Temporal separation of Cerenkov radiation and scintillation using artificial neural networks in Clinical LINACs

The irradiation of scintillator-fiber optic dosimeters by clinical LINACs results in the measurement of scintillation and Cerenkov radiation. In scintillator-fiber optic dosimetry, the scintillation and Cerenkov radiation responses are separated to determine the dose deposited in the scintillator volume. Artificial neural networks (ANNs) were trained and applied in a novel single probe method for the temporal separation of scintillation and Cerenkov radiation. Six dose profiles were measured using the ANN, with the dose profiles compared to those measured using background subtraction and an ionisation chamber. The average dose discrepancy of the ANN measured dose was 2.2% with respect to the ionisation chamber dose and 1.2% with respect to the background subtraction measured dose, while the average dose discrepancy of the background subtraction dose was 1.6% with respect to the ionisation chamber dose. The ANNs performance was degraded when compared with background subtraction, arising from an inaccurate model used to synthesise ANN training data.     

Host–parasitoid population density prediction using artificial neural networks: diamondback moth and its natural enemies

• 1 An integrated pest management (IPM) system incorporating the introduction and field release of Diadegma semiclausum (Hellén), a parasitoid of diamondback moth (DBM) Plutella xylostella (L.), comprising the worst insect pest of the cabbage family, has been developed in Kenya to replace the pesticides‐only approach.
• 2 Mathematical modelling using differential equations has been used in theoretical studies of host–parasitoid systems. Although, this method helps in gaining an understanding of the system's dynamics, it is generally less accurate when used for prediction. The artificial neural network (ANN) approach was therefore chosen to aid prediction.
• 3 The ANN methodology was applied to predict the population density of the DBM and D. semiclausum, its larval parasitoid. Two data sets, each from different release areas in the Kenya highlands, and both collected during a 3‐year period after the release of the parasitoid, were used in the present study. Two ANN models were developed using these data.
• 4 The ANN approach gave satisfactory results for DBM and for D. semiclausum. Sensitivity analysis suggested that pest populations may be naturally controlled by rainfall.
• 5 The ANN provides a powerful tool for predicting host–parasitoid population densities and made few assumptions on the field data. The approach allowed the use of data collected at any appropriate scale of the system, bypassing the assumptions and uncertainties that could have occurred when parameters are imported from other systems. The methodology can be explored with respect to the development of tools for monitoring and forecasting the population densities of a pest and its natural enemies. In addition, the model can be used to evaluate the relative effectiveness of the natural enemies and to investigate augmentative biological control strategies.

     

A kinetic spectrophotometric method for simultaneous determination of glycine and lysine by artificial neural networks

A spectrophotometric method for simultaneous analysis of glycine and lysine is proposed by application of neural networks on the spectral kinetic data. The method is based on the reaction of glycine and lysine with 1,2-naphthoquinone-4-sulfonate (NQS) in slightly basic medium. On the basis of the difference in the rate between the two reactions, these two amino acids can be determined simultaneously in binary mixtures. Feed-forward neural networks have been trained to quantify considered amino acids in mixtures under optimum conditions. In this way, a one-layer network was trained. Sigmoidal and linear transfer functions were used in the hidden and output layers, respectively. Linear calibration graphs were obtained in the concentration range of 1 to 25microgml(-1) for glycine and 1 to 19microgml(-1) for lysine. The analytical performance of this method was characterized by the relative standard error. The proposed method was applied to the determination of considered amino acids in synthetic samples.     

The use of artificial neural networks to reduce data collection demands in determining spine loading: a laboratory based analysis

The extensive data requirements of three-dimensional inverse dynamics and joint modelling to estimate spinal loading prevent the implementation of these models in industry and may hinder development of advanced injury prevention standards. This work examines the potential of feed forward artificial neural networks (ANNs) as a data reduction approach and compared predictions to rigid link and EMG-assisted models. Ten males and ten females performed dynamic lifts, all approaches were applied and comparisons of predicted joint moments and joint forces were evaluated. While the ANN under- predicted peak extension moments (p = 0.0261) and joint compression (p < 0.0001), predictions of cumulative extension moments (p = 0.8293) and cumulative joint compression (p = 0.9557) were not different. Therefore, the ANNs proposed may be used to obtain estimates of cumulative exposure variables with reduced input demands; however they should not be applied to determine peak demands of a worker's exposure.     

The application of artificial neural networks to the problem of reservoir classification and land use determination on the basis of water sediment composition

Presented work reports on the use of artificial neural networks to recognize and classify water reservoir types (lakes, rivers) and the nature of their surroundings (forests, fields, meadows) based on the chemical composition of sediments. The quantitative content of a selection of elements (Ag, As, Ba Ca, Cd, Co, Cr, Cu, Fe, Hg, Mg, Mn, Ni, P, Pb, S, Sr, TOC – Total Organic Cabon, V and Zn) in the sediments of lakes and rivers in the Lublin Province (Poland) were taken and used as working data file. Statistical analysis suggested that both reservoir types and area usage differ in terms of the quantity of studied determinants (elements) and thus might be distinguished on their basis. Artificial neural networks were then examined with respect to their ability to recognize and classify the data. Multilayer perceptron was used as the statistical model. Constructed models were able to give correct answers in 74% of cases when classifying reservoir’s area usage and 100% for the type of body of water.     

Cell-cycle-dependent variations in FTIR micro-spectra of single proliferating HeLa cells: Principal component and artificial neural network analysis

We have previously reported spectral differences for cells at different stages of the eukaryotic cell division cycle. These differences are due to the drastic biochemical and morphological changes that occur as a consequence of cell proliferation. We correlate these changes in FTIR absorption and Raman spectra of individual cells with their biochemical age (or phase in the cell cycle), determined by immunohistochemical staining to detect the appearance (and subsequent disappearance) of cell-cycle-specific cyclins, and/or the occurrence of DNA synthesis. Once spectra were correlated with their cells' staining patterns, we used methods of multivariate statistics to analyze the changes in cellular spectra as a function of cell cycle phase.     

Simultaneous determination of glucose, fructose and lactose in food samples using a continuous-flow chemiluminescence method with the aid of artificial neural networks.

In this study, a simple continuous-flow chemiluminescence (CL) system was developed for simultaneous determination of glucose, fructose and lactose in ternary mixtures of reducing sugars without previous separation. This method was based on the different kinetics of the individual sugars in the oxidation reaction with potassium ferricyanide. The known luminol-K(3)Fe(CN)(6) CL system was used to measure the kinetic data of the system. The CL intensity was measured and recorded every second from 1 to 300 s. The data obtained were processed chemometrically using an artificial neural network. The relative standard errors of prediction for three analytes were <5%. The proposed method was successfully applied to the simultaneous determination of the three sugars in some food samples.     

Extraction of chlorophylls and carotenoids from dry and wet biomass of isolated Chlorella Thermophila: Optimization of process parameters and modelling by artificial neural network

Chlorophylls and carotenoids can be extracted from microalgae using various solvents. However, there is lack of studies regarding the comparison of extraction yield of these pigments from wet and dry microalgal biomass using different combination of cell disruption methods. Therefore, in this work, we have investigated the comparison of the extraction yield of chlorophylls and carotenoids from the wet and heat-dried microalgal biomass (isolated Chlorella thermophila) using ethanol. Extraction parameters such as homogenisation time, homogenisation speed, solvent temperature, solid-solvent ratio, boiling time and microwave time have been optimised. Chlorophyll extraction yield was observed to be 2.7 fold higher from wet biomass than dry biomass while carotenoid yield was 6.7 fold higher. Highest chlorophyll yield (∼60 mg/g-dry biomass) was observed at 6 min of homogenisation time, 10,000 rpm, solid solvent ratio of 1 mg/mL and 58 °C of solvent temperature from wet biomass with extraction efficiency of ∼94 %. Highest carotenoid yield was noticed following the same conditions of chlorophyll extraction except 4 °C of solvent temperature. The modelling of the extraction process was performed using artificial neural network (ANN) which may be useful for the scale-up of the extraction process at the industrial level.     

The use of artificial neural networks for the selection of the most appropriate formulation and processing variables in order to predict the in vitro dissolution of sustained release minitablets

The objective of this work was to apply artificial neural networks (ANNs) to examine the relative importance of various factors, both formulation and process, governing the in-vitro dissolution from enteric-coated sustained release (SR) minitablets. Input feature selection (IFS) algorithms were used in order to give an estimate of the relative importance of the various formulation and processing variables in determining minitablet dissolution rate. Both forward and backward stepwise algorithms were used as well as genetic algorithms. Networks were subsequently trained using the back propagation algorithm in order to check whether or not the IFS process had correctly located any unimportant inputs. IFS gave consistent rankings for the importance of the various formulation and processing variables in determining the release of drug from minitablets. Consistent ranking was achieved for both indices of the release process; ie, the time taken for release to commence through the enteric coat (T_lag) and that for the drug to diffuse through the SR matrix of the minitablet into the dissolution medium (T_90-10). In the case of the T_lag phase, the main coating parameters, along with the original batch blend size and the blend time with lubricant, were found to have most influence. By contrast, with the T_90-10 phase, the amounts of matrix forming polymer and direct compression filler were most important. In the subsequent training of the ANNs, removal of inputs regarded as less important led to improved network performance. ANNs were capable of ranking the relative importance of the various formulations and processing variables that influenced the release rate of the drug from minitablets. This could be done for all main stages of the release process. Subsequent training of the ANN verified that removal of less relevant inputs from the training process led to an improved performance from the ANN.     

Novel optimal temperature profile for acidification process of <Emphasis Type="Italic">Lactobacillus bulgaricus</Emphasis> and <Emphasis Type="Italic">Streptococcus thermophilus</Emphasis> in yoghurt fermentation using artificial neural network and genetic algorithm

The acidification behavior of Lactobacillus bulgaricus and Streptococcus thermophilus for yoghurt production was investigated along temperature profiles within the optimal window of 38–44 °C. For the optimal acidification temperature profile search, an optimization engine module built on a modular artificial neural network (ANN) and genetic algorithm (GA) was used. Fourteen batches of yoghurt fermentations were evaluated using different temperature profiles in order to train and validate the ANN sub-module. The ANN captured the nonlinear relationship between temperature profiles and acidification patterns on training data after 150 epochs. This served as an evaluation function for the GA. The acidification slope of the temperature profile was the performance index. The GA sub-module iteratively evolved better temperature profiles across generations using GA operations. The stopping criterion was met after 11 generations. The optimal profile showed an acidification slope of 0.06117 compared to an initial value of 0.0127 and at a set point sequence of 43, 38, 44, 43, and 39 °C. Laboratory evaluation of three replicates of the GA suggested optimum profile of 43, 38, 44, 43, and 39 °C gave an average slope of 0.04132. The optimization engine used (to be published elsewhere) could effectively search for optimal profiles of different physico-chemical parameters of fermentation processes.     

A simulation study comparing the impact of experimental error on the performance of experimental designs and artificial neural networks used for process screening

Many variables and their interactions can affect a biotechnological process. Testing a large number of variables and all their possible interactions is a cumbersome task and its cost can be prohibitive. Several screening strategies, with a relatively low number of experiments, can be used to find which variables have the largest impact on the process and estimate the magnitude of their effect. One approach for process screening is the use of experimental designs, among which fractional factorial and Plackett–Burman designs are frequent choices. Other screening strategies involve the use of artificial neural networks (ANNs). The advantage of ANNs is that they have fewer assumptions than experimental designs, but they render black-box models (i.e., little information can be extracted about the process mechanics). In this paper, we simulate a biotechnological process (fed-batch growth of bakers yeast) to analyze and compare the effect of random experimental errors of different magnitudes and statistical distributions on experimental designs and ANNs. Except for the situation in which the error has a normal distribution and the standard deviation is constant, it was not possible to determine a clear-cut rule for favoring one screening strategy over the other. Instead, we found that the data can be better analyzed using both strategies simultaneously.     

Automata networks as preprocessing technique of artificial neural network in estimating primary production and dominating phytoplankton levels in a reservoir: An experimental work

Artificial Neural Networks (ANN) is computational architectures that can be used for estimating primary production levels and dominating phytoplankton species in reservoirs. Automata Networks (AN) were applied as a pre-processing method with subsequent ANN model development for Demirdöven Dam Reservoir. The primary purpose of using pre-processing technique was to distinguish the suitable and appropriate constituents of the input parameters' matrix, to eliminate redundancy, to enhance prediction power and calculation efficiency. The data were collected monthly over two years. The applications have yielded following results: The correlation coefficients (r values) between predicted and observed counts were as high as 0.83, 0.87, 0.83 and 0.88 for Cyclotella ocellata, Sphaerocystis schroeteri, Staurastrum longiradiatum counts, and Chlorophyll-a (Chl-a) concentrations respectively with AN. The performance of AN based pre-processing technique was compared with the performance of a well-known pre-processing technique, namely Principle Component Analysis(PCA), experimentally. r values between the predicted and observed C. ocellata, S. schroeteri and S. longiradiatum counts, and (Chl-a) were as high as 0.80, 0.86, 0.81 and 0.86 respectively with PCA.     

Media optimization for biosurfactant production by <Emphasis Type="Italic">Rhodococcus erythropolis</Emphasis> MTCC 2794: artificial intelligence versus a statistical approach

This paper entails a comprehensive study on production of a biosurfactant from Rhodococcus erythropolis MTCC 2794. Two optimization techniques—(1) artificial neural network (ANN) coupled with genetic algorithm (GA) and (2) response surface methodology (RSM)—were used for media optimization in order to enhance the biosurfactant yield by Rhodococcus erythropolis MTCC 2794. ANN and RSM models were developed, incorporating the quantity of four medium components (sucrose, yeast extract, meat peptone, and toluene) as independent input variables and biosurfactant yield [calculated in terms of percent emulsification index (% EI₂₄)] as output variable. ANN-GA and RSM were compared for their predictive and generalization ability using a separate data set of 16 experiments, for which the average quadratic errors were ~3 and ~6%, respectively. ANN-GA was found to be more accurate and consistent in predicting optimized conditions and maximum yield than RSM. For the ANN-GA model, the values of correlation coefficient and average quadratic error were ~0.99 and ~3%, respectively. It was also shown that ANN-based models could be used accurately for sensitivity analysis. ANN-GA-optimized media gave about a 3.5-fold enhancement in biosurfactant yield.     

Artificial neural networks for qualitative and quantitative analysis of target proteins with polymerized liposome vesicles

We investigate the feasibility of using the luminescence response of polymerized liposomes incorporating ethylenediaminetetraacetate europium(III) (EDTA-Eu(3+)) for monitoring protein concentrations in aqueous media. Quantitative analysis is based on the linear relationship between the luminescence enhancement of the lanthanide ion and protein concentration. Analytical figures of merit are presented for carbonic anhydrase, human serum albumin, gamma-globulins, and thermolysin. Qualitative analysis is based on the luminescence lifetime of the liposome sensor. This parameter, which follows well-behaved single exponential decays and provides characteristic values for each of the four studied proteins, demonstrates the selective potential for protein identification. Then partial least squares-1 and artificial neural networks are compared toward the quantitative and qualitative analysis of human serum albumin and carbonic anhydrase in binary mixtures without previous separation at the concentration levels found in aqueous humor.     

Glucose concentration determination by means of fluorescence emission spectra of soluble and insoluble glucose oxidase: some useful indications for optical fibre-based sensors

By using soluble and insoluble glucose oxidase, the changes in intrinsic emission fluorescence in the visible spectral region were studied as a function of glucose concentration. Insoluble glucose oxidase (GOD) was obtained by entrapment in a gelatine membrane or by covalent attachment on an agarose membrane grafted with hexamethylendiamine. The intensity of the fluorescence emission peak at 520 nm or the value of the integral fluorescence area from 480 to 580 nm were taken as physical parameters representative of the glucose concentration during the enzyme reaction. By using these parameters, linear calibration curves for glucose concentration were obtained. The extension of the calibration curve and the sensitivity of the adopted systems were found to be dependent on the enzyme state (free or immobilized) and on the immobilization method. In particular, it was found that the extent of the linear range of the calibration curves is increased of one order of magnitude when the glucose oxidase is immobilized, while the sensitivity of the measure is decreased of one order of magnitude by the immobilization process. Measures carried out by using the integral fluorescence area resulted more sensitive than those obtained with the peak size. Useful indications for the construction of optical fibre-based sensors were drawn from the reported results.     

Phytoplankton community dynamics of two adjacent Dutch lakes in response to seasons and eutrophication control unravelled by non-supervised artificial neural networks

Long-term time-series of the eutrophic Dutch lakes Veluwemeer and Wolderwijd were subject to ordination and clustering by means of non-supervised artificial neural networks (ANN). A combination of bottom-up and top-down eutrophication control measures has been implemented in both lakes since 1979. Dividing time-series data from 1976 to 1993 into three distinctive management periods has facilitated a comparative analysis of the two lakes regarding both the seasonal and long-term dynamics in response to eutrophication control. Results of the study have demonstrated that non-supervised ANN are an alternative technique: (1) to elucidate causal relationships of complex ecological processes, and (2) to reveal long-term behaviours of ecosystems in response to different management approaches. It has been shown that external nutrient control combined with food web manipulation have turned both lakes from nitrogen to phosphorus limitation, and from blue-green algae to diatom and green algae dominance.     

The potential of random forest and neural networks for biomass and recombinant protein modeling in Escherichia coli fed‐batch fermentations

Product quality assurance strategies in production of biopharmaceuticals currently undergo a transformation from empirical “quality by testing” to rational, knowledge‐based “quality by design” approaches. The major challenges in this context are the fragmentary understanding of bioprocesses and the severely limited real‐time access to process variables related to product quality and quantity. Data driven modeling of process variables in combination with model predictive process control concepts represent a potential solution to these problems. The selection of statistical techniques best qualified for bioprocess data analysis and modeling is a key criterion. In this work a series of recombinant Escherichia coli fed‐batch production processes with varying cultivation conditions employing a comprehensive on‐ and offline process monitoring platform was conducted. The applicability of two machine learning methods, random forest and neural networks, for the prediction of cell dry mass and recombinant protein based on online available process parameters and two‐dimensional multi‐wavelength fluorescence spectroscopy is investigated. Models solely based on routinely measured process variables give a satisfying prediction accuracy of about ± 4% for the cell dry mass, while additional spectroscopic information allows for an estimation of the protein concentration within ± 12%. The results clearly argue for a combined approach: neural networks as modeling technique and random forest as variable selection tool.     

A comparative assessment of support vector regression,artificial neural networks,and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape

Soil organic carbon (SOC) is a key indicator of ecosystem health, with a great potential to affect climate change. This study aimed to develop, evaluate, and compare the performance of support vector regression (SVR), artificial neural network (ANN), and random forest (RF) models in predicting and mapping SOC stocks in the Eastern Mau Forest Reserve, Kenya. Auxiliary data, including soil sampling, climatic, topographic, and remotely-sensed data were used for model calibration. The calibrated models were applied to create prediction maps of SOC stocks that were validated using independent testing data. The results showed that the models overestimated SOC stocks. Random forest model with a mean error (ME) of −6.5 Mg C ha⁻¹ had the highest tendency for overestimation, while SVR model with an ME of −4.4 Mg C ha⁻¹ had the lowest tendency. Support vector regression model also had the lowest root mean squared error (RMSE) and the highest R² values (14.9 Mg C ha⁻¹ and 0.6, respectively); hence, it was the best method to predict SOC stocks. Artificial neural network predictions followed closely with RMSE, ME, and R² values of 15.5, −4.7, and 0.6, respectively. The three prediction maps broadly depicted similar spatial patterns of SOC stocks, with an increasing gradient of SOC stocks from east to west. The highest stocks were on the forest-dominated western and north-western parts, while the lowest stocks were on the cropland-dominated eastern part. The most important variable for explaining the observed spatial patterns of SOC stocks was total nitrogen concentration. Based on the close performance of SVR and ANN models, we proposed that both models should be calibrated, and then the best result applied for spatial prediction of target soil properties in other contexts.     

Biosorption of Acid Black 172 and Congo Red from aqueous solution by nonviable Penicillium YW 01: Kinetic study, equilibrium isotherm and artificial neural network modeling

The main objective of this work was to investigate the biosorption performance of nonviable Penicillium YW 01 biomass for removal of Acid Black 172 metal-complex dye (AB) and Congo Red (CR) in solutions. Maximum biosorption capacities of 225.38 and 411.53 mg g⁻¹ under initial dye concentration of 800 mg L⁻¹, pH 3.0 and 40 °C conditions were observed for AB and CR, respectively. Biosorption data were successfully described with Langmuir isotherm and the pseudo-second-order kinetic model. The Weber-Morris model analysis indicated that intraparticle diffusion was the limiting step for biosorption of AB and CR onto biosorbent. Analysis based on the artificial neural network and genetic algorithms hybrid model indicated that initial dye concentration and temperature appeared to be the most influential parameters for biosorption process of AB and CR onto biosorbent, respectively. Characterization of the biosorbent and possible dye-biosorbent interaction were confirmed by Fourier transform infrared spectroscopy and scanning electron microscopy.     

Analysis of two chloride requirements for sodium-dependent amino acid and glucose transport by intestinal brush-border membrane vesicles of fish

Intestinal brush border vesicles of a Mediterranean sea fish (Dicentrarchus labrax) were prepared using the Ca²⁺-sedimentation method. The transport of glucose, glycine and 2-aminoisobutyric acid is energized by an Na⁺ gradient ($\text{out > in}$). In addition, amino acid uptake requires Cl^? in the extravesicular medium (2-aminoisobutyric acid more than glycine). This Na⁺- and Cl^?-dependent uptake is electrogenic, since it can be stimulated by negative charges inside the vesicles. The specific Cl^? requirement of glycine and 2-aminoisobutyric acid transport is markedly influenced by pH, a change from 6.5 to 8.4 reducing the role played by Cl^?. In the presence of Cl^?, the $\text{K}{}_{\mathrm{<mtext>m</mtext>}}$ of 2-aminoisobutyric acid uptake is reduced and its $\text{V}{}_{\mathrm{<mtext>max</mtext>}}$ is enhanced. Cl^? affects also a non-saturable Na⁺-dependent component of this amino acid uptake. Amino acid transport is also increased by intravesicular Cl^? (2-aminoisobutyric acid less than glycine). This effect is more concerned with glucose uptake, which can be then multiplied by 2.3. A concentration gradient ($\text{in > out}$) as well as the presence of Na⁺ in the incubation medium seems to enter into this requirement. This intravesicular Cl^? effect is not influenced by pH between 6.5 and 8.4.