1. Learning deep representations of enzyme thermal adaptationGang Li, Filip Buric, Jan Zrimec, Sandra Viknander, Jens Nielsen, Aleksej Zelezniak, Martin K. M. Engqvist, 2022, izvirni znanstveni članek Povzetek: Temperature is a fundamental environmental factor that shapes the evolution of organisms. Learning thermal determinants of protein sequences in evolution thus has profound significance for basic biology, drug discovery, and protein engineering. Here, we use a data set of over 3 million BRENDA enzymes labeled with optimal growth temperatures (OGTs) of their source organisms to train a deep neural network model (DeepET). The protein-temperature representations learned by DeepET provide a temperature-related statistical summary of protein sequences and capture structural properties that affect thermal stability. For prediction of enzyme optimal catalytic temperatures and protein melting temperatures via a transfer learning approach, our DeepET model outperforms classical regression models trained on rationally designed features and other deep-learning-based representations. DeepET thus holds promise for understanding enzyme thermal adaptation and guiding the engineering of thermostable enzymes.
Ključne besede: bioinformatics, deep neural networks, enzyme catalytic temperatures, optimal growth temperatures, protein thermostability, transfer learning
Objavljeno v DiRROS: 17.07.2024; Ogledov: 8; Prenosov: 2
 Celotno besedilo (2,61 MB)
Gradivo ima več datotek! Več... |
2. Adaptive visual quality inspection based on defect prediction from production parametersZvezdan Lončarević, Simon Reberšek, Samo Šela, Jure Skvarč, Aleš Ude, Andrej Gams, 2024, izvirni znanstveni članek Povzetek: At the end of a production process, the manufactured products must usually be visually inspected to ensure their quality. Often, it is necessary to inspect the final product from several viewpoints. However, the inspection of all possible aspects might take too long and thus create a bottleneck in the production process. In this paper we propose and evaluate a methodology for adaptive, robot-aided visual quality inspection. With the proposed method, the most probable defects are first predicted based on the production process parameters. A suitable classifier for defect prediction is learnt in an unsupervised manner from a database that includes the produced parts and the associated parameters.Arobot then steers the camera only towards viewpoints associated with predicted defects, which implies that the trajectories of robot motion for the inspection might be different for every product. To enable dynamic planning of camera trajectories, we describe a methodology for evaluation and selection of the most appropriate autonomous motion planner. The proposed defect prediction approach was compared to other methods and evaluated on the products from a real-world production line for injection moulding, which was implemented for a producer of parts in the automotive industry.
Ključne besede: robot learning, robotic quality inspection, visual quality inspection, injection moulding, production parameters, robot motion planning
Objavljeno v DiRROS: 15.07.2024; Ogledov: 42; Prenosov: 15
Celotno besedilo (7,44 MB)
Gradivo ima več datotek! Več... |
3. Exploiting image quality measure for automatic trajectory generation in robot-aided visual quality inspectionAtae Jafari-Tabrizi, Dieter P. Gruber, Andrej Gams, 2024, izvirni znanstveni članek Povzetek: Currently, the standard method of programming industrial robots is to perform it manually, which is cumbersome and time-consuming. Thus, it can be a burden for the flexibility of inspection systems when a new component with a different design needs to be inspected. Therefore, developing a way to automate the task of generating a robotic trajectory offers a substantial improvement in the field of automated manufacturing and quality inspection. This paper proposes and evaluates a methodology for automatizing the process of scanning a 3D surface for the purpose of quality inspection using only visual feedback. The paper is divided into three sub-tasks in the same general setting: (1) autonomously finding the optimal distance of the camera on the robot’s end-effector from the surface, (2) autonomously generating a trajectory to scan an unknown surface, and (3) autonomous localization and scan of a surface with a known shape, but with an unknown position. The novelty of this work lies in the application that only uses visual feedback, through the image focus measure, for determination and optimization of the motion. This reduces the complexity and the cost of such a setup. The methods developed have been tested in simulation and in real-world experiments and it was possible to obtain a precision in the optimal pose of the robot under 1 mm in translational, and 0.1° in angular directions. It took less than 50 iterations to generate a trajectory for scanning an unknown free-form surface. Finally, with less than 30 iterations during the experiments it was possible to localize the position of the surface. Overall, the results of the proposed methodologies show that they can bring substantial improvement to the task of automatic motion generation for visual quality inspection.
Ključne besede: robot learning, eobotic quality inspection, visual quality inspection
Objavljeno v DiRROS: 09.05.2024; Ogledov: 252; Prenosov: 492
Celotno besedilo (3,00 MB)
Gradivo ima več datotek! Več... |
4. Outward Bound and outdoor adventure education : a scoping review, 1995-2019Timothy J. Mateer, Joshua Pighetti, Derrick Taff, Pete Allison, 2022, izvirni znanstveni članek Povzetek: Outdoor adventure education (OAE) programming is often referenced as an ef-fective intervention that encourages a wide array of outcomes in participants such as increased confidence, independence, and communication skills. However, as outdoor adventure education continues to increase globally, what does the academic literature say about the outcomes related to these programs? Hattie, Marsh, Neill, and Richards (1997) conducted the last major review of program efficacy in this realm. This updated scoping review, largely following PRISMA guidelines (Tricco et al., 2018), aims to summarize the academic literature on one of the primary outdoor adventure education providers internationally, Outward Bound (OB). Fifty-four studies, published betwe-en 1995 and 2019, have been summarized in this review. Utilizing Outward Bound International’s (OBI) framework of “people”, “place”, and “process”, themes and gaps in the literature are explored. Specifically, the OB literature has progressed since 1995 in demonstrating social and emotional outcomes in a variety of settings, a better understanding of the nature of effective programming, and further documenting the role the instructor plays in the learning experience. Recommendations are provided on developing more rigorous methodologies for future research, understanding the role of the physical environment in the learning experience, and utilizing theoretical approa-ches to integrate outdoor adventure education into broader academic realms
Ključne besede: outdoor education, adventure education, Outward Bound, emotional learning, experiental learning, scoping review
Objavljeno v DiRROS: 15.04.2024; Ogledov: 272; Prenosov: 172
Celotno besedilo (951,53 KB)
Gradivo ima več datotek! Več... |
5. Sensitivity analysis of RF+clust for leave-one-problem-out performance predictionAna Nikolikj, Michal Pluhacek, Carola Doerr, Peter Korošec, Tome Eftimov, 2023, objavljeni znanstveni prispevek na konferenci Ključne besede: automated performance prediction, autoML, single-objective black-box optimization, zero-shot learning
Objavljeno v DiRROS: 13.11.2023; Ogledov: 500; Prenosov: 285
Celotno besedilo (4,94 MB)
Gradivo ima več datotek! Več... |
6. |
7. Models for forecasting the traffic flow within the city of LjubljanaGašper Petelin, Rok Hribar, Gregor Papa, 2023, izvirni znanstveni članek Povzetek: Efficient traffic management is essential in modern urban areas. The development of intelligent traffic flow prediction systems can help to reduce travel times and maximize road capacity utilization. However, accurately modeling complex spatiotemporal dependencies can be a difficult task, especially when real-time data collection is not possible. This study aims to tackle this challenge by proposing a solution that incorporates extensive feature engineering to combine historical traffic patterns with covariates such as weather data and public holidays. The proposed approach is assessed using a new real-world data set of traffic patterns collected in Ljubljana, Slovenia. The constructed models are evaluated for their accuracy and hyperparameter sensitivity, providing insights into their performance. By providing practical solutions for real-world scenarios, the proposed approach offers an effective means to improve traffic flow prediction without relying on real-time data.
Ključne besede: traffic modeling, time-series forecasting, traffic-count data set, machine learning, model comparison
Objavljeno v DiRROS: 28.09.2023; Ogledov: 485; Prenosov: 218
Celotno besedilo (5,05 MB)
Gradivo ima več datotek! Več... |
8. Hierarchical learning of robotic contact policiesMihael Simonič, Aleš Ude, Bojan Nemec, 2023, izvirni znanstveni članek Povzetek: The paper addresses the issue of learning tasks where a robot maintains permanent contact with the environment. We propose a new methodology based on a hierarchical learning scheme coupled with task representation through directed graphs. These graphs are constituted of nodes and branches that correspond to the states and robotic actions, respectively. The upper level of the hierarchy essentially operates as a decision-making algorithm. It leverages reinforcement learning (RL) techniques to facilitate optimal decision-making. The actions are generated by a constraint-space following (CSF) controller that autonomously identifies feasible directions for motion. The controller generates robot motion by adjusting its stiffness in the direction defined by the Frenet–Serret frame, which is aligned with the robot path. The proposed framework was experimentally verified through a series of challenging robotic tasks such as maze learning, door opening, learning to shift the manual car gear, and learning car license plate light assembly by disassembly.
Ključne besede: autonomous robot learning, learning, experience, compliance and impedance contro
Objavljeno v DiRROS: 21.09.2023; Ogledov: 542; Prenosov: 293
Celotno besedilo (1,73 MB)
Gradivo ima več datotek! Več... |
9. Algorithm instance footprint : separating easily solvable and challenging problem instancesAna Nikolikj, Sašo Džeroski, Mario Andrés Muñoz, Carola Doerr, Peter Korošec, Tome Eftimov, 2023, objavljeni znanstveni prispevek na konferenci Ključne besede: black-box optimization, algorithms, problem instances, machine learning
Objavljeno v DiRROS: 15.09.2023; Ogledov: 432; Prenosov: 251
Celotno besedilo (2,03 MB)
Gradivo ima več datotek! Več... |
10. Assessing the generalizability of a performance predictive modelAna Nikolikj, Gjorgjina Cenikj, Gordana Ispirova, Diederick Vermetten, Ryan Dieter Lang, Andries Petrus Engelbrecht, Carola Doerr, Peter Korošec, Tome Eftimov, 2023, objavljeni znanstveni prispevek na konferenci Ključne besede: algorithms, predictive models, machine learning
Objavljeno v DiRROS: 15.09.2023; Ogledov: 443; Prenosov: 292
Celotno besedilo (935,67 KB)
Gradivo ima več datotek! Več... |
