DSpace Collection:https://hdl.handle.net/10356/791722024-03-24T18:39:56Z2024-03-24T18:39:56ZCrowdFL: a marketplace for crowdsourced federated learningFeng, DaifeiHelena, CiciliaLim, Bryan Wei YangNg, Jer ShyuanJiang, HongchaoXiong, ZehuiKang, JiawenYu, HanNiyato, DusitMiao, Chunyanhttps://hdl.handle.net/10356/1560422023-12-29T06:44:16Z2022-01-01T00:00:00ZTitle: CrowdFL: a marketplace for crowdsourced federated learning
Authors: Feng, Daifei; Helena, Cicilia; Lim, Bryan Wei Yang; Ng, Jer Shyuan; Jiang, Hongchao; Xiong, Zehui; Kang, Jiawen; Yu, Han; Niyato, Dusit; Miao, Chunyan
Abstract: Amid data privacy concerns, Federated Learning (FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists a need for a platform that matches data owners (supply) with model requesters (demand). In this paper, we present CrowdFL, a platform to facilitate the crowdsourcing of FL model training. It coordinates client selection, model training, and reputation management, which are essential steps for the FL crowdsourcing operations. By implementing model training on actual mobile devices, we demonstrate that the platform improves model performance and training efficiency. To the best of our knowledge, it is the first platform to support crowdsourcing-based FL on edge devices.2022-01-01T00:00:00ZA molecular dynamics study into zeolitic imidazolate frameworks-based capacitive deionization electrodes for Mg²⁺ removal and seawater desalinationHong, Terence Zhi XiangDahanayaka, MadhaviLiu, BoLaw, Adrian Wing-KeungZhou, Kunhttps://hdl.handle.net/10356/1554302022-06-25T20:11:16Z2022-01-01T00:00:00ZTitle: A molecular dynamics study into zeolitic imidazolate frameworks-based capacitive deionization electrodes for Mg²⁺ removal and seawater desalination
Authors: Hong, Terence Zhi Xiang; Dahanayaka, Madhavi; Liu, Bo; Law, Adrian Wing-Keung; Zhou, Kun
Abstract: In this study, molecular dynamics simulations are performed to study the surface interactions between the zeolitic imidazolate frameworks (ZIFs)-based capacitive deionization (CDI) electrodes with seawater and Mg2+ ions. Using the same organic linkers but different metal atoms to construct the electrodes, the CDI performance of the said electrodes is tested in terms of ion rejection and water flux. The effects of metal atoms on the ZIF interactions with the seawater and Mg2+ are studied and explained using ion distribution, water velocity, and radial distribution function (RDF). The results revealed that the metal and N atoms have a strong affinity for ions, and the maximum ion rejection by the electrode achieved in the presence of Mg2+ is 97.6%. Furthermore, ZIF hydrophilicity is dependent on the metal atoms which have the strongest affinity with water molecules, and this water affinity determines the water flux. Overall, the results proved that metal atoms can influence the ZIF performance. Among the four ZIFs tested, CdIF-1 has the best performance.2022-01-01T00:00:00ZMonte Carlo simulations and photoacoustic experiments to compare imaging depth at 532 nm, 800 nm, and 1064 nmSharma, ArunimaSrishti, SrishtiPeriyasamy, VijithaPramanik, Manojithttps://hdl.handle.net/10356/1466492023-12-29T06:44:09Z2020-01-01T00:00:00ZTitle: Monte Carlo simulations and photoacoustic experiments to compare imaging depth at 532 nm, 800 nm, and 1064 nm
Authors: Sharma, Arunima; Srishti, Srishti; Periyasamy, Vijitha; Pramanik, Manojit
Abstract: Photoacoustic imaging (PAI) is a rapidly growing imaging modality which offers the advantages of good optical contrast and high ultrasound resolution. Although PAI provides imaging depth beyond the optical diffusion limit, penetration depth in biological samples is limited due to absorption and scattering of light in tissues. Improvement in imaging depth has been achieved by irradiating the sample with laser pulses of near infrared-I (NIR-I) region (700 nm-900 nm) due to decreased scattering of light in tissues within this optical window. Recently, further improvement in imaging depth has been reported by irradiating the sample in near infrared-II (NIR-II) region (900 nm-1700 nm). In this work, imaging depth in breast tissues when samples were irradiated by wavelengths in different optical windows has been compared. Initially, Monte Carlo simulation for light propagation in biological tissues was performed to compute imaging depth for excitation wavelengths of 532 nm, 800 nm, and 1064 nm. Further, photoacoustic tomography at 532 nm, 740 nm, and 1064 nm and acoustic resolution photoacoustic microscopy at 570 nm and 1064 nm were conducted to validate the results. We have shown that maximum imaging depth is achieved by NIR-I (740 nm/800 nm) when surface energy for all wavelengths is kept constant. However, when the energy density is proportional to maximum permissible exposure (MPE) at corresponding wavelength, maximum imaging depth is achieved by 1064 nm (NIR-II window). Therefore, we conclude that increased MPE in NIR-II window is responsible for the improved penetration depth in breast tissue in this region.2020-01-01T00:00:00ZIn vivo evaluation of cerebral venous sinus morphology using pulsed-laser-diode-based desktop photoacoustic tomography systemRajendran, PraveenbalajiSahu, SamiranDienzo, Rhonnie AustriaPramanik, Manojithttps://hdl.handle.net/10356/1465652023-12-29T06:44:12Z2020-01-01T00:00:00ZTitle: In vivo evaluation of cerebral venous sinus morphology using pulsed-laser-diode-based desktop photoacoustic tomography system
Authors: Rajendran, Praveenbalaji; Sahu, Samiran; Dienzo, Rhonnie Austria; Pramanik, Manojit
Abstract: Assessment of morphological changes in cerebral venous sinus of small animal models is important to gain insights of various disease conditions such as intracranial hypotension, Idiopathic intracranial hypertension (IIH), Cerebral venous sinus thrombosis, subdural hematoma etc. Photoacoustic Tomography (PAT), a fast-growing non-invasive hybrid imaging modality which combines high optical contrast and resolution in deep tissue imaging offers a novel, rapid and cost-effective way to analyze the morphological changes of venous sinus in comparison with the conventional imaging modalities. In this study, we examined the morphological changes of sagittal sinus in the rat brain due to intracranial pressure changes induced by Cerebrospinal fluid (CSF) extraction using low cost pulsed laser diode (PLD) based desktop (PAT) system. Our results indicate that the desktop PLD-PAT system can be employed to evaluate the changes in the cerebral venous sinus in preclinical models. We observed a ∼30% average increase in the area of sagittal venous sinus from the baseline, when the CSF is extracted.2020-01-01T00:00:00Z