A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Hybrid and optical packet switching supporting different service classes in data center network

Photonic Network Communications - Optical packet switching is a prominent technology proposing not only a reduction in the energy consumption by the elimination of numerous...     

Expression of RCAS1 Correlates with Urothelial Bladder Cancer Malignancy

RCAS1 is a protein that participates in regulation of the tumor microenvironment and its immune responses, all in order to evade the immune system. The aim of this study was to analyze RCAS1 expression in urothelial bladder cancer cells (and in fibroblasts and macrophages of the tumor stroma) and its relationship with the histological pattern of malignancy. Eighty-three postcystectomy patients were enrolled. We analyzed the histological maturity (grade), progress (pT stage), tissue invasion type (TIT), nonclassic differentiation number (NDN), and the ability to metastasize (pN). The expression of RCAS1 protein was analyzed by immunohistochemistry. Indicators of histological malignancy were observed solely in association with the RCAS1 expression in cells in the border parts (BPs) of the tumor. Histological malignancy of the tumor, indicated by the pT and pN, and metastasis-free survival time, correlated significantly with RCAS1 expression in tumor neoplastic cells, whereas malignancy determined by grade, TIT, and NDN correlated with RCAS1 expression in fibroblasts and macrophages in the tumor microenvironment. These findings suggest that the increased RCAS1 expression depends on its cellular source and that RCAS1 expression itself is a component of various signaling pathways. The immune escape occurs within the tumor BPs, where the increase in the RCAS1 expression occurs within tumor cells and stromal cells in its microenvironment. We conclude that the histological pattern of tumor malignancy, indicated by grade, TIT, NDN, pT, and pN is a morphological indicator of immune escape.     

Quality enhancement of the abundant under‐valued crustacean,lobster krill (Munida spp.), during its chilled storage

Lobster krill (Munida genus) represents an under‐valued crustacean frequently caught on European fishing banks. In this work, its sensory, microbiological and biochemical qualities were evaluated during chilled storage. Additionally, the effects of a prestorage antimelanosic treatment consisting of soaking in sodium metabisulphite (SMB) solutions at two different concentrations (0.25% and 0.75%) were also studied. SMB prestorage treatment provided lobster specimens that still exhibited acceptable sensory quality after 10 days of storage, while control specimens were unacceptable at that time. SMB treatment also resulted in a significant (P < 0.05) inhibition of microbial growth, mainly of Enterobacteriaceae, psychrotrophes and proteolytic bacteria. Low lipid oxidation levels were observed for all batches; however, a significantly higher (P < 0.05) retention of polyunsaturated fatty acids was found in SMB‐treated lobster, especially in the 0.75% SMB batch. The results presented here open the way to the potential commercialisation of currently under‐utilised lobster krill as a chilled product.     

Sustainable ammonia production through process synthesis and global optimization

Current ammonia production technologies have a significant carbon footprint. In this study, we present a process synthesis and global optimization framework to discover the efficient utilization of renewable resources in ammonia production. Competing technologies are incorporated in a process superstructure where biomass, wind, and solar routes are compared with the natural gas-based reference case. A deterministic global optimization-based branch-and-bound algorithm is used to solve the resulting large-scale nonconvex mixed-integer nonlinear programming problem (MINLP). Case studies for Texas, California, and Iowa are conducted to examine the effects of different feedstock prices and availabilities. Results indicate that profitability of ammonia production is highly sensitive to feedstock and electricity prices, as well as greenhouse gas (GHG) restrictions. Under strict 75% GHG reductions, biomass to ammonia route is found to be competitive with natural gas route, whereas wind and solar to ammonia routes require further improvement to compete with those two routes. © 2018 American Institute of Chemical Engineers AIChE J, 65: e16498 2019