Automated Classification of Unstructured Bilingual Software Bug Reports: An Industrial Case Study Research

Software bug report classification is a critical process to understand the nature, implications, and causes of software failures. Furthermore, classification enables a fast and appropriate reaction to software bugs. However, for large-scale projects, one must deal with a broad set of bugs from multiple types. In this context, manually classifying bugs becomes cumbersome and time-consuming. Although several studies have addressed automated bug classification using machine learning techniques, they have mainly focused on academic case studies, open-source software, and unilingual text input. This paper presents our automated bug classification approach applied and validated in an industrial case study. In contrast to earlier studies, our study is applied to a commercial software system based on unstructured bilingual bug reports written in English and Turkish. The presented approach adopts and integrates machine learning (ML), text mining, and natural language processing (NLP) techniques to support the classification of software bugs. The approach has been applied within an industrial case study. Compared to manual classification, our results show that bug classification can be automated and even performs better than manual bug classification. Our study shows that the presented approach and the corresponding tools effectively reduce the manual classification time and effort.

Fast Urban Land Cover Mapping Exploiting Sentinel-1 and Sentinel-2 Data

The rapid change and expansion of human settlements raise the need for precise remote-sensing monitoring tools. While some Land Cover (LC) maps are publicly available, the knowledge of the up-to-date urban extent for a specific instance in time is often missing. The lack of a relevant urban mask, especially in developing countries, increases the burden on Earth Observation (EO) data users or requires them to rely on time-consuming manual classification. This paper explores fast and effective exploitation of Sentinel-1 (S1) and Sentinel-2 (S2) data for the generation of urban LC, which can be frequently updated. The method is based on an Object-Based Image Analysis (OBIA), where one Multi-Spectral (MS) image is used to define clusters of similar pixels through super-pixel segmentation. A short stack (<2 months) of Synthetic Aperture Radar (SAR) data is then employed to classify the clusters, exploiting the unique characteristics of the radio backscatter from human-made targets. The repeated illumination and acquisition geometry allows defining robust features based on amplitude, coherence, and polarimetry. Data from ascending and descending orbits are combined to overcome distortions and decrease sensitivity to the orientation of structures. Finally, an unsupervised Machine Learning (ML) model is used to separate the signature of urban targets in a mixed environment. The method was validated in two sites in Portugal, with diverse types of LC and complex topography. Comparative analysis was performed with two state-of-the-art high-resolution solutions, which require long sensing periods, indicating significant agreement between the methods (averaged accuracy of around 90%).

Sustainable development: Innovations in business

Innovation and sustainable development have become buzzwords in the 21st century with the idea of creative destruction launched by Joseph Alois Schumpeter being the base for evolutionary economics. However, new institutional economics helps to understand the necessity of support provided to entrepreneurs and innovators by science and administration to reduce the risk of launching the said innovations. This e-book is devoted to selected types of innovation. Every type of innovation is described with the use of theoretical background and is enriched by adequate case study. Traditional division into four types of innovation, proposed by J.A. Schumpeter (1934), containing product, process, organizational and marketing innovations, was widely accepted, including European Union institutions (OECD/Eurostat, 2008). The concept of innovation has long been dominated by a technical approach to the innovation process, despite the economic arguments exposed by one of the precursors of the theory of innovation and, at the same time, the school of evolutionary economics—Joseph Alois Schumpeter. Frequently, in the context of innovation, it is indicated that organizational and marketing aspects play a part in the successful introduction of innovation onto the market. The structure of the book is based on the typology proposed by Keeley, Walters, Pikkel and Quinn (2013), which focuses on the economic character of innovations. Ten types of innovation are directly related to Schumpeter’s and Oslo Manual classification. A new set of innovations emphasize the economic side of innovation process. The technical novelties are to support new configuration, offering or customers’ experience. This new approach is based on presumptions coming from design thinking idea, leading to user—driven innovation and on cooperation with institutions and entities supporting innovation process. The chapters are devoted to every type of innovation, grouped into three major parts: innovations based on configuration, offering and experience. In the book, configuration includes types of innovations focused on innermost workings of an enterprise and its business system. Offering part contains the types of innovations, that are focused on an enterprise’s core product (good or service), or a collection of its products. The last part, dedicated to innovations based on experience, is focused on more customer-facing elements of an enterprise and its business system.

A machine learning pipeline for classification of cetacean echolocation clicks in large underwater acoustic datasets

Machine learning algorithms, including recent advances in deep learning, are promising for tools for detection and classification of broadband high frequency signals in passive acoustic recordings. However, these methods are generally data-hungry and progress has been limited by challenges related to the lack of labeled datasets adequate for training and testing. Large quantities of known and as yet unidentified broadband signal types mingle in marine recordings, with variability introduced by acoustic propagation, source depths and orientations, and interacting signals. Manual classification of these datasets is unmanageable without an in-depth knowledge of the acoustic context of each recording location. A signal classification pipeline is presented which combines unsupervised and supervised learning phases with opportunities for expert oversight to label signals of interest. The method is illustrated with a case study using unsupervised clustering to identify five toothed whale echolocation click types and two anthropogenic signal categories. These categories are used to train a deep network to classify detected signals in either averaged time bins or as individual detections, in two independent datasets. Bin-level classification achieved higher overall precision (>99%) than click-level classification. However, click-level classification had the advantage of providing a label for every signal, and achieved higher overall recall, with overall precision from 92 to 94%. The results suggest that unsupervised learning is a viable solution for efficiently generating the large, representative training sets needed for applications of deep learning in passive acoustics.

A topic modeling analysis of Korea’s T&I research trends in the 2010s

The present study aims to demonstrate the relevance of topic modeling as a new research tool for analyzing research trends in the T&I field. Until now, most efforts to this end have relied on manual classification based on pre-established typologies. This method is time- and labor-consuming, prone to subjective biases, and limited in describing a vast amount of research output. As a key component of text mining, topic modeling offers an efficient way of summarizing topic structure and trends over time in a collection of documents while being able to describe the entire system without having to rely on sampling. As a case study, the present paper applies the technique to analyzing a collection of abstracts from four Korean Language T&I journals for the 2010s decade (from 2010 to 2019). The analysis proves the technique to be highly successful in uncovering hidden topical structure and trends in the abstract corpus. The results are discussed along with implications of the technique for the T&I field.

Wood–leaf Classification of Tree Point Cloud Based on Intensity and Geometric Information

Terrestrial laser scanning (TLS) can obtain tree point clouds with high precision and high density. The efficient classification of wood points and leaf points is essential for the study of tree structural parameters and ecological characteristics. Using both intensity and geometric information, we present an automated wood–leaf classification with a three-step classification and wood point verification. The tree point cloud was classified into wood points and leaf points using intensity threshold, neighborhood density and voxelization successively, and was then verified. Twenty-four willow trees were scanned using the RIEGL VZ-400 scanner. Our results were compared with the manual classification results. To evaluate the classification accuracy, three indicators were introduced into the experiment: overall accuracy (OA), Kappa coefficient (Kappa), and Matthews correlation coefficient (MCC). The ranges of OA, Kappa, and MCC of our results were from 0.9167 to 0.9872, 0.7276 to 0.9191, and 0.7544 to 0.9211, respectively. The average values of OA, Kappa, and MCC were 0.9550, 0.8547, and 0.8627, respectively. The time costs of our method and another were also recorded to evaluate the efficiency. The average processing time was 1.4 seconds per million points for our method. The results show that our method represents a potential wood–leaf classification technique with the characteristics of automation, high speed, and good accuracy.

Using neural networks to support high-quality evidence mapping

Background The Living Evidence Map Project at the Norwegian Institute of Public Health (NIPH) gives an updated overview of research results and publications. As part of NIPH’s mandate to inform evidence-based infection prevention, control and treatment, a large group of experts are continously monitoring, assessing, coding and summarising new COVID-19 publications. Screening tools, coding practice and workflow are incrementally improved, but remain largely manual. Results This paper describes how deep learning methods have been employed to learn classification and coding from the steadily growing NIPH COVID-19 dashboard data, so as to aid manual classification, screening and preprocessing of the rapidly growing influx of new papers on the subject. Our main objective is to make manual screening scalable through semi-automation, while ensuring high-quality Evidence Map content. Conclusions We report early results on classifying publication topic and type from titles and abstracts, showing that even simple neural network architectures and text representations can yield acceptable performance.

Classification of Echocardiogram View using A Convolutional Neural Network

The standard views in echocardiography capture distinct slices of the heart which can be used to assess cardiac function. Determining the view of a given echocardiogram is the first step for analysis. To automate this step, a deep network of the ResNet-18 architecture was used to classify between six standard views. The network parameters were pre-trained with the ImageNet database and prediction quality was assessed with a visualization tool known as gradient-weighted class activation mapping (Grad-CAM). The network was able to distinguish between three parasternal short axis views and three apical views to ~99\% accuracy. 10-fold cross validation showed a 97\%-98\% accuracy for the apical view subcategories (which included apical two-, three-, and four- chamber views). Grad-CAM images of these views highlighted features that were similar to those used by experts in manual classification. Parasternal short axis subcategories (which included apex level, mitral valve level, and papillary muscle level) had accuracies of 54\%-73\%. Grad-CAM images illustrate that the network classifies most parasternal short axis views as belonging to the papillary muscle level. Likely more images and incorporating time-dependent features would increase the parasternal short axis view accuracy. Overall, a convolutional neural network can be used to reliably classify echocardiogram views.

Evaluation of a machine learning classifier for metamodels

Modeling is a ubiquitous activity in the process of software development. In recent years, such an activity has reached a high degree of intricacy, guided by the heterogeneity of the components, data sources, and tasks. The democratized use of models has led to the necessity for suitable machinery for mining modeling repositories. Among others, the classification of metamodels into independent categories facilitates personalized searches by boosting the visibility of metamodels. Nevertheless, the manual classification of metamodels is not only a tedious but also an error-prone task. According to our observation, misclassification is the norm which leads to a reduction in reachability as well as reusability of metamodels. Handling such complexity requires suitable tooling to leverage raw data into practical knowledge that can help modelers with their daily tasks. In our previous work, we proposed AURORA as a machine learning classifier for metamodel repositories. In this paper, we present a thorough evaluation of the system by taking into consideration different settings as well as evaluation metrics. More importantly, we improve the original AURORA tool by changing its internal design. Experimental results demonstrate that the proposed amendment is beneficial to the classification of metamodels. We also compared our approach with two baseline algorithms, namely gradient boosted decision tree and support vector machines. Eventually, we see that AURORA outperforms the baselines with respect to various quality metrics.