Search

Your search keyword '"Zhu, Yadi"' showing total 33 results
Start Over Author "Zhu, Yadi"
33 results on '"Zhu, Yadi"'

2. Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit

Author

Zhang, Jinlei, Chen, Feng, Cui, Zhiyong, Guo, Yinan, and Zhu, Yadi

Subjects
Electrical Engineering and Systems Science - Signal Processing
Abstract

Short-term passenger flow forecasting is an essential component in urban rail transit operation. Emerging deep learning models provide good insight into improving prediction precision. Therefore, we propose a deep learning architecture combining the residual network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM) (called "ResLSTM") to forecast short-term passenger flow in urban rail transit on a network scale. First, improved methodologies of the ResNet, GCN, and attention LSTM models are presented. Then, the model architecture is proposed, wherein ResNet is used to capture deep abstract spatial correlations between subway stations, GCN is applied to extract network topology information, and attention LSTM is used to extract temporal correlations. The model architecture includes four branches for inflow, outflow, graph-network topology, as well as weather conditions and air quality. To the best of our knowledge, this is the first time that air-quality indicators have been taken into account, and their influences on prediction precision quantified. Finally, ResLSTM is applied to the Beijing subway using three time granularities (10, 15, and 30 min) to conduct short-term passenger flow forecasting. A comparison of the prediction performance of ResLSTM with those of many state-of-the-art models illustrates the advantages and robustness of ResLSTM. Moreover, a comparison of the prediction precisions obtained for time granularities of 10, 15, and 30 min indicates that prediction precision increases with increasing time granularity. This study can provide subway operators with insight into short-term passenger flow forecasting by leveraging deep learning models., Comment: in IEEE Transactions on Intelligent Transportation Systems

Published
2019
Full Text
View/download PDF

6. Soluble programmed death-1 (sPD-1) and programmed death ligand 1 (sPD-L1) as potential biomarkers for the diagnosis and prognosis of glioma patients

Author

Liu Shujun, Zhu Yadi, Zhang Chenxi, Liu Jiajia, Lv Hong, Zhang Guojun, and Kang Xixiong

Subjects
soluble programmed death-1, soluble programmed death ligand 1, glioma, biomarkers, prognosis, Biochemistry, QD415-436
Abstract

Background: This study aimed at investigating the feasibility of testing for soluble programmed death-1 (sPD-1) and soluble programmed death ligand 1 (sPD-L1) in serum samples of glioma patients and to evaluate the diagnostic and prognostic value of these two soluble molecules. Methods: Serum samples collected from 70 glioma patients before surgery were designated as the pre-operative (Pre) group, samples obtained from 90 post-surgery glioblastoma patients were designated as the Post group, and samples from 20 healthy volunteers were used as controls. Peripheral blood sPD-1 and sPD-L1 levels were detected by using ELISA kits and compared among the groups. The associations of these soluble molecule levels with clinicopathological variables and tumour progression were investigated. Results: Among the three groups, the Pre group had the highest sPD-1 levels, whereas the median sPD-L1 level was significantly lower in the Post group than in the other two groups. The area under the curve (AUC) of sPD-1 (0.762) for diagnosis was similar to that of sPD-L1 (0.718). Higher serum levels of sPD-1 and sPD-L1 were present in samples of patients with more advanced brain tumours. Kaplan-Meier analysis showed that higher serum levels of sPD-1 (>11.14 pg/mL) and sPD-L1 (>63.03 pg/mL) might predict shorter progression-free survival times of glioma patients. Conclusions: This study showed that sPD-1 and sPD-L1 might be promising predictive biomarkers for the diagnosis and prognosis of glioma patients.

Published
2020

7. Fire evacuation integration modelling in subway station using the lattice Boltzmann method.

Author

Zhu, Yadi, Han, Fengfan, Yang, Yang, and Li, Xiaohong

Subjects
*LATTICE Boltzmann methods, *FIRE protection engineering, *SUSTAINABLE communities, *SUSTAINABLE urban development, *BUS terminals, *SUBWAY stations
Abstract

Fire evacuation simulations are essential for assessing evacuation schemes in subway stations. However, most studies and practical solutions have primarily focused on the effects of fire smoke on the evacuation behaviour of evacuees. Moreover, these solutions overlook the effects of the movement of evacuees on fire-smoke diffusion; hence, they do not adequately reflect fire–pedestrian interaction. This study addresses this problem by formulating a fire-smoke evolution model using the lattice Boltzmann method to simulate fire smoke from a mesoscopic perspective. The proposed model can reflect fire-smoke diffusion, including the effects of evacuees on the evacuation scheme. The model easily exchanges data with the microscopic pedestrian simulation model. An agent-based evacuation model is formulated using the social force method. The agent can regulate the evacuation states using perceptive environment information. Finally, the models are integrated into one framework to evaluate fire–pedestrian interaction. A simplified fire evacuation scenario based on a two-dimensional subway station platform is simulated using the proposed integration model. The results show that the proposed integration model can simulate the effect of the disturbance of the movement of evacuees on fire-smoke diffusion and evaluate fire–pedestrian interaction. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

9. Artificial Intelligence Aided Crowd Analytics in Rail Transit Station

Author

Zhu, Yadi, Ni, Ke, Li, Xiaohong, Zaman, Asim, Liu, Xiang, and Bai, Yun

Abstract

Crowd analysis and management is a key area of study for transit agencies seeking to optimize their operations and to facilitate safety risk management activities. Key features of crowd analytics include passenger flow volume, crowd density, and walking speed. This study proposes a generalized artificial intelligence (AI)-based crowd analytics model framework for rail transit stations, by analyzing and visualizing crowd analysis data from video records of high-density crowds. Specifically, we propose a generalized AI-aided methodological framework (AI-Crowd) for calculating flow volume, crowd density, and walking speed. You Only Look Once (YOLO) and Deep SORT are integrated into the model framework to detect and track each individual’s dynamic position. Camera calibration is utilized to transform detected trajectories into a real-world coordinate system. Methods for calculating crowd dynamic metrics are formulated based on the data. To validate the model framework, several video records from a platform scenario at a major rail transit station are used. The model’s pedestrian counting accuracy can reach 95% and the fundamental diagrams of density–speed are shown to be consistent with empirical studies. Further crowd analysis of a stair scenario and a transferring passage scenario using the proposed model framework shows some differentiations in walking behavior. The methodology has further practical applications, such as monitoring social distancing.

Published
2024
Full Text
View/download PDF

10. Artificial Intelligence Aided Crowd Analytics in Rail Transit Station

Author

Zhu, Yadi, Ni, Ke, Li, Xiaohong, Zaman, Asim, Liu, Xiang, Bai, Yun, Zhu, Yadi, Ni, Ke, Li, Xiaohong, Zaman, Asim, Liu, Xiang, and Bai, Yun

Abstract

Crowd analysis and management is a key area of study for transit agencies seeking to optimize their operations and to facilitate safety risk management activities. Key features of crowd analytics include passenger flow volume, crowd density, and walking speed. This study proposes a generalized artificial intelligence (AI)-based crowd analytics model framework for rail transit stations, by analyzing and visualizing crowd analysis data from video records of high-density crowds. Specifically, we propose a generalized AI-aided methodological framework (AI-Crowd) for calculating flow volume, crowd density, and walking speed. You Only Look Once (YOLO) and Deep SORT are integrated into the model framework to detect and track each individual's dynamic position. Camera calibration is utilized to transform detected trajectories into a real-world coordinate system. Methods for calculating crowd dynamic metrics are formulated based on the data. To validate the model framework, several video records from a platform scenario at a major rail transit station are used. The model's pedestrian counting accuracy can reach 95% and the fundamental diagrams of density-speed are shown to be consistent with empirical studies. Further crowd analysis of a stair scenario and a transferring passage scenario using the proposed model framework shows some differentiations in walking behavior. The methodology has further practical applications, such as monitoring social distancing.

Published
2023

12. Midazolam Ameliorates Acute Liver Injury Induced by Carbon Tetrachloride via Enhancing Nrf2 Signaling Pathway

Author

Zhang, Yongyan, Zhu, Yadi, Li, Ying, Ji, Feng, Ge, Guangbo, and Xu, Hua

Subjects
Pharmacology, Pharmacology (medical)
Abstract

Oxidative stress contributes greatly to initiation and progression of liver injury. Activation of nuclear-factor erythroid 2-related factor 2 (Nrf2) has been considered as an attractive strategy for preventing and treating the oxidative damage related to liver injury. This study aimed to find an efficacious agent to activate Nrf2/HO-1 signaling pathway from clinically used therapeutic agents and to characterize the usefulness for preventing and treating CCl4-induced acute liver injury. For this purpose, a series of clinically used therapeutic agents were collected and their activation potentials on Nrf2 were assayed by using 293T-Nrf2-luc cell line. Among all tested therapeutic agents, midazolam was found with good Nrf2 activation effect and this agent could significantly ameliorate CCl4-induced damage to HepG2 cells. In vivo animal tests showed that pretreatment with midazolam reduced the liver pathological tissue damage and the serum levels of ALT and AST in CCl4-induced liver injury mice. Further investigations showed that midazolam could strongly up-regulate the expression of both Nrf2 and HO-1 in the mice liver, accompanied by increasing of the levels of antioxidant enzyme SOD and reducing the production of MDA, as well as reducing the pro-inflammatory cytokines (IL-6, TNF-α) secretion. Collectively, our results clearly demonstrate that midazolam can ameliorate CCl4-induced acute liver injury and oxidative stress via activating the Nrf2 signaling pathway.

Published
2022
Full Text
View/download PDF

20. Alterations in Effective Connectivity of the Hippocampus in Migraine without Aura

Author

Zhu,Yadi, Dai,Lingling, Zhao,Hongru, Ji,Boan, Yu,Yang, Dai,Hui, Hu,Chunhong, Wang,Ximing, Ke,Jun, Zhu,Yadi, Dai,Lingling, Zhao,Hongru, Ji,Boan, Yu,Yang, Dai,Hui, Hu,Chunhong, Wang,Ximing, and Ke,Jun

Abstract

Yadi Zhu,1,2,* Lingling Dai,1,2,* Hongru Zhao,3,* Boan Ji,4 Yang Yu,1,2 Hui Dai,1,2 Chunhong Hu,1,2 Ximing Wang,1,2 Jun Ke1,2 1Department of Radiology, The First Affiliated Hospital of Soochow University, Soochow, Jiangsu Province, People’s Republic of China; 2Institute of Medical Imaging, Soochow University, Soochow, Jiangsu Province, People’s Republic of China; 3Department of Neurology, The First Affiliated Hospital of Soochow University, Soochow, Jiangsu Province, People’s Republic of China; 4Medical School of Soochow University, Soochow, Jiangsu Province, People’s Republic of China*These authors contributed equally to this workCorrespondence: Ximing Wang; Jun KeDepartment of Radiology, The First Affiliated Hospital of Soochow University, No. 188 Shizi Road, Soochow, 215000, Jiangsu Province, People’s Republic of ChinaTel +86-512-67973062Fax +86-512-67973061Email wangximing1998@163.com; fmrikej@126.comPurpose: Neuroimaging studies on migraine have revealed structural and functional alterations in the hippocampus, a region involved in pain processing and stress response. This study was designed to investigate whether effective connectivity of this region is disrupted in migraine and relates to chronicity of this disease.Patients and Methods: In 39 episodic migraine (EM) patients, 17 chronic migraine (CM) patients, and 35 healthy controls, we investigated differences in the directional influences between the hippocampus and the rest of the brain by combining resting-state functional magnetic resonance imaging and Granger causality analysis (GCA), with bilateral hippocampus as seed regions. The associations between directional influences and the clinical variables were also examined.Results: Comparing each patient group to the control group, we found increased and decreased negative influence on the hippocampus exerted by the bilateral visual areas and right dorsolateral prefrontal cortex (dlPFC), respectively. The hippocamp

Published
2021

32. Optimized design of signal crosstalk in high speed PCB

Author

Tian Wenchao, Zhu Yadi, Shan Lei, and Wang Wenlong

Subjects
Crosstalk, Amplitude, Computer science, Low-power electronics, Electronic engineering, Data lines, Detection theory, Signal integrity, Field-programmable gate array, Signal acquisition
Abstract

Aiming to the high signal crosstalk noise in key data line D2 of the FPGA dual-channel signal acquisition system with 6 layers, the data line D2 design is optimized by adjusting the line spaces. The simulation results show that the amplitude of crosstalk noise decreases from 415mV without optimized to 141mV with optimized at frequency 133MHz. The decline reaches up to 294%.

Published
2012
Full Text
View/download PDF

33. Dose optimization of extended collimators in boron neutron capture therapy.

Author

Zhu Y, Lian C, Ji X, Zhang X, Li C, Bai Y, and Gao J

Subjects
Humans, Gamma Rays, Computer Simulation, Radiotherapy Planning, Computer-Assisted methods, Neoplasms radiotherapy, Equipment Design, Polyethylene chemistry, Organs at Risk radiation effects, Boron Neutron Capture Therapy methods, Boron Neutron Capture Therapy instrumentation, Monte Carlo Method, Phantoms, Imaging, Radiotherapy Dosage, Neutrons
Abstract

In this paper, we propose the design of extending collimators aimed at reducing the radiation dose received by patients with normal tissues and protecting organs at risk in Boron Neutron Capture Therapy (BNCT). Three types of extended collimators are studied: Type 1, which is a traditional design; Type 2, which is built upon Type 1 by incorporating additional polyethylene material containing lithium fluoride (PE(LiF)); Type 3, which adds lead (Pb) to Type 1. We evaluated the dose distribution characteristics of the above-extended collimators using Monte Carlo methods simulations under different configurations: in air, in a homogeneous phantom, and a humanoid phantom model. Firstly, the neutron and gamma-ray fluxes at the collimator outlet of the three designs showed no significant changes, thus it can be expected that their therapeutic effects on tumors will be similar. Then, the dose distribution outside the irradiation field was studied. The results showed that, compared with Type 1, Type 2 has a maximum reduction of 57.14% in neutron leakage dose, and Type 3 has a maximum reduction of 21.88% in gamma-ray leakage dose. This will help to reduce the radiation dose to the local skin. Finally, the doses of different organs were simulated. The results showed that the neutron dose of Type 2 was relatively low, especially for the skin, thyroid, spinal cord, and left lung, with the neutron dose reduced by approximately 20.34%, 16.18%, 26.05%, and 18.91% respectively compared to Type 1. Type 3 collimator benefits in reducing gamma-ray dose for the thyroid, esophagus, and left lung organs, with gamma-ray dose reductions of around 10.81%, 9.45%, and 10.42% respectively. This indicates that attaching PE(LiF) or Pb materials to a standard collimator can suppress the dose distribution of patient organs, which can provide valuable insights for the design of extended collimators in BNCT., (© 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.)

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results