Measuring the Effectiveness of Adaptive Random Forest for Handling Concept Drift in Big Data Streams

We are living in the age of big data, a majority of which is stream data. The real-time processing of this data requires careful consideration from different perspectives. Concept drift is a change in the data’s underlying distribution, a significant issue, especially when learning from data streams. It requires learners to be adaptive to dynamic changes. Random forest is an ensemble approach that is widely used in classical non-streaming settings of machine learning applications. At the same time, the Adaptive Random Forest (ARF) is a stream learning algorithm that showed promising results in terms of its accuracy and ability to deal with various types of drift. The incoming instances’ continuity allows for their binomial distribution to be approximated to a Poisson(1) distribution. In this study, we propose a mechanism to increase such streaming algorithms’ efficiency by focusing on resampling. Our measure, resampling effectiveness (ρ), fuses the two most essential aspects in online learning; accuracy and execution time. We use six different synthetic data sets, each having a different type of drift, to empirically select the parameter λ of the Poisson distribution that yields the best value for ρ. By comparing the standard ARF with its tuned variations, we show that ARF performance can be enhanced by tackling this important aspect. Finally, we present three case studies from different contexts to test our proposed enhancement method and demonstrate its effectiveness in processing large data sets: (a) Amazon customer reviews (written in English), (b) hotel reviews (in Arabic), and (c) real-time aspect-based sentiment analysis of COVID-19-related tweets in the United States during April 2020. Results indicate that our proposed method of enhancement exhibited considerable improvement in most of the situations.     

On the applications of Extremal Graph Theory to Coding Theory and Cryptography

Explicit constructions in Extremal graph theory give appropriate lower bound for Turan type problems. In the case of prohibited cycles explicit constructions can be used in various problems of Information Security. We observe algebraic constructions of regular graphs of large girth and graphs with large cycle indicator and describe some algorithms of Coding Theory and Cryptography based on such special families of graphs.     

An Electrochemical Determination of Uric Acid in Sera by a Flow-Through Equipment with and Without Uricase

Abstract

A comparison of an enzymeless direct electrochemical oxidation procedure at a platinum electrode for the determination of uric acid, and an enzyme sensor with immobilized urate: oxygen oxidoreductase (uricase), was performed in flow stream systems. The uricase enzyme electrode is based on the H₂O₂ oxidation current. Both amperometric methods were related to the wall-known photometric uricase-catalase-procedure (UCM) as a reference method. The measured values of both methods are of the first derivatives of current change (dI/dt) due to the electrochemical or electrochemical enzymatic reaction, respectively. The analytical quality of the measurements is characterized by: precision s% within run < 2% day to day < 5% accuracy acceptable (control materials) correlation to reference method r >0.93 analysis rate 80 samples/hr     

Spectral method for vorticity‐stream function form of Navier–Stokes equations with slip boundary conditions

In this paper, we propose a spectral method for the vorticity‐stream function form of the Navier–Stokes equations with slip boundary conditions. The numerical solutions fulfill the incompressibility and the physical boundary conditions automatically. The stability and convergence of the proposed methods are proven. Numeric results demonstrate the efficiency of suggested algorithm. Copyright © 2011 John Wiley & Sons, Ltd.     

Study of the Contents and Speciation of Heavy Metals in River sediments By Factor Analysis

Abstract

Heavy metals Zn, Cd, Pb, Cu, Ni and Co from two spanish river sediments have been determined by voltammetric techniques, along with % CaCO₃ and % organic matter, and the whole data set examined by means of Factor Analysis, finding a different behaviour of the metals in each river.

Heavy metal speciation in the sediments was carried out by using the Tessier's scheme: Zn and Pb were mainly associated to ‘reducible phases’, Cd and Cu bound to ‘organic matter and sulphides’, and Ni and Co were distributed between the above fractions. The ‘residual’ metals were used as pollution indicators from the rivers, finding a similar behaviour to other industrialized river systems.     

Distribution and fate of tributyltin in the united states marine environment

Tributyltin (TBT) has been measured in water in 12 of 15 harbors studied during US Navy baseline surveys. The highest concentrations of TBT (some exceeding laboratory toxicity limits) have been found in yacht harbors and near vessel repair facilities. Many sites (75%) in harbors and estuaries had no detectable (<5 ng dm^?3) TBT. TBT monitoring studies with increased detection limits (<1 ng dm^?3) have documented a high degree of TBT variability associated with tide, season and intermittent point source discharges. Although yacht harbors were shown to be the principal TBT source in most regions, dry-docks can be significant sources. Tributyltin degradation studies were conducted using unfiltered seawater from four geographic regions and incubated under natural conditions. Degradation half-lives were always in the range of 4–19 days, providing evidence that TBT is not highly persistent in the water column at environmental concentrations. Preliminary degradation experiments suggest that TBT has a longer residence time in sediment with a half-life of several months. Tributyltin is primarily in the dissolved form in unfiltered seawater, although the association with particulate fractions may increase in samples collected near yacht repair facilities, Partition coefficients for particulate TBT versus bulk water are frequently near 3000 and vary with the particulate concentration, salinity and presence of natural organics.     

Degradation of a tetramethylarsonium salt by microorganisms occurring in sediments and suspended substances under both aerobic and anaerobic conditions

Microbial degradation of a tetramethylarsonium salt during incubation at 25°C was investigated under both aerobic and anaerobic conditions. Two media (1/5 ZoBell 2216E and inorganic salt medium), added with the sediments or suspended substances as the sources of the microorganisms, were used. Degradation of the tetramethylarsonium salt occurred only in the ZoBell medium: under anaerobic conditions, trimethylarsine oxide and dimethylarsinic acid were derived with the sediments, and dimethylarsinic acid with the suspended substances, the salt degrading more rapidly with the former than with the latter. Small amounts of two metabolites, trimethylarsine oxide and inorganic arsenic(V), was also derived in the aerobically incubated ZoBell medium added with the suspended substances. This result means that the tetramethylarsonium salt is degraded to inorganic arsenic, which is the starting material for arsenic circulation in marine ecosystems, via trimethylarsine oxide and dimethylarsinic acid.     

Fast algorithms for determining the linear complexities of sequences over GF(p~m) with the period 3n

In this paper, for the the primes p such that 3 is a divisor of p-1, we prove a result which reduces the computation of the linear complexity of a sequence over GF(pm)(any positive integer m) with the period 3n (n and pm - 1 are coprime) to the computation of the linear complexities of three sequences with the period n. Combined with some known algorithms such as generalized Games-Chan algorithm, Berlekamp-Massey algorithm and Xiao-Wei-Lam-lmamura algorithm, we can determine the linear complexity of any sequence over GF(pm) with the period 3n (n and pm - 1 are coprime) more efficiently.     

南黄海表层沉积物稀土元素分布与物源关系

对南黄海295个表层沉积物样品稀土元素的电感耦合等离子体质谱法分析,结果表明,南黄海表层沉积物稀土元素平均含量为188.39μg.g-1,稀土富集与重矿物有密切关系;稀土元素的球粒陨石配分模式均呈现Eu负异常,模式具负斜率,表明表层沉积物物质主要来源于大陆地壳。从稀土元素地球化学特征的区域变化来看,南黄海东部沉积物来源于朝鲜半岛,西部沉积物来源于黄河和长江物质输入,中部细粒沉积物主要与黄河及长江物质东南、东北扩散有关,东南部为朝鲜半岛及黄河、长江物质共同作用的结果。