ISLAB/CAISR - User contributions [en]

Adapt LoCoMotif to forklift data

2025-09-09T14:33:07Z

Kunru:

{{StudentProjectTemplate
|Summary=LoCoMotif is a novel TSMD method able to discover motifs that have different lengths (variable-length motifs), exhibit slight temporal differences (time-warped motifs), and span multiple dimensions (multivariate motifs)
|TimeFrame=Fall 2024
|Supervisor=Kunru Chen, ...
|Level=Master
|Status=Finished
}}
Try out LoCoMotif on forklift data from Toyota Material Handling Europe, and adapt it as required:
https://link.springer.com/article/10.1007/s10618-024-01032-z
https://github.com/ML-KULeuven/locomotif

Project opportunities at Toyota

2023-10-13T08:42:08Z

Kunru:

{{StudentProjectTemplate
|Summary=Each year there are several project opportunities at Toyota
|TimeFrame=Fall 2023
|Supervisor=TBD
|Level=Master
|Status=Open
}}
[https://toyota-forklifts.se/ Toyota] often offers several thesis topics for students.

Two examples can be found here:<br>
[https://toyota-forklifts.se/lediga-tjanster/2023-2564_external_master_thesis_machine_learningiot_unsupervised_driver_behaviour_classification_using_machine_learning/ Master Thesis Machine Learning/IoT: Unsupervised driver behavior classification using Machine Learning]<br>
[https://toyota-forklifts.se/lediga-tjanster/2023-2565_external_master_thesis_machine_learningiot_unsupervised_activity_recognition_using_machine_learning/ Master Thesis Machine Learning/IoT: Unsupervised activity recognition using Machine Learning]

If you find one that is interesting to you, please get in touch with the contact person mentioned there. Since Toyota manages those opportunities, they make the final decision on who is selected for any given thesis. From the University side, we will support you throughout the process, but we cannot make any guarantees or influence the selection in any way.

In addition, as with all industry-driven projects, you will also need to find a suitable supervisor here at the University. Based on the topics presented here, you should be able to identify some people with related interests; feel free to contact them directly. If you have trouble finding the right supervisor, contact Slawomir, and he will try to help you.

Generative Approach for Multivariate Signals

2022-10-05T11:34:07Z

Kunru:

{{StudentProjectTemplate
|Summary=The topic focuses on generative models (VAE) for CAN-bus data and investigating the representation learning capabilities of such techniques
|Keywords=VAE, Time-series data, Streaming data, MAR
|TimeFrame=2021 Fall - 2022 Summer
|References=https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks.pdf

https://openreview.net/pdf?id=Sy2fzU9gl

https://www.sciencedirect.com/science/article/pii/S092658051930367X

|Prerequisites=Excellent Programming Skills
Excellent knowledge in Machine Learning and Neural Networks
|Supervisor=Kunru Chen, Abdallah Alabdallah, Thorsteinn Rögnvaldsson
|Level=Master
|Status=Open
}}

Meta-learning for Multivariate Signals

2022-09-21T12:13:19Z

Kunru:

{{StudentProjectTemplate
|Summary=Apply meta-learning algorithms to unlabelled time-series data to solve machine activity recognition problems.
|Programme=Master Thesis (30 Credits)
|Keywords=Meta-learning, domain adaptation, neural network, time-series data, activity recognition
|TimeFrame=2022 Fall - 2023 Summer
|References=[1] Finn, Chelsea, Pieter Abbeel, and Sergey Levine. "Model-agnostic meta-learning for fast adaptation of deep networks." International conference on machine learning. PMLR, 2017.

[2] Ganin, Yaroslav, et al. "Domain-adversarial training of neural networks." The journal of machine learning research 17.1 (2016): 2096-2030.

[3] A. Fischer, A. B. Bedrikow, S. Kessler and J. Fottner, "Equipment data-based activity recognition of construction machinery," 2021 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2021, pp. 1-6.

[4] Xianjie Gao, Maolin Shi, Xueguan Song, Chao Zhang, Hongwei Zhang. “Recurrent neural networks for real-time prediction of TBM operating parameters.” Automation in Construction, Volume 98, 2019.
|Prerequisites=A solid background in neural networks; good knowledge of Python for implementing deep learning algorithms.
Courses: Learning System; Deep Learning
|Supervisor=Kunru Chen, Anna Vettoruzzo, Mohamed-Rafik Bouguelia
|Level=Master
|Status=Open
}}

Background:

In the machine learning community, meta-learning or learning to learn indicates the ability of the models to accumulate experience from multiple domains and exploit it to achieve fast adaptation to a new domain. Multiple attempts have been made in the past for solving few-shot supervised problems, where only a few labelled data are available, e.g., see [1]. However, it is difficult and expensive to obtain labelled data in many real-world applications, opening the way to unsupervised meta-learning. Let’s take for example the machine activity recognition (MAR) problem where the aim is to extend the knowledge learned for classifying different activities to different countries, warehouses, or machines. This problem could be addressed with domain adaptation methods, like DANN [2], but the time required for adaptation and the resource for training the algorithm is huge. Therefore, exploiting meta-learning to solve MAR problems could lead to a significant improvement in the field.

In this project, time-series data are collected in warehouses from different countries (i.e., Sweden, Norway, Italy, and Czech) during normal operations of forklift trucks. These data are unlabelled, and they consist of 262 multi-variate features acquired at 10 Hz for 2 months. The goal is to recognize three forklift activities performed by trucks from working places. A processing operation has been implemented to assign pseudo-labels to the data at the scope of recognizing three different classes: driving (D), loading (L), and other (O). The project aims to apply meta-learning to the unsupervised setting with the scope of exploiting the knowledge acquired from Sweden, Norway, and Italy to predict the correct activity on Czech data.

Research questions:

1-How to achieve domain adaptation for solving MAR problem?

2-How to apply meta-learning with real-world time-series data?

3-How to extend the knowledge acquired from a set of domains to a new unlabelled domain?

4-What are the challenges of this method for MAR?

If you want more information about this topic, you can contact us with kunru.chen@hh.se and anna.vettoruzzo@hh.se, or pass by our office at F504a.

Note: the project is a part of the collaboration between Halmstad University and Toyota Material Handling Sweden AB.

Meta-learning for Multivariate Signals

2022-09-21T12:12:54Z

Kunru: Created page with "{{StudentProjectTemplate |Summary=Apply meta-learning algorithms to unlabelled time-series data to solve machine activity recognition problems. |Programme=Master Thesis (30 Cr..."

{{StudentProjectTemplate
|Summary=Apply meta-learning algorithms to unlabelled time-series data to solve machine activity recognition problems.
|Programme=Master Thesis (30 Credits)
|Keywords=Meta-learning, domain adaptation, neural network, time-series data, activity recognition
|TimeFrame=2022 Fall - 2023 Summer
|References=[1] Finn, Chelsea, Pieter Abbeel, and Sergey Levine. "Model-agnostic meta-learning for fast adaptation of deep networks." International conference on machine learning. PMLR, 2017.

[2] Ganin, Yaroslav, et al. "Domain-adversarial training of neural networks." The journal of machine learning research 17.1 (2016): 2096-2030.

[3] A. Fischer, A. B. Bedrikow, S. Kessler and J. Fottner, "Equipment data-based activity recognition of construction machinery," 2021 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2021, pp. 1-6.

[4] Xianjie Gao, Maolin Shi, Xueguan Song, Chao Zhang, Hongwei Zhang. “Recurrent neural networks for real-time prediction of TBM operating parameters.” Automation in Construction, Volume 98, 2019.
|Prerequisites=A solid background in neural networks; good knowledge of Python for implementing deep learning algorithms.
Courses: Learning System; Deep Learning
|Supervisor=Kunru Chen, Anna Vettoruzzo, Mohamed-Rafik Bouguelia
|Level=Master
|Status=Open
}}
In the machine learning community, meta-learning or learning to learn indicates the ability of the models to accumulate experience from multiple domains and exploit it to achieve fast adaptation to a new domain. Multiple attempts have been made in the past for solving few-shot supervised problems, where only a few labelled data are available, e.g., see [1]. However, it is difficult and expensive to obtain labelled data in many real-world applications, opening the way to unsupervised meta-learning. Let’s take for example the machine activity recognition (MAR) problem where the aim is to extend the knowledge learned for classifying different activities to different countries, warehouses, or machines. This problem could be addressed with domain adaptation methods, like DANN [2], but the time required for adaptation and the resource for training the algorithm is huge. Therefore, exploiting meta-learning to solve MAR problems could lead to a significant improvement in the field.

In this project, time-series data are collected in warehouses from different countries (i.e., Sweden, Norway, Italy, and Czech) during normal operations of forklift trucks. These data are unlabelled, and they consist of 262 multi-variate features acquired at 10 Hz for 2 months. The goal is to recognize three forklift activities performed by trucks from working places. A processing operation has been implemented to assign pseudo-labels to the data at the scope of recognizing three different classes: driving (D), loading (L), and other (O). The project aims to apply meta-learning to the unsupervised setting with the scope of exploiting the knowledge acquired from Sweden, Norway, and Italy to predict the correct activity on Czech data.

Research questions:

1-How to achieve domain adaptation for solving MAR problem?

2-How to apply meta-learning with real-world time-series data?

3-How to extend the knowledge acquired from a set of domains to a new unlabelled domain?

4-What are the challenges of this method for MAR?

If you want more information about this topic, you can contact us with kunru.chen@hh.se and anna.vettoruzzo@hh.se, or pass by our office at F504a.

Note: the project is a part of the collaboration between Halmstad University and Toyota Material Handling Sweden AB.

Kunru Chen

2021-10-11T10:37:58Z

Kunru: Created page with "{{Person |Family Name=Chen |Given Name=Kunru |Title=M. Sc. |Cell Phone=+46729773831 |Position=PhD Student |Email=kunru.chen@hh.se |Image=kunru.jpg |Office=E522 }} {{AssignProj..."

{{Person
|Family Name=Chen
|Given Name=Kunru
|Title=M. Sc.
|Cell Phone=+46729773831
|Position=PhD Student
|Email=kunru.chen@hh.se
|Image=kunru.jpg
|Office=E522
}}
{{AssignProjects
|project=CAISR+
}}
{{AssignSubjectAreas
|SubjectArea=Representation Learning
}}
{{AssignSubjectAreas
|SubjectArea=Domain Adaptation
}}
{{AssignSubjectAreas
|SubjectArea=Semi-supervised Learning
}}
{{AssignApplicationAreas
|ApplicationArea=Activity Recognition
}}
{{AssignApplicationAreas
|ApplicationArea=Usage Analysis
}}
{{AssignApplicationAreas
|ApplicationArea=Forklift Trucks
}}
[[Category:Staff]]


{{ShowPerson}}
{{InsertProjects}}

File:Kunru.jpg

2021-10-11T10:33:07Z

Kunru:

Generative Approach for Multivariate Signals

2021-08-24T08:08:15Z

Kunru:

{{StudentProjectTemplate
|Summary=The topic focuses on generative models (GAN) for CAN-bus data and investigating the representation learning capabilities of such techniques
|Keywords=GAN, Time-series data, Streaming data, MAR
|TimeFrame=2021 Fall - 2022 Summer
|References=https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks.pdf

https://arxiv.org/abs/1706.02633

https://openreview.net/pdf?id=rJedV3R5tm

https://www.aaai.org/Conferences/AAAI/2017/PreliminaryPapers/12-Yu-L-14344.pdf

https://arxiv.org/pdf/1511.06434.pdf
|Prerequisites=Excellent Programming Skills
Excellent knowledge in Machine Learning and Neural Networks
|Supervisor=Kunru Chen, Tiago Cortinhal, Thorsteinn Rögnvaldsson,
|Level=Master
|Status=Open
}}
Control Area Network (CAN) is a protocol that is used to manipulate vehicles. It is multidimensional and consists of control and sensor signals to and from different parts of the equipment. Since this data comes internally from the machine itself, it is stable and cheap to collect it. Previous work has shown that CAN data can be used to build representations for machine activity recognition (MAR) for forklift trucks. However, those representations are limited to only describing the existing data in both realism and diversity. Creating representation by training a vanilla autoencoder has disadvantages when trying to explore the entire space of CAN signals.

Generative approaches have been used mostly in traditional types of data, like images, and have shown to have great capabilities to learn the underlying distribution as well as allowing us to sample new unseen data points. This has shown great results as we can see in https://thispersondoesnotexist.com, or even in pictures to picture translations and style transfers. This generative capability also allows us to perform arithmetic operations on the vector and see the underlying structure of each different “class” of outputs.

Nevertheless, the work done in other data modalities is still sparse but nevertheless growing in interest. In this thesis, the main interest is focused on a very specific type of data that might bring all kinds of hardships and obstacles to overcome. Some of those hardships might come from the type of data we are trying to generate. This needs to be investigated and solutions to overcome these types of situations are a key aspect we will be looking for.
The students need to develop a GAN-based network to generate CAN data, to evaluate the quality of the generated data, and to use that data in a MAR task.

Research Questions:
Can GANs generate realistic CAN data?
Can GANs generate/predict the (near) future CAN signals?
Is the latent space an informative representation about the CAN signals?

If you want more information about this topic you can contact us at kunru.chen@hh.se and tiago.cortinhal@hh.se or pass by our office at E522!

Generative Approach for Multivariate Signals

2020-10-09T11:23:33Z

Kunru:

{{StudentProjectTemplate
|Summary=The topic focuses on generative models (GAN) for CAN-bus data and investigating the representation learning capabilities of such techniques
|Keywords=GAN, CAN data, MAR
|TimeFrame=2020 Fall - 2021 Summer
|References=https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks.pdf

https://arxiv.org/abs/1706.02633

https://openreview.net/pdf?id=rJedV3R5tm

https://www.aaai.org/Conferences/AAAI/2017/PreliminaryPapers/12-Yu-L-14344.pdf

https://arxiv.org/pdf/1511.06434.pdf
|Prerequisites=Excellent Programming Skills
Excellent knowledge in Machine Learning and Neural Networks
|Supervisor=Kunru Chen, Tiago Cortinhal, Thorsteinn Rögnvaldsson,
|Level=Master
|Status=Open
}}
Control Area Network (CAN) is a protocol that is used to manipulate vehicles. It is multidimensional and consists of control and sensor signals to and from different parts of the equipment. Since this data comes internally from the machine itself, it is stable and cheap to collect it. Previous work has shown that CAN data can be used to build representations for machine activity recognition (MAR) for forklift trucks. However, those representations are limited to only describing the existing data in both realism and diversity. Creating representation by training a vanilla autoencoder has disadvantages when trying to explore the entire space of CAN signals.

Generative approaches have been used mostly in traditional types of data, like images, and have shown to have great capabilities to learn the underlying distribution as well as allowing us to sample new unseen data points. This has shown great results as we can see in https://thispersondoesnotexist.com, or even in pictures to picture translations and style transfers. This generative capability also allows us to perform arithmetic operations on the vector and see the underlying structure of each different “class” of outputs.

Nevertheless, the work done in other data modalities is still sparse but nevertheless growing in interest. In this thesis, the main interest is focused on a very specific type of data that might bring all kinds of hardships and obstacles to overcome. Some of those hardships might come from the type of data we are trying to generate. This needs to be investigated and solutions to overcome these types of situations are a key aspect we will be looking for.
The students need to develop a GAN-based network to generate CAN data, to evaluate the quality of the generated data, and to use that data in a MAR task.

Research Questions:
Can GANs generate realistic CAN data?
Can GANs generate/predict the (near) future CAN signals?
Is the latent space an informative representation about the CAN signals?

If you want more information about this topic you can contact us at kunru.chen@hh.se and tiago.cortinhal@hh.se or pass by our office at E522!

Forklift Trucks Usage Analysis

2019-10-01T11:35:43Z

Kunru:

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen, Alexander Galozy
|Level=Master
|Status=Open
}}
Background:

Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

The goal of the project to derive knowledge about forklift trucks activities. Machine learning techniques should be applied for usage analysis. There are also two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
# multi-class classifications and optimization;
# data augmentation for the specific industrial application;
# unsupervised learning to cover and interpret most of the usage.

If you are interested in this project, please contact kunru.chen@hh.se or pay visit to E522.

Forklift Trucks Usage Analysis

2019-09-27T11:53:28Z

Kunru:

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen
|Level=Master
|Status=Open
}}
Background:

Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

There are two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
# multi-class classifications and optimization;
# data augmentation for the specific industrial application;
# unsupervised learning to cover and interpret most of the usage.

If you are interested in this project, please contact kunru.chen@hh.se or pay visit to E522.

Forklift Trucks Usage Analysis

2019-09-27T11:51:45Z

Kunru:

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen
|Level=Master
|Status=Open
}}
Background:

Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

There are two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
# multi-class classifications and optimization;
# data augmentation for the specific industrial application;
# unsupervised learning to cover and interpret most of the usage.

If you are interested in this project, please contact kunru.chen@hh.se.

Forklift Trucks Usage Analysis

2019-09-27T08:37:57Z

Kunru:

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen
|Level=Master
|Status=Open
}}
Background:

Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

There are two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
1) multi-class classifications and optimization;
2) data augmentation for the specific industrial application;
3) unsupervised learning to cover and interpret most of the usage.

If you are interested in this project, please contact kunru.chen@hh.se.

Forklift Trucks Usage Analysis

2019-09-27T08:35:13Z

Kunru:

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen
|Level=Master
|Status=Open
}}
Background:
Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

There two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
1) multi-class classifications and optimization;
2) data augmentation for the specific industrial application;
3) unsupervised learning to cover and interpret most of the usage.

If you are interested in this project, please contact kunru.chen@hh.se.

Forklift Trucks Usage Analysis

2019-09-26T08:28:50Z

Kunru: Created page with "{{StudentProjectTemplate |Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial applic..."

{{StudentProjectTemplate
|Summary=This project is about applying machine learning methods to have a better understanding for the usage of forklifts trucks in industrial application.
|Keywords=Data Mining, Sequence modelling, Representation learning, Activity recognition, Time-series data
|TimeFrame=Fall 2019
|References=[1] J.Wang et al., “Deep learning for sensor-based activity recognition: A survey”, in Pattern Recognition Letters, 119, (2019) 3–11
[2] S. Herath et al., “Going deeper into action recognition: A survey”, in Image and Vision Computing, 60, (2017) 4–21
|Prerequisites=Data Structure and Algorithms, Artificial Intelligence and Learning Systems courses, programming skills for implementing machine learning algorithms
|Supervisor=Kunru Chen
|Level=Master
|Status=Open
}}
Background:
Vehicle manufacturers have certain rules when the equipment is designed, i.e. they expect that their customers use the equipment in their expected manners. In practical life, however, customers might not notice those details: they use the product in the way that they want to use. This fact causes a series of unexpected and unknown behaviors, and the customers might not use the product in a correct way. Without the knowledge about the actual usage of the product, the company would have problems on maintenance service and product improvement.

This project is in collaboration between Halmstad University and an enterprise, which means that the datasets involved are from real industrial application. The objective of this project is the forklift trucks from that company. They would like to know the practical usage of the forklifts with data mining techniques. They have collected signal-based data with high frequency and have applied some basic data pre-processing. There are some background studies derived from the same dataset, which focus on rule-based analysis and lift events definition.

There two main challenges in this project: 1) same activities can consist of different patterns in different tasks. For example, the vehicle speed can largely vary when the truck is in a warehouse and when it is working outdoors; 2) activities which happen closely in time can be hard to distinguish from each other, since they have a small or even no period of transition.

Possible directions:
1) multi-class classifications and optimization;
2) data augmentation for the specific industrial application;
3) unsupervised learning to cover and interpret most of the usage.