| 1. |
- Alsolai, Hadeel, et al.
(författare)
-
A Systematic Review of Literature on Automated Sleep Scoring
- 2022
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 10, s. 79419-79443
-
Forskningsöversikt (refereegranskat)abstract
- Sleep is a period of rest that is essential for functional learning ability, mental health, and even the performance of normal activities. Insomnia, sleep apnea, and restless legs are all examples of sleep-related issues that are growing more widespread. When appropriately analyzed, the recording of bio-electric signals, such as the Electroencephalogram, can tell how well we sleep. Improved analyses are possible due to recent improvements in machine learning and feature extraction, and they are commonly referred to as automatic sleep analysis to distinguish them from sleep data analysis by a human sleep expert. This study outlines a Systematic Literature Review and the results it provided to assess the present state-of-the-art in automatic analysis of sleep data. A search string was organized according to the PICO (Population, Intervention, Comparison, and Outcome) strategy in order to determine what machine learning and feature extraction approaches are used to generate an Automatic Sleep Scoring System. The American Academy of Sleep Medicine and Rechtschaffen & Kales are the two main scoring standards used in contemporary research, according to the report. Other types of sensors, such as Electrooculography, are employed in addition to Electroencephalography to automatically score sleep. Furthermore, the existing research on parameter tuning for machine learning models that was examined proved to be incomplete. Based on our findings, different sleep scoring standards, as well as numerous feature extraction and machine learning algorithms with parameter tuning, have a high potential for developing a reliable and robust automatic sleep scoring system for supporting physicians. In the context of the sleep scoring problem, there are evident gaps that need to be investigated in terms of automatic feature engineering techniques and parameter tuning in machine learning algorithms.
|
|
| 2. |
- Alsolai, Hadeel, et al.
(författare)
-
Employing a Long-Short-Term Memory Neural Network to Improve Automatic Sleep Stage Classification of Pharmaco-EEG Profiles
- 2022
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 12:10
-
Tidskriftsartikel (refereegranskat)abstract
- An increasing problem in today's society is the spiraling number of people suffering from various sleep disorders. The research results presented in this paper support the use of a novel method that employs techniques from the classification of sleep disorders for more accurate scoring. Applying this novel method will assist researchers with better analyzing subject profiles for recommending prescriptions or to alleviate sleep disorders. In biomedical research, the use of animal models is required to experimentally test the safety and efficacy of a drug in the pre-clinical stage. We have developed a novel LSTM Recurrent Neural Network to process Pharmaco-EEG Profiles of rats to automatically score their sleep-wake stages. The results indicate improvements over the current methods; for the case of combined channels, the model accuracy improved by 1% and 3% in binary or multiclass classifications, respectively, to accuracies of 93% and 82%. In the case of using a single channel, binary and multiclass LSTM models for identifying rodent sleep stages using single or multiple electrode positions for binary or multiclass problems have not been evaluated in prior literature. The results reveal that single or combined channels, and binary or multiclass classification tasks, can be applied in the automatic sleep scoring of rodents.
|
|
| 3. |
- Gerlitz, Laima, et al.
(författare)
-
Sourcing Sustainability Transition in Small and Medium-Sized Ports of the Baltic Sea Region : A Case of Sustainable Futuring with Living Labs
- 2024
-
Ingår i: Sustainability. - : MDPI. - 2071-1050. ; 16:11
-
Tidskriftsartikel (refereegranskat)abstract
- The present research points to an alternative concern against the mainstream research of future ports’ development by taking a transdisciplinary approach of a Living Lab (LL) concept for a better sustainability and innovation record in Small and Medium-Sized Ports (SMSPs). Deploying qualitative research for the examination of this new phenomenon of aggregating LLs into SMSPs, this research builds upon stakeholder workshops, in-depth interviews, and designed port pilots as case studies dedicated to innovation and sustainability transition in the Baltic Sea Region (BSR) at the turn of 2030. Given its rich and significant empirical foundation, the present research substantially contributes to sustainability orientation and transitions in ports. The key original elements of this study are fourfold: (1) the research provides a theoretical and practical LL framework enabling innovation and sustainability to be grasped in ports in times of technological, social, and political disruption; (2) this research increases the minimal number of existing previous efforts studying SMSPs in the transitional discourse; (3) the paper addresses not only hard technological innovation concerns but also aspects of social acceptance and the role of social interactions; (4) the research goes beyond geographical boundaries of a single port, thus providing a joint and collaborative approach towards sustainability rather than an individual perception on sustainability transition, existing networks, and clusters. © 2024 by the authors.
|
|
| 4. |
- Henesey, Lawrence, et al.
(författare)
-
Improved load planning of RoRo vessels by adopting blockchain and internet-of-things
- 2020
-
Ingår i: 22nd International Conference on Harbor, Maritime and Multimodal Logistics Modelling and Simulation, HMS 2020. - : Dime University of Genoa. - 9788885741478 ; , s. 58-65
-
Konferensbidrag (refereegranskat)abstract
- Ports are vital to the global economy, as up to 90% of goods are transferred through seaports. With increasing vessel sizes, cargo volumes and higher demand for supply-chain optimization, seaports are required to be more efficient and competitive. In the present study, a proposed solution incorporating IoT and Blockchain is considered into automating many of the activities in the load planning process, which is then evaluated via simulation. Real data is collected concerning different types of cargo for RoPax vessels with the intended goal of reducing planning time in a seaport. The results contribute as one piece of the mosaic on the avenue towards becoming a “Smart Port”, which deploys various digitalization technologies in order to become a fully automated port. The suggested approach to be integrated, builds upon IoT sensors in combination with the lightweight version of a Blockchain to improve balance indicators on a trim of a vessel. A developed simulation tool was used for evaluating a number of scenarios, with each scenario run set to 2500 times. The simulation results indicate an improvement of 50-160% from the current load planning operations for RoPax vessels. © 2020 The Authors.
|
|
| 5. |
- Henesey, Lawrence, et al.
(författare)
-
Smart Container Stacking in the Yard
- 2021
-
Ingår i: International Conference on Harbour, Maritime and Multimodal Logistics Modelling and Simulation. - : CAL-TEK. - 9788885741591 ; , s. 37-44
-
Konferensbidrag (refereegranskat)abstract
- The workloads at seaport container terminals are increasing; thus, to enhance performance, the focus on improving container stacking is argued to be an integral factor that should be studied. The main problem is the number of unproductive moves of handling containers. A well-planned stacking area is argued to be a key requirement in order to increase the performance of the terminal operations and assist in maximum utilization of existing resources. In this work, we investigated and then propose the best possible solution by evaluating GAs in order to minimize the unproductive moves often witnessed in terminal operations. A discrete-event simulation CSS model has been developed to study the inbound container stacking that considers in the model the following: the working of the yard crane, Automated Guided Vehicles, delivery trucks and obtain the simulation-based results of GA. We propose a mathematical model to minimize the container handling costs during stacking and retrieval operations in the container terminal yard. © 2021 The Authors.
|
|
| 6. |
- Martin Sagayam, K., et al.
(författare)
-
Augmented reality-based solar system for e-magazine with 3-D audio effect
- 2020
-
Ingår i: International Journal of Simulation and Process Modelling. - : Inderscience Publishers. - 1740-2123 .- 1740-2131. ; 15:6, s. 524-534
-
Tidskriftsartikel (refereegranskat)abstract
- Augmented reality (AR) is the newest technology that can be applied to computer vision, audio, video and other sensor-based input projects into 3D vision. It is the backbone for all specialisation of science, medical and engineering concepts. Currently, the reading and learning method through AR-based approaches are quite highly intensive than the existing methods such as papers, books and magazines. This strategy is more expensive but it is more interactive to the user in understanding the root concepts in an effective manner. This paper explores the experiment on solar system revolution pattern along with 3D audio effect in spatial dimension. This novel idea inculcates more vibrancy in the current generation of students to understand the concepts with the clear illustrations and demonstrations. © 2020 Inderscience Enterprises Ltd.
|
|
| 7. |
- Meyer, Christopher, et al.
(författare)
-
Cross-Border Capacity-Building for Port Ecosystems in Small and Medium-Sized Baltic Ports
- 2021
-
Ingår i: Baltic Journal of European studies. - : De Gruyter Open. - 2228-0596 .- 2228-0588 .- 2674-4619. ; 11:1, s. 113-132
-
Tidskriftsartikel (refereegranskat)abstract
- One of the key challenges related to the threat posed by the COVID-19 pandemic is preservation of employment and protecting staff who are working in port operations and struggling to keep ports operating for ship calls. These activities performed by port labour are deemed to be crucial for the EU and European ports, since 75% of the EU external trade and 30% of intra-EU transport goods are moved by waterborne transport. As a response to the global lockdown and the vulnerability of global supply chains, the majority of international organisations and maritime ports networks have shortlisted measures necessary to keep the severe effects of the lockdown to a minimum. One of the key measures identified is how to limit physical interaction. As an effect, millions of people and organisations across the globe have had to use and/or increase their deployment of digital technologies, such as digital documentation, tracing information systems and digital group-working platforms. Hence, blockchain and data-enabling systems have become to be recognised as a core element maintaining the uninterrupted flow of goods and services at ports. In pursuing uninterrupted trade and keeping ports open and running, this research paper addresses how the current situation afflicts the small and medium-sized ports located on the Baltic Sea which are argued to be critical actors of the port-centric logistics' ecosystem. Given the topicality of this research and addressing the research gap, the authors suggest a conceptual capacity-building framework for port employees. This suggested framework is based on empirical insights: primary and secondary data collected from the project Connect2SmallPorts, part-financed by the Interreg South Baltic Programme 2014-2020 from the European Regional Development Fund (ERDF). The conceptual framework aims towards a practical training programme dedicated to fill in the missing skills or expand the limited competence of human resources and ports' capacity when adapting or advancing digitalisation in the ports' ecosystems. In particular, specific areas of capacity building are addressed and individual solutions suggested to foster a digital transformation of ports. The conceptual training framework is designed as a training tool indicating opportunities to help ports upgrade their competences with the blockchain technology, and to advance their transportation, environmental and economic performance with improved digitalisation. For this purpose, the conducted research employed mixed methods and applied concepts and approaches based on the field of management. For example, the construct of absorptive capacity, organisational learning, transformation, resource-based view and the concept of dynamic capabilities are included in the ecosystem discourse and are linked with open innovation and service design. The research presented in this article provides both theoretical and practical contributions, in which the affected stakeholders can test and utilise the developed tool as well as transfer it to other regions. © 2021 Christopher Meyer et al., published by Sciendo 2021.
|
|
| 8. |
- Mhathesh, T. S. R., et al.
(författare)
-
A 3d convolutional neural network for bacterial image classification
- 2021
-
Ingår i: Advances in Intelligent Systems and Computing. - Singapore : Springer. - 9789811552847 ; , s. 419-431
-
Konferensbidrag (refereegranskat)abstract
- Identification and analysis of biological microscopy images need high focus and years of experience to master the art. The rise of deep neural networks enables analyst to achieve the desired results with reduced time and cost. Light sheet fluorescence microscopies are one of the types of 3D microcopy images. Processing microscopy images is tedious process as it consists of low-level features. It is necessary to use proper image processing techniques to extract the low-level features of the biological microscopy images. Deep neural networks (DNN) are efficient in extracting the features of images and able to classify with high accuracy. Convolutional neural networks (CNN) are one of the types of neural networks that can provide promising results with less error rates. The ability of CNN to extract the low-level features of images makes it popular for image classification. In this paper, a CNN-based 3D bacterial image classification is proposed. 3D images contain more in-depth features than 2D images. The proposed CNN model is trained on 3D light sheet fluorescence microscopy images of larval zebrafish. The proposed CNN model classifies the bacterial and non-bacterial images effectively. Intense experimental analyses are carried out to find the optimal complexity and to get better classification accuracy. The proposed model provides better results than human comprehension and other traditional machine learning approaches like random forest, support vector classifier, etc. The details of network architecture, regularization, and hyperparameter optimization techniques are also presented. © Springer Nature Singapore Pte Ltd 2021.
|
|
| 9. |
- Paulauskas, Vytautas, et al.
(författare)
-
Optimizing transportation between ports and the hinterland for decreasing impact to the environment
- 2022
-
Ingår i: International Conference on Harbour, Maritime and Multimodal Logistics Modelling and Simulation. - : CAL-TEK. - 2724-0339. - 9788885741744 ; , s. 1-14
-
Konferensbidrag (refereegranskat)abstract
- Today different transport modes use to deliver cargo between regions, from ports to final destination location or visa-versa. It is quite common to use road transport, which can deliver cargo “from door to door” but road transport causes big environmental impact. Considering alternative possibilities (road, railway and/or inland waterway transport) to decrease environmental impact from transport, it is very important. Based on theoretical and experimental tests, were find optimal solutions, which transport mode make minimum environmental impact and could be the most technically and economically effective solution. Traffic congestion on the roads, in some cases very high railway traffic in some regions, generates requirements by many stakeholders on ways to decrease the environmental impact from transport modes, which studded in Article to find and identify optimal transportation solutions with minimum environmental impact. A theoretical method evaluation conducted on the optimal transportation possibility that minimizes environmental impact. A transport modes environmental comparative index (ECI) is developed and used for evaluations. This paper presents possible alternative transportation conditions based on multi-criteria evaluation system, proposes theoretical basis for the optimal solutions from environmental and economic point of view, and provides for experimental testing during the specific case study, and finally provides recommendations and conclusions. © 2022 The Authors.
|
|
| 10. |
- Paulauskas, Vytautas, et al.
(författare)
-
Optimizing Transportation between Sea Ports and Regions by Road Transport and Rail and Inland Waterway Transport Means Including “Last Mile” Solutions
- 2022
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 12:20
-
Tidskriftsartikel (refereegranskat)abstract
- Optimization transportation cargo and passengers between ports and regions are very important, because industrial regions are located some distance from ports. The demand for energy request for the movement of transport is a necessity in the modern world. Transport and activity called transportation are used daily, everywhere, and a lot of energy is needed to power the various transport modes. Today different transport modes are being used to transport passengers and cargo. It is quite common to use road transport, which can transport passengers and cargo from door to door. Considering alternative possibilities (road, railway and/or inland waterway transport), it is important, based on theoretical and experimentation, to identify optimal solutions. In finding transport modes that are either most technically or economically effective, we could unearth possible solutions which would require minimal energy use. Unfortunately, with increased transportation, this often leads to traffic congestion on the roads, which requires additional energy (fuel). This situation generates requirements from many stakeholders in terms of finding ways to decrease the transportation time and energy (fuel) consumed by transport modes. A theoretical method evaluation is conducted on the optimal transportation possibility that minimizes transportation time and energy (fuel) use by employing graph theory, which is presented in this paper. The scientific contribution is the development of a transport modes comparative index, which is then used for evaluations. This paper presents possible alternative transportation conditions based on a multi-criteria evaluation system, proposes a theoretical basis for the optimal solutions from an eco-economic perspective that considers energy, and provides for experimental testing during a specific case study. The final results from the case study provide recommendations and conclusions. © 2022 by the authors.
|
|
