Discrete Missing Data Imputation Using Multilayer Perceptron and Momentum Gradient Descent.

Data are a strategic resource for industrial production, and an efficient data-mining process will increase productivity. However, there exist many missing values in data collected in real life due to various problems. Because the missing data may reduce productivity, missing value imputation is an important research topic in data mining. At present, most studies mainly focus on imputation methods for continuous missing data, while a few concentrate on discrete missing data. In this paper, a discrete missing value imputation method based on a multilayer perceptron (MLP) is proposed, which employs a momentum gradient descent algorithm, and some prefilling strategies are utilized to improve the convergence speed of the MLP. To verify the effectiveness of the method, experiments are conducted to compare the classification accuracy with eight common imputation methods, such as the mode, random, hot-deck, KNN, autoencoder, and MLP, under different missing mechanisms and missing proportions. Experimental results verify that the improved MLP model (IMLP) can effectively impute discrete missing values in most situations under three missing patterns.

Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning.

Light Detection and Ranging (LiDAR) produces 3D point clouds that describe ground objects, and has been used to make object interpretation in many cases. However, traditional LiDAR only records discrete echo signals and provides limited feature parameters of point clouds, while full-waveform LiDAR (FWL) records the backscattered echo in the form of a waveform, which provides more echo information. With the development of machine learning, support vector machine (SVM) is one of the commonly used classifiers to deal with high dimensional data via small amount of samples. Ensemble learning, which combines a set of base classifiers to determine the output result, is presented and SVM ensemble is used to improve the discrimination ability, owing to small differences in features between different types of data. In addition, previous kernel functions of SVM usually cause under-fitting or over-fitting that decreases the generalization performance. Hence, a series of kernel functions based on wavelet analysis are used to construct different wavelet SVMs (WSVMs) that improve the heterogeneity of ensemble system. Meanwhile, the parameters of SVM have a significant influence on the classification result. Therefore, in this paper, FWL point clouds are classified by WSVM ensemble and particle swarm optimization is used to find the optimal parameters of WSVM. Experimental results illustrate that the proposed method is robust and effective, and it is applicable to some practical work.

Digital deformation model for fisheye image rectification.

Fisheye lens can provide a wide view over 180°. It then has prominence advantages in three dimensional reconstruction and machine vision applications. However, the serious deformation in the image limits fisheye lens's usage. To overcome this obstacle, a new rectification method named DDM (Digital Deformation Model) is developed based on two dimensional perspective transformation. DDM is a type of digital grid representation of the deformation of each pixel on CCD chip which is built by interpolating the difference between the actual image coordinate and pseudo-ideal coordinate of each mark on a control panel. This method obtains the pseudo-ideal coordinate according to two dimensional perspective transformation by setting four mark's deformations on image. The main advantages are that this method does not rely on the optical principle of fisheye lens and has relatively less computation. In applications, equivalent pinhole images can be obtained after correcting fisheye lens images using DDM.

FBP1 knockdown decreases ovarian cancer formation and cisplatin resistance through EZH2-mediated H3K27me3.

Worldwide, ovarian cancer (OC) is the seventh common cancer and the second most common cause of cancer death in women. Due to high rates of relapse, there is an urgent need for the identification of new targets for OC treatment. The far-upstream element binding protein 1 (FBP1) and enhancer of zeste homolog 2 (EZH2) are emerging proto-oncogenes that regulate cell proliferation and metastasis. In the present study, Oncomine data analysis demonstrated that FBP1 was closely associated with the development of OC, and The Cancer Genome Atlas (TCGA) data analysis indicated that there was a positive correlation between FBP1 and EZH2 in ovarian tissues. Moreover, we found that FBP1 knockdown suppressed tumor formation in nude mice and cisplatin resistance of OC cells, but the role of FBP1 in the cisplatin resistance of OC cells remained unclear. In addition, we verified physical binding between FBP1 and EZH2 in OC cells, and we demonstrated that FBP1 knockdown enhanced cisplatin cytotoxicity in OC cells and down-regulated EZH2 expression and trimethylation of H3K27. These results suggested that FBP1 increases cisplatin resistance of OC cells by up-regulating EZH2/H3K27me3. Thus, FBP1 is a prospective novel target for the development of OC treatment.

Diversity roles of CHD1L in normal cell function and tumorigenesis.

Chromodomain helicase/ATPase DNA binding protein 1-like gene (CHD1L) is a multifunctional protein participated in diverse cellular processes, including chromosome remodeling, cell differentiation and development. CHD1L is a regulator of chromosomal integrity maintenance, DNA repair and transcriptional regulation through its bindings to DNA. By regulating kinds of complex networks, CHD1L has been identified as a potent anti-apoptotic and pro-proliferative factor. CHD1L is also an oncoprotein since its overexpression leads to dysregulation of related downstream targets in various cancers. The latest advances in the functional molecular basis of CHD1L in normal cells will be described in this review. As the same time, we will describe the current understanding of CHD1L in terms of structure, characteristics, function and the molecular mechanisms underlying CHD1L in tumorigenesis. We inference that the role of CHD1L which involve in multiple cellular processes and oncogenesis is well worth further studying in basic biology and clinical relevance.

Comparative study on intercalation-exfoliation and thermal activation modified kaolin for heavy metals immobilization during high-organic solid waste pyrolysis.

With the new municipal solid waste classification policy implemented in China, attention on achieving the waste-to-energy disposal of "dry waste" has been growing. Pyrolysis conversion of organic waste into value-added chemicals is a promising method to treat solid waste. However, after removing the non-combustible components of "dry waste", the obtained high-organic solid waste (HSW) contains various heavy metals, which requires urgent attention during thermochemical conversion. To mitigate heavy metals risk, kaolin was employed as additive during HSW pyrolysis, and intercalation-exfoliation and thermal activation modifications were performed on the kaolin to further immobilize and stabilize heavy metals in the derived chars. The characterization results illustrated that the interlayer spacing, pore volume and diameter of kaolin were expanded after intercalation-exfoliation modification, providing more opportunities for the adsorption of metals. The thermal activation method favored the transformation of kaolin into metakaolin via dehydroxylation to enhance its nonhexacoordinated Al proportion and chemisorption. During 450-650 °C, kaolin exhibited an effective solid enrichment performance for targeting heavy metals, and the intercalation-exfoliation and thermal activation modification further enhanced the adsorption capacity of the kaolin for Cd, Cr, Pb and Cr, Cu, Pb, Zn, respectively. Compared with Cu and Zn, additives demonstrated better stabilization effects for Cd, Pb, and Cr, transforming more bioavailable fractions to the residual speciation. Overall, a higher pyrolytic temperature (650 °C) and the addition of effective additives could simultaneously increase the residual fraction and decrease the bioavailable fraction of heavy metals in HSW-derived chars, reducing the potential ecological risk.

Insights Into Amentoflavone: A Natural Multifunctional Biflavonoid.

Amentoflavone is an active phenolic compound isolated from Selaginella tamariscina over 40 years. Amentoflavone has been extensively recorded as a molecule which displays multifunctional biological activities. Especially, amentoflavone involves in anti-cancer activity by mediating various signaling pathways such as extracellular signal-regulated kinase (ERK), nuclear factor kappa-B (NF-κB) and phosphoinositide 3-kinase/protein kinase B (PI3K/Akt), and emerges anti-SARS-CoV-2 effect via binding towards the main protease (Mpro/3CLpro), spike protein receptor binding domain (RBD) and RNA-dependent RNA polymerase (RdRp) of SARS-CoV-2. Therefore, amentoflavone is considered to be a promising therapeutic agent for clinical research. Considering the multifunction of amentoflavone, the current review comprehensively discuss the chemistry, the progress in its diverse biological activities, including anti-inflammatory, anti-oxidation, anti-microorganism, metabolism regulation, neuroprotection, radioprotection, musculoskeletal protection and antidepressant, specially the fascinating role against various types of cancers. In addition, the bioavailability and drug delivery of amentoflavone, the molecular mechanisms underlying the activities of amentoflavone, the molecular docking simulation of amentoflavone through in silico approach and anti-SARS-CoV-2 effect of amentoflavone are discussed.

Experimental study on enrichment of heavy metals by intercalation-exfoliation modified kaolin during coal combustion.

An intercalation-exfoliation method is applied to modify the natural kaolin mineral, so that to improve the enrichment effects on heavy metals (Zn, Pb, Cr & Cd) during coal combustion. The modified kaolin is scanned by electron microscope (SEM), X-ray diffraction (XRD), Fourier Transform infrared spectroscopy (FTIR) and Brunner-Emmett-Teller (BET), which indicate that the natural kaolin is peeled off to form fine flakes and the interlayer spacing is significantly increased. The coal-kaolin combustion tests were performed in a tube furnace from 900°C to 1300°C. It is found that the enrichment of heavy metals is enhanced obviously during the coal combustion, especially when the raw kaolin has high activity. Besides, the adsorption effects on the above four heavy metals are different. To be specific, the kaolin modified by potassium acetate has a better performance for Zn and Pb, but that intercalated by dimethyl sulfoxide shows better influences on Cd and Cr. The modified kaolin can provide more active sites for the adsorption of heavy metals, enhance chemical adsorption, and fix heavy metals in the form of aluminosilicates, silicates and aluminates. These founding could reduce the pollutant emissions of coal combustion in industrial applications.

Investigation on gaseous pollutants emissions during co-combustion of coal and wheat straw in a fluidized bed combustor.

Co-combustion of coal and wheat straw (WS) was conducted in a lab-scale BFB combustor. Fuel composition (coal, 70%coal+30%WS), temperature (750, 800, 850, 900, 950 °C), secondary air ratio (0, 10%, 20%, 30%) were varied to on the release of gaseous pollutant was studied. CO, NOx and SO2 concentration in flue gas (FG) were measured on-line by a flue gas analyzer. Fly ash (FA), bottom slag (BS) and bed material (BM) were collected, digested and analyzed by ICP-OES to determine the distribution of heavy metals (e.g. Pb, Zn, Cr and Cd). Results indicated that co-combustion could improve the combustion of coal alone by reducing CO, NOx and SO2 emission and carbon content in fly ash effectively. In co-combustion the increasing secondary air could reduce CO emission and SO2 by enhancing disturbance and promoting sulfation respectively while the minimum NO emission was reached at the ratio of 20%. Co-combustion restrained the release of Zn, Cd and Pb compared with coal combustion alone. In co-combustion, high temperature increased their portion in the flue gas. For Zn, Pb and Cd, their content in the bottom solids increased while the portion of Cr decreased. Secondary air decreased their content in fly ash and transferred into flue gas significantly and in bottom solids content of Zn and Pb decreased while Cd increased.

A "Tuned" Mask Learnt Approach Based on Gravitational Search Algorithm.

Texture image classification is an important topic in many applications in machine vision and image analysis. Texture feature extracted from the original texture image by using "Tuned" mask is one of the simplest and most effective methods. However, hill climbing based training methods could not acquire the satisfying mask at a time; on the other hand, some commonly used evolutionary algorithms like genetic algorithm (GA) and particle swarm optimization (PSO) easily fall into the local optimum. A novel approach for texture image classification exemplified with recognition of residential area is detailed in the paper. In the proposed approach, "Tuned" mask is viewed as a constrained optimization problem and the optimal "Tuned" mask is acquired by maximizing the texture energy via a newly proposed gravitational search algorithm (GSA). The optimal "Tuned" mask is achieved through the convergence of GSA. The proposed approach has been, respectively, tested on some public texture and remote sensing images. The results are then compared with that of GA, PSO, honey-bee mating optimization (HBMO), and artificial immune algorithm (AIA). Moreover, feature extracted by Gabor wavelet is also utilized to make a further comparison. Experimental results show that the proposed method is robust and adaptive and exhibits better performance than other methods involved in the paper in terms of fitness value and classification accuracy.