Evaluation of Machine Learning Classifiers for Mobile Network Intrusion Detection Systems

Mobile malwares are increasing with the growing number of Mobile users. Mobile malwares can perform several operations which lead to cybersecurity threats such as, stealing financial or personal information, installing malicious applications, sending premium SMS, creating backdoors, keylogging and crypto-ransomware attacks. Knowing the fact that there are many illegitimate Applications available on the App stores, most of the mobile users remain careless about the security of their Mobile devices and become the potential victim of these threats. Previous studies have shown that not every antivirus is capable of detecting all the threats; due to the fact that Mobile malwares use advance techniques to avoid detection. A Network-based IDS at the operator side will bring an extra layer of security to the subscribers and can detect many advanced threats by analyzing their traffic patterns. Machine Learning(ML) will provide the ability to these systems to detect unknown threats for which signatures are not yet known. This research is focused on the evaluation of Machine Learning classifiers in Network-based Intrusion detection systems for Mobile Networks. In this study, different techniques of Network-based intrusion detection with their advantages, disadvantages and state of the art in Hybrid solutions are discussed. Finally, a ML based NIDS is proposed which will work as a subsystem, to Network-based IDS deployed by Mobile Operators, that can help in detecting unknown threats and reducing false positives. In this research, several ML classifiers were implemented and evaluated. This study is focused on Android-based malwares, as Android is the most popular OS among users, hence most targeted by cyber criminals. Supervised ML algorithms based classifiers were built using the dataset which contained the labeled instances of relevant features. These features were extracted from the traffic generated by samples of several malware families and benign applications. These classifiers were able to detect malicious traffic patterns with the TPR upto 99.6% during Cross-validation test. Also, several experiments were conducted to detect unknown malware traffic and to detect false positives. These classifiers were able to detect unknown threats with the Accuracy of 97.5%. These classifiers could be integrated with current NIDS', which use signatures, statistical or knowledge-based techniques to detect malicious traffic. Technique to integrate the output from ML classifier with traditional NIDS is discussed and proposed for future work.

Predicting diffusion of innovations with self-organisation and machine learning

The main subject of this master's thesis was predicting diffusion of innovations. The prediction was done in a special case: product has been available in some countries, and based on its diffusion in those countries the prediction is done for other countries. The prediction was based on finding similar countries with Self-Organizing Map~(SOM), using parameters of countries. Parameters included various economical and social key figures. SOM was optimised for different products using two different methods: (a) by adding diffusion information of products to the country parameters, and (b) by weighting the country parameters based on their importance for the diffusion of different products. A novel method using Differential Evolution (DE) was developed to solve the latter, highly non-linear optimisation problem. Results were fairly good. The prediction method seems to be on a solid theoretical foundation. The results based on country data were good. Instead, optimisation for different products did not generally offer clear benefit, but in some cases the improvement was clearly noticeable. The weights found for the parameters of the countries with the developed SOM optimisation method were interesting, and most of them could be explained by properties of the products.

Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Sentence Compression with Supervised Machine Learning

The subject of the thesis is automatic sentence compression with machine learning, so that the compressed sentences remain both grammatical and retain their essential meaning. There are multiple possible uses for the compression of natural language sentences. In this thesis the focus is generation of television program subtitles, which often are compressed version of the original script of the program. The main part of the thesis consists of machine learning experiments for automatic sentence compression using different approaches to the problem. The machine learning methods used for this work are linear-chain conditional random fields and support vector machines. Also we take a look which automatic text analysis methods provide useful features for the task. The data used for machine learning is supplied by Lingsoft Inc. and consists of subtitles in both compressed an uncompressed form. The models are compared to a baseline system and comparisons are made both automatically and also using human evaluation, because of the potentially subjective nature of the output. The best result is achieved using a CRF - sequence classification using a rich feature set. All text analysis methods help classification and most useful method is morphological analysis. Tutkielman aihe on suomenkielisten lauseiden automaattinen tiivistäminen koneellisesti, niin että lyhennetyt lauseet säilyttävät olennaisen informaationsa ja pysyvät kieliopillisina. Luonnollisen kielen lauseiden tiivistämiselle on monta käyttötarkoitusta, mutta tässä tutkielmassa aihetta lähestytään television ohjelmien tekstittämisen kautta, johon käytännössä kuuluu alkuperäisen tekstin lyhentäminen televisioruudulle paremmin sopivaksi. Tutkielmassa kokeillaan erilaisia koneoppimismenetelmiä tekstin automaatiseen lyhentämiseen ja tarkastellaan miten hyvin erilaiset luonnollisen kielen analyysimenetelmät tuottavat informaatiota, joka auttaa näitä menetelmiä lyhentämään lauseita. Lisäksi tarkastellaan minkälainen lähestymistapa tuottaa parhaan lopputuloksen. Käytetyt koneoppimismenetelmät ovat tukivektorikone ja lineaarisen sekvenssin mallinen CRF. Koneoppimisen tukena käytetään tekstityksiä niiden eri käsittelyvaiheissa, jotka on saatu Lingsoft OY:ltä. Luotuja malleja vertaillaan Lopulta mallien lopputuloksia evaluoidaan automaattisesti ja koska teksti lopputuksena on jossain määrin subjektiivinen myös ihmisarviointiin perustuen. Vertailukohtana toimii kirjallisuudesta poimittu menetelmä. Tutkielman tuloksena paras lopputulos saadaan aikaan käyttäen CRF sekvenssi-luokittelijaa laajalla piirrejoukolla. Kaikki kokeillut teksin analyysimenetelmät auttavat luokittelussa, joista tärkeimmän panoksen antaa morfologinen analyysi.

Scalable Feature Selection Applications for Genome-Wide Association Studies of Complex Diseases

Personalized medicine will revolutionize our capabilities to combat disease. Working toward this goal, a fundamental task is the deciphering of geneticvariants that are predictive of complex diseases. Modern studies, in the formof genome-wide association studies (GWAS) have afforded researchers with the opportunity to reveal new genotype-phenotype relationships through the extensive scanning of genetic variants. These studies typically contain over half a million genetic features for thousands of individuals. Examining this with methods other than univariate statistics is a challenging task requiring advanced algorithms that are scalable to the genome-wide level. In the future, next-generation sequencing studies (NGS) will contain an even larger number of common and rare variants. Machine learning-based feature selection algorithms have been shown to have the ability to effectively create predictive models for various genotype-phenotype relationships. This work explores the problem of selecting genetic variant subsets that are the most predictive of complex disease phenotypes through various feature selection methodologies, including filter, wrapper and embedded algorithms. The examined machine learning algorithms were demonstrated to not only be effective at predicting the disease phenotypes, but also doing so efficiently through the use of computational shortcuts. While much of the work was able to be run on high-end desktops, some work was further extended so that it could be implemented on parallel computers helping to assure that they will also scale to the NGS data sets. Further, these studies analyzed the relationships between various feature selection methods and demonstrated the need for careful testing when selecting an algorithm. It was shown that there is no universally optimal algorithm for variant selection in GWAS, but rather methodologies need to be selected based on the desired outcome, such as the number of features to be included in the prediction model. It was also demonstrated that without proper model validation, for example using nested cross-validation, the models can result in overly-optimistic prediction accuracies and decreased generalization ability. It is through the implementation and application of machine learning methods that one can extract predictive genotype–phenotype relationships and biological insights from genetic data sets.

IoT Based Pain Management using Physiological Parameters

The continuous technology evaluation is benefiting our lives to a great extent. The evolution of Internet of things and deployment of wireless sensor networks is making it possible to have more connectivity between people and devices used extensively in our daily lives. Almost every discipline of daily life including health sector, transportation, agriculture etc. is benefiting from these technologies. There is a great potential of research and refinement of health sector as the current system is very often dependent on manual evaluations conducted by the clinicians. There is no automatic system for patient health monitoring and assessment which results to incomplete and less reliable heath information. Internet of things has a great potential to benefit health care applications by automated and remote assessment, monitoring and identification of diseases. Acute pain is the main cause of people visiting to hospitals. An automatic pain detection system based on internet of things with wireless devices can make the assessment and redemption significantly more efficient. The contribution of this research work is proposing pain assessment method based on physiological parameters. The physiological parameters chosen for this study are heart rate, electrocardiography, breathing rate and galvanic skin response. As a first step, the relation between these physiological parameters and acute pain experienced by the test persons is evaluated. The electrocardiography data collected from the test persons is analyzed to extract interbeat intervals. This evaluation clearly demonstrates specific patterns and trends in these parameters as a consequence of pain. This parametric behavior is then used to assess and identify the pain intensity by implementing machine learning algorithms. Support vector machines are used for classifying these parameters influenced by different pain intensities and classification results are achieved. The classification results with good accuracy rates between two and three levels of pain intensities shows clear indication of pain and the feasibility of this pain assessment method. An improved approach on the basis of this research work can be implemented by using both physiological parameters and electromyography data of facial muscles for classification.

New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

Learning Preferences with Kernel-Based Methods

Learning of preference relations has recently received significant attention in machine learning community. It is closely related to the classification and regression analysis and can be reduced to these tasks. However, preference learning involves prediction of ordering of the data points rather than prediction of a single numerical value as in case of regression or a class label as in case of classification. Therefore, studying preference relations within a separate framework facilitates not only better theoretical understanding of the problem, but also motivates development of the efficient algorithms for the task. Preference learning has many applications in domains such as information retrieval, bioinformatics, natural language processing, etc. For example, algorithms that learn to rank are frequently used in search engines for ordering documents retrieved by the query. Preference learning methods have been also applied to collaborative filtering problems for predicting individual customer choices from the vast amount of user generated feedback. In this thesis we propose several algorithms for learning preference relations. These algorithms stem from well founded and robust class of regularized least-squares methods and have many attractive computational properties. In order to improve the performance of our methods, we introduce several non-linear kernel functions. Thus, contribution of this thesis is twofold: kernel functions for structured data that are used to take advantage of various non-vectorial data representations and the preference learning algorithms that are suitable for different tasks, namely efficient learning of preference relations, learning with large amount of training data, and semi-supervised preference learning. Proposed kernel-based algorithms and kernels are applied to the parse ranking task in natural language processing, document ranking in information retrieval, and remote homology detection in bioinformatics domain. Training of kernel-based ranking algorithms can be infeasible when the size of the training set is large. This problem is addressed by proposing a preference learning algorithm whose computation complexity scales linearly with the number of training data points. We also introduce sparse approximation of the algorithm that can be efficiently trained with large amount of data. For situations when small amount of labeled data but a large amount of unlabeled data is available, we propose a co-regularized preference learning algorithm. To conclude, the methods presented in this thesis address not only the problem of the efficient training of the algorithms but also fast regularization parameter selection, multiple output prediction, and cross-validation. Furthermore, proposed algorithms lead to notably better performance in many preference learning tasks considered.

Kernel-Based Ranking. Methods for Learning and Performance Estimation

Machine learning provides tools for automated construction of predictive models in data intensive areas of engineering and science. The family of regularized kernel methods have in the recent years become one of the mainstream approaches to machine learning, due to a number of advantages the methods share. The approach provides theoretically well-founded solutions to the problems of under- and overfitting, allows learning from structured data, and has been empirically demonstrated to yield high predictive performance on a wide range of application domains. Historically, the problems of classification and regression have gained the majority of attention in the field. In this thesis we focus on another type of learning problem, that of learning to rank. In learning to rank, the aim is from a set of past observations to learn a ranking function that can order new objects according to how well they match some underlying criterion of goodness. As an important special case of the setting, we can recover the bipartite ranking problem, corresponding to maximizing the area under the ROC curve (AUC) in binary classification. Ranking applications appear in a large variety of settings, examples encountered in this thesis include document retrieval in web search, recommender systems, information extraction and automated parsing of natural language. We consider the pairwise approach to learning to rank, where ranking models are learned by minimizing the expected probability of ranking any two randomly drawn test examples incorrectly. The development of computationally efficient kernel methods, based on this approach, has in the past proven to be challenging. Moreover, it is not clear what techniques for estimating the predictive performance of learned models are the most reliable in the ranking setting, and how the techniques can be implemented efficiently. The contributions of this thesis are as follows. First, we develop RankRLS, a computationally efficient kernel method for learning to rank, that is based on minimizing a regularized pairwise least-squares loss. In addition to training methods, we introduce a variety of algorithms for tasks such as model selection, multi-output learning, and cross-validation, based on computational shortcuts from matrix algebra. Second, we improve the fastest known training method for the linear version of the RankSVM algorithm, which is one of the most well established methods for learning to rank. Third, we study the combination of the empirical kernel map and reduced set approximation, which allows the large-scale training of kernel machines using linear solvers, and propose computationally efficient solutions to cross-validation when using the approach. Next, we explore the problem of reliable cross-validation when using AUC as a performance criterion, through an extensive simulation study. We demonstrate that the proposed leave-pair-out cross-validation approach leads to more reliable performance estimation than commonly used alternative approaches. Finally, we present a case study on applying machine learning to information extraction from biomedical literature, which combines several of the approaches considered in the thesis. The thesis is divided into two parts. Part I provides the background for the research work and summarizes the most central results, Part II consists of the five original research articles that are the main contribution of this thesis.

Similarity measure based classification

Luokittelujärjestelmää suunniteltaessa tarkoituksena on rakentaa systeemi, joka pystyy ratkaisemaan mahdollisimman tarkasti tutkittavan ongelma-alueen. Hahmontunnistuksessa tunnistusjärjestelmän ydin on luokitin. Luokittelun sovellusaluekenttä on varsin laaja. Luokitinta tarvitaan mm. hahmontunnistusjärjestelmissä, joista kuvankäsittely toimii hyvänä esimerkkinä. Myös lääketieteen parissa tarkkaa luokittelua tarvitaan paljon. Esimerkiksi potilaan oireiden diagnosointiin tarvitaan luokitin, joka pystyy mittaustuloksista päättelemään mahdollisimman tarkasti, onko potilaalla kyseinen oire vai ei. Väitöskirjassa on tehty similaarisuusmittoihin perustuva luokitin ja sen toimintaa on tarkasteltu mm. lääketieteen paristatulevilla data-aineistoilla, joissa luokittelutehtävänä on tunnistaa potilaan oireen laatu. Väitöskirjassa esitetyn luokittimen etuna on sen yksinkertainen rakenne, josta johtuen se on helppo tehdä sekä ymmärtää. Toinen etu on luokittimentarkkuus. Luokitin saadaan luokittelemaan useita eri ongelmia hyvin tarkasti. Tämä on tärkeää varsinkin lääketieteen parissa, missä jo pieni tarkkuuden parannus luokittelutuloksessa on erittäin tärkeää. Väitöskirjassa ontutkittu useita eri mittoja, joilla voidaan mitata samankaltaisuutta. Mitoille löytyy myös useita parametreja, joille voidaan etsiä juuri kyseiseen luokitteluongelmaan sopivat arvot. Tämä parametrien optimointi ongelma-alueeseen sopivaksi voidaan suorittaa mm. evoluutionääri- algoritmeja käyttäen. Kyseisessä työssä tähän on käytetty geneettistä algoritmia ja differentiaali-evoluutioalgoritmia. Luokittimen etuna on sen joustavuus. Ongelma-alueelle on helppo vaihtaa similaarisuusmitta, jos kyseinen mitta ei ole sopiva tutkittavaan ongelma-alueeseen. Myös eri mittojen parametrien optimointi voi parantaa tuloksia huomattavasti. Kun käytetään eri esikäsittelymenetelmiä ennen luokittelua, tuloksia pystytään parantamaan.

Learning Grasp Affordances from Vision

Monimutkaisissa ja muuttuvissa ympäristöissä työskentelevät robotit tarvitsevat kykyä manipuloida ja tarttua esineisiin. Tämä työ tutkii robottitarttumisen ja robottitartuntapis-teiden koneoppimisen aiempaa tutkimusta ja nykytilaa. Nykyaikaiset menetelmät käydään läpi, ja Le:n koneoppimiseen pohjautuva luokitin toteutetaan, koska se tarjoaa parhaan onnistumisprosentin tutkituista menetelmistä ja on muokattavissa sopivaksi käytettävissä olevalle robotille. Toteutettu menetelmä käyttää intensititeettikuvaan ja syvyyskuvaan po-hjautuvia ominaisuuksi luokitellakseen potentiaaliset tartuntapisteet. Tämän toteutuksen tulokset esitellään.

Deep generative models for facial keypoints detection

A new area of machine learning research called deep learning, has moved machine learning closer to one of its original goals: artificial intelligence and general learning algorithm. The key idea is to pretrain models in completely unsupervised way and finally they can be fine-tuned for the task at hand using supervised learning. In this thesis, a general introduction to deep learning models and algorithms are given and these methods are applied to facial keypoints detection. The task is to predict the positions of 15 keypoints on grayscale face images. Each predicted keypoint is specified by an (x,y) real-valued pair in the space of pixel indices. In experiments, we pretrained deep belief networks (DBN) and finally performed a discriminative fine-tuning. We varied the depth and size of an architecture. We tested both deterministic and sampled hidden activations and the effect of additional unlabeled data on pretraining. The experimental results show that our model provides better results than publicly available benchmarks for the dataset.

Intelligent Internet Data Searching

In this thesis author approaches the problem of automated text classification, which is one of basic tasks for building Intelligent Internet Search Agent. The work discusses various approaches to solving sub-problems of automated text classification, such as feature extraction and machine learning on text sources. Author also describes her own multiword approach to feature extraction and pres-ents the results of testing this approach using linear discriminant analysis based classifier, and classifier combining unsupervised learning for etalon extraction with supervised learning using common backpropagation algorithm for multilevel perceptron.

A Dependency Parsing Approach to Biomedical Text Mining

Biomedical research is currently facing a new type of challenge: an excess of information, both in terms of raw data from experiments and in the number of scientific publications describing their results. Mirroring the focus on data mining techniques to address the issues of structured data, there has recently been great interest in the development and application of text mining techniques to make more effective use of the knowledge contained in biomedical scientific publications, accessible only in the form of natural human language. This thesis describes research done in the broader scope of projects aiming to develop methods, tools and techniques for text mining tasks in general and for the biomedical domain in particular. The work described here involves more specifically the goal of extracting information from statements concerning relations of biomedical entities, such as protein-protein interactions. The approach taken is one using full parsing—syntactic analysis of the entire structure of sentences—and machine learning, aiming to develop reliable methods that can further be generalized to apply also to other domains. The five papers at the core of this thesis describe research on a number of distinct but related topics in text mining. In the first of these studies, we assessed the applicability of two popular general English parsers to biomedical text mining and, finding their performance limited, identified several specific challenges to accurate parsing of domain text. In a follow-up study focusing on parsing issues related to specialized domain terminology, we evaluated three lexical adaptation methods. We found that the accurate resolution of unknown words can considerably improve parsing performance and introduced a domain-adapted parser that reduced the error rate of theoriginal by 10% while also roughly halving parsing time. To establish the relative merits of parsers that differ in the applied formalisms and the representation given to their syntactic analyses, we have also developed evaluation methodology, considering different approaches to establishing comparable dependency-based evaluation results. We introduced a methodology for creating highly accurate conversions between different parse representations, demonstrating the feasibility of unification of idiverse syntactic schemes under a shared, application-oriented representation. In addition to allowing formalism-neutral evaluation, we argue that such unification can also increase the value of parsers for domain text mining. As a further step in this direction, we analysed the characteristics of publicly available biomedical corpora annotated for protein-protein interactions and created tools for converting them into a shared form, thus contributing also to the unification of text mining resources. The introduced unified corpora allowed us to perform a task-oriented comparative evaluation of biomedical text mining corpora. This evaluation established clear limits on the comparability of results for text mining methods evaluated on different resources, prompting further efforts toward standardization. To support this and other research, we have also designed and annotated BioInfer, the first domain corpus of its size combining annotation of syntax and biomedical entities with a detailed annotation of their relationships. The corpus represents a major design and development effort of the research group, with manual annotation that identifies over 6000 entities, 2500 relationships and 28,000 syntactic dependencies in 1100 sentences. In addition to combining these key annotations for a single set of sentences, BioInfer was also the first domain resource to introduce a representation of entity relations that is supported by ontologies and able to capture complex, structured relationships. Part I of this thesis presents a summary of this research in the broader context of a text mining system, and Part II contains reprints of the five included publications.