Hans Lobel

Hans Lobel

Auto-generated profile, based on publicly available information

Hans Lobel

Department of Computer Science, Pontificia Universidad Católica de Chile, Santiago, Chile

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in Landscape and Urban Planning
Verified
Journal Article
Closed access
TRTomás Rossetti
Tomás Rossetti
HLHans Lobel
Hans Lobel
VRVíctor Rocco
Víctor Rocco
RHRicardo Hurtubia
Ricardo Hurtubia

18 June 2021 in IEEE Access
Verified
Journal Article
Open access
JHJulio Hurtado
Julio Hurtado
HLHans Lobel
Hans Lobel
ASAlvaro Soto
Alvaro Soto
Continuous learning occurs naturally in human beings. However, Deep Learning methods suffer from a problem known as Catastrophic Forgetting (CF) that consists of a model drastically decreasing its performance on previously learned tasks when it is sequentially trained on new tasks. This situation, known as task interference, occurs when a network modifies relevant weight values as it learns a new task. In this work, we propose two main strategies to face the problem of task interference in convolutional neural networks. First, we use a sparse coding technique to adaptively allocate model capacity to different tasks avoiding interference between them. Specifically, we use a strategy based on group sparse regularization to specialize groups of parameters to learn each task. Afterward, by adding binary masks, we can freeze these groups of parameters, using the rest of the network to learn new tasks. Second, we use a meta learning technique to foster knowledge transfer among tasks, encouraging weight reusability instead of overwriting. Specifically, we use an optimization strategy based on episodic training to foster learning weights that are expected to be useful to solve future tasks. Together, these two strategies help us to avoid interference by preserving compatibility with previous and future weight values. Using this approach, we achieve state-of-the-art results on popular benchmarks used to test techniques to avoid CF. In particular, we conduct an ablation study to identify the contribution of each component of the proposed method, demonstrating its ability to avoid retroactive interference with previous tasks and to promote knowledge transfer to future tasks.

21 April 2021 in IEEE Access
Verified
Journal Article
Open access
PCPedro Pablo Correa
Pedro Pablo Correa
ACAldo Cipriano
Aldo Cipriano
FNFelipe Nunez
Felipe Nunez
JSJuan Carlos Salas
Juan Carlos Salas
HLHans Lobel
Hans Lobel
Electrolytic refining is the last step of pyrometallurgical copper production. Here, smelted copper is converted into high-quality cathodes through electrolysis. Cathodes that do not meet the physical quality standards are rejected and further reprocessed or sold at a minimum profit. Prediction of cathodic rejection is therefore of utmost importance to accurately forecast the electrorefining cycle economic production. Several attempts have been made to estimate this process outcomes, mostly based on physical models of the underlying electrochemical reactions. However, they do not stand the complexity of real operations. Data-driven methods, such as deep learning, allow modeling complex non-linear processes by learning representations directly from the data. We study the use of several recurrent neural network models to estimate the cathodic rejection of a cathodic cycle, using a series of operational measurements throughout the process. We provide an ARMAX model as a benchmark. Basic recurrent neural network models are analyzed first: a vanilla RNN and an LSTM model provide an initial approach. These are further composed into an Encoder-Decoder model, that uses an attention mechanism to selectively weight the input steps that provide most information upon inference. This model obtains 5.45% relative error, improving by 81.4% the proposed benchmark. Finally, we study the attention mechanism's output to distinguish the most relevant electrorefining process steps. We identify the initial state as critical in predicting cathodic rejection. This information can be used as an input for decision support systems or control strategies to reduce cathodic rejection and improve electrolytic refining's profitability.

4 October 2022 in Journal of Intelligent Transportation Systems
Verified
Journal Article
Closed access
HCHernán Catalán
Hernán Catalán
HLHans Lobel
Hans Lobel
JHJuan Carlos Herrera
Juan Carlos Herrera
The way in which public transport buses are driven has an influence in users’perception and satisfaction with the service. Bus driver’s behavior is usually obtained surveying passengers and/or using the mystery passenger method, not necessarily allowing for an objective and continuous evaluation. In this work, we introduce a novel methodology to automatically classify drivers’ behavior in a more consistent and objective manner, based on data from inertial measurement units, and machine learning techniques. By substituting human evaluators with automatic data collection and classification algorithms, we are able to reduce the subjectivity and cost of the current methodology, while increasing sample size. Our approach is based on three components: i) data capture using inertial measurement units (e.g. mobile devices), ii) carefully tuned classifiers that deal with sample imbalance problems, and iii) an interpretable scoring system. Results show that collected data captures several types of undesirable maneuvers, providing a rich information to the classification process. In terms of categorization performance, the evaluated classifiers, namely support vector machines, decision trees and k-NN, deliver high and consistent accuracy after the tuning process, even in the presence of a highly imbalanced sample. Finally, the proposed driver’s behavior score shows high discriminative power, effectively characterizing differences between drivers, and providing driver-tailored driving recommendations, that can be generated in specific spots, in order to improve passengers’ experience. The resulting methodology can be cost-effectively deployed at a large scale with good performance.

6 June 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
JFJaviera I. Fuentes-Guíñez
Javiera I. Fuentes-Guíñez
GTGiancarlo Troni
Giancarlo Troni
HLHans Lobel
Hans Lobel
High-resolution seafloor mapping continues to be challenging, primarily due to the high costs and complexity of traditional sensors. Laser scanners offer a more affordable alternative, using a monocular camera and a laser stripe. While this method provides high-resolution 3D reconstructions, it is sensitive to underwater lighting and surface reflections. This work introduces SPLASH-SegFormer Pipeline, a novel method that leverages attention mechanisms and multi-level feature integration to enhance laser stripe segmentation in underwater environments, marking, to the best of our knowledge, the first application of a transformer-based architecture for this task. The proposed method is trained and evaluated using both simulated and field experimental data collected in a test tank and during multiple sea expeditions, allowing it to learn from diverse and challenging environments. A complete pipeline is constructed around this network, enabling the processing of images from a camera to a 3D point cloud reconstruction quickly and accurately. The results demonstrate that SPLASH-SegFormer significantly enhances segmentation robustness and accuracy while maintaining a reasonable speed. It outperforms traditional underwater thresholding by over 64 points in mIoU and surpasses all evaluated methods, achieving 6.6 points higher mIoU than Stripe Segmentor while running over 65% faster. This speed enhances efficiency and makes it ideal for real-time onboard applications, enabling millimeter-level underwater 3D reconstruction and high-resolution seafloor mapping using smaller, cost-effective sensors.

8 May 2025
Verified
Conference Paper
Open access
CMCarlos Muñoz
Carlos Muñoz
Marcelo MendozaMarcelo Mendoza
Marcelo Mendoza
HLHans Lobel
Hans Lobel
Brian Keith-NormabuenaBrian Keith-Normabuena
Brian Keith-Normabuena