Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 51) Show all publications
Arvidsson, V., Al-Mashahedi, A. & Boldt, M. (2023). Evaluation of Defense Methods Against the One-Pixel Attack on Deep Neural Networks. In: Håkan Grahn, Anton Borg and Martin Boldt (Ed.), 35th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2023: . Paper presented at The 35th Swedish Artificial Intelligence Society (SAIS'23) annual workshop, Karlskrona, 12-13 June 2023 (pp. 49-57). Linköping University Electronic Press
Open this publication in new window or tab >>Evaluation of Defense Methods Against the One-Pixel Attack on Deep Neural Networks
2023 (English)In: 35th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2023 / [ed] Håkan Grahn, Anton Borg and Martin Boldt, Linköping University Electronic Press, 2023, p. 49-57Conference paper, Published paper (Refereed)
Abstract [en]

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase is not a workable defense against the one-pixel attack. ©2023, Copyright held by the authors   

Place, publisher, year, edition, pages
Linköping University Electronic Press, 2023
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-25418 (URN)10.3384/ecp199005 (DOI)9789180752749 (ISBN)
Conference
The 35th Swedish Artificial Intelligence Society (SAIS'23) annual workshop, Karlskrona, 12-13 June 2023
Available from: 2023-09-27 Created: 2023-09-27 Last updated: 2023-09-27Bibliographically approved
Ahlstrand, J., Boldt, M., Borg, A. & Grahn, H. (2023). Preliminary Results on the use of Artificial Intelligence for Managing Customer Life Cycles. In: Håkan Grahn, Anton Borg and Martin Boldt (Ed.), 35th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2023: . Paper presented at The 35th Swedish Artificial Intelligence Society (SAIS'23) annual workshop, Karlskrona, 12-13 June, 2023 (pp. 68-76). Linköping University Electronic Press
Open this publication in new window or tab >>Preliminary Results on the use of Artificial Intelligence for Managing Customer Life Cycles
2023 (English)In: 35th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2023 / [ed] Håkan Grahn, Anton Borg and Martin Boldt, Linköping University Electronic Press, 2023, p. 68-76Conference paper, Published paper (Refereed)
Abstract [en]

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI.

Place, publisher, year, edition, pages
Linköping University Electronic Press, 2023
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 199
Keywords
artificial intelligence, customer life cycle, machine learning, policy evaluation
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-25419 (URN)10.3384/ecp199007 (DOI)9789180752749 (ISBN)
Conference
The 35th Swedish Artificial Intelligence Society (SAIS'23) annual workshop, Karlskrona, 12-13 June, 2023
Note

This work was funded by Telenor Sverige AB.

Available from: 2023-09-27 Created: 2023-09-27 Last updated: 2023-09-27Bibliographically approved
Boldt, M. (2023). Utökad samverkan bortom våra traditionella studentprojekt. Karlskrona: Blekinge Tekniska Högskola
Open this publication in new window or tab >>Utökad samverkan bortom våra traditionella studentprojekt
2023 (Swedish)Report (Other (popular science, discussion, etc.))
Abstract [sv]

Denna presentation handlar om ett samverkansinitiativ för studenterna på Civilingenjörsprogrammet i AI och Maskininlärning tillsammans med regionala aktörer inom privat och offentlig sektor. Syftet är att genom samverkan mellan våra studenter och företag/myndigheter i Blekinge nå en rad synergieffekter för såväl studenterna som BTH och de medverkande regionala aktörerna. Nyckeln till framgång är få studenter och företag-/myndigheter att diskutera konkreta AI-case med varandra.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Tekniska Högskola, 2023. p. 1
Series
Blekinge Tekniska Högskola Best practice ; 42
Keywords
samverkan, studentprojekt, AI, civilingenjör
National Category
Didactics Learning Pedagogy Pedagogical Work
Identifiers
urn:nbn:se:bth-25661 (URN)
Available from: 2023-11-29 Created: 2023-11-29 Last updated: 2023-12-04Bibliographically approved
Boldt, M., Ickin, S., Borg, A., Kulyk, V. & Gustafsson, J. (2021). Alarm prediction in cellular base stations using data-driven methods. IEEE Transactions on Network and Service Management, 18(2), 1925-1933
Open this publication in new window or tab >>Alarm prediction in cellular base stations using data-driven methods
Show others...
2021 (English)In: IEEE Transactions on Network and Service Management, ISSN 1932-4537, E-ISSN 1932-4537, Vol. 18, no 2, p. 1925-1933Article in journal (Refereed) Published
Abstract [en]

The importance of cellular networks continuously increases as we assume ubiquitous connectivity in our daily lives. As a result, the underlying core telecom systems have very high reliability and availability requirements, that are sometimes hard to meet. This study presents a proactive approach that could aid satisfying these high requirements on reliability and availability by predicting future base station alarms. A data set containing 231 internal performance measures from cellular (4G) base stations is correlated with a data set containing base station alarms. Next, two experiments are used to investigate (i) the alarm prediction performance of six machine learning models, and (ii) how different predict-ahead times (ranging from 10 min to 48 hours) affect the predictive performance. A 10-fold cross validation evaluation approach and statistical analysis suggested that the Random Forest models showed best performance. Further, the results indicate the feasibility of predicting severe alarms one hour in advance with a precision of 0.812 (±0.022, 95 % CI), recall of 0.619 (±0.027) and F1-score of 0.702 (±0.022). A model interpretation package, ELI5, was used to identify the most influential features in order to gain model insight. Overall, the results are promising and indicate the potential of an early-warning system that enables a proactive means for achieving high reliability and availability requirements. IEEE

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2021
Keywords
Alarm prediction, Base stations, base stations., Cellular networks, Data models, machine learning, Machine learning algorithms, Prediction algorithms, Predictive models, telecom, Telecommunications
National Category
Media and Communication Technology Communication Systems
Identifiers
urn:nbn:se:bth-21020 (URN)10.1109/TNSM.2021.3052093 (DOI)000660636700057 ()2-s2.0-85099732813 (Scopus ID)
Available from: 2021-02-05 Created: 2021-02-05 Last updated: 2021-07-08Bibliographically approved
Lewenhagen, K., Boldt, M., Borg, A., Gerell, M. & Dahlen, J. (2021). An Interdisciplinary Web-based Framework for Data-driven Placement Analysis of CCTV Cameras. In: Proceedings of the 2021 Swedish Workshop on Data Science, SweDS 2021: . Paper presented at 9th Swedish Workshop on Data Science, SweDS 2021, Virtual, Vaxjo, 2 December 2021 through 3 December 2021. Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>An Interdisciplinary Web-based Framework for Data-driven Placement Analysis of CCTV Cameras
Show others...
2021 (English)In: Proceedings of the 2021 Swedish Workshop on Data Science, SweDS 2021, Institute of Electrical and Electronics Engineers Inc. , 2021Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes work in progress of an interdisciplinary research project that focuses on the placement and analysis of public close-circuit television (CCTV) cameras using data-driven analysis of crime data. A novel web-based prototype that acts as a framework for the camera placement analysis with regards to historical crime occurrence is presented. The web-based prototype enables various analyses involving public CCTV cameras e.g., to determine suitable locations for both stationary CCTV cameras as well as temporary cameras that are moved around after a few months to address crime seasonality. The framework also opens up for other analyses, e.g. automatically highlighting crimes that are carried out closed by at least one camera. The research also investigates to what extent it is possible to generate estimates on the amount of detail captured by a camera given the distance to the crime light conditions. The research project includes interdisciplinary competences from various areas such as criminology, computer and data science as well as the Swedish Police. © 2021 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2021
Keywords
CCTV camera placement, Data-driven placement analysis, Intelligent models, Web-based prototype, Video cameras, Websites, Camera placement, Close-circuit television camera placement, Crime data, Data driven, Data-driven analysis, Data-driven placement analyse, Seasonality, Web-based framework, Crime
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:bth-22607 (URN)10.1109/SweDS53855.2021.9637719 (DOI)000833296400002 ()2-s2.0-85123850535 (Scopus ID)9781665418300 (ISBN)
Conference
9th Swedish Workshop on Data Science, SweDS 2021, Virtual, Vaxjo, 2 December 2021 through 3 December 2021
Available from: 2022-02-11 Created: 2022-02-11 Last updated: 2022-08-12Bibliographically approved
Borg, A., Boldt, M., Rosander, O. & Ahlstrand, J. (2021). E-mail classification with machine learning and word embeddings for improved customer support. Neural Computing & Applications, 33(6), 1881-1902
Open this publication in new window or tab >>E-mail classification with machine learning and word embeddings for improved customer support
2021 (English)In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 33, no 6, p. 1881-1902Article in journal (Refereed) Published
Abstract [en]

Classifying e-mails into distinct labels can have a great impact on customer support. By using machine learning to label e-mails, the system can set up queues containing e-mails of a specific category. This enables support personnel to handle request quicker and more easily by selecting a queue that match their expertise. This study aims to improve a manually defined rule-based algorithm, currently implemented at a large telecom company, by using machine learning. The proposed model should have higher F1-score and classification rate. Integrating or migrating from a manually defined rule-based model to a machine learning model should also reduce the administrative and maintenance work. It should also make the model more flexible. By using the frameworks, TensorFlow, Scikit-learn and Gensim, the authors conduct a number of experiments to test the performance of several common machine learning algorithms, text-representations, word embeddings to investigate how they work together. A long short-term memory network showed best classification performance with an F1-score of 0.91. The authors conclude that long short-term memory networks outperform other non-sequential models such as support vector machines and AdaBoost when predicting labels for e-mails. Further, the study also presents a Web-based interface that were implemented around the LSTM network, which can classify e-mails into 33 different labels. © 2020, The Author(s).

Place, publisher, year, edition, pages
Springer, 2021
Keywords
E-mail classification, Long short-term memory, Machine learning, Natural language processing, Adaptive boosting, Brain, Electronic mail, Embeddings, Learning systems, Multimedia systems, Support vector machines, Classification performance, Classification rates, Email classification, Machine learning models, Rule based algorithms, Rule-based models, Text representation, Web-based interface
National Category
Language Technology (Computational Linguistics) Computer Sciences
Identifiers
urn:nbn:se:bth-20122 (URN)10.1007/s00521-020-05058-4 (DOI)000541326700002 ()2-s2.0-85086707161 (Scopus ID)
Note

Open access

Available from: 2020-07-06 Created: 2020-07-06 Last updated: 2022-05-04Bibliographically approved
Borg, A., Ahlstrand, J. & Boldt, M. (2021). Improving Corporate Support by Predicting Customer e-Mail Response Time: Experimental Evaluation and a Practical Use Case. In: Filipe J., Śmiałek M., Brodsky A., Hammoudi S. (Ed.), Enterprise Information Systems: . Paper presented at 22nd International Conference on Enterprise Information Systems, ICEIS 2020, Virtual, Online, 5 May through 7 May (pp. 100-121). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>Improving Corporate Support by Predicting Customer e-Mail Response Time: Experimental Evaluation and a Practical Use Case
2021 (English)In: Enterprise Information Systems / [ed] Filipe J., Śmiałek M., Brodsky A., Hammoudi S., Springer Science and Business Media Deutschland GmbH , 2021, p. 100-121Conference paper, Published paper (Refereed)
Abstract [en]

Customer satisfaction is an important aspect for any corporations customer support process. One important factor keeping the time customers’ wait for a reply at acceptable levels. By utilizing learning models based on the Random Forest Algorithm, the extent to which it is possible to predict e-Mail time-to-respond is investigated. This is investigated both for customers, but also for customer support agents. The former focusing on how long until customers reply, and the latter focusing on how long until a customer receives an answer. The models are trained on a data set consisting of 51, 682 customer support e-Mails. The e-Mails covers various topics from a large telecom operator. The models are able to predict the time-to-respond for customer support agents with an AUC of 0.90, and for customers with an AUC of 0.85. These results indicate that it is possible to predict the TTR for both groups. The approach were also implemented in an initial trial in a live environment. How the predictions can be applied to improve communication efficiency, e.g. by anticipating the staff needs in customer support, is discussed in more detail in the paper. Further, insights gained from an initial implementation are provided. © 2021, Springer Nature Switzerland AG.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2021
Series
Lecture Notes in Business Information Processing, ISSN 1865-1348, E-ISSN 1865-1356 ; 417
Keywords
Decision support, e-Mail time-to-respond, machine learning, Prediction, Random forest, Decision trees, Electronic mail, Forecasting, Information systems, Information use, Sales, Communication efficiency, Customer support, Customer support process, Experimental evaluation, Learning models, Practical use, Random forest algorithm, Telecom operators, Customer satisfaction
National Category
Computer Sciences Business Administration
Identifiers
urn:nbn:se:bth-22342 (URN)10.1007/978-3-030-75418-1_6 (DOI)2-s2.0-85106400443 (Scopus ID)9783030754174 (ISBN)
Conference
22nd International Conference on Enterprise Information Systems, ICEIS 2020, Virtual, Online, 5 May through 7 May
Funder
Knowledge Foundation, 20140032
Available from: 2021-11-11 Created: 2021-11-11 Last updated: 2022-12-02Bibliographically approved
Boldt, M., Borg, A., Ickin, S. & Gustafsson, J. (2020). Anomaly detection of event sequences using multiple temporal resolutions and Markov chains. Knowledge and Information Systems, 62, 669-686
Open this publication in new window or tab >>Anomaly detection of event sequences using multiple temporal resolutions and Markov chains
2020 (English)In: Knowledge and Information Systems, ISSN 0219-1377, E-ISSN 0219-3116, Vol. 62, p. 669-686Article in journal (Refereed) Published
Abstract [en]

Streaming data services, such as video-on-demand, are getting increasingly more popular, and they are expected to account for more than 80% of all Internet traffic in 2020. In this context, it is important for streaming service providers to detect deviations in service requests due to issues or changing end-user behaviors in order to ensure that end-users experience high quality in the provided service. Therefore, in this study we investigate to what extent sequence-based Markov models can be used for anomaly detection by means of the end-users’ control sequences in the video streams, i.e., event sequences such as play, pause, resume and stop. This anomaly detection approach is further investigated over three different temporal resolutions in the data, more specifically: 1 h, 1 day and 3 days. The proposed anomaly detection approach supports anomaly detection in ongoing streaming sessions as it recalculates the probability for a specific session to be anomalous for each new streaming control event that is received. Two experiments are used for measuring the potential of the approach, which gives promising results in terms of precision, recall, F 1 -score and Jaccard index when compared to k-means clustering of the sessions. © 2019, The Author(s).

Place, publisher, year, edition, pages
Springer London, 2020
Keywords
Anomaly detection, Event sequences, Markov Chains, Multiple temporal resolutions, Video-on-demand
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-18026 (URN)10.1007/s10115-019-01365-y (DOI)000512784400009 ()2-s2.0-85066031197 (Scopus ID)
Note

open access

Available from: 2019-06-14 Created: 2019-06-14 Last updated: 2021-10-08Bibliographically approved
Moraes, A. L., Kvist, O., Sanmartin Berglund, J., Ruiz, S. D., Boldt, M., Flodmark, C.-E. & Anderberg, P. (2020). Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach. JMIR Medical Informatics, 8(9), Article ID e18846.
Open this publication in new window or tab >>Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach
Show others...
2020 (English)In: JMIR Medical Informatics, E-ISSN 2291-9694, Vol. 8, no 9, article id e18846Article in journal (Refereed) Published
Abstract [en]

Background: Bone age assessment (BAA) is used in numerous pediatric clinical settings, as well as in legal settings when entities need an estimate of chronological age (CA) when valid documents are lacking. The latter case presents itself as critical since the law is harsher for adults and granted rights along with imputability changes drastically if the individual is a minor. Traditional BAA methods suffer from drawbacks such as exposure of minors to radiation, do not consider factors that might affect the bone age and they mostly focus on a single region. Given the critical scenarios in which BAA can affect the lives of young individuals it is important to focus on the drawbacks of the traditional methods and investigate the potential of estimating CA through BAA.

Objective: This paper aims to investigate CA estimation through BAA in young individuals of 14 to 21 years with machine learning methods, addressing the drawbacks in the research using magnetic resonance imaging (MRI), assessment of multiple ROIs and other factors that may affect the bone age.

Methods: MRI examinations of the radius, distal tibia, proximal tibia, distal femur and calcaneus were carried out on 465 males and 473 females subjects (14-21 years). Measures of weight and height were taken from the subjects and a questionnaire was given for additional information (self-assessed Tanner Scale, physical activity level, parents' origin, type of residence during upbringing). Two pediatric radiologists assessed, independently, the MRI images as to their stage of bone development (blinded to age, gender and each other). All the gathered information was used in training machine learning models for chronological age estimation and minor versus adults classification (threshold of 18 years). Different machine learning methods were investigated.

Results: The minor versus adults classification produced accuracies of 90% and 84%, for male and female subjects, respectively, with high recalls for the classification of minors. The chronological age estimation for the eight age groups (14-21 years) achieved mean absolute errors of 0.95 years and 1.24 years for male and female subjects, respectively. However, for the latter lower error occurred only for the ages of 14 and 15.

Conclusions: This paper proposed to investigate the CA estimation through BAA using machine learning methods in two ways: minor versus adults classification and CA estimation in eight age groups (14-21 years), while addressing the drawbacks in the research on BAA. The first achieved good results, however, for the second case BAA showed not precise enough for the classification.

Place, publisher, year, edition, pages
JMIR Publications Inc., 2020
Keywords
chronological age assessment, bone age, skeletal maturity, machine learning, magnetic resonance imaging, radius, distal tibia, proximal tibia, distal femur, calcaneus
National Category
Other Medical Sciences not elsewhere specified
Identifiers
urn:nbn:se:bth-19500 (URN)10.2196/18846 (DOI)000577388800006 ()2-s2.0-85097465282 (Scopus ID)
Funder
Swedish National Board of Health and Welfare
Note

open access

Available from: 2020-05-26 Created: 2020-05-26 Last updated: 2022-04-29Bibliographically approved
Borg, A., Ahlstrand, J. & Boldt, M. (2020). Predicting e-mail response time in corporate customer support. In: ICEIS 2020 - Proceedings of the 22nd International Conference on Enterprise Information Systems: . Paper presented at 22nd International Conference on Enterprise Information Systems, ICEIS 2020 Prague, Virtual, Online, 5 May 2020 through 7 May 2020 (pp. 305-314). SciTePress
Open this publication in new window or tab >>Predicting e-mail response time in corporate customer support
2020 (English)In: ICEIS 2020 - Proceedings of the 22nd International Conference on Enterprise Information Systems, SciTePress , 2020, p. 305-314Conference paper, Published paper (Refereed)
Abstract [en]

Maintaining high degree of customer satisfaction is important for any corporation, which involves the customer support process. One important factor in this work is to keep customers' wait time for a reply at levels that are acceptable to them. In this study we investigate to what extent models trained by the Random Forest learning algorithm can be used to predict e-mail time-to-respond time for both customer support agents as well as customers. The data set includes 51,682 customer support e-mails of various topics from a large telecom operator. The results indicate that it is possible to predict the time-to-respond for both customer support agents (AUC of 0.90) as well as for customers (AUC of 0.85). These results indicate that the approach can be used to improve communication efficiency, e.g. by anticipating the staff needs in customer support, but also indicating when a response is expected to take a longer time than usual. Copyright © 2020 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.

Place, publisher, year, edition, pages
SciTePress, 2020
Keywords
Decision Support, E-Mail Time-to-Respond, Machine Learning, Prediction, Random Forest, Decision trees, Electronic mail, Forecasting, Information systems, Information use, Random forests, Sales, Communication efficiency, Corporate customers, Customer support, Customer support process, Data set, Respond time, Telecom operators, Customer satisfaction
National Category
Business Administration Computer Sciences
Identifiers
urn:nbn:se:bth-20484 (URN)10.5220/0009347303050314 (DOI)000621581300034 ()2-s2.0-85090785576 (Scopus ID)9789897584237 (ISBN)
Conference
22nd International Conference on Enterprise Information Systems, ICEIS 2020 Prague, Virtual, Online, 5 May 2020 through 7 May 2020
Note

open access

Available from: 2020-09-25 Created: 2020-09-25 Last updated: 2021-07-31Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-9316-4842

Search in DiVA

Show all publications