Learning task specific distributed paragraph representations using a 2-tier convolutional neural network

We introduce a type of 2-tier convolutional neural network model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categorization). We decompose the paragraph semantics into 3 cascaded constitutes: word representation, sentence composition and document composition. Specifically, we learn distributed word representations by a continuous bag-of-words model from a large unstructured text corpus. Then, using these word representations as pre-trained vectors, distributed task specific sentence representations are learned from a sentence level corpus with task-specific labels by the first tier of our model. Using these sentence representations as distributed paragraph representation vectors, distributed paragraph representations are learned from a paragraph-level corpus by the second tier of our model. It is evaluated on DBpedia ontology classification dataset and Amazon review dataset. Empirical results show the effectiveness of our proposed learning model for generating distributed paragraph representations.

From biomedical literature to knowledge:mining protein-protein interactions

To date, more than 16 million citations of published articles in biomedical domain are available in the MEDLINE database. These articles describe the new discoveries which accompany a tremendous development in biomedicine during the last decade. It is crucial for biomedical researchers to retrieve and mine some specific knowledge from the huge quantity of published articles with high efficiency. Researchers have been engaged in the development of text mining tools to find knowledge such as protein-protein interactions, which are most relevant and useful for specific analysis tasks. This chapter provides a road map to the various information extraction methods in biomedical domain, such as protein name recognition and discovery of protein-protein interactions. Disciplines involved in analyzing and processing unstructured-text are summarized. Current work in biomedical information extracting is categorized. Challenges in the field are also presented and possible solutions are discussed.

A survey of UK selection practices across different organization sizes and industry sectors

This paper presents results of a study examining the methods used to select employees in 579 UK organizations representing a range of different organization sizes and industry sectors. Overall, a smaller proportion of organizations in this sample reported using formalized methods (e.g., assessment centres) than informal methods (e.g., unstructured interviews). The curriculum vitae (CVs) was the most commonly used selection method, followed by the traditional triad of application form, interviews, and references. Findings also indicated that the use of different selection methods was similar in both large organizations and small-to-medium-sized enterprises. Differences were found across industry sector with public and voluntary sectors being more likely to use formalized techniques (e.g., application forms rather than CVs and structured rather than unstructured interviews). The results are discussed in relation to their implications, both in terms of practice and future research.

Relation discovery from web data for competency management

In current organizations, valuable enterprise knowledge is often buried under rapidly expanding huge amount of unstructured information in the form of web pages, blogs, and other forms of human text communications. We present a novel unsupervised machine learning method called CORDER (COmmunity Relation Discovery by named Entity Recognition) to turn these unstructured data into structured information for knowledge management in these organizations. CORDER exploits named entity recognition and co-occurrence data to associate individuals in an organization with their expertise and associates. We discuss the problems associated with evaluating unsupervised learners and report our initial evaluation experiments in an expert evaluation, a quantitative benchmarking, and an application of CORDER in a social networking tool called BuddyFinder.

Implications of query caching for JXTA peers

This dissertation studies the caching of queries and how to cache in an efficient way, so that retrieving previously accessed data does not need any intermediary nodes between the data-source peer and the querying peer in super-peer P2P network. A precise algorithm was devised that demonstrated how queries can be deconstructed to provide greater flexibility for reusing their constituent elements. It showed how subsequent queries can make use of more than one previous query and any part of those queries to reconstruct direct data communication with one or more source peers that have supplied data previously. In effect, a new query can search and exploit the entire cached list of queries to construct the list of the data locations it requires that might match any locations previously accessed. The new method increases the likelihood of repeat queries being able to reuse earlier queries and provides a viable way of by-passing shared data indexes in structured networks. It could also increase the efficiency of unstructured networks by reducing traffic and the propensity for network flooding. In addition, performance evaluation for predicting query routing performance by using a UML sequence diagram is introduced. This new method of performance evaluation provides designers with information about when it is most beneficial to use caching and how the peer connections can optimize its exploitation.

A classification model for product-service offerings

Organisations have been approaching servitisation in an unstructured fashion. This is partially because there is insufficient understanding of the different types of Product-Service offerings. Therefore, a more detailed understanding of Product-Service types might advance the collective knowledge and assist organisations that are considering a servitisation strategy. Current models discuss specific aspects on the basis of few (or sometimes single) dimensions. In this paper, we develop a comprehensive model for classifying traditional and green Product-Service offerings, thus combining business and green offerings in a single model. We describe the model building process and its practical application in a case study. The model reveals the various traditional and green options available to companies and identifies how to compete between services; it allows servitisation positions to be identified such that a company may track its journey over time. Finally it fosters the introduction of innovative Product-Service Systems as promising business models to address environmental and social challenges. © 2013 Elsevier Ltd. All rights reserved.

The importance of mealtime structure for reducing child food fussiness

The aim of this study was to explore how the structure of mealtimes within the family setting is related to children's fussy eating behaviours. Seventy-five mothers of children aged between 2 and 4 years were observed during a typical mealtime at home. The mealtimes were coded to rate mealtime structure and environment as well as the child's eating behaviours (food refusal, difficulty to feed, eating speed, positive and negative vocalisations). Mealtime structure emerged as an important factor which significantly distinguished children with higher compared with lower levels of food fussiness. Children whose mothers ate with their child and ate the same food as their child were observed to refuse fewer foods and were easier to feed compared with children whose mothers did not. During mealtimes where no distractors were used (e.g. no TV, magazines or toys), or where children were allowed some input into food choice and portioning, children were also observed to demonstrate fewer fussy eating behaviours. Findings of this study suggest that it may be important for parents to strike a balance between structured mealtimes, where the family eats together and distractions are minimal, alongside allowing children some autonomy in terms of food choice and intake.

An optical fiber Bragg grating tactile sensor

Tactile sensors are needed for many emerging robotic and telepresence applications such as keyhole surgery and robot operation in unstructured environments. We have proposed and demonstrated a tactile sensor consisting of a fibre Bragg grating embedded in a polymer "finger". When the sensor is placed in contact with a surface and translated tangentially across it measurements on the changes in the reflectivity spectrum of the grating provide a measurement of the spatial distribution of forces perpendicular to the surface and thus, through the elasticity of the polymer material, to the surface roughness. Using a sensor fabricated from a Poly Siloxane polymer (Methyl Vinyl Silicone rubber) spherical cap 50 mm in diameter, 6 mm deep with an embedded 10 mm long Bragg grating we have characterised the first and second moment of the grating spectral response when scanned across triangular and semicircular periodic structures both with a modulation depth of 1 mm and a period of 2 mm. The results clearly distinguish the periodicity of the surface structure and the differences between the two different surface profiles. For the triangular structure a central wavelength modulation of 4 pm is observed and includes a fourth harmonic component, the spectral width is modulated by 25 pm. Although crude in comparison to human senses these results clearly shown the potential of such a sensor for tactile imaging and we expect that with further development in optimising both the grating and polymer "finger" properties a much increased sensitivity and spatial resolution is achievable.

Unsupervised KDD to creatively support managers' decision making with fuzzy association rules:a distribution channel application

To be competitive in contemporary turbulent environments, firms must be capable of processing huge amounts of information, and effectively convert it into actionable knowledge. This is particularly the case in the marketing context, where problems are also usually highly complex, unstructured and ill-defined. In recent years, the development of marketing management support systems has paralleled this evolution in informational problems faced by managers, leading to a growth in the study (and use) of artificial intelligence and soft computing methodologies. Here, we present and implement a novel intelligent system that incorporates fuzzy logic and genetic algorithms to operate in an unsupervised manner. This approach allows the discovery of interesting association rules, which can be linguistically interpreted, in large scale databases (KDD or Knowledge Discovery in Databases.) We then demonstrate its application to a distribution channel problem. It is shown how the proposed system is able to return a number of novel and potentially-interesting associations among variables. Thus, it is argued that our method has significant potential to improve the analysis of marketing and business databases in practice, especially in non-programmed decisional scenarios, as well as to assist scholarly researchers in their exploratory analysis. © 2013 Elsevier Inc.

Expert System for Decision-Making Problem in Economics

An expert system (ES) is a class of computer programs developed by researchers in artificial intelligence. In essence, they are programs made up of a set of rules that analyze information about a specific class of problems, as well as provide analysis of the problems, and, depending upon their design, recommend a course of user action in order to implement corrections. ES are computerized tools designed to enhance the quality and availability of knowledge required by decision makers in a wide range of industries. Decision-making is important for the financial institutions involved due to the high level of risk associated with wrong decisions. The process of making decision is complex and unstructured. The existing models for decision-making do not capture the learned knowledge well enough. In this study, we analyze the beneficial aspects of using ES for decision- making process.

Help-seeking for medically unexplained hearing difficulties:a qualitative study

Aims - Up to 10% of audiology patients report diffi culties hearing speech in noise even though clinical investigation reveals normal hearing thresholds, in other words, no evidence of physical pathology. The diagnostic category applied to these patients is known as King-Kopetzky Syndrome (KKS). This study aimed to gather descriptions of patients' experiences of the clinical encounter involving their KKS diagnosis and analyse the themes of help-seeking, as part of a larger study into the process of coping with medically unexplained hearing diffi culties. Method - A qualitative approach was employed, comprising unstructured interviews in the homes of 25 patients who had attended audiology services (and received a diagnosis of KKS) in Bath and Cardiff. Thematic analysis of transcripts was undertaken, infl uenced by grounded theory techniques. Findings - Informants characterized the clinical encounter as either negative or positive. Negative consultations were those in which patients' illness claims were dismissed and as such not validated. Positive encounters were typifi ed by the provision of meaningful information that reconciled clinical information with the patients' experiences of hearing loss. Conclusion - Successful management of medically unexplained illnesses requires the adoption of a patient-centred approach, rather than focusing on the absence of observable pathology

Coordinating expertise across knowledge boundaries in offshore-outsourcing projects:the role of codification

The coordination of effort within and among different expert groups is a central feature of contemporary organizations. Within the existing literature, however, a dichotomy has emerged in our understanding of the role played by codification in coordinating expert groups. One strand of literature emphasizes codification as a process that supports coordination by enabling the storage and ready transfer of knowledge. In contrast, another strand highlights the persistent differences between expert groups that create boundaries to the transfer of knowledge, seeing coordination as dependent on the quality of the reciprocal interactions between groups and individuals. Our research helps to resolve such contested understandings of the coordinative role played by codification. By focusing on the offshore-outsourcing of knowledge-intensive services, we examine the role played by codification when expertise was coordinated between client staff and onsite and offshore vendor personnel in a large-scale outsourcing contract between TATA Consultancy Services (TCS) and ABN AMRO bank. A number of theoretical contributions flow from our analysis of the case study, helping to move our understanding beyond the dichotomized views of codification outlined above. First, our study adds to previous work where codification has been seen as a static concept by demonstrating the multiple, coexisting, and complementary roles that codification may play. We examine the dynamic nature of codification and show changes in the relative importance of these different roles in coordinating distributed expertise over time. Second, we reconceptualize the commonly accepted view of codification as focusing on the replication and diffusion of knowledge by developing the notion of the codification of the “knower” as complementary to the codification of knowledge. Unlike previous studies of expertise directories, codification of the knower does not involve representing expertise in terms of occupational skills or competences but enables the reciprocal interrelating of expertise required by more unstructured tasks.

Semantic Interpretation of 3D Point Clouds of Historical Objects

This paper presents the main concepts of a project under development concerning the analysis process of a scene containing a large number of objects, represented as unstructured point clouds. To achieve what we called the "optimal scene interpretation" (the shortest scene description satisfying the MDL principle) we follow an approach for managing 3-D objects based on a semantic framework based on ontologies for adding and sharing conceptual knowledge about spatial objects.

A Bayesian Model for Learning Using Flashcards

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2015

Implementing a knowledge management system within an NHS hospital:a case study exploring the roll-out of an Electronic Patient Record (EPR)

This research aims to contribute to understanding the implementation of knowledge management systems (KMS) in the field of health through a case study, leading to theory building and theory extension. We use the concept of the business process approach to knowledge management as a theoretical lens to analyse and explore how a large teaching hospital developed, executed and practically implemented a KMS. A qualitative study was conducted over a 2.5 year period with data collected from semi-structured interviews with eight members of the strategic management team, 12 clinical users and 20 patients in addition to non-participant observation of meetings and documents. The theoretical propositions strategy was used as the overarching approach for data analysis. Our case study provides evidence that true patient centred approaches to supporting care delivery with a KMS benefit from process thinking at both the planning and implementation stages, and an emphasis on the knowledge demands resulting from: the activities along the care pathways; where cross-overs in care occur; and knowledge sharing for the integration of care. The findings also suggest that despite the theoretical awareness of KMS implementation methodologies, the actual execution of such systems requires practice and learning. Flexible, fluid approaches through rehearsal are important and communications strategies should focus heavily on transparency incorporating both structured and unstructured communication methods.