| 1. |
|
|
| 2. |
- Almemark, Mats, et al.
(författare)
-
Analysis and Development of the Interpretation process in LCA
- 2000
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The objective of this work is to study interpretation as a procedure to use the quantitative results of a life-cycle inventory to compare process alternatives with the aim to conclude, whether or not significant differences exist with regard to the studied issues (individual emissions or impact categories). As a result of an introductory survey a procedure for quantitative interpretations is suggested, with data-quality scoring, statistical experimental planning, and multivariate data analysis as basic tools. The procedure has been tested on a case study of treatment of paper packaging waste, either by material recycling or by energy recovery (incineration). The inventory of an earlier study has been used. With the aid of what is called a conceptual model five variables, which could be presumed to have an influence on the environmental impact of paper packaging waste treatment, were identified. The choice of technology, material recycling or energy recovery, was one of these variables. Subsequently 36 scenario calculations, organised in an experimental matrix, were performed. The result was interpreted with the multivariate techniques principal component analysis (PCA), partial least-square modelling (PLS), and uncertainty analysis. The multivariate analysis made it possible to isolate the influence of the variable 'choice of technology' on the environmental impact of the system.
|
|
| 3. |
- Andreasson, Philip, et al.
(författare)
-
Quantum error correction for the toric code using deep reinforcement learning
- 2019
-
Ingår i: Quantum. - : Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften. - 2521-327X. ; 3
-
Tidskriftsartikel (refereegranskat)abstract
- We implement a quantum error correction algorithm for bit-flip errors on the topological toric code using deep reinforcement learning. An action-value Q-function encodes the discounted value of moving a defect to a neighboring site on the square grid (the action) depending on the full set of defects on the torus (the syndrome or state). The Q-function is represented by a deep convolutional neural network. Using the translational invariance on the torus allows for viewing each defect from a central perspective which significantly simplifies the state space representation independently of the number of defect pairs. The training is done using experience replay, where data from the algorithm being played out is stored and used for mini-batch upgrade of the Q-network. We find performance which is close to, and for small error rates asymptotically equivalent to, that achieved by the Minimum Weight Perfect Matching algorithm for code distances up to d=7. Our results show that it is possible for a self-trained agent without supervision or support algorithms to find a decoding scheme that performs on par with hand-made algorithms, opening up for future machine engineered decoders for more general error models and error correcting codes.
|
|
| 4. |
- Balabanov, Oleksandr, et al.
(författare)
-
Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
- 2021
-
Ingår i: Machine Learning. - : IOP Publishing. - 2632-2153. ; 2:2
-
Tidskriftsartikel (refereegranskat)abstract
- Multi-band insulating Bloch Hamiltonians with internal or spatial symmetries, such as particle-hole or inversion, may have topologically disconnected sectors of trivial atomic-limit (momentum-independent) Hamiltonians. We present a neural-network-based protocol for finding topologically relevant indices that are invariant under transformations between such trivial atomic-limit Hamiltonians, thus corresponding to the standard classification of band insulators. The work extends the method of 'topological data augmentation' for unsupervised learning introduced (2020 Phys. Rev. Res. 2 013354) by also generalizing and simplifying the data generation scheme and by introducing a special 'mod' layer of the neural network appropriate for Z ( n ) classification. Ensembles of training data are generated by deforming seed objects in a way that preserves a discrete representation of continuity. In order to focus the learning on the topologically relevant indices, prior to the deformation procedure we stack the seed Bloch Hamiltonians with a complete set of symmetry-respecting trivial atomic bands. The obtained datasets are then used for training an interpretable neural network specially designed to capture the topological properties by learning physically relevant momentum space quantities, even in crystalline symmetry classes.
|
|
| 5. |
- Balabanov, Oleksandr, 1991, et al.
(författare)
-
Unsupervised learning using topological data augmentation
- 2020
-
Ingår i: PHYSICAL REVIEW RESEARCH. - 2643-1564. ; 2
-
Tidskriftsartikel (refereegranskat)abstract
- Unsupervised machine learning is a cornerstone of artificial intelligence as it provides algorithms capable of learning tasks, such as classification of data, without explicit human assistance. We present an unsupervised deep learning protocol for finding topological indices of quantum systems. The core of the proposed scheme is a “topological data augmentation” procedure that uses seed objects to generate ensembles of topologically equivalent data. Such data, assigned with dummy labels, can then be used to train a neural network classifier for sorting arbitrary objects into topological equivalence classes. Importantly, we also show how to retrieve the local quantities corresponding to the learned topological indices from the intermediate outputs of the trained network. Our protocol is explicitly illustrated on two-band insulators in one and two dimensions, characterized by a winding number and a Chern number respectively. Using the augmentation technique also in the classification step, to classify a family of topologically equivalent objects instead of a single object, we can achieve accuracy arbitrarily close to 100% even for indices outside the training regime. Apart from the method's applicability to topological classification, it also provides a new perspective on data augmentation in supervised machine learning, where given sufficient mathematical structure the set of category-preserving deformations can be rigorously defined.
|
|
| 6. |
- Cusumano, Linda, 1981, et al.
(författare)
-
Current benefits and future possibilities with digital field reporting
- 2024
-
Ingår i: International Journal of Construction Management. - 1562-3599. ; In Press
-
Tidskriftsartikel (refereegranskat)abstract
- Mobile phones and tablets enable contractors to digitally collect large amounts of production remarks and facilitate the acquisition. The increased data access and machine learning techniques allow the construction industry to take a significant step forward in shifting from implicit to explicit knowledge. However, this step requires both standardisation and data quality assurance combined with project incitements ensuring continuous data collection. Therefore, this study examines the current data quality and standardisation of inspection data generated using the production software Dalux Field, mining a dataset of more than 95000 production issues. Additionally, a survey of production software users assesses project and project member benefits and future possibilities with digital inspection reporting. The results show considerable benefits with digital inspection reporting, such as time savings, cost reductions and increased general quality control. However, the standardisation in reporting between projects and team members is low. Finally, this paper suggests methods for improving data quality and standardization for automation of the data analysis, allowing new projects in project-based organisations to benefit from previous project experiences.
|
|
| 7. |
- Cusumano, Linda, 1981, et al.
(författare)
-
Current benefits and future possibilities with digital field reporting
- 2024
-
Ingår i: INTERNATIONAL JOURNAL OF CONSTRUCTION MANAGEMENT. - 1562-3599 .- 2331-2327.
-
Tidskriftsartikel (refereegranskat)abstract
- Mobile phones and tablets enable contractors to digitally collect large amounts of production remarks and facilitate the acquisition. The increased data access and machine learning techniques allow the construction industry to take a significant step forward in shifting from implicit to explicit knowledge. However, this step requires both standardisation and data quality assurance combined with project incitements ensuring continuous data collection. Therefore, this study examines the current data quality and standardisation of inspection data generated using the production software Dalux Field, mining a dataset of more than 95000 production issues. Additionally, a survey of production software users assesses project and project member benefits and future possibilities with digital inspection reporting. The results show considerable benefits with digital inspection reporting, such as time savings, cost reductions and increased general quality control. However, the standardisation in reporting between projects and team members is low. Finally, this paper suggests methods for improving data quality and standardization for automation of the data analysis, allowing new projects in project-based organisations to benefit from previous project experiences.
|
|
| 8. |
- Cusumano, Linda, 1981, et al.
(författare)
-
Intelligent building contract tendering - potential and exploration
- 2022
-
Ingår i: IABSE Symposium Prague, 2022: Challenges for Existing and Oncoming Structures - Report. - Zurich, Switzerland : International Association for Bridge and Structural Engineering (IABSE). ; , s. 1902-1909
-
Konferensbidrag (refereegranskat)abstract
- Project tendering is the construction business “Tightrope-walking.” It is a time-limited balance act where technical and business specialists find the best technical proposal at the right price. The purpose and aim of this study were to explore artificial intelligence (AI) in the tender work and to identify challenges and possibilities with data-driven decision-making. An AI work support tool was adopted and used to extract and process client requirements. The tool and digital-work procedure were presented and discussed with tender specialists from a large contractor in a workshop. A two-step survey was performed in connection to the workshop, investigating the potential users' insights and attitudes for implementation. The main result and conclusion were that AI and digitalization could support tendering; however, successfully generating business value will require higher levels of digitalization, well-structured databases, and access to historical project data.
|
|
| 9. |
- Cusumano, Linda, 1981, et al.
(författare)
-
Natural language processing as work support in project tendering
- 2022
-
Ingår i: Current Perspectives and New Directions in Mechanics, Modelling and Design of Structural Systems. - London : CRC Press. - 9781003348443 ; , s. 1583-1588
-
Konferensbidrag (refereegranskat)abstract
- When producing a tender, contractors manually analyze client requirements contained within many different text documents. The combination of requirements lead to crucial design decisions and every decision is related to costs and risks. This study explores the possibility of making the client requirement analysis in design-bid contracts automated to reduce the risk of conceptual design mistakes. The research approach chosen includes developing a work support tool based on natural language processing and analyzing its usefulness through a combination of surveys and a workshop for tendering specialist. The results show that applying digitalized working methods and using artificial intelligence in the tender phase can enable data-informed decision making and generate benchmarking and risk management opportunities. The study contributes to insights regarding automation and digitization possibilities in tender projects and how artificial intelligence tools can be designed for supporting data-driven decisions.
|
|
| 10. |
|
|
