| 1. |
- Alawadi, Sadi, et al.
(författare)
-
A Federated Interactive Learning IoT-Based Health Monitoring Platform
- 2021
-
Ingår i: New Trends in Database and Information Systems. - Cham : Springer. ; , s. 235-246, s. 235-246
-
Konferensbidrag (refereegranskat)abstract
- Remote health monitoring is a trend for better health management which necessitates the need for secure monitoring and privacy-preservation of patient data. Moreover, accurate and continuous monitoring of personal health status may require expert validation in an active learning strategy. As a result, this paper proposes a Federated Interactive Learning IoT-based Health Monitoring Platform (FIL-IoT-HMP) which incorporates multi-expert feedback as ‘Human-in-the-loop’ in an active learning strategy in order to improve the clients’ Machine Learning (ML) models. The authors have proposed an architecture and conducted an experiment as a proof of concept. Federated learning approach has been preferred in this context given that it strengthens privacy by allowing the global model to be trained while sensitive data is retained at the local edge nodes. Also, each model’s accuracy is improved while privacy and security of data has been upheld.
|
|
| 2. |
|
|
| 3. |
- Ekblom Bak, Elin, 1981-, et al.
(författare)
-
Accelerometer derived physical activity patterns in 27.890 middle‐aged adults : The SCAPIS cohort study
- 2022
-
Ingår i: Scandinavian Journal of Medicine and Science in Sports. - : John Wiley & Sons. - 0905-7188 .- 1600-0838. ; 32:5, s. 866-880
-
Tidskriftsartikel (refereegranskat)abstract
- The present study aims to describe accelerometer-assessed physical activity (PA) patterns and fulfillment of PA recommendations in a large sample of middle-aged men and women, and to study differences between subgroups of socio-demographic, socio-economic, and lifestyle-related variables. A total of 27 890 (92.5% of total participants, 52% women, aged 50–64 years) middle-aged men and women with at least four days of valid hip-worn accelerometer data (Actigraph GT3X+, wGT3X+ and wGT3X-BT) from the Swedish CArdioPulmonary bioImage Study, SCAPIS, were included. In total, 54.5% of daily wear time was spent sedentary, 39.1% in low, 5.4% in moderate, and only 0.1% in vigorous PA. Male sex, higher education, low financial strain, born in Sweden, and sedentary/light working situation were related to higher sedentary time, but also higher levels of vigorous PA. High BMI and having multiple chronic diseases associated strongly with higher sedentary time and less time in all three PA intensities. All-year physically active commuters had an overall more active PA pattern. The proportion fulfilling current PA recommendations varied substantially (1.4% to 92.2%) depending on data handling procedures and definition used. Twenty-eight percent was defined as having an “at-risk” behavior, which included both high sedentary time and low vigorous PA. In this large population-based sample, a majority of time was spent sedentary and only a fraction in vigorous PA, with clinically important variations between subgroups. This study provides important reference material and emphasizes the importance of a comprehensive assessment of all aspects of the individual PA pattern in future research and clinical practice.
|
|
| 4. |
- Ericsson, Stefan, et al.
(författare)
-
Towards automatic detection of local bearing defects in rotating machines
- 2005
-
Ingår i: Mechanical systems and signal processing. - : Elsevier BV. - 0888-3270 .- 1096-1216. ; 19:3, s. 509-535
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we derive and compare several different vibration analysis techniques for automatic detection of local defects in bearings. Based on a signal model and a discussion on to what extent a good bearing monitoring method should trust it, we present several analysis tools for bearing condition monitoring and conclude that wavelets are especially well suited for this task. Then we describe a large-scale evaluation of several different automatic bearing monitoring methods using 103 laboratory and industrial environment test signals for which the true condition of the bearing is known from visual inspection. We describe the four best performing methods in detail (two wavelet-based, and two based on envelope and periodisation techniques). In our basic implementation, without using historical data or adapting the methods to (roughly) known machine or signal parameters, the four best methods had 9-13% error rate and are all good candidates for further fine-tuning and optimisation. Especially for the wavelet-based methods, there are several potentially performance improving additions, which we finally summarise into a guiding list of suggestion.
|
|
| 5. |
- Hamodi, Hussan
(författare)
-
Reliability and Life Cycle Cost Modelling of Mining Drilling Rigs
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In the context of mining, drilling is the process of making holes in the face and walls of underground mine rooms, to prepare those rooms for the subsequent operation, which is the charging process. Due to the nature of the task, drilling incurs a high number of drilling rig failures. Through a combination of a harsh environment (characterised by dust, high humidity, etc.), the operating context, and reliability and maintainability issues, drilling rigs are identified as a major contributor to unplanned downtime.The purpose of the research performed for this thesis has been to develop methods that can be used to identify the problems affecting drilling rig downtime and to identify the economic lifetime of drilling rigs. New models have been developed for calculating the optimum replacement time of drilling rigs. These models can also be used for other machines which have repairable or replaceable components. Based on an analysis performed in a case study, a life cycle cost (LCC) optimization model has been developed, taking the most important factors affecting the economic replacement time of drilling rigs into consideration. To this end, research literature studies, case studies, and simulation studies have been performed, interviews have been held, observations have been made and data have been collected. For the data analysis, theories and methodologies within reliability, maintainability, ergonomics and optimization have been combined with the best practices from the related industries.Firstly, this thesis analyses the downtime of the studied drilling rigs, with the precision and uncertainty of the estimation at a given confidence level, along with the factors influencing the failures. Secondly, the thesis identifies components that significantly contribute to the downtime and the reason for that downtime (maintainability and/or reliability problems). Based on the failure analysis, some minor suggestions have been made as to how to improve the critical components of the drilling rig. Thirdly, a new method is proposed that can help decision makers to identify the replacement time of reparable equipment from an economic point of view. Finally, the thesis proposes a method using the artificial neural network (ANN) for predicting the economic lifetime of drilling rigs through a series of basic weights and response functions. This ANN-based method can be made available to engineers without the use of complicated software.Most of the results are related to specific industrial and scientific challenges, such as planning for cost-effectiveness. The results of the case study are promising for the possibility of making a significant reduction in the LCC by optimizing the lifetime. The results have been verified through interaction with experienced practitioners from both the manufacturer and the mining company using the drilling rig in question.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Jouybari, Nima Fallah, et al.
(författare)
-
An investigation of forces on a representative surface in a pulp flow through rotating and non-rotating grooves
- 2023
-
Ingår i: Journal of the Brazilian Society of Mechanical Sciences and Engineering. - : Springer. - 1678-5878 .- 1806-3691. ; 45:5
-
Tidskriftsartikel (refereegranskat)abstract
- Softwood pulp flow in rotating and non-rotating grooves is numerically simulated in the present study to investigate the fluid flow and the forces acting on a representative surface mounted in the groove. The viscosity of softwood pulp with various consistencies is available from the measurements reported in the literature providing the opportunity to examine the effects of fiber consistency on the velocity and pressure distribution within the groove. The simulations are carried out in OpenFOAM for different values of gap thickness, angular velocity and radial positions from which the pressure coefficient and shear forces values are obtained. It is found that the shear forces within the gap increase linearly with the angular velocity for all fiber consistencies investigated and in both grooves. Also, this behavior can be successfully predicted by modeling the gap flow as a Couette flow in a two-dimensional channel. Meanwhile, a more detailed analysis of the flow kinetic energy close to the stagnation point using Bernoulli’s principle is carried out to provide a better understanding of the pressure coefficient variation with angular velocity in the non-rotating groove. A comparison of pressure coefficients obtained numerically with those calculated by considering the compression effects revealed that the comparison effects are dominating in the pulp flow within the groove.
|
|
| 9. |
- Kebande, Victor R., Dr, et al.
(författare)
-
Active Machine Learning Adversarial Attack Detection in the User Feedback Process
- 2021
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 9, s. 36908-36923
-
Tidskriftsartikel (refereegranskat)abstract
- Modern Information and Communication Technology (ICT)-based applications utilize current technological advancements for purposes of streaming data, as a way of adapting to the ever-changing technological landscape. Such efforts require providing accurate, meaningful, and trustworthy output from the streaming sensors particularly during dynamic virtual sensing. However, to ensure that the sensing ecosystem is devoid of any sensor threats or active attacks, it is paramount to implement secure real-time strategies. Fundamentally, real-time detection of adversarial attacks/instances during the User Feedback Process (UFP) is the key to forecasting potential attacks in active learning. Also, according to existing literature, there lacks a comprehensive study that has a focus on adversarial detection from an active machine learning perspective at the time of writing this paper. Therefore, the authors posit the importance of detecting adversarial attacks in active learning strategy. Attack in the context of this paper through a UFP-Threat driven model has been presented as any action that exerts an alteration to the learning system or data. To achieve this, the study employed ambient data collected from a smart environment human activity recognition from (Continuous Ambient Sensors Dataset, CASA) with fully labeled connections, where we intentionally subject the Dataset to wrong labels as a targeted/manipulative attack (by a malevolent labeler) in the UFP, with an assumption that the user-labels were connected to unique identities. While the dataset's focus is to classify tasks and predict activities, our study gives a focus on active adversarial strategies from an information security point of view. Furthermore, the strategies for modeling threats have been presented using the Meta Attack Language (MAL) compiler for purposes adversarial detection. The findings from the experiments conducted have shown that real-time adversarial identification and profiling during the UFP could significantly increase the accuracy during the learning process with a high degree of certainty and paves the way towards an automated adversarial detection and profiling approaches on the Internet of Cognitive Things (ICoT).
|
|
| 10. |
- Khan, Saad Ahmed, 1987-, et al.
(författare)
-
Prediction of the effects of friction control on top-of-rail cracks
- 2018
-
Ingår i: Proceedings of the Institution of mechanical engineers. Part F, journal of rail and rapid transit. - : Sage Publications. - 0954-4097 .- 2041-3017. ; 232:2, s. 484-494
-
Tidskriftsartikel (refereegranskat)abstract
- Rolling contact fatigue is a major problem connected with railway tracks, especially in curves, since it leads to highermaintenance costs. By optimising the top-of-rail friction, the wear and cracks on the top of the rail can eventually bereduced without causing very long braking distances. There are several research articles available on crack prediction,but most of the research is focused either on rail without a friction modifier or on wheels with and without frictioncontrol. In the present study, in order to predict the formation of surface-initiated rolling contact fatigue, a range offriction coefficients with different Kalker’s reduction factors has been assumed. Kalker’s reduction factor takes care ofthe basic tendency of creepage as a function of the traction forces at lower creepage. The assumed range covers possiblefriction values from those for non-lubricated rail to those for rail with a minimum measured friction control on the top ofthe rail using a friction modifier. A fatigue index model based on the shakedown theory was used to predict thegeneration of surface-initiated rolling contact fatigue. Simulations were performed using multi-body simulation, forwhich inputs were taken from the Iron Ore line in the north of Sweden. The effect of friction control was studiedfor different curve radii, ranging from 200 m to 3000 m, and for different axle loads from 30 to 40 tonnes at a constanttrain speed of 60 km/h. One example of a result is that a maximum friction coefficient (m) of 0.2 with a Kalker’s reductionfactor of 15% is needed in the case of trains with a heavy axle load to avoid crack formation.
|
|
