Searched for: subject%3A%22generalization%22
(1 - 20 of 46)

Pages

document
Wang, Zipeng (author)
Deep-learning-based object detectors, while offering exceptional performance, are data-dependent and can suffer from generalization issues. In this thesis, we investigated deep neural networks for detecting people and medical instruments in the vision-based workflow analysis system inside Catheterization Laboratories (Cath Labs). The central...
master thesis 2024
document
Fang, G. (author), Zhang, Tianyu (author), Huang, Yuming (author), Zhang, Zhizhou (author), Masania, K. (author), Wang, C.C. (author)
This work explores a spatial printing method to fabricate continuous fiber-reinforced thermoplastic composites (CFRTPCs), which can achieve exceptional mechanical performance. For models giving complex 3D stress distribution under loads, typical planar-layer based fiber placement usually fails to provide sufficient reinforcement due to their...
journal article 2024
document
Song, Yanjie (author), Ou, Junwei (author), Pedrycz, Witold (author), Suganthan, Ponnuthurai Nagaratnam (author), Wang, X. (author), Xing, Lining (author), Zhang, Yue (author)
Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem ...
journal article 2024
document
Cao, Chengtai (author), Chen, Xinhong (author), Wang, J. (author), Song, Q. (author), Tan, Rui (author), Li, Yung Hui (author)
Autonomous driving systems rely on precise trajectory prediction for safe and efficient motion planning. Despite considerable efforts to enhance prediction accuracy, inherent uncertainties persist due to data noise and incomplete observations. Many strategies entail formalizing prediction outcomes into distributions and utilizing variance to...
journal article 2024
document
Lu, T. (author), Wang, Ruizhi (author), Tang, Z. (author), Zou, Yiwei (author), Yue, X. (author), Liang, Yansong (author), Gong, Haoran (author), Liu, Shurui (author), Chen, Zhiyuan (author), Liu, Xun (author), Du, S. (author)
This article presents a 10mV-startup-voltage thermoelectric energy harvesting system, assisted by a piezoelectric generator (PEG) as a cold starter. It exploits the fact that when a thermoelectric energy harvesting system is implemented in a place where kinetic energy is also present, the PEG starter can provide a clock signal to start the...
journal article 2024
document
Wang, Ziyi (author)
Orthopedic surgeries are identified as one of the most noisy surgeries inside the OR (operation room). The highest noise sound level could reach up to around 130 dB, which is harmful to patients’ well-being and are likely to evoke negative feelings during surgery. In the previous study investigating the emotional experience of patients who...
master thesis 2023
document
Wang, C. (author)
The scale of the power system has been significantly expanded in recent decades. To gain real-time insights into the power system, an increasing number of sensors have been deployed tomonitor grid states, resulting in a rapidly growing number of measurement points. Simultaneously, there has also been a rise in the penetration of renewable energy...
doctoral thesis 2023
document
Wang, Z. (author), Huang, Ketong (author), Massobrio, R.M. (author), Bombelli, A. (author), Cats, O. (author)
Network hierarchy describes the relative arrangement of network elements and reflects its fundamental structure. We propose a multi-dimensional topology-based method for quantifying and comparing the extent to which different Public Transport Networks (PTNs) exhibit a hierarchical structure. The proposed method considers the uneven distribution...
journal article 2023
document
Zhao, Wenzhao (author), Fan, Yuling (author), Wang, Hongjian (author), Gemmeke, Hartmut (author), van Dongen, K.W.A. (author), Hopp, Torsten (author), Hesser, Jürgen (author)
Objective. The image reconstruction of ultrasound computed tomography is computationally expensive with conventional iterative methods. The fully learned direct deep learning reconstruction is promising to speed up image reconstruction significantly. However, for direct reconstruction from measurement data, due to the lack of real labeled...
journal article 2023
document
Wang, X. (author), Xie, Qicong (author), Xie, Lei (author), Zhu, Jihua (author), Scharenborg, O.E. (author)
Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary...
journal article 2023
document
Wang, Zhiyi (author)
Deep-learning models are commonly used in short-term precipitation forecasting. However, most deep-learning models are likely to produce blurry output problems. In order to get realistic and accurate results, AENN, a variant of Generative Adversarial Networks (GANs), has been developed. The AENN implements an additional temporal discriminator to...
master thesis 2022
document
Wang, Zhongkai (author), Choi, Minsoo (author), Lee, Kyoungtae (author), Park, Kwanseo (author), Liu, Zhaokai (author), Biswas, Ayan (author), Han, Jaeduk (author), Du, S. (author), Alon, Elad (author)
This article presents a 200-Gb/s pulse amplitude-modulation four-level (PAM-4) and 100-Gb/s non-return-to-zero (NRZ) transmitter (TX) in 28-nm CMOS technology. To achieve the target data rate, the output bandwidth and swing of the proposed TX are optimized by minimizing the output capacitance of the 4:1 multiplexer (MUX) and driver stage with...
journal article 2022
document
Tan, J. (author), Wang, X. (author), Polinder, H. (author), Jarquin Laguna, A. (author), Miedema, S.A. (author)
A crucial part of wave energy converters (WECs) is the power take-off (PTO) mechanism, and PTO sizing has been shown to have a considerable impact on the levelized cost of energy (LCOE). However, as a dominating type of PTO system in WECs, previous research pertinent to PTO sizing did not take modeling and optimization of the linear permanent...
journal article 2022
document
Zhang, Y. (author), An, T. (author), Wang, A. (author), Frey, S. (author), Gurvits, L. (author), Gabányi, K. E. (author), Perger, K. (author), Paragi, Z. (author)
The nature of jets in active galactic nuclei (AGNs) in the early Universe and their feedback to the host galaxy remains a highly topical question. Observations of the radio structure of high-redshift AGNs enabled by very long baseline interferometry (VLBI) provide indispensable input into studies of their properties and role in the galaxies'...
journal article 2022
document
Wang, C. (author), Sharifnia, E. (author), Gao, Zhi (author), Tindemans, Simon H. (author), Palensky, P. (author)
For planning of power systems and for the calibration of operational tools, it is essential to analyse system performance in a large range of representative scenarios. When the available historical data is limited, generative models are a promising solution, but modelling high-dimensional dependencies is challenging. In this paper, a...
journal article 2022
document
Wang, C. (author), Tindemans, Simon H. (author), Palensky, P. (author)
Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient. In this paper, we described a generative model for load profiles of industrial and commercial customers, based on the...
conference paper 2022
document
Wang, Zhongkai (author), Choi, Minsoo (author), Wright, John (author), Lee, Kyoungtae (author), Liu, Zhaokai (author), Yin, Bozhi (author), Han, Jaeduk (author), Du, S. (author), Alon, Elad (author)
We present a ring-oscillator-based sub-sampling phase-locked loop (PLL) using a generator-based design flow. A hybrid loop with a delta-sigma ($\Delta \Sigma$) modulator is applied to reduce the loop filter (LF) area and the control ripple. The generator automatically produces the ring oscillator and PLL to meet the provided specifications. The...
conference paper 2022
document
Wang, Ruizhi (author), Liang, Yansong (author), Du, S. (author)
An ultra-low-startup-voltage thermoelectric energy harvesting system assisted by a piezoelectric generator (PEG) is presented in this paper. When the energy harvesting system is implemented in a place where there is mechanical vibration, the associated PEG can generate a stable clock signal and drive the boost converter to start from the cold...
conference paper 2022
document
Wang, Z. (author), Quaglietta, E. (author), Bartholomeus, Maarten G.P. (author), Goverde, R.M.P. (author)
Automatic Train Operation (ATO) is well-known in urban railways and gets increasing interest from mainline railways at present to improve capacity and punctuality. A main function of ATO is the train trajectory generation that specifies the speed profile over the given running route considering the timetable and the characteristics of the...
journal article 2022
document
Wang, R. (author), Ponsard, Bernard (author), Wolterbeek, H.T. (author), Denkova, A.G. (author)
Background: Radionuclide therapy (RNT) has become a very important treatment modality for cancer nowadays. Comparing with other cancer treatment options, sufficient efficacy could be achieved in RNT with lower toxicity. β<sup>−</sup> emitters are frequently used in RNT due to the long tissue penetration depth of the β<sup>−</sup> particles....
journal article 2022
Searched for: subject%3A%22generalization%22
(1 - 20 of 46)

Pages