• Transport Research
• Publications close
• SE close

This study investigates the combination of audio and image data to classify road conditions, particularly focusing on loose gravel scenarios. The dataset underwent binary categorisation, comprising audio segments capturing gravel sounds and corresponding images. Early feature fusion, utilising a pre-trained Very Deep Convolutional Networks 19 (VGG19) and Principal component analysis (PCA), improved the accuracy of the Random Forest classifier, surpassing other models in accuracy, precision, recall, and F1-score. Late fusion, involving decision-level processing with logical disjunction and conjunction gates (AND and OR) in combination with individual classifiers 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 fusion method 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. This method can help to identify loose gravel on gravel roads, substantially improving road safety and implementing a precise maintenance strategy through a data-driven approach.

Renewable energy sources (RES) and electric vehicles (EVs) are two promising technologies that are widely recognized as key components for achieving sustainable cities. However, intermittent RES generation and increased peak load due to EV charging can pose technical challenges for the power systems. Many studies have shown that improved load matching through energy system optimization can minimize these challenges. This paper assesses the optimal urban-scale energy matching potentials in a net-zero energy city powered by wind and solar energy, considering three EV charging scenarios: opportunistic charging, smart charging, and vehicle-to-grid (V2G). This paper takes a city on the west coast of Sweden as a case study. The smart charging and V2G schemes in this study aim to minimize the mismatch between generation and load and are formulated as quadratic programming problems. Results show that the optimal load matching performance is achieved in a net-zero energy city with the V2G scheme and a wind-PV electricity production share of 70:30. The load matching performance is increased from 68% in the opportunistic charging scenario to 73% in the smart charging scenario and to 84% in the V2G scenario. It is also shown that a 2.4 GWh EV battery participating in the V2G scheme equals 1.4 GWh stationary energy storage in improving urban-scale load matching performance. The findings in this paper indicate a high potential from EV flexibility in improving urban energy system performance.  De två första författarna delar förstaförfattarskapet

Bundling of multiple access technologies is currently being standardized by 3GPP in the 5G access traffic steering, switching and splitting (ATSSS) framework, with the goal to increase robustness, resiliency and capacity of wireless access. A key part of an ATSSS framework is the packet scheduler, which decides the access network over which each packet is to be transmitted. As wireless channels are highly dynamic, a challenge for any scheduler is to correctly estimate the capacity of each path, and thereby avoid congesting the paths. In this paper, we further develop a recent packet scheduler that exploits cross-layer information from the congestion control state of individual transport layer tunnels when making scheduling decisions. Our aim is to achieve good path utilization while keeping the congestion delay low. Extensive emulations show that our approach reduces the excess delay at the bottleneck to as little as 34%. We furthermore show that our approach improves the performance of end-to-end applications including WebRTC and YouTube compared to state-of-the art. 

This study involved a survey of Swedish water utilities to evaluate their pipe-network data-collection objectives, usage, storage, and exchange routines. Factors impacting data integration (and the associated benefits) were also identified. Results showed that current data storage and exchange routines can be augmented to support commonly identified objectives and data utilisation needs, especially in larger water utilities. Levels of awareness of the opportunities for and benefits gained through asset management processes and data integration varied between utilities. Further research on the benefits of data integration in pipe network asset management is required to develop an evidence base on benefits accrued in practice, especially considering metadata, the diversity of legacy systems still in operation, costs and policy use. Validerad;2024;Nivå 2;2024-01-01 (hanlid);Full text license: CC BY Stormwater & Sewers

This study addresses the critical safety issue of declining retroreflectivity values of road traffic signs, which can lead to unsafe driving conditions, especially at night. The paper aims to predict the retroreflectivity coefficient values of these signs and to classify their status as acceptable or rejected (in need of replacement) using machine learning models. Moreover, logistic regression and survival analysis are used to predict the median lifespans of road traffic signs across various geographical locations, focusing on signs in Croatia and Sweden as case studies. The results indicate high accuracy in the predictive models, with classification accuracy at 94% and an R2 value of 94% for regression analysis. A significant finding is that a considerable number of signs maintain acceptable retroreflectivity levels within their warranty period, suggesting the feasibility of extending maintenance checks and warranty periods to 15 years which is longer than the current standard of 10 years. Additionally, the study reveals notable variations in the median lifespans of signs based on color and location. Blue signs in Croatia and Sweden exhibit the longest median lifespans (28 to 35 years), whereas white signs in Sweden and red signs in Croatia show the shortest (16 and 10 years, respectively). The high accuracy of logistic regression models (72–90%) for lifespan prediction confirms the effectiveness of this approach. These findings provide valuable insights for road authorities regarding the maintenance and management of road traffic signs, enhancing road safety standards. © 2024 Tongji University and Tongji University Press

Climate change impacts such as extreme temperatures, snow and ice, flooding, and sea level rise posed significant threats to railway infrastructure networks. One of the important questions that infrastructure managers need to answer is, “How will maintenance costs be affected due to climate change in different climate change scenarios?” This paper proposes an approach to estimate the implication of climate change on the life cycle cost (LCC) of railways infrastructure assets. The proportional hazard model is employed to capture the dynamic effects of climate change on reliability parameters and LCC of railway assets. A use-case from a railway in North Sweden is analyzed to validate the proposed process using data collected over 18 years. The results have shown that precipitation, temperature, and humidity are significant weather factors in selected use-case. Furthermore, our analyses show that LCC under future climate scenarios will be about 11 % higher than LCC without climate impacts. Funder: Vinnova (2019-03181, 2021-02456); Kempe foundation (JCK-3123); Järnvägstekniskt Centrum, Luleå Tekniska Universitet; Trafikverket; Kempe Foundation; Sveriges Meteorologiska och Hydrologiska Institut;Full text license: CC BY

The element silicon is everywhere! In fact, silicon is the second most abundant element in Earth’s crust. Silicon in rocks and minerals breaks down and is transported from rivers and streams into the world’s oceans. Many marine organisms need silicon as it is a crucial nutrient to build their skeletons. Silicon eventually reaches the seafloor, but its journey into the abyss is not straightforward due to biological, physical, and chemical processes. All these processes transport and transform silicon, creating a cycle that we call the marine silicon cycle. The silicon cycle is directly connected to the carbon cycle, making silicon a key player in the regulation of Earth’s climate. In this article, we discuss why we need to understand the marine silicon cycle, explain the steps that happen in the ocean, and demonstrate how the marine silicon cycle affects humans.

Silicon is a crucial nutrient that can join with the element oxygen to form a substance commonly called silica. Silica, commonly known as glass, is found in rocks in the Earth’s crust and dissolves into the oceans, where organisms like algae and sponges use it to build their glassy skeletons. This process, called biosilicification, is extremely important in the silica cycle. Over time, organisms have changed the silica cycle. Today, because of these organisms, the oceans no longer contain much silica. However, when the Earth was younger and these organisms had not evolved yet, no biological processes affected silica in the oceans. The evolution of these oceanic organisms across time has removed silica from the oceans. In this article, we discuss how the evolution of silicon-using sponges, as well as tiny organisms called zooplankton and algae, have changed the amount of silica in the world’s oceans through geologic time.