lnu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 34) Show all publications
Chatzimparmpas, A., Martins, R. M., Jusufi, I. & Kerren, A. (2020). A survey of surveys on the use of visualization for interpreting machine learning models. Information Visualization
Open this publication in new window or tab >>A survey of surveys on the use of visualization for interpreting machine learning models
2020 (English)In: Information Visualization, ISSN 1473-8716, E-ISSN 1473-8724Article in journal (Refereed) Epub ahead of print
Abstract [en]

Research in machine learning has become very popular in recent years, with many types of models proposed to comprehend and predict patterns and trends in data originating from different domains. As these models get more and more complex, it also becomes harder for users to assess and trust their results, since their internal operations are mostly hidden in black boxes. The interpretation of machine learning models is currently a hot topic in the information visualization community, with results showing that insights from machine learning models can lead to better predictions and improve the trustworthiness of the results. Due to this, multiple (and extensive) survey articles have been published recently trying to summarize the high number of original research papers published on the topic. But there is not always a clear definition of what these surveys cover, what is the overlap between them, which types of machine learning models they deal with, or what exactly is the scenario that the readers will find in each of them. In this article, we present a metaanalysis (i.e. a ‘‘survey of surveys’’) of manually collected survey papers that refer to the visual interpretation of machine learning models, including the papers discussed in the selected surveys. The aim of our article is to serve both as a detailed summary and as a guide through this survey ecosystem by acquiring, cataloging, and presenting fundamental knowledge of the state of the art and research opportunities in the area. Our results confirm the increasing trend of interpreting machine learning with visualizations in the past years, and that visualization can assist in, for example, online training processes of deep learning models and enhancing trust into machine learning. However, the question of exactly how this assistance should take place is still considered as an open challenge of the visualization community.

Place, publisher, year, edition, pages
Sage Publications, 2020
Keywords
Survey of surveys, literature review, visualization, explainable machine learning, interpretable machine learning, taxonomy, meta-analysis
National Category
Computer Sciences
Research subject
Computer Science, Information and software visualization
Identifiers
urn:nbn:se:lnu:diva-90815 (URN)10.1177/1473871620904671 (DOI)
Available from: 2020-01-09 Created: 2020-01-09 Last updated: 2020-03-20
Jusufi, I. & Memedi, M. (2019). Interactive visualization of sensor and self-reported data of patients with Parkinson's disease. In: MIRAI AGEING Seminar, November 13-14, 2019, Stockh: . Paper presented at MIRAI AGEING Seminar, November 13-14, 2019, Stockh.
Open this publication in new window or tab >>Interactive visualization of sensor and self-reported data of patients with Parkinson's disease
2019 (English)In: MIRAI AGEING Seminar, November 13-14, 2019, Stockh, 2019Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

Advancements in telemedicine have been helpful for frequent monitoring of patients with Parkinson's disease (PD) from remote locations and assessment of their individual symptoms and treatment-related complications. These data can be useful for helping clinicians and patients to interpret symptom states and individually tailor the treatments by visualizing the physiological information collected by sensor-based systems as well as patient self-reported states. Here we present various visualization and interaction techniques to help physicians explore patient’s daily activities, which could be useful for guiding them during the decision-making process. An interface is designed to visualize symptom and medication information, collected by an Internet of Things-based system comprising of a smartphone, electronic dosing device, wrist sensor and a bed sensor.

National Category
Computer Sciences Human Computer Interaction
Research subject
Computer Science, Information and software visualization; Health and Caring Sciences, Health Informatics
Identifiers
urn:nbn:se:lnu:diva-91018 (URN)
Conference
MIRAI AGEING Seminar, November 13-14, 2019, Stockh
Projects
EMPARK
Funder
Knowledge Foundation
Available from: 2020-01-19 Created: 2020-01-19 Last updated: 2020-01-29Bibliographically approved
Jusufi, I. & Memedi, M. (2019). Interactive visualization tools for improving empowerment and treatment of Parkinson's disease patients. In: MIRAI AGEING Workshop, June 2-5, 2019, Tokyo: . Paper presented at MIRAI AGEING Workshop, June 2-5, 2019, Tokyo.
Open this publication in new window or tab >>Interactive visualization tools for improving empowerment and treatment of Parkinson's disease patients
2019 (English)In: MIRAI AGEING Workshop, June 2-5, 2019, Tokyo, 2019Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

Advancements in telemedicine have been helpful for frequent monitoring of patients with Parkinson's disease (PD) from remote locations and assessment of their individual symptoms and treatment-related complications. These data can be useful for helping clinicians and patients to interpret symptom states and individually tailor the treatments by visualizing the physiological information collected by sensor-based systems. Here we present various visualization and interaction techniques developed to help patients track their daily activities. We also present our most recent development to aid physicians in exploring this data in more detailed fashion. Both sets of interfaces are designed to visualize symptom and medication information, collected by an Internet of Things (IoT)-based system comprising of a smartphone, electronic dosing device, wrist sensor and a bed sensor.

National Category
Human Computer Interaction Computer Sciences
Research subject
Computer Science, Information and software visualization; Health and Caring Sciences, Health Informatics
Identifiers
urn:nbn:se:lnu:diva-91016 (URN)
Conference
MIRAI AGEING Workshop, June 2-5, 2019, Tokyo
Projects
EMPARK
Funder
Knowledge Foundation
Available from: 2020-01-19 Created: 2020-01-19 Last updated: 2020-01-29Bibliographically approved
Memeti, S., Pllana, S., Ferati, M., Kurti, A. & Jusufi, I. (2019). IoTutor: How Cognitive Computing Can Be Applied to Internet of Things Education. In: Leon Strous and Vinton G. Cerf (Ed.), : . Paper presented at IFIPIoT 2018 (pp. 1-16). Springer
Open this publication in new window or tab >>IoTutor: How Cognitive Computing Can Be Applied to Internet of Things Education
Show others...
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

We present IoTutor that is a cognitive computing solution for education of students in the IoT domain. We implement the IoTutor as a platform-independent web-based application that is able to interact with users via text or speech using natural language. We train the IoTutor with selected scientific publications relevant to the IoT education. To investigate users' experience with the IoTutor, we ask a group of students taking an IoT master level course at the Linnaeus University to use the IoTutor for a period of two weeks. We ask students to express their opinions with respect to the attractiveness, perspicuity, efficiency, stimulation, and novelty of the IoTutor. The evaluation results show a trend that students express an overall positive attitude towards the IoTutor with majority of the aspects rated higher than the neutral value.

Place, publisher, year, edition, pages
Springer, 2019
Series
IFIP Advances in Information and Communication Technology, ISSN 1868-4238 ; 548
Keywords
Internet of Things (IoT), education, cognitive computing, IBM Watson
National Category
Computer Systems
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:lnu:diva-80835 (URN)10.1007/978-3-030-15651-0_18 (DOI)2-s2.0-85064686693 (Scopus ID)978-3-030-15651-0 (ISBN)978-3-030-15650-3 (ISBN)
Conference
IFIPIoT 2018
Funder
Knowledge Foundation, 20150088, 20150259
Available from: 2019-02-26 Created: 2019-02-26 Last updated: 2019-08-29Bibliographically approved
Memedi, M., Tshering, G., Fogelberg, M., Jusufi, I., Kolkowska, E. & Klein, G. O. (2018). An interface for IoT: feeding back health-related data to Parkinson's disease patients. Journal of Sensor and Actuator Networks, 7(1), 1-16, Article ID 14.
Open this publication in new window or tab >>An interface for IoT: feeding back health-related data to Parkinson's disease patients
Show others...
2018 (English)In: Journal of Sensor and Actuator Networks, E-ISSN 2224-2708, Vol. 7, no 1, p. 1-16, article id 14Article in journal (Refereed) Published
Abstract [en]

This paper presents a user-centered design (UCD) process of an interface for Parkinson’s disease (PD) patients for helping them to better manage their symptoms. The interface is designed to visualize symptom and medication information, collected by an Internet of Things (IoT)-based system, which will consist of a smartphone, electronic dosing device, wrist sensor and a bed sensor. In our work, the focus is on measuring data related to some of the main health-related quality of life aspects such as motor function, sleep, medication compliance, meal intake timing in relation to medication intake, and physical exercise. A mock-up demonstrator for the interface was developed using UCD methodology in collaboration with PD patients. The research work was performed as an iterative design and evaluation process based on interviews and observations with 11 PD patients. Additional usability evaluations were conducted with three information visualization experts. Contributions include a list of requirements for the interface, results evaluating the performance of the patients when using the demonstrator during task-based evaluation sessions as well as opinions of the experts. The list of requirements included ability of the patients to track an ideal day, so they could repeat certain activities in the future as well as determine how the scores are related to each other. The patients found the visualizations as clear and easy to understand and could successfully perform the tasks. The evaluation with experts showed that the visualizations are in line with the current standards and guidelines for the intended group of users. In conclusion, the results from this work indicate that the proposed system can be considered as a tool for assisting patients in better management of the disease by giving them insights on their own aggregated symptom and medication information. However, the actual effects of providing such feedback to patients on their health-related quality of life should be investigated in a clinical trial.

Place, publisher, year, edition, pages
MDPI, 2018
Keywords
Information visualization, User-centered design, Internet of things, Sensor technology, Parkinson’s disease, Patient empowerment, Quality of life
National Category
Human Computer Interaction
Research subject
Informatics
Identifiers
urn:nbn:se:lnu:diva-71530 (URN)10.3390/jsan7010014 (DOI)000428559500013 ()2-s2.0-85044327671 (Scopus ID)
Projects
EMPARK
Funder
Knowledge Foundation, 20160176
Available from: 2018-03-15 Created: 2018-03-15 Last updated: 2019-08-29Bibliographically approved
Gimenez, A., Gamblin, T., Jusufi, I., Bhatele, A., Schulz, M., Bremer, P.-T. & Hamann, B. (2018). MemAxes: Visualization and Analytics for Characterizing Complex Memory Performance Behaviors. IEEE Transactions on Visualization and Computer Graphics, 24(7), 2180-2193
Open this publication in new window or tab >>MemAxes: Visualization and Analytics for Characterizing Complex Memory Performance Behaviors
Show others...
2018 (English)In: IEEE Transactions on Visualization and Computer Graphics, ISSN 1077-2626, E-ISSN 1941-0506, Vol. 24, no 7, p. 2180-2193Article in journal (Refereed) Published
Abstract [en]

Memory performance is often a major bottleneck for high-performance computing (HPC) applications. Deepening memory hierarchies, complex memory management, and non-uniform access times have made memory performance behavior difficult to characterize, and users require novel, sophisticated tools to analyze and optimize this aspect of their codes. Existing tools target only specific factors of memory performance, such as hardware layout, allocations, or access instructions. However, today's tools do not suffice to characterize the complex relationships between these factors. Further, they require advanced expertise to be used effectively. We present MemAxes, a tool based on a novel approach for analytic-driven visualization of memory performance data. MemAxes uniquely allows users to analyze the different aspects related to memory performance by providing multiple visual contexts for a centralized dataset. We define mappings of sampled memory access data to new and existing visual metaphors, each of which enabling a user to perform different analysis tasks. We present methods to guide user interaction by scoring subsets of the data based on known performance problems. This scoring is used to provide visual cues and automatically extract clusters of interest. We designed MemAxes in collaboration with experts in HPC and demonstrate its effectiveness in case studies.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Performance Visualization, High-Performance Computing, Memory Visualization
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science, Computer Science; Computer Science, Information and software visualization
Identifiers
urn:nbn:se:lnu:diva-65915 (URN)10.1109/TVCG.2017.2718532 (DOI)000433321900010 ()28650817 (PubMedID)2-s2.0-85021808475 (Scopus ID)
Available from: 2017-06-28 Created: 2017-06-28 Last updated: 2019-08-29Bibliographically approved
Jusufi, I., Memedi, M. & Nyholm, D. (2018). TapVis: A Data Visualization Approach for Assessment of Alternating Tapping Performance in Patients with Parkinson's Disease. In: / J. Johansson, F. Sadlo, and T. Schreck (Ed.), EuroVis 2018 - Short Papers: . Paper presented at 20th EG/VGTC Conference on Visualization (EuroVis '18), 4-8 June 2018, Brno, Czech Republic (pp. 55-59). Eurographics - European Association for Computer Graphics
Open this publication in new window or tab >>TapVis: A Data Visualization Approach for Assessment of Alternating Tapping Performance in Patients with Parkinson's Disease
2018 (English)In: EuroVis 2018 - Short Papers / [ed] / J. Johansson, F. Sadlo, and T. Schreck, Eurographics - European Association for Computer Graphics, 2018, p. 55-59Conference paper, Published paper (Refereed)
Abstract [en]

Advancements in telemedicine have been helpful for frequent monitoring of patients with Parkinson's disease (PD) from remote locations and assessment of their individual symptoms and treatment-related complications. These data can be useful for helping clinicians to interpret symptom states and individually tailor the treatments by visualizing the physiological information collected by sensor-based systems. In this paper we present a visualization metaphor that represents symptom information of PD patients during tapping tests performed with a smartphone. The metaphor has been developed and evaluated with a clinician. It enabled the clinician to observe fine motor impairments and identify motor fluctuations regarding several movement aspects of patients that perform the tests from their homes.

Place, publisher, year, edition, pages
Eurographics - European Association for Computer Graphics, 2018
National Category
Computer Sciences Human Computer Interaction
Research subject
Computer Science, Information and software visualization; Health and Caring Sciences, Health Informatics
Identifiers
urn:nbn:se:lnu:diva-75547 (URN)10.2312/eurovisshort.20181078 (DOI)978-3-03868-060-4 (ISBN)
Conference
20th EG/VGTC Conference on Visualization (EuroVis '18), 4-8 June 2018, Brno, Czech Republic
Projects
EMPARK
Available from: 2018-06-11 Created: 2018-06-11 Last updated: 2018-09-13Bibliographically approved
Golub, K., Tyrkkö, J., Kerren, A., Jusufi, I. & Ardö, A. (2017). Automatic subject classification for improving retrieval in a Swedish repository. In: ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London: . Paper presented at ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London.
Open this publication in new window or tab >>Automatic subject classification for improving retrieval in a Swedish repository
Show others...
2017 (English)In: ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London, 2017Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

The recent adoption of the Dewey Decimal Classification (DDC) in Sweden has ignited discussions about automated subject classification especially for digital collections, which generally seem to lack subject indexing from controlled vocabularies. This is particularly problematic in the context of academic resource retrieval tasks, which require an understanding of discipline-specific terminologies and the narratives behind their internal ontologies. The currently available experimental classification software have not been adequately tested and their usefulness is unproven especially for Swedish language resources. We address these issues by investigating a unifying framework of automatic subject indexing for the DDC, including an analysis of suitable interactive visualisation features for supporting these aims. We will address the disciplinary narratives behind the DDC in selected subject areas and the preliminary results will include an analysis of the data collection and a breakdown of the methodology. Major visualisation possibilities in support of the classification process are also outlined. The project will contribute significantly to Swedish information infrastructure by improving the findability of Swedish research resources by subject searching, one of the most common yet the most challenging types of searching.

National Category
Information Studies
Research subject
Computer Science, Information and software visualization
Identifiers
urn:nbn:se:lnu:diva-67925 (URN)
Conference
ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London
Projects
DISA-DH
Available from: 2017-09-12 Created: 2017-09-12 Last updated: 2020-03-16Bibliographically approved
Jusufi, I., Milrad, M. & Legaspi, X. (2016). Interactive Exploration of Student Generated Content presented in Blogs. In: Tobias Isenberg & Filip Sadlo (Ed.), EuroVis 2016 - Posters: Eurographics - European Association for Computer Graphics. Paper presented at The 18th EG/VGTC Conference on Visualization (EuroVis '16), Groningen, The Netherlands, 6-10 June, 2016 (pp. 53-55). Eurographics - European Association for Computer Graphics
Open this publication in new window or tab >>Interactive Exploration of Student Generated Content presented in Blogs
2016 (English)In: EuroVis 2016 - Posters: Eurographics - European Association for Computer Graphics / [ed] Tobias Isenberg & Filip Sadlo, Eurographics - European Association for Computer Graphics, 2016, p. 53-55Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Nowadays blogs are regarded as tools for communication as well as an important source for spreading information in almost every subject. In recent years, school teachers have started to take advantage of this technology in order to support their educational practices. In this paper we focus on the data generated by a project involving more than 50 Swedish schools where teachers and pupils are posting content related to their astronomy class activities in their blogs with the aims of improving the teaching process. The challenge here is to find suitable methods to explore all these blogs in an interactive and discovery fashion. Our proposed solution to this challenge is to provide a visual and interactive tool for the exploration of blog corpora by teachers, pupils, project managers and parents.

Place, publisher, year, edition, pages
Eurographics - European Association for Computer Graphics, 2016
Keywords
Visualization, Text Visualization
National Category
Computer Sciences
Research subject
Computer Science, Information and software visualization; Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-54119 (URN)10.2312/eurp.20161140 (DOI)978-3-03868-015-4 (ISBN)
Conference
The 18th EG/VGTC Conference on Visualization (EuroVis '16), Groningen, The Netherlands, 6-10 June, 2016
Available from: 2016-06-22 Created: 2016-06-22 Last updated: 2018-01-10Bibliographically approved
Jusufi, I. & Kerren, A. (2016). Network Visualization for Digital Humanities: Two Case Studies of Visual Analyses for Text Analytics. In: International Symposium on Digital Humanities, Växjö 7-8 November 2016: Book of Abstracts. Paper presented at International Symposium on Digital Humanities, Växjö, Sweden, November 7-8, 2016. (pp. 39-43). Linnaeus University
Open this publication in new window or tab >>Network Visualization for Digital Humanities: Two Case Studies of Visual Analyses for Text Analytics
2016 (English)In: International Symposium on Digital Humanities, Växjö 7-8 November 2016: Book of Abstracts, Linnaeus University , 2016, p. 39-43Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Much of the data created nowadays in fields such as Digital Humanities (DH) is of relational nature, such as social or semantic networks. Researchers often decide to depict networks as node-link diagrams to make a better sense of the complex nature of data. Understanding the topology of such a network can be very important. For instance, if we show our friends as network nodes and their friendship as edges between the nodes, it becomes easy to identify groups of friends from different social settings (work friends, high school friends, etc.).

Networks usually have additional attributes attached to their elements. For instance, we can model a number of documents in a repository as nodes and use edges to describe co-authorship. Additionally, we might want to explore other aspects of such a corpus, like the keywords for each document, its genre, and various other data associated. Here, it is often desirable to get an overview about the network structure and how different data values relate to this structure. In this paper, we present two case studies for visualizations in DH with a focus on publication networks. But first, we will introduce our data sets used in these studies.

Place, publisher, year, edition, pages
Linnaeus University, 2016
Keywords
digital humanities, networks, visualization, social networks, interaction
National Category
Computer Sciences Human Computer Interaction
Research subject
Computer Science, Information and software visualization; Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-57762 (URN)
Conference
International Symposium on Digital Humanities, Växjö, Sweden, November 7-8, 2016.
Available from: 2016-11-01 Created: 2016-11-01 Last updated: 2018-01-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-6745-4398

Search in DiVA

Show all publications