Simulation of Soybean Phenology with the Use of Artificial Neural Networks

Biophysics - The phenology of soybean explicitly indicates environmental changes and strongly depends on temperature and day length. We adapted an artificial neural network model to predict the...     

The Use of Artificial Neural Networks for Species Identification of Aegilops Based on Analysis of D Genomes

The possibilities of the use of artificial neural networks (ANNs) for identification of some polyploid species of genus Aegilopsbased on the idiograms of theirDgenomes were demonstrated.     

The Use of Artificial Neural Networks for Automatic Analysis and Genetic Identification of Gliadin Electrophoretic Spectra in Durum Wheat

Each wheat cultivar has a characteristic spectrum of gliadins. This makes it possible to use blocks of the components of reserve proteins as genetic markers when estimating seed purity and identity. However, identification of the blocks that constitute the electrophoretic spectrum is a complicated task. For this purpose artificial neural network (ANN) technology is proposed. Using experimental data, a teaching database and testing databases have been created. ANN was shown to be highly efficient (efficiency up to 100%) expert system for deciphering the electrophoretic spectra of gliadins of durum wheat cultivars.     

Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks

The Semantic Pointer Architecture (SPA) is a proposal of specifying the computations and architectural elements needed to account for cognitive functions. By means of the Neural Engineering Framework (NEF) this proposal can be realized in a spiking neural network. However, in any such network each SPA transformation will accumulate noise. By increasing the accuracy of common SPA operations, the overall network performance can be increased considerably. As well, the representations in such networks present a trade-off between being able to represent all possible values and being only able to represent the most likely values, but with high accuracy. We derive a heuristic to find the near-optimal point in this trade-off. This allows us to improve the accuracy of common SPA operations by up to 25 times. Ultimately, it allows for a reduction of neuron number and a more efficient use of both traditional and neuromorphic hardware, which we demonstrate here.     

The Heuristic Work of the Brain and Artificial Neural Networks

Biophysics - This paper presents two new fundamental principles of the functioning of real neural networks of the brain. These principles have inspired the design of artificial neural networks (a...     

Use of Artificial Neural Networks To Accurately Identify Cryptosporidium Oocyst and Giardia Cyst Images

Cryptosporidium parvum and Giardia lamblia are protozoa capable of causing gastrointestinal diseases. Currently, these organisms are identified using immunofluorescent antibody (IFA)-based microscopy, and identification requires trained individuals for final confirmation. Since artificial neural networks (ANN) can provide an automated means of identification, thereby reducing human errors related to misidentification, ANN were developed to identify Cryptosporidium oocyst and Giardia cyst images. Digitized images of C. parvum oocysts and G. lamblia cysts stained with various commercial IFA reagents were used as positive controls. The images were captured using a color digital camera at 400× (total magnification), processed, and converted into a binary numerical array. A variety of “negative” images were also captured and processed. The ANN were developed using these images and a rigorous training and testing protocol. The Cryptosporidium oocyst ANN were trained with 1,586 images, while Giardia cyst ANN were trained with 2,431 images. After training, the best-performing ANN were selected based on an initial testing performance against 100 images (50 positive and 50 negative images). The networks were validated against previously “unseen” images of 500 Cryptosporidium oocysts (250 positive, 250 negative) and 282 Giardia cysts (232 positive, 50 negative). The selected ANNs correctly identified 91.8 and 99.6% of the Cryptosporidium oocyst and Giardia cyst images, respectively. These results indicate that ANN technology can be an alternate to having trained personnel for detecting these pathogens and can be a boon to underdeveloped regions of the world where there is a chronic shortage of adequately skilled individuals to detect these pathogens.     

A Model for Improving the Learning Curves of Artificial Neural Networks

In this article, the performance of a hybrid artificial neural network (i.e. scale-free and small-world) was analyzed and its learning curve compared to three other topologies: random, scale-free and small-world, as well as to the chemotaxis neural network of the nematode Caenorhabditis Elegans. One hundred equivalent networks (same number of vertices and average degree) for each topology were generated and each was trained for one thousand epochs. After comparing the mean learning curves of each network topology with the C. elegans neural network, we found that the networks that exhibited preferential attachment exhibited the best learning curves.     

人工神经网络在蝙蝠回声定位叫声识别方面的应用

近年来,人工神经网络被不断应用于野生动物的声学研究中,本文概括地介绍了人工神经网络的概念以及这项新技术的研究方法,并且重点介绍了它在蝙蝠回声定位叫声识别方面的应用。     

Interaction between bisphenol derivatives and protein disulphide isomerase (PDI) and inhibition of PDI functions: requirement of chemical structure for binding to PDI

Bisphenol A (BPA) is an endocrine disrupting chemical and several biological effects have been reported. Previously, protein disulphide isomerase (PDI) was isolated as a target molecule of bisphenol A. In this study, to clarify the effects of BPA on PDI functions, we investigated the relationship between the chemical structure of BPA derivatives and the effects on PDI-mediated isomerase and chaperone activity. We also investigated the effects of changes in the isomerase domain of PDI on the binding of chemicals, using PDI mutants and oxidized or reduced PDI. Among six chemicals, only chemicals, which have a phenol group, can bind to PDI and these chemicals also have an inhibitory effect on PDI-mediated isomerase activity. Changes in the structure of the PDI isomerase domain did not affect chemical-binding activity. On the other hand, the chemicals used in this study have low effects on chaperone activity of PDI. Substitutions in Cys residues (Cys398 and Cys401) of the isomerase active site changed chaperone activity. The present study indicates that phenolic compounds specifically bind to PDI and inhibit isomerase activity. This study provides useful information to predict the biological effects of chemicals and structural studies of PDI containing the function of chemical binding.     

Protein-disulfide isomerase (PDI) in FRTL5 cells. pH-dependent thyroglobulin/PDI interactions determine a novel PDI function in the post-endoplasmic reticulum of thyrocytes

Thyroglobulin (TG) is secreted by the thyrocytes into the follicular lumen of the thyroid. After maturation and hormone formation, TG is endocytosed and delivered to lysosomes. Quality control mechanisms may occur during this bidirectional traffic since 1) several molecular chaperones are cosecreted with TG in vivo, and 2) lysosomal targeting of immature TG is thought to be prevented via the interaction, in acidic conditions, between the Ser(789)-Met(1172) TG hormonogenic domain (BD) and an unidentified membrane receptor. We investigated the secretion and cell surface expression of PDI and other chaperones in the FRTL5 thyroid cell line, and then studied the characteristics of the interaction between TG and PDI. We demonstrated that PDI, but also other chaperones such as calnexin and KDEL-containing proteins are exposed at the cell surface. We observed on living cells or membrane preparations that PDI specifically binds TG in acidic conditions, and that only BD is involved in binding. Surface plasmon resonance analysis of TG/PDI interactions indicated: 1) that PDI bound TG but only in acidic conditions, and that it preferentially recognized immature molecules, and 2) BD is involved in binding even if cysteine-rich modules are deleted. The notion that PDI acts as an "escort" for immature TG in acidic post-endoplasmic reticulum compartments is discussed.     

The Intrinsic Role of Molecular Mass and Polydispersity Index in High-Performance Non-Fullerene Polymer Solar Cells

The degree of polymerization can cause significant changes in the blend microstructure and physical mechanism of the active layer of non-fullerene polymer solar cells, resulting in a huge difference in device performance. However, the diversity of stability issues, including photobleaching stability, storage stability, photostability, thermal stability, and mechanical stability, and more, poses a challenge for the degree of polymerization to comprehensively address the trade-off between device efficiency and stability and reasonably evaluate the application potential of polymer materials. Herein, a series of PM6 polymers with different weight-average molecular weights (M_w) and polydispersity index (PDI) are synthesized. The effects of the degree of PM6 polymerization on the efficiency and degradation behaviors of the photovoltaic systems based on Y6 as acceptor are investigated systematically. The findings regarding stability issues, together with the trade-offs in the efficiency-stability gap, formulate a complete guideline for the material design and performance evaluation in a way that relies much less on trial-and-error efforts.     

Growing of a Fuzzy Recurrent Artificial Neural Network (FRANN) for pattern classification

This paper describes a method for growing a recurrent neural network of fuzzy threshold units for the classification of feature vectors. Fuzzy networks seem natural for performing classification, since classification is concerned with set membership and objects generally belonging to sets of various degrees. A fuzzy unit in the architecture proposed here determines the degree to which the input vector lies in the fuzzy set associated with the fuzzy unit. This is in contrast to perceptrons that determine the correlation between input vector and a weighting vector. The resulting membership value, in the case of the fuzzy unit, is compared with a threshold, which is interpreted as a membership value. Training of a fuzzy unit is based on an algorithm for linear inequalities similar to Ho-Kashyap recording. These fuzzy threshold units are fully connected in a recurrent network. The network grows as it is trained. The advantages of the network and its training method are: (1) Allowing the network to grow to the required size which is generally much smaller than the size of the network which would be obtained otherwise, implying better generalization, smaller storage requirements and fewer calculations during classification; (2) The training time is extremely short; (3) Recurrent networks such as this one are generally readily implemented in hardware; (4) Classification accuracy obtained on several standard data sets is better than that obtained by the majority of other standard methods; and (5) The use of fuzzy logic is very intuitive since class membership is generally fuzzy.     

Chromosomal assignment of gene sequences coding for protein disulphide isomerase (PDI) in wheat

 Three different probes, obtained by PCR amplification and labelling of different segments of a PDI cDNA clone from common wheat, were used to identify and assign to wheat chromosomes the gene sequences coding for protein disulphide isomerase (PDI). One of these probes, containing the whole coding region except for a short segment coding for the C-terminal sequence, displayed defined and specific RFLP patterns. PDI gene sequences were consequently assigned to wheat chromosome arms 4BS, 4DS, 4AL and 1BS by Southern hybridisation of EcoRI- HindIII- and BamHI-digested total DNA of nulli-tetrasomic and di-telosomic lines of Chinese Spring. This probe was also employed for assessing the restriction fragment length polymorphism in several hexaploid and tetraploid cultivated wheats. These showed considerable conservation at PDI loci; in fact polymorphism was only observed for the chromosome 1B fragment. Received: 7 July 1998 / Accepted: 14 August 1998     

Use of Surface Enhanced Blocking (SEB) Electrodes for Microbial Cell Lysis in Flow-Through Devices

By simultaneously subjecting microbial cells to high amplitude pulsed electric fields and flash heating of the cell suspension fluid, effective release of intracellular contents was achieved. The synergistic effect of the applied electric field and elevated temperature on cell lysis in a flow-through device was demonstrated for Gram-negative and Gram-positive bacteria, and Mycobacterium species. The resulting lysate is suitable for downstream nucleic acid amplification and detection without requiring further preparation. The lysis chamber employs surface enhanced blocking electrodes which possess an etched micro-structured surface and a thin layer of dielectric metal oxide which provides a large effective area and blocks transmission of electrical current. The surface enhanced blocking electrodes enable simultaneous suppression of the rapid onset of electric field screening in the bulk of the cell suspension medium and avoidance of undesired electrochemical processes at the electrode-electrolyte interface. In addition the blocking layer ensures the robustness of the cell lysis device in applications involving prolonged flow-through processing of the microbial cells.     

Use of Neural Networks to Correlate Spine and Rib Deformity in Scoliosis

Abstract

Artificial neural networks (ANN's) recognize patterns relating input and output data in a manner analogous to the function of biological neurons. Here, we show that ANN's can predict rib deformity in scoliosis more accurately than regression analysis. ANN's and linear regression models were developed to predict rib rotation from several combinations of input spinal indices including Cobb angle, vertebral rotation, apex location and orientation of the plane of maximal curvature. ANN's averaged 60% correct predictions compared to 34% for regression analysis. This study provides evidence for the utility of artificial neural networks in scoliosis research. These data lend credence to the use of ANN's in future work on the prediction of scoliotic spinal deformity from torso surface data, which would permit assessment of scoliosis severity with minimal use of harmful X-rays.     

Use of Neural Networks to Correlate Spine and Rib Deformity in Scoliosis

Artificial neural networks (ANN's) recognize patterns relating input and output data in a manner analogous to the function of biological neurons. Here, we show that ANN's can predict rib deformity in scoliosis more accurately than regression analysis. ANN's and linear regression models were developed to predict rib rotation from several combinations of input spinal indices including Cobb angle, vertebral rotation, apex location and orientation of the plane of maximal curvature. ANN's averaged 60% correct predictions compared to 34% for regression analysis. This study provides evidence for the utility of artificial neural networks in scoliosis research. These data lend credence to the use of ANN's in future work on the prediction of scoliotic spinal deformity from torso surface data, which would permit assessment of scoliosis severity with minimal use of harmful X-rays.     

The use of Artificial Neural Networks to classify primate vocalizations: a pilot study on black lemurs

The identification of the vocal repertoire of a species represents a crucial prerequisite for a correct interpretation of animal behavior. Artificial Neural Networks (ANNs) have been widely used in behavioral sciences, and today are considered a valuable classification tool for reducing the level of subjectivity and allowing replicable results across different studies. However, to date, no studies have applied this tool to nonhuman primate vocalizations. Here, we apply for the first time ANNs, to discriminate the vocal repertoire in a primate species, Eulemur macaco macaco. We designed an automatic procedure to extract both spectral and temporal features from signals, and performed a comparative analysis between a supervised Multilayer Perceptron and two statistical approaches commonly used in primatology (Discriminant Function Analysis and Cluster Analysis), in order to explore pros and cons of these methods in bioacoustic classification. Our results show that ANNs were able to recognize all seven vocal categories previously described (92.5–95.6%) and perform better than either statistical analysis (76.1–88.4%). The results show that ANNs can provide an effective and robust method for automatic classification also in primates, suggesting that neural models can represent a valuable tool to contribute to a better understanding of primate vocal communication. The use of neural networks to identify primate vocalizations and the further development of this approach in studying primate communication are discussed. Am. J. Primatol. 72:337–348, 2010. © 2009 Wiley‐Liss, Inc.     

Simple Microfluidic Devices for in vivo Imaging of C. elegans,Drosophila and Zebrafish

Micro fabricated fluidic devices provide an accessible micro-environment for in vivo studies on small organisms. Simple fabrication processes are available for microfluidic devices using soft lithography techniques ^1-3. Microfluidic devices have been used for sub-cellular imaging ^4,5, in vivo laser microsurgery ^2,6 and cellular imaging ^4,7. In vivo imaging requires immobilization of organisms. This has been achieved using suction ^5,8, tapered channels ^6,7,9, deformable membranes ^2-4,10, suction with additional cooling ⁵, anesthetic gas ¹¹, temperature sensitive gels ¹², cyanoacrylate glue ¹³ and anesthetics such as levamisole ^14,15. Commonly used anesthetics influence synaptic transmission ^16,17 and are known to have detrimental effects on sub-cellular neuronal transport ⁴. In this study we demonstrate a membrane based poly-dimethyl-siloxane (PDMS) device that allows anesthetic free immobilization of intact genetic model organisms such as Caenorhabditis elegans (C. elegans), Drosophila larvae and zebrafish larvae. These model organisms are suitable for in vivo studies in microfluidic devices because of their small diameters and optically transparent or translucent bodies. Body diameters range from ~10 μm to ~800 μm for early larval stages of C. elegans and zebrafish larvae and require microfluidic devices of different sizes to achieve complete immobilization for high resolution time-lapse imaging. These organisms are immobilized using pressure applied by compressed nitrogen gas through a liquid column and imaged using an inverted microscope. Animals released from the trap return to normal locomotion within 10 min.We demonstrate four applications of time-lapse imaging in C. elegans namely, imaging mitochondrial transport in neurons, pre-synaptic vesicle transport in a transport-defective mutant, glutamate receptor transport and Q neuroblast cell division. Data obtained from such movies show that microfluidic immobilization is a useful and accurate means of acquiring in vivo data of cellular and sub-cellular events when compared to anesthetized animals (Figure 1J and 3C-F⁴).Device dimensions were altered to allow time-lapse imaging of different stages of C. elegans, first instar Drosophila larvae and zebrafish larvae. Transport of vesicles marked with synaptotagmin tagged with GFP (syt.eGFP) in sensory neurons shows directed motion of synaptic vesicle markers expressed in cholinergic sensory neurons in intact first instar Drosophila larvae. A similar device has been used to carry out time-lapse imaging of heartbeat in ~30 hr post fertilization (hpf) zebrafish larvae. These data show that the simple devices we have developed can be applied to a variety of model systems to study several cell biological and developmental phenomena in vivo.     

The application of Artificial Neural Network (ANN) model to the simulation of denitrification rates in mesocosm-scale wetlands

Denitrification and its regulating factors are of great importance to aquatic ecosystems, as denitrification is a critical process to nitrogen removal. Additionally, a by-product of denitrification, nitrous oxide, is a much more potent greenhouse gas than carbon dioxide. However, the estimation of denitrification rates is usually clouded with uncertainty, mainly due to high spatial and temporal variations, as well as complex regulating factors within wetlands. This hampers the development of general mechanistic models for denitrification as well, as most previously developed models were empirical or exhibited low predictability with numerous assumptions. In this study, we tested Artificial Neural Network (ANN) as an alternative to classic empirical models for simulating denitrification rates in wetlands. ANN, multiple linear regression (MLR) with two different methods, and simplified mechanistic models were applied to estimate the denitrification rates of 2-year observations in a mesocosm-scale constructed wetland system. MLR and simplified mechanistic models resulted in lower prediction power and higher residuals compared to ANN. Although the stepwise linear regression model estimated similar average values of denitrification rates, it could not capture the fluctuation patterns accurately. In contrast, ANN model achieved a fairly high predictability, with an R² of 0.78 for model validation, 0.93 for model calibration (training), and a low root mean square error (RMSE) together with low bias, indicating a high capacity to simulate the dynamics of denitrification. According to a sensitivity analysis of the ANN, non-linear relationships between input variables and denitrification rates were well explained. In addition, we found that water temperature, denitrifying enzyme activity (DEA), and DO accounted for 70% of denitrification rates. Our results suggest that the ANN developed in this study has a greater performance in simulating variations in denitrification rates than multivariate linear regressions or simplified nonlinear mechanistic model.