Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines

This study proposes a novel prediction approach for human breast and colon cancers using different feature spaces. The proposed scheme consists of two stages: the preprocessor and the predictor. In the preprocessor stage, the mega-trend diffusion (MTD) technique is employed to increase the samples of the minority class, thereby balancing the dataset. In the predictor stage, machine-learning approaches of K-nearest neighbor (KNN) and support vector machines (SVM) are used to develop hybrid MTD-SVM and MTD-KNN prediction models. MTD-SVM model has provided the best values of accuracy, G-mean and Matthew's correlation coefficient of 96.71%, 96.70% and 71.98% for cancer/non-cancer dataset, breast/non-breast cancer dataset and colon/non-colon cancer dataset, respectively. We found that hybrid MTD-SVM is the best with respect to prediction performance and computational cost. MTD-KNN model has achieved moderately better prediction as compared to hybrid MTD-NB (Naïve Bayes) but at the expense of higher computing cost. MTD-KNN model is faster than MTD-RF (random forest) but its prediction is not better than MTD-RF. To the best of our knowledge, the reported results are the best results, so far, for these datasets. The proposed scheme indicates that the developed models can be used as a tool for the prediction of cancer. This scheme may be useful for study of any sequential information such as protein sequence or any nucleic acid sequence.     

Deep features-based speech emotion recognition for smart affective services

Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

     

Ergogenic Attributes of Young and Mature Coconut (Cocos nucifera L.) Water Based on Physical Properties,Sugars and Electrolytes Contents

The present work aimed to compare the main ergogenic attributes of two commercialized stages (young and mature) of coconut water (CW) obtained from four coconut varieties. The changes of electrolytes and sugars in CW upon maturation were quantified by inductively coupled plasma mass spectrophotometer and high-performance liquid chromatography, respectively. Based on the electrolyte profiling, potassium yielded the highest amount (ranging from 237.41 to 361.20 mg/100 mL) followed by sodium, magnesium, calcium, iron, manganese, copper, selenium, and zinc across all the maturity stages tested. For sugars, there were lower amounts of fructose and glucose, but a higher amount of sucrose with the maturation of the fruits. In conclusion, the amount of beneficial nutrients in the form of sugars and minerals was higher than that of young CW, and the ergogenic attributes of mature CW especially from MATAG variety (M-MATAG) were the best to be exploited further in the development of natural energy drinks.     

The effects of physical refining on the formation of 3-monochloropropane-1,2-diol esters in relation to palm oil minor components

The formation of 3-monochloropropane-1,2-diol (3-MCPD) esters in refined palm oil during deodorisation is attributed to the intrinsic composition of crude palm oil. Utilising D-optimal design, the effects of the degumming and bleaching processes on the reduction in 3-MCPD ester formation in refined palm oil from poor-quality crude palm oil were studied relative to the palm oil minor components that are likely to be their precursors. Water degumming remarkably reduced 3-MCPD ester formation by up to 84%, from 9.79 mg/kg to 1.55 mg/kg. Bleaching with synthetic magnesium silicate caused a further 10% reduction, to 0.487 mg/kg. The reduction in 3-MCPD ester formation could be due to the removal of related precursors prior to the deodorisation step. The phosphorus content of bleached palm oil showed a significant correlation with 3-MCPD ester formation.     

Potential Use of FTIR-ATR Spectroscopic Method for Determination of Virgin Coconut Oil and Extra Virgin Olive Oil in Ternary Mixture Systems

The aim of this study was to investigate the feasibility of Fourier-transform infrared (FTIR) spectroscopy combined with multivariate calibrations of partial least square (PLS) and principle component regression (PCR) for analysis of virgin coconut oil (VCO) in the ternary mixture with palm oil (PO) and olive oil, and for analysis of extra virgin olive oil (EVOO) mixed with soybean oil (SO) and corn oil (CO). The spectra of individual oils and their blends with certain concentrations were scanned using horizontal attenuated total reflectance accessory at mid-infrared region of 4,000–650 cm⁻¹. The optimal frequency regions selected for calibration models were based on its ability to give the highest values of coefficient of determination (R ²) and the lowest values of root mean standard error of calibration (RMSEC). PLS was slightly better for quantitative analysis of VCO and EVOO compared with PCR. VCO in ternary mixtures is successfully determined at frequency region of 1,200–1,000 using second derivative FTIR spectra with R ² and RMSEC values of 0.999 and 0.200, respectively. Meanwhile, EVOO is best determined at 1,200–1,000 using first derivative FTIR spectra with R ² and RMSEC values of 0.999 and 0.975, respectively. The results showed that FTIR spectroscopy offers accurate and reliable technique for quantitative analysis of VCO and EVOO in ternary systems. In addition, the developed method can be used for the monitoring of VCO and EVOO adulteration with cheaper oils like PO in VCO as well as SO and CO in EVOO.     

Putative virulence factors of the Aeromonas spp. isolated from food and environment in Abu Dhabi, United Arab Emirates

Thirty randomly selected Aeromonas isolates from food and the environment in Abu Dhabi, United Arab Emirates, were characterized for putative virulence determinants, such as production of cytotoxin, cytotonic toxin, and hemolysin and their capacity to adhere to and invade Henle 407 cells in vitro. Seventy percent of the tested isolates were cytotoxin producers, and 80% were hemolytic. Cytotoxin was produced by 6 of 7 A. hydrophila strains, 6 of 13 A. caviae strains, and 6 of 7 A. veronii bv. sobria strains, mostly from food sources. A. schubertii, A. jandaei, and A. trota also produced both cytotoxin and hemolysin. All of the 30 isolates tested adhered to Henle 407 cells, but none were able to invade the cells, as determined with the in vitro assay. However, no significant correlation of the presence of these putative virulence factors was found among these aeromonad food isolates.     

Electroless copper-phosphorus coatings with the addition of silicon carbide （SiC） particles

Cu-P-silicon carbide(SiC)composite coatings were deposited by means of electroless plating.The effects ofpH values,temperature,and different concentrations of sodium hypophosphite(NaH2PO2·H2O),nickel sulfate(NiSO4·6H2O),sodium citrate(C6H5Na3O7·2H2O)and SiC on the deposition rate and coating compositions were evaluated,and the bath formulation for Cu-P-SiC composite coatings was optimised.The coating compositions were determined using energy-dispersive X-ray analysis(EDX).The corresponding optimal operating parameters for depositing Cu-P-SiC are as follows:pH 9; temperature,90℃; NaH2PO2·H2O concentration,125 g/L; NiSO4·6H2O concentration,3.125 g/L; SiC concentration,5 g/L; and C6H5Na3O7·2H2O concentration,50 g/L.The surface morphology of the coatings analysed by scanning electron microscopy(SEM)shows that Cu particles are uniformly distributed.The hardness and wear resistance of Cu-P composite coatings are improved with the addition of SiC particles and increase with the increase of SiC content.     

On the role of Ca in suppressing the corrosion of Pb anode in H2SO4

Abstract-The anodic behaviour of some Pb-Ca (0·2–0·8 per cent) alloys in H₂SO₄ solutions has been studied both under potentiostatic and galvanostatic conditions. It has been shown that the protective nature of the PbSO₄ film is markedly improved by alloying Ca with Pb. The role of Ca in increasing the corrosion resistance of Pb in H₂SO₄ is discussed.     

Determining the Impact of Personal Mobility Carbon Allowance Schemes in Transportation Networks

Personal mobility carbon allowance (PMCA) schemes are designed to reduce carbon consumption from transportation networks. PMCA schemes influence the travel decision process of users and accordingly impact the system metrics including travel time and greenhouse gas (GHG) emissions. We develop a multi-user class dynamic user equilibrium model to evaluate the transportation system performance when PMCA scheme is implemented. The results using Sioux-Falls test network indicate that PMCA schemes can achieve the emissions reduction goals for transportation networks. Further, users characterized by high value of travel time are found to be less sensitive to carbon budget in the context of work trips. Results also show that PMCA scheme can lead to higher emissions for a path compared with the case without PMCA because of flow redistribution. The developed network equilibrium model allows to examine the change in system states at different carbon allocation levels and to design parameters of PMCA schemes accounting for population heterogeneity.