Mapping of Source and Target Data for Application to Machine Learning Driven Discovery of IS Usability Problems

Improving IS (Information System) end-user experience is one of the most important tasks in the analysis of end-users behaviour, evaluation and identification of its improvement potential. However, the application of Machine Learning methods for the UX (User Experience) usability and effic iency improvement is not widely researched. In the context of the usability analysis, the information about behaviour of end-users could be used as an input, while in the output data the focus should be made on non-trivial or difficult attention-grabbing events and scenarios. The goal of this paper is to identify which data potentially can serve as an input for Machine Learning methods (and accordingly graph theory, transformation methods, etc.), to define dependency between these data and desired output, which can help to apply Machine Learning / graph algorithms to user activity records.

The Impact of Note-Taking on the Learning Process in Intelligent Tutoring System Tutomat

The research investigates how note-taking practice affects the learning process in Tutomat, an intelligent tutoring system. The complete analysis includes (i) the identification of learning analytics variables to describe student-Tutomat interaction; (ii) the description of experimental student groups using learning analytics variables; (iii) data-driven clustering and (iv) the comparison of the experimental groups and revealed clusters. The results show that there is a difference in how a student interacts with Tutomat based on note-taking practice. It is revealed that the note-taking practice can be detected using the proposed learning analytics variables with the prediction accuracy of the clustering approach of 85 %.

VP-RDF: An RDF Based Framework to Introduce the Viewpoint in the Description of Resources

The description of resources and their relationships is an essential task on the web. Generally, the web users do not share the same interests and viewpoints. Each user wants that the web provides data and information according to their interests and specialty. The existing query languages, which allow querying data on the web, cannot take into consideration the viewpoint of the user. We propose introducing the viewpoint in the description of the resources. The Resource Description Framework (RDF) represents a common framework to share data and describe resources. In this study, we aim at introducing the notion of the viewpoint in the RDF. Therefore, we propose a View-Point Resource Description Framework (VP-RDF) as an extension of RDF by adding new elements. The existing query languages (e.g., SPARQL) can query the VP-RDF graphs and provide the user with data and information according to their interests and specialty. Therefore, VP-RDF can be useful in intelligent systems on the web.

Time Series Smoothing Improving Forecasting

Both statistical and neural network methods may fail in forecasting time series even operating on a great amount of data. It is an open question of which amount fits best to make sufficiently accurate forecasts on it. This implies that the length or time series might be optimised. Hence, the objective is to improve the quality of forecasting by an assumption that parameters are set nearly at their optimal values. To achieve objective, the two types of the benchmark time series are considered: sine-shaped series and random-like series with repeatability. Trend, seasonality, and decay properties embedded into each type. Based on the benchmark of 24 time series models, it is ascertained that, for improving the forecasting, the time series should be smoothed and then downsampled. These operations can be fulfilled successively until the improvement fails. If preliminary smoothing worsens forecasts, the raw time series is straightforwardly downsampled until the forecasting accuracy starts dropping. However, if time series has a visible property of being noised, the preliminary smoothing is strongly recommended.

Solving Systems of Linear Equations Based on Approximation Solution Projection Analysis

The paper considers an iterative method for solving systems of linear equations (SLE), which applies multiple displacement of the approximation solution point in the direction of the final solution, simultaneously reducing the entire residual of the system of equations. The method reduces the requirements for the matrix of SLE. The following SLE property is used: the point is located farther from the system solution result compared to the point projection onto the equation. Developing the approach, the main emphasis is made on reduction of requirements towards the matrix of the system of equations, allowing for higher volume of calculations.

Expert Survey on Current Trends in Agile, Disciplined and Hybrid Practices for Software Development

Every software development company makes software development based on a specific approach. There are a number of approaches to software development, both disciplined and agile. Each approach includes a set of different activities. Sometimes, the specific nature of a company’s work requires a specific approach, but the need to make work more efficient, faster and better requires implementing activities of other approaches. Then hybrid software development approaches come in. The paper presents an expert survey to examine the most important software development activities, the combinations of development approaches that are used in software development processes and the way of upgrading existing approaches. The evaluated activities of software development process are classified according to their nature – whether they correspond with a team, organisation, documentation, development, and testing. The conclusions are also made on the practices that are required most – disciplined, Agile or hybrid.

Real-Time Turkish Sign Language Recognition Using Cascade Voting Approach with Handcrafted Features

In this study, a machine learning-based system, which recognises the Turkish sign language person-independent in real-time, was developed. A leap motion sensor was used to obtain raw data from individuals. Then, handcraft features were extracted by using Euclidean distance on the raw data. Handcraft features include finger-to-finger, finger -to-palm, finger -to-wrist bone, palm-to-palm and wrist-to-wrist distances. LR, k-NN, RF, DNN, ANN single classifiers were trained using the handcraft features. Cascade voting approach was applied with two-step voting. The first voting was applied for each classifier’s final prediction. Then, the second voting, which voted the prediction of all classifiers at the final decision stage, was applied to improve the performance of the proposed system. The proposed system was tested in real-time by an individual whose hand data were not involved in the training dataset. According to the results, the proposed system presents 100 % value of accuracy in the classification of one hand letters. Besides, the recognition accuracy ratio of the system is 100 % on the two hands letters, except “J” and “H” letters. The recognition accuracy rates were 80 % and 90 %, respectively for “J” and “H” letters. Overall, the cascade voting approach presented a high average classification performance with 98.97 % value of accuracy. The proposed system enables Turkish sign language recognition with high accuracy rates in real time.

Evaluating the Impact of Design Pattern Usage on Energy Consumption of Applications for Mobile Platform

Energy efficiency in mobile computing is really an important issue these days. Owing to the popularity and prevalence of Android operating system among the people, a great number of Android smartphone applications have been developed and proliferated by the software developers. While developing these applications, developers have to keep energy consumption factor in mind, as the efficiency of an application is largely affected by it. Thus, designers and programmers endeavour to choose the best designing approaches to develop energy-efficient applications. It is imperative to assist the programmers in choosing appropriate techniques and strategies to manage power consumption. In the present research, we have investigated the effect of Android application design on its energy utilisation. For this purpose, we have practically implemented design patterns on two Android applications and evaluated their energy consumption before and after implementing these patterns. We have modelled the high-level design of these two Android applications by using software design patterns in such a way as to abate their energy requirement. We have also checked how the quality, maintainability, and efficiency of code are affected by these design patterns. The outcomes of the research can facilitate programmers to utilise these details while developing energy efficient solutions.

Assessing the Impact of Expert Labelling of Training Data on the Quality of Automatic Classification of Lithological Groups Using Artificial Neural Networks

Machine learning (ML) methods are nowadays widely used to automate geophysical study. Some of ML algorithms are used to solve lithological classification problems during uranium mining process. One of the key aspects of using classical ML methods is causing data features and estimating their influence on the classification. This paper presents a quantitative assessment of the impact of expert opinions on the classification process. In other words, we have prepared the data, identified the experts and performed a series of experiments with and without taking into account the fact that the expert identifier is supplied to the input of the automatic classifier during training and testing. Feedforward artificial neural network (ANN) has been used as a classifier. The results of the experiments show that the “knowledge” of the ANN of which expert interpreted the data improves the quality of the automatic classification in terms of accuracy (by 5 %) and recall (by 20 %). However, due to the fact that the input parameters of the model may depend on each other, the SHapley Additive exPlanations (SHAP) method has been used to further assess the impact of expert identifier. SHAP has allowed assessing the degree of parameter influence. It has revealed that the expert ID is at least two times more influential than any of the other input parameters of the neural network. This circumstance imposes significant restrictions on the application of ANNs to solve the task of lithological classification at the uranium deposits.

Definition and Validation of the Subset of SCORM Requirements for the Enhanced Reusability of Learning Content in Learning Management Systems

Nowadays, interoperability of learning management systems is still not very high. The authoring tools can help transfer e-learning content between different learning management systems. However, in this context, they should be able to produce learning content that is compliant with some industry standards. One of the most widely used standards is the SCORM 1.2 release. The research addresses the extension of the functionality of the previously developed content development tool EMMA by incorporating into it the support for the subset of SCORM 1.2 requirements. The paper describes the process of the acquisition, implementation, and validation of the defined requirements. Moreover, it presents the results of the analysis of 33 SCORM authoring tools and 16 SCORM players.