Postdoc in data mining for health - Hiring in process/Finished, not possible to apply

Background
Recent growth in the research activities and the well-established educational programs of the School of Information Technology (ITE) is enabling a significant expansion. In 2018 the total research expenditures exceeded 70 MSEK and the school hosted over 850 students. Over the next two years, the School will grow significantly. 

Description
We are seeking to appoint a full-time post-doctoral researcher. The recruited person will be expected to teach up to 20% and do research at least 80%, within one or several scientific projects. Research activities will depend on competences and interests, but are expected to build upon our existing portfolio.

Examples include the iMedA project, which aims to improve medication adherence of hypertensive patients, by addressing three research questions. First, how to create a meaningful and comprehensive representation of each patient based on comprehensive medical data. Second, how to predict different clinical outcomes (e.g., re-admissions) and non-clinical behaviors (e.g., medication non-adherence) using interpretable machine learning methods. Third, how to identify a selection of intervention strategies that are most appropriate for a particular patient, by combining both data-driven and knowledge driven approaches. The overall scope is to increase information driven care capabilities using AI/ML on data that includes, but is not limited to, Electronic Health records.

Another example is the EVE project, which aims to extend the life of electric vehicles but (semi-)autonomously creating knowledge about their usage and degradation patterns from on-board sensor data. The research questions in this area are related to novel approaches exploiting Generative Adversarial Networks within the field of Transfer Learning. For example, how to estimate battery degradation in electric vehicles based on the historical usage data. Monitoring the behavior of vehicle based on on-board signals will provide an understanding of the patterns linked to quality degradation, and those early symptoms can be used to create a predictive maintenance service. This requires aggregating available information between diesel and electric buses, combining data from multiple sources, and constructing the feature space appropriate for TL. Due to the rapid change in technology, there is not enough historical data about electric vehicles to achieve reliable accuracy and thus we need to find a relevant mapping of data between diesel and electromobility buses.

The third example, CAISR+ project, focuses on aware systems research and autonomous knowledge creation. By this we mean research on the design of systems that, as autonomously as possible, can construct knowledge from real life data created through the interaction between a system and its environment. Such systems should be able to handle events that are unknown at the time of design. One research question addresses machine activity recognition and representation learning using streaming data. The same type of machine will not be used in exactly the same way in two locations (i.e. a high level of intraclass variability), there is an expected high inter-class similarity (some operations look very similar), there is a high amount of uninteresting data (e.g. “other” is a very common activity), and there is high class imbalance. Another research question concerns survivability analysis for complex machines with different components. The core challenge in this area is censoring, i.e., incomplete information about failures. We will address it using proxy events and using transfer learning.

All these research questions pose challenges that go beyond current state-of-the-art solutions in terms of information fusion from diverse data sources, identification of relevant factors, interpretability of data mining results, causal relation discovery and augmenting machine learning with expert knowledge.

AI and ML is an important part of our education. The recruited person will have an opportunity to advance Bachelor and Master level courses such as Artificial Intelligence, Learning Systems, Data Mining, Applied Data Mining, and Deep Learning. The person will also be involved in the Graduate professional development program (second-cycle courses targeted at the business sector). Finally, the recruited person is expected to participate in supervision of thesis projects for bachelor and master level students, as well as co-supervise PhD students.

Principal duties
The duties will be:

• To undertake data mining and machine learning research in one or several of the application domains where the university conducts research
• To contribute to academic publications and conference papers (where appropriate leading on these)
• To contribute to report writing

In Sweden the position of postdoctoral researcher is a qualifying appointment, which is intended to enable the employee to develop their independence as a researcher and to obtain merits that may develop their competence for another post with higher eligibility requirements. 

Qualification
A postdoc position requires that the doctoral degree was awarded within three years of the application deadline. The applicant must hold a doctoral degree in Artificial Intelligence/Data Mining/Machine Learning/Information Technology or related fields. The applicant needs to demonstrate a strong research profile in the fields related to topics of interest for CAISR research environment, including recent activities with high impact. The scientific production is expected to be published in high-quality, peer-reviewed research journals and conferences. Documented experience from innovation, research and development in an industrial environment is also a strong merit. The applicant should share the value that diversity and equality among researchers and teachers brings higher quality to research and education.

For appointment as a postdoc, the following assessment criteria will be applied:

• Ability to conduct research of high international quality in artificial intelligence, specifically data mining and machine learning
• Documented experience from research in collaboration with industrial partners and/or interdisciplinary teams
• Ability to conduct high-quality teaching and to develop courses at different levels
• Experience in supervision of master / PhD students
• Ability to attract external funding
• Dynamism, curiosity, independence, creativity and good teamwork
• Willingness to address opportunities and challenges within AI, machine learning and data mining

Salary
Salary is to be settled by negotiation. The application should include a statement of the salary level required by the candidate.

Application
Applications should be sent via Halmstad University's recruitment system Varbi (see link on this page).

The application package shall consist of:
1) a cover letter stating the purpose of the application and a brief statement of why you believe that your goals are well-matched with the goals of this position, together with a description of future research plans

2) a CV that includes at least
- a list of previous degrees, with dates and institutions
- a complete list of publications with 2-3 most relevant ones for this position marked
- a description of previous research and other work experience and links to online copies of the most important publications

3) contact information for at least three references.

For further information, please contact Stefan Byttner(Stefan.Byttner@hh.se) or head of school Magnus Clarin (Magnus.Clarin@hh.se).

General Information
We value the qualities that gender balance and diversity bring to our organization. We therefore welcome applicants with different backgrounds, gender, functionality and, not least, life experience.

Read more about Halmstad University at http://hh.se/english/discover/discoverhalmstaduniversity.9285.html