Differential convergence of life-cycle inventories toward upstream production layers

We present an input-output analysis of the life-cycle labor, land, and greenhouse gas (GHG) requirements of alternative options for three case studies: investing money in a new vehicle versus in repairs of an existing vehicle (labor), passenger transport modes for a trip between Sydney and Melbourne (land use), and renewable electricity generation (GHG emissions). These case studies were chosen to demonstrate the possibility of rank crossovers in life-cycle inventory (LCI) results as system boundaries are expanded and upstream production inputs are taken into account. They demonstrate that differential convergence can cause crossovers in the ranking of inventories for alternative functional units occurring at second-and higher-order upstream production layers.

System boundary selection in life-cycle inventories using hybrid approaches

Life-cycle assessment (LCA) is a method for evaluating the environmental impacts of products holistically, including direct and supply chain impacts. The current LCA methodologies and the standards by the International Organization for Standardization (ISO) impose practical difficulties for drawing system boundaries; decisions on inclusion or exclusion of processes in an analysis (the cutoff criteria) are typically not made on a scientific basis. In particular, the requirement of deciding which processes could be excluded from the inventory can be rather difficult to meet because many excluded processes have often never been assessed by the practitioner, and therefore, their negligibility cannot be guaranteed. LCA studies utilizing economic input−output analysis have shown that, in practice, excluded processes can contribute as much to the product system under study as included processes; thus, the subjective determination of the system boundary may lead to invalid results. System boundaries in LCA are discussed herein with particular attention to outlining hybrid approaches as methods for resolving the boundary selection problem in LCA. An input−output model can be used to describe at least a part of a product system, and an ISO-compatible system boundary selection procedure can be designed by applying hybrid input−output-assisted approaches. There are several hybrid input−output analysis-based LCA methods that can be implemented in practice for broadening system boundary and also for ISO compliance.

A generic classifier-ensemble approach for biomedical named entity recognition

In named entity recognition (NER) for biomedical literature, approaches based on combined classifiers have demonstrated great performance improvement compared to a single (best) classifier. This is mainly owed to sufficient level of diversity exhibited among classifiers, which is a selective property of classifier set. Given a large number of classifiers, how to select different classifiers to put into a classifier-ensemble is a crucial issue of multiple classifier-ensemble design. With this observation in mind, we proposed a generic genetic classifier-ensemble method for the classifier selection in biomedical NER. Various diversity measures and majority voting are considered, and disjoint feature subsets are selected to construct individual classifiers. A basic type of individual classifier – Support Vector Machine (SVM) classifier is adopted as SVM-classifier committee. A multi-objective Genetic algorithm (GA) is employed as the classifier selector to facilitate the ensemble classifier to improve the overall sample classification accuracy. The proposed approach is tested on the benchmark dataset – GENIA version 3.02 corpus, and compared with both individual best SVM classifier and SVM-classifier ensemble algorithm as well as other machine learning methods such as CRF, HMM and MEMM. The results show that the proposed approach outperforms other classification algorithms and can be a useful method for the biomedical NER problem.

A hybrid model for named entity recognition using unstructured medical text

Named entity recognition (NER) is an essential step in the process of information extraction within text mining. This paper proposes a technique to extract drug named entities from unstructured and informal medical text using a hybrid model of lexicon-based and rule-based techniques. In the proposed model, a lexicon is first used as the initial step to detect drug named entities. Inference rules are then deployed to further extract undetected drug names. The designed rules employ part of speech tags and morphological features for drug name detection. The proposed hybrid model is evaluated using a benchmark data set from the i2b2 2009 medication challenge, and is able to achieve an f-score of 66.97%.

Enhancing medical named entity recognition with an extended segment representation technique

Objective : The objective of this paper is to formulate an extended segment representation (SR) technique to enhance named entity recognition (NER) in medical applications.

Methods : An extension to the IOBES (Inside/Outside/Begin/End/Single) SR technique is formulated. In the proposed extension, a new class is assigned to words that do not belong to a named entity (NE) in one context but appear as an NE in other contexts. Ambiguity in such cases can negatively affect the results of classification-based NER techniques. Assigning a separate class to words that can potentially cause ambiguity in NER allows a classifier to detect NEs more accurately; therefore increasing classification accuracy.

Results : The proposed SR technique is evaluated using the i2b2 2010 medical challenge data set with eight different classifiers. Each classifier is trained separately to extract three different medical NEs, namely treatment, problem, and test. From the three experimental results, the extended SR technique is able to improve the average F1-measure results pertaining to seven out of eight classifiers. The kNN classifier shows an average reduction of 0.18% across three experiments, while the C4.5 classifier records an average improvement of 9.33%.

Classification ensemble to improve medical named entity recognition

An accurate Named Entity Recognition (NER) is important for knowledge discovery in text mining. This paper proposes an ensemble machine learning approach to recognise Named Entities (NEs) from unstructured and informal medical text. Specifically, Conditional Random Field (CRF) and Maximum Entropy (ME) classifiers are applied individually to the test data set from the i2b2 2010 medication challenge. Each classifier is trained using a different set of features. The first set focuses on the contextual features of the data, while the second concentrates on the linguistic features of each word. The results of the two classifiers are then combined. The proposed approach achieves an f-score of 81.8%, showing a considerable improvement over the results from CRF and ME classifiers individually which achieve f-scores of 76% and 66.3% for the same data set, respectively.

Enhancement of medical named entity recognition using graph-based features

Named Entity Recognition (NER) is a crucial step in text mining. This paper proposes a new graph-based technique for representing unstructured medical text. The new representation is used to extract discriminative features that are able to enhance the NER performance. To evaluate the usefulness of the proposed graph-based technique, the i2b2 medication challenge data set is used. Specifically, the 'treatment' named entities are extracted for evaluation using six different classifiers. The F-measure results of five classifiers are enhanced, with an average improvement of up to 26% in performance.

Named entity recognition in unstructured text.

The thesis introduces a set of machine learning techniques that enhance the extraction of Named Entities from informal and unstructured free text.