Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

This study presents an approach to combine uncertainties of the hydrological model outputs predicted from a number of machine learning models. The machine learning based uncertainty prediction approach is very useful for estimation of hydrological models' uncertainty in particular hydro-metrological situation in real-time application [1]. In this approach the hydrological model realizations from Monte Carlo simulations are used to build different machine learning uncertainty models to predict uncertainty (quantiles of pdf) of the a deterministic output from hydrological model . Uncertainty models are trained using antecedent precipitation and streamflows as inputs. The trained models are then employed to predict the model output uncertainty which is specific for the new input data. We used three machine learning models namely artificial neural networks, model tree, locally weighted regression to predict output uncertainties. These three models produce similar verification results, which can be improved by merging their outputs dynamically. We propose an approach to form a committee of the three models to combine their outputs. The approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model in the Brue catchment in UK and the Bagmati catchment in Nepal. The verification results show that merged output is better than an individual model output. [1] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press, 2013.

Aquatic weed automatic classification using machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Extended Hierarchical Censored Production Rules (EHCPRs) system: An approach toward generalized knowledge representation

One common problem in all basic techniques of knowledge representation is the handling of the trade-off between precision of inferences and resource constraints, such as time and memory. Michalski and Winston (1986) suggested the Censored Production Rule (CPR) as an underlying representation and computational mechanism to enable logic based systems to exhibit variable precision in which certainty varies while specificity stays constant. As an extension of CPR, the Hierarchical Censored Production Rules (HCPRs) system of knowledge representation, proposed by Bharadwaj & Jain (1992), exhibits both variable certainty as well as variable specificity and offers mechanisms for handling the trade-off between the two. An HCPR has the form: Decision If(preconditions) Unless(censor) Generality(general_information) Specificity(specific_information). As an attempt towards evolving a generalized knowledge representation, an Extended Hierarchical Censored Production Rules (EHCPRs) system is suggested in this paper. With the inclusion of new operators, an Extended Hierarchical Censored Production Rule (EHCPR) takes the general form: Concept If (Preconditions) Unless (Exceptions) Generality (General-Concept) Specificity (Specific Concepts) Has_part (default: structural-parts) Has_property (default:characteristic-properties) Has_instance (instances). How semantic networks and frames are represented in terms of an EHCPRs is shown. Multiple inheritance, inheritance with and without cancellation, recognition with partial match, and a few default logic problems are shown to be tackled efficiently in the proposed system.

Remote phenology: Applying machine learning to detect phenological patterns in a cerrado savanna

Plant phenology has gained importance in the context of global change research, stimulating the development of new technologies for phenological observation. Digital cameras have been successfully used as multi-channel imaging sensors, providing measures of leaf color change information (RGB channels), or leafing phenological changes in plants. We monitored leaf-changing patterns of a cerrado-savanna vegetation by taken daily digital images. We extract RGB channels from digital images and correlated with phenological changes. Our first goals were: (1) to test if the color change information is able to characterize the phenological pattern of a group of species; and (2) to test if individuals from the same functional group may be automatically identified using digital images. In this paper, we present a machine learning approach to detect phenological patterns in the digital images. Our preliminary results indicate that: (1) extreme hours (morning and afternoon) are the best for identifying plant species; and (2) different plant species present a different behavior with respect to the color change information. Based on those results, we suggest that individuals from the same functional group might be identified using digital images, and introduce a new tool to help phenology experts in the species identification and location on-the-ground. ©2012 IEEE.

An approach to implement data fusion techniques in wireless sensor networks using genetic machine learning algorithms

Wireless Sensor Networks (WSNs) can be used to monitor hazardous and inaccessible areas. In these situations, the power supply (e.g. battery) of each node cannot be easily replaced. One solution to deal with the limited capacity of current power supplies is to deploy a large number of sensor nodes, since the lifetime and dependability of the network will increase through cooperation among nodes. Applications on WSN may also have other concerns, such as meeting temporal deadlines on message transmissions and maximizing the quality of information. Data fusion is a well-known technique that can be useful for the enhancement of data quality and for the maximization of WSN lifetime. In this paper, we propose an approach that allows the implementation of parallel data fusion techniques in IEEE 802.15.4 networks. One of the main advantages of the proposed approach is that it enables a trade-off between different user-defined metrics through the use of a genetic machine learning algorithm. Simulations and field experiments performed in different communication scenarios highlight significant improvements when compared with, for instance, the Gur Game approach or the implementation of conventional periodic communication techniques over IEEE 802.15.4 networks. © 2013 Elsevier B.V. All rights reserved.

Applying machine learning based on multiscale classifiers to detect remote phenology patterns in Cerrado savanna trees

Plant phenology is one of the most reliable indicators of species responses to global climate change, motivating the development of new technologies for phenological monitoring. Digital cameras or near remote systems have been efficiently applied as multi-channel imaging sensors, where leaf color information is extracted from the RGB (Red, Green, and Blue) color channels, and the changes in green levels are used to infer leafing patterns of plant species. In this scenario, texture information is a great ally for image analysis that has been little used in phenology studies. We monitored leaf-changing patterns of Cerrado savanna vegetation by taking daily digital images. We extract RGB channels from the digital images and correlate them with phenological changes. Additionally, we benefit from the inclusion of textural metrics for quantifying spatial heterogeneity. Our first goals are: (1) to test if color change information is able to characterize the phenological pattern of a group of species; (2) to test if the temporal variation in image texture is useful to distinguish plant species; and (3) to test if individuals from the same species may be automatically identified using digital images. In this paper, we present a machine learning approach based on multiscale classifiers to detect phenological patterns in the digital images. Our results indicate that: (1) extreme hours (morning and afternoon) are the best for identifying plant species; (2) different plant species present a different behavior with respect to the color change information; and (3) texture variation along temporal images is promising information for capturing phenological patterns. Based on those results, we suggest that individuals from the same species and functional group might be identified using digital images, and introduce a new tool to help phenology experts in the identification of new individuals from the same species in the image and their location on the ground. © 2013 Elsevier B.V. All rights reserved.

Challenges of Knowledge Representation in Contemporary Archival Science

Since its emergence as a discipline, in the nineteenth century (1889), the theory and practice of Archival Science have focused on the arrangement and description of archival materials as complementary and inseparable nuclear processes that aim to classify, to order, to describe and to give access to records. These processes have their specific goals sharing one in common: the representation of archival knowledge. In the late 1980 a paradigm shift was announced in Archival Science, especially after the appearance of the new forms of document production and information technologies. The discipline was then invited to rethink its theoretical and methodological bases founded in the nineteenth century so it could handle the contemporary archival knowledge production, organization and representation. In this sense, the present paper aims to discuss, under a theoretical perspective, the archival representation, more specifically the archival description facing these changes and proposals, in order to illustrate the challenges faced by Contemporary Archival Science in a new context of production, organization and representation of archival knowledge.

Preliminary diagnosis of ophtalmological diseases through machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Alternative Tasks for the Teaching and the Learning of functions: analysis of an intervention in the High School

In this paper we focus on the application of two mathematical alternative tasks to the teaching and learning of functions with high school students. The tasks were elaborated according to the following methodological approach: (i) Problem Solving and/or mathematics investigation and (ii) a pedagogical proposal, which defends that mathematical knowledge is developed by means of a balance between logic and intuition. We employed a qualitative research approach (characterized as a case study) aimed at analyzing the didactic pedagogical potential of this type of methodology in high school. We found that tasks such as those presented and discussed in this paper provide a more significant learning for the students, allowing a better conceptual understanding, becoming still more powerful when one considers the social-cultural context of the students.

Knowledge management and strategic orientation: leveraging innovativeness and performance

Purpose - The aim of this study is to investigate whether knowledge management (KM) contributes to the development of strategic orientation and to enhance innovativeness, and whether these three factors contribute to improve business performance. Design/methodology/approach - A sample of 241 Brazilian companies was surveyed, using Web-based questionnaires with 54 questions, using ten-point scales to measure the degree of agreement on each item of each construct. Structural equation modeling techniques were applied for model assessment and analysis of the relationships among constructs. Exploratory factor analysis, confirmatory factor analysis, and path analysis using the technique of structural equation modeling were applied to the data. Findings - Effective KM contributes positively to strategic orientation. Although there is no significant direct effect of KM on innovativeness, the relationship is significant when mediated by strategic orientation. Similarly effective KM has no direct effect on business performance, but this relationship becomes statistically significant when mediated by strategic orientation and innovativeness. Research limitations/implications - The findings indicate that KM permeates all relationships among the constructs, corroborating the argument that knowledge is an essential organizational resource that leverages all value-creating activities. The results indicate that both KM and innovativeness produce significant impacts on performance when they are aligned with a strategic orientation that enables the organization to anticipate and respond to changing market conditions. Originality/value - There is a substantial body of research on several types of relationships involving KM, strategic orientation, innovativeness and performance. This study offers an original contribution by analyzing all of those constructs simultaneously using established scales so that comparative studies are possible.

Machine learning methods for prediction of disulphide bonding states of cysteine residues in proteins

The goal of this thesis work is to develop a computational method based on machine learning techniques for predicting disulfide-bonding states of cysteine residues in proteins, which is a sub-problem of a bigger and yet unsolved problem of protein structure prediction. Improvement in the prediction of disulfide bonding states of cysteine residues will help in putting a constraint in the three dimensional (3D) space of the respective protein structure, and thus will eventually help in the prediction of 3D structure of proteins. Results of this work will have direct implications in site-directed mutational studies of proteins, proteins engineering and the problem of protein folding. We have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM), the so-called Hidden Neural Network (HNN) as a machine learning technique to develop our prediction method. By using different global and local features of proteins (specifically profiles, parity of cysteine residues, average cysteine conservation, correlated mutation, sub-cellular localization, and signal peptide) as inputs and considering Eukaryotes and Prokaryotes separately we have reached to a remarkable accuracy of 94% on cysteine basis for both Eukaryotic and Prokaryotic datasets, and an accuracy of 90% and 93% on protein basis for Eukaryotic dataset and Prokaryotic dataset respectively. These accuracies are best so far ever reached by any existing prediction methods, and thus our prediction method has outperformed all the previously developed approaches and therefore is more reliable. Most interesting part of this thesis work is the differences in the prediction performances of Eukaryotes and Prokaryotes at the basic level of input coding when ‘profile’ information was given as input to our prediction method. And one of the reasons for this we discover is the difference in the amino acid composition of the local environment of bonded and free cysteine residues in Eukaryotes and Prokaryotes. Eukaryotic bonded cysteine examples have a ‘symmetric-cysteine-rich’ environment, where as Prokaryotic bonded examples lack it.

Machine-learning methods for structure prediction of β-barrel membrane proteins

Different types of proteins exist with diverse functions that are essential for living organisms. An important class of proteins is represented by transmembrane proteins which are specifically designed to be inserted into biological membranes and devised to perform very important functions in the cell such as cell communication and active transport across the membrane. Transmembrane β-barrels (TMBBs) are a sub-class of membrane proteins largely under-represented in structure databases because of the extreme difficulty in experimental structure determination. For this reason, computational tools that are able to predict the structure of TMBBs are needed. In this thesis, two computational problems related to TMBBs were addressed: the detection of TMBBs in large datasets of proteins and the prediction of the topology of TMBB proteins. Firstly, a method for TMBB detection was presented based on a novel neural network framework for variable-length sequence classification. The proposed approach was validated on a non-redundant dataset of proteins. Furthermore, we carried-out genome-wide detection using the entire Escherichia coli proteome. In both experiments, the method significantly outperformed other existing state-of-the-art approaches, reaching very high PPV (92%) and MCC (0.82). Secondly, a method was also introduced for TMBB topology prediction. The proposed approach is based on grammatical modelling and probabilistic discriminative models for sequence data labeling. The method was evaluated using a newly generated dataset of 38 TMBB proteins obtained from high-resolution data in the PDB. Results have shown that the model is able to correctly predict topologies of 25 out of 38 protein chains in the dataset. When tested on previously released datasets, the performances of the proposed approach were measured as comparable or superior to the current state-of-the-art of TMBB topology prediction.

Knowledge Management and Decision Support for Sustainable Land Management

Much research has focused on desertification and land degradation assessments without putting sufficient emphasis on prevention and mitigation, although the concept of sustainable land management (SLM) is increasingly being acknowledged. A variety of SLM measures have already been applied at the local level, but they are rarely adequately recognised, evaluated, shared or used for decision support. WOCAT (World Overview of Technologies and Approaches) has developed an internationally recognised, standardised methodology to document and evaluate SLM technologies and approaches, including spatial distribution, allowing the sharing of SLM knowledge worldwide. The recent methodological integration into a participatory process allows now analysing and using this knowledge for decision support at the local and national level. The use of the WOCAT tools stimulates evaluation (self-evaluation as well as learning from comparing experiences) within SLM initiatives where all too often there is not only insufficient monitoring but also a lack of critical analysis. The comprehensive questionnaires and database system facilitate to document, evaluate and disseminate local experiences of SLM technologies and their implementation approaches. This evaluation process - in a team of experts and together with land users - greatly enhances understanding of the reasons behind successful (or failed) local practices. It has now been integrated into a new methodology for appraising and selecting SLM options. The methodology combines a local collective learning and decision approach with the use of the evaluated global best practices from WOCAT in a concise three step process: i) identifying land degradation and locally applied solutions in a stakeholder learning workshop; ii) assessing local solutions with the standardised WOCAT tool; iii) jointly selecting promising strategies for implementation with the help of a decision support tool. The methodology has been implemented in various countries and study sites around the world mainly within the FAO LADA (Land Degradation Assessment Project) and the EU-funded DESIRE project. Investments in SLM must be carefully assessed and planned on the basis of properly documented experiences and evaluated impacts and benefits: concerted efforts are needed and sufficient resources must be mobilised to tap the wealth of knowledge and learn from SLM successes.

Radiation metabolomics. 3. Biomarker discovery in the urine of gamma-irradiated rats using a simplified metabolomics protocol of gas chromatography-mass spectrometry combined with random forests machine learning algorithm

Abstract Radiation metabolomics employing mass spectral technologies represents a plausible means of high-throughput minimally invasive radiation biodosimetry. A simplified metabolomics protocol is described that employs ubiquitous gas chromatography-mass spectrometry and open source software including random forests machine learning algorithm to uncover latent biomarkers of 3 Gy gamma radiation in rats. Urine was collected from six male Wistar rats and six sham-irradiated controls for 7 days, 4 prior to irradiation and 3 after irradiation. Water and food consumption, urine volume, body weight, and sodium, potassium, calcium, chloride, phosphate and urea excretion showed major effects from exposure to gamma radiation. The metabolomics protocol uncovered several urinary metabolites that were significantly up-regulated (glyoxylate, threonate, thymine, uracil, p-cresol) and down-regulated (citrate, 2-oxoglutarate, adipate, pimelate, suberate, azelaate) as a result of radiation exposure. Thymine and uracil were shown to derive largely from thymidine and 2'-deoxyuridine, which are known radiation biomarkers in the mouse. The radiation metabolomic phenotype in rats appeared to derive from oxidative stress and effects on kidney function. Gas chromatography-mass spectrometry is a promising platform on which to develop the field of radiation metabolomics further and to assist in the design of instrumentation for use in detecting biological consequences of environmental radiation release.

Digital Systems for Open Access to Formal and Informal Learning

Today, Digital Systems and Services for Technology Supported Learning and Education are recognized as the key drivers to transform the way that individuals, groups and organizations “learn” and the way to “assess learning” in 21st Century. These transformations influence: Objectives - moving from acquiring new “knowledge” to developing new and relevant “competences”; Methods – moving from “classroom” based teaching to “context-aware” personalized learning; and Assessment – moving from “life-long” degrees and certifications to “on-demand” and “in-context” accreditation of qualifications. Within this context, promoting Open Access to Formal and Informal Learning, is currently a key issue in the public discourse and the global dialogue on Education, including Massive Open Online Courses (MOOCs) and Flipped School Classrooms. This volume on Digital Systems for Open Access to Formal and Informal Learning contributes to the international dialogue between researchers, technologists, practitioners and policy makers in Technology Supported Education and Learning. It addresses emerging issues related with both theory and practice, as well as, methods and technologies that can support Open Access to Formal and Informal Learning. In the twenty chapters contributed by international experts who are actively shaping the future of Educational Technology around the world, topics such as: - The evolution of University Open Courses in Transforming Learning - Supporting Open Access to Teaching and Learning of People with Disabilities - Assessing Student Learning in Online Courses - Digital Game-based Learning for School Education - Open Access to Virtual and Remote Labs for STEM Education - Teachers’ and Schools’ ICT Competence Profiling - Web-Based Education and Innovative Leadership in a K-12 International School Setting are presented. An in-depth blueprint of the promise, potential, and imminent future of the field, Digital Systems for Open Access to Formal and Informal Learning is necessary reading for researchers and practitioners, as well as, undergraduate and postgraduate students, in educational technology.