The electrocardiogram (ECG) has become an important tool for the diagnosis of cardiovascular diseases. As long-term ECG recordings become more common, driven partly by the development of intelligent hardware, the requirement for automatic ECG analysis continues to grow. Research has attempted to use the expert knowledge to optimise ECG-related algorithms, however, visual analysis of long-term ECG is tedious and operator dependent. In previous studies, an ECG beat clustering approach based on self-organising maps has been applied to reduce the amount of time the operator must to spend. This unsupervised approach partitions the ECG beats into 25 groups, however, the cluster number (25) does not accurately reflect the actual number of categories. In this study, an integrated method is presented for the clustering of ECG beats based on an improved semi-supervised affinity propagation algorithm with independent component analysis. Using the MIT-BIH arrhythmia database, the authors find that the resulting clusters to exhibit a high degree of precision. The integrated method outperforms other conventional methods in the MIT-BIH database, and has great theoretical and practical significance in the field of cardiac disease.

Twitter is a popular microblogging platform, with 310 million monthly active users as of the first quarter of 2016. It is a rapidly growing microblogging platform where people share opinions, news on any topic of their interest. More than 7000 tweets are posted every second. Due to the enormous volume of data being generated, it becomes difficult to extract useful/meaningful information. Tweets collected from Twitter on a certain topic may consist of numerous conversation threads about relevant sub-topics. However, it is difficult to discern these sub-topics if the data is visualised as a single word cloud. The authors transform a corpus of tweets to a spectral domain and evaluate the results from a number of clustering algorithms, including K-means, latent semantic indexing and non-negative matrix factorisation to construct clustered word clouds that helps identify sub-topics under a broader topic.

Non-functional requirements (NFR) elicitation is a complex activity, since it requires specific knowledge in many different areas, such as performance, security, portability and usability. An approach for the definition of NFR elicitation guides (ADEG-NFR) was proposed with the objective of supporting the requirement engineers in carrying out this activity and providing mechanisms for customer involvement in this process. An elicitation guide consists of a set of questions, templates and examples of requirements to make the elicitation process easier using an appropriate language to customer. Besides, appropriate language to the customer's understanding is the natural language described in a clear way, avoiding the use of technical terms. This study evaluates the results of the experience of use of ADEG-NFR in a software development organisation. Results have shown that ADEG-NFR fulfills its purpose. In addition, the ADEG-NFR evaluation process has identified opportunities for improvement that can help in the evolution and adoption of ADEG-NFR by different organisations in the industry.

The sentiment implied in user generated content represents the authors' personality, attitude, education level and social status. In Crowdfunding, the sentimental factor of the text description may impact the backers' investment intention on the project. The authors study the textual description from the sentimental aspect on the pledge results by employing text mining. The study proves that positive sentiment in the blurb and detailed description promotes the successful campaigns while it should not contain any sentimental factor in title. The predictive analysis shows that the predictive accuracy can be improved 7% based on the baseline model after considering sentimental factors from 64.4% to 71.7%.

Hadoop on datacentre is a popular analytical platform for enterprises. Cloud vendors host Hadoop clusters on the datacentre to provide high performance analytical computing facilities to its customers, who demand a parallel programming model to deal with huge data. Effective cost/time management and ingenious resource consumption among the concurrent users, must be the primary concern without which the key aspiration behind high performance cloud computing would suffer. Workflows portray such high performance applications in terms of individual jobs and dependencies between them. Workflows can be scheduled on virtual machines (VMs) in datacentre to make best possible use of resources. In the authors’ earlier work, a mechanism to pack and execute the customer jobs as workflows on Hadoop platform was proposed which minimises the VM cost and also executes the workflow jobs within deadline. In this work, the authors try to optimise certain other parameters such as load on cloud, response time for workflows, resource usage effectiveness by applying soft computing methods. Stochastic hill climbing (SCH) is a soft computing approach used to solve many optimisation problems. In this study, they have employed the SHC approach to schedule workflow jobs to VMs and thereby optimise the above mentioned multiple parameters in cloud datacentre.

An increasingly common practice in large software development companies is to distribute tasks among geographically dispersed teams. This practice can bring many benefits, such as gains in terms of time and cost, but many are the challenges. One of the major challenges regards the method of assigning tasks to remote teams. This method involves knowing, classifying and ordering the factors that drive the assignment of tasks in a distributed scenario. This is a typical scenario for decision-making based on multiple criteria. Verbal decision analysis (VDA) is a multi-criteria framework to decision-making. This study presents a hybrid methodology structured on methods of VDA for classification ORdinal CLASSification (ORCLASS) and ordering (ZAPROS III-i) of factors that drive task assignment to distributed teams in software development projects. Tasks were grouped according to their type, i.e. requirements, architecture, implementation, and testing.

The diversity of terminologies used in primary care causes significant challenges regarding semantic interoperability. Attempts to address these challenges usually focus on the creation of metaterminologies, with the peculiarities of national variations of terminologies being overlooked. In this study the extent to which primary care data can be meaningfully exchanged between nationally implemented terminologies is assessed using a rule-based approach. To determine this, a model comprising primary care terminologies and including axioms to define their relations was developed. Generic metrics were designed to determine the completeness and accuracy of any two arbitrary vocabularies within an ontological model. These metrics were used on an implementation of the model to determine the data quality that is preserved when expressing similar data in different primary care terminologies. The results show that values of terminologies which are closely related can express each other's concepts relatively well. The authors conclude that the current state of accuracy and completeness between primary care terminologies does not allow for sufficiently meaningful semantic interoperability, but that their approach of mapping lower-level terminologies to each other next to an ontological approach may yield better results than relying solely on the latter.

Productivity prediction of a software engineer is necessary to determine whether corrective actions are needed and to identify improvement options to produce better results. It can be performed from abstraction levels such as organisation, team project, individual project, or task. Software engineering education and training has approached its efforts at individual level. In this study, the authors propose the application of a data mining technique named support vector regression (SVR) to predict the productivity of individuals (i.e. graduate students). Its prediction accuracy was compared with that of a statistical regression model, and with those of two neural networks. After applying a Wilcoxon statistical test, results suggest that an SVR with linear kernel using new and changed lines of code, and programming language experience as independent variables, could be used for predicting the individual productivity of a higher education graduate student, when software projects coded in either Java or C++ programming languages, have been developed by following a disciplined process specifically proposed for academic environments.

Big data is collected and processed using different sources and tools that lead to privacy issues. Privacy preserving data publishing techniques such as k-anonymity, l-diversity, and t-closeness are used to de-identify the data; however, the chances of re-identification are always remain present since data is collected from multiple sources. Owing to the large volume of data, less generalisation or suppression is required to achieve the same level of privacy, which is also known as ‘large crowd effect’, although it is always challenging to handle such a large data for anonymization. MapReduce handles large volume of data and distributes the data into the smaller chunks across the multiple nodes; consequently, the full advantage of large volume of data is underachieved. Therefore, scalability of privacy preserving techniques becomes a challenging area of research. The authors explore this area and propose an algorithm named scalable k-anonymization (SKA) using MapReduce for privacy preserving big data publishing. The authors also compare the approach with existing approaches that results into a remarkable improvement of the data utility and significantly enhances the performance in terms of running time.