1
|
Yang P, Zhang X. A Dual-Branch Fusion of a Graph Convolutional Network and a Convolutional Neural Network for Hyperspectral Image Classification. SENSORS (BASEL, SWITZERLAND) 2024; 24:4760. [PMID: 39066156 PMCID: PMC11281073 DOI: 10.3390/s24144760] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/04/2024] [Revised: 07/12/2024] [Accepted: 07/19/2024] [Indexed: 07/28/2024]
Abstract
Semi-supervised graph convolutional networks (SSGCNs) have been proven to be effective in hyperspectral image classification (HSIC). However, limited training data and spectral uncertainty restrict the classification performance, and the computational demands of a graph convolution network (GCN) present challenges for real-time applications. To overcome these issues, a dual-branch fusion of a GCN and convolutional neural network (DFGCN) is proposed for HSIC tasks. The GCN branch uses an adaptive multi-scale superpixel segmentation method to build fusion adjacency matrices at various scales, which improves the graph convolution efficiency and node representations. Additionally, a spectral feature enhancement module (SFEM) enhances the transmission of crucial channel information between the two graph convolutions. Meanwhile, the CNN branch uses a convolutional network with an attention mechanism to focus on detailed features of local areas. By combining the multi-scale superpixel features from the GCN branch and the local pixel features from the CNN branch, this method leverages complementary features to fully learn rich spatial-spectral information. Our experimental results demonstrate that the proposed method outperforms existing advanced approaches in terms of classification efficiency and accuracy across three benchmark data sets.
Collapse
Affiliation(s)
- Pan Yang
- College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China;
- Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen 361024, China
| | - Xinxin Zhang
- College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China;
- Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen 361024, China
| |
Collapse
|
2
|
Wang L, Cheng Y, Parekh G, Naidu R. Real-time monitoring and predictive analysis of VOC flux variations in soil vapor: Integrating PID sensing with machine learning for enhanced vapor intrusion forecasts. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 924:171616. [PMID: 38479534 DOI: 10.1016/j.scitotenv.2024.171616] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/22/2023] [Revised: 03/06/2024] [Accepted: 03/08/2024] [Indexed: 03/17/2024]
Abstract
In the rapidly evolving domain of vapor intrusion (VI) assessments, traditional methodologies encompass detailed groundwater and soil vapor sampling coupled with comprehensive laboratory measurements. These models, blending empirical data, theoretical equations, and site-specific parameters, evaluate VI risks by considering a spectrum of influential factors, from volatile organic compounds (VOC) concentrations in groundwater to nuanced soil attributes. However, the challenge of variability, influenced by dynamic ambient conditions and intricate soil properties, remains. Our study presents an advanced on-site gas sensing station geared towards real-time VOC flux monitoring, enriched with an array of ambient sensors, and spearheaded by the reliable PID sensor for VOC detection. Integrating this dynamic system with machine learning, we developed predictive models, notably the random forest regression, which boasts an R-squared value exceeding 79 % and mean relative error near 0.25, affirming its capability to predict trichloroethylene (TCE) concentrations in soil vapor accurately. By synergizing real-time monitoring and predictive insights, our methodology refines VI risk assessments, equipping communities with proactive, informed decision-making tools and bolstering environmental safety. Implementing these predictive models can simplify monitoring for residents, reducing dependence on specialized systems. Once proven effective, there's potential to repurpose monitoring stations to other VI-prone regions, expanding their reach and benefit. The developed model can leverage weather forecasting data to predict and provide alerts for future VOC events.
Collapse
Affiliation(s)
- Liang Wang
- Global Centre for Environmental Remediation (GCER), College of Engineering, Science and Environment, University of Newcastle, Callaghan, NSW 2308, Australia; CRC for Contamination Assessment and Remediation of the Environment, ATC, University Drive, Callaghan, NSW 2308, Australia.
| | - Ying Cheng
- Global Centre for Environmental Remediation (GCER), College of Engineering, Science and Environment, University of Newcastle, Callaghan, NSW 2308, Australia; CRC for Contamination Assessment and Remediation of the Environment, ATC, University Drive, Callaghan, NSW 2308, Australia
| | - Gaurang Parekh
- CRC for Contamination Assessment and Remediation of the Environment, ATC, University Drive, Callaghan, NSW 2308, Australia
| | - Ravi Naidu
- Global Centre for Environmental Remediation (GCER), College of Engineering, Science and Environment, University of Newcastle, Callaghan, NSW 2308, Australia; CRC for Contamination Assessment and Remediation of the Environment, ATC, University Drive, Callaghan, NSW 2308, Australia
| |
Collapse
|
3
|
Ma T, Wang G, Guo R, Chen L, Ma J. Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine. JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024; 359:120966. [PMID: 38677225 DOI: 10.1016/j.jenvman.2024.120966] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Revised: 02/29/2024] [Accepted: 04/19/2024] [Indexed: 04/29/2024]
Abstract
Forest fires threaten global ecosystems, socio-economic structures, and public safety. Accurately assessing forest fire susceptibility is critical for effective environmental management. Supervised learning methods dominate this assessment, relying on a substantial dataset of forest fire occurrences for model training. However, obtaining precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors for training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in scenarios with limited samples. We conducted a comparative analysis, evaluating its performance against widely used supervised learning methods. The assessment area for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accuracies for both supervised and semi-supervised learning methods across various small sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findings indicate that TSVM exhibits superior prediction accuracy compared to supervised learning with limited samples, yielding more plausible forest fire susceptibility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves prediction accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In contrast, random forests, the top performers in supervised learning, demonstrate accuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the same small sample sizes. Additionally, we discussed three key aspects: TSVM parameter configuration, the impact of unlabeled sample size, and performance within typical sample sizes. Our findings support semi-supervised learning as a promising approach compared to supervised learning for forest fire susceptibility assessment and mapping, particularly in scenarios with small sample sizes.
Collapse
Affiliation(s)
- Tianwu Ma
- Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, China; School of Geography, Nanjing Normal University, Nanjing, 210023, China
| | - Gang Wang
- School of Geography, Nanjing Normal University, Nanjing, 210023, China; School of Urban and Plan, Yancheng Teachers University, Yancheng, 224002, China.
| | - Rui Guo
- Administration of Zhejiang Qingliangfeng National Nature Reserve, Hangzhou, 311300, China
| | - Liang Chen
- Department of Environmental and Biological Sciences, University of Eastern Finland, Joensuu, 80101, Finland
| | - Junfei Ma
- Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, China; School of Geography, Nanjing Normal University, Nanjing, 210023, China
| |
Collapse
|
4
|
Semi-supervised learning for MALDI–TOF mass spectrometry data classification: an application in the salmon industry. Neural Comput Appl 2023. [DOI: 10.1007/s00521-023-08333-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/23/2023]
|
5
|
Hassan HA, Hemdan EE, El-Shafai W, Shokair M, El-Samie FEA. Intrusion Detection Systems for the Internet of Thing: A Survey Study. WIRELESS PERSONAL COMMUNICATIONS 2023; 128:2753-2778. [DOI: 10.1007/s11277-022-10069-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 09/28/2022] [Indexed: 09/02/2023]
|
6
|
Wan Z, Yang R, Huang M, Alsaadi FE, Sheikh MM, Wang Z. Segment alignment based cross-subject motor imagery classification under fading data. Comput Biol Med 2022; 151:106267. [PMID: 36356391 DOI: 10.1016/j.compbiomed.2022.106267] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Revised: 10/06/2022] [Accepted: 10/30/2022] [Indexed: 11/06/2022]
Abstract
Motor imagery (MI) aims to use brain imagination without actual body activities to support motor learning, and machine learning algorithms such as common spatial patterns (CSP) are proven effective in the analysis of MI signals. In the conventional machine learning-based approaches, there are two main difficulties in feature extraction and recognition of MI signals: high personalization and data fading. The high personalization problem is due to the multi-subject nature when collecting MI signals, and the data fading problem as a recurring issue in MI signal quality is first raised by us but is not widely discussed at present. Aiming to solve the above two mentioned problems, a cross-subject fading data classification approach with segment alignment is proposed to classify the fading data of one single target with the model trained with the normal data of multiple sources in this paper. he effectiveness of proposed method is verified via two experiments: a dataset-based experiment with the dataset from BCI Competition and a lab-based experiment designed and conducted by us. The experimental results obtained from both experiments show that the proposed method can obtain optimal classification performance effectively under different fading levels with data from different subjects.
Collapse
Affiliation(s)
- Zitong Wan
- Design School, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China; Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3BX, United Kingdom
| | - Rui Yang
- School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou 215123, China.
| | - Mengjie Huang
- Design School, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China.
| | - Fuad E Alsaadi
- Department of Electrical and Computer Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Muntasir M Sheikh
- Department of Electrical and Computer Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Zidong Wang
- Department of Computer Science, Brunel University London, Uxbridge, Middlesex UB8 3PH, United Kingdom
| |
Collapse
|
7
|
Pan W, Xiao H, Li H, Li Y, Zhang B, Liu B, Yang L. Terahertz spectroscopic detection of antifatigue illegal additives in health care product matrices. APPLIED OPTICS 2022; 61:9904-9910. [PMID: 36606822 DOI: 10.1364/ao.462727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/29/2022] [Accepted: 09/13/2022] [Indexed: 06/17/2023]
Abstract
Tadalafil is an illegal additive in antifatigue supplements. It is often misused in various plant dietary supplements (BDS), resulting in serious health risks. In this paper, terahertz spectroscopy combined with chemometrics is used to quantitatively analyze the content of tadalafil in nutritional and health products. The absorption coefficient spectrum of tadalafil in the range of 0.1-2.5 THz was obtained, and an obvious characteristic absorption peak appeared at 1.7 THz. To verify the accuracy of this characteristic absorption peak theoretically, tadalafil was simulated by density functional theory, and the calculated terahertz vibration spectrum matched well with the experimental spectrum. Then, the pure fatigue-based nutraceutical matrix and pure tadalafil were mixed in different proportions, and the terahertz absorption coefficient spectra of the mixtures were obtained. Finally, a quantitative analysis model of the tadalafil mixture was developed based on the support vector regression (SVR) algorithm, and the SVR model was optimized using particle swarm optimization (PSO) and genetic algorithm (GA), respectively. Compared with the SVR model, both PSO-SVR and GA-SVR enabled some improvement in their prediction accuracy, but the PSO-SVR model ran faster at 4.85 s, whereas the GA-SVR model had a higher prediction accuracy with a prediction set correlation coefficient (R P) of 0.9996 and a root mean square error (RMSEP) of 0.011. In summary, this study used terahertz time-domain spectroscopy for the identification and quantification of tadalafil in health product matrices. This study provides a new solution for the nondestructive detection of illegally added tadalafil in antifatigue health products, which is pivotal to the quality control of the health product industry.
Collapse
|
8
|
Landslide Susceptibility Mapping Based on the Germinal Center Optimization Algorithm and Support Vector Classification. REMOTE SENSING 2022. [DOI: 10.3390/rs14112707] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
A landslide susceptibility model based on a metaheuristic optimization algorithm (germinal center optimization (GCO)) and support vector classification (SVC) is proposed and applied to landslide susceptibility mapping in the Three Gorges Reservoir area in this paper. The proposed GCO-SVC model was constructed via the following steps: First, data on 11 influencing factors and 292 landslide polygons were collected to establish the spatial database. Then, after the influencing factors were subjected to multicollinearity analysis, the data were randomly divided into training and testing sets at a ratio of 7:3. Next, the SVC model with 5-fold cross-validation was optimized by hyperparameter space search using GCO to obtain the optimal hyperparameters, and then the best model was constructed based on the optimal hyperparameters and training set. Finally, the best model acquired by GCO-SVC was applied for landslide susceptibility mapping (LSM), and its performance was compared with that of 6 popular models. The proposed GCO-SVC model achieved better performance (0.9425) than the genetic algorithm support vector classification (GA-SVC; 0.9371), grid search optimized support vector classification (GRID-SVC; 0.9198), random forest (RF; 0.9085), artificial neural network (ANN; 0.9075), K-nearest neighbor (KNN; 0.8976), and decision tree (DT; 0.8914) models in terms of the area under the receiver operating characteristic curve (AUC), and the trends of the other metrics were consistent with that of the AUC. Therefore, the proposed GCO-SVC model has some advantages in LSM and may be worth promoting for wide use.
Collapse
|
9
|
Lu Y, Yao G, Wang X, Zhang Y, Zhao J, Yu YJ, Wang H. Chemometric discrimination of the geographical origin of licorice in China by untargeted metabolomics. Food Chem 2022; 380:132235. [DOI: 10.1016/j.foodchem.2022.132235] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2021] [Revised: 01/18/2022] [Accepted: 01/20/2022] [Indexed: 12/13/2022]
|
10
|
Li Z, Jin H, Dong S, Qian B, Yang B, Chen X. Semi-supervised ensemble support vector regression based soft sensor for key quality variable estimation of nonlinear industrial processes with limited labeled data. Chem Eng Res Des 2022. [DOI: 10.1016/j.cherd.2022.01.026] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
|
11
|
Li D, Dick S. Semi-supervised multi-label classification using an extended graph-based manifold regularization. COMPLEX INTELL SYST 2022; 8:1561-1577. [PMID: 35535331 PMCID: PMC9054917 DOI: 10.1007/s40747-021-00611-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2021] [Accepted: 12/03/2021] [Indexed: 11/28/2022]
Abstract
Graph-based algorithms are known to be effective approaches to semi-supervised learning. However, there has been relatively little work on extending these algorithms to the multi-label classification case. We derive an extension of the Manifold Regularization algorithm to multi-label classification, which is significantly simpler than the general Vector Manifold Regularization approach. We then augment our algorithm with a weighting strategy to allow differential influence on a model between instances having ground-truth vs. induced labels. Experiments on four benchmark multi-label data sets show that the resulting algorithm performs better overall compared to the existing semi-supervised multi-label classification algorithms at various levels of label sparsity. Comparisons with state-of-the-art supervised multi-label approaches (which of course are fully labeled) also show that our algorithm outperforms all of them even with a substantial number of unlabeled examples.
Collapse
Affiliation(s)
- Ding Li
- Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB Canada T6G 1H9
| | - Scott Dick
- Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB Canada T6G 1H9
| |
Collapse
|
12
|
Lin H, Jian C, Cao Y, Ma X, Wang H, Miao F, Fan X, Yang J, Zhao G, Zhou H. MDD-TSVM: A novel semisupervised-based method for major depressive disorder detection using electroencephalogram signals. Comput Biol Med 2022; 140:105039. [PMID: 34864299 DOI: 10.1016/j.compbiomed.2021.105039] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2021] [Revised: 11/13/2021] [Accepted: 11/13/2021] [Indexed: 11/17/2022]
Abstract
Major depressive disorder (MDD) is a common mental illness characterized by persistent feeling of depressed mood and loss of interest. It would cause, in a severe case, suicide behaviors. In clinical settings, automatic MDD detection is mainly based on electroencephalogram (EEG) signals with supervised learning techniques. However, supervised-based MDD detection methods encounter two ineviTable bottlenecks: firstly, such methods rely heavily on an EEG training dataset with MDD labels annotated by a physical therapist, leading to subjectivity and high cost; secondly, most of EEG signals are unlabeled in a real scenario. In this paper, a novel semisupervised-based MDD detection method named MDD-TSVM is presented. Specifically, the MDD-TSVM utilizes the semisupervised method of transductive support vector machine (TSVM) as its backbone, further dividing the unlabeled penalty item of the TSVM objective function into two pseudo-labeled penalty items with or without MDD. By such improvement, the MDD-SVM can make full use of labeled and unlabeled datasets as well as alleviate the class imbalance problem. Experiment results showed that our proposed MDD-TSVM achieved F1 score of 0.85 ± 0.05 and accuracy of 0.89 ± 0.03 on identifying MDD patients, which is superior to the state-of-the-art methods.
Collapse
Affiliation(s)
- Hongtuo Lin
- School of Computer Science, South China Normal University, Guangzhou, China.
| | - Chufan Jian
- School of Computer Science, South China Normal University, Guangzhou, China.
| | - Yang Cao
- School of Computer Science, South China Normal University, Guangzhou, China.
| | - Xiaoguang Ma
- The State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China; Foshan Graduate School, Northeastern University, Foshan, China.
| | - Hailiang Wang
- School of Design, Hong Kong Polytechnic University, Hong Kong Special Administrative Region.
| | - Fen Miao
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
| | - Xiaomao Fan
- School of Computer Science, South China Normal University, Guangzhou, China.
| | - Jinzhu Yang
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China; School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China.
| | - Gansen Zhao
- School of Computer Science, South China Normal University, Guangzhou, China.
| | - Hui Zhou
- School of Automation, Nanjing University of Science and Technology, Nanjing, China.
| |
Collapse
|
13
|
Optimizing Matching Area for Underwater Gravity-Aided Inertial Navigation Based on the Convolution Slop Parameter-Support Vector Machine Combined Method. REMOTE SENSING 2021. [DOI: 10.3390/rs13193940] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
This paper focuses on the selection of matching areas in the gravity-aided inertial navigation system. Firstly, the Sobel operator was used in convolution of the gravity anomaly map to obtain the feature map. The convolution slope parameters were constructed by combining the feature map and the gravity anomaly map. The characteristic parameters, such as the difference between convolution rows and columns, convolution variance of the feature map, the pooling difference, and range of the gravity anomaly map, were combined. Based on the support vector machine algorithm, the convolution slope parameter-support vector machine combined method is proposed. Second, we selected the appropriate training sample set and set parameters to verify. The results show that compared with the pre-calibration results, the classification accuracy of the test set is more than 92%, which proves that the convolution slope parameter-support vector machine combined method can effectively distinguish between the suitable and the unsuitable area. Thirdly, we applied this method to another region. The navigation experiment was performed in the split-matching area. The average positioning error was better than 100 m, and the correct rate was more than 90%. The results show that sailing in the selected area can accurately match the trajectory and reduce the positioning error.
Collapse
|
14
|
Pozi MSM, Azhar NA, Raziff ARA, Ajrina LH. SVGPM: evolving SVM decision function by using genetic programming to solve imbalanced classification problem. PROGRESS IN ARTIFICIAL INTELLIGENCE 2021. [DOI: 10.1007/s13748-021-00260-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
15
|
Xiao Y, Feng J, Liu B. A new transductive learning method with universum data. APPL INTELL 2021. [DOI: 10.1007/s10489-020-02113-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
16
|
A Novel Approach to Oil Layer Recognition Model Using Whale Optimization Algorithm and Semi-Supervised SVM. Symmetry (Basel) 2021. [DOI: 10.3390/sym13050757] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
The dataset distribution of actual logging is asymmetric, as most logging data are unlabeled. With the traditional classification model, it is hard to predict the oil and gas reservoir accurately. Therefore, a novel approach to the oil layer recognition model using the improved whale swarm algorithm (WOA) and semi-supervised support vector machine (S3VM) is proposed in this paper. At first, in order to overcome the shortcomings of the Whale Optimization Algorithm applied in the parameter-optimization of the S3VM model, such as falling into a local optimization and low convergence precision, an improved WOA was proposed according to the adaptive cloud strategy and the catfish effect. Then, the improved WOA was used to optimize the kernel parameters of S3VM for oil layer recognition. In this paper, the improved WOA is used to test 15 benchmark functions of CEC2005 compared with five other algorithms. The IWOA–S3VM model is used to classify the five kinds of UCI datasets compared with the other two algorithms. Finally, the IWOA–S3VM model is used for oil layer recognition. The result shows that (1) the improved WOA has better convergence speed and optimization ability than the other five algorithms, and (2) the IWOA–S3VM model has better recognition precision when the dataset contains a labeled and unlabeled dataset in oil layer recognition.
Collapse
|
17
|
Classification of acoustical signals by combining active learning strategies with semi-supervised learning schemes. Neural Comput Appl 2021. [DOI: 10.1007/s00521-021-05749-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
18
|
Zhang T, Huang M, Wang Z. Estimation of chlorophyll-a Concentration of lakes based on SVM algorithm and Landsat 8 OLI images. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2020; 27:14977-14990. [PMID: 32128729 DOI: 10.1007/s11356-020-07706-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/07/2019] [Accepted: 01/09/2020] [Indexed: 06/10/2023]
Abstract
Chlorophyll-a (Chl-a) is the main component of phytoplankton and an important index of water quality. Pearson correlation analysis is conducted on measured Chl-a concentration and band reflectance to determine the sensitive bands or multiband combinations of the Chl-a to input to a support vector machine (SVM) model. An indicator β is defined to evaluate the model performance of fitting and prediction. The model performs well with the lowest β (decision coefficient, (R2) = 0.774; root mean square error (RMSE) = 22.636 μg/L) of the validation set. The model test results prove that the model performs well. We analyze the impact factors of the model. The seasonal factor affects the model performance significantly; thus, samples from different seasons should be combined to train the model and inverse the water quality. Noise points reduce the model accuracy significantly; therefore, obvious outliers must be excluded at first. Additionally, the sampling method affects model accuracy, and systematic sampling in the descending order of Chl-a concentration is recommended. The combination of SVM algorithm and remote sensing technology provides a convenient, scientific, and real-time method to monitor and control water quality.
Collapse
Affiliation(s)
- Teng Zhang
- Department of Hydraulic Engineering, Tsinghua University, Beijing, 100084, China
- School of Hydropower & Information Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China
| | - Mutao Huang
- School of Hydropower & Information Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China.
| | - Zhongjing Wang
- Department of Hydraulic Engineering, Tsinghua University, Beijing, 100084, China.
- State Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing, 100084, China.
- State Key Laboratory of Plateau Ecology and Agriculture, Qinghai University, Xining, 810016, China.
| |
Collapse
|
19
|
Krzhizhanovskaya VV, Závodszky G, Lees MH, Dongarra JJ, Sloot PMA, Brissos S, Teixeira J. Deep Low-Density Separation for Semi-supervised Classification. LECTURE NOTES IN COMPUTER SCIENCE 2020. [PMCID: PMC7304056 DOI: 10.1007/978-3-030-50420-5_22] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (ssl) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised methods applied to the labeled training set alone. Effective ssl imposes structural assumptions on the data, e.g. that neighbors are more likely to share a classification or that the decision boundary lies in an area of low density. For complex and high-dimensional data, neural networks can learn feature embeddings to which traditional ssl methods can then be applied in what we call hybrid methods. Previously-developed hybrid methods iterate between refining a latent representation and performing graph-based ssl on this representation. In this paper, we introduce a novel hybrid method that instead applies low-density separation to the embedded features. We describe it in detail and discuss why low-density separation may better suited for ssl on neural network-based embeddings than graph-based algorithms. We validate our method using in-house customer survey data and compare it to other state-of-the-art learning methods. Our approach effectively classifies thousands of unlabeled users from a relatively small number of hand-classified examples.
Collapse
|
20
|
Abstract
PURPOSE OF REVIEW Artificial intelligence (AI) technology holds both great promise to transform mental healthcare and potential pitfalls. This article provides an overview of AI and current applications in healthcare, a review of recent original research on AI specific to mental health, and a discussion of how AI can supplement clinical practice while considering its current limitations, areas needing additional research, and ethical implications regarding AI technology. RECENT FINDINGS We reviewed 28 studies of AI and mental health that used electronic health records (EHRs), mood rating scales, brain imaging data, novel monitoring systems (e.g., smartphone, video), and social media platforms to predict, classify, or subgroup mental health illnesses including depression, schizophrenia or other psychiatric illnesses, and suicide ideation and attempts. Collectively, these studies revealed high accuracies and provided excellent examples of AI's potential in mental healthcare, but most should be considered early proof-of-concept works demonstrating the potential of using machine learning (ML) algorithms to address mental health questions, and which types of algorithms yield the best performance. As AI techniques continue to be refined and improved, it will be possible to help mental health practitioners re-define mental illnesses more objectively than currently done in the DSM-5, identify these illnesses at an earlier or prodromal stage when interventions may be more effective, and personalize treatments based on an individual's unique characteristics. However, caution is necessary in order to avoid over-interpreting preliminary results, and more work is required to bridge the gap between AI in mental health research and clinical care.
Collapse
|
21
|
Li H, Jiang Y, Ji H, Liu G, Yu S. 3D Reconstruction of Slug Flow in Mini-Channels with a Simple and Low-Cost Optical Sensor. SENSORS (BASEL, SWITZERLAND) 2019; 19:s19204573. [PMID: 31640172 PMCID: PMC6832154 DOI: 10.3390/s19204573] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/03/2019] [Revised: 10/15/2019] [Accepted: 10/17/2019] [Indexed: 06/10/2023]
Abstract
The present work provides a new approach for 3D image reconstruction of gas-liquid two-phase flow (GLF) in mini-channels based on a new optical sensor. The sensor consists of a vertical and a horizontal photodiode array. Firstly, with the optical signals obtained by the vertical array, a measurement model developed by Support Vector Regression (SVR) was used to determine the cross-sectional information. The determined information was further used to reconstruct cross-sectional 2D images. Then, the gas velocity was calculated according to the signals obtained by the horizontal array, and the spatial interval of the 2D images was determined. Finally, 3D images were reconstructed by piling up the 2D images. In this work, the cross-sectional gas-liquid interface was considered as circular, and high-speed visualization was utilized to provide the reference values. The image deformation caused by channel wall was also considered. Experiments of slug flow in a channel with an inner diameter of 4.0 mm were carried out. The results verify the feasibility of the proposed 3D reconstruction method. The proposed method has the advantages of simple construct, low cost, and easily multipliable. The reconstructed 3D images can provide detailed and undistorted information of flow structure, which could further improve the measurement accuracy of other important parameters of gas-liquid two-phase flow, such as void fraction, pressure drop, and flow pattern.
Collapse
Affiliation(s)
- Huajun Li
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.
| | - Yandan Jiang
- College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
| | - Haifeng Ji
- College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
| | - Guangyu Liu
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.
| | - Shanen Yu
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.
| |
Collapse
|
22
|
Bi L, Zhang J, Lian J. EEG-Based Adaptive Driver-Vehicle Interface Using Variational Autoencoder and PI-TSVM. IEEE Trans Neural Syst Rehabil Eng 2019; 27:2025-2033. [PMID: 31502984 DOI: 10.1109/tnsre.2019.2940046] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Event-related potential (ERP)-based driver-vehicle interfaces (DVIs) have been developed to provide a communication channel for people with disabilities to drive a vehicle. However, they require a tedious and time-consuming training procedure to build the decoding model, which can translate EEG signals into commands. In this paper, to address this problem, we propose an adaptive DVI by using a new semi-supervised algorithm. The decoding model of the proposed DVI is first built with a small labeled training set, and then gradually improved by updating the proposed semi-supervised decoding model with new collected unlabeled EEG signals. In our semi-supervised algorithm, independent component analysis (ICA) and Kalman smoother are first used to improve the signal-to-noise ratio (SNR). After that, variational autoencoder is applied to provide a robust feature representation of EEG signals. Finally, a prior information-based transductive support vector machine (PI-TSVM) classifier is developed to translate these features into commands. Experimental results show that the proposed DVI can significantly reduce the training effort. After a short updating, its performance can be close to that of the supervised DVI requiring a lengthy training procedure. This work is vital for advancing the application of these DVIs.
Collapse
|
23
|
|
24
|
Patwary MJ, Wang XZ. Sensitivity analysis on initial classifier accuracy in fuzziness based semi-supervised learning. Inf Sci (N Y) 2019. [DOI: 10.1016/j.ins.2019.03.036] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
25
|
Jayadeva, Pant H, Sharma M, Soman S. Twin Neural Networks for the classification of large unbalanced datasets. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2018.07.089] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
26
|
Zhao J, Liu N, Malov A. Safe semi-supervised classification algorithm combined with active learning sampling strategy. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2018. [DOI: 10.3233/jifs-169722] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Affiliation(s)
- Jianhua Zhao
- College of Mathematics and Computer Application, Shangluo University, Shangluo, China
| | - Ning Liu
- College of Economics Management, Shangluo University, Shangluo, China
| | - A. Malov
- Department of Mathematical and Statistical Methods, Poznan University Life Sci, Poznan, Poland
| |
Collapse
|
27
|
An accelerator for support vector machines based on the local geometrical information and data partition. INT J MACH LEARN CYB 2018. [DOI: 10.1007/s13042-018-0877-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|