Lars Lundberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lars Lundberg has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Håkan Grahn
Blekinge Institute of Technology
8 shared publications - Håkan Lennerstad
Blekinge Institute of Technology
4 shared publications - Julia Sidorova
Bioinformatics Platform, Biomedical Research Networking Centre in Hepatic and Digestive Disease (CIBEREHD), 28029 Madrid, Spain
4 shared publications - Emiliano Casalicchio
Department of Computer Science, Blekinge Institute of Technology, Karlskrona, Sweden
3 shared publications Sogand Shirinbab
Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden
3 shared publicationsL. Skold
Telenor
2 shared publications
Latest Publications
- Open Access
Bibliometric Mining of Research Trends in Machine Learning
We present a method, including tool support, for bibliometric mining of trends in large and dynamic research areas. The method is applied to the machine learning research area for the years 2013 to 2022. A total number of 398,782 documents from Scopus were analyzed. A taxonomy containing 26 research directions within machine learning was defined by four experts with the help of a Python program and existing taxonomies. The trends in terms of productivity, growth rate, and citations were analyzed for the research directions in the taxonomy. Our results show that the two directions, Applications and Algorithms, are the largest, and that the direction Convolutional Neural Networks is the one that grows the fastest and has the highest average number of citations per document. It also turns out that there is a clear correlation between the growth rate and the average number of citations per document, i.e., documents in fast-growing research directions have more citations. The trends for machine learning research in four geographic regions (North America, Europe, the BRICS countries, and The Rest of the World) were also analyzed. The number of documents during the time period considered is approximately the same for all regions. BRICS has the highest growth rate, and, on average, North America has the highest number of citations per document. Using our tool and method, we expect that one could perform a similar study in some other large and dynamic research area in a relatively short time.
Open AccessBibliometric Mining of Research Trends in Machine Learning
We present a method, including tool support, for bibliometric mining of trends in large and dynamic research areas. The method is applied to the machine learning research area for the years 2013 to 2022. A total number of 398,782 documents from Scopus were analyzed. A taxonomy containing 26 research directions within machine learning was defined by four experts with the help of a Python program and existing taxonomies. The trends in terms of productivity, growth rate, and citations were analyzed for the research directions in the taxonomy. Our results show that the two directions, Applications and Algorithms, are the largest, and that the direction Convolutional Neural Networks is the one that grows the fastest and has the highest average number of citations per document. It also turns out that there is a clear correlation between the growth rate and the average number of citations per document, i.e., documents in fast-growing research directions have more citations. The trends for machine learning research in four geographic regions (North America, Europe, the BRICS countries, and The Rest of the World) were also analyzed. The number of documents during the time period considered is approximately the same for all regions. BRICS has the highest growth rate, and, on average, North America has the highest number of citations per document. Using our tool and method, we expect that one could perform a similar study in some other large and dynamic research area in a relatively short time.
- Open Access
- 1 July 2023
- Published by Springer Nature in Journal of Big Data
- Vol. 10 (1) , 1-27
Bibliometric mining of research directions and trends for big data
In this paper a program and methodology for bibliometric mining of research trends and directions is presented. The method is applied to the research area Big Data for the time period 2012 to 2022, using the Scopus database. It turns out that the 10 most important research directions in Big Data are Machine learning, Deep learning and neural networks, Internet of things, Data mining, Cloud computing, Artificial intelligence, Healthcare, Security and privacy, Review, and Manufacturing. The role of Big Data research in different fields of science and technology is also analysed. For four geographic regions (North America, European Union, China, and The Rest of the World) different activity levels in Big Data during different parts of the time period are analysed. North America was the most active region during the first part of the time period. During the last years China is the most active region. The citation scores for documents from different regions and from different research directions within Big Data are also compared. North America has the highest average citation score among the geographic regions and the research direction Review has the highest average citation score among the research directions. The program and methodology for bibliometric mining developed in this study can be used also for other large research areas. Now that the program and methodology have been developed, it is expected that one could perform a similar study in some other research area in a couple of days.
- 1 July 2023
- Published by Springer Nature in Journal of Big Data
- Vol. 10 (1) , 1-27
Open AccessBibliometric mining of research directions and trends for big data
In this paper a program and methodology for bibliometric mining of research trends and directions is presented. The method is applied to the research area Big Data for the time period 2012 to 2022, using the Scopus database. It turns out that the 10 most important research directions in Big Data are Machine learning, Deep learning and neural networks, Internet of things, Data mining, Cloud computing, Artificial intelligence, Healthcare, Security and privacy, Review, and Manufacturing. The role of Big Data research in different fields of science and technology is also analysed. For four geographic regions (North America, European Union, China, and The Rest of the World) different activity levels in Big Data during different parts of the time period are analysed. North America was the most active region during the first part of the time period. During the last years China is the most active region. The citation scores for documents from different regions and from different research directions within Big Data are also compared. North America has the highest average citation score among the geographic regions and the research direction Review has the highest average citation score among the research directions. The program and methodology for bibliometric mining developed in this study can be used also for other large research areas. Now that the program and methodology have been developed, it is expected that one could perform a similar study in some other research area in a couple of days.
- Open Access
- 31 May 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (6) , 204
Avoiding Detection by Hostile Nodes in Airborne Tactical Networks
Contemporary airborne radio networks are usually implemented using omnidirectional antennas. Unfortunately, such networks suffer from disadvantages such as easy detection by hostile aircraft and potential information leakage. In this paper, we present a novel mobile ad hoc network (MANET) routing protocol based on directional antennas and situation awareness data that utilizes adaptive multihop routing to avoid sending information in directions where hostile nodes are present. Our protocol is implemented in the OMNEST simulator and evaluated using two realistic flight scenarios involving 8 and 24 aircraft, respectively. The results show that our protocol has significantly fewer leaked packets than comparative protocols, but at a slightly higher cost in terms of longer packet lifetime.
- 31 May 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (6) , 204
Open AccessAvoiding Detection by Hostile Nodes in Airborne Tactical Networks
Contemporary airborne radio networks are usually implemented using omnidirectional antennas. Unfortunately, such networks suffer from disadvantages such as easy detection by hostile aircraft and potential information leakage. In this paper, we present a novel mobile ad hoc network (MANET) routing protocol based on directional antennas and situation awareness data that utilizes adaptive multihop routing to avoid sending information in directions where hostile nodes are present. Our protocol is implemented in the OMNEST simulator and evaluated using two realistic flight scenarios involving 8 and 24 aircraft, respectively. The results show that our protocol has significantly fewer leaked packets than comparative protocols, but at a slightly higher cost in terms of longer packet lifetime.
- Open Access
- 3 November 2022
- Published by Springer Nature in Research Square
Bibliometric Mining of Research Directions and Trends for Big Data
In this paper a program and methodology for bibliometric mining of research trends and directions is presented. The method is applied on the research area Big Data for the time period 2012 to 2021, using the Scopus database. It turns out that the 10 most important research directions in Big Data are Machine learning, Deep learning and neural networks, Internet of things, Data mining, Cloud computing, Artificial intelligence, Healthcare, Security and privacy, Review, and Manufacturing. For four geographical regions (North America, European Union, China, and The Rest of the World) we investigate different activity levels in Big Data during different parts of the time period. North America was the most active region during the first part of the time period. During the last years China is the most active region. The citation scores for documents from different regions and from different research directions within Big Data are also compared. North America has the highest average citation score among the geographical regions and the research direction Review has the highest average citation score among the research directions. The program and a methodology for bibliometric mining developed in this study can be used also for other large research areas than Big Data. Now that the program and methodology have been developed, one could probably perform a similar study in some other research area in a couple of days.
- 3 November 2022
- Published by Springer Nature in Research Square
Open AccessBibliometric Mining of Research Directions and Trends for Big Data
In this paper a program and methodology for bibliometric mining of research trends and directions is presented. The method is applied on the research area Big Data for the time period 2012 to 2021, using the Scopus database. It turns out that the 10 most important research directions in Big Data are Machine learning, Deep learning and neural networks, Internet of things, Data mining, Cloud computing, Artificial intelligence, Healthcare, Security and privacy, Review, and Manufacturing. For four geographical regions (North America, European Union, China, and The Rest of the World) we investigate different activity levels in Big Data during different parts of the time period. North America was the most active region during the first part of the time period. During the last years China is the most active region. The citation scores for documents from different regions and from different research directions within Big Data are also compared. North America has the highest average citation score among the geographical regions and the research direction Review has the highest average citation score among the research directions. The program and a methodology for bibliometric mining developed in this study can be used also for other large research areas than Big Data. Now that the program and methodology have been developed, one could probably perform a similar study in some other research area in a couple of days.
- Open Access
- 9 August 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (8) , 280
Research Trends, Enabling Technologies and Application Areas for Big Data
The availability of large amounts of data in combination with Big Data analytics has transformed many application domains. In this paper, we provide insights into how the area has developed in the last decade. First, we identify seven major application areas and six groups of important enabling technologies for Big Data applications and systems. Then, using bibliometrics and an extensive literature review of more than 80 papers, we identify the most important research trends in these areas. In addition, our bibliometric analysis also includes trends in different geographical regions. Our results indicate that manufacturing and agriculture or forestry are the two application areas with the fastest growth. Furthermore, our bibliometric study shows that deep learning and edge or fog computing are the enabling technologies increasing the most. We believe that the data presented in this paper provide a good overview of the current research trends in Big Data and that this kind of information is very useful when setting strategic agendas for Big Data research.
- 9 August 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (8) , 280
Open AccessResearch Trends, Enabling Technologies and Application Areas for Big Data
The availability of large amounts of data in combination with Big Data analytics has transformed many application domains. In this paper, we provide insights into how the area has developed in the last decade. First, we identify seven major application areas and six groups of important enabling technologies for Big Data applications and systems. Then, using bibliometrics and an extensive literature review of more than 80 papers, we identify the most important research trends in these areas. In addition, our bibliometric analysis also includes trends in different geographical regions. Our results indicate that manufacturing and agriculture or forestry are the two application areas with the fastest growth. Furthermore, our bibliometric study shows that deep learning and edge or fog computing are the enabling technologies increasing the most. We believe that the data presented in this paper provide a good overview of the current research trends in Big Data and that this kind of information is very useful when setting strategic agendas for Big Data research.
- Open Access
- 23 May 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (2) , 597-610
Clustering-based adaptive data augmentation for class-imbalance in machine learning (CADA): additive manufacturing use case
Large amount of data are generated from in-situ monitoring of additive manufacturing (AM) processes which is later used in prediction modelling for defect classification to speed up quality inspection of products. A high volume of this process data is defect-free (majority class) and a lower volume of this data has defects (minority class) which result in the class-imbalance issue. Using imbalanced datasets, classifiers often provide sub-optimal classification results, i.e. better performance on the majority class than the minority class. However, it is important for process engineers that models classify defects more accurately than the class with no defects since this is crucial for quality inspection. Hence, we address the class-imbalance issue in manufacturing process data to support in-situ quality control of additive manufactured components. For this, we propose cluster-based adaptive data augmentation (CADA) for oversampling to address the class-imbalance problem. Quantitative experiments are conducted to evaluate the performance of the proposed method and to compare with other selected oversampling methods using AM datasets from an aerospace industry and a publicly available casting manufacturing dataset. The results show that CADA outperformed random oversampling and the SMOTE method and is similar to random data augmentation and cluster-based oversampling. Furthermore, the results of the statistical significance test show that there is a significant difference between the studied methods. As such, the CADA method can be considered as an alternative method for oversampling to improve the performance of models on the minority class.
- 23 May 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (2) , 597-610
Open AccessClustering-based adaptive data augmentation for class-imbalance in machine learning (CADA): additive manufacturing use case
Large amount of data are generated from in-situ monitoring of additive manufacturing (AM) processes which is later used in prediction modelling for defect classification to speed up quality inspection of products. A high volume of this process data is defect-free (majority class) and a lower volume of this data has defects (minority class) which result in the class-imbalance issue. Using imbalanced datasets, classifiers often provide sub-optimal classification results, i.e. better performance on the majority class than the minority class. However, it is important for process engineers that models classify defects more accurately than the class with no defects since this is crucial for quality inspection. Hence, we address the class-imbalance issue in manufacturing process data to support in-situ quality control of additive manufactured components. For this, we propose cluster-based adaptive data augmentation (CADA) for oversampling to address the class-imbalance problem. Quantitative experiments are conducted to evaluate the performance of the proposed method and to compare with other selected oversampling methods using AM datasets from an aerospace industry and a publicly available casting manufacturing dataset. The results show that CADA outperformed random oversampling and the SMOTE method and is similar to random data augmentation and cluster-based oversampling. Furthermore, the results of the statistical significance test show that there is a significant difference between the studied methods. As such, the CADA method can be considered as an alternative method for oversampling to improve the performance of models on the minority class.
- Open Access
Smart and Adaptive Architecture for a Dedicated Internet of Things Network Comprised of Diverse Entities: A Proposal and Evaluation
Advances in 5G and the Internet of Things (IoT) have to cater to the diverse and varying needs of different stakeholders, devices, sensors, applications, networks, and access technologies that come together for a dedicated IoT network for a synergistic purpose. Therefore, there is a need for a solution that can assimilate the various requirements and policies to dynamically and intelligently orchestrate them in the dedicated IoT network. Thus we identify and describe a representative industry-relevant use case for such a smart and adaptive environment through interviews with experts from a leading telecommunication vendor. We further propose and evaluate candidate architectures to achieve dynamic and intelligent orchestration in such a smart environment using a systematic approach for architecture design and by engaging six senior domain and IoT experts. The candidate architecture with an adaptive and intelligent element (“Smart AAA agent”) was found superior for modifiability, scalability, and performance in the assessments. This architecture also explores the enhanced role of authentication, authorization, and accounting (AAA) and makes the base for complete orchestration. The results indicate that the proposed architecture can meet the requirements for a dedicated IoT network, which may be used in further research or as a reference for industry solutions.
Open AccessSmart and Adaptive Architecture for a Dedicated Internet of Things Network Comprised of Diverse Entities: A Proposal and Evaluation
Advances in 5G and the Internet of Things (IoT) have to cater to the diverse and varying needs of different stakeholders, devices, sensors, applications, networks, and access technologies that come together for a dedicated IoT network for a synergistic purpose. Therefore, there is a need for a solution that can assimilate the various requirements and policies to dynamically and intelligently orchestrate them in the dedicated IoT network. Thus we identify and describe a representative industry-relevant use case for such a smart and adaptive environment through interviews with experts from a leading telecommunication vendor. We further propose and evaluate candidate architectures to achieve dynamic and intelligent orchestration in such a smart environment using a systematic approach for architecture design and by engaging six senior domain and IoT experts. The candidate architecture with an adaptive and intelligent element (“Smart AAA agent”) was found superior for modifiability, scalability, and performance in the assessments. This architecture also explores the enhanced role of authentication, authorization, and accounting (AAA) and makes the base for complete orchestration. The results indicate that the proposed architecture can meet the requirements for a dedicated IoT network, which may be used in further research or as a reference for industry solutions.
- 27 May 2021
- Published by Elsevier in Journal of Systems and Software
- Vol. 180, 111013
Understanding the perceived relevance of capability measures: A survey of Agile Software Development practitioners
- 27 May 2021
- Published by Elsevier in Journal of Systems and Software
- Vol. 180, 111013
Understanding the perceived relevance of capability measures: A survey of Agile Software Development practitioners
- Open Access
- 11 December 2020
- Published by MDPI AG in Algorithms
- Vol. 13 (12) , 332
An Evaluation Framework and Algorithms for Train Rescheduling
In railway traffic systems, whenever disturbances occur, it is important to effectively reschedule trains while optimizing the goals of various stakeholders. Algorithms can provide significant benefits to support the traffic controllers in train rescheduling, if well integrated into the overall traffic management process. In the railway research literature, many algorithms are proposed to tackle different versions of the train rescheduling problem. However, limited research has been performed to assess the capabilities and performance of alternative approaches, with the purpose of identifying their main strengths and weaknesses. Evaluation of train rescheduling algorithms enables practitioners and decision support systems to select a suitable algorithm based on the properties of the type of disturbance scenario in focus. It also guides researchers and algorithm designers in improving the algorithms. In this paper, we (1) propose an evaluation framework for train rescheduling algorithms, (2) present two train rescheduling algorithms: a heuristic and a MILP-based exact algorithm, and (3) conduct an experiment to compare the two multi-objective algorithms using the proposed framework (a proof-of-concept). It is found that the heuristic algorithm is suitable for solving simpler disturbance scenarios since it is quick in producing decent solutions. For complex disturbances wherein multiple trains experience a primary delay due to an infrastructure failure, the exact algorithm is found to be more appropriate.
- 11 December 2020
- Published by MDPI AG in Algorithms
- Vol. 13 (12) , 332
Open AccessAn Evaluation Framework and Algorithms for Train Rescheduling
In railway traffic systems, whenever disturbances occur, it is important to effectively reschedule trains while optimizing the goals of various stakeholders. Algorithms can provide significant benefits to support the traffic controllers in train rescheduling, if well integrated into the overall traffic management process. In the railway research literature, many algorithms are proposed to tackle different versions of the train rescheduling problem. However, limited research has been performed to assess the capabilities and performance of alternative approaches, with the purpose of identifying their main strengths and weaknesses. Evaluation of train rescheduling algorithms enables practitioners and decision support systems to select a suitable algorithm based on the properties of the type of disturbance scenario in focus. It also guides researchers and algorithm designers in improving the algorithms. In this paper, we (1) propose an evaluation framework for train rescheduling algorithms, (2) present two train rescheduling algorithms: a heuristic and a MILP-based exact algorithm, and (3) conduct an experiment to compare the two multi-objective algorithms using the proposed framework (a proof-of-concept). It is found that the heuristic algorithm is suitable for solving simpler disturbance scenarios since it is quick in producing decent solutions. For complex disturbances wherein multiple trains experience a primary delay due to an infrastructure failure, the exact algorithm is found to be more appropriate.
- Open Access
- 13 February 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (17)
Performance evaluation of containers and virtual machines when running Cassandra workload concurrently
Summary: NoSQL distributed databases are often used as Big Data platforms. To provide efficient resource sharing and cost effectiveness, such distributed databases typically run concurrently on a virtualized infrastructure that could be implemented using hypervisor‐based virtualization or container‐based virtualization. Hypervisor‐based virtualization is a mature technology but imposes overhead on CPU, networking, and disk. Recently, by sharing the operating system resources and simplifying the deployment of applications, container‐based virtualization is getting more popular. This article presents a performance comparison between multiple instances of VMware VMs and Docker containers running concurrently. Our workload models a real‐world Big Data Apache Cassandra application from Ericsson. As a baseline, we evaluated the performance of Cassandra when running on the nonvirtualized physical infrastructure. Our study shows that Docker has lower overhead compared with VMware; the performance on the container‐based infrastructure was as good as on the nonvirtualized. Our performance evaluations also show that running multiple instances of a Cassandra database concurrently affected the performance of read and write operations differently; for both VMware and Docker, the maximum number of read operations was reduced when we ran several instances concurrently, whereas the maximum number of write operations increased when we ran instances concurrently.
- 13 February 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (17)
Open AccessPerformance evaluation of containers and virtual machines when running Cassandra workload concurrently
Summary: NoSQL distributed databases are often used as Big Data platforms. To provide efficient resource sharing and cost effectiveness, such distributed databases typically run concurrently on a virtualized infrastructure that could be implemented using hypervisor‐based virtualization or container‐based virtualization. Hypervisor‐based virtualization is a mature technology but imposes overhead on CPU, networking, and disk. Recently, by sharing the operating system resources and simplifying the deployment of applications, container‐based virtualization is getting more popular. This article presents a performance comparison between multiple instances of VMware VMs and Docker containers running concurrently. Our workload models a real‐world Big Data Apache Cassandra application from Ericsson. As a baseline, we evaluated the performance of Cassandra when running on the nonvirtualized physical infrastructure. Our study shows that Docker has lower overhead compared with VMware; the performance on the container‐based infrastructure was as good as on the nonvirtualized. Our performance evaluations also show that running multiple instances of a Cassandra database concurrently affected the performance of read and write operations differently; for both VMware and Docker, the maximum number of read operations was reduced when we ran several instances concurrently, whereas the maximum number of write operations increased when we ran instances concurrently.