Article
Automation & Control Systems
XuDong Shi, Qi Kang, Jing An, MengChu Zhou
Summary: This article proposes a novel L1 norm-based extreme learning machine (ELM) by integrating bound optimization theory with variational Bayesian inference. The proposed method efficiently solves the overfitting problem and demonstrates competitive performance in an industrial case study.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Biotechnology & Applied Microbiology
Victor Pozzobon, Wendie Levasseur, Cedric Guerin, Patrick Perre
Summary: The article introduces a machine learning workflow to construct spectrophotometric equations predicting nitrate and nitrite concentrations in microalgae culture samples. The workflow involves recording UV absorbance spectra of samples, constructing a machine learning model based on partial least square regression, and utilizing 3 wavelengths to quantify nitrate and nitrite concentrations. The proposed equations provide a faster and more accurate alternative to ion chromatography for determining sample concentrations.
JOURNAL OF APPLIED PHYCOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Shuang Hou, Yi Wang, Sixian Jia, Meiqi Wang, Xiaosheng Wang
Summary: This study proposes a least squares ELM with derivative characteristics (DLSELM) which increases the diversity of activation functions in the network and determines the weights and biases of the network through a twice least squares method. DLSELM possesses the best regression accuracy, stability, and generalization performance compared with the other networks.
Article
Automation & Control Systems
Xudong Shi, Qi Kang, Hanqiu Bao, Wangya Huang, Jing An
Summary: This paper proposes a principal component-based semi-supervised extreme learning machine (PCSELM) model, which can simultaneously extract latent features and learn the nonlinear input-output relationship, thus efficiently utilizing unlabeled samples for feature representation and model accuracy improvement.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Feixiang Zhao, Mingzhe Liu, Kun Wang, Tao Wang, Xin Jiang
Summary: The proposed approach utilizes SPCA for dimensionality reduction and an improved ELM algorithm, LSO-ELM, for soft measurement model construction, showing excellent performance on BOD5 and COD prediction in wastewater treatment process.
Review
Computer Science, Artificial Intelligence
Gongming Wang, Qing-Shan Jia, MengChu Zhou, Jing Bi, Junfei Qiao, Abdullah Abusorrah
Summary: This paper presents a comprehensive survey on water quality soft-sensing in wastewater treatment processes using artificial neural networks (ANNs). It covers problem formulation, common models, practical examples, and performance discussions. Various soft-sensing models are compared in terms of accuracy, efficiency, and complexity, with factors affecting the accuracy discussed as well. Challenges in soft-sensing models of WWTP are also pointed out for future exploration.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Computer Science, Information Systems
Maira Alvi, Tim French, Rachel Cardell-Oliver, Philip Keymer, Andrew Ward
Summary: Wastewater treatment plants are complex systems that require monitoring using sensor systems. Soft sensor models can be a cost-effective alternative to expensive sensors for certain parameters in wastewater. This paper proposes a hybrid neural network architecture for learning soft sensors for complex phenomena, and validates the effectiveness using real-world data from a wastewater treatment plant. Additionally, a annotated dataset of a secondary wastewater treatment plant is publicly released to accelerate research in the development of soft sensors.
Article
Chemistry, Multidisciplinary
Mojtaba Farrokh, Farzaneh Ghasemi, Mohammad Noori, Tianyu Wang, Vasilis Sarhosis
Summary: This study proposes a novel approach combining extreme learning machine (ELM) and least-squares support vector machine (LS-SVM) for simulating hysteresis with different features. The approach accurately identifies hysteretic systems and provides more accurate results with lower computational cost compared to previous experimental studies.
APPLIED SCIENCES-BASEL
(2022)
Review
Engineering, Environmental
Phoebe M. L. Ching, Richard H. Y. So, Tobias Morck
Summary: The use of soft sensors in wastewater treatment plants has advanced significantly, from mechanistic modelling to machine learning models. Neural networks have been the dominant methodology for soft sensor development, but decision tree-based approaches have shown promising performance and enhanced robustness. Utilizing soft sensor modelling approaches can enhance hardware sensor performance, leading to continuous improvements in reliability and measurement range.
JOURNAL OF WATER PROCESS ENGINEERING
(2021)
Article
Environmental Sciences
P. M. L. Ching, X. Zou, Di Wu, R. H. Y. So, G. H. Chen
Summary: This study developed a new soft sensor using XGBoost machine learning to measure the concentration of organics in wastewater. Compared to conventional soft sensors, this new sensor can more accurately detect extremely high levels of pollutants.
ENVIRONMENTAL RESEARCH
(2022)
Article
Mathematics, Applied
Qing Wu, Fan Wang, Yu An, Ke Li
Summary: In this paper, a novel extreme learning machine algorithm called L-1-ACELM is proposed to address the overfitting problem. The algorithm benefits from L-1 norm and replaces the square loss function with the AC-loss function, which is non-convex, bounded, and relatively insensitive to noise. Experimental results show that L-1-ACELM achieves better generalization performance compared to other state-of-the-art algorithms, especially in the presence of noise.
Article
Engineering, Environmental
Jinlin Xiong, Zihan Tao, Lei Hua, Xiujie Qiao, Tian Peng, Muhammad Shahzad Nazir, Chu Zhang
Summary: Accurate and prompt measurement of key variables, such as effluent ammonia nitrogen (NH4-N) and biological oxygen demand (BOD), is crucial in wastewater treatment. This study proposes a soft measurement model that combines random forest (RF), enhanced atomic search optimization (EASO), and online sequential outlier robust extreme learning machine (OSORELM) for this purpose. The model selects auxiliary variables with high correlation to NH4-N and BOD using RF, improves algorithm performance through dynamic perturbation and generalized opposition-based learning in ASO, and optimizes hyperparameters using EASO. The results demonstrate that the proposed model has better prediction accuracy and robustness in soft measurements of NH4-N and BOD.
JOURNAL OF WATER PROCESS ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Chang Peng, Bao Xun, Meng FanChao, Lu RuiWei
Summary: Under the increasingly severe fresh water supply pressure, wastewater treatment is considered to be the optimal strategy to satisfy the current and future water demand, thus being highly valued by most countries. However, there are some hard-to-measure effluent indicators in wastewater treatment, which brings significant difficulties to the monitoring of key indicators in sewage disposal process, thus imposing massive constraints on evaluation of effluent quality.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Gongming Wang, Qing-Shan Jia, MengChu Zhou, Jing Bi, Junfei Qiao
Summary: This paper proposes a Deep Belief Network with Event-triggered Learning (DBN-EL) to improve the efficiency and accuracy of soft-sensing model in WWTP. Through defining events, designing event-triggered learning strategy, and conducting convergence analysis, the effectiveness of this method in practical WWTP applications is demonstrated.
Article
Engineering, Multidisciplinary
Suchuan Dong, Zongwei Li
Summary: The neural network-based method combines ELM, domain decomposition, and local neural networks to solve linear and nonlinear partial differential equations. It shows significant convergence with respect to neural network degrees of freedom and performs well in numerical experiments.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Haijiao Xu, Changqin Huang, Dianhui Wang
KNOWLEDGE-BASED SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Hailiang Ye, Feilong Cao, Dianhui Wang
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Automation & Control Systems
Changqin Huang, Qionghao Huang, Dianhui Wang
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Computer Science, Information Systems
H. K. Zhang, Y. F. Wang, D. H. Wang, Y. L. Wang
INFORMATION SCIENCES
(2020)
Article
Automation & Control Systems
Ming Li, Dianhui Wang
Summary: The study extends original SCNs to 2DSCNs for fast building randomized learners with matrix inputs, showing good potential for image data analytics.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Review
Computer Science, Artificial Intelligence
Wenxuan Liu, Junhua Zhao, Dianhui Wang
Summary: This paper presents an initial discussion on the applications and advancements of big data mining in intelligent energy systems. It discusses applications such as load forecasting, integrated energy systems, and electricity market forecasting, as well as research problems that need further attention in the future.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2021)
Article
Computer Science, Artificial Intelligence
Aijun Yan, Jingcheng Guo, Dianhui Wang
Summary: In this paper, a heterogeneous feature ensemble method is proposed for modeling furnace temperature in the process of municipal solid waste incineration. By constructing multiple base models and utilizing a negative correlation learning strategy, accurate prediction and control of furnace temperature are achieved.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Pengxin Tian, Kai Sun, Dianhui Wang
Summary: This study develops a soft-sensing technique using SCNs and NNG algorithm to infer difficult-to-measure variables with easy-to-measure variables in industrial processes. The proposed method consists of two stages: using SCNs for industrial data modeling and applying NNG algorithm for model optimization. Experimental results demonstrate that the proposed soft-sensor performs better in terms of prediction accuracy.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Automation & Control Systems
Yan Pan, Chang-Qin Huang, Dianhui Wang
Summary: Multiview clustering partitions data based on multiple perspectives to generate more meaningful clusters. This article proposes a multiview spectral clustering method based on robust subspace segmentation. The method constructs feature matrices, performs low rank and sparse decomposition, and utilizes spectral clustering to produce the final clusters. Experimental results demonstrate that the proposed method outperforms other state-of-the-art multiview clustering techniques on benchmark datasets.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Weitao Li, Yali Deng, Meishuang Ding, Dianhui Wang, Wei Sun, Qiyue Li
Summary: This paper proposes an intelligent classification method based on self-attention learning features and stochastic configuration networks to tackle the issues in current industrial data classification models. By utilizing self-attention mechanism for feature extraction and SCNs for classifier design, the proposed method enhances the robustness of the classification model through fuzzy integral integration.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Automation & Control Systems
Jia Chen, Ming Zhong, Jianxin Li, Dianhui Wang, Tieyun Qian, Hang Tu
Summary: This article focuses on the "oversmoothing" problem in attributed network representation learning, proposing to evaluate a smoothing parameter based on network topological characteristics to adaptively smooth node attributes and structure information, resulting in robust and distinguishable node features.Extensive experiments show that this approach effectively preserves the intrinsic information of networks compared to state-of-the-art works on benchmark datasets with varying topological characteristics.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Civil
Yongfu Wang, Bingxin Ma, Dianhui Wang, Tianyou Chai
Summary: This paper focuses on the problem of prescribed tracking performance control for uncertain steer-by-wire (SbW) systems with input nonlinearity and the limitation of CAN bandwidth. It introduces an adaptive interval type-2 fuzzy logic system (IT2 FLS) to approximate the lumped model uncertainty and applies a switching event-triggering mechanism (ETM) to save communication resources. By combining the backstepping approach and barrier Lyapunov function techniques, a prescribed tracking performance control method is proposed for SbW systems, eliminating the need for initial values of state errors in controller design. Theoretical analysis shows that the tracking error can converge to the predefined residual set within a preset time, while the closed-loop system is semi-globally stable. Simulations and vehicle experiments are conducted to verify the effectiveness of the proposed control method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wenhua Jiao, Ruilin Li, Jianguo Wang, Dianhui Wang, Kuan Zhang
Summary: Rehabilitation training has shifted from therapies to strategies with remote assistance. This paper proposes two solutions, Bagging SCNs and Boosting SCNs, for activity recognition based on SCNs. Experimental results demonstrate that these methods have good performance in remote rehabilitation training.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Automation & Control Systems
Kang Li, Junfei Qiao, Dianhui Wang
Summary: This article presents an online self-learning stochastic configuration network that improves the continuous learning ability of SCNs for modeling nonstationary data streams. The network autonomously adjusts parameters and structure based on real-time arriving data streams, using recursive learning mechanism and sensitivity analysis. Experimental results demonstrate the potential of the proposed method for analyzing nonstationary data streams.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Wu Ai, Dianhui Wang
INFORMATION SCIENCES
(2020)
