Dalarna University's logo and link to the university's website

du.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 57) Show all publications
Saeed, N., Alam, M. & Nyberg, R. G. (2024). A multimodal deep learning approach for gravel road condition evaluation through image and audio integration. Transportation Engineering, 16, Article ID 100228.
Open this publication in new window or tab >>A multimodal deep learning approach for gravel road condition evaluation through image and audio integration
2024 (English)In: Transportation Engineering, ISSN 2666-691X, Vol. 16, article id 100228Article in journal (Refereed) Published
Abstract [en]

This study investigates the combination of audio and image data to classify road conditions, particularly focusingon loose gravel scenarios. The dataset underwent binary categorisation, comprising audio segments capturinggravel sounds and corresponding images. Early feature fusion, utilising a pre-trained Very Deep ConvolutionalNetworks 19 (VGG19) and Principal component analysis (PCA), improved the accuracy of the Random Forestclassifier, surpassing other models in accuracy, precision, recall, and F1-score. Late fusion, involving decisionlevelprocessing with logical disjunction and conjunction gates (AND and OR) in combination with individualclassifiers for images and audio based on Densely Connected Convolutional Networks 121 (DenseNet121),demonstrated notable performance, especially with the OR gate, achieving 97 % accuracy. The late fusionmethod enhances adaptability by compensating for limitations in one modality with information from the other.Adapting maintenance based on identified road conditions minimises unnecessary environmental impact. Thismethod can help to identify loose gravel on gravel roads, substantially improving road safety and implementing aprecise maintenance strategy through a data-driven approach.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Gravel road maintenance, Data fusion, Sound analysis, Machine vision, Machine, Learning
National Category
Architectural Engineering
Identifiers
urn:nbn:se:du-48032 (URN)10.1016/j.treng.2024.100228 (DOI)2-s2.0-85184492304 (Scopus ID)
Available from: 2024-02-13 Created: 2024-02-13 Last updated: 2024-02-23
Saleh, R., Fleyeh, H., Alam, M. & Hintze, A. (2023). Assessing the color status and daylight chromaticity of road signs through machine learning approaches. IATSS Research, 47(3), 305-317
Open this publication in new window or tab >>Assessing the color status and daylight chromaticity of road signs through machine learning approaches
2023 (English)In: IATSS Research, ISSN 0386-1112, Vol. 47, no 3, p. 305-317Article in journal (Refereed) Published
Abstract [en]

The color of road signs is a critical aspect of road safety, as it helps drivers quickly and accurately identify and respond to these signs. Properly colored road signs improve visibility during the day and make it easier for drivers to make informed decisions while driving. In order to ensure the safety and efficiency of road traffic, it is essential to maintain the appropriate color level of road signs. The objective of this study was to analyze the color status and daylight chromaticity of in-use road signs using supervised machine learning models, and to explore the correlation between road sign's age and daylight chromaticity. Three algorithms were employed: Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The data used in this study was collected from road signs that were in-use on roads in Sweden. The study employed classification models to assess the color status (accepted or rejected) of the road signs based on minimum acceptable color levels according to standards, and regression models to predict the daylight chromaticity values. The correlation between road sign's age and daylight chromaticity was explored through regression analysis. Daylight chromaticity describes the color quality of road signs in daylight, that is expressed in terms of X and Y chromaticity coordinates. The study revealed a linear relationship between the road sign's age and daylight chromaticity for blue, green, red, and white sheeting, but not for yellow. The lifespan of red signs was estimated to be around 12 years, much shorter than the estimated lifespans of yellow, green, blue, and white sheeting, which are 35, 42, 45, and 75 years, respectively. The supervised machine learning models successfully assessed the color status of the road signs and predicted the daylight chromaticity values using the three algorithms. The results of this study showed that the ANN classification and ANN regression models achieved high accuracy of 81% and R2 of 97%, respectively. The RF and SVM models also performed well, with accuracy values of 74% and 79% and R2 ranging from 59% to 92%. The findings demonstrate the potential of machine learning to effectively predict the status and daylight chromaticity of road signs and their impact on road safety in the Swedish context. © 2023 International Association of Traffic and Safety Sciences

Keywords
Classification, Daylight chromaticity, Machine learning algorithms, Prediction, Regression, Road signs, Accident prevention, Color, Forecasting, Forestry, Learning algorithms, Learning systems, Motor transportation, Regression analysis, Roads and streets, Support vector machines, Color levels, Machine learning models, Random forests, Regression modelling, Road safety, Supervised machine learning, Neural networks
National Category
Transport Systems and Logistics Computer and Information Sciences
Identifiers
urn:nbn:se:du-46627 (URN)10.1016/j.iatssr.2023.06.003 (DOI)001048708900001 ()2-s2.0-85164276006 (Scopus ID)
Available from: 2023-08-04 Created: 2023-08-04 Last updated: 2023-09-01Bibliographically approved
Marmstål Hammar, L., Alam, M., Eklund, C., Boström, A.-M. & Lövenmark, A. (2023). Clarity and adaptability of instructions preventing the spread of the COVID-19 virus and its association with individual and organisational factors regarding the psychosocial work environment: a cross-sectional study. BMC Health Services Research, 23(1), Article ID 1312.
Open this publication in new window or tab >>Clarity and adaptability of instructions preventing the spread of the COVID-19 virus and its association with individual and organisational factors regarding the psychosocial work environment: a cross-sectional study
Show others...
2023 (English)In: BMC Health Services Research, E-ISSN 1472-6963, Vol. 23, no 1, article id 1312Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: In Sweden, older people in residential care had the highest mortality rates, followed by those who received home care, during the coronavirus disease 2019 (COVID-19) pandemic. Staff working in the care of older people assumed responsibility for preventing the spread of the virus despite lacking the prerequisites and training. This study aimed to investigate the psychosocial work environment during the COVID-19 pandemic among staff in the care of older people and examine the factors associated with staff's perceptions of the clarity of instructions and the ability to follow them.

METHODS: A cross-sectional study design was employed using a web survey. The staff's perceptions of their psychosocial environment were analysed using descriptive statistics. The association between organisational and individual factors, as well as the degree of clarity of the instructions and the staff's ability to follow them, were assessed using multivariate (ordinal) regression analysis.

RESULTS: The main findings show that perceptions of the clarity and adaptability of the instructions were primarily correlated with organisational factors, as higher responses (positive) for the subscales focusing on role clarity, support and encouragement in leadership at work were associated with the belief that the instructions were clear. Similarly, those indicating high job demands and high individual learning demands were less likely to report that the instructions were clear. Regarding adaptability, high scores for demands on learning and psychological demands were correlated with lower adaptability, while high scores for role clarity, encouraging leadership and social support, were associated with higher adaptability.

CONCLUSIONS: High job demands and individual learning demands were demonstrated to decrease the staff's understanding and adoption of instructions. These findings are significant on an organisational level since the work environment must be prepared for potential future pandemics to promote quality improvement and generally increase patient safety and staff health.

Keywords
COVID-19, Care aide geriatric nursing, Home care service, Nursing assistant, Occupational health, Residential facilities, Work conditions
National Category
Nursing
Identifiers
urn:nbn:se:du-47436 (URN)10.1186/s12913-023-10320-1 (DOI)001107670600001 ()38017458 (PubMedID)2-s2.0-85178076918 (Scopus ID)
Available from: 2023-12-05 Created: 2023-12-05 Last updated: 2023-12-21Bibliographically approved
Niebuhr, B. B., Van Moorter, B., Stien, A., Tveraa, T., Strand, O., Langeland, K., . . . Panzacchi, M. (2023). Estimating the cumulative impact and zone of influence of anthropogenic features on biodiversity. Methods in Ecology and Evolution, 14, 2362-2375
Open this publication in new window or tab >>Estimating the cumulative impact and zone of influence of anthropogenic features on biodiversity
Show others...
2023 (English)In: Methods in Ecology and Evolution, E-ISSN 2041-210X, Vol. 14, p. 2362-2375Article in journal (Refereed) Published
Abstract [en]

The concept of cumulative impacts is widespread in policy documents, regulations and ecological studies, but quantification methods are still evolving. Infrastructure development usually takes place in landscapes with preexisting anthropogenic features. Typically, their impact is determined by computing the distance to the nearest feature only, thus ignoring the potential cumulative impacts of multiple features. We propose the cumulative ZOI approach to assess whether and to what extent anthropogenic features lead to cumulative impacts. The approach estimates both effect size and zone of influence (ZOI) of anthropogenic features and allows for estimation of cumulative effects of multiple features distributed in the landscape. First, we use simulations and an empirical study to understand under which circumstances cumulative impacts arise. Second, we demonstrate the approach by estimating the cumulative impacts of tourist infrastructure in Norway on the habitat of wild reindeer (Rangifer t. tarandus), a near-threatened species highly sensitive to anthropogenic disturbance. In the simulations, we showed that analyses based on the nearest feature and our cumulative approach are indistinguishable in two extreme cases: when features are few and scattered and their ZOI is small, and when features are clustered and their ZOI is large. The empirical analyses revealed cumulative impacts of private cabins and tourist resorts on reindeer, extending up to 10 and 20 km, with different decaying functions. Although the impact of an isolated private cabin was negligible, the cumulative impact of ‘cabin villages’ could be much larger than that of a single large tourist resort. Focusing on the nearest feature only underestimates the impact of ‘cabin villages’ on reindeer. The suggested approach allows us to quantify the magnitude and spatial extent of cumulative impacts of point, linear, and polygon features in a computationally efficient and flexible way and is implemented in the oneimpact R package. The formal framework offers the possibility to avoid widespread underestimations of anthropogenic impacts in ecological and impact assessment studies and can be applied to a wide range of spatial response variables, including habitat selection, population abundance, species richness and diversity, community dynamics and other ecological processes. © 2023 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.

Place, publisher, year, edition, pages
British Ecological Society, 2023
Keywords
Anthropocene, cumulative effects, distance-weighting, habitat loss, habitat selection, kernel density, Rangifer tarandus, scale of effect
National Category
Ecology
Identifiers
urn:nbn:se:du-46164 (URN)10.1111/2041-210X.14133 (DOI)001000663600001 ()2-s2.0-85160813753 (Scopus ID)
Available from: 2023-06-12 Created: 2023-06-12 Last updated: 2024-01-17Bibliographically approved
Saleh, R., Fleyeh, H. & Alam, M. (2022). An Analysis of the Factors Influencing the Retroreflectivity Performance of In-Service Road Traffic Signs. Applied Sciences, 12(5), Article ID 2413.
Open this publication in new window or tab >>An Analysis of the Factors Influencing the Retroreflectivity Performance of In-Service Road Traffic Signs
2022 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 12, no 5, article id 2413Article in journal (Refereed) Published
Abstract [en]

The road traffic signs in Sweden have no inventory system and it is unknown when a sign has reached the end of its service life and needs to be replaced. As a result, the road authorities do not have a systematic maintenance program for road traffic signs, and many signs which are not in compliance with the minimum retroreflectivity performance requirements are still found on the roads. Therefore, it is very important to find an inexpensive, safe, easy, and highly accurate method to judge the retroreflectivity performance of road signs. This will enable maintenance staff to determine the retroreflectivity of road signs without requiring measuring instruments for retroreflectivity or colors performance. As a first step toward the above goal, this paper aims to identify factors affecting the retroreflectivity of road signs. Two different datasets were used, namely, the VTI dataset from Sweden and NMF dataset from Denmark. After testing different models, two logarithmic regression models were found to be the best-fitting models, with R2 values of 0.50 and 0.95 for the VTI and NMF datasets, respectively. The first model identified the age, direction, GPS positions, color, and class of road signs as significant predictors, while the second model used age, color, and the class of road signs. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords
Linear regression, Retroreflective sheeting material, Road traffic sign
National Category
Computer Systems Signal Processing Infrastructure Engineering
Identifiers
urn:nbn:se:du-39844 (URN)10.3390/app12052413 (DOI)000926968600001 ()2-s2.0-85125768375 (Scopus ID)
Available from: 2022-03-14 Created: 2022-03-14 Last updated: 2023-04-14Bibliographically approved
Johansson-Pajala, R.-M., Alam, M., Gusdal, A., Heideken Wågert, P. v., Löwenmark, A., Boström, A.-M. & Marmstål Hammar, L. (2022). Anxiety and loneliness among older people living in residential care facilities or receiving home care services in Sweden during the COVID-19 pandemic: a national cross-sectional study. BMC Geriatrics, 22(1), Article ID 927.
Open this publication in new window or tab >>Anxiety and loneliness among older people living in residential care facilities or receiving home care services in Sweden during the COVID-19 pandemic: a national cross-sectional study
Show others...
2022 (English)In: BMC Geriatrics, ISSN 1471-2318, E-ISSN 1471-2318, Vol. 22, no 1, article id 927Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: Older people were subjected to significant restrictions on physical contacts with others during the COVID-19 pandemic. Social distancing impacts older people's experiences of anxiety and loneliness. Despite a large body of research on the pandemic, there is little research on its effects on older people in residential care facilities (RCF) and in home care services (HCS), who are the frailest of the older population. We aimed to investigate the effect of the first wave of the COVID-19 pandemic in March-May 2020 on experiences of anxiety and loneliness among older people living in RCF or receiving HCS and the impact of the progression of the pandemic on these experiences.

METHODS: A retrospective cross-sectional design using data from the national user satisfaction survey (March - May 2020) by the Swedish National Board of Health and Welfare. Survey responses were retrieved from 27,872 older people in RCF (mean age 87 years) and 82,834 older people receiving HCS (mean age 84 years). Proportional-odds (cumulative logit) model was used to estimate the degree of association between dependent and independent variables.

RESULTS: Loneliness and anxiety were more prevalent among the older persons living in RCF (loneliness: 69%, anxiety: 63%) than those receiving HCS (53% and 47%, respectively). Proportional odds models revealed that among the RCF and HCS respondents, the cumulative odds ratio of experiencing higher degree of anxiety increased by 1.06% and 1.04%, respectively, and loneliness by 1.13% and 1.16%, respectively, for 1% increase in the COVID-19 infection rate. Poor self-rated health was the most influential factor for anxiety in both RCF and HCS. Living alone (with HCS) was the most influential factor affecting loneliness. Experiences of disrespect from staff were more strongly associated with anxiety and loneliness in RCF than in HCS.

CONCLUSION: Older people in RCF or receiving HCS experienced increasing levels of anxiety and loneliness as the first wave of the pandemic progressed. Older people' mental and social wellbeing should be recognized to a greater extent, such as by providing opportunities for social activities. Better preparedness for future similar events is needed, where restrictions on social interaction are balanced against the public health directives.

Keywords
Aged, COVID-19, Community health services, Emotions, Residential facilities, Social isolation
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:du-43914 (URN)10.1186/s12877-022-03544-z (DOI)000914898600001 ()36456904 (PubMedID)2-s2.0-85143163763 (Scopus ID)
Available from: 2022-12-06 Created: 2022-12-06 Last updated: 2023-03-17Bibliographically approved
Borg, J., Alam, M., Boström, A.-M. & Marmstål Hammar, L. (2022). Experiences of Assistive Products and Home Care among Older Clients with and without Dementia in Sweden. International Journal of Environmental Research and Public Health, 19(19), Article ID 12350.
Open this publication in new window or tab >>Experiences of Assistive Products and Home Care among Older Clients with and without Dementia in Sweden
2022 (English)In: International Journal of Environmental Research and Public Health, ISSN 1661-7827, E-ISSN 1660-4601, Vol. 19, no 19, article id 12350Article in journal (Refereed) Published
Abstract [en]

The purpose was to compare selection, use and outcomes of assistive products among older home care clients with and without dementia in Sweden, and to explore the relations between the use of assistive products and perceptions of home care, loneliness and safety. Self-reported data from 89,811 home care clients aged 65 years or more, of whom 8.9% had dementia, were analysed using regression models. Excluding spectacles, 88.2% of them used assistive products. Respondents without dementia were more likely to use at least one assistive product but less likely to use assistive products for remembering. Respondents with dementia participated less in the selection of assistive products, used less assistive products, and benefited less from them. Users of assistive products were more likely to be anxious and bothered by loneliness, to feel unsafe at home with home care, to experience that their opinions and wishes regarding assistance were disregarded by home care personnel, and to be treated worse by home care personnel. The findings raise concerns about whether the needs for assistive products among home care clients with dementia are adequately provided for. They also indicate a need to strengthen a person-centred approach to providing home care to users of assistive products.

Keywords
Sweden, assistive products, assistive technology, dementia, home care, home care services, older adults
National Category
Health Sciences
Identifiers
urn:nbn:se:du-42859 (URN)10.3390/ijerph191912350 (DOI)000868127300001 ()36231646 (PubMedID)2-s2.0-85139937007 (Scopus ID)
Available from: 2022-10-19 Created: 2022-10-19 Last updated: 2023-03-17
Roos, C., Alam, M., Swall, A., Boström, A.-M. & Marmstål Hammar, L. (2022). Factors associated with older persons’ perceptions of dignity and well-being over a three-year period: A retrospective national study in residential care facilities. BMC Geriatrics, 22(1), Article ID 515.
Open this publication in new window or tab >>Factors associated with older persons’ perceptions of dignity and well-being over a three-year period: A retrospective national study in residential care facilities
Show others...
2022 (English)In: BMC Geriatrics, ISSN 1471-2318, E-ISSN 1471-2318, Vol. 22, no 1, article id 515Article in journal (Refereed) Published
Abstract [en]

Background: Dignity and well-being are central concepts in the care of older people, 65 years and older, world‑wide. The person-centred practice framework identifes dignity and well-being as person-centred outcomes. Older persons living in residential care facilities, residents, have described that they sometimes lack a sense of dignity and well-being, and there is a need to understand which modifable factors to target to improve this. The aim of this study was to examine the associations between perceptions of dignity and wellbeing and the independent variables of the attitudes of staf, the indoor-outdoor-mealtime environments, and individual factors for residents over a three-year period.

Methods: A national retrospective longitudinal mixed cohort study was conducted in all residential care facilities within 290 municipalities in Sweden. All residents aged 65 years and older in 2016, 2017 and 2018 were invited to responded to a survey; including questions regarding self-rated health and mobility, the attitudes of staf, the indooroutdoor-mealtime environments, safety, and social activities. Data regarding age, sex and diagnosed dementia/pre‑scribed medication for dementia were collected from two national databases. Descriptive statistics and ordinal logistic regression models were used to analyse the data.

Results: A total of 13 763 (2016), 13 251 (2017) and 12 620 (2018) residents answered the survey. Most of them (69%) were women and the median age was 88 years. The odds for satisfaction with dignity did not difer over the three-year period, but the odds for satisfaction with well-being decreased over time. Residents who rated their health as good, who were not diagnosed with dementia/had no prescribed medication for dementia, who had not experienced disrespectful attitudes of staf and who found the indoor-outdoor-mealtime environments to be pleasant had higher odds of being satisfed with aspects of dignity and well-being over the three-year period.

Conclusions: The person-centred practice framework, which targets the attitudes of staf and the care environment, can be used as a theoretical framework when designing improvement strategies to promote dignity and well-being. Registered nurses, due to their core competencies, focusing on person-centred care and quality improvement work, should be given an active role as facilitators in such improvement strategies.

Keywords
Dignity, Long‑term care, Older persons, Person‑centred care, Person‑centred practice framework, Residential care facilities, Well‑being
National Category
Nursing
Identifiers
urn:nbn:se:du-41706 (URN)10.1186/s12877-022-03205-1 (DOI)000815083800002 ()35739497 (PubMedID)2-s2.0-85132572700 (Scopus ID)
Funder
Dalarna University
Available from: 2022-06-23 Created: 2022-06-23 Last updated: 2023-03-17Bibliographically approved
Roos, C., Alam, M., Swall, A., Boström, A. & Marmstål Hammar, L. (2022). Factors associated with perceptions of dignity and well‐being among older people living in residential care facilities in Sweden. A national cross‐sectional study. Health & Social Care in the Community, 30(5), e2350-e2364
Open this publication in new window or tab >>Factors associated with perceptions of dignity and well‐being among older people living in residential care facilities in Sweden. A national cross‐sectional study
Show others...
2022 (English)In: Health & Social Care in the Community, ISSN 0966-0410, E-ISSN 1365-2524, Vol. 30, no 5, p. e2350-e2364Article in journal (Refereed) Published
Abstract [en]

The care of older people living in residential care facilities (RCFs) should promote dignity and well-being, but research shows that these aspects are lacking in such facilities. To promote dignity and well-being, it is important to understand which associated factors to target. The aim of this study was to examine the associations between perceived dignity and well-being and factors related to the attitudes of staff, the care environment and individual issues among older people living in RCFs. A national retrospective cross-sectional study was conducted in all RCFs for older people within 290 municipalities in Sweden. All older people 65 years and older (n = 71,696) living in RCFs in 2018 were invited to respond to the survey. The response rate was 49%. The survey included the following areas: self-rated health, indoor-outdoor-mealtime environment, performance of care, attitudes of staff, safety, social activities, availability of staff and care in its entirety. Data were supplemented with additional data from two national databases regarding age, sex and diagnosed dementia. Descriptive statistics and ordinal logistic regression models were used to analyse the data. Respondents who had experienced disrespectful treatment, those who did not thrive in the indoor-outdoor-mealtime environment, those who rated their health as poor and those with dementia had higher odds of being dissatisfied with dignity and well-being. To promote dignity and well-being, there is a need to improve the prerequisites of staff regarding respectful attitudes and to improve the care environment. The person-centred practice framework can be used as a theoretical framework for improvements, as it targets the prerequisites of staff and the care environment. As dignity and well-being are central values in the care of older people worldwide, the results of this study can be generalised to other care settings for older people in countries outside of Sweden.

Keywords
care environment; dignity; older people; person-centred care; person-centred practice framework; residential care facility; well-being
National Category
Health Care Service and Management, Health Policy and Services and Health Economy
Identifiers
urn:nbn:se:du-39056 (URN)10.1111/hsc.13674 (DOI)000727785800001 ()34877717 (PubMedID)2-s2.0-85120697563 (Scopus ID)
Available from: 2021-12-15 Created: 2021-12-15 Last updated: 2023-03-17Bibliographically approved
Saeed, N., Nyberg, R. G. & Alam, M. (2022). Gravel road classification based on loose gravel using transfer learning. The international journal of pavement engineering, 1-8
Open this publication in new window or tab >>Gravel road classification based on loose gravel using transfer learning
2022 (English)In: The international journal of pavement engineering, ISSN 1029-8436, E-ISSN 1477-268X, p. 1-8Article in journal (Refereed) Epub ahead of print
Abstract [en]

Road maintenance agencies subjectively assess loose gravel as one of the parameters for determininggravel road conditions. This study aims to evaluate the performance of deep learning-based pretrainednetworks in rating gravel road images according to classical methods as done by humanexperts. The dataset consists of images of gravel roads extracted from self-recorded videos andimages extracted from Google Street View. The images were labelled manually, referring to thestandard images as ground truth defined by the Road Maintenance Agency in Sweden (Trafikverket).The dataset was then partitioned in a ratio of 60:40 for training and testing. Various pre-trainedmodels for computer vision tasks, namely Resnet18, Resnet50, Alexnet, DenseNet121, DenseNet201,and VGG-16, were used in the present study. The last few layers of these models were replaced toaccommodate new image categories for our application. All the models performed well, with anaccuracy of over 92%. The results reveal that the pre-trained VGG-16 with transfer learning exhibitedthe best performance in terms of accuracy and F1-score compared to other proposed models.

Place, publisher, year, edition, pages
Taylor & Francis, 2022
Keywords
Convolutional neural networks; transfer learning; deep learning; loose gravel; gravel road maintenance; road condition assessment
National Category
Other Civil Engineering
Identifiers
urn:nbn:se:du-43181 (URN)10.1080/10298436.2022.2138879 (DOI)000882702900001 ()2-s2.0-85141687244 (Scopus ID)
Available from: 2022-11-13 Created: 2022-11-13 Last updated: 2024-01-30
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-3183-3756

Search in DiVA

Show all publications