Code smells are structures in code that often harm its quality. Manually detecting code smells is challenging, so researchers proposed many automatic detectors. Traditional code smell detectors employ metric-based heuristics, but researchers have recently adopted a Machine-Learning (ML) based approach. This paper compares the performance of multiple ML-based code smell detection models against multiple metric-based heuristics for detection of God Class and Long Method code smells. We assess the effectiveness of different source code representations for ML: we evaluate the effectiveness of traditionally used code metrics against code embeddings (code2vec, code2seq, and CuBERT). This study is the first to evaluate the effectiveness of pre-trained neural source code embeddings for code smell detection to the best of our knowledge. This approach helped us leverage the power of transfer learning – our study is the first to explore whether the knowledge mined from code understanding models can be transferred to code smell detection. A secondary contribution of our research is the systematic evaluation of the effectiveness of code smell detection approaches on the same large-scale, manually labeled MLCQ dataset. Almost every study that proposes a detection approach tests this approach on the dataset unique for the study. Consequently, we cannot directly compare the reported performances to derive the best-performing approach.

As the importance of application performance grows in modern enterprise systems, many organizations employ application performance management (APM) tools to help them deal with potential performance problems during production. In addition to monitoring capabilities, these tools provide problem detection and alerting. In large enterprise systems these tools can report a very large number of performance problems. They have to be dealt with individually, in a time-consuming and error-prone manual process, even though many of them have a common root cause. In this vision paper, we propose using automatic categorization for dealing with large numbers of performance problems reported by APM tools. This leads to the aggregation of reported problems, reducing the work required for resolving them. Additionally, our approach opens the possibility of extending the analysis approaches to use this information for a more efficient diagnosis of performance problems.

A recent promise to access unstructured clinical data from electronic health records on large-scale has revitalized the interest in automated de-identification of clinical notes, which includes the identification of mentions of Protected Health Information (PHI). We describe the methods developed and evaluated as part of the i2b2/UTHealth 2014 challenge to identify PHI defined by 25 entity types in longitudinal clinical narratives. Our approach combines knowledge-driven (dictionaries and rules) and data-driven (machine learning) methods with a large range of features to address de-identification of specific named entities. In addition, we have devised a two-pass recognition approach that creates a patient-specific run-time dictionary from the PHI entities identified in the first step with high confidence, which is then used in the second pass to identify mentions that lack specific clues. The proposed method achieved the overall micro F1-measures of 91% on strict and 95% on token-level evaluation on the test dataset (514 narratives). Whilst most PHI entities can be reliably identified, particularly challenging were mentions of Organizations and Professions. Still, the overall results suggest that automated text mining methods can be used to reliably process clinical notes to identify personal information and thus providing a crucial step in large-scale de-identification of unstructured data for further clinical and epidemiological studies.

Heart disease is the leading cause of death globally and a significant part of the human population lives with it. A number of risk factors have been recognized as contributing to the disease, including obesity, coronary artery disease (CAD), hypertension, hyperlipidemia, diabetes, smoking, and family history of premature CAD. This paper describes and evaluates a methodology to extract mentions of such risk factors from diabetic clinical notes, which was a task of the i2b2/UTHealth 2014 Challenge in Natural Language Processing for Clinical Data. The methodology is knowledge-driven and the system implements local lexicalized rules (based on syntactical patterns observed in notes) combined with manually constructed dictionaries that characterize the domain. A part of the task was also to detect the time interval in which the risk factors were present in a patient. The system was applied to an evaluation set of 514 unseen notes and achieved a micro-average F-score of 88% (with 86% precision and 90% recall). While the identification of CAD family history, medication and some of the related disease factors (e.g. hypertension, diabetes, hyperlipidemia) showed quite good results, the identification of CAD-specific indicators proved to be more challenging (F-score of 74%). Overall, the results are encouraging and suggested that automated text mining methods can be used to process clinical notes to identify risk factors and monitor progression of heart disease on a large-scale, providing necessary data for clinical and epidemiological studies.

OBJECTIVE: Identification of clinical events (eg, problems, tests, treatments) and associated temporal expressions (eg, dates and times) are key tasks in extracting and managing data from electronic health records. As part of the i2b2 2012 Natural Language Processing for Clinical Data challenge, we developed and evaluated a system to automatically extract temporal expressions and events from clinical narratives. The extracted temporal expressions were additionally normalized by assigning type, value, and modifier. MATERIALS AND METHODS: The system combines rule-based and machine learning approaches that rely on morphological, lexical, syntactic, semantic, and domain-specific features. Rule-based components were designed to handle the recognition and normalization of temporal expressions, while conditional random fields models were trained for event and temporal recognition. RESULTS: The system achieved micro F scores of 90% for the extraction of temporal expressions and 87% for clinical event extraction. The normalization component for temporal expressions achieved accuracies of 84.73% (expression's type), 70.44% (value), and 82.75% (modifier). DISCUSSION: Compared to the initial agreement between human annotators (87-89%), the system provided comparable performance for both event and temporal expression mining. While (lenient) identification of such mentions is achievable, finding the exact boundaries proved challenging. CONCLUSIONS: The system provides a state-of-the-art method that can be used to support automated identification of mentions of clinical events and temporal expressions in narratives either to support the manual review process or as a part of a large-scale processing of electronic health databases.

We propose a novel semi-supervised learning algorithm, called IMCC, designed for co-training classifiers on single-view datasets. Our method runs the co-training algorithm for a predefined number of times, each time using a different random split of features. Thus, a set of diverse co-training classifiers is created. Each of these classifiers then labels each of the examples for which we want to determine the class label. In this way, each example for classification is assigned multiple labels. We then treat this as a problem of learning from inconsistent and unreliable annotators in a multi-annotator problem setting and estimate the single hidden true label for each example. In experimental results obtained on 25 benchmark datasets of various properties IMCC outperformed five considered alternative methods for co-training on single-view datasets, and resulted in a statistical tie with a Naive Bayes classifier trained using a much larger set of labeled examples.

A wide-spread integration of Wireless Sensor Networks (WSNs) into daily life applications demands modular and flexible service oriented architectures. Discovering nodes and their services is imperative to any large-scale sensor network deployment. In this paper, we describe nanoSD, a lightweight service discovery protocol, designed for highly dynamic, mobile and heterogeneous sensor networks. We demonstrate through a fully functional implementation and its performance evaluation that nanoSD supports heterogeneous architectures and is scalable. It is able to efficiently cope network dynamics present in real WSN deployments. It uses features like delta service advertisements, message compression and piggy-backing techniques, which results in low network overhead. Furthermore, nanoSD protocol is easily integratable to web-service based backend systems using very limited resources.