Multisensor Data Fusion for High Quality Data Analysis and Processing in Measurement and Instrumentation

Multisensor data fusion （MDF） is an emerging technology to fuse data from multiple sensors in order to make a more accurate estimation of the environment through measurement and detection. Applications of MDF cross a wide spectrum in military and civilian areas. With the rapid evolution of computers and the proliferation of micro-mechanical/electrical systems sensors, the utilization of MDF is being popularized in research and applications. This paper focuses on application of MDF for high quality data analysis and processing in measurement and instrumentation. A practical, general data fusion scheme was established on the basis of feature extraction and merge of data from multiple sensors. This scheme integrates artificial neural networks for high performance pattern recognition. A number of successful applications in areas of NDI （Non-Destructive Inspection） corrosion detection, food quality and safety characterization, and precision agriculture are described and discussed in order to motivate new applications in these or other areas. This paper gives an overall picture of using the MDF method to increase the accuracy of data analysis and processing in measurement and instrumentation in different areas of applications.     

Artificial neural networks for solution scattering data analysis

1. Download : Download high-res image (142KB)
2. Download : Download full-size image

     

Artificial neural network based experimental design procedure for enhancing fermentation development

Conventional experimental design techniques are available to assist in the optimization of fermentation processes, but due to the nonlinearities in the bioprocess, they are limited in their effectiveness. This problem is further complicated with recombinant systems as a result of the additional complexities of the process. This article describes a general strategy using artificial neural networks as an alternative approach to fermentation process development laboratory are presented for the neural network based procedures. (c) 1994 John Wiley & Sons, Inc.     

Performance evaluation of a machine vision system for insect pests identification of field crops using artificial neural networks

Feature extraction is a crucial part of advanced image recognition systems. In this research, an autonomous detection device was designed and developed for insect pest detection to improve the ability of intelligent systems in order to annihilate harmful insect pests in agricultural crop fields. Device included a dark chamber, a CCD digital camera, a LDR lightening module and a personal computer. The proposed programme for precise insect pest detection was based on an image processing algorithm and artificial neural networks (ANNs). After image acquisition, the insect pests’ images were extracted from original images with Canny filtration. Afterwards, four morphological and three textural features from the obtained images were measured and normalised. Performance of ANN model was tested successfully for Beet armyworm (Spodoptera exigua) recognition in images using back-propagation supervised learning method and inspection data. Results showed that proposed system was able to identify S. exigua in the images from other species. Such this machine vision system can be used in autonomous field robots to achieve a modern farmer’s assistant.     

A novel feature extraction approach for microarray data based on multi-algorithm fusion

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions.     

Phytoplankton food quality control of planktonic food web processes

We developed a mechanistic model of nutrient, phytoplankton, zooplankton and fish interactions to test the effects of phytoplankton food quality for herbivorous zooplankton on planktonic food web processes. When phytoplankton food quality is high strong trophic cascades suppress phytoplankton biomass, the zooplankton can withstand intense zooplanktivory, and energy is efficiently transferred through the food web sustaining higher trophic level production. Low food quality results in trophic decoupling at the plant-animal interface, with phytoplankton biomass determined primarily by nutrient availability, zooplankton easily eliminated by fish predation, and poor energy transfer through the food web. At a given nutrient availability, food quality and zooplanktivory interact to determine zooplankton biomass which in turn determines algal biomass. High food quality resulted in intense zooplankton grazing which favored fast-growing phytoplankton taxa, whereas fish predation favored slow-growing phytoplankton. These results suggest algal food quality for herbivorous zooplankton can strongly influence the nature of aquatic food web dynamics, and can have profound effects on water quality and fisheries production. Handling editor: D. Hamilton     

Temperature and the effects of elemental food quality on Daphnia

1. We examined the responses of two species of Daphnia to changes in food phosphorus (P) content, with animals reared at three different water temperatures. Specifically, we measured mass‐specific growth rate (MSGR), body P content and respiration rate of Daphnia magna and Daphnia pulex acclimatised to 10, 17.5 and 25 °C and fed food carbon : phosphorus (C : P) ratios of either 150 or 500. 2. The responses of these three physiological variables to temperature–food quality interactions were species‐specific. There was a significant interactive effect of temperature and food quality on D. magna, as the greatest proportional effect of food quality on growth was observed at 10 °C and reductions in body P because of low food P content were relatively greater at 25 °C. These effects may reflect the temperature dependence of mechanisms that reduce elemental constraints associated with food quality in D. magna. By contrast, there were no interactive effects between food quality and temperature on MSGR, body P or mass‐specific respiration of D. pulex. 3. It thus appears that temperature can alter food quality effects on Daphnia but the nature of these alterations depends upon the daphniid species and its thermal adaptability. Significant temperature–food quality interactions will complicate efforts to understand zooplankton nutrition in nature and warrant future consideration.     

Pattern identification and classification in gene expression data using an autoassociative neural network model

The application of DNA microarray technology for analysis of gene expression creates enormous opportunities to accelerate the pace in understanding living systems and identification of target genes and pathways for drug development and therapeutic intervention. Parallel monitoring of the expression profiles of thousands of genes seems particularly promising for a deeper understanding of cancer biology and the identification of molecular signatures supporting the histological classification schemes of neoplastic specimens. However, the increasing volume of data generated by microarray experiments poses the challenge of developing equally efficient methods and analysis procedures to extract, interpret, and upgrade the information content of these databases. Herein, a computational procedure for pattern identification, feature extraction, and classification of gene expression data through the analysis of an autoassociative neural network model is described. The identified patterns and features contain critical information about gene-phenotype relationships observed during changes in cell physiology. They represent a rational and dimensionally reduced base for understanding the basic biology of the onset of diseases, defining targets of therapeutic intervention, and developing diagnostic tools for the identification and classification of pathological states. The proposed method has been tested on two different microarray datasets-Golub's analysis of acute human leukemia [Golub et al. (1999) Science 286:531-537], and the human colon adenocarcinoma study presented by Alon et al. [1999; Proc Natl Acad Sci USA 97:10101-10106]. The analysis of the neural network internal structure allows the identification of specific phenotype markers and the extraction of peculiar associations among genes and physiological states. At the same time, the neural network outputs provide assignment to multiple classes, such as different pathological conditions or tissue samples, for previously unseen instances.     

Resource limitation and food quality for cladocerans in a tropical Brazilian lake

Food quality of the natural food (seston) from Lake Monte Alegre was evaluated throughout a series of life-table experiments with cladocerans from the same lake carried out in summer and autumn. Experiments were performed using cohorts of newborns originated from ovigerous females cultured for several generations in the lab or taken directly from the lake. For these tests of food limitation, juveniles of different species were submitted to one of the following treatments: (1) lake seston and (2) lake seston + green algae. The age at first reproduction, mean clutch size, total offspring and the intrinsic rate of natural increase (r) were estimated. Cladocerans responded to both seasonal changes in food resources and to additions of green algae. In summer, food levels were higher and cladocerans grew better than in autumn. The low fecundity and population growth rates of Daphnia gessneri, together with high C:P ratios (>500) in the seston in summer, suggested P limitation. The other cladocerans (Moina micrura, Ceriodaphnia cornuta and Simocephalus mixtus) were apparently less sensitive than D. gessneri to P-limitation in summer. However, energy limitation cannot be disregarded even in summer, although in a lower degree compared to autumn. In this season, the predominance of large diatoms and dinophyceans of low nutritional value and the low food concentration suggested both quantitative and qualitative food limitation. Phytoplankton composition, nutritional value and particle size appeared to be important factors in determining cladocerans reproduction rates with seston diets.     

基于人工神经网络的叶脉信息提取--植物活体机器识别研究I

叶片的识别是识别植物的重要组成部分,特别在野外识别植物活体尤其重要.叶脉的脉序是植物的内在特征,包含有重要的遗传信息.但由于叶脉本身的多样性,利用单一特征的图像处理方法难以有效地提取叶脉.为了充分利用图像的信息,本文提出了一种基于人工神经网络的叶脉提取方法.该方法利用边缘梯度、局部对比度和邻域统计特征等10个参数来描述像素的邻域特征,并将其作为神经网络的输入层.实验结果表明,与传统方法相比,经过训练的神经网络能够更准确地提取叶脉图像,为进一步的叶片识别打下了良好的基础.     

Niche overlap between herbivorous cladocerans; the role of food quality and habitat homogeneity

In spite of resource limitation, five abundant species of herbivorous metazoan zooplankton in a humic lake exhibited extensive niche overlap both with regard to seasonal and spatial occurrence, time of reproductive maxima, juvenile release and food choice. Their coexistence could not be explained by modifying predation, environmental oscillations or recolonization.Laboratory bottle experiments indicated only weak interspecific interactions between the three tested species at low food levels, but negative interactions were induced at elevated food levels. Bosmina appeared as competitively inferior during enrichment with cultured algae, but as the superior species during starvation. At low nutrient levels, all species coexisted for several generations with low reproduction, in accordance with the lake situation. It was concluded that the observed niche overlaps would be promoted if; 1) Intraspecific competition is more important than interspecific competition. 2) All species are co-adapted to low nutrient availability, food is quantitatively in surplus, but qualitatively deficient (mainly recycled detritus). During such conditions, no species would be capable of obtaining a population increase until extinction of the other species. This situation may be typical of oligotrophic humic lakes, and of other localities with low predation pressure and high inputs of allochthonous particulate carbon.     

BP人工神经网络在光谱定量预测中的应用

人工神经网络是模仿大脑神经元网络结构和功能而建立的一种信息处理系统,广泛的应用于各种波谱数据处理。误差反向传播多层前馈式网络(back-propagation network,简称BP网络)应用最广,发展最为迅速。将BP神经网络用于紫外-可见吸收光谱和拉曼光谱数据的定量分析和预测,与原文的一元线性回归模型数据处理方法相比,获得了比较满意的预测结果,预测精度有显著提高。这为相关的光谱分析和数据处理提供了一种更有效、更精确的方法。     

UV-B irradiance gradient affects photosynthesis and pigments but not food quality of periphyton

• 1 This laboratory study examined the effect of a gradient of UV‐B radiation (280–320 nm) on photosynthesis and food quality of periphyton, the trophic base of many freshwater benthic communities. Four irradiances of UV‐B (0, 0.6, 1.2, and 2.3 W m^‐2) were delivered by UV‐B lamps (313 nm peak irradiance) over a 13‐day period in the first experiment and over a 4‐h period in the second experiment. These irradiances were roughly equivalent to 0, 1, 2, and 4 times the ambient biologically effective (DNA) midsummer, midday UV‐B irradiance in Tennessee.
• 2 Rates of photosynthesis and photosynthetic pigments were significantly reduced by irradiances greater than ambient during the 13‐day experiment, suggesting that food supply rates to grazers would be depressed by increases in current UV‐B levels. Effects on community structure were minor, but mean diatom cell size decreased at higher UV‐B irradiances.
• 3 Irradiated periphyton was fed in surplus to juvenile snails (Physella gyrina) in the first experiment as a bioassay for food quality. Snail growth was the same on all four diets, suggesting that UV‐B did not affect food quality. Nitrogen and phosphorus content of the periphyton were not affected by UV‐B, either.
• 4 Photosynthesis by low‐biomass periphyton in the second experiment was significantly depressed by irradiances above ambient after only 4 h. Photosynthesis by the high biomass periphyton was not significantly affected by UV‐B, suggesting that self‐shading reduced UV‐B effects.

     

Effects of food quality on life history of the rotifer Brachionus calyciflorus Pallas

1. Herbivorous zooplankton face considerable temporal and spatial variation in food quality, to which they respond by adapting their life histories. Zooplankton may even take up mineral nutrients directly, and use these to counter the effects of algal nutrient limitation (mineral compensation). This study examined the life history of the rotifer Brachionus calyciflorus fed phosphorus‐, and nitrogen‐limited Scenedesmus obliquus (Chlorophyta), and investigated whether B. calyciflorus was capable of mineral compensation. 2. Both phosphorus‐ and nitrogen‐limited algae gave similar life history responses: somatic growth and reproduction were reduced, whereas lifespan remained unaffected. 3. No evidence was found for mineral compensation in B. calyciflorus in relation to detrimental life history effects, so mineral compensation does not seem to be relevant for this species under field conditions. 4. The similarity in life history responses of B. calyciflorus and the low levels of ω‐3 PUFAs in both phosphorus‐ and nitrogen‐depleted algae suggest that ω‐3 PUFAs were limiting to B. calyciflorus, although other (bio)chemicals or mineral nutrients may also have been important. 5. No trade‐off was observed between life span and reproduction during algal nutrient limitation. Reduced population growth rates of B. calyciflorus were caused by shorter reproductive periods.     

ANNA – Artificial Neural Network model for predicting species abundance and succession of blue-green algae

Predictive potential of deductive and inductivephytoplankton models are compared regarding theirusefulness for forecasting and control of harmfulalgal blooms. While applications of deductive modelsstill seem to be restricted by lack of knowledge, ad hocinductive models sometimes prove to bestraightforward and useful. The inductive neuralnetwork model ANNA is documented by means of anapplication to Lake Kasumigaura, Japan. ANNA wasvalidated for five blue-green algae species wherepredictive accuracy has improved with increased eventand time resolution of training data. A scenarioanalysis on species succession has demonstrated thepotential of ANNA for hypothesis testing. Finally,implications for use of ANNA for operational algalbloom control are discussed.     

Relevance of evolutionary history for food web structure

Explaining the structure of ecosystems is one of the great challenges of ecology. Simple models for food web structure aim at disentangling the complexity of ecological interaction networks and detect the main forces that are responsible for their shape. Trophic interactions are influenced by species traits, which in turn are largely determined by evolutionary history. Closely related species are more likely to share similar traits, such as body size, feeding mode and habitat preference than distant ones. Here, we present a theoretical framework for analysing whether evolutionary history--represented by taxonomic classification--provides valuable information on food web structure. In doing so, we measure which taxonomic ranks better explain species interactions. Our analysis is based on partitioning of the species into taxonomic units. For each partition, we compute the likelihood that a probabilistic model for food web structure reproduces the data using this information. We find that taxonomic partitions produce significantly higher likelihoods than expected at random. Marginal likelihoods (Bayes factors) are used to perform model selection among taxonomic ranks. We show that food webs are best explained by the coarser taxonomic ranks (kingdom to class). Our methods provide a way to explicitly include evolutionary history in models for food web structure.     

On the influence of food quality in consumer–resource interactions

While nutrients are an important regulating factor in food webs, no theoretical studies have examined limits to consumer growth imposed by nutrient concentrations (i.e. food quality) of their prey. Empirical studies have suggested that nutrients may play a role in limiting assimilation efficiencies of herbivores. Using a simple food chain model, I find that prey nutrient concentration does directly influence the growth rate of consumers and potentially increase the stability of consumer–resource interactions. This suggests that the strength of trophic cascades and the relative importance of top–down versus bottom–up control in food webs is significantly influenced by nutrient availability in food resources of consumers. Additionally, the results imply that increases in resource input may cause a change in which resource is limiting and thereby negate any potential "paradox of enrichment".     

The influence of food quality on the phototactic behaviour of Daphnia magnaStraus

We examined the influence of food quality on the phototactic behaviour of Daphnia magna. Cohorts of a positively phototactic D. magna clone were fed nine diets differing in quality. Diets were obtained by substitution of a fraction of unicellular algae ( Scenedesmus acutus) by a biomass-equivalent of fresh yeast ( Saccharomyces cerevisiae). Some of the diets were enriched with an inoculum of ciliates and organic compounds added as a hay infusion filtrate. Animals fed with a diet containing at least 25% algae showed a similar phototactic behaviour as animals fed with a diet that contained 100% algae. Addition of ciliates to the yeast diets resulted in a lower mortality and a higher reproductive rate compared to diets without a ciliate supplement. The presence of ciliates did not influence phototactic behaviour. Experiments testing for a maternal effect showed that the phototactic behaviour of the animals was strongly influenced by diet during the early developmental stages, but was not influenced by the diet of the mother. This revised version was published online in July 2006 with corrections to the Cover Date.