Counter Propagation Research Articles

Calculating curly arrows from ab initio wavefunctions

Despite being at the heart of chemical thought, the curly arrow notation of reaction mechanisms has been treated with suspicion—the connection with rigorous molecular quantum mechanics being unclear. The connection requires a view of the wavefunction that goes beyond molecular orbitals and rests on the most fundamental property of electrons. The antisymmetry of electronic wavefunctions requires that an N-electron wavefunction repeat itself in 3N dimensions, thus exhibiting tiles. Inspection of wavefunction tiles permits insight into structure and mechanism. Here, we demonstrate that analysis of the wavefunction tile along a reaction coordinate reveals the electron movements depicted by the curly arrow notation for several reactions. The Diels–Alder reaction is revealed to involve the separation and counter propagation of electron spins. This unprecedented method of extracting the movements of electrons during a chemical reaction is a breakthrough in connecting traditional depictions of chemical mechanism with state-of-the-art quantum chemical calculations.

Gradient evolution-based counter propagation network for approximation of noncanonical system

In this paper, gradient evolution-based counter propagation network (GE-CPN) is developed for approximation of noncanonical form of nonlinear system and compared with some existing neural networks. GE-CPN is a multilayer feed-forward neural network, in which initial weights are assigning by the minimization of fitness function, i.e., mean-square error (MSE). An important feature of GE-CPN networks is learning from input data of nonlinear systems with parametric uncertainties. Under the framework of nonlinear system approximation using soft computing method, a new method GE-CPN is used to approximate the noncanonical systems. Adaptive and robust control of noncanonical systems in the presence of parameterization of system dynamics is much difficult. GE-CPN is used for approximation of noncanonical nonlinear systems at relative degree of accuracy. This paper shows that it is necessary to reparameterize neural network model and that such reparameterization is helpful for approximation of noncanonical systems. To demonstrate the effectiveness of GE-CPN method, simulation has been carried out by four noncanonical nonlinear systems.

Category Maps Describe Driving Episodes Recorded with Event Data Recorders

This study was conducted to create driving episodes using machine-learning-based algorithms that address long-term memory (LTM) and topological mapping. This paper presents a novel episodic memory model for driving safety according to traffic scenes. The model incorporates three important features: adaptive resonance theory (ART), which learns time-series features incrementally while maintaining stability and plasticity; self-organizing maps (SOMs), which represent input data as a map with topological relations using self-mapping characteristics; and counter propagation networks (CPNs), which label category maps using input features and counter signals. Category maps represent driving episode information that includes driving contexts and facial expressions. The bursting states of respective maps produce LTM created on ART as episodic memory. For a preliminary experiment using a driving simulator (DS), we measure gazes and face orientations of drivers as their internal information to create driving episodes. Moreover, we measure cognitive distraction according to effects on facial features shown in reaction to simulated near-misses. Evaluation of the experimentally obtained results show the possibility of using recorded driving episodes with image datasets obtained using an event data recorder (EDR) with two cameras. Using category maps, we visualize driving features according to driving scenes on a public road and an expressway.

Comparison Performance Evaluation of Modified Genetic Algorithm and Modified Counter Propagation Network for Online Character Recognition

This paper carries out performance evaluation of a Modified Genetic Algorithm (MGA) and Modified Counter Propagation Network (MCPN) Network for online character recognition. Two techniques were used to train the feature vectors using supervised and unsupervised methods. First, the modified genetic algorithm used feature selection to filter irrelevant features vectors and improve character recognition because of its stochastic nature. Second, MCPN has its capability to extract statistical properties of the input data. MGA and MCPN techniques were used as classifiers for online character recognition then evaluated using 6200-character images for training and testing with best selected similarity threshold value. The experimental results of evaluation showed that, at 5 x 7 pixels, MGA had 97.89% recognition accuracy with training time of 61.20ms while MCPN gave 97.44% recognition accuracy in a time of 62.46ms achieved. At 2480, MGA had 96.67% with a training time of 4.53ms, whereas MCPN had 96.33% accuracy with a time of 4.98ms achieved. Furthermore, at 1240 database sizes, MGA has 96.44 % recognition accuracy with 0.62ms training time whereas MCPN gave 96.11% accuracy with 0.75ms training time. The two techniques were evaluated using different performance metrics. The results suggested the superior nature of the MGA technique in terms of epoch, recognition accuracy, convergence time, training time and sensitivity.

Real-time simultaneous detection of microbial contamination and determination of an ultra low-content active pharmaceutical ingredient in tazarotene gel by near-infrared spectroscopy.

This paper proposes and proves a real-time and non-destructive strategy for sensitive and simultaneous detection of microbial contamination and determination of an ultra low-content active pharmaceutical ingredient in tazarotene gel by near-infrared (NIR) spectroscopy. In this experiment, 88 samples of tazarotene gel (0.41–0.65 mg g−1 of tazarotene) were prepared using the standard addition method. Among them, 47 samples were inoculated with 50 μl of different concentrations of Escherichia coli (E. coli) DH5a in Luria–Bertani (LB) broth to give 1–4 log CFU g−1 of E. coli DH5a in the gel, 6 samples with 50 μl of LB broth, and 35 samples with nothing. Based on the gel NIR transflectance spectra, E. coli DH5a in the gel was detected by the counter propagation artificial neural network (CP-ANN) model with a classification accuracy of 100.0%, while tazarotene in the gel was simultaneously determined by the partial least squares regression (PLS) model with a root mean square error of cross-validation of 0.0232 mg g−1. Furthermore, 9 samples of real tazarotene gel were used to verify the practicality of the established NIR spectroscopy. The developed NIR strategy can be used to correctly and quickly release the pharmaceutical gels, required for sensitive and simultaneous control of microbial contamination and the active pharmaceutical ingredient (API) content, to the next stage.

Non-Rectangular RoI Extraction and Machine Learning Based Multiple Object Recognition Used for Time-Series Areal Images Obtained Using MAV

This paper presents a novel method to recognize multiple objects from aerial scene images obtained using a micro air vehicle (MAV). As a robot vision extended platform, MAVs measure objects in time-series images obtained from various angles and altitudes with advanced outstanding active vision characteristics. The proposed method consists of four major steps: region of interest (RoI) extraction using binarized normed gradients (BING), feature point detection and description using accelerated-KAZE (AKAZE), generation of codebook as histogram features quantized using self-organizing map (SOMs), and semantic recognition of multiple objects using category maps created using counter propagation networks (CPNs). We obtained five datasets of time-series aerial images at an atrium while flying a MAV manually. The original video images were downsampled from 30 fps to 1 fps in consideration of calculation cost and appearance changes between frames. We annotated ground truth (GT) labels to all images used for teaching signals for learning and validation signals for testing. Experimentally obtained results with leave-one-out cross-validation (LOOCV) revealed the mean recognition accuracy for all datasets as 71.96%. For each dataset, the maximum and minimum recognition accuracies were, respectively, 77.26% in Dataset 3 and 65.25% in Dataset 2.

GreenSched: An intelligent energy aware scheduling for deadline-and-budget constrained cloud tasks

The constant growth of the energy crisis within the ICT Sector has persistently gained importance thereby prompting endeavors to curb growing energy demands and associated expenditures. This paper attempts to propose an intelligent energy aware task allocation and resource provisioning technique running in GreenSched model. The GreenSched model tends to exploit the heterogeneity of tasks and multi-core capacity of the varied nodes in the cloud environment and attempts to proactively schedule the deadline-and budget- constrained tasks on identified less energy consuming or energy aware nodes. It implements a Forward-only Counter Propagation Network (CPN) based intelligent scheduler unit that runs a scheduling technique to identify the best nodes for the task allocation process, one with least energy consumption and deadline- and budget -fulfilling capability. The nodes are clustered and classified by comparing their energy consumption values. The proposed algorithm has been implemented using the CloudSim toolkit and Kohonen and CP-ANN Toolbox with the help of MatlabTM platform. The experimental results exhibit that the proposed technique offers reduced energy consumption along with an overall improvement in the performance by meeting the deadline-and-budget constraints imposed by the users.

Turbulent amplification of magnetic field in laser plasma interaction and astrophysical plasmas

The investigation of the nonlinear evolution of magnetosonic wave (MSW) in the presence of density fluctuations at the background has been presented in this paper. The propagation of a single beam or counter propagation of beams is assumed to change the background density accordingly. The model equation for MSW has been obtained by considering the effect of modified plasma density in the background, along with the nonlinear ponderomotive force. The equation so found has been numerically solved to study its effect on the localization of MSW. From the results, the localized and filamentary structures of the MSW can be observed. The effect of variation of the amplitude of density perturbation has been studied on the amplification of magnetic field. To get better insight of these structures, a semi-analytical model with paraxial approximation has been studied. The effect of background density fluctuations on the resulting turbulent spectrum has been evaluated. The results show that the turbulent spectrum gets flattened towards smaller scales as the counter propagation of beams takes place as compared to the single beam propagation. The nonlinear interaction presented here may be important in interpreting the phenomenon of turbulence and magnetic field amplification due to mergers and jets in central galaxy.

Image Recognition from Face Feature Descriptor Using Counter Propagation Neural Network

Image Recognition from Face Feature Descriptor Using Counter Propagation Neural Network

The way to cover prediction for cytotoxicity for all existing nano-sized metal oxides by using neural network method

The regulatory agencies should fulfil the data gap in toxicity for new chemicals including nano-sized compounds, like metal oxides nanoparticles (MeOx NPs) according to the registration, evaluation, authorisation and restriction of chemicals (REACH) legislation policy. This study demonstrates the perspective capability of neural network models for prediction of cytotoxicity of MeOx NPs to bacteria Escherichia coli (E. coli) for the widest range of metal oxides extracted from Periodic table. The counter propagation artificial neural network (CP ANN) models for prediction of cytotoxicity of MeOx NPs for data sets of 17, 36 and 72 metal oxides were employed in the study. The cytotoxicity of studied metal oxide NPs was correlated with (i) χ-metal electronegativity (EN) by Pauling scale and composition of metal oxides characterised by (ii) number of metal atoms in oxide, (iii) number of oxygen atoms in oxide and (iv) charge of metal cation in oxide. The paper describes the models in context of five OECD principles of validation models accepted for regulatory use. The recommendations were done for the minimal number of cytotoxicity tests needs for evaluation of the large set of MeOx with different oxidation states. The methodology is expected to be useful for potential hazard assessment of MeOx NPs and prioritisation for further testing and risk assessment.

Detection of Silybum marianum infection with Microbotryum silybum using VNIR field spectroscopy

Microbotryum silybum is a smut fungus infecting Silybum marianum (milk thistle) weed and is currently investigated as a means for its biological control. Although the fungus' detection is important for the evaluation of biological control effectiveness and decision making, in-situ diagnosis is not always possible. The presented approach describes the identification of systemically infected S. marianum plants by using field spectroscopy and hierarchical self-organizing maps. An experimental field that contained both healthy and artificially inoculated S. marianum plants was used to acquire leaf spectra using a handheld visible and near-infrared spectrometer (310–1100nm). Three supervised hierarchical self-organizing models, including Supervised Kohonen Network (SKN), Counter propagation Artificial Neural Network (CP-ANN) and XY-Fusion network (XY-F) were utilized for the identification of the systemically infected S. marianum plants. As input features to the classifiers, the pre-processed spectral signatures were used. The pre-processing of the spectra included normalisation, second derivative and principal component extraction. The systemically infected S. marianum identification rates using SKN and CP-ANN reached high overall accuracy (up to 90%) and even higher using the XY-F (95.16%). The results demonstrate the potential for a high accuracy identification of systemically infected S. marianum plants during vegetative growth, with the assistance of hierarchical self-organizing maps.

Classification of sphingosine kinase inhibitors using counter propagation artificial neural networks: A systematic route for designing selective SphK inhibitors

Accurate and robust classification models for describing and predicting the activity of 330 chemicals that are sphingosine kinase 1 (SphK1) and/or sphingosine kinase 2 (SphK2) inhibitors were derived. The classification models developed in this work assist in finding selective subspaces in chemical space occupied by particular groups of SphK inhibitors. A combination of a genetic algorithm (GA) and a counter propagation artificial neural network (CPANN) was utilized to select the most efficient subsets of the molecular descriptors. The optimized models in this work reasonably separate active inhibitors of SphK1 from active SphK2 inhibitors. Generally, the CPANN models in this work were used to classify the compounds according to their therapeutic targets and activities. The simplicity of the chosen descriptors and their relative importance sheds some light on the structural features necessary to induce selective inhibitory activity to the studied molecules. The areas under the receiver operating characteristic (ROC) curves for the GA–CPANN models in this work were 0.934 and 0.922 for active SphK1 and SphK2 inhibitors, respectively. Generally, the results in this work suggest some important molecular features and pharmacophores that could help medicinal chemists develop selective and potent SphK inhibitors.

Application of multiple self‐organizing maps for classification of soil samples in Thailand according to their geographic origins

Multiple self‐organizing maps (SOMs) were applied to classify soil samples according to their geographic origins. The soil physical and chemical parameters, including textures, pH, and chemical nutrients, were analyzed and used for establishing the chemometric models. To determine the optimum size and arrangement of the maps, we adapted a growing self‐organizing map algorithm. To evaluate the reliability of the models, we calculated statistic indices based on the majority vote including percentage predictive ability, percentage model stability, and percentage correctly classified using a bootstrap methodology. For means of comparison, we also used linear discriminant analysis, quadratic discriminant analysis, partial least squares‐discriminant analysis, soft independent modeling of class analogy, counter propagation network, supervised Kohonen network, and k‐nearest neighbors. In comparison to a single SOM, multiple SOMs clearly provided better classification results. The extension of multiple SOMs also led to the best discrimination of the soil origins.

Modified Chaotic Bat Algorithm Based Counter Propagation Neural Network for Uncertain Nonlinear Discrete Time System

Weight and bias connection are important features of neural networks, which is still challenging for researchers. In this work, we focus on initial weights and bias connection of counter propagation network (CPN) using modified chaotic bat algorithm (MCBA) i.e., MCBA-CPN for uncertain nonlinear systems and compare it with CPN using chaotic bat algorithm (CBA) i.e., CBA-CPN. Chaotic function is used for pulse frequency of bats in MCBA. We have implemented CBA and MCBA, which are based on the consideration of the global solution in the sound intensity adjustment. MCBA-CPN is applied on different uncertain nonlinear systems and Mackey–Glass time series data to test the concert in terms of prediction accuracy. Proposed method is validated through statistical testing like chi-square and [Formula: see text]-test demonstrate that the difference between target and output of proposed method are acceptable. Finally, MCBA-CPN is applied to a real world problem for prediction of milk production data.

Hybridisation of Mel Frequency Cepstral Coefficient and Higher Order Spectral Features for Musical Instruments Classification

Abstract This paper presents the classification of musical instruments using Mel Frequency Cepstral Coefficients (MFCC) and Higher Order Spectral features. MFCC, cepstral, temporal, spectral, and timbral features have been widely used in the task of musical instrument classification. As music sound signal is generated using non-linear dynamics, non-linearity and non-Gaussianity of the musical instruments are important features which have not been considered in the past. In this paper, hybridisation of MFCC and Higher Order Spectral (HOS) based features have been used in the task of musical instrument classification. HOS-based features have been used to provide instrument specific information such as non-Gaussianity and non-linearity of the musical instruments. The extracted features have been presented to Counter Propagation Neural Network (CPNN) to identify the instruments and their family. For experimentation, isolated sounds of 19 musical instruments have been used from McGill University Master Sample (MUMS) sound database. The proposed features show the significant improvement in the classification accuracy of the system.

An evaluation of regionalization and watershed classification schemes for continuous daily streamflow prediction in ungauged watersheds

Regionalization – the process of transferring hydrological information from gauged to ungauged watersheds – has the potential to perform significantly better if these watersheds are classified in advance. In this study, we demonstrate the benefits of classification by a systematic combination of watershed classification techniques, regionalization methods, and rainfall-runoff models. Basins are first classified, then regionalization methods are applied, for continuous daily streamflow estimation at ungauged watersheds in Ontario, Canada. Nonlinear data-driven methods are used as regionalization and watershed classification schemes to transfer the parameters of two conceptual hydrologic models – namely McMaster University Hydrologiska Byråns Vattenbalansavdelning (MAC-HBV) and Sacramento Soil Moisture Accounting (SAC-SMA) – from gauged to ungauged watersheds. Our results suggest that a certain combination of watershed classification technique, regionalization method and hydrologic model can significantly improve the estimation of continuous streamflow at ungauged basins by improving the accuracy of estimated daily mean, low and peak flows. However, some combinations do not provide a clear improvement when compared to the scenario of unclassified basins. For example, the MAC-HBV model coupled with a counter propagation neural network as a regionalization technique provides a clear improvement in estimated daily mean, low and peak flow when the watersheds are first classified using a nonlinear principal component analysis method. Interestingly, a higher improvement is achieved for low flow as well, which is usually difficult to estimate in ungauged basins.

Neural based Security Approach for Cloud Databases using Counter Propagation

Neural Network is an efficient implementing technique for cryptographic algorithms to provide security in cloud environment. Cloud Computing is an outsourced on-demand computing service, where Privacy preserving is very difficult to provide. Secured Data Sharing is important in cloud storage aspect. The proposed Neural Data Security Model ensures high data confidentiality and security in cloud database environment. This Model is a combination of , Sensitive Data Component (SDC) and Counter Propagation Neural Data Security Component (CPNDSC). The Sensitive data Component is implemented for storing the fragmented sensitive data. In Neural Data Security Component the Neural cryptographic algorithm is used to encrypt the sensitive data to enhance the confidentiality level by using Counter Propagation Neural Network.This reasearch is carried on cloud databases and artificial Neural Network that achieves high data security in cloud environment.

LiNbO 3 thin film ACP phase modulator for hybridly integrated ACP‐OPLL

The first LiNbO3 thin film attenuated counter propagation (ACP) phase modulator is presented. The modulator demonstrates a Vπ of 2.5 V and a record 3 dB ACP modulator bandwidth of ∼1.8 GHz. It also demonstrated a lumped element response that is free of propagation delay. This device should be able to be integrated with external photodetectors to form a wideband ACP-optical phase lock loop.

Pattern recognition analysis of chromatographic fingerprints of Crocus sativus L. secondary metabolites towards source identification and quality control.

Chromatographic fingerprinting is an effective methodology for authentication and quality control of herbal products. In the presented study, a chemometric strategy based on multivariate curve resolution-alternating least squares (MCR-ALS) and multivariate pattern recognition methods was used to establish a gas chromatography-mass spectrometry (GC-MS) fingerprint of saffron. For this purpose, the volatile metabolites of 17 Iranian saffron samples, collected from different geographical regions, were determined using the combined method of ultrasound-assisted solvent extraction (UASE) and dispersive liquid-liquid microextraction (DLLME), coupled with GC-MS. The resolved elution profiles and the related mass spectra obtained by an extended MCR-ALS algorithm were then used to estimate the relative concentrations and to identify the saffron volatile metabolites, respectively. Consequently, 77 compounds with high reversed match factors (RMFs > 850) were successfully determined. The relative concentrations of these compounds were used to generate a new data set which was analyzed by multivariate data analysis methods including principal component analysis (PCA) and k-means. Accordingly, the saffron samples were categorized into five classes using these techniques. The results revealed that 11 compounds, as biomarkers of saffron, contributed to the class discrimination and characterization. Eleven biomarkers including nine secondary metabolites of saffron (safranal, α- and β-isophorone, phenylethyl alcohol, ketoisophorone, 2,2,6-trimethyl-1,4-cyclohexanedione, 2,6,6-trimethyl-4-oxo-2-cyclohexen-1-carbaldehyde, 2,4,4-trimethyl-3-carboxaldehyde-5-hydroxy-2,5-cyclohexadien-1-one, and 2,6,6-trimethyl-4-hydroxy-1-cyclohexene-1-carboxaldehyde (HTCC)), a primary metabolite (linoleic acid), and a long chain fatty alcohol (nanocosanol) were distinguished as the saffron fingerprint. Finally, the individual contribution of each biomarker to the classes was determined by the counter propagation artificial neural network (CPANN) method.

Performance Evaluation of an Improved Self-organizing Feature Map and Modified Counter Propagation Network in Face Recognition

Performance Evaluation of an Improved Self-organizing Feature Map and Modified Counter Propagation Network in Face Recognition