Nikola Milosevic

Machine learning aided Android malware classification

The widespread adoption of Android devices and their capability to access significant private and confidential information have resulted in these devices being targeted by malware developers. Existing Android malware analysis techniques can be broadly categorized into static and dynamic analysis. In this paper, we present two machine learning aided approaches for static analysis of Android malware. The first approach is based on permissions and the other is based on source code analysis utilizing a bag-of-words representation model. Our permission-based model is computationally inexpensive, and is implemented as the feature of OWASP Seraphimdroid Android app that can be obtained from Google Play Store. Our evaluations of both approaches indicate an F-score of 95.1% and F-measure of 89% for the source code-based classification and permission-based classification models, respectively.

Extracting Patient Data from Tables in Clinical Literature - Case Study on Extraction of BMI, Weight and Number of Patients

Current biomedical text mining efforts are mostly focused on extracting information from the body of research articles. However, tables contain important information such as key characteristics of clinical trials. Here, we examine the feasibility of information extraction from tables. We focus on extracting data about clinical trial participants. We propose a rule-based method that decomposes tables into cell level structures and then extracts information from these structures. Our method performed with a F-measure of 83.3% for extraction of number of patients, 83.7% for extraction of patient’s body mass index and 57.75% for patient’s weight. These results are promising and show that information extraction from tables in biomedical literature is feasible.

Disentangling the Structure of Tables in Scientific Literature

Within the scientific literature, tables are commonly used to present factual and statistical information in a compact way, which is easy to digest by readers. The ability to “understand” the structure of tables is key for information extraction in many domains. However, the complexity and variety of presentation layouts and value formats makes it difficult to automatically extract roles and relationships of table cells. In this paper, we present a model that structures tables in a machine readable way and a methodology to automatically disentangle and transform tables into the modelled data structure. The method was tested in the domain of clinical trials: it achieved an F-score of 94.26 % for cell function identification and 94.84 % for identification of inter-cell relationships.

Classification of Intangible Social Innovation Concepts

In social sciences, similarly to other fields, there is exponential growth of literature and textual data that people are no more able to cope with in a systematic manner. In many areas there is a need to catalogue knowledge and phenomena in a certain area. However, social science concepts and phenomena are complex and in many cases there is a dispute in the field between conflicting definitions. In this paper we present a method that catalogues a complex and disputed concept of social innovation by applying text mining and machine learning techniques. Recognition of social innovations is performed by decomposing a definitions into several more specific criteria (social objectives, social actor interactions, outputs and innovativeness). For each of these criteria, a machine learning-based classifier is created that checks whether certain text satisfies given criteria. The criteria can be successfully classified with an F1-score of 0.83–0.86. The presented method is flexible, since it allows combining criteria in a later stage in order to build and analyse the definition of choice.