Generally, software measurement is considered as a management tool which if conducted in an effective manner, helps the project manager and the entire software team to take decisions that leads to successful completion of the project. Many indicators have been projected and validated in the field of software engineering but indicators related to Global Software Development (GSD) projects still need to be explored. Identification of indicators may guide the project managers to assess the coordination processes effectively between collocated and distributed team in GSD environment. The aim of this paper is to identify the coordination strategies and related indicators from the perspectives of GSD practitioners. We carried out semi structured interview sessions among project managers and consultants from GSD industries to accomplish this task. The collected data were analysed using Thematic Analysis and Nvivo software. The results of this study are a set of coordination strategies and related indicators that can be a guideline for project managers to assess the coordination processes in GSD projects development towards its success.
Linked data is a data publishing method that can be used to connect any kind of globally available data into a single multigraph. This kind of graph provides enormous opportunities for machine learning and data mining techniques to train models with large heterogenous types of data and find new relationships. Both are however strongly dependent on the engineering of high quality features and therefore requires knowledge of the domain. Recent advances in the field of representation learning has led to significant progress in automating the feature engineering process. Neural word embedding techniques from the natural language processing domain have been used to learn representations of graph nodes and subsequently applied to linked data nodes. In contrast to natural language where sentences serve as natural boundary for the context of a word, in a graph – boundaries are not clearly defined and multiple context sampling strategies exist. Applying different context sampling strategies on graph nodes result in different context sentences and subsequently different features. In this work, we explore two different context sampling strategies: predicate removal from random walks as well as breadth first search based sampling and compare them to the state of the art based on random walks. The quality of the generated features is evaluated indirectly by measuring the performance of machine learning models on a classification task across multiple data sets. Furthermore, we explore the effect of generating embeddings only for the entities that have to be classified and their neighbors, instead of generating embeddings for every node in a possibly large RDF graph. The results suggest that for classification of same typed entities the inclusion of predicates in the sampled walks for generating embeddings is of little use and can be omitted without losing classification accuracy. Results also show that the in-degree and out-degree of the entities may be useful hint for selecting the optimal sampling technique.
Takumi Sato, Toshihiro Endo, Alexander Vazhenin, Rentaro Yoshioka
571 - 581
This article presents the GUI-based Support Tool for convenient usage of the BBCoM technology. This technology is designed to integrate software components in a system, provide communications between them using script-based specifications of protocols and data dependencies between system components. The presented tool extends on the possibilities of existing system and allows making the programming process more effective and convenient. Accordingly, the user may graphically manage all design stages that are needed for preparing and executing the BBCoM applications. The results of experiments demonstrate correctness and accuracy of the presented tool.
Stefan Gries, Ole Meyer, Julius Ollesch, Florian Wessling, Marc Hesenius, Volker Gruhn
582 - 595
Developing CPS means uniting multiple engineering disciplines: mechanical, electrical and software engineering. Each of them provides a set of models, guidelines and processes crucial for a projects success. Consequently, CPS development is heavily influenced by processes known in either engineering discipline. There is currently no coherent software engineering approach to develop CPS, making it very hard to align the aforementioned domain experts in a controlled and repeatable process. This paper takes a step towards filling this gap by providing the insights during the development of a CPS in the form of an experience report. Based on our findings we validated the use of the Double TwinPeaks model and contribute to the field of software engineering for CPS the Matrix of Granularity to assess the components of a CPS in terms of customizability, risk and constraints.
Agile Software Development methods have been largely adopted in the last ten years since they have certain advantages over the traditional approaches. However, industrial software development processes are getting more and more complex and dynamic. As a consequence, optimization of software project scheduling has always been big challenges in both practice and academia, even with Agile methods. There is always uncertainty as well as a need for a probabilistic method that better model and predict uncertainty in software projects. This paper proposes Bayesian Networks to model risk factors in Agile software projects as well as managing risks in Agile iteration scheduling. The paper also addresses 19 common risk factors that affect iteration scheduling. Based on the method, a software was developed as a support tool for managers to control their project schedules as it can assess the possibility of each schedule.
Andreas Fuchs, Vincent von Hof, Matthias Neugebauer
607 - 620
Software testing is a broad research field and of great relevance to practitioners. Software testing involves multiple consecutive testing phases. One of these phases is the unit-testing phase, during which individual requirements of the software component are checked. Only once software-units and -components have been tested, can the testing process continue. Trivially, if this phase requires a great amount time, the testing process is delayed and in the worst case, the rollout of the system has to be rescheduled. Focusing on the widely adopted JUnit test framework, a system was proposed to execute test cases on multiple distributed virtual machines. This paper evaluates the approach to distribute such test cases across multiple Java Virtual Machines (JVMs), leveraging container-based virtualization, by means of a prototype. The distribution achieves a significant runtime decrease. Furthermore, the effect of different distributions strategies on the overall runtime is evaluated.
The paper suggests a new approach to create online decision support systems (ODSSs) to control distributed cyber-physical systems (DCPSs). We consider ODSSs which are based on applying hierarchical fuzzy situational networks together with fuzzy mathematical programming and fuzzy logical inference. These methods allow one to make efficient decisions in the conditions of dynamically changing external factors. The conceptual principles to create ODSSs are provided. The generalized algorithm of ODSS' functioning is developed. As a case study we consider a multi-service communication network which is a communication basis of DCPSs and one of the most complicated subsystem operating with fuzzy data. The performed evaluation of the proposed approach demonstrates its significant gain in comparison with known statistical methods and methods based on the application of reference situations. Based on the results of the evaluation, the structure of intelligent agents' software implementing ODSS for DCPSs is developed.
Hoang-Nhat Do, Duc-Man Nguyen, Quyet-Thang Huynh, Nhu-Hang Ha
637 - 649
It is undeniable that visual aid is the most useful option to capture the objects than any methods by using text, log. With current trends of software development methods, instead of documenting requirements in hundreds of pages or planning projects, developers are using Scrum-board and Mind-map as tools to visualize their plans, project progress, and project requirements. To the given challenges of Exploratory Testing, one of the solutions is to track in detail all of what has been done by testers and visualize them in any form which easies to capture information. By using a case study, this study investigates the role of One2Explore as a visual tool for testing in MeU Company. The findings of this study indicate that using graphs as a method to display test execution and relevant information is an approach that can be beneficial in achieving effective testing.
Datasets basically contains data and metadata. Data are often misinterpreted due to insufficient metadata and gives rise to quality issues associated with the datasets such as failure to clearly identify the entity being measured and inability to clarify how the metrics were generated. We believe creating common agreement about the terminology and concepts in datasets is important to ensure the meaning of data able to be interpreted correctly. We developed dataset metamodel that describes the structure and concepts in a dataset, and the relationships between each concept to gain a shared understanding of the content of datasets. As a preliminary evaluation, we conducted a user study to evaluate the effectiveness of dataset metamodel. We used an online survey as our user study method. The survey aims to study how well participants understand the definitions of dataset category elements in the dataset metamodel and able to apply them to a range of data sets. We found that participants who had relevant background knowledge and experience in research, particularly in analysing data sets able to answer more questions correctly than participants who had less relevant background knowledge and experience in research. The results of our survey provide evidence that our dataset metamodel is effective to be used by researchers to model datasets for analysis in software engineering. Future work, we need to reproduce the results with more appropriately sized samples of researchers in the relevant areas.
Imen Marsit, Mohamed Nazih Omri, Ji Meng Loh, Ali Mili
664 - 677
Software mutation is a widely used technique of software testing that consists in generating variants of a base program by applying standard modifications to its source code. One of the main obstacles in the use of software mutations is the existence of equivalent mutants, i.e. mutants whose behavior is indistinguishable from the base program, even though their source code is distinct. Despite several decades of research, the identification of equivalent mutants remains an open problem. Rather than attempting to identify individual mutants that are equivalent to the base, we argue that it is often sufficient to estimate the number of equivalent mutants; also, we argue that the number of equivalent mutants depends on two factors that must be considered in the estimation effort, namely the base program and the mutation operators that are used; in this paper, we explore the impact of mutation operators on the number of equivalent mutants.
Projects in software engineering have very low success rate compared to other engineering areas. This rate can be increased by building a better project plan with the help of project success forecasting tools. These tools employ prediction methods, which use time, budget and scope to perform estimations and they can only be used in late phases of the project. In this study, we proposed a new approach, which is capable of forecasting the project success in the initiation or the analysis phase of the project. In order to achieve this, we utilized sponsor score, which reflects the business outcomes of a project, as a metric. We also derived several features of these projects and evaluated their applicability with different classifiers in our forecasting approach. We tested our proposed method on a dataset of software projects, which were carried out in an international telecommunication company. Our results show that the proposed model is capable of predicting project success in the early stages of the project, in means of sponsor score.
Fadoua Fellir, Khalid Nafil, Ali Idri, Lawrence Chung
688 - 701
Software effort estimation is a key factor for software development project success. Case-based reasoning (CBR), as a viable alternative to analogy methods, has often been used as a reference to calculate effort estimation. Albeit its conceptual simplicity, however, CBR-based effort estimation seems difficult and complex in reality, especially when enhancement on the estimate precision is highly desirable. For an effective and fast estimation, we present in this paper an innovative tool, automated-SEE (software effort estimation), for estimating software development effort using improved CBR. This tool enables the consideration of a comprehensive set of different types of requirements, including both functional requirements (FRs) and non-functional requirements (NFRs), and domain properties (DPs). Application of this tool to 36 (students') projects shows that the resulting software effort estimation is highly reliable.
In this paper, we describe how mobile learning sets new impulses for teaching and learning in project-oriented higher education. In our project clavis, we support the self-directed learning, deepening and application of knowledge and skills in project phases of the master program of “Applied Computer Science and Systems Engineering” (AI-SE) at the University of Duisburg-Essen. Therefore, we want to provide practical examples and relevant learning units in a mobile multimedia toolbox. Students can come back to the small learning chunks during their master projects regardless of time and place. The development of our learning platform is an agile and iterative process model that is tailored to the needs of the target group. To ensure user-friendly implementation and to increase the acceptance, we involve members of the target group continuously throughout the development and implementation process. We raised the requirements in workshops with the participation of future users and the development team. Based on the findings we became aware of the requirements related to the content, didactic methods and technical concepts, that form the basis for the implementation. In this article, we provide a brief insight into our approach, the concept and the students' requirements for the development of the micro learning units and mobile learning platform.
Xiomarah Maria Guzmán de Núñez, Edward Rolando Núñez-Valdez, Jordán Pascual Espada, Rubén González Crespo, Vicente García-Díaz
713 - 722
People rely on other people's opinions to make decisions, especially if they belong to their circle of trust. In addition, there are lots of websites of recognized prestige that provide people opinions about different products and services, which are read by millions of people before making a decision. That is why systems for sentiment analysis are becoming increasingly important to automatically process the information and determine feelings of users. They analyze their written words, usually conditioned by the characteristics of microblogging platforms, in which a large number of messages are published every day, providing a great source of information, impossible to be managed manually. In this work, we show a proposal to analyze the feeling that Twitter users have towards different hotels or hotel chains through a platform that could be easily adapted to other contexts. The goal is to create q a structure based on independent and interchangeable components that will make it possible to conduct studies in a more uniform, open and transparent way.
In this paper, a neural network is proposed to analyse Twitter sentiment classification for the Twitter domain. The study examines and evaluates the performance of neural networks with word embedding features in Twitter sentiment classification. Four benchmark datasets were used to represent different domains. The results indicated that the proposed method significantly improves the accuracy of the neural network classifier compared to existing works in aspect-based sentiment classification, especially for the highly imbalanced dataset.
Juan Bernabé-Moreno, Alvaro Tejeda-Lorente, Julio Herce-Zelaya, Carlos Porcel, Enrique Herrera-Viedma
735 - 748
Polarity detection plays a pivotal role in the modern cognitive research field. Common approaches to compute the polarity of a given word rely on experimental dictionaries providing always the same value, no matter where the word is used and lacking therefore adaptivity to particular contexts. In a previous article, we proposed a method supported by fuzzy linguistic modelling to quantify this contextual bias and to enable the bias-aware sentiment analysis. In this work, we implement the bias contextualization based on a word embeddings technique to capture a larger portion of the contextual bias. To show how our approach works, we measure the bias of common concepts in two different domains and discuss the results compared with our previous attempt based on document contextualization.
Word2vec have been proven to facilitate various NLP tasks. We suppose that the vector space of word2vec can be divided into positive and negative. Hence, word2vec is applicable to Sentiment Analysis tasks. In this paper, we proposed supervised approach for Sentence-level Sentiment Analysis. We utilize pre trained Word Embeddings to extract features from Sentence. We train feature vectors and their polarities to make classification model. After training, we use the model for predicting new sentence's polarity. We compare our method against state of the arts and discuss about how to improve our method.
Ahmad Alaqsam, Ali Selamat, Rose Alinda Alias, Nor Hidayati Zakaria, Fatimah Puteh, Lim Kok Cheng, Mohammad Nazir Ahmad
759 - 770
The enhancement of English language proficiency is a clear aim in many educational institutions around the world. One of the latest technology that has been adopted in education recently is Augmented Reality (AR) but still needs more consideration and investigation to insure its effectiveness in English language learning ELL. This paper highlights the most AR technologies that have been employed in ELL and views to what extent they have been useful and beneficial. Moreover, it points out to the limitations that would slowdown the adoption of AR in Education generally and English language learning particularly.
The user reviews of mobile apps are important assets that reflect the users' needs and complaints about particular apps regarding features, usability, and designs. From investigating the content of such reviews, the app developers can acquire useful information guiding the future maintenance and evolution work. Previous studies on opinion mining in mobile app reviews have provided various approaches to eliciting such critical information. A particular update of an app can provide changes to the app that result in users' reversed opinions, as well as, specific new complaints or praises. However, limited studies focus on eliciting the user opinions regarding a particular mobile app update, or the impact the update imposes. In this paper, we propose a method for systematically studying and analyzing the evolution of the users' opinions taking into consideration a set of mobile app updates. For doing so, we compare the topics appearing in the users' reviews before and after the updates. We also validate the method with an experiment on an existing mobile app.
Event extraction plays a significant role in information extraction (IE). Compared with previous works on event extraction in English, relatively little effort has been made to extract Chinese events. Existing Chinese event extraction systems have two main drawbacks. First, they can only extract a limited number of events. Second, they don't organize their extracted events by entities or date or demonstrate them in a user-friendly way. In this paper, we propose Timeline, a Chinese event extraction system that extracts massive events from Chinese online encyclopedias . Our proposed system extracts event triples (entity, date and event description) from huge numbers of articles meanwhile generating the largest Chinese structured event base. Our system also automatizes event validation and normalization procedures to harvest high-quality events, and then organize events by corresponding entities and dates. Furthermore, we have also developed an interactive web portal that encodes events along a visual timeline, which satisfies the process of exploring historical events. We also designed comprehensive experiments to show the effectiveness of our extraction and validation work. Both extracted event triples and timeline web portal are published.
The unmanned surface vehicles (USVs) have become a major trend in the construction of naval equipment and its flexibility and intelligence making it widely used in real-scenes. For cooperative defense with multiple USVs to intercept intruders, it is proposed that planning the path with obstacle avoidance and protecting the target by task allocation actions. The particle swarm optimization based on probe mechanism (PM-PSO) is proposed for pathing planning with obstacle avoidance. With the consideration of the constraints of different defense schemes such as the path cost, the interception loss, the defense income and so on, it is proposed that the dispersed particle swarm optimization based on genetic algorithm (GA-PSO) for the interception task allocation. Furthermore, the fitness function is proposed to evaluate the feasibility of the interception path and the quality of the allocation scheme. Extensive simulation experiments are conducted and demonstrated the effectiveness, rationality and superiority of the proposed methods.