Chalmers Research
Not a member yet
88095 research outputs found
Sort by
A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
Get PDFWe propose a unified deep learning framework for the generation and analysis of driving scenario trajectories, and validate its effectiveness in a principled way. To model and generate scenarios of trajectories with different lengths, we develop two approaches. First, we adapt the Recurrent Conditional Generative Adversarial Networks (RC-GAN) by conditioning on the length of the trajectories. This provides us the flexibility to generate variable-length driving trajectories, a desirable feature for scenario test case generation in the verification of autonomous driving. Second, we develop an architecture based on Recurrent Autoencoder with GANs to obviate the variable length issue, wherein we train a GAN to learn/generate the latent representations of original trajectories. In this approach, we train an integrated feed-forward neural network to estimate the length of the trajectories to be able to bring them back from the latent space representation. In addition to trajectory generation, we employ the trained autoencoder as a feature extractor, for the purpose of clustering and anomaly detection, to obtain further insights into the collected scenario dataset. We experimentally investigate the performance of the proposed framework on real-world scenario trajectories obtained from in-field data collection
Ginsenoside Rg3 Reduces the Toxicity of Graphene Oxide Used for pH-Responsive Delivery of Doxorubicin to Liver and Breast Cancer Cells
Get PDFDoxorubicin (DOX) is extensively used in chemotherapy, but it has serious side effects and is inefficient against some cancers, e.g., hepatocarcinoma. To ameliorate the delivery of DOX and reduce its side effects, we designed a pH-responsive delivery system based on graphene oxide (GO) that is capable of a targeted drug release in the acidic tumor microenvironment. GO itself disrupted glutathione biosynthesis and induced reactive oxygen species (ROS) accumulation in human cells. It induced IL17-directed JAK-STAT signaling and VEGF gene expression, leading to increased cell proliferation as an unwanted effect. To counter this, GO was conjugated with the antioxidant, ginsenoside Rg3, prior to loading with DOX. The conjugation of Rg3 to GO significantly reduced the toxicity of the GO carrier by abolishing ROS production. Furthermore, treatment of cells with GO–Rg3 did not induce IL17-directed JAK-STAT signaling and VEGF gene expression—nor cell proliferation—suggesting GO–Rg3 as a promising drug carrier. The anticancer activity of GO–Rg3–DOX conjugates was investigated against Huh7 hepatocarcinoma and MDA-MB-231 breast cancer cells. GO–Rg3–DOX conjugates significantly reduced cancer cell viability, primarily via downregulation of transcription regulatory genes and upregulation of apoptosis genes. GO–Rg3 is an effective, biocompatible, and pH responsive DOX carrier with potential to improve chemotherapy—at least against liver and breast cancers
From the War in Ukraine to Cannabis Use: Exploring a Diverse Set of Papers
No full textThis edition of the "Practitioners\u27 Digest"covers an eclectic mix of topics from cannabis usage to world politics to large language models
Convergence of a robust deep FBSDE method for stochastic control
Get PDFIn this paper, we propose a deep learning based numerical scheme for strongly coupled FBSDEs, stemmingfrom stochastic control. It is a modification of the deep BSDE method in which the initial value to thebackward equation is not a free parameter, and with a new loss function being the weighted sum of the costof the control problem, and a variance term which coincides with the mean squared error in the terminalcondition. We show by a numerical example that a direct extension of the classical deep BSDE methodto FBSDEs, fails for a simple linear-quadratic control problem, and motivate why the new method works.Under regularity and boundedness assumptions on the exact controls of time continuous and time discretecontrol problems, we provide an error analysis for our method. We show empirically that the methodconverges for three different problems, one being the one that failed for a direct extension of the deep BSDEmethod
Voltage-based Current Limitation Strategy to Preserve Grid-forming Properties Under Severe Grid Disturbances
No full textGrid-forming (GFM) converters are a promising solution to enable large scale integration of renewable energy sources into the power system. However, due to the intrinsic voltage-source behaviour of GFM converters, current limitation during large grid disturbances is challenging. This paper presents a novel limitation strategy that preserves the GFM properties of the converter and at the same time effectively limits the converter current to the desired value. Through the limitation of the converter\u27s internal voltage, stable operation even during faults and in case of large frequency disturbances in the grid is achieved. Experimental results show the effectiveness of the proposed current limitation strategy in case of various grid disturbances
Characterization from Diesel and Renewable Fuel Engine Exhaust: Particulate Size/Mass Distributions and Optical Properties
Get PDFCombustion of fossil fuel produces emissions and is one of the major environmental problems leading to climate change. Diesel engines are highly efficient but produce particulate emissions. These particulate emissions are considered dangerous to human health because inhaling particulates may cause respiratory and heart disease. Substituting fossil diesel fuel with renewable diesel fuel and using diesel particulate filters is one possibility to meet stringent legislative requirements. With this motivation, the present experimental investigation aimed to evaluate the particle size distribution (PSD), optical properties of particulate matter (PM) emitted, and the outcome of using an after-treatment system comprising of a diesel particle filter (DPF). This investigation aimed to make a comparative analysis of particulate emission upstream and downstream of the DPF with and without ultraviolet (UV) light (405\ua0nm and 781\ua0nm wavelength) turned on/off. Experiments were performed at (a) engine idle with a torque of 6 Nm at 750\ua0rpm, IMEP of 1.35\ua0bar and power of 0.5\ua0kW, (b) engine at part load with a torque of 32 Nm at 1200\ua0rpm, IMEP of 8.5\ua0bar and power of 4.5\ua0kW. Diesel engine was operated on two fuels (a) Diesel and (b) EHR7. Results showed that as and when UV light was turned on, a distinct nucleation mode that dominated the number concentration for both test fuels were observed. Downstream of the filter had relatively higher AAE values which show the contribution to climate change. Present experimental research is important for renewable fuel industries, industrial innovation\u27s future, and the exhaust gas after-treatment system (EATS) community. The results contribute to knowledge for occupational exposure, human health, and the environment
Deuterium-enriched water ties planet-forming disks to comets and protostars
No full textWater is a fundamental molecule in the star and planet formation process, essential for catalysing the growth of solid material and the formation of planetesimals within disks1,2. However, the water snowline and the HDO:H2O ratio within proto-planetary disks have not been well\ua0characterized because water only sublimates at roughly 160 K (ref. 3), meaning that most water is frozen out onto dust grains and\ua0that the water snowline radii are less than 10 AU (astronomical units)4,5. The sun-like protostar V883 Ori (M* = 1.3 M⊙)6 is undergoing an accretion burst7, increasing its luminosity to roughly 200 L⊙ (ref. 8), and previous observations suggested that its water snowline is 40-120 AU in radius6,9,10. Here we report the direct detection of gas phase water (HDO and [Formula: see text]) from the disk of V883 Ori. We measure a midplane water snowline radius of approximately 80 AU, comparable to the scale of the Kuiper Belt, and detect\ua0water out to a radius of roughly 160 AU. We then measure the HDO:H2O ratio of the disk to be (2.26 \ub1 0.63)
7 10-3. This ratio is comparable to those\ua0of\ua0protostellar envelopes and comets, and exceeds that of Earth\u27s oceans by 3.1σ. We conclude that disks directly inherit water from the star-forming cloud and this water becomes incorporated into large icy bodies, such as comets, without substantial chemical alteration
Bicycle safety outside the crosswalks: Investigating cyclists\u27 risky street-crossing behavior and its relationship with built environment
No full textMost bicycle accidents are inextricably bound up with risky riding behaviors, which crossing the street illegally at unprotected mid-block locations is nothing to sneeze at. Compared with cyclists crossing the street at the crosswalk or intersections, there is a huge risk of accidents when they ignore or disobey road rules and across recklessly. Yet, the misbehavior of cyclists is an under-explored area in cyclist research due to the limited availability of detailed cycling data. This study creatively develops a GPS-based detection framework to capture risky street-crossing actions for the cyclists from large-scale bike sharing trajectory data. A data-driven modeling approach, based on structural topic modeling (STM), is developed to reveal the complexity and regularity of cyclists\u27 habitual risky crossing behavior. Since objective built environment is one of the key factors associated with cycling, another goal of this paper is to apply a gradient boosting decision tree (GBDT) model to disentangle how the features of built environment may influence the frequency of risky crossing events. The case study results show that risky street-crossing behavior is prevalent in bicycle traffic – for example, 16.94% of cycling trips are involved in illegal crossing action. Most cyclists engage in illegal crossing behavior at the approximate central part of the streets and during the day, which reveals the presence of heterogeneity over space and time. Strong correlations between commuting activities and risky street-crossing behaviors are identified from topic modeling. Meanwhile, the latent illegal crossing patterns unraveled here highlight that typical reasons for committing the risky riding action include the lure of the travel destination across the road and the inconvenience of riding round in distant legal crossing facilities. GBDT findings provide new insights on the existence of the association between built environment and cyclists\u27 illegal crossing action. The places related employment and catering play a dominant role in contributing risky street-crossing behavior, and the influences of road length, road level, bus stop and metro station are not neglectable. Most built environment attributes show nonlinear correlations with crossing frequency. It is anticipated that this study would successfully shed a first light on the pattern of cyclists\u27 risky street-crossing behavior at the metropolitan scale, and compliment engineering practices to improve crossing behaviors and bicycle safety
Tracking social regulation of learning in interdisciplinary group work
Get PDFRecent years have seen a growing interest in how student groups regulate their learning when taking part in collaborative and interdisciplinary project-courses that are increasingly becoming popular in Engineering Education programs. While there is a rich research landscape on self-regulated learning, more empirical studies are needed on social regulation of peer-learning in collaborative group work. This study addresses this gap by conducting a narrative comparative case study to document shared regulation in three student groups from three project-based courses. Qualitative data was collected through interviews with members from those interdisciplinary groups working on real world challenges. The interviews were analysed for regulation episodes and synthesised into narratives representing key aspects of the groups regulative behaviours. The results are expected to highlight numerous instances of social regulation of learning within the various groups’ at different stages of the project. Preliminary results presented here demonstrate challenges faced by a group when attempting to socially regulate their learning, underlining the importance of scaffolding for collaborative learning. Findings from the full study will highlight the important role that social regulation processes play in group learning and add to the current understanding of the interplay between different modes of social regulation in groups
Dietary Sources of Anthocyanins and Their Association with Metabolome Biomarkers and Cardiometabolic Risk Factors in an Observational Study
Get PDFAnthocyanins (ACNs) are (poly)phenols associated with reduced cardiometabolic risk. Associations between dietary intake, microbial metabolism, and cardiometabolic health benefits of ACNs have not been fully characterized. Our aims were to study the association between ACN intake, considering its dietary sources, and plasma metabolites, and to relate them with cardiometabolic risk factors in an observational study. A total of 1351 samples from 624 participants (55% female, mean age: 45 \ub1 12 years old) enrolled in the DCH-NG MAX study were studied using a targeted metabolomic analysis. Twenty-four-hour dietary recalls were used to collect dietary data at baseline, six, and twelve months. ACN content of foods was calculated using Phenol Explorer and foods were categorized into food groups. The median intake of total ACNs was 1.6mg/day. Using mixed graphical models, ACNs from different foods showed specific associations with plasma metabolome biomarkers. Combining these results with censored regression analysis, metabolites associated with ACNs intake were: salsolinol sulfate, 4-methylcatechol sulfate, linoleoyl carnitine, 3,4-dihydroxyphenylacetic acid, and one valerolactone. Salsolinol sulfate and 4-methylcatechol sulfate, both related to the intake of ACNs mainly from berries, were inversely associated with visceral adipose tissue. In conclusion, plasma metabolome biomarkers of dietary ACNs depended on the dietary source and some of them, such as salsolinol sulfate and 4-methylcatechol sulfate may link berry intake with cardiometabolic health benefits