1. |
- Ma, Liyao, et al.
(författare)
-
Apple grading method based on neural network with ordered partitions and evidential ensemble learning
- 2022
-
Ingår i: CAAI Transactions on Intelligence Technology. - : John Wiley & Sons. - 2468-6557 .- 2468-2322. ; 7:4, s. 561-569
-
Tidskriftsartikel (refereegranskat)abstract
- In order to improve the performance of the automatic apple grading and sorting system, in this paper, an ensemble model of ordinal classification based on neural network with ordered partitions and Dempster–Shafer theory is proposed. As a non-destructive grading method, apples are graded into three grades based on the Soluble Solids Content value, with features extracted from the preprocessed near-infrared spectrum of apple serving as model inputs. Considering the uncertainty in grading labels, mass generation approach and evidential encoding scheme for ordinal label are proposed, with uncertainty handled within the framework of Dempster–Shafer theory. Constructing neural network with ordered partitions as the base learner, the learning procedure of the Bagging-based ensemble model is detailed. Experiments on Yantai Red Fuji apples demonstrate the satisfactory grading performances of proposed evidential ensemble model for ordinal classification. © 2022 The Authors. CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.
|
|
2. |
- Ma, Liyao, et al.
(författare)
-
Bagging likelihood-based belief decision trees
- 2017
-
Ingår i: 20th International Conference on Information Fusion, Fusion 2017. - : Institute of Electrical and Electronics Engineers (IEEE). - 9780996452700 ; , s. 321-326
-
Konferensbidrag (refereegranskat)abstract
- To embed ensemble techniques into belief decision trees for performance improvement, the bagging algorithm is explored. Simple belief decision trees based on entropy intervals extracted from evidential likelihood are constructed as the base classifiers, and a combination of individual trees promises to lead to a better classification accuracy. Requiring no extra querying cost, bagging belief decision trees can obtain good classification performance by simple belief tree combination, making it an alternative to single belief tree with querying. Experiments on UCI datasets verify the effectiveness of bagging approach. In various uncertain cases, the bagging method outperforms single belief tree without querying, and is comparable in accuracy to single tree with querying. © 2017 International Society of Information Fusion (ISIF).
|
|
3. |
- Ma, Liyao, et al.
(författare)
-
Learning Decision Forest from Evidential Data : the Random Training Set Sampling Approach
- 2017
-
Ingår i: International Conference on Systems and Informatics. - : IEEE. - 9781538611074 ; , s. 1423-1428
-
Konferensbidrag (refereegranskat)abstract
- To learn decision trees from uncertain data modelled by mass functions, the random training set sampling approach for learning belief decision forests is proposed. Given an uncertain training set, a collection of simple belief decision trees are trained separately on each corresponding new set drawn by random sampling from the original one. Then the final prediction is made by majority voting. After discussing the selection of parameters for belief decision forests, experiments on Balance scale data are carried on for performance validation. Results show that with different kinds of uncertainty, the proposed method guarantees an obvious improvement in classification accuracy.
|
|
4. |
- Ma, Liyao, et al.
(författare)
-
Training Instance Random Sampling Based Evidential Classification Forest Algorithms
- 2018
-
Ingår i: 2018 21st International Conference on Information Fusion, FUSION 2018. - : Institute of Electrical and Electronics Engineers Inc.. - 9780996452762 ; , s. 883-888
-
Konferensbidrag (refereegranskat)abstract
- Modelling and handling epistemic uncertainty with belief function theory, different ways to learn classification forests from evidential training data are explored. In this paper, multiple base classifiers are learned on uncertain training subsets generated by training instance random sampling approach. For base classifier learning, with the tool of evidential likelihood function, gini impurity intervals of uncertain datasets are calculated for attribute splitting and consonant mass functions of labels are generated for leaf node prediction. The construction of gini impurity based belief binary classification tree is proposed and then compared with C4.5 belief classification tree. For base classifier combination strategy, both evidence combination method for consonant mass function outputs and majority voting method for precise label outputs are discussed. The performances of different proposed algorithms are compared and analysed with experiments on VCI Balance scale dataset. © 2018 ISIF
|
|
5. |
- Sun, Bin, 1988-, et al.
(författare)
-
A Robust Data-Driven Method for Multiseasonality and Heteroscedasticity in Time Series Preprocessing
- 2021
-
Ingår i: Wireless Communications & Mobile Computing. - : Wiley-Hindawi. - 1530-8669 .- 1530-8677. ; 2021
-
Tidskriftsartikel (refereegranskat)abstract
- Internet of Things (IoT) is emerging, and 5G enables much more data transport from mobile and wireless sources. The data to be transmitted is too much compared to link capacity. Labelling data and transmit only useful part of the collected data or their features is a promising solution for this challenge. Abnormal data are valuable due to the need to train models and to detect anomalies when being compared to already overflowing normal data. Labelling can be done in data sources or edges to balance the load and computing between sources, edges, and centres. However, unsupervised labelling method is still a challenge preventing to implement the above solutions. Two main problems in unsupervised labelling are long-term dynamic multiseasonality and heteroscedasticity. This paper proposes a data-driven method to handle modelling and heteroscedasticity problems. The method contains the following main steps. First, raw data are preprocessed and grouped. Second, main models are built for each group. Third, models are adapted back to the original measured data to get raw residuals. Fourth, raw residuals go through deheteroscedasticity and become normalized residuals. Finally, normalized residuals are used to conduct anomaly detection. The experimental results with real-world data show that our method successfully increases receiver-operating characteristic (AUC) by about 30%.
|
|
6. |
- Sun, Bin, et al.
(författare)
-
An Improved k-Nearest Neighbours Method for Traffic Time Series Imputation
- 2017
-
Konferensbidrag (refereegranskat)abstract
- Intelligent transportation systems (ITS) are becoming more and more effective, benefiting from big data. Despite this, missing data is a problem that prevents many prediction algorithms in ITS from working effectively. Much work has been done to impute those missing data. Among different imputation methods, k-nearest neighbours (kNN) has shown excellent accuracy and efficiency. However, the general kNN is designed for matrix instead of time series so it lacks the usage of time series characteristics such as windows and weights that are gap-sensitive. This work introduces gap-sensitive windowed kNN (GSW-kNN) imputation for time series. The results show that GSW-kNN is 34% more accurate than benchmarking methods, and it is still robust even if the missing ratio increases to 90%.
|
|
7. |
- Sun, Bin, et al.
(författare)
-
Anomaly-Aware Traffic Prediction Based on Automated Conditional Information Fusion
- 2018
-
Ingår i: Proceedings of 21st International Conference on Information Fusion. - : IEEE conference proceedings. - 9780996452762
-
Konferensbidrag (refereegranskat)abstract
- Reliable and accurate short-term traffic prediction plays a key role in modern intelligent transportation systems (ITS) for achieving efficient traffic management and accident detection. Previous work has investigated this topic but lacks study on automated anomaly detection and conditional information fusion for ensemble methods. This works aims to improve prediction accuracy by fusing information considering different traffic conditions in ensemble methods. In addition to conditional information fusion, a day-week decomposition (DWD) method is introduced for preprocessing before anomaly detection. A k-nearest neighbours (kNN) based ensemble method is used as an example. Real-world data are used to test the proposed method with stratified ten-fold cross validation. The results show that the proposed method with incident labels improves predictions up to 15.3% and the DWD enhanced anomaly-detection improves predictions up to 8.96%. Conditional information fusion improves ensemble prediction methods, especially for incident traffic. The proposed method works well with enhanced detections and the procedure is fully automated. The accurate predictions lead to more robust traffic control and routing systems.
|
|