Data- och informationsteknik (CSE) // Computer Science and Engineering (CSE)

Använd denna länk för att länka till samlingen:

https://odr.chalmers.se/handle/20.500.12380/11

Vi utbildar för framtiden och skapar samhällsnytta genom vår forskning som levandegörs i nära samarbete med näringslivet. Vi bedriver forskning inom computer science, datateknik, software engineering och interaktionsdesign - från grundforskning till direkta tillämpningar. Institutionen har en stark internationell prägel och är delad mellan Chalmers och Göteborgs universitet.

Läs mer om våra utbildningar

För forskning och forskningspublikationer, se https://research.chalmers.se/organisation/data-och-informationsteknik/

We are engaged in research and education across the full spectrum of computer science, computer engineering, software engineering, and interaction design, from foundations to applications. We educate for the future, conduct research with high international visibility, and create societal benefits through close cooperation with businesses and industry. The department is joint between Chalmers and the University of Gothenburg.

Studying at the Department of Computer Science and Engineering at Chalmers

For research and research output, please visit https://research.chalmers.se/en/organization/computer-science-and-engineering/

Browse

Visar 1 - 20 av 24

AI-Wolf in Sheep’s Clothing Distinguishing between Swedish humans and AI wannabes
(2024) Landberg, Adam; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Axelson-Frisk, Marina; Wozniak, Pawel
This report is investigating whether it is possible for Artificial Intelligence (AI) chatbots and AI detectors to detect texts created by AI in Swedish and in English. Mainly focusing on texts created by the AI chatbot ChatGPT 4, the performances of the AI detectors Smodin and Copyleaks are investigated. The research is motivated by a scarce previous research about AI in Swedish and an articulated need from Swedish schools to understand if it is possible to detect AI created content in homework and essays. By prompting the AI detectors with 400 articles written by humans in Swedish, 400 articles written by humans in English, 400 texts created by AI in Swedish, and 400 texts created by AI in English the AI detectors were thorogly examined. What could be proven was that Smodin showed an accuracy between 73.61% - 73.89% on a 99% confidence level on Swedish content, and an accuracy between 94.68% - 94.82% on a 99% confidence level on English content. On the other hand, Copyleaks showed an accuracy between 94.80% - 94.95% on a 99% confidence level on Swedish content, and an accuracy between 100% on a 99% confidence level on English content. This indicates that, whilst always sucessfully detecting texts written by humans, it is possible to detect Swedish text created by AI nine out of ten times.
An Empirical Survey of Bandits in an Industrial Recommender System Setting
(2023) Brandby, Johan; Schwarz, Tobias; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dubhashi, Devdatt; Jorge, Emilio
In this thesis, the effects of incorporating unstructured data—images in the wild—in contextual multi-armed bandits are investigated, when used within a recommender system setting, which focuses on picture-based content suggestion. The idea is to employ image features, extracted by a pre-trained convolutional neural network, and study the resulting bandit behaviors when including respective excluding this information in the typical context creation, which normally relies on structured data sources—such as metadata. The evaluation is made both online, through A/B-testing enabled by the industrial partner YouPic AB, and offline, effectuated by a simulation pipeline that models the online counterpart. The results are compiled as a survey, covering a selection of contextual bandit algorithms, highlighting the differences brought by the unstructured data. The offline result points towards that if the contextual bandit utilizes a joint or hybrid action-value function, with respect to the parameterization, the addition of the image vectors can significantly outperform the instances without it; however, if a disjoint model is instead employed, no noticeable change is observed. In comparison, those from the online trials can be interpreted as supporting the inclusion of convolutional features, but due to meager and unbalanced sample sizes, the outcomes are deemed inconclusive. To summarize, though there is support for incorporating unstructured data, given that the action-value function is joint or hybrid, the online experiments gave too little evidence for any trustworthy findings; in other words, the question is still partially open.
Applicability of Supervised Machine Learning for CI Configuration Selection
(2023) Lönnfält, Albin; Tu, Viktor; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Gren, Lucas; Gay, Gregory
This study introduces a novel supervised machine learning (ML) model for accurately assigning CI configurations to test specifications. Current solutions to optimize selection of CI configurations lack the ability to select CI configurations for individual test cases and assigning them into predefined CI configurations. The model employs an ensemble architecture with three sub-models and a rule-based component, each focusing on specific aspects of the problem. Extensive model analysis reveals important features that contribute to the assignment process. A decision support system based on the ML model is developed to evaluate the applicability of supervised ML in CI configuration assignment, validated through a survey study involving domain experts. The study demonstrates that supervised ML can exceed the performance requirements of domain experts. Certain features in test specifications are found to be influential in the assignment outcome. Implementing supervised ML brings business value, reducing misassignments, saving time, and reducing fault slip through. Proposed future research includes exploring fully automated CI configuration assignments and investigating more complex ML models, such as neural networks, for enhanced performance and exploring the potential for fully automated adaptation.
Autoencoder and Active Learning to Reduce False Positive Warnings in a Slippery Road Alert System
(2023) Axenhamn, Philip; Greppe, Andreas; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Damaschke, Peter; Selpi, Selpi
Modern vehicles are commonly equipped with a slippery road alert (SRA) system that warns drivers of slippery roads. Current implementations of this system occasionally produce warnings when the road is not slippery. These warnings are called false positives and can harm the system’s trustworthiness. In this thesis, we propose a false positive filter capable of reducing the number of false positive alerts generated by an SRA system based on two machine learning techniques: autoencoder and active learning. The available data was completely unlabeled and contained few informative features. The analysis of this data showed that vehicles send bursts of data points forming sequences. Due to the limitations of the data, multi-variate time series were constructed with the idea that the sequential data might reveal more about the situation than a single-point measurement. Furthermore, the sequences were grouped into true- and false-positive classes based on assumptions of the causes for the alerts, such as driving on ice or a speed bump. The sequential data was used to train GRU- and LSTM-based autoencoders and classifiers to detect sequences that correspond to false positive situations such that they can be removed. The hyperparameters for the models were tuned using Optuna and the best-performing models with the most optimal hyperparameters were further evaluated. Since the data was not labeled, the actual performance of the proposed solution could not be assessed. Instead, the evaluation was based on computing the proportion of remaining assumed true positive (ATP) sequences and assumed false positive (AFP) sequences after filtering. The results show that the LSTM autoencoder could find patterns in the sequential data and was able to remove 43% of the AFP sequences while retaining 90% of the ATP sequences. The active learning approach proved to not work well with the available data.
Combinatorial Optimization with Reinforcement Learning
(2023) Persson Hijazi, Aladdin; Persson, Sanna; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Bernardy, Jean-Philippe; Damaschke, Peter
This master’s thesis delves into the topic of solving combinatorial optimization problems with methods based on reinforcement learning, and specifically, we explore the potential of iterative route decoding and gradient updates in enhancing the performance of route decoding. In this context, route decoding refers to determining the most efficient route for a set of destinations, a combinatorial optimization problem often encountered in logistics and transportation planning. We introduce two methods for iteratively updating solutions for the heterogeneous capacitated vehicle routing problems. They are built upon a reinforcement learning algorithm with an attention graph encoder and use previously computed routes for an instance to improve solution quality. Our results show improved performance, in particular, on out-of-distribution data, which suggests the practical applicability of the methods. In particular, our results show that a pre-trained route planner can, with a few gradient updates with a policy gradient method, significantly improve on out-ofdistribution data.
Cut-in Detection from Videos
(2023) Udayakumar, Apoorva; Varma, Aditya Padmanabhan; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Damaschke, Peter; Panahi, Ashkan
For autonomous driving, it is crucial to anticipate the behaviour of other road users and act accordingly. One important scenario is when a vehicle cuts into the lane of the ego-vehicle with or without sufficient indicator cue. This thesis studies such a scenario and investigates the application of deep learning techniques for understanding and predicting when the cut-in maneuver is performed by the vehicles ahead. As a first step, indicator cues from videos of vehicles performing cut-ins are detected successfully with an F1 score of of 83% and recall value of 85%. We achieve this result by employing ResNet-18 and CNN-LSTM with a tuned level of context around the target vehicle. Further we predict the estimates of interest such as start and end of cut-in intention using the same architectures and discuss the challenges.
Data driven running technique identification
(2023) Lamm, Johan; Preiman, Jessica; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dubhashi, Devdatt; Johansson, Moa
We evaluate if acceleration and rotational IMU data and marker-based positional data can be used to quantify the running technique. We also investigate patterns between the runners’ anatomy, fitness level and technique, and how common instructions impact their running technique. Running technique data, consisting of rotational velocity and acceleration from a foot mounted IMU and position from a marker-based motion capture system, is collected from 47 participants, together with data on anatomy and fitness level. Participants perform a testing protocol containing treadmill running at different velocities while receiving different technique instructions. Data is processed to extract a representative stride cycle for each data source for every participant at every velocity and technique instruction. We evaluate three methods to quantify the technique using dimensionality reduction and reconstruction: sequential feature selection using multivaritate linear regression, principal component analysis, and autoencoder. Best performance is obtained for principal component analysis on all data sources. Information loss is significantly larger on rotational and acceleration data from the IMU than for positional data from the marker-based system. Limited patterns between the anatomy and fitness level of runners and their technique were observed, and the found patterns are generally on parameters that are not related to technique, such as ground contact time and contact to flight-time ratio. Most technique instructions are shown to impact technique, but the effect diminishes as velocity increases. A larger impact is seen when runners are asked to increase back-kick height, knee lift, or frequency, and a smaller impact is seen when asked to land further back with the foot or push the hip forward.
Deep Dynamic Graphical Models for Molecular Kinetics
(2023) Gao, Wenli; Su, Enmin; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Damaschke, Peter; Olsson, Simon
With the massive growth of molecular dynamics simulation results comes a great demand for efficient analysis methods to distill essential information from simulation and enable quantitative characterization of molecular properties. Dynamic Graphical Model (DGM) is currently the most data-efficient method towards this goal. However, DGMs rely on extensive manual intervention by experts: division of molecules into smaller subsystems and their discretization into an unknown number of states. We aim to automate this expert-guided procedure using a deep-learning approach and make an end-to-end learning system. To achieve this, we examine the Variational Approach to Markov Processes (VAMP), and its ability to detect meta-stable subsystems in molecular systems, and to decide the number of states for each subsystem. We put forward a model which uses VAMP to learn subsystem states via a deep neural network and DGM to connect the subsystems by modeling their time-correlated dynamics. The model is trained in an end-to-end manner and optimized using a weighted sum of VAMP loss, DGM loss, and regularizer. We also introduce a pruning-based algorithm to automatically decide the number of states per subsystem. Our results show that VAMP is suitable for enumerating subsystems of a molecular system, however, VAMP alone cannot decide the number of states for each subsystem. This thesis sheds light on how an end-to-end learning system may be built with DGMs to analyze molecular dynamics and outlines possible future extensions of this work.
Detecting Metastable States in Proteins using E(3) Equivariant VAMPnets
(2023) Arnesen , Sara; Nordström, David; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dubhashi, Devdatt; Olsson, Simon
As proteins fold, they encounter intermediary conformations, often denoted metastable states, that are vital to deciphering diseases related to malfunctions in conformational changes. To detect these metastable states, a deep learning framework using the variational approach for Markov processes (VAMP) has been proposed, dubbed VAMPnets. In this master’s thesis, we improve the training of VAMPnets through the use of E(3) equivariant neural networks. These networks incorporate the symmetries of Euclidean space, facilitating faster and more data-efficient learning. To study the effectiveness of these networks, we benchmark two different equivariant Transformer architectures and an equivariant convolutional network against both a simple and an invariant multilayered perceptron. The models are evaluated on molecular dynamics trajectories of alanine dipeptide and protein folding datasets. The use of E(3) equivariant neural networks in training VAMPnets is shown to significantly improve the prediction accuracy on random downsampled data. Using only 1% of the dataset, the equivariant Transformer achieves almost twice the VAMP-2 score as the benchmarks. Furthermore, the model exhibits improved robustness. With only 20% data remaining, the model scores on par with the complete dataset. On average, the model requires significantly fewer backward passes, converging more than twice as fast as the benchmark models, showing enhanced data efficiency. Furthermore, the results highlight the significant computational burden that equivariant neural networks pose, especially for larger molecules, proving almost 1,000 times slower on the protein folding dataset. Finally, we propose a novel algorithm for detecting the number of metastable states of a molecule using the VAMP-2 score and provide estimates for the 12 proteins in the protein folding dataset.
Epidemic tracking using network-based scaling - An Innovative Approach for Real-time Epidemic Surveillance and Control in East
(2024) Murgolo , Daniele; Vu, Tomas; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Papatriantafilou, Marina; Tsigas, Philippas
Estimating the sizes of subpopulations enables the potential to optimally allocate resources and funding for people in need, e.g., subpopulations that are affected by epidemics such as HIV/AIDS. We propose a method based on related literature on networking to accomplish this, namely the survey-based Network scale-up method (NSUM). This is done by collecting aggregated relational data (ARD) by asking participants “How many X do you know?”, where X can be any subpopulation, such as people named Michael or doctors. The internal workings behind NSUM is that with the use of participants’ social networks, the sizes of hard-to-reach subpopulations can be estimated by extrapolating and scaling up the total population. The aim of this thesis is to build a system based on a Web questionnaire and the use of NSUM in hopes of estimating the sizes of hard-to-reach subpopulations. Different models within NSUM such as the random degree model (RD-model), barrier effect model (BE-model), and transmission bias model (TB-model) which account for various errors and biases, were also explored where comparisons and analysis of their performance were conducted. Data sets from Uganda, pertaining to occupational distribution, and Rwanda, focusing on the age distribution were used. The results from the two data sets are presented in a forest plot. The metric of choice is the difference in magnitude between the true value and the estimated values. The RD-model produces estimates that are close to the true value with small variances whereas the TB-model overestimates with a large dispersion for both datasets. Lastly, the BE-model produces conflicting estimates between the two datasets. Even though it is difficult to affirm the estimated value, we conclude that, while these estimates are consistent to a certain degree, the various biases and errors may produce less than satisfactory results.
Ideology and Power Identification in Parliamentary Debates
(2024) Jiremalm, Johan; Palmqvist, Oscar; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Johansson, Moa; Picazo-Sanchez, Pablo
Political debates are vital in shaping public opinion and influencing policy decisions. However, understanding the complex linguistic structures used by politicians to ascertain their orientations and power dynamics can be challenging. In this paper we explore Natural Language Processing techniques for identifying political orientation and power structures in parliamentary debates. We introduce a Located Missing Labels-loss in order to train jointly to predict both power and ideology. Furthermore, our proposed method also trains to predict a third synthetically generated polarity label. Finally, we combine this training method with pre-processing steps including back-translation and meta data inclusion. Our results show that our method manages to improve upon conventional methods of fine-tuning. We take part in the Touché competition as part of CLEF 2024 and find that our method achieves the highest performance out of all participants [1]. Keywords: Political
Importance Sampling in Deep Learning Object Detection - An empirical investigation into accelerating deep learning object detection training by exploiting informative data points
(2023) Huang, Alexander; Kvernes, Johannes; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Angelov, Krasimir; Yu, Yinan
In recent years, the field of deep learning object detection has witnessed a notable surge in progress, largely fueled by the growth of available data. While the ever growing amount of data has enabled complex object detection models to improve generalization performance and to facilitate training phases that are less prone to over-fitting, the time to reach desired performance with this remarkable amount of data has been reported to be an emerging problem in practice. This is certainly the case when each sample consist of high resolution image data that could burden the capacity of loading data. This thesis explores the possibilities of leveraging importance sampling as a means to accelerate gradient-based training of an object detection model. This avenue of research aims at biasing the sampling of training examples during training, in the hope of exploiting informative samples and reduce the amount of computation on uninformative, noisy and out-of-distribution samples. While previous art shows compelling evidence of importance sampling in deep learning, it is consistently reported in a context of less complex tasks. In this work, we propose techniques that can be applied to single-stage anchor-free object detectors, in order to adopt importance sampling to accelerate training. Our methods do not require modifications to the objective function, and allow for a biased sampling procedure that remains consistent across runs and samples. Our results suggest that an uncertainty-based heuristic outperforms loss-based heuristics, and that object detection training can be subject to a remarkable speed-up in terms of reaching the baseline’s performance in fewer iterations, where the baseline samples the training examples uniformly without replacement. Furthermore, the empiric observations reported in this work also indicate that an increased final generalization performance can be achieved given an equal amount of training time when compared to the baseline.
Learning to Navigate Over Stochastic Transport Networks Using Multi-Armed Bandits: A Contextual Approach for Efficient Online Learning in Road Network Graphs with Multi-Armed Bandits to Minimize Long- Term Travel Time
(2024) Nilsson, Hannes; Johansson, Rikard; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dubhashi, Devdatt; Haghir Chehreghani, Morteza
As part of the ongoing process of phasing out fossil fuel vehicles, attempts have been made to extend the effective range and adoption rate of electric vehicles through navigation systems focused on energy consumption. One way to approach this problem is by viewing route selections as a multi-armed bandit problem. This allows the system to adapt and recommend better routes over time, to minimize energy consumption. For navigation systems to be useful in practice, guiding vehicles from one point to another in minimal time is crucial. Therefore, this project examines the effectiveness of multi-armed bandit algorithms for time-efficient navigation in complex real-world environments, without initial information. For this purpose, we adapt a previously studied online learning framework developed for energy efficiency, and extract road segment travel time distributions from the traffic simulation software SUMO. The framework is applied to the Luxembourg road network and our results demonstrate that contextual multi-armed bandits using tree ensembles are highly effective. More specifically, we show that TEUCB and TETS, which we implement using both XGBoost and random forest, outperform state-of-the-art contextual multi-armed bandits based on neural networks and linear models. Further, by additional comparison of TEUCB and TETS to other bandit algorithms based on tree models, we identify at least two properties to explain their high level of performance. First, tree ensemble methods appear to offer relatively accurate travel time predictions from the contextual information available in this problem. Second, the ability to generalize over different arms and infer the travel time on one road segment from observations gathered on other ones, based on similarities, seems highly advantageous for this problem.
Low latency video analytics system with multi-exit neural networks
(2022) HARINDRAN, NEETHU; POOJARY, BHARATH; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Tsigas, Philippas; Ali-Eldin Hassan, Ahmed
Computer vision-based control systems have become increasingly powerful and promising in tackling real-world problems. This can be accredited to the use of deep learning methods in these systems with state-of-the-art performance sometimes outperforming humans in tasks which require subjective decision making. This has resulted in increased interest in these systems from Swedish industry, including Volvo. One example system where these systems are used is the Volvo GPSS system, where semantic segmentation is used to perform real-time decisions based on pixel level classification of a monitored area. However, such systems frequently deal with a trade-off between latency and accuracy. This is primarily due to the increasing number of model layers being used to develop Deep-Neural-Network models for vision systems, resulting in equal resource utilization regardless of input complexity. In this thesis, we develop an approach that employs input adaptive multi-exit strategy to exploit latency benefits of dynamic processing based on the input complexity. The proposed approach aims to have a reduced average inference time as the simple input samples takes an early exit and only the complex samples need more computation offered by all the model layers. The open source CityScapes dataset and the Volvo dataset were used in a number of multi-exit semantic segmentation experiments with HRNet architecture chosen as the backbone. The thesis work studies three novel exit strategies, including reinforcement learning, auxiliary models, and fast Fourier transform. Out of all the methods examined, the reinforcement learningbased exit strategy displayed the best performance advantages, with accuracy on par with unbranched HRNet and a significant decrease in latency and computation.
Machine Learning for Detecting Gender Bias at Chalmers
(2023) Nilsson, Linnea; Lindau, Sarah; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Johansson, Moa; Ljunglöf, Peter
This thesis studies gender bias in course evaluations through the lens of machine learning and NLP. Different methods are used to examine and explore the data and find differences in what students write about courses depending on the gender of the examiner. The data is also examined using more traditional statistical methods to get an understanding of how the students’ impressions of the courses are related to the gender of the examiner. Other aspects related to gender and gender bias are also examined, such as how the proportion of female students relates to the gender of the examiner and whether male or female examiners give different grades to their students. Student grades and teaching language are also factors that are being examined to see whether there is any bias against female examiners or students that is easily detectable in the data. The main findings are that courses with female examiners seem to get lower overall impression scores than those with male examiners. Courses taught in Swedish also receive lower scores, compared to the English courses. No clear patterns as to what words are used when writing comments about a course with a male or female examiner were found. When trying to predict the author gender the patterns were clearer, finding that men write more words directly related to the course and women write more words related to communication.
Machine Learning for generative painting informed by visual arts
(2023) Wang, Chaoming; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dahlstedt, Palle; Tatar, Kıvanç
Visual art practice is a complicated, varied, creative process based on the artist’s style and preferences. Although many studies have attempted to apply artificial intelligence techniques to art production and statistical analysis, there is still significant scope for exploring how to incorporate the techniques in visual arts practices into generative painting pipelines using Machine Learning. This thesis applies machine learning to analyzing painting techniques in painting practices with a research-through-design approach. The problem is mainly presented as tasks such as segmentation of artworks (in this thesis, paintings), stroke prediction, and the presentation of painting processes based on different painting techniques through different algorithmic pipelines. The results show that most segmentation models based on photo training are challenging to apply to the segmentation of artwork components directly, and relevant improvement solutions are discussed in Chapter 6. In addition, due to the diverse presentation of painting art, this paper presents different painting techniques based on the foreground and background segmentation and ’blocking-in’ techniques based on line detection. It discusses the possibility of transferring these painting processes to other painting processes.
Machine Learning for Predicting Targeted Protein Degradation
(2023) Ribes, Stefano; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Damaschke, Peter; Mercado, Rocío
PROteolysis TArgeting Chimeras (PROTACs) are an emerging high-potential therapeutic technology. PROTACs leverage the ubiquitination and proteasome processes within a cell to degrade a Protein Of Interest (POI). Designing new PROTAC molecules, however, is a challenging task, as assessing the degradation efficacy of PROTACs often requires extensive effort, mostly in terms of expertise, cost and time, for instance via laboratory assays. Machine Learning (ML) and Deep Learning (DL) technologies are revolutionizing many scientific fields, including the drug development pipeline. In this thesis, we present the data collection and curation strategy, as well as several candidate DL models, for ultimately predicting the degradation efficacy of PROTAC molecules. In order to train and evaluate our system, we propose a curated version of open source datasets from literature. Relevant features such as pDC50, Dmax, E3 ligase type, POI amino acid sequence, and experimental cell type are carefully organized and parsed via a Named Entity Recognition system based on a BERT model. The curated datasets have been used for developing three candidate DL models. Each DL model is designed to leverage different PROTAC representations: molecular fingerprints, molecular graphs and tokenized SMILES. The proposed models are evaluated against an XGBoost model baseline and the State-of-The-Art (SOTA) model for predicting PROTACs degradation activity. Overall, our best DL models achieved a validation accuracy of 80.26% versus SOTA’s 77.95% score, and a Receiver Operating Characteristic Area Under the Curve (ROC AUC) validation score of 0.849 versus SOTA’ 0.847.
Model-based deadlock prevention for traffic planning of autonomous vehicles
(2023) Möller, David; Ohlin, Alexander; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Damaschke, Peter; Gheorghiu, Andru
Volvo Autonomous Solutions are developing a system for planning the routes of fleets of autonomous vehicles. Autonomous control creates several problems that must be solved; among these is the possibility for the policy of said vehicles to end up in deadlock. This thesis proposes new concepts to describe the problem and methods for preventing a vehicle fleet from deadlocking. As the action that led to deadlock might not be recent, the term implicit deadlock was introduced, which is a configuration of vehicle positions from which deadlock is inevitable. The methods developed successfully prevent deadlocks at several pilot and test sites. However, results indicate that time for computing implicit deadlocks grows exponentially in the size of the site and the number of vehicles in the fleet. A neural network model was also trained using data generated from preprocessing of deadlocks to approximate the process and enable deadlock predictions not discovered before.
Multi-agent Communication via Reinforcement Learning in Social Networks
(2024) Liang, Zhitao; Wang, Wanqiu; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Dubhashi, Devdatt; David Thomas, Jonathan; Carlsson, Emil
This thesis investigates the use of multi-agent reinforcement learning (MARL) to explore emergent communications of artificial agents in social networks. The main goal is understanding how agents develop shared communication protocols to perform collaborative tasks in complex environments. Using the World Color Survey (WCS) dataset, we implement a speaker-listener model in which an agent learns to name colors, providing a framework for observing the formation of communication strategies. In contrast to existing work, we utilize a shared neural network for both speaker’s and listener’s functions, which promotes equivalence in language use between agents and supports consistent communication. Extending the model to multiple agents, we studied how social network structure affects emergency communication, finding that denser networks produce more consistent language while sparser networks allow for greater diversity. The introduction of new agents and different levels of interaction between communities also affects language evolution, with newly generated languages found to be more similar to more populous collectives. However, the scale of our research could be improved. In future work, investigating larger populations of agents would be beneficial for better understanding scalability and refining our findings. Additionally, we could explore other communication modes, such as one to-many or many-to-one interactions, to gain a more comprehensive understanding of emergent communication in artificial systems.
Multimodal Data Fusion for BEV Perception
(2024) XUAN, YUNER; QU, YING; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Axelson-Fisk, Marina; Selpi, Selpi
In autonomous driving, sensors are situated across different parts of the vehicle to capture the information from the surrounding environments to allow the autonomous vehicles to address various tasks related to driving decisions, like object detection, semantic segmentation and path planning. In the diverse approaches of perception, birds-eye-view (BEV) perception has progressed impressively over recent years. In contrast to front-view or perspective view modalities, BEV provides a comprehensive representation of the vehicles surrounding environment, which is fusion-friendly and offering convenience for downstream applications. As vehicle cameras are oriented outward and parallel to the ground, the captured images are in a perspective view that is perpendicular to the BEV. Consequently, a crucial part of BEV perception is the transformation of multi-sensor data from perspective view (PV) to BEV. The quality and efficiency of this transformation play a critical role in influencing the performance of subsequent specific tasks. This thesis project aims to study comprehensive multimodal data fusion solutions for PV-to-BEV transformation. We analyzed the common and unique characteristics of existing approaches and assessed their performance against a selected downstream perception task, focusing on object detection within a short distance. Additionally, we implemented mainly two modules Global Position Encoding (GPE) and Information Enhanced Decoder (IED) to enhance the performance of the multi-modal data fusion model. Keywords:

Browse

Browsar Data- och informationsteknik (CSE) // Computer Science and Engineering (CSE) efter Program "Data science and AI (MPDSC), MSc"

Sökresultat per sida

Sortera efter