document

Monte Carlo drift correction-quantifying the drift uncertainty of global climate models

Grandey, Benjamin S. (author), Koh, Zhi Yang (author), Samanta, Dhrubajyoti (author), Horton, Benjamin P. (author), Dauwels, J.H.G. (author), Chew, Lock Yue (author)

Global climate models are susceptible to drift, causing spurious trends in output variables. Drift is often corrected using data from a control simulation. However, internal climate variability within the control simulation introduces uncertainty to the drift correction process. To quantify this drift uncertainty, we develop a probabilistic...

journal article 2023

document

Guest Editorial Special Issue on Sensing and Machine Learning for Automotive Perception

Santra, Avik (author), Pandharipande, Ashish (author), Wang, Pu Perry (author), Gurbuz, Sevgi Zubeyde (author), Ibanez-Guzman, Javier (author), Cheng, Chih Hong (author), Dauwels, J.H.G. (author), Li, Guofa (author)

contribution to periodical 2023

document

Sensing and Machine Learning for Automotive Perception: A Review

Pandharipande, Ashish (author), Cheng, Chih Hong (author), Dauwels, J.H.G. (author), Gurbuz, Sevgi Z. (author), Ibanez-Guzman, Javier (author), Li, Guofa (author), Piazzoni, Andrea (author), Wang, Pu (author), Santra, Avik (author)

Automotive perception involves understanding the external driving environment and the internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving high levels of safety and autonomy in driving. This article provides an overview of different sensor modalities, such as cameras, radars, and light detection and...

journal article 2023

document

Modeling and Inference of Sparse Neural Dynamic Functional Connectivity Networks Underlying Functional Ultrasound Data

Wijnands, R. (author), Dauwels, J.H.G. (author), Serra, Ines (author), Kruizinga, P. (author), Badura, Aleksandra (author), Hunyadi, Borbala (author)

Functional ultrasound (fUS) is a novel neuroimaging technique that measures brain hemodynamics through a time series of Doppler images. The measured spatiotemporal hemodynamic changes reflect changes in neural activity through the neurovascular coupling (NVC). Often, such image time series is used to analyze dynamic functional connectivity ...

conference paper 2023

document

Evaluation of different classification methods using electronic nose data to diagnose sarcoidosis

van der Sar, Iris G. (author), van Jaarsveld, Nynke (author), Spiekerman, Imme A. (author), Toxopeus, Floor J. (author), Langens, Quint L. (author), Wijsenbeek, Marlies S. (author), Dauwels, J.H.G. (author), Moor, Catharina C. (author)

Electronic nose (eNose) technology is an emerging diagnostic application, using artificial intelligence to classify human breath patterns. These patterns can be used to diagnose medical conditions. Sarcoidosis is an often difficult to diagnose disease, as no standard procedure or conclusive test exists. An accurate diagnostic model based on...

journal article 2023

document

PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles

Piazzoni, Andrea (author), Cherian, Jim (author), Dauwels, J.H.G. (author), Chau, Lap Pui (author)

Even though virtual testing of Autonomous Vehicles (AVs) has been well recognized as essential for safety assessment, AV simulators are still undergoing active development. One particular challenge is the problem of including the Sensing and Perception (S&P) subsystem into the virtual simulation loop in an efficient and effective manner....

journal article 2023

document

MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization

Chua, Victoria Y.H. (author), Liu, Hexin (author), Perera, Leibny Paola Garcia (author), Woon, Fei Ting (author), Wong, Jinyi (author), Zhang, X. (author), Khudanpur, Sanjeev (author), Khong, Andy W.H. (author), Dauwels, J.H.G. (author), Styles, Suzy J. (author)

To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a...

journal article 2023

document

Investigating model performance in language identification: beyond simple error statistics

Styles, Suzy J. (author), Chua, Victoria Y.H. (author), Woon, Fei Ting (author), Liu, Hexin (author), Perera, Leibny Paola Garcia (author), Khudanpur, Sanjeev (author), Khong, Andy W.H. (author), Dauwels, J.H.G. (author)

Language development experts need tools that can automatically identify languages from fluent, conversational speech and provide reliable estimates of usage rates at the level of an individual recording. However, LID systems are typically evaluated on metrics such as equal error rate and balanced accuracy, applied at the level of an entire...

journal article 2023

document

Automatic Camera Pose Estimation by Key-Point Matching of Reference Objects

Zeng, Jinchen (author), Butler, R.M. (author), van den Dobbelsteen, J.J. (author), Hendriks, B.H.W. (author), van der Elst, M. (author), Dauwels, J.H.G. (author)

In this paper, we aim to design an automatic camera pose estimation pipeline for clinical spaces such as catheterization laboratories. Our proposed pipeline exploits Scaled-YOLOv4 to detect fixed objects. We adopt the self-supervised key-point detector SuperPoint in combination with SuperGlue, a keypoint matching technique based on graph neural...

conference paper 2023

document

Nowcasting of Extreme Precipitation Using Deep Generative Models

Bi, Haoran (author), Kyryliuk, Maksym (author), Wang, Zhiyi (author), Meo, C. (author), Wang, Y. (author), Imhoff, Ruben (author), Uijlenhoet, R. (author), Dauwels, J.H.G. (author)

Nowcasting is an observation-based method that uses the current state of the atmosphere to forecast future weather conditions over several hours. Recent studies have shown the promising potential of using deep learning models for precipitation nowcasting. In this paper, novel deep generative models are proposed for precipitation nowcasting....

conference paper 2023

document

A Dynamic Object Removal and Reconstruction Algorithm for Point Clouds

Nagavarapu, Sarat Chandra (author), Abraham, Anuj (author), Selvaraj, Nithish Muthuchamy (author), Dauwels, J.H.G. (author)

Autonomous vehicles (AV) are one of the greatest technological advancements of this decade and a giant leap in the transportation industry and mobile robotics. Autonomous vehicles face several major challenges in achieving higher levels of autonomy. One of these is to find a fast and reliable algorithm to process the sensor data so that the...

conference paper 2023

document

Learning to Solve Multiple-TSP With Time Window and Rejections via Deep Reinforcement Learning

Zhang, Rongkai (author), Zhang, Cong (author), Cao, Zhiguang (author), Song, Wen (author), Tan, Puay Siew (author), Zhang, Jie (author), Wen, Bihan (author), Dauwels, J.H.G. (author)

We propose a manager-worker framework (the implementation of our model is publically available at: https://github.com/zcaicaros/manager-worker-mtsptwr) based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), i.e. multiple-vehicle TSP with time window and rejections (mTSPTWR), where...

journal article 2023

document

Six-Center Assessment of CNN-Transformer with Belief Matching Loss for Patient-Independent Seizure Detection in EEG

Peh, Wei Yan (author), Thangavel, Prasanth (author), Yao, Yuanyuan (author), Thomas, John (author), Tan, Yee Leng (author), Dauwels, J.H.G. (author)

Neurologists typically identify epileptic seizures from electroencephalograms (EEGs) by visual inspection. This process is often time-consuming, especially for EEG recordings that last hours or days. To expedite the process, a reliable, automated, and patient-independent seizure detector is essential. However, developing a patient-independent...

journal article 2023

document

Slot-VAE: Object-Centric Scene Generation with Slot Attention

Wang, Y. (author), Liu, Letao (author), Dauwels, J.H.G. (author)

Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the...

journal article 2023

document

Data Science Education: The Signal Processing Perspective [SP Education]

Gannot, Sharon (author), Tan, Zheng Hua (author), Haardt, Martin (author), Chen, Nancy F. (author), Wai, Hoi To (author), Tashev, Ivan (author), Kellermann, Walter (author), Dauwels, J.H.G. (author)

In the last decade, the signal processing (SP) community has witnessed a paradigm shift from model-based to data-driven methods. Machine learning (ML) - more specifically, deep learning - methodologies are nowadays widely used in all SP fields, e.g., audio, speech, image, video, multimedia, and multimodal/multisensor processing, to name a few...

journal article 2023

document

Recurrent Affine Transform Encoder for Image Representation

Liu, Letao (author), Jiang, Xudong (author), Saerbeck, Martin (author), Dauwels, J.H.G. (author)

This paper proposes a Recurrent Affine Transform Encoder (RATE) that can be used for image representation learning. We propose a learning architecture that enables a CNN encoder to learn the affine transform parameter of images. The proposed learning architecture decomposes an affine transform matrix into two transform matrices and learns them...

journal article 2022

document

Efficient Variational Bayes Learning of Graphical Models with Smooth Structural Changes

Yu, Hang (author), Wu, Songwei (author), Dauwels, J.H.G. (author)

Estimating a sequence of dynamic undirected graphical models, in which adjacent graphs share similar structures, is of paramount importance in various social, financial, biological, and engineering systems, since the evolution of such networks can be utilized for example to spot trends, detect anomalies, predict vulnerability, and evaluate...

journal article 2022

document

Carbon Footprinting of Universities Worldwide Part II: First Quantification of Complete Embodied Impacts of Two Campuses in Germany and Singapo

Helmers, Eckard (author), Chang, Chia Chien (author), Dauwels, J.H.G. (author)

Universities, as innovation drivers in science and technology worldwide, should attempt to become carbon-neutral institutions and should lead this transformation. Many universities have picked up the challenge and quantified their carbon footprints; however, up-to-date quantification is limited to use-phase emissions. So far, data on embodied...

journal article 2022

document

Object Detection and Person Tracking in CathLab with Automatically Calibrated Cameras

Jiang, Y. (author), Dai, R. (author), Zeng, J. (author), Butler, R.M. (author), Vijfvinkel, T.S. (author), Wang, Y. (author), van den Dobbelsteen, J.J. (author), van der Elst, M. (author), Dauwels, J.H.G. (author)

Workflow analysis is a young research field that has been gaining traction in recent years. Work in this field aims to improve the efficiency and safety in operating rooms by analysing surgical processes and providing feedback or support, where observations are made and evaluated by algorithms rather than human experts. For our study, we mount...

conference paper 2022

document

Image Search Engine by Deep Neural Networks

Yao, Y. (author), Zhang, Q. (author), HU, Y. (author), Meo, C. (author), Wang, Y. (author), Nanetti, Andrea (author), Dauwels, J.H.G. (author)

We typically search for images by keywords, e.g., when looking for images of apples, we would enter the word “apple” as query. However, there are limitations. For example, if users input keywords in a specific language, then they may miss results labeled in other languages. Moreover, users may have an image of the object they want to obtain more...

conference paper 2022