| 1. |
- Ahmed, Mobyen Uddin, Dr, 1976-, et al.
(författare)
-
A Machine Learning Approach to Classify Pedestrians’ Event based on IMU and GPS
- 2019
-
Ingår i: International Conference on Modern Intelligent Systems Concepts MISC'18. - : CESER Publications. ; 17:2, s. 154-167
-
Konferensbidrag (refereegranskat)abstract
- This paper investigates and implements six Machine Learning (ML) algorithms, i.e. Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Extra Tree (ET), and Gradient Boosted Trees (GBT) to classify different Pedestrians’ events based on Inertial Measurement Unit (IMU) and Global Positioning System (GPS) signals. Pedestrians’ events are pedestrian movements as the first step of H2020 project called SimuSafe1 with a goal to reduce traffic fatalities by doing risk assessments of the pedestrians. The movements the MLs’ models are attempting to classify are standing, walking, and running. Data, i.e. IMU, GPS sensor signals and other contextual information are collected by a smartphone through a controlled procedure. The smartphone is placed in five different positions onto the body of participants, i.e. arm, chest, ear, hand and pocket. The recordings are filtered, trimmed, and labeled. Next, samples are generated from small overlapping sections from which time and frequency domain features are extracted. Three different experiments are conducted to evaluate the performances in term of accuracy of the MLs’ models in different circumstances. The best performing MLs’ models determined by the average accuracy across all experiments is Extra Tree (ET) with a classification accuracy of 91%.
|
|
| 2. |
- Fasth, Jonas, et al.
(författare)
-
Small and medium-sized enterprises response to Covid-19: The effect of external openness and procedural management
- 2023
-
Ingår i: International Small Business Journal: Researching Entrepreneurship. - : SAGE Publications. - 0266-2426 .- 1741-2870. ; 41:5, s. 465-487
-
Tidskriftsartikel (refereegranskat)abstract
- Crisis management research is strongly influenced by the behaviour of large multinationals with few insights into how small and medium sized enterprises (SMEs) mitigate the negative effects of exogenous shocks such as the Covid-19 pandemic. Inspired by the capability-based view on crisis management, we postulate that management openness and degree of interactivity determine SME crisis response. We test our theoretical model with an original dataset of 902 Swedish SMEs compiled from a telephone-based survey conducted in June 2020. We find that formalised procedures for crisis management and openness to input from others, particularly external actors, enhances an organisation’s ability to make a decisive rapid response. We discuss our findings and suggest that formalised procedures and openness are important components of an SME’s rapid response capability.
|
|
| 3. |
- Palmqvist, Anna, et al.
(författare)
-
Concepts for Digitalisation of Assembly Instructions for Short Takt Times
- 2021
-
Ingår i: Procedia CIRP. - : Elsevier BV. - 2212-8271. ; 97, s. 154-159
-
Konferensbidrag (refereegranskat)abstract
- Operational complexity for shop-floor operators can be reduced with eective presentation of instructions, which in turn improves product quality. While this has been researched for longer takt times, final assembly with shorter takt times requires new approaches to properly support operators. Hence, this paper aims to present findings regarding concepts for digitalised assembly instructions to support shop-floor operators in a mixed model final assembly with shorter takt times. A bottom-up mixed-methods approach was applied in an iterative development process, resulting in concepts for short takt time instructions. The findings indicate how to cognitively support operators in two situations. First, work tasks are preferably taught beforehand, with educational instructions. Second, operators should be supported with simplified instructions, presenting key elements and deviations in real-time. Conclusively, these concepts will increase the likelihood of the instruction to be used by operators, which enables standardised work and contributes to enhanced product quality.
|
|
