An Adaptive Machine Learning Decision System for Flexible Predictive Maintenance

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

Development of an app to support learning in A-level maths

This project involved producing an app for smart devices to enable modernised learning for A-level maths students. Research in a stakeholder school showed that 94% of pupils surveyed within the upper-secondary level owned a smartphone and most owned a tablet also, emphasising the opportunity for using apps to support learning. The app was developed using iBuildApp, an online app-creation programme which requires no programming. Past exam questions and solutions, notes and video tutorials were included and the topic was vectors, identified by teachers as problematic. Pupils generally found the app easy to use and wanted further development. The videos were popular despite this not ranking highly as a preferred method of revision previously. Teachers were happy for pupils to use the app to supplement their learning, both in the classroom and outside.

Machine learning for transient discovery in Pan-STARRS1 difference imaging

Efficient identification and follow-up of astronomical transients is hindered by the need for humans to manually select promising candidates from data streams that contain many false positives. These artefacts arise in the difference images that are produced by most major ground-based time-domain surveys with large format CCD cameras. This dependence on humans to reject bogus detections is unsustainable for next generation all-sky surveys and significant effort is now being invested to solve the problem computationally. In this paper, we explore a simple machine learning approach to real-bogus classification by constructing a training set from the image data of similar to 32 000 real astrophysical transients and bogus detections from the Pan-STARRS1 Medium Deep Survey. We derive our feature representation from the pixel intensity values of a 20 x 20 pixel stamp around the centre of the candidates. This differs from previous work in that it works directly on the pixels rather than catalogued domain knowledge for feature design or selection. Three machine learning algorithms are trained (artificial neural networks, support vector machines and random forests) and their performances are tested on a held-out subset of 25 per cent of the training data. We find the best results from the random forest classifier and demonstrate that by accepting a false positive rate of 1 per cent, the classifier initially suggests a missed detection rate of around 10 per cent. However, we also find that a combination of bright star variability, nuclear transients and uncertainty in human labelling means that our best estimate of the missed detection rate is approximately 6 per cent.

A decision support system for managing irrigation in agriculture

In this paper, an automatic Smart Irrigation Decision Support System, SIDSS, is proposed to manage irrigation in agriculture. Our system estimates the weekly irrigations needs of a plantation, on the basis of both soil measurements and climatic variables gathered by several autonomous nodes deployed in field. This enables a closed loop control scheme to adapt the decision support system to local perturbations and estimation errors. Two machine learning techniques, PLSR and ANFIS, are proposed as reasoning engine of our SIDSS. Our approach is validated on three commercial plantations of citrus trees located in the South-East of Spain. Performance is tested against decisions taken by a human expert.

MASCEM - an electricity market simulator providing coalition support for virtual power players

This paper presents MASCEM - a multi-agent based electricity market simulator. MASCEM uses game theory, machine learning techniques, scenario analysis and optimization techniques to model market agents and to provide them with decision-support. This paper mainly focus on the MASCEM ability to provide the means to model and simulate Virtual Power Players (VPP). VPPs are represented as a coalition of agents, with specific characteristics and goals. The paper details some of the most important aspects considered in VPP formation and in the aggregation of new producers and includes a case study based on real data.

Data Mining Approach to support the Generation of Realistic Scenarios for Multi-Agent simulation of Electricity Markets

This paper presents the Realistic Scenarios Generator (RealScen), a tool that processes data from real electricity markets to generate realistic scenarios that enable the modeling of electricity market players’ characteristics and strategic behavior. The proposed tool provides significant advantages to the decision making process in an electricity market environment, especially when coupled with a multi-agent electricity markets simulator. The generation of realistic scenarios is performed using mechanisms for intelligent data analysis, which are based on artificial intelligence and data mining algorithms. These techniques allow the study of realistic scenarios, adapted to the existing markets, and improve the representation of market entities as software agents, enabling a detailed modeling of their profiles and strategies. This work contributes significantly to the understanding of the interactions between the entities acting in electricity markets by increasing the capability and realism of market simulations.

Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.

Directed integration of new insulated lentiviral vectors to heterochromatin towards safer gene transfer to stem cells

The need for better gene transfer systems towards improved risk=benefit balance for patients remains a major challenge in the clinical translation of gene therapy (GT). We have investigated the improvement of integrating vectors safety in combining (i) new short synthetic genetic insulator elements (GIE) and (ii) directing genetic integration to heterochromatin. We have designed SIN-insulated retrovectors with two candidate GIEs and could identify a specific combination of insulator 2 repeats which translates into best functional activity, high titers and boundary effect in both gammaretro (p20) and lentivectors (DCaro4) (see Duros et al, abstract ibid). Since GIEs are believed to shield the transgenic cassette from inhibitory effects and silencing, DCaro4 has been further tested with chimeric HIV-1 derived integrases which comprise C-ter chromodomains targeting heterochromatin through either histone H3 (ML6chimera) or methylatedCpGislands (ML10). With DCaro4 only and both chimeras, a homogeneous expression is evidenced in over 20% of the cells which is sustained over time. With control lentivectors, less than 2% of cells express GFP as compared to background using a control double-mutant in both catalytic and ledgf binding-sites; in addition, a two-times increase of expression can be induced with histone deacetylase inhibitors. Our approach could significantly reduce integration into open chromatin sensitive sites in stem cells at the time of transduction, a feature which might significantly decrease subsequent genotoxicity, according to X-SCIDs patients data.Work performed with the support of EC-DG research within the FP6-Network of Excellence, CLINIGENE: LSHB-CT-2006-018933

Syntactic Based Machine Translation from English to Malayalam

Due to the emergence of multiple language support on the Internet, machine translation (MT) technologies are indispensable to the communication between speakers using different languages. Recent research works have started to explore tree-based machine translation systems with syntactical and morphological information. This work aims the development of Syntactic Based Machine Translation from English to Malayalam by adding different case information during translation. The system identifies general rules for various sentence patterns in English. These rules are generated using the Parts Of Speech (POS) tag information of the texts. Word Reordering based on the Syntax Tree is used to improve the translation quality of the system. The system used Bilingual English –Malayalam dictionary for translation.

Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers

The Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special cases. In the RBF case, the SV algorithm automatically determines centers, weights and threshold such as to minimize an upper bound on the expected test error. The present study is devoted to an experimental comparison of these machines with a classical approach, where the centers are determined by $k$--means clustering and the weights are found using error backpropagation. We consider three machines, namely a classical RBF machine, an SV machine with Gaussian kernel, and a hybrid system with the centers determined by the SV method and the weights trained by error backpropagation. Our results show that on the US postal service database of handwritten digits, the SV machine achieves the highest test accuracy, followed by the hybrid approach. The SV approach is thus not only theoretically well--founded, but also superior in a practical application.

Entropic risk analysis by a high level decision support system (e-FDSS) for construction SMEs

The method of entropy has been useful in evaluating inconsistency on human judgments. This paper illustrates an entropy-based decision support system called e-FDSS to the solution of multicriterion risk and decision analysis in projects of construction small and medium enterprises (SMEs). It is optimized and solved by fuzzy logic, entropy, and genetic algorithms. A case study demonstrated the use of entropy in e-FDSS on analyzing multiple risk criteria in the predevelopment stage of SME projects. Survey data studying the degree of impact of selected project risk criteria on different projects were input into the system in order to evaluate the preidentified project risks in an impartial environment. Without taking into account the amount of uncertainty embedded in the evaluation process; the results showed that all decision vectors are indeed full of bias and the deviations of decisions are finally quantified providing a more objective decision and risk assessment profile to the stakeholders of projects in order to search and screen the most profitable projects.

Modelling capability and affordance as properties of human/machine resource systems

Understanding how and why the capability of one set of business resources, its structural arrangements and mechanisms compared to another works can provide competitive advantage in terms of new business processes and product and service development. However, most business models of capability are descriptive and lack formal modelling language to qualitatively and quantifiably compare capabilities, Gibson’s theory of affordance, the potential for action, provides a formal basis for a more robust and quantitative model, but most formal affordance models are complex and abstract and lack support for real-world applications. We aim to understand the ‘how’ and ‘why’ of business capability, by developing a quantitative and qualitative model that underpins earlier work on Capability-Affordance Modelling – CAM. This paper integrates an affordance based capability model and the formalism of Coloured Petri Nets to develop a simulation model. Using the model, we show how capability depends on the space time path of interacting resources, the mechanism of transition and specific critical affordance factors relating to the values of the variables for resources, people and physical objects. We show how the model can identify the capabilities of resources to enable the capability to inject a drug and anaesthetise a patient.

Comparing machine learning classifiers in potential distribution modelling

Species` potential distribution modelling consists of building a representation of the fundamental ecological requirements of a species from biotic and abiotic conditions where the species is known to occur. Such models can be valuable tools to understand the biogeography of species and to support the prediction of its presence/absence considering a particular environment scenario. This paper investigates the use of different supervised machine learning techniques to model the potential distribution of 35 plant species from Latin America. Each technique was able to extract a different representation of the relations between the environmental conditions and the distribution profile of the species. The experimental results highlight the good performance of random trees classifiers, indicating this particular technique as a promising candidate for modelling species` potential distribution. (C) 2010 Elsevier Ltd. All rights reserved.

Measuring time series predictability using support vector regression

Most studies involving statistical time series analysis rely on assumptions of linearity, which by its simplicity facilitates parameter interpretation and estimation. However, the linearity assumption may be too restrictive for many practical applications. The implementation of nonlinear models in time series analysis involves the estimation of a large set of parameters, frequently leading to overfitting problems. In this article, a predictability coefficient is estimated using a combination of nonlinear autoregressive models and the use of support vector regression in this model is explored. We illustrate the usefulness and interpretability of results by using electroencephalographic records of an epileptic patient.

Machine Learning Algorithms in Heavy Process Manufacturing

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.