94 results on '"Counter propagation"'
Search Results
2. Detection of fraud in lime juice using pattern recognition techniques and FT‐IR spectroscopy
- Author
-
Mohsen Barzegar, Ahmad Mani-Varnosfaderani, and Amirhossein Mohammadian
- Subjects
Citrus aurantifolia ,FT‐IR spectroscopy ,01 natural sciences ,0404 agricultural biotechnology ,TX341-641 ,Cluster analysis ,Original Research ,Mathematics ,Lime Juice ,Nutrition. Foods and food supply ,business.industry ,010401 analytical chemistry ,Counter propagation ,modeling ,Pattern recognition ,04 agricultural and veterinary sciences ,Citrus limetta ,040401 food science ,0104 chemical sciences ,classification ,Principal component analysis ,Pattern recognition (psychology) ,Ft ir spectroscopy ,Artificial intelligence ,lime juice ,business ,artificial neural networks ,Food Science - Abstract
The lime juice is one of the products that has always fallen victim to fraud by manufacturers for reducing the cost of products. The aim of this research was to determine fraud in distributed lime juice products from different factories in Iran. In this study, 101 samples were collected from markets and also prepared manually and finally derived into 5 classes as follows: two natural classes (Citrus limetta, Citrus aurantifolia), including 17 samples, and three reconstructed classes, including 84 samples (made from Spanish concentrate, Chinese concentrate, and concentrate containing adulteration compounds). The lime juice samples were freeze‐dried and analyzed using FT‐IR spectroscopy. At first, principal component analysis (PCA) was applied for clustering, but the samples were not thoroughly clustered with respect to their original groups in score plots. To enhance the classification rates, different chemometric algorithms including variable importance in projection (VIP), partial least square‐discriminant analysis (PLS‐DA), and counter propagation artificial neural networks (CPANN) were used. The best discriminatory wavenumbers related to each class were selected using the VIP‐PLS‐DA algorithm. Then, the CPANN algorithm was used as a nonlinear mapping tool for classification of the samples based on their original groups. The lime juice samples were correctly designated to their original groups in CPANN maps and the overall accuracy of the model reached up to 0.96 and 0.87 for the training and validation procedures. This level of accuracy indicated the FT‐IR spectroscopy coupled with VIP‐PLS‐DA and CPANN methods can be used successfully for detection of authenticity of lime juice samples., In this work, the authenticity of commercial lime juice was detected and quantified using FT‐IR spectroscopy coupled with the VIP variable selection and CPANN models. The main advantage of the present contribution is the diversity of the calibrating samples which include broad ranges of natural, synthetic, and adulterated lime juice samples. Therefore, applicability domain of the developed discriminative model in this work would be broad and wide which is a needed property in fraud detection in lime juice industry. more...
- Published
- 2021
- Full Text
- View/download PDF
Catalog
3. Audio File Compression Using Counter Propagation Neural Network
- Author
-
Saja Mohammed
- Subjects
neural network ,counter propagation ,compression ,audio file ,Mathematics ,QA1-939 ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
In this paper audio files are compressed using counter propagation neural network (CPNN) which is one of the fastest neural networks in multi media. The utilized counter propagation neural network was trained on uncompressed sound file to obtain the final weights of this CPNN (Kohonen layer, Grossberg layer ). In compression operation: the sound signal segmented to number of frames equal in size. Then these frames are applied step by step, to the first layer of the neural network(kohonen layer) to obtain some compression results. The decompression operation done by retrieve stored information in resulted file. This information is applied to second layer of this CPNN (Grosberg layer) which will perform decompression operation and retrieve the original sound file. The proposed algorithm is applied on (.wav) audio files , The results show high performance in addition to short time in compression and decompression operation. more...
- Published
- 2010
- Full Text
- View/download PDF
4. The LVQ-based Counter Propagation Network -- an Interpretable Information Bottleneck Approach
- Author
-
Lucas Schwarz, Thomas Villmann, Mehrdad Mohannazadeh Bakhtiari, Ronny Schubert, and Marika Kaden
- Subjects
Learning vector quantization ,Computer science ,Counter propagation ,Information bottleneck method ,Data mining ,computer.software_genre ,computer - Published
- 2021
- Full Text
- View/download PDF
5. Advanced multivariate techniques for the classification and pollution of marine sediments due to aquaculture
- Author
-
Nikolaos S. Thomaidis, Cecile Baulard, Constantinos E. Efstathiou, Leonidas Papaharisis, Ioannis N. Pasias, Nikolaos I. Rousis, and Eleni G. Farmaki
- Subjects
Pollution ,Multivariate statistics ,Environmental Engineering ,010504 meteorology & atmospheric sciences ,business.industry ,media_common.quotation_subject ,Counter propagation ,Environmental engineering ,Sediment ,Environmental pollution ,010501 environmental sciences ,01 natural sciences ,Nutrient ,Aquaculture ,Environmental Chemistry ,Environmental science ,business ,Waste Management and Disposal ,Population dynamics of fisheries ,0105 earth and related environmental sciences ,media_common - Abstract
Aquaculture production has globally increased and its environmental impact is not well understood and assessed yet. Therefore, in this work nine metals and metalloids (Cu, Cd, Pb, Hg, Ni, Fe, Mn, Zn and As) and three nutrients (P, N and C) that seem to accumulate in marine sediments, were determined under the fish cages (zero distance) and about 50 and 100 m away from them, in three aquacultures in Greece. The analysis of these data is crucial due to the negative impact of the intensive aquaculture activities on fish population, human health and marine environment. This study investigated the environmental impact associated with aquaculture cages on marine sediments, using Supervised Artificial Neural Networks (ANNs) in parallel with Classification Trees (CTs). Optimised models were constructed in order to detect the significance of each variable, predict the origin of the sediment samples and successfully visualise their results. Three popular ANN architectures, as multi-layer perceptrons (MLPs), radial basis function (RBF) and counter propagation artificial neural networks (CP-ANNs) were used to assess the impact of the intensive aquaculture activities on marine sediments. In addition, more traditional multivariate chemometric techniques like CTs were applied to the same data set for comparison purposes. The modelling study showed that P, N, Cu, Cd were the most critical (and polluting) factors of those metals studied. Moreover, single-element models achieved elevated predictive percentages. The results were justified due to the usual practices used for fish feeding or cages maintenance. more...
- Published
- 2020
6. Resetting Threshold Values for Improving Facial Expression Recognition Accuracy
- Author
-
Yoichi Kageyama, Ryo Kiyokawa, and Masaki Ishii
- Subjects
Facial expression ,Computer science ,business.industry ,Feature vector ,Counter propagation ,Pattern recognition ,Fuzzy adaptive ,stomatognathic diseases ,Facial expression recognition ,Resonance theory ,Adaptive learning ,Artificial intelligence ,business ,Pattern learning - Abstract
When facial expression recognition is performed using a counter propagation network and fuzzy adaptive resonance theory, additional facial expression pattern learning is also performed based on the feature space of facial expression generated by the initial learning. It is necessary to carefully judge whether or not to perform this additional learning. In this study, appropriate provisional threshold values were investigated for this purpose. more...
- Published
- 2020
- Full Text
- View/download PDF
7. Novel attenuation-counter-propagating phase modulator for highly linear fiber-optic links.
- Author
-
Li, Y. and Herezfeld, P.R.
- Abstract
A key to the development of a high-dynamic-range phase-modulation fiber-optic link is a novel integrated photonic-phase-locked-loop (PPLL) linear phase demodulator, which consists of an inloop phase modulator and feedback control. At present, the propagation delay of the inloop phase modulator is the principal bottleneck in the implementation of this device. This paper specifically concerns a novel attenuation-counter-propagating (ACP) phase modulator (PM) that is free of propagation delay and therefore provides the solution. A rigorous theoretical model and an experimental verification of the ACP phase modulator were provided [ABSTRACT FROM PUBLISHER] more...
- Published
- 2006
- Full Text
- View/download PDF
8. Detection of Silybum marianum infection with Microbotryum silybum using VNIR field spectroscopy
- Author
-
Giorgos Kontouris, Alexandra A. Tamouridou, Xanthoula Eirini Pantazi, Thomas Alexandridis, Anastasia L. Lagopodi, and Dimitrios Moshou
- Subjects
Milk Thistle ,010401 analytical chemistry ,Counter propagation ,Forestry ,Smut fungus ,02 engineering and technology ,Horticulture ,Biology ,biology.organism_classification ,01 natural sciences ,0104 chemical sciences ,Computer Science Applications ,Microbotryum silybum ,Silybum marianum ,VNIR ,Botany ,0202 electrical engineering, electronic engineering, information engineering ,Field spectroscopy ,020201 artificial intelligence & image processing ,Biological system ,Weed ,Agronomy and Crop Science - Abstract
Identification of a smut fungus with no visual signs on leaves using non-destructive spectroscopy.The method was applied in-situ on live plants using low cost tools.Three innovative classifiers were tested to evaluate their performance.An independent dataset was used for the validation of the results. 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 (3101100nm). 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. more...
- Published
- 2017
- Full Text
- View/download PDF
9. A Comprehensive Cheminformatics Analysis of Structural Features Affecting the Binding Activity of Fullerene Derivatives
- Author
-
Bakhtiyor Rasulev, Katja Venko, Natalja Fjodorova, and Marjana Novič
- Subjects
Self-organizing map ,Computer science ,Priority list ,drug-like descriptors ,General Chemical Engineering ,02 engineering and technology ,010402 general chemistry ,01 natural sciences ,Article ,lcsh:Chemistry ,neural networks modelling ,General Materials Science ,Fullerene derivatives ,Counter propagation ,cheminformatics ,021001 nanoscience & nanotechnology ,0104 chemical sciences ,lcsh:QD1-999 ,Cheminformatics ,fullerene derivatives ,hydrogenation ,pharmacology ,0210 nano-technology ,Biological system ,binding activity ,toxicology - Abstract
Nanostructures like fullerene derivatives (FDs) belong to a new family of nano-sized organic compounds. Fullerenes have found a widespread application in material science, pharmaceutical, biomedical, and medical fields. This fact caused the importance of the study of pharmacological as well as toxicological properties of this relatively new family of chemicals. In this work, a large set of 169 FDs and their binding activity to 1117 disease-related proteins was investigated. The structure-based descriptors widely used in drug design (so-called drug-like descriptors) were applied to understand cheminformatics characteristics related to the binding activity of fullerene nanostructures. Investigation of applied descriptors demonstrated that polarizability, topological diameter, and rotatable bonds play the most significant role in the binding activity of FDs. Various cheminformatics methods, including the counter propagation artificial neural network (CPANN) and Kohonen network as visualization tool, were applied. The results of this study can be applied to compose the priority list for testing in risk assessment related to the toxicological properties of FDs. The pharmacologist can filter the data from the heat map to view all possible side effects for selected FDs. more...
- Published
- 2020
10. All-fiber counter-propagation pumped amplifier tailored for Coherent Beam Combining technique
- Author
-
Jason D. Tafoya, Louis Daniault, Severine Bellanger, Matthieu Veinhard, Jean-Christophe Chanteloup, Ihsan Fsaifes, Daniel S. Schulz, Donald L. Sipes, chanteloup, jean-christophe, Laboratoire pour l'utilisation des lasers intenses (LULI), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École polytechnique (X)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS) more...
- Subjects
Materials science ,[SPI.OPTI] Engineering Sciences [physics]/Optics / Photonic ,business.industry ,Scattering ,Amplifier ,Counter propagation ,Physics::Optics ,02 engineering and technology ,Nanosecond ,021001 nanoscience & nanotechnology ,7. Clean energy ,01 natural sciences ,010309 optics ,All fiber ,Fiber laser ,0103 physical sciences ,Fiber amplifier ,[SPI.OPTI]Engineering Sciences [physics]/Optics / Photonic ,Optoelectronics ,0210 nano-technology ,business ,ComputingMilieux_MISCELLANEOUS ,Beam (structure) - Abstract
International audience; we report on the qualification of an all-fiber counter propagating pumped amplifier by using a narrow-linewidth single-frequency nanosecond fiber laser. The proposed amplifier design is tailored to be used for coherent beam combining of fiber amplifiers in tiled-aperture configuration. more...
- Published
- 2020
- Full Text
- View/download PDF
11. Single-Fiber Bidirectional Filterless Metro Network
- Author
-
Marco Presi, Pantea Nadimi Goki, Andrea Sgambelluri, Filippo Cugini, and Francesco Paolucci
- Subjects
Crosstalk ,020210 optoelectronics & photonics ,Computer science ,Counter propagation ,Single fiber ,0202 electrical engineering, electronic engineering, information engineering ,Electronic engineering ,020206 networking & telecommunications ,02 engineering and technology ,Bidirectional transmission ,Transmission performance ,Frequency allocation - Abstract
Horseshoe filterless metro network is designed and experimentally validated for bidirectional transmission over a single fiber. Transmission impairments, dominated by in-band crosstalk, are specifically assessed, leading to extremely good transmission performance when misalignment in spectrum allocation is configured among the two directions. more...
- Published
- 2020
12. Neural network model for rapid forecasting of freeway link travel time
- Author
-
Dharia, Abhijit and Adeli, Hojjat
- Subjects
- *
TRAFFIC engineering , *EXPERT systems , *ARTIFICIAL neural networks , *COMPUTER science - Abstract
Estimation of freeway travel time with reasonable accuracy is essential for successful implementation of an advanced traveler information system (ATIS) for use in an intelligent transportation system (ITS). An ATIS consists of a route guiding system that recommends the most suitable route based on the traveler''s requirements using the information gathered from various sources such as loop detectors and probe vehicles. This information can be disseminated through mass media or on on-board satellite-based navigational system. Based on the estimated travel times for various routes, the traveler can make a route choice. In this article, a neural network model is presented for forecasting the freeway link travel time using the counter propagation neural (CPN) network. The performance of the model is compared with a recently reported freeway link travel forecasting model using the backpropagation (BP) neural network algorithm. It is shown that the new model based on the CPN network, and the learning coefficients proposed by Adeli and Park, is nearly two orders of magnitude faster than the BP network. As such, the proposed freeway link travel-forecasting model is particularly suitable for real-time advanced travel information and management systems. [Copyright &y& Elsevier] more...
- Published
- 2003
- Full Text
- View/download PDF
13. Asymmetric counter propagation of domain walls
- Author
-
V. Odent, I. Andrade-Silva, and Marcel G. Clerc
- Subjects
Numerical Analysis ,Bistability ,Applied Mathematics ,Counter propagation ,Type (model theory) ,01 natural sciences ,Domain (mathematical analysis) ,Symmetry (physics) ,010305 fluids & plasmas ,Physics::Fluid Dynamics ,Nonlinear system ,Classical mechanics ,Liquid crystal ,Modeling and Simulation ,Orientation (geometry) ,0103 physical sciences ,010306 general physics ,Mathematics - Abstract
Far from equilibrium systems show different states and domain walls between them. These walls, depending on the type of connected equilibria, exhibit a rich spatiotemporal dynamics. Here, we investigate the asymmetrical counter propagation of domain walls in an in-plane-switching cell filled with a nematic liquid crystal. Experimentally, we characterize the shape and speed of the domain walls. Based on the molecular orientation, we infer that the counter propagative walls have different elastic deformations. These deformations are responsible of the asymmetric counter propagating fronts. Theoretically, based on symmetry arguments, we propose a simple bistable model under the influence of a nonlinear gradient, which qualitatively describes the observed dynamics. more...
- Published
- 2016
- Full Text
- View/download PDF
14. Robust modelling of acute toxicity towards fathead minnow (Pimephales promelas) using counter-propagation artificial neural networks and genetic algorithm
- Author
-
Š Župerl, F Como, Marjan Vračko, V Drgan, and Marjana Novič
- Subjects
Cyprinidae ,Quantitative Structure-Activity Relationship ,Bioengineering ,010501 environmental sciences ,Biology ,Risk Assessment ,01 natural sciences ,Toxicology ,biology.animal ,Toxicity Tests ,Drug Discovery ,Genetic algorithm ,Animals ,Computer Simulation ,Organic Chemicals ,0105 earth and related environmental sciences ,Artificial neural network ,Counter propagation ,General Medicine ,Minnow ,Acute toxicity ,0104 chemical sciences ,010404 medicinal & biomolecular chemistry ,Molecular Medicine ,Neural Networks, Computer ,Biochemical engineering ,Pimephales promelas ,Risk assessment ,Algorithms ,Applicability domain - Abstract
Large worldwide use of chemicals has caused great concern about their possible adverse effects on human health, flora and fauna. Increased production of new chemicals has also increased demand for their risk assessment. Traditionally, results from animal tests have been used to assess toxicity of chemicals. However, such methods are ethically questionable since they involve killing and causing suffering of the test animals. Therefore, new in silico methods are being sought to replace the traditional in vivo and in vitro testing methods. In this article we report on one method that can be used to build robust models for the prediction of compounds' properties from their chemical structure. The method has been developed by combining a genetic algorithm, a counter-propagation artificial neural network and cross-validation. It has been tested using existing data on toxicity to fathead minnow (Pimephales promelas). The results show that the method may give reliable results for chemicals belonging to the applicability domain of the developed models. Therefore, it can aid the risk assessment of chemicals and consequently reduce demand for animal tests. more...
- Published
- 2016
- Full Text
- View/download PDF
15. Counter - propagation network for character recognition
- Author
-
Nguyễn Thanh Thủy and Trần Ngọc Hà
- Subjects
Computer science ,business.industry ,Counter propagation ,Pattern recognition ,Artificial intelligence ,business ,Character recognition - Published
- 2016
- Full Text
- View/download PDF
16. Investigation on factors influencing flatness of a bidirectional SOA-based multiwavelength fiber laser
- Author
-
Nelidya Md Yusoff, Muhammad Zamzuri Abdul Kadir, Fairuz Abdullah, Abdul Hadi Sulaiman, Yasmin Mustapha Kamil, Mohd Adzir Mahdi, and Noran Azizan Cholan
- Subjects
Optical amplifier ,Materials science ,business.industry ,Flatness (systems theory) ,Counter propagation ,Condensed Matter Physics ,Lyot filter ,Atomic and Molecular Physics, and Optics ,Spectral line ,Electronic, Optical and Magnetic Materials ,law.invention ,Polarization controller ,Optics ,Semiconductor ,law ,Fiber laser ,business - Abstract
We investigate the flatness of the output spectrum in two multiwavelength fiber lasers (MWFLs) using two different configurations, unidirectional and bidirectional semiconductor optical amplifiers (SOAs). The most significant finding is the large variance in flatness values between the configurations where the unidirectional SOA is at 6.54 dB and the bidirectional SOA is at 1.45 dB. This is due to the lower total power and incomplete counter propagation in the cavity. The best SOA-based MWFL using a bidirectional SOA can generate 215 spectral lines within 5 dB uniformity. The multiwavelength spectrum is flat with a broad range, about 20 nm, owing to the property of spectral reshaping by the bidirectional amplification process in the SOA as well as complete counter propagation. Apart from the bidirectional SOA, the intensity-dependent loss (IDL) mechanism also contributes to the multiwavelength spectrum flatness. The adjustment of the half-wave plate (HWP) in the polarization controller (PC) affects the wavelength range and optical signal-to-noise ratio (OSNR). The MWFL shows excellent power stability, with the highest power deviation being only 0.95 dB. more...
- Published
- 2021
- Full Text
- View/download PDF
17. Linear and nonlinear classification models for tea grade identification based on the elemental profile
- Author
-
Xiaojing Chen, Chen Xi, Guangzao Huang, Wen Shi, Liuwei Meng, Qibo Cai, and Lei-ming Yuan
- Subjects
business.industry ,010401 analytical chemistry ,Counter propagation ,Pattern recognition ,02 engineering and technology ,Exploratory analysis ,021001 nanoscience & nanotechnology ,Linear discriminant analysis ,01 natural sciences ,0104 chemical sciences ,Analytical Chemistry ,Identification (information) ,Partial least squares regression ,Artificial intelligence ,Nonlinear classification ,0210 nano-technology ,business ,Inductively coupled plasma mass spectrometry ,Spectroscopy ,Mathematics - Abstract
The content of mineral elements in tea is an important quality indicator that determines the quality and grade of tea to a certain extent. However, there are almost no studies using mineral element information to identify tea grade. To this end, the contents of 18 mineral elements from three tea grades were determined using inductively coupled plasma mass spectrometry (ICP-MS), and a few exploratory analysis methods were adopted to preliminarily analyse the dataset structure before modelling. Then the feasibility of combining elemental profiles and the two classification models partial least squares discriminant analysis (PLS-DA) and counter propagation artificial neural networks (CP-ANNs) to identify tea grade was evaluated. By comparing the performance of the PLS-DA and CP-ANNs models, better results were obtained from the PLS-DA classification model with an accuracy of 0.900, a specificity of 0.960 and a sensitivity of 0.923. The results demonstrate that it is feasible to identify tea grades using the elemental profile along with chemometric methods. Moreover, this study also provides a new perspective on the content of mineral elements as an identifier of tea grade. more...
- Published
- 2020
- Full Text
- View/download PDF
18. Real-time simultaneous detection of microbial contamination and determination of an ultra low-content active pharmaceutical ingredient in tazarotene gel by near-infrared spectroscopy
- Author
-
Xiaoxiao Zhong, Ruanqi Wu, Yanhong Dong, Xie Qian, and Fan Qi
- Subjects
Active ingredient ,Chromatography ,Chemistry ,General Chemical Engineering ,010401 analytical chemistry ,Near-infrared spectroscopy ,Counter propagation ,02 engineering and technology ,General Chemistry ,Microbial contamination ,equipment and supplies ,021001 nanoscience & nanotechnology ,01 natural sciences ,0104 chemical sciences ,Tazarotene ,Standard addition ,Partial least squares regression ,medicine ,0210 nano-technology ,Spectroscopy ,medicine.drug - Abstract
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. more...
- Published
- 2018
19. Performance Evaluation of an Improved Self-organizing Feature Map and Modified Counter Propagation Network in Face Recognition
- Author
-
O Awodoye, I Adeyanju, and E Omidiora
- Subjects
Feature (computer vision) ,Computer science ,business.industry ,Counter propagation ,General Earth and Planetary Sciences ,Pattern recognition ,Artificial intelligence ,business ,Facial recognition system ,General Environmental Science - Published
- 2016
- Full Text
- View/download PDF
20. Counter propagation auto-associative neural network based data imputation
- Author
-
Vadlamani Ravi and Chandan Gautam
- Subjects
Information Systems and Management ,Wilcoxon signed-rank test ,Artificial neural network ,Time delay neural network ,business.industry ,Computer science ,Competitive learning ,Counter propagation ,computer.software_genre ,Machine learning ,Computer Science Applications ,Theoretical Computer Science ,Auto associative neural network ,Artificial Intelligence ,Control and Systems Engineering ,Artificial intelligence ,Imputation (statistics) ,Data mining ,business ,computer ,Software - Abstract
In this paper, we propose two novel methods viz., counterpropagation auto-associative neural network (CPAANN) and grey system theory (GST) hybridised with CPAANN for data imputation. The effectiveness of these methods is demonstrated on 12 datasets and the results are compared with that of various extant methods. Wilcoxon signed rank test conducted at 1% level of significance, indicated that the proposed methods are statistically significant against all methods. The spectacular success of CPAANN can be attributed to the local learning, global approximation and auto-association that take place in tandem in a single architecture. Furthermore, significantly CPAANN turned out to be the best in the class of AANN architectures used for imputation. The reason could be the competitive learning that is intrinsic to the CPAANN architecture, but conspicuously absent in other auto-associative neural network architectures. more...
- Published
- 2015
- Full Text
- View/download PDF
21. Pattern Recognition of Movements on Bed Aimed at Prediction of Bed-leaving Behaviors
- Author
-
Nobuhiro Shimoi, Li Xu, Kazuhito Sato, and Hirokazu Madokoro
- Subjects
Series (mathematics) ,business.industry ,Computer science ,Pattern recognition (psychology) ,Counter propagation ,Pattern recognition ,Artificial intelligence ,Type (model theory) ,business ,Feature learning - Published
- 2015
- Full Text
- View/download PDF
22. Classification of Melakartha ragas using neural networks
- Author
-
Akshaya Asokan, K. Gunavathi, and R. Anitha
- Subjects
Back propagation neural network ,Network architecture ,Artificial neural network ,business.industry ,Computer science ,Feature extraction ,Counter propagation ,Pattern recognition ,Artificial intelligence ,business ,Timbre ,Classifier (UML) ,Backpropagation - Abstract
The objective of this paper is to classify all the 72 Melakartha Ragas of South Indian Carnatic Music using musical features. Melakartha raga classification is done by incorporating the well known classifier named Artificial Neural Network (ANN) which is structured by Feed-forward network architecture with back propagation learning algorithm and Counter propagation network. This paper represents one of the first attempts to classify all the seventy two Melakartha ragas of Carnatic music using ANN. The musical features that efficiently classify the Melakartha ragas are found. The classification results show that the counter propagation networks perform better classification compared to back propagation neural networks. more...
- Published
- 2017
- Full Text
- View/download PDF
23. Hepatotoxicity Modeling Using Counter-Propagation Artificial Neural Networks: Handling an Imbalanced Classification Problem
- Author
-
Benjamin Bajželj and Viktor Drgan
- Subjects
hepatotoxicity ,Quantitative structure–activity relationship ,Drug-Related Side Effects and Adverse Reactions ,Databases, Pharmaceutical ,Computer science ,Quantitative Structure-Activity Relationship ,Pharmaceutical Science ,Machine learning ,computer.software_genre ,Article ,Analytical Chemistry ,lcsh:QD241-441 ,Set (abstract data type) ,03 medical and health sciences ,0302 clinical medicine ,lcsh:Organic chemistry ,Molecular descriptor ,Drug Discovery ,Genetic algorithm ,genetic algorithm ,Computer Simulation ,Physical and Theoretical Chemistry ,counter-propagation artificial neural networks ,030304 developmental biology ,0303 health sciences ,Artificial neural network ,QSAR ,business.industry ,Balanced set ,Organic Chemistry ,Counter propagation ,Class (biology) ,Liver ,Chemistry (miscellaneous) ,030220 oncology & carcinogenesis ,imbalanced dataset ,Molecular Medicine ,Neural Networks, Computer ,Artificial intelligence ,Chemical and Drug Induced Liver Injury ,business ,computer ,Algorithms ,Databases, Chemical - Abstract
Drug-induced liver injury is a major concern in the drug development process. Expensive and time-consuming in vitro and in vivo studies do not reflect the complexity of the phenomenon. Complementary to wet lab methods are in silico approaches, which present a cost-efficient method for toxicity prediction. The aim of our study was to explore the capabilities of counter-propagation artificial neural networks (CPANNs) for the classification of an imbalanced dataset related to idiosyncratic drug-induced liver injury and to develop a model for prediction of the hepatotoxic potential of drugs. Genetic algorithm optimization of CPANN models was used to build models for the classification of drugs into hepatotoxic and non-hepatotoxic class using molecular descriptors. For the classification of an imbalanced dataset, we modified the classical CPANN training algorithm by integrating random subsampling into the training procedure of CPANN to improve the classification ability of CPANN. According to the number of models accepted by internal validation and according to the prediction statistics on the external set, we concluded that using an imbalanced set with balanced subsampling in each learning epoch is a better approach compared to using a fixed balanced set in the case of the counter-propagation artificial neural network learning methodology. more...
- Published
- 2020
- Full Text
- View/download PDF
24. Highly Effective Crosstalk Mitigation Method Using Counter-Propagation in Semiconductor Optical Amplifier for Remodulation WDM-PONs
- Author
-
Quang Thai Pham
- Subjects
Crosstalk ,Optical amplifier ,Signal processing ,Engineering ,business.industry ,Wavelength-division multiplexing ,Bit rate ,Counter propagation ,Electrical engineering ,Bit error rate ,Baseband ,Electronic engineering ,business - Abstract
Remodulation-induced crosstalk mitigation in WDM-PON using remodulation approach is presented in this paper. Utilizing all-optical signal processing, the proposed method has been able to significantly improve system performance in terms of bit error rate (BER) and bit rate distance product. Moreover, the proposed method could be used for both baseband and modulated downstream electrical signals. more...
- Published
- 2014
- Full Text
- View/download PDF
25. Research on Adaptive Quantum Forward Counter Propagation Algorithm
- Author
-
Nan Li and Xuan Hou
- Subjects
Computer science ,Counter propagation ,Electrical and Electronic Engineering ,Algorithm ,Quantum - Published
- 2014
- Full Text
- View/download PDF
26. A High Performance Liquid Chromatography and Electrospray Ionization Mass Spectrometry Method for the Analysis of the Natural Medicine,Forsythia Suspensa
- Author
-
Yongnian Ni, Hua Zhuang, and Serge Kokot
- Subjects
Forsythia suspensa ,Chromatography ,biology ,Chemistry ,Electrospray ionization ,Biochemistry (medical) ,Clinical Biochemistry ,Counter propagation ,biology.organism_classification ,Linear discriminant analysis ,Biochemistry ,High-performance liquid chromatography ,Analytical Chemistry ,Hierarchical clustering ,Principal component analysis ,Electrochemistry ,Natural medicine ,Spectroscopy - Abstract
Samples of Forsythia suspensa from raw (Laoqiao) and ripe (Qingqiao) fruit were analyzed with the use of HPLC-DAD and the EIS-MS techniques. Seventeen peaks were detected, and of these, twelve were identified. Most were related to the glucopyranoside molecular fragment. Samples collected from three geographical areas (Shanxi, Henan and Shandong Provinces), were discriminated with the use of hierarchical clustering analysis (HCA), discriminant analysis (DA), and principal component analysis (PCA) models, but only PCA was able to provide further information about the relationships between objects and loadings; eight peaks were related to the provinces of sample origin. The supervised classification models-K-nearest neighbor (KNN), least squares support vector machines (LS-SVM), and counter propagation artificial neural network (CP-ANN) methods, indicated successful classification but KNN produced 100% classification rate. Thus, the fruit were discriminated on the basis of their places of origin. more...
- Published
- 2013
- Full Text
- View/download PDF
27. Classification of sphingosine kinase inhibitors using counter propagation artificial neural networks: A systematic route for designing selective SphK inhibitors
- Author
-
M. S. Neiband, Ali Benvidi, and Ahmad Mani-Varnosfaderani
- Subjects
0301 basic medicine ,Chemistry, Pharmaceutical ,Sphingosine kinase ,Bioengineering ,Computational biology ,01 natural sciences ,03 medical and health sciences ,Molecular descriptor ,Drug Discovery ,Computer Simulation ,Enzyme Inhibitors ,biology ,Artificial neural network ,Counter propagation ,Sphingosine Kinase 2 ,General Medicine ,Chemical space ,0104 chemical sciences ,010404 medicinal & biomolecular chemistry ,SPHK2 ,Phosphotransferases (Alcohol Group Acceptor) ,030104 developmental biology ,Sphingosine kinase 1 ,Biochemistry ,ROC Curve ,biology.protein ,Molecular Medicine ,Neural Networks, Computer ,Algorithms - Abstract
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. more...
- Published
- 2017
28. Analysis of Learning Rate Using CPN Algorithm for Hand Written Character Recognition Application
- Author
-
Qamar Abbas, Waqas Haider Bangyal, and Jamil Ahmad
- Subjects
business.industry ,Computer science ,Speech recognition ,Counter propagation ,Process (computing) ,Value (computer science) ,Artificial intelligence ,business ,Algorithm ,Character recognition - Abstract
This paper presents the analysis of the learning rate using the Counter Propagation network (CPN) algorithm for the hand written characters recognition application. The recognition process uses the forward only CPN algorithm to recognize the hand written characters. The experimental results obtained with different learning rate values shows that learning rate has large effect on the recognition process. Upper-case English alphabets for a number of different styles gathered from different peoples are used in the analysis for the performance of the CPN algorithm. The obtained recognition rates were 60% to 98% using the CPN for different learning rate value. The experimental results are very encouraging and satisfactory. more...
- Published
- 2013
- Full Text
- View/download PDF
29. Recognition of Off-line Isolated Handwritten Character Using Counter Propagation Network
- Author
-
Jamil Ahmad, Qamar Abbas, and Waqas Haider Bangyal
- Subjects
Writing style ,ComputingMethodologies_PATTERNRECOGNITION ,Artificial neural network ,Character (computing) ,Intelligent character recognition ,Computer science ,Speech recognition ,Counter propagation ,Process (computing) ,Intelligent word recognition ,Off line - Abstract
This paper presents the recognition of off line handwritten English characters using the forward only Counter Propagation network (CPN) algorithm Upper case English alphabets are used in this paper. In the recognition process different people's writing style are gathered. The obtained results in this paper show the effect of the learning rate and recognition accuracy of the CPN neural network. The algorithm is tested and the recognition rate obtained was over 90%.It shows that proposed algorithm results are reasonable and acceptable for the hand written character recognition application. more...
- Published
- 2013
- Full Text
- View/download PDF
30. A Method of Improved Generalization Abilities for Support Vector Machines Using Topological Mapping on Counter Propagation Networks
- Author
-
Kazuhito Sato and Hirokazu Madokoro
- Subjects
Support vector machine ,Theoretical computer science ,business.industry ,Generalization ,Counter propagation ,Pattern recognition ,Topological mapping ,Artificial intelligence ,business ,Mathematics - Published
- 2013
- Full Text
- View/download PDF
31. A forward only counter propagation network-based approach for contraceptive method choice classification task
- Author
-
Imran Shafi, Qamar Abbas, Jamil Ahmad, and Waqas Haider Bangyal
- Subjects
Computer science ,business.industry ,Counter propagation ,Medical classification ,Self organising maps ,Machine learning ,computer.software_genre ,Theoretical Computer Science ,Artificial Intelligence ,Artificial intelligence ,Data mining ,business ,computer ,Neighbourhood (mathematics) ,Software - Abstract
This article proposes the forward only counter propagation network (FOCPN) for solving the contraceptive medical classification task. Contraceptive method choice (CMC) application is used for the medical classification and it is one of the challenging jobs in the field of the medicine. The experiments are performed on different radii of the neighbourhood and learning rate based on the size of the map. Experimental results show that FOCPN's convergence is faster and it gives the improved learning efficiency and reliable prediction performance. Also, the classification accuracy is much higher than the other models used for this purpose. more...
- Published
- 2012
- Full Text
- View/download PDF
32. Computer-aided design of novel antibacterial 3-hydroxypyridine-4-ones: application of QSAR methods based on the MOLMAP approach
- Author
-
Razieh Sabet, Ramin Miri, Lotfollah Saghaei, Bahram Hemmateenejad, Afshin Fassihi, and Maryam Gholami
- Subjects
Staphylococcus aureus ,Quantitative structure–activity relationship ,Pyridones ,Chemistry ,Counter propagation ,Quantitative Structure-Activity Relationship ,Quantitative structure ,3-hydroxypyridin-4-one ,Microbial Sensitivity Tests ,Antimicrobial ,Combinatorial chemistry ,Anti-Bacterial Agents ,Computer Science Applications ,Drug Discovery ,Evaluation methods ,Partial least squares regression ,Computer-Aided Design ,Physical and Theoretical Chemistry ,Antibacterial activity - Abstract
3-Hydroxypyridine-4-one derivatives have shown good inhibitory activity against bacterial strains. In this work we report the application of MOLMAP descriptors based on empirical physicochemical properties with genetic algorithm partial least squares (GA-PLS) and counter propagation artificial neural networks (CP-ANN) methods to propose some novel 3-hydroxypyridine-4-one derivatives with improved antibacterial activity against Staphylococcus aureus. A large collection of 302 novel derivatives of this chemical scaffold was selected for this purpose. The activity classes of these compounds were determined using the two quantitative structure activity relationships models. To evaluate the predictability and accuracy of the obtained models, nineteen compounds belonging to all three activity classes were prepared and the activity of them was determined against S. aureus. Comparing the experimental results and the predicted activity classes revealed the accuracy of the obtained models. Seventeen of the nineteen synthesized molecules were correctly predicted by GA-PLS model according to the antimicrobial evaluation method. Molecules 5f and 5h proved to be moderately active and active experimentally, but were predicted as inactive and moderately active compounds, respectively by this model. The CP-ANN based prediction was correct for sixteen out of the nineteen synthesized molecules. 5a, 5h and 5q were moderately active and active based on the antimicrobial assays, but they were introduced as members of inactive, moderately active and inactive classes of compounds, respectively according to CP-ANN model. more...
- Published
- 2012
- Full Text
- View/download PDF
33. Evaluating the applicability domain in the case of classification predictive models for carcinogenicity based on the counter propagation artificial neural network
- Author
-
Alessandra Roncaglioni, Natalja Fjodorova, Emilio Benfenati, and Marjana Novič
- Subjects
Quantitative structure–activity relationship ,Carcinogenicity Tests ,Computer science ,Quantitative Structure-Activity Relationship ,computer.software_genre ,Machine learning ,Models, Biological ,Drug Discovery ,Euclidean geometry ,Animals ,Humans ,Leverage (statistics) ,Physical and Theoretical Chemistry ,Scientific society ,Artificial neural network ,business.industry ,Counter propagation ,Computer Science Applications ,Nonlinear system ,Carcinogens ,Neural Networks, Computer ,Data mining ,Artificial intelligence ,business ,computer ,Applicability domain - Abstract
The applicability domain (AD) of models developed for regulatory use has attached great attention recently. The AD of quantitative structure-activity relationship (QSAR) models is the response and chemical structure space in which the model makes predictions with a given reliability. The evaluation of AD of regressions QSAR models for congeneric sets of chemicals can be find in many papers and books while the issue about metrics for the evaluation of an AD for the non-linear models (like neural networks) for the diverse set of chemicals represents the new field of investigations in QSAR studies. The scientific society is standing before the challenge to find out reliable way for the evaluation of an AD of non linear models. The new metrics for the evaluation of the AD of the counter propagation artificial neural network (CP ANN) models are discussed in the article: the Euclidean distances between an object (molecule) and the corresponding excited neuron of the neural network and between an object (molecule) and the representative object (vector of average values of descriptors). The investigation of the training and test sets chemicals coverage in the descriptors space was made with the respect to false predicted chemicals. The leverage approach was used to compare non linear (CP ANN) models with linear ones. more...
- Published
- 2011
- Full Text
- View/download PDF
34. Induced focusing due to counter-propagation of a pair of bright and dark optical beams in self-defocusing Kerr media
- Author
-
R. Goldouzian and M.H. Majles Ara
- Subjects
Physics ,business.industry ,Cross-phase modulation ,Counter propagation ,Physics::Optics ,Atomic and Molecular Physics, and Optics ,Electronic, Optical and Magnetic Materials ,Nonlinear optical ,Optics ,Modulation ,Physics::Accelerator Physics ,Wafer ,Electrical and Electronic Engineering ,business ,Self defocusing ,Beam (structure) - Abstract
We present two-dimensional numerical simulations of a nonlinear optical system made of a bright probe and a dark pump beam that counter propagate in a thin slice of self-defocusing Kerr media, simultaneously. The numerical results show that although the medium is self-defocusing to both pump and probe beam, a profile compression occurs under some conditions, and the weak bright probe beam is focused due to cross-phase modulation. The influence of the characteristics of beams and medium length on the probe beam compression is also investigated. more...
- Published
- 2011
- Full Text
- View/download PDF
35. Counter-propagation of harmonic waves in exponentially graded materials
- Author
-
A. Ravasoo
- Subjects
Acoustics and Ultrasonics ,business.industry ,Mechanical Engineering ,Physics::Medical Physics ,Counter propagation ,Nonlinear theory ,Mechanics ,Elasticity (physics) ,Condensed Matter Physics ,Optics ,Exponential growth ,Mechanics of Materials ,Nondestructive testing ,Harmonic ,Ultrasonic sensor ,business ,Material properties ,Mathematics - Abstract
Counter-propagation and interaction of two ultrasonic harmonic waves in strongly inhomogeneous exponentially graded material is studied. Deformations of a specimen with two parallel boundaries are described by the five-constant nonlinear theory of elasticity. One-dimensional problems are investigated in detail. The influence of material properties variation on the profile of boundary oscillations is clarified. The obtained results will be useful in ultrasonic nondestructive material characterization. more...
- Published
- 2011
- Full Text
- View/download PDF
36. Half-hourly Rainfall Monitoring over the Indochina Area from MTSAT Infrared Measurements: Development of Rain Estimation Algorithm using an Artificial Neural Network
- Author
-
Nguyen Vinh Thu and Byung-Ju Sohn
- Subjects
Estimation ,Geography ,Meteorology ,Artificial neural network ,Counter propagation ,Geostationary orbit ,Training (meteorology) ,Cloud top temperature ,Satellite imagery ,Hourly rainfall - Abstract
Summary and Discussion To estimate rain rates over the Indochina regionwhere highly populated residential areas are prone tonatural disasters, in particular those associated withheavy rainfall, we developed an ANN-based retrievalalgorithm. The method was developed by training theIR-based cloud top temperature and the temperaturedifference between the 11-µm and water vaporchannels against collocated PMW-based rain ratesusing the counter propagation network, which consistsof three layers and a linear output layer. The surfacetype and geographical location were also included asinitial inputs. We aimed to produce surface rain rateswith a 0.04 o ×0.04 o grid area and a 30-minute timeinterval from the Japanese geostationary satelliteMTSAT measurements. Training was carried out foreach individual month from June to September 2005,and the results were applied to the same months for2006.The results for the June to September 2006 rainyseason reveal that the ANN technique appears toenhance our capability for rain estimation fromgeostationary satellite imagery over the Indochinaregion, in terms of output quality and temporalresolution. It has also been shown that instantaneousrain rates with a 0.25 more...
- Published
- 2010
- Full Text
- View/download PDF
37. QSAR Models for Reproductive Toxicity and Endocrine Disruption Activity
- Author
-
Marjana Novič and Marjan Vračko
- Subjects
reproductive toxicity ,Quantitative structure–activity relationship ,In silico ,Quantitative Structure-Activity Relationship ,Pharmaceutical Science ,Estrogen receptor ,Review ,Computational biology ,Endocrine Disruptors ,Pharmacology ,Biology ,In vivo tests ,Analytical Chemistry ,lcsh:QD241-441 ,lcsh:Organic chemistry ,Drug Discovery ,Animals ,Humans ,Endocrine system ,CAESAR program ,Physical and Theoretical Chemistry ,Reproduction ,Organic Chemistry ,Counter propagation ,modeling ,Rats ,Chemistry (miscellaneous) ,counter propagation neural networks ,Molecular Medicine ,Reproductive toxicity - Abstract
Reproductive toxicity is an important regulatory endpoint, which is required in registration procedures of chemicals used for different purposes (for example pesticides). The in vivo tests are expensive, time consuming and require large numbers of animals, which must be sacrificed. Therefore an effort is ongoing to develop alternative In vitro and in silico methods to evaluate reproductive toxicity. In this review we describe some modeling approaches. In the first example we describe the CAESAR model for prediction of reproductive toxicity; the second example shows a classification model for endocrine disruption potential based on counter propagation artificial neural networks; the third example shows a modeling of relative binding affinity to rat estrogen receptor, and the fourth one shows a receptor dependent modeling experiment. more...
- Published
- 2010
- Full Text
- View/download PDF
38. Quantitative structure–activity relationship study of antitubercular fluoroquinolones
- Author
-
Marjan Vračko, Tom Solmajer, and Nikola Minovski
- Subjects
Quantitative structure–activity relationship ,Logarithm ,Antitubercular Agents ,Quantitative Structure-Activity Relationship ,computer.software_genre ,Catalysis ,Cross-validation ,Inorganic Chemistry ,Molecular descriptor ,Drug Discovery ,Linear regression ,Humans ,Physical and Theoretical Chemistry ,Molecular Biology ,Models, Statistical ,Artificial neural network ,Chemistry ,Organic Chemistry ,Counter propagation ,General Medicine ,Drug Design ,Data mining ,Biological system ,computer ,Algorithms ,Fluoroquinolones ,Information Systems - Abstract
Quantitative structure-activity relationship study on three diverse sets of structurally similar fluoroquinolones was performed using a comprehensive set of molecular descriptors. Multiple linear regression technique was applied as a preprocessing tool to find the set of relevant descriptors (10) which are subsequently used in the artificial neural networks approach (non-linear procedure). The biological activity in the series (minimal inhibitory concentration (μg/mL) was treated as negative decade logarithm, pMIC). Using the non-linear technique counter propagation artificial neural networks, we obtained good predictive models. All models were validated using cross validation leave-one-out procedure. The results (the best models: Assay1, R = 0.8108; Assay2, R = 0.8454, and Assay3, R = 0.9212) obtained on external, previously excluded test datasets show the ability of these models in providing structure-activity relationship of fluoroquinolones. Thus, we demonstrated the advantage of non-linear approach in prediction of biological activity in these series. Furthermore, these validated models could be proficiently used for the design of novel structurally similar fluoroquinolone analogues with potentially higher activity. more...
- Published
- 2010
- Full Text
- View/download PDF
39. Counter propagation artificial neural network categorical models for prediction of carcinogenicity for non-congeneric chemicals
- Author
-
Marjana Novic, Marjan Vračko, Aneta Jezierska, and Natalja Fjodorova
- Subjects
Quantitative structure–activity relationship ,Molecular Structure ,Artificial neural network ,Carcinogenicity Tests ,Computer science ,Counter propagation ,Authorization ,Quantitative Structure-Activity Relationship ,Bioengineering ,General Medicine ,Toxicology ,computer.software_genre ,Sensitivity and Specificity ,Human health ,Models, Chemical ,Research Design ,Test set ,Drug Discovery ,Categorical models ,Molecular Medicine ,Neural Networks, Computer ,Data mining ,Sensitivity (control systems) ,computer ,Software - Abstract
One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fill the gaps on the toxicological properties of chemicals that affect human health. Carcinogenicity is one of the endpoints under consideration. The information obtained from (quantitative) structure-activity relationship ((Q)SAR) models is accepted as an alternative solution to avoid expensive and time-consuming animal tests. The reported results were obtained within the framework of the European project 'Computer Assisted Evaluation of industrial chemical Substances According to Regulations (CAESAR)'. In this article, we demonstrate intermediate results for counter propagation artificial neural network (CP ANN) models for the prediction category of the carcinogenic potency using two-dimensional (2D) descriptors from different software programs. A total of 805 non-congeneric chemicals were extracted from the Carcinogenic Potency Database (CPDBAS). The resulting models had prediction accuracies for internal (training) and external (test) sets as high as 91-93% and 68-70%, respectively. The sensitivity and specificity of the test set were 69-73 and 63-72% correspondingly. High specificity is critical in models for regulatory use that are aimed at ensuring public safety. Thus, the errors that give rise to false negatives are much more relevant. We discuss how we can increase the number of correctly predicted carcinogens using the correlation between the threshold and the values of the sensitivity and specificity. more...
- Published
- 2010
- Full Text
- View/download PDF
40. Quantitative and qualitative models for carcinogenicity prediction for non-congeneric chemicals using CP ANN method for regulatory uses
- Author
-
Ralph Kühne, Marjan Tusar, Natalja Fjodorova, Gerrit Schüürmann, Marjana Novič, Marjan Vračko, and Aneta Jezierska
- Subjects
Self-organizing map ,Quantitative structure–activity relationship ,Databases, Factual ,Carcinogenicity Tests ,Quantitative Structure-Activity Relationship ,Machine learning ,computer.software_genre ,Rodent carcinogenicity ,Catalysis ,Inorganic Chemistry ,Drug Discovery ,Animals ,Humans ,Physical and Theoretical Chemistry ,Molecular Biology ,Categorical variable ,Carcinogen ,Mathematics ,Principal Component Analysis ,business.industry ,Organic Chemistry ,Counter propagation ,General Medicine ,Rats ,ROC Curve ,Test set ,Principal component analysis ,Carcinogens ,Drug and Narcotic Control ,Neural Networks, Computer ,Artificial intelligence ,business ,computer ,Information Systems - Abstract
The new European chemicals regulation Regis- tration, Evaluation, Authorization and Restriction of Chem- icals entered into force in June 2007 and accelerated the development of quantitative structure-activity relationship (QSAR) models for a variety of endpoints, including carcino- genicity. Here, we would like to present quantitative (continu- ous) and qualitative (categorical) models for non-congeneric chemicals for prediction of carcinogenic potency. A dataset of 805 substances was obtained after a preliminary screen- ing of findings of rodent carcinogenicity for 1,481 chemi- cals accessible via Distributed Structure-Searchable Toxic- ity (DSSTox) Public Database Network originated from the Lois Gold Carcinogenic Potency Database (CPDB). Twenty seven two-dimensional MDL descriptors were selected us- ing Kohonen mapping and principal component analysis. The counter propagation artificial neural network (CP ANN) technique was applied. Quantitative models were developed exploring the relationship between the experimental and pre- dicted carcinogenic potency expressed as a tumorgenic dose TD50 for rats. The obtained models showed low prediction power with correlation coefficient less than 0.5 for the test set. In the next step, qualitative models were developed. We found that the qualitative models exhibit good accuracy for the training set (92%). The model demonstrated good pre- dicted performance for the test set. It was obtained accuracy (68%), sensitivity (73%), and specificity (63%). We believe that CP ANN method is a good in silico approach for model- ing and predicting rodent carcinogenicity for non-congeneric chemicals and may find application for other toxicological endpoints. more...
- Published
- 2009
- Full Text
- View/download PDF
41. Automatic adjustment of the relative importance of different input variables for optimization of counter-propagation artificial neural networks
- Author
-
Marjana Novič, Mira Trpkovska, and Igor Kuzmanovski
- Subjects
Quantitative structure–activity relationship ,Artificial neural network ,Chemistry ,Counter propagation ,Quantitative Structure-Activity Relationship ,HIV Protease Inhibitors ,Overfitting ,computer.software_genre ,Biochemistry ,Analytical Chemistry ,Automation ,HIV Protease ,Calibration ,Genetic algorithm ,Environmental Chemistry ,Neural Networks, Computer ,Data mining ,Peptides ,computer ,Algorithms ,Spectroscopy - Abstract
In this work we present a quantitative structure–activity relationship study with 49 peptidic molecules, inhibitors of the HIV-1 protease. The modelling was preformed using counter-propagation artificial neural networks (CPANN), an algorithm which has been proven as a valuable tool for data analysis. The initial pre-processing of the data involved auto-scaling, which gives equal importance to all the variables considered in the model. In order to enhance the influence of some of the variables that carry valuable information for improvement of the model, we introduce a novel approach for adjustment of the relative importance of different input variables. Having involved a genetic algorithm, the relative importance was adjusted during the training of the CPANN. The proposed approach is capable of finding simpler efficient models, when compared to the approach with the original, i.e. equally important input variables. A simpler model also means more robust and less subjected to the overfitting model, therefore we consider the proposed procedure as a valuable improvement of the CPANN algorithm. more...
- Published
- 2009
- Full Text
- View/download PDF
42. Customer cross‐selling model based on counter propagation network
- Author
-
Chao‐hua Liu and Shu‐qin Cai
- Subjects
Marketing ,Direct marketing ,Customer orientation ,Market competition ,Cross-selling ,business.industry ,Counter propagation ,Business ,Customer group ,Demographic data ,Profit (economics) - Abstract
PurposeWith increasing market competition, enterprises have come to realize that it is easier to maximize profit by cross‐selling services to existing customers than to attract new customers. It can often be observed that consumers sequentially purchase multiple products and services from the same provider. Accordingly, this commonly observed situation offers huge opportunities for companies carrying multiple products and services to “cross‐sell” other products and services to their existing customer group. The purpose of this paper is to find out a convenient way to identify the customers with cross‐selling potential.Design/methodology/approachIn this paper, the authors investigate the customer demographic data, including age, income, gender and educational level, and study the relation between the variables and the customers' cross‐selling potential based on counter propagation network (CPN).FindingsThe authors set up a cross‐selling model successfully. After inputting age, gender, education level, and income into the input layer of the model, the model will show us which products the potential customers should buy in the output layer. This process can provide useful information for the enterprise to persuade the customers into buying the unpurchased products and provide the products to the right customer.Originality/valueIn this paper, the authors set up the cross‐selling model based on the CPN. The model can predict the customer cross‐selling potential successfully according to the customer demography data – age, income, gender, and educational level. more...
- Published
- 2008
- Full Text
- View/download PDF
43. Counter-propagation neural networks in Matlab
- Author
-
Marjana Novič and Igor Kuzmanovski
- Subjects
Artificial neural network ,business.industry ,Computer science ,Process Chemistry and Technology ,Counter propagation ,Chemical data ,Kohonen self organizing map ,Machine learning ,computer.software_genre ,Toolbox ,Computer Science Applications ,Analytical Chemistry ,Visualization ,Hybrid Kohonen self-organizing map ,Artificial intelligence ,Data mining ,business ,MATLAB ,computer ,Spectroscopy ,Software ,computer.programming_language - Abstract
The counter-propagation neural networks have been widely used by the chemometricians for more than fifteen years. This valuable tool for data analysis has been applied for solving many different chemometric problems. In this paper the implementation of counter-propagation neural networks in Matlab environment is described. The program presented here is an extension of Self-Organizing Maps Toolbox for Matlab that is not widely used by chemometricians. This program coupled with the excellent visualization tools available in Self-Organizing Maps Toolbox and with other valuable functions in this environment could be of great interest for analysis of chemical data. The use of the program is demonstrated on the development of the regression and classification models. more...
- Published
- 2008
- Full Text
- View/download PDF
44. Using a modified counter-propagation algorithm to classify conjoined data
- Author
-
Tim Hendtlass and Hans Pierrot
- Subjects
Artificial Intelligence ,Computer science ,business.industry ,Counter propagation ,Boundary (topology) ,Data mining ,Artificial intelligence ,computer.software_genre ,business ,computer - Abstract
Conjoined data is data in which the classes abut but do not overlap. It is difficult to determine the boundary between the classes, as there are no inherent clusters. As a result traditional classification methods, such as Counter-Propagation networks, may underperform. This paper describes a modified Counter-Propagation network that is able to refine the boundary definition and so perform better when classifying conjoined data. The efficiency with which network resources are used suggests that it is worthy of consideration for classifying all kinds of data, not just conjoined data. more...
- Published
- 2006
- Full Text
- View/download PDF
45. Structure-mutagenicity modelling using counter propagation neural networks
- Author
-
Denise Mills, Marjan Vračko, and Subhash C. Basak
- Subjects
Pharmacology ,Counter propagation neural network ,Quantum chemical ,Correlation coefficient ,Loo ,Artificial neural network ,Chemistry ,Health, Toxicology and Mutagenesis ,Counter propagation ,Structure (category theory) ,General Medicine ,Toxicology ,Hierarchical clustering ,Biological system - Abstract
The set of 95 aromatic amines and their mutagenic potency was treated with counter propagation neural network, which enables analysis of self-organising maps (SOMs) and also the prediction of mutagenicity. Compounds were described with four classes of descriptors: topostructural (TS), topochemical (TC), geometrical, and quantum chemical (QC). The models were tested on their prediction ability with leave-one-out (LOO) cross-validation method. The squares of correlation coefficient lie between 0.65 and 0.75 and are comparable with models obtained by linear methods. In addition, we analysed self-organising maps and found clusters of structurally similar compounds. more...
- Published
- 2004
- Full Text
- View/download PDF
46. A Comparison between a Modified Counter Propagation Network and an Extended Self-Organizing Map in Remotely Sensed Data Classification
- Author
-
Chen, Yongliang, Pazner, Micha I., and Wu, Wei
- Published
- 2007
- Full Text
- View/download PDF
47. LiNbO 3 thin film ACP phase modulator for hybridly integrated ACP‐OPLL
- Author
-
Longtao Xu, Yifei Li, and Shilei Jin
- Subjects
Materials science ,business.industry ,Counter propagation ,Bandwidth (signal processing) ,Photodetector ,02 engineering and technology ,Propagation delay ,021001 nanoscience & nanotechnology ,01 natural sciences ,010309 optics ,Phase-locked loop ,0103 physical sciences ,Electronic engineering ,Optoelectronics ,Electrical and Electronic Engineering ,Thin film ,Wideband ,0210 nano-technology ,business ,Phase modulation - Abstract
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. more...
- Published
- 2016
- Full Text
- View/download PDF
48. Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy
- Author
-
Slavica Erić, Marija Jovanović, Igor Kuzmanovski, Tomaž Vovk, Milica Prostran, Iztok Grabnar, Branislava Miljković, Katarina Vučićević, and Dragoslav Sokić
- Subjects
Adult ,Male ,Topiramate ,Population ,lcsh:RS1-441 ,Pharmaceutical Science ,Fructose ,030226 pharmacology & pharmacy ,01 natural sciences ,Machine Learning ,lcsh:Pharmacy and materia medica ,03 medical and health sciences ,Epilepsy ,0302 clinical medicine ,Statistics ,medicine ,Humans ,Drug Interactions ,In patient ,education ,Chromatography, High Pressure Liquid ,Pharmacology ,education.field_of_study ,Artificial neural network ,business.industry ,lcsh:RM1-950 ,010401 analytical chemistry ,Counter propagation ,Middle Aged ,medicine.disease ,Confidence interval ,0104 chemical sciences ,3. Good health ,Carbamazepine ,lcsh:Therapeutics. Pharmacology ,Test set ,Anticonvulsants ,Female ,Neural Networks, Computer ,business ,Algorithms ,Glomerular Filtration Rate ,medicine.drug - Abstract
Purpose: The application of artificial neural networks in the pharmaceutical sciences is broad, ranging from drug discovery to clinical pharmacy. In this study, we explored the applicability of counter-propagation artificial neural networks (CPANNs), combined with genetic algorithm (GA) for prediction of topiramate (TPM) serum levels based on identified factors important for its prediction. Methods: The study was performed on 118 TPM measurements obtained from 78 adult epileptic patients. Patients were on stable TPM dosing regimen for at least 7 days; therefore, steady-state was assumed. TPM serum concentration was determined by high performance liquid chromatography with fluorescence detection. The influence of demographic, biochemical parameters and therapy characteristics of the patients on TPM levels were tested. Data analysis was performed by CPANNs. GA was used for optimal CPANN parameters, variable selection and adjustment of relative importance. Results: Data for training included 88 measured TPM concentrations, while remaining were used for validation. Among all factors tested, TPM dose, renal function (eGFR) and carbamazepine dose significantly influenced TPM level and their relative importance were 0.7500, 0.2813, 0.0625, respectively. Relative error and root mean squared relative error (%) and their corresponding 95% confidence intervals for training set were 2.14 [(-2.41) - 6.70] and 21.5 [18.5 - 24.1]; and for test set were -6.21 [(-21.2) - 8.77] and 39.9 [31.7 - 46.7], respectively. Conclusions: Statistical parameters showed acceptable predictive performance. Results indicate the feasibility of CPANNs combined with GA to predict TPM concentrations and to adjust relative importance of identified variability factors in population of adult epileptic patients. This article is open to POST-PUBLICATION REVIEW. Registered readers (see “For Readers”) may comment by clicking on ABSTRACT on the issue’s contents page. more...
- Published
- 2015
49. Constructing the Analytic Solutions of the Em Field in Cylindrically Stratified Media By the Counter-Propagation Deduction Method
- Author
-
Q. Y. Zhang and J. M. Zhu
- Subjects
Electromagnetic field ,Wave propagation ,Mathematical analysis ,Counter propagation ,General Physics and Astronomy ,Boundary (topology) ,Geometry ,Electrical and Electronic Engineering ,Computer Science::Databases ,Analysis method ,Electronic, Optical and Magnetic Materials ,Mathematics ,Transverse mode - Abstract
—A new method, the Counter-Propagation Deduction (CPD) method is applied to deduce the Ez and Hz in a cylindrically stratified medium, from which the other components of the E and H can be deduced. By introducing a new concept, the Boundary Originated Sets (BOS), the CPD method can directly construct the analytic solutions, which, due to the simplicity of the deduction procedure and the expressions, can be easily evaluated numerically, irrespective of the number of the layers. more...
- Published
- 2002
- Full Text
- View/download PDF
50. Counter-propagation artificial neural network models in read-across predictions of toxicity
- Author
-
Marjan Vračko, Marjana Novič, Katja Venko, Viktor Drgan, and Špela Župerl
- Subjects
Artificial neural network ,Computer science ,business.industry ,Counter propagation ,General Medicine ,Artificial intelligence ,Toxicology ,business - Published
- 2017
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.