10 results on '"Wang, Zixuan"'
Search Results
2. Machine learning accelerated carbon neutrality research using big data—from predictive models to interatomic potentials
- Author
-
Wu, LingJun, Xu, ZhenMing, Wang, ZiXuan, Chen, ZiJian, Huang, ZhiChao, Peng, Chao, Pei, XiangDong, Li, XiangGuo, Mailoa, Jonathan P., Hsieh, Chang-Yu, Wu, Tao, Yu, Xue-Feng, and Zhao, HaiTao
- Published
- 2022
- Full Text
- View/download PDF
3. Data‐Driven Fine Element Tuning of Halide Double Perovskite for Enhanced Photoluminescence.
- Author
-
Wu, Lingjun, Chen, Zijian, Yuan, Zhongcheng, Wu, Bobin, Liu, Shaohui, Wang, Zixuan, Mailoa, Jonathan P., Duan, Chenru, Huang, Hao, Hsieh, Chang‐Yu, Yu, Xue‐Feng, and Zhao, Haitao
- Subjects
PHOTOLUMINESCENCE ,PEROVSKITE ,HALIDES ,ION pairs ,X-ray diffraction ,MACHINE learning - Abstract
Element tuning of targeted materials and obtaining the optimal synthesis recipe are major goals for many material scientists. However, this is often limited by conventional trial‐and‐error procedures, which are time‐consuming and labor‐intensive. In this work, fine element tuning of halide double perovskite Cs2NaxAg1‐xInyBi1‐yCl6 is conducted by performing a data‐driven investigation combining high‐throughput experiments with machine learning (ML). A positive correlation between the more accessible R value in emission RGB values (the intensities of the red/green/blue primary colors) and photoluminescence intensity is revealed, and over a thousand R values of the Cs2NaxAg1‐xInyBi1‐yCl6 crystals synthesized with different additives and element compositions are collected. More importantly, the volume ratios of Na+/Ag+ (VNa: VAg) and Bi3+/In3+ (VBi: VIn) with the corresponding R values are correlated through ML, and the synergistic regulation of the two ion pairs is revealed. A possible correlation between R and XRD is also proposed. Finally, different emission intensities of LED beads coated with Cs2NaxAg1‐xInyBi1‐yCl6 synthesized using parameters obtained from ML are demonstrated, and an emission enhancement of ≈50 times is observed between the brightest and dimmest LEDs. This work illustrates that data‐driven investigation helps guide material synthesis and will significantly reduce the workload for developing novel materials, especially for complex compositions. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Genetic algorithm-based feature selection with manifold learning for cancer classification using microarray data.
- Author
-
Wang, Zixuan, Zhou, Yi, Takagi, Tatsuya, Song, Jiangning, Tian, Yu-Shi, and Shibuya, Tetsuo
- Subjects
- *
TUMOR classification , *MACHINE learning , *CANCER genes , *GENETIC algorithms , *BLENDED learning , *FEATURE selection - Abstract
Background: Microarray data have been widely utilized for cancer classification. The main characteristic of microarray data is "large p and small n" in that data contain a small number of subjects but a large number of genes. It may affect the validity of the classification. Thus, there is a pressing demand of techniques able to select genes relevant to cancer classification. Results: This study proposed a novel feature (gene) selection method, Iso-GA, for cancer classification. Iso-GA hybrids the manifold learning algorithm, Isomap, in the genetic algorithm (GA) to account for the latent nonlinear structure of the gene expression in the microarray data. The Davies–Bouldin index is adopted to evaluate the candidate solutions in Isomap and to avoid the classifier dependency problem. Additionally, a probability-based framework is introduced to reduce the possibility of genes being randomly selected by GA. The performance of Iso-GA was evaluated on eight benchmark microarray datasets of cancers. Iso-GA outperformed other benchmarking gene selection methods, leading to good classification accuracy with fewer critical genes selected. Conclusions: The proposed Iso-GA method can effectively select fewer but critical genes from microarray data to achieve competitive classification performance. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
5. Scalable energy management approach of residential hybrid energy system using multi-agent deep reinforcement learning.
- Author
-
Wang, Zixuan, Xiao, Fu, Ran, Yi, Li, Yanxue, and Xu, Yang
- Subjects
- *
DEEP reinforcement learning , *MACHINE learning , *ENERGY management , *MULTIAGENT systems , *THERMAL comfort , *REINFORCEMENT (Psychology) , *REINFORCEMENT learning , *SOLAR technology - Abstract
Deploying renewable energy and implementing smart energy management strategies are crucial for decarbonizing Building Energy Systems (BES). Despite recent advancements in data-driven Deep Reinforcement Learning (DRL) for BES optimization, significant challenges still exist, such as the time-consuming and data-intensive nature of training DRL controllers and the complexity of environment dynamics in Multi-Agent Reinforcement Learning (MARL). Consequently, these obstacles impede the synchronization and coordination of multiple agent control, leading to slow DRL convergence performance. To address these issues. This paper proposes a novel approach to optimize hybrid building energy systems. We introduce an integrated system combining a multi-stage Proximal Policy Optimization (PPO) on-policy framework with Imitation Learning (IL), interacting with the model environment. To improve scalability and robustness of Multi-agent Systems (MAS), this approach is designed to enhance training efficiency with centralized training and decentralized execution. Simulation results of case studies demonstrate the effectiveness of the Multi-agent Deep Reinforcement Learning (MADRL) model in optimizing the operations of hybrid building energy systems in terms of indoor thermal comfort and energy efficiency. Results show the proposed framework significantly improve performance in achieving convergence in just 50 episodes for dynamic decision-making. The scalability and robustness of the proposed model have been validated across various scenarios. Compared with the baseline during cold and warm weeks, the proposed control approach achieved improvements of 34.86% and 46.10% in energy self-sufficiency ratio, respectively. Additionally, the developed MADRL effectively improved solar photovoltaic (PV) self-consumption and reduced household energy costs. Notably, it increased the average indoor temperature closer to the desired set-point by 1.33 °C, and improved the self-consumption ratio by 15.78% in the colder week and 18.47% in the warmer week, compared to baseline measurements. These findings highlight the advantages of the multi-stage PPO on-policy framework, enabling faster learning and reduced training time, resulting in cost-effective solutions and enhanced solar PV self-consumption. • Integrated a multi-stage RL algorithm with imitation learning in the MAPPO framework to optimize system energy performances. • Proposed model achieved faster MAPPO convergence under resource constraints • Introduced a shared reward function in MAPPO to align agent incentives with collective energy optimization. • Improved solar PV self-consumption and reduced energy costs while maintaining indoor thermal comfort with MAPPO. • Validated the scalability and adaptability of MAPPO across various scenarios. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Transfer Learning Based Screen Defect Classification
- Author
-
Chang Shuo, Li Yilei, wang zixuan, Zhang Yifan, Zhang Fan, and Li Chengyuan
- Subjects
Training set ,Test data generation ,Computer science ,business.industry ,Process (computing) ,Overfitting ,Machine learning ,computer.software_genre ,Convolutional neural network ,Model learning ,Learning based ,Artificial intelligence ,Transfer of learning ,business ,computer - Abstract
For the screen defect classification, human inspectors and traditional machine learning algorithms are inefficient and inaccurate. Convolutional neural network (CNN) driven by data are feasible solutions. However, real training images are limited in the industrial scenario, which causes overfitting. Hence, in this paper, a novel learning based method is proposed for defect classification, which is based on the CNN. To alleviate the problem of limited images, two strategies are introduced into model learning. For the training data, a data generation module is implemented to enlarge the training dataset. For the CNN model learning, transfer learning is applied in the whole training process. To verify the proposed method, various experiments are carried out. The results indicate that our screen defect classification model achieves superior performance.
- Published
- 2020
7. Network traffic classification based on federated semi-supervised learning.
- Author
-
Wang, ZiXuan, Li, ZeYi, Fu, MengYi, Ye, YingChun, and Wang, Pan
- Subjects
- *
FEDERATED learning , *COMPUTER network traffic , *SUPERVISED learning , *DATA privacy , *DEEP learning , *MACHINE learning - Abstract
Traffic Classification (TC) has been applied to a wide range of applications, from security monitoring to quality of service (QoS) provisioning in network Internet Service Providers (ISPs). In recent years, many researchers have applied Machine Learning (ML) or Deep Learning (DL) to TC, namely AI-TC. However, AI-TC methods face significant challenges, including high data dependency, exhaustively costly traffic labeling, and network subscribers' privacy. This paper proposes a TC framework for smart home networks using Federated Learning (FL) that protects traffic data privacy by performing local training and inference of TC models. Firstly, we design a DPI-based traffic labeling method on edge home gateways as FL nodes, which enables these nodes to have data labeling capability while protecting data privacy. Then, a semi-supervised TC model based on an autoencoder (AE) is proposed to reduce the dependence of the model on labeled traffic samples. Finally, an XAI-based method is utilized to interpret the model to ensure its explainability. We validate the proposed method on public and real datasets using benchmarking methods. The experimental results show that the method can achieve high performance using a small number of samples while protecting data privacy and improving the model's credibility. Experimental code can be found in the following url: https://github.com/PrinceXuan12138/HGW-TC-Experimental-code. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
8. Prediction of rural domestic water and sewage production based on automated machine learning in northern China.
- Author
-
Cao, Yingnan, Wang, Zixuan, Li, Pengyu, Zhou, Ziyu, Li, Wenkai, Zheng, Tianlong, Liu, Jianguo, Wu, Wenjun, Shi, Zhining, and Liu, Junxin
- Subjects
- *
SEWAGE , *RESIDENTIAL water consumption , *MACHINE learning , *SEWAGE purification , *WATER consumption - Abstract
Determining the rural domestic water consumption (RDWS, L/person-day) and rural sewage production (RSP, L/person-day) of rural residents at the county scale can provide decision support for rural domestic sewage treatment. However, methods for predicting county-scale RDWS and RSP based on geographical, social, and governance factors are rarely reported. This paper proposes an RDWS and RSP prediction method based on Automated Machine Learning (AutoML) for the Inner Mongolia Autonomous Region. The RDWS and RSP in the Inner Mongolia Autonomous Region were successfully predicted from multi-source data. The AutoML model accurately predicted RDWS (mean absolute error = 1.7072, R2 = 0.7759) and RSP (mean absolute error = 0.6580, R2 = 0.65107). Average years of education (AYOS), proportion of resident population, and proportion of elderly and children (POEAC) were key driving factors related to RDWS prediction. The most important factors associated with RSP prediction were AYOS, POEAC, and annual average precipitation (AAP). An explanatory analysis further revealed dependence between the input variables, RDWS, and RSP. The framework was demonstrated to be a practical tool for qualitative and quantitative analyses of rural domestic water consumption and domestic sewage production in the Inner Mongolia Autonomous Region. Overall, this study provides a solution for predicting county-level RDWS and RSP, providing a reference for the design of rural domestic sewage treatment. [Display omitted] • Less than 24% of rural domestic sewage is currently treated in Inner Mongolia. • Planning needs county-scale domestic water consumption and sewage production data. • Best of many models based on data from multiple sources were selected automatically. • Nonlinear relationships between input output variables were quickly revealed. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
9. Adaptive Visual Interaction Based Multi-Target Future State Prediction For Autonomous Driving Vehicles.
- Author
-
Du, Li, Wang, Zixuan, Zhao, Zhicheng, Su, Fei, Wang, Leiquan, Zhuang, Bojin, and Boulgouris, Nikolaos V.
- Subjects
- *
AUTONOMOUS vehicles , *TRAFFIC estimation , *PREDICTION models , *VISUAL aids , *COMPUTER vision , *MACHINE learning - Abstract
Predicting the state of dynamic objects in a real traffic environment is a key issue in autonomous driving vehicles. Various approaches have been proposed to learn the dynamics from visual observations with static background. However, minimal research has been conducted in a real traffic environment due to the complicated and changeable scenes. This paper proposes an adaptive multi-target future state prediction (position/velocity) method under autonomous driving conditions. In particular, an adaptive visual interaction method and control mechanism are introduced to overcome the change in the number of objects in continuous driving frames. In addition, a two-stream architecture with stage-wise learning is utilized for accurate object state prediction by simultaneously complementing spatial and temporal information. Experiments on two public challenging datasets, namely Udacity (CrowdAI) and Udacity (Autti), demonstrate the effectiveness of the proposed method on multi-target dynamic state prediction in a real traffic environment. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
10. 771: MACHINE LEARNING PREDICTION OF RESPONSIVENESS PHENOTYPES IN NON-NEUROLOGIC ICU PATIENTS.
- Author
-
XU, Haoyin, Desman, Jacob, Huang, Qianqi, Igboko, Munachiso, Kodibagkar, Alisha, Wang, Zixuan, Gong, Kirby, Winslow, Raimond, Greenstein, Joseph, and Stevens, Robert
- Subjects
- *
MACHINE learning , *PHENOTYPES , *BLOOD cell count - Abstract
B Conclusions: b In patients admitted to the ICU with a non-neurological illness, machine learning models trained with data collected in the first 24 hours of ICU stay accurately predicted responsiveness at discharge. B Introduction/Hypothesis: b A significant number of patients admitted to ICU for a non-neurological illness develop an encephalopathy characterised by decreased levels of responsiveness. [Extracted from the article]
- Published
- 2022
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.