, statistically significant differences were observed, and the highest sensitivity of the selected classifier was found at early stages of infection.

Professor Da-Wen Sun Conferred with Honorary Doctorate Degree from Peru

Professor Da-Wen Sun, from UCD School of Biosystems and Food Engineering, has been conferred with Honorary Doctorate Degree from the Universidad Privada del Norte (UPN) in Peru in recognition of his exceptional contribution and leading role for advancing food and biosystems engineering research and education at the global level. A special conferring ceremony was held on 12 February 2018 in the Breña Campus of UPN in Lima. Dr. Andrés Velarde, the Rector of UPN, presented Professor Sun with the certificate, medal and plaque of the honorary doctorate of UPN (Fig. 1). In his conferring speech, Dr. Andrés Velarde said that this was the first honorary doctorate he has conferred during his rectorship in the past 7 years; he hoped that this honour would further strengthen the collaboration between Professor Sun and UPN and helps uplift the quality and reputation of UPN at international level. Speaking for accepting the honour during the event, Professor Sun said it was a great honour for him to have received an honorary doctorate from UPN, BI really appreciate UPN for conferring this honorary doctorate degree upon me today. I will forever hold it with pride and humility and allow it to serve as a testament to the value of serving our profession with commitment and compassion^; BI understand that accepting this distinction is not only a great honour, but also a responsibility to me. The honorary doctorate degree from UPN provides me an opportunity, a platform and a communication channel for furthering our effective collaboration.^ UPN, established by the Peruvian Congress Law N° 26275 in November 1993, is the first international university in northern Peru. The university has six campuses in Trujillo and Cajamarca and Lima, with a total student population of over 60,000. Since September 2007, UPN has become a member of Laureate International Universities and has quickly developed an outstanding reputation for the quality of its teaching and scholarship, and for its pluralistic and global outlook. According to the latest ranking of uniRankTM based in Australia, UPN is ranked No. 10 in about 150 universities in Peru, and based on QS World University Rankings, UPN is among the best in Latin America. Professor Sun is a world authority in food engineering research and education. His many scholarly works have become standard reference materials for researchers in the areas of computer vision/hyperspectral imaging, computational fluid dynamics modelling, vacuum cooling, etc. Results of his work have been published in more than 500 peer-reviewed journal papers (Web of Science hindex = 86, SCOPUS h-index = 90) with 39 papers being designated by ESI as highly cited papers. He is the recipient of numerous awards and honours including election to the Royal Irish Academy in 2010, selection as a Member of Academia Europaea (The Academy of Europe) in 2011, induction as a Fellow of International Academy of Food Science and Technology in 2012, award as a Fellow of International Academy of Agricultural and Biosystems Engineering in 2016, and election as a Foreign Member of Polish Academy of Sciences in 2017. Among other international recognitions, * Wilson Castro wilson.castro@upn.edu.pe