A novel classification approach based on Extreme Learning Machine and Wavelet Neural Networks

Multimedia Tools and Applications - In this paper, we present a novel classification approach based on Extreme Learning Machine (ELM) and Wavelet Neural Networks. We introduce two novel...     

An E-Business Event Stream Mechanism for Improving User Tracing Processes

With the rapid development in business transactions, especially in recent years, it has become necessary to develop different mechanisms to trace business user records in web server log in an efficient way. Online business transactions have increased, especially when the user or customer cannot obtain the required service. For example, with the spread of the epidemic Coronavirus (COVID-19) throughout the world, there is a dire need to rely more on online business processes. In order to improve the efficiency and performance of E-business structure, a web server log must be well utilized to have the ability to trace and record infinite user transactions. This paper proposes an event stream mechanism based on formula patterns to enhance business processes and record all user activities in a structured log file. Each user activity is recorded with a set of tracing parameters that can predict the behavior of the user in business operations. The experimental results are conducted by applying clustering-based classification algorithms on two different datasets; namely, Online Shoppers Purchasing Intention and Instacart Market Basket Analysis. The clustering process is used to group related objects into the same cluster, then the classification process measures the predicted classes of clustered objects. The experimental results record provable accuracy in predicting user preferences on both datasets.     

Improvement of Aglycone π-Stacking Yields Nanomolar to Sub-nanomolar FimH Antagonists

Antimicrobial resistance has become a serious concern for the treatment of urinary tract infections. In this context, an anti-adhesive approach targeting FimH, a bacterial lectin enabling the attachment of E. coli to host cells, has attracted considerable interest. FimH can adopt a low/medium-affinity state in the absence and a high-affinity state in the presence of shear forces. Until recently, mostly the high-affinity state has been investigated, despite the fact that a therapeutic antagonist should bind predominantly to the low-affinity state. In this communication, we demonstrate that fluorination of biphenyl α-d -mannosides leads to compounds with perfect π–π stacking interactions with the tyrosine gate of FimH, yielding low nanomolar to sub-nanomolar K_D values for the low- and high-affinity states, respectively. The face-to-face alignment of the perfluorinated biphenyl group of FimH ligands and Tyr48 was confirmed by crystal structures as well as ¹H,¹⁵N-HSQC NMR analysis. Finally, fluorination improves pharmacokinetic parameters predictive for oral availability.     

Using spray-dried sugar beet molasses in ice cream as a novel bulking agent

In this study, it is aimed to investigate and evaluate the use of molasses which is a by-product of sugar production as a novel bulking agent in ice cream as a sugar replacer. Sugar beet molasses (75%) and 12 DE maltodextrin (25%) were converted into powder form by spray drying. Spray-dried sugar beet molasses (SDSM) was then used as a substitute of sugar in different ratios (0:100, 25:75, 50:50, 75:25 and 100:0) in the ice cream products. The increased amount of SDSM decreased the overrun, L*, whiteness index (WI) and melting behaviours and increased a*, b*, total phenolic content, consistency and viscosity. Meanwhile, thermal properties have not been affected by the use of SDSM (P < 0.05). The sensory findings have been particularly interesting especially when replacing above 50% sugar with SDSM, aroma, flavour and general acceptability decrease. According to the results of this study, substituting 25% of total sugar with SDSM as a bulking agent can decrease cost of the product and improve total phenolic content and some quality parameters without compromising sensorial properties.     

A Potent Mimetic of the Siglec-8 Ligand 6’-Sulfo-Sialyl Lewisx

Siglecs are members of the immunoglobulin gene family containing sialic acid binding N-terminal domains. Among them, Siglec-8 is expressed on various cell types of the immune system such as eosinophils, mast cells and weakly on basophils. Cross-linking of Siglec-8 with monoclonal antibodies triggers apoptosis in eosinophils and inhibits degranulation of mast cells, making Siglec-8 a promising target for the treatment of eosinophil- and mast cell-associated diseases such as asthma. The tetrasaccharide 6’-sulfo-sialyl Lewis^x has been identified as a specific Siglec-8 ligand in glycan array screening. Here, we describe an extended study enlightening the pharmacophores of 6’-sulfo-sialyl Lewis^x and the successful development of a high-affinity mimetic. Retaining the neuraminic acid core, the introduction of a carbocyclic mimetic of the Gal moiety and a sulfonamide substituent in the 9-position gave a 20-fold improved binding affinity. Finally, the residence time, which usually is the Achilles tendon of carbohydrate/lectin interactions, could be improved.     

Proposed network structures and combined adaptive algorithms for electrocardiogram signal denoising

An electrocardiogram (ECG) signal is a record of the electrical activities of heart muscle and is used clinically to diagnose heart diseases. An ECG signal should be presented as clear as possible to support accurate decisions made by doctors. This article proposes different combinations of combined adaptive algorithms to derive different noise-cancelling structures to remove (denoise) different kinds of noise from ECG signals. The algorithms are applied to the following types of noise: power line interference, baseline wander, electrode motion artifact, and muscle artifacts. Moreover, the results of the suggested models and algorithms are compared with those of conventional denoising tools such as the discrete wavelet transform, an adaptive filter, and a multilayer neural network (NN) to ensure the superiority of the proposed combined structures and algorithms. Furthermore, the hybrid concept is based on dual, triple, and quadruple combinations of well-known algorithms that derive adaptive filters, such as the least mean squares, normalized least mean squares and recursive least squares algorithms. The combinations are formulated based on partial update, variable step-size (VSS), and second iterative VSS algorithms, which are considered in different combinations. In addition, biased NN and unbiased linear neural network (ULNN) structures are considered. The performance of the different structures and related algorithms are evaluated by measuring the post-signal-to-noise ratio, mean square error, and percentage root mean square difference.