| 1. |
- Hedenberg, Klas, 1968-, et al.
(författare)
-
Obstacle Detection For Thin Horizontal Structures
- 2008
-
Ingår i: World Congress on Engineering and Computer Science. - Hong Kong : International Association of Engineers. - 9789889867102 ; , s. 689-693
-
Konferensbidrag (refereegranskat)abstract
- Many vision-based approaches for obstacle detection often state that vertical thin structure is of importance, e.g. poles and trees. However, there are also problem in detecting thin horizontal structures. In an industrial case there are horizontal objects, e.g. cables and fork lifts, and slanting objects, e.g. ladders, that also has to be detected. This paper focuses on the problem to detect thin horizontal structures. The system uses three cameras, situated as a horizontal pair and a vertical pair, which makes it possible to also detect thin horizontal structures. A comparison between a sparse disparity map based on edges and a dense disparity map with a column and row filter is made. Both methods use the Sum of Absolute Difference to compute the disparity maps. Special interest has been in scenes with thin horizontal objects. Tests show that the sparse dense method based on the Canny edge detector works better for the environments we have tested.
|
|
| 2. |
- Josefsson, Torbjörn, 1965, et al.
(författare)
-
The effects of a short-term mindfulness based intervention on self-reported mindfulness, decentering, executive attention, psychological health, and coping style: Examining unique mindfulness effects and mediators.
- 2014
-
Ingår i: Mindfulness. - New York, United States : Springer Science and Business Media LLC. - 1868-8527 .- 1868-8535. ; 5:1, s. 18-35
-
Tidskriftsartikel (refereegranskat)abstract
- The majority of mindfulness intervention studies do not include active control groups. To examine potential unique effects of mindfulness practice and to study the mechanism responsible for beneficial mental health effects associated with mindfulness-based interventions, the present study compared mindfulness meditation with an active control group in a randomised controlled trial. A short-term mindfulness-based intervention (n = 46) was compared with both an active control group—relaxation training (n = 40)—and an inactive wait-list group (n = 40) on self-reported mindfulness and decentering, executive attention, psychological well-being, anxiety, depression, and coping style, in an adult working population with no prior meditation experience. Analyses of covariance showed that the mindfulness group scored higher than the wait-list group on self-reported mindfulness and psychological well-being. However, no differences were found on decentering, anxiety, depression, executive attention, or coping style. Moreover, the study failed to distinguish any unique mindfulness effects since there were no differences between mindfulness and relaxation on any of the variables. Simple mediation analyses, using a bootstrap approach, revealed that decentering acted as a mediator between self-reported mindfulness and psychological well-being. The length of the intervention, the similarities between body scan exercises in MBI and relaxation, and the absence of decentering effects may partly explain the lack of distinct MBI effects, suggesting that MBIs aimed at increasing well-being and problem-focused coping whilst reducing psychological symptoms in a working population should be longer than merely 4 weeks and include more than seven sessions.
|
|
| 3. |
- Albinsson, John, et al.
(författare)
-
Combined use of Iteration, Quadratic Interpolation and an Extra Kernel for high-resolution 2D particle tracking : a first evaluation
- 2010
-
Ingår i: 2010 ieee international ultrasonics symposium. - New York : IEEE Press. - 9781457703829 ; , s. 2000-2003
-
Konferensbidrag (refereegranskat)abstract
- A novel 2D particle tracking method, that uses 1) iteration, 2) fast quadratic sub-pixel estimation (with only 28 multiplications per movement), and 3) a previous kernel, has been evaluated and compared with a full-search block-matching method. The comparison with high-frequency ultrasound data (40 MHz) was conducted in silico and on phantoms, which comprised lateral, diagonal, and ellipsoidal movement patterns with speeds of 0–15 mm/s. The mean tracking error was reduced by 68% in silico and 71% for the phantom measurements. When only sub-pixel estimation was used, the decrease in the tracking error was 61% in silico and 57% for the phantom measurements. As well as decreasing the tracking error, the new method only used 70% of the computational time needed by the full-search block-matching method. With a fast method having good tracking ability for high-frequency ultrasound data, we now have a tool to better investigate tissue movements and its dynamic functionality.
|
|
| 4. |
|
|
| 5. |
- Soliman, Amira, 1980-, et al.
(författare)
-
Adopting transfer learning for neuroimaging : a comparative analysis with a custom 3D convolution neural network model
- 2022
-
Ingår i: BMC Medical Informatics and Decision Making. - London : BioMed Central (BMC). - 1472-6947. ; 22, s. 1-15
-
Tidskriftsartikel (refereegranskat)abstract
- Background: In recent years, neuroimaging with deep learning (DL) algorithms have made remarkable advances in the diagnosis of neurodegenerative disorders. However, applying DL in different medical domains is usually challenged by lack of labeled data. To address this challenge, transfer learning (TL) has been applied to use state-of-the-art convolution neural networks pre-trained on natural images. Yet, there are differences in characteristics between medical and natural images, also image classification and targeted medical diagnosis tasks. The purpose of this study is to investigate the performance of specialized and TL in the classification of neurodegenerative disorders using 3D volumes of 18F-FDG-PET brain scans. Results: Results show that TL models are suboptimal for classification of neurodegenerative disorders, especially when the objective is to separate more than two disorders. Additionally, specialized CNN model provides better interpretations of predicted diagnosis. Conclusions: TL can indeed lead to superior performance on binary classification in timely and data efficient manner, yet for detecting more than a single disorder, TL models do not perform well. Additionally, custom 3D model performs comparably to TL models for binary classification, and interestingly perform better for diagnosis of multiple disorders. The results confirm the superiority of the custom 3D-CNN in providing better explainable model compared to TL adopted ones. © 2022, The Author(s).
|
|
| 6. |
- Li, Ping, et al.
(författare)
-
Sparse regularized joint projection model for identifying associations of non-coding RNAs and human diseases
- 2022
-
Ingår i: Knowledge-Based Systems. - Amsterdam : Elsevier. - 0950-7051 .- 1872-7409. ; 258
-
Tidskriftsartikel (refereegranskat)abstract
- Current human biomedical research shows that human diseases are closely related to non-coding RNAs, so it is of great significance for human medicine to study the relationship between diseases and non-coding RNAs. Current research has found associations between non-coding RNAs and human diseases through a variety of effective methods, but most of the methods are complex and targeted at a single RNA or disease. Therefore, we urgently need an effective and simple method to discover the associations between non-coding RNAs and human diseases. In this paper, we propose a sparse regularized joint projection model (SRJP) to identify the associations between non-coding RNAs and diseases. First, we extract information through a series of ncRNA similarity matrices and disease similarity matrices and assign average weights to the similarity matrices of the two sides. Then we decompose the similarity matrices of the two spaces into low-rank matrices and put them into SRJP. In SRJP, we innovatively use the projection matrix to combine the ncRNA side and the disease side to identify the associations between ncRNAs and diseases. Finally, the regularization term in SRJP effectively improves the robustness and generalization ability of the model. We test our model on different datasets involving three types of ncRNAs: circRNA, microRNA and long non-coding RNA. The experimental results show that SRJP has superior ability to identify and predict the associations between ncRNAs and diseases. © 2022 The Author(s)
|
|
| 7. |
- Shakya, Akhilesh Kumar, et al.
(författare)
-
An update on smart biocatalysts for industrial and biomedical applications
- 2018
-
Ingår i: Journal of the Royal Society Interface. - : The Royal Society. - 1742-5689 .- 1742-5662. ; 15:139
-
Tidskriftsartikel (refereegranskat)abstract
- Recently, smart biocatalysts, where enzymes are conjugated to stimuli-responsive (smart) polymers, have gained significant attention. Based on the presence or absence of external stimuli, the polymer attached to the enzyme changes its conformation to protect the enzyme from the external environment and regulate the enzyme activity, thus acting as a molecular switch. Owing to this behaviour, smart biocatalysts can be separated easily from a reaction mixture and re-used several times. Several such smart polymer-based biocatalysts have been developed for industrial and biomedical applications. In addition, they have been used in biosensors, biometrics and nano-electronic devices. This review article covers recent advances in developing different kinds of stimuli-responsive enzyme bioconjugates, including conjugation strategies, and their applications.
|
|
| 8. |
- Geng, H., et al.
(författare)
-
Incomplete B cell tolerance to cartilage oligomeric matrix protein in mice
- 2013
-
Ingår i: Arthritis and Rheumatism. - : Wiley. - 0004-3591 .- 1529-0131. ; 65:9, s. 2301-2309
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVE: Cartilage oligomeric matrix protein (COMP) is a major noncollagenous component of cartilage and is used as a biomarker in rheumatoid arthritis and experimental arthritis. Injection of COMP leads to severe inflammatory joint disease, and antibodies play a critical role in mediating arthritis. The arthritogenicity of COMP might be due to the lack of self tolerance. This study was undertaken to determine the status of COMP-specific B cell tolerance using COMP-deficient mice. METHODS: Arthritis development and antibody responses were compared between COMP-sufficient and COMP-deficient littermates after immunization with rat COMP. Serum anti-COMP antibody levels were measured using a panel of recombinant mouse COMP proteins, and antibody-secreting cells were enumerated by enzyme-linked immunospot assays. A novel sandwich enzyme-linked immunosorbent assay was developed to assess COMP molecules in serum. RESULTS: COMP-sufficient mice, but not COMP-deficient mice, developed severe arthritis following immunization with rat COMP. However, anti-COMP antibody titers to native COMP and recombinant protein domains covering the entire mouse COMP sequence, except the less immunodominant type 3 repeat domains, were decreased in COMP-sufficient mice compared to COMP-deficient mice. In addition, COMP-sufficient mice had fewer B cells secreting COMP-reactive antibodies. Detectable levels of full-length COMP in arthritic COMP-sufficient B10.Q NCF-1(*/*) and healthy mice suggested systemic availability of COMP to the immune system. CONCLUSION: The lack of arthritis, together with high levels of COMP-specific antibodies, in COMP-deficient mice indicates that susceptibility to arthritis is COMP specific and that endogenous expression of COMP in wild-type mice tolerizes B cells in vivo.
|
|
| 9. |
- Guo, Xiaoyi, et al.
(författare)
-
Subspace projection-based weighted echo state networks for predicting therapeutic peptides
- 2023
-
Ingår i: Knowledge-Based Systems. - Amsterdam : Elsevier. - 0950-7051 .- 1872-7409. ; 263
-
Tidskriftsartikel (refereegranskat)abstract
- Detection of therapeutic peptide is a major research direction in the current biopharmaceutical field. However, traditional biochemical experimental detection methods take a lot of time. As supplementary methods for biochemical experiments, the computational methods can improve the efficiency of therapeutic peptide detection. Currently, most machine learning-based therapeutic peptide identification algorithms do not consider the processing of noisy samples. We propose a therapeutic peptide classifier, called weighted echo state networks based on subspace projection (WESN-SP), which reduces the bias caused by high-dimensional noisy features and noisy samples. WESN-SP is trained by sparse Bayesian learning algorithm (SBL) and introduces a weight coefficient for each sample by kernel dependence maximization-based subspace projection. The experimental results show that WESN-SP has better performance than other existing methods. © 2023 The Author(s). Published by Elsevier B.V.
|
|
| 10. |
|
|
