Jaakko Suutala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jaakko Suutala has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Andre Noll Barreto
Barkhausen Institut
2 shared publications - Barend van Liempd
IMEC, Leuven, Belgium
2 shared publications - Carlos Heracles Moraes de Lima
Centre for Wireless Communications (CWC) University of Oulu Oulu Finland
2 shared publications - Davide Dardari
University of Bologna, Cesena, Italy
2 shared publications Didier Belot
CEA-Leti, Gif-sur-Yvette, France
2 shared publications- Elena Simona Lohan
Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 100868-100883
Chessboard Masked AutoEncoder Against Hidden Backdoor Attacks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 100868-100883
Open AccessChessboard Masked AutoEncoder Against Hidden Backdoor Attacks
- Open Access
- 28 August 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e75117
A Machine Learning Algorithm With an Oversampling Technique in Limited Data Scenarios for the Prediction of Present and Future Restorative Treatment Need: Development and Validation Study
Background: Untreated dental caries is the most common health condition worldwide. Therefore, new strategies need to be developed to reduce the manifestations of dental caries. Objective: This study aimed to develop and test a machine learning (ML) algorithm for detecting present and predicting future carious lesions in the adolescent population using a set of easy-to-collect predictive variables. In addition, this study aimed to deal with an imbalanced and small dataset using an oversampling method. Methods: This population-based study was conducted among secondary schoolchildren, aged between 13 and 17 years, from the northern parts of Finland in 2022. After meeting the inclusion criteria, a total of 218 participants were included in this study. The inclusion criteria consisted of participants having completed a web-based risk assessment questionnaire and having undergone a clinical examination at public health care services. Dental caries (International Caries Detection and Assessment System [ICDAS] scores of 4, 5, and 6; ie, ICDAS 4-6) and active initial caries (ICDAS 2+, 3+) were considered as outcomes. Several predictors, such as behavioral and dietary habits, were included. An extreme gradient boosting model was developed, tested, and assessed for its predictive performance. A 4-fold cross-validation was performed using the nested resampling technique. The random oversampling examples method and the k-nearest neighbors classifiers were used for all 4 folds. The mean (SD) performance of all the folds was computed. Results: Dental caries (ICDAS 2+,3+,4-6) were prevalent in 65.6% (143/218) of the participants. The mean area under the curve was 0.77 (SD 0.04) and the mean F1-score was 0.82 (SD 0.06) for the extreme gradient boosting model. Similarly, the mean area under the curve and mean F1-scores after oversampling were 0.74 (SD 0.05) and 0.79 (SD 0.04), respectively. The Shapley additive explanation values were calculated for all 4 folds to assess feature importance, revealing that previous dental fillings were the feature most strongly associated with the need for restorative treatment. Conclusions: On the basis of the performance metrics, the ML algorithm developed and tested in this study can be considered good. The ML algorithm could serve as a cost-effective screening tool for dental professionals to identify the risk of future restorative treatment needs. However, future studies with longitudinal cohorts and longitudinal data, along with external validation for generalizability, are needed to validate our model.
- 28 August 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e75117
Open AccessA Machine Learning Algorithm With an Oversampling Technique in Limited Data Scenarios for the Prediction of Present and Future Restorative Treatment Need: Development and Validation Study
Background: Untreated dental caries is the most common health condition worldwide. Therefore, new strategies need to be developed to reduce the manifestations of dental caries. Objective: This study aimed to develop and test a machine learning (ML) algorithm for detecting present and predicting future carious lesions in the adolescent population using a set of easy-to-collect predictive variables. In addition, this study aimed to deal with an imbalanced and small dataset using an oversampling method. Methods: This population-based study was conducted among secondary schoolchildren, aged between 13 and 17 years, from the northern parts of Finland in 2022. After meeting the inclusion criteria, a total of 218 participants were included in this study. The inclusion criteria consisted of participants having completed a web-based risk assessment questionnaire and having undergone a clinical examination at public health care services. Dental caries (International Caries Detection and Assessment System [ICDAS] scores of 4, 5, and 6; ie, ICDAS 4-6) and active initial caries (ICDAS 2+, 3+) were considered as outcomes. Several predictors, such as behavioral and dietary habits, were included. An extreme gradient boosting model was developed, tested, and assessed for its predictive performance. A 4-fold cross-validation was performed using the nested resampling technique. The random oversampling examples method and the k-nearest neighbors classifiers were used for all 4 folds. The mean (SD) performance of all the folds was computed. Results: Dental caries (ICDAS 2+,3+,4-6) were prevalent in 65.6% (143/218) of the participants. The mean area under the curve was 0.77 (SD 0.04) and the mean F1-score was 0.82 (SD 0.06) for the extreme gradient boosting model. Similarly, the mean area under the curve and mean F1-scores after oversampling were 0.74 (SD 0.05) and 0.79 (SD 0.04), respectively. The Shapley additive explanation values were calculated for all 4 folds to assess feature importance, revealing that previous dental fillings were the feature most strongly associated with the need for restorative treatment. Conclusions: On the basis of the performance metrics, the ML algorithm developed and tested in this study can be considered good. The ML algorithm could serve as a cost-effective screening tool for dental professionals to identify the risk of future restorative treatment needs. However, future studies with longitudinal cohorts and longitudinal data, along with external validation for generalizability, are needed to validate our model.
- Open Access
- 4 April 2025
- Published by JMIR Publications Inc. in JMIR Preprints
A Machine Learning Algorithm With an Oversampling Technique in Limited Data Scenarios for the Prediction of Present and Future Restorative Treatment Need: Development and Validation Study (Preprint)
BACKGROUND Untreated dental caries is the most common health condition worldwide. Therefore, new strategies need to be developed to reduce the manifestations of dental caries. OBJECTIVE This study aimed to develop and test a machine learning (ML) algorithm for detecting present and predicting future carious lesions in the adolescent population using a set of easy-to-collect predictive variables. In addition, this study aimed to deal with an imbalanced and small dataset using an oversampling method. METHODS This population-based study was conducted among secondary schoolchildren, aged between 13 and 17 years, from the northern parts of Finland in 2022. After meeting the inclusion criteria, a total of 218 participants were included in this study. The inclusion criteria consisted of participants having completed a web-based risk assessment questionnaire and having undergone a clinical examination at public health care services. Dental caries (International Caries Detection and Assessment System [ICDAS] scores of 4, 5, and 6; ie, ICDAS 4-6) and active initial caries (ICDAS 2+, 3+) were considered as outcomes. Several predictors, such as behavioral and dietary habits, were included. An extreme gradient boosting model was developed, tested, and assessed for its predictive performance. A 4-fold cross-validation was performed using the nested resampling technique. The random oversampling examples method and the k-nearest neighbors classifiers were used for all 4 folds. The mean (SD) performance of all the folds was computed. RESULTS Dental caries (ICDAS 2+,3+,4-6) were prevalent in 65.6% (143/218) of the participants. The mean area under the curve was 0.77 (SD 0.04) and the mean F1-score was 0.82 (SD 0.06) for the extreme gradient boosting model. Similarly, the mean area under the curve and mean F1-scores after oversampling were 0.74 (SD 0.05) and 0.79 (SD 0.04), respectively. The Shapley additive explanation values were calculated for all 4 folds to assess feature importance, revealing that previous dental fillings were the feature most strongly associated with the need for restorative treatment. CONCLUSIONS On the basis of the performance metrics, the ML algorithm developed and tested in this study can be considered good. The ML algorithm could serve as a cost-effective screening tool for dental professionals to identify the risk of future restorative treatment needs. However, future studies with longitudinal cohorts and longitudinal data, along with external validation for generalizability, are needed to validate our model.
- 4 April 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA Machine Learning Algorithm With an Oversampling Technique in Limited Data Scenarios for the Prediction of Present and Future Restorative Treatment Need: Development and Validation Study (Preprint)
BACKGROUND Untreated dental caries is the most common health condition worldwide. Therefore, new strategies need to be developed to reduce the manifestations of dental caries. OBJECTIVE This study aimed to develop and test a machine learning (ML) algorithm for detecting present and predicting future carious lesions in the adolescent population using a set of easy-to-collect predictive variables. In addition, this study aimed to deal with an imbalanced and small dataset using an oversampling method. METHODS This population-based study was conducted among secondary schoolchildren, aged between 13 and 17 years, from the northern parts of Finland in 2022. After meeting the inclusion criteria, a total of 218 participants were included in this study. The inclusion criteria consisted of participants having completed a web-based risk assessment questionnaire and having undergone a clinical examination at public health care services. Dental caries (International Caries Detection and Assessment System [ICDAS] scores of 4, 5, and 6; ie, ICDAS 4-6) and active initial caries (ICDAS 2+, 3+) were considered as outcomes. Several predictors, such as behavioral and dietary habits, were included. An extreme gradient boosting model was developed, tested, and assessed for its predictive performance. A 4-fold cross-validation was performed using the nested resampling technique. The random oversampling examples method and the k-nearest neighbors classifiers were used for all 4 folds. The mean (SD) performance of all the folds was computed. RESULTS Dental caries (ICDAS 2+,3+,4-6) were prevalent in 65.6% (143/218) of the participants. The mean area under the curve was 0.77 (SD 0.04) and the mean F1-score was 0.82 (SD 0.06) for the extreme gradient boosting model. Similarly, the mean area under the curve and mean F1-scores after oversampling were 0.74 (SD 0.05) and 0.79 (SD 0.04), respectively. The Shapley additive explanation values were calculated for all 4 folds to assess feature importance, revealing that previous dental fillings were the feature most strongly associated with the need for restorative treatment. CONCLUSIONS On the basis of the performance metrics, the ML algorithm developed and tested in this study can be considered good. The ML algorithm could serve as a cost-effective screening tool for dental professionals to identify the risk of future restorative treatment needs. However, future studies with longitudinal cohorts and longitudinal data, along with external validation for generalizability, are needed to validate our model.
- Open Access
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 172610-172637
Threat Modeling AI/ML With the Attack Tree
The pervasive use of AI assistant systems and machine learning-based applications in various fields and everyday life has significantly shifted. However, this shift is not without its challenges. The emergence of security threats, various attacks, and vulnerabilities in this domain has not only questioned their use but also sparked the interest of security experts and researchers, underlining the urgency and importance of this topic. However, a comprehensive and systematic research endeavor is yet to be undertaken on threat modeling based on violating basic tenets of information security on the various components of a machine learning system and evaluating their security risks. This lack of comprehensive threat modeling for each violation of a machine learning system’s confidentiality, integrity, availability, and privacy for various attacks and their risk analysis is a significant gap in the field. This article aims to bridge this gap by proposing a simple, efficient, and time-saving approach to evaluate potential attacks and their security risks by utilizing the attack tree and a risk analysis method in the Adversarial Machine Learning (AML) field. One of the most important steps in determining the overall risk of the attack is evaluating the risk attached to each node in an attack tree. A systematic approach that includes describing the system architecture and identifying its assets under various operational environment scenarios is also outlined in this paper. This approach can also offer crucial insights to security experts, aiding them in understanding and mitigating potential threats and risk analysis in AML systems. To ensure the validity and reliability of our findings, we have conducted a thorough and rigorous review of academic papers, summarizing different threats and attacks and their root cause analysis.
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 172610-172637
Open AccessThreat Modeling AI/ML With the Attack Tree
The pervasive use of AI assistant systems and machine learning-based applications in various fields and everyday life has significantly shifted. However, this shift is not without its challenges. The emergence of security threats, various attacks, and vulnerabilities in this domain has not only questioned their use but also sparked the interest of security experts and researchers, underlining the urgency and importance of this topic. However, a comprehensive and systematic research endeavor is yet to be undertaken on threat modeling based on violating basic tenets of information security on the various components of a machine learning system and evaluating their security risks. This lack of comprehensive threat modeling for each violation of a machine learning system’s confidentiality, integrity, availability, and privacy for various attacks and their risk analysis is a significant gap in the field. This article aims to bridge this gap by proposing a simple, efficient, and time-saving approach to evaluate potential attacks and their security risks by utilizing the attack tree and a risk analysis method in the Adversarial Machine Learning (AML) field. One of the most important steps in determining the overall risk of the attack is evaluating the risk attached to each node in an attack tree. A systematic approach that includes describing the system architecture and identifying its assets under various operational environment scenarios is also outlined in this paper. This approach can also offer crucial insights to security experts, aiding them in understanding and mitigating potential threats and risk analysis in AML systems. To ensure the validity and reliability of our findings, we have conducted a thorough and rigorous review of academic papers, summarizing different threats and attacks and their root cause analysis.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
AI-Assisted Decision Support for District Heating Demand Response
Digital twins as decision support platforms construct a comprehensive digital representation of large-scale systems. This depiction can be utilised with machine learning to promote value from system data. Research conducted for this paper uses district heating data as basis for decision support digital twin that helps predict demand response situations in a district heating network by using a multi-modal model pipeline. Findings of the study include that computationally generated models can represent the data accurately enough to fit a well-defined purpose, even if model degradation increases variation from the actualised values. Additionally, the study illustrates the capability to observe and manipulate the digital twin environment through an interface, enhancing its value proposition.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
AI-Assisted Decision Support for District Heating Demand Response
Digital twins as decision support platforms construct a comprehensive digital representation of large-scale systems. This depiction can be utilised with machine learning to promote value from system data. Research conducted for this paper uses district heating data as basis for decision support digital twin that helps predict demand response situations in a district heating network by using a multi-modal model pipeline. Findings of the study include that computationally generated models can represent the data accurately enough to fit a well-defined purpose, even if model degradation increases variation from the actualised values. Additionally, the study illustrates the capability to observe and manipulate the digital twin environment through an interface, enhancing its value proposition.
- Top Cited PapersOpen Access
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 26902-26925
Convergent Communication, Sensing and Localization in 6G Systems: An Overview of Technologies, Opportunities and Challenges
Herein, we focus on convergent 6G communication, localization and sensing systems by identifying key technology enablers, discussing their underlying challenges, implementation issues, and recommending potential solutions. Moreover, we discuss exciting new opportunities for integrated localization and sensing applications, which will disrupt traditional design principles and revolutionize the way we live, interact with our environment, and do business. Regarding potential enabling technologies, 6G will continue to develop towards even higher frequency ranges, wider bandwidths, and massive antenna arrays. In turn, this will enable sensing solutions with very fine range, Doppler, and angular resolutions, as well as localization to cm-level degree of accuracy. Besides, new materials, device types, and reconfigurable surfaces will allow network operators to reshape and control the electromagnetic response of the environment. At the same time, machine learning and artificial intelligence will leverage the unprecedented availability of data and computing resources to tackle the biggest and hardest problems in wireless communication systems. As a result, 6G will be truly intelligent wireless systems that will provide not only ubiquitous communication but also empower high accuracy localization and high-resolution sensing services. They will become the catalyst for this revolution by bringing about a unique new set of features and service capabilities, where localization and sensing will coexist with communication, continuously sharing the available resources in time, frequency, and space. This work concludes by highlighting foundational research challenges, as well as implications and opportunities related to privacy, security, and trust.
- 21 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 26902-26925
Top Cited PapersOpen AccessConvergent Communication, Sensing and Localization in 6G Systems: An Overview of Technologies, Opportunities and Challenges
Herein, we focus on convergent 6G communication, localization and sensing systems by identifying key technology enablers, discussing their underlying challenges, implementation issues, and recommending potential solutions. Moreover, we discuss exciting new opportunities for integrated localization and sensing applications, which will disrupt traditional design principles and revolutionize the way we live, interact with our environment, and do business. Regarding potential enabling technologies, 6G will continue to develop towards even higher frequency ranges, wider bandwidths, and massive antenna arrays. In turn, this will enable sensing solutions with very fine range, Doppler, and angular resolutions, as well as localization to cm-level degree of accuracy. Besides, new materials, device types, and reconfigurable surfaces will allow network operators to reshape and control the electromagnetic response of the environment. At the same time, machine learning and artificial intelligence will leverage the unprecedented availability of data and computing resources to tackle the biggest and hardest problems in wireless communication systems. As a result, 6G will be truly intelligent wireless systems that will provide not only ubiquitous communication but also empower high accuracy localization and high-resolution sensing services. They will become the catalyst for this revolution by bringing about a unique new set of features and service capabilities, where localization and sensing will coexist with communication, continuously sharing the available resources in time, frequency, and space. This work concludes by highlighting foundational research challenges, as well as implications and opportunities related to privacy, security, and trust.
- Open Access
6G White Paper on Localization and Sensing
This white paper explores future localization and sensing opportunities for beyond 5G wireless communication systems by identifying key technology enablers and discussing their underlying challenges, implementation issues, and identifying potential solutions. In addition, we present exciting new opportunities for localization and sensing applications, which will disrupt traditional design principles and revolutionize the way we live, interact with our environment, and do business. Following the trend initiated in the 5G NR systems, 6G will continue to develop towards even higher frequency ranges, wider bandwidths, and massive antenna arrays. In turn, this will enable sensing solutions with very fine range, Doppler and angular resolutions, as well as localization to cm-level degree of accuracy. Moreover, new materials, device types, and reconfigurable surfaces will allow network operators to reshape and control the electromagnetic response of the environment. At the same time, machine learning and artificial intelligence will leverage the unprecedented availability of data and computing resources to tackle the biggest and hardest problems in wireless communication systems. 6G will be truly intelligent wireless systems that will not only provide ubiquitous communication but also empower high accuracy localization and high-resolution sensing services. They will become the catalyst for this revolution by bringing about a unique new set of features and service capabilities, where localization and sensing will coexist with communication, continuously sharing the available resources in time, frequency and space. This white paper concludes by highlighting foundational research challenges, as well as implications and opportunities related to privacy, security, and trust. Addressing these challenges will undoubtedly require an inter-disciplinary and concerted effort from the research community.
Open Access6G White Paper on Localization and Sensing
This white paper explores future localization and sensing opportunities for beyond 5G wireless communication systems by identifying key technology enablers and discussing their underlying challenges, implementation issues, and identifying potential solutions. In addition, we present exciting new opportunities for localization and sensing applications, which will disrupt traditional design principles and revolutionize the way we live, interact with our environment, and do business. Following the trend initiated in the 5G NR systems, 6G will continue to develop towards even higher frequency ranges, wider bandwidths, and massive antenna arrays. In turn, this will enable sensing solutions with very fine range, Doppler and angular resolutions, as well as localization to cm-level degree of accuracy. Moreover, new materials, device types, and reconfigurable surfaces will allow network operators to reshape and control the electromagnetic response of the environment. At the same time, machine learning and artificial intelligence will leverage the unprecedented availability of data and computing resources to tackle the biggest and hardest problems in wireless communication systems. 6G will be truly intelligent wireless systems that will not only provide ubiquitous communication but also empower high accuracy localization and high-resolution sensing services. They will become the catalyst for this revolution by bringing about a unique new set of features and service capabilities, where localization and sensing will coexist with communication, continuously sharing the available resources in time, frequency and space. This white paper concludes by highlighting foundational research challenges, as well as implications and opportunities related to privacy, security, and trust. Addressing these challenges will undoubtedly require an inter-disciplinary and concerted effort from the research community.