12 April 2022 in IEEE Transactions on Smart Grid
Multienergy load forecasting technique is the basis for the operation and scheduling of integrated energy system. Different types of loads in an integrated energy system, i.e., electricity load, heat load, cold load, might have complex and strong coupling relationships among them. If the internal relationship of multienergy load can be considered to realize joint prediction, the accuracy of multienergy load forecasting could be improved. This paper proposes a multi-task model, MultiDeT (Multiple-Decoder Transformer), which firstly adopts the one-encoder multi-decoder structure to realize the multi-task architecture and perform joint prediction of multienergy load. Based on the encoder-decoder architecture, the proposed model encodes all the input data by a uniform encoder and performs each forecasting task by multiple decoders. All tasks share the same encoder parameters, but have dedicated decoders for subtask learning. Therefore, the proposed multi-decoder structure can achieve different levels of attention to the output representation of the encoder by multi-head attention. The entire model is jointly trained end-to-end with losses from each task. Finally, the proposed model is tested on the publicly available datasets. Compared with other forecasting models, the results show that the proposed model has more accurate load forecasting results and has higher generalization capability.
4 November 2021 in IEEE Transactions on Medical Imaging
Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/ .
22 October 2019 in BMC Medical Informatics and Decision Making
Background: Breast cancer causes hundreds of thousands of deaths each year worldwide. The early stage diagnosis and treatment can significantly reduce the mortality rate. However, the traditional manual diagnosis needs intense workload, and diagnostic errors are prone to happen with the prolonged work of pathologists. Automatic histopathology image recognition plays a key role in speeding up diagnosis and improving the quality of diagnosis. Methods: In this work, we propose a breast cancer histopathology image classification by assembling multiple compact Convolutional Neural Networks (CNNs). First, a hybrid CNN architecture is designed, which contains a global model branch and a local model branch. By local voting and two-branch information merging, our hybrid model obtains stronger representation ability. Second, by embedding the proposed Squeeze-Excitation-Pruning (SEP) block into our hybrid model, the channel importance can be learned and the redundant channels are thus removed. The proposed channel pruning scheme can decrease the risk of overfitting and produce higher accuracy with the same model size. At last, with different data partition and composition, we build multiple models and assemble them together to further enhance the model generalization ability. Results: Experimental results show that in public BreaKHis dataset, our proposed hybrid model achieves comparable performance with the state-of-the-art. By adopting the multi-model assembling scheme, our method outperforms the state-of-the-art in both patient level and image level accuracy for BACH dataset. Conclusions: We propose a novel compact breast cancer histopathology image classification scheme by assembling multiple compact hybrid CNNs. The proposed scheme achieves promising results for the breast cancer image classification task. Our method can be used in breast cancer auxiliary diagnostic scenario, and it can reduce the workload of pathologists as well as improve the quality of diagnosis.
18 July 2023 in IEEE Transactions on Smart Grid
Probabilistic multi-energy load forecasting in an integrated energy system is very complex, because it needs to consider the following three aspects simultaneously: 1) Complex coupling relationship exists between multi-energy loads. 2) The intrinsic distribution of load uncertainties and dynamic changes of the distributions should be captured. 3) The probability distribution containing sufficient information should be generated. To address these issues, this paper proposes a multi-task Bayesian neural network, Bayesian Multiple-Decoder Transformer (BMDeT), which can capture both epistemic and aleatoric uncertainty, and achieve the joint probabilistic forecasting of the multi-energy loads considering their complex coupling relationship and related uncertainties. Firstly, the proposed model adopts the one-encoder multi-decoder framework, which could catch the multi-load coupling information by one Bayesian encoder and perform respective subtasks by multiple Bayesian decoders. Specifically, the Bayesian multi-head attention mechanism is proposed to capture the complex coupling relationship and uncertainties between multi-energy loads by optimizing the distribution of network parameters. Then, a multi-task balance method based on Bayesian theory is proposed to quantify the uncertainties of different tasks by giving trainable weights. Finally, the proposed model has been verified on a real-world load data set, the results show that it has superior performance over other benchmark models.
17 August 2022 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Survival analysis is a significant study in cancer prognosis, and the multi-modal data, including histopathological images, genomic data, and clinical information, provides unprecedented opportunities for its development. However, because of the high dimensionality and the heterogeneity of histopathological images and genomic data, acquiring effective predictive characters from these multi-modal data has always been a challenge for survival analysis. In this study, we propose a transformer-based survival analysis model (TransSurv) for colorectal cancer that can effectively integrate intra-modality and inter-modality features of histopathological images, genomic data, and clinical information. Specifically, to integrate the intra-modality relationship of image patches, we develop a multi-scale histopathological features fusion transformer (MS-Trans). Furthermore, we provide a cross-modal fusion transformer based on cross attention for multi-scale pathological representation and multi-omics representation, which includes RNA-seq expression and copy number alteration (CNA). At the output layer of the TransSurv, we adopt the Cox layer to integrate multi-modal fusion representation with clinical information for end-to-end survival analysis. The experimental results on the Cancer Genome Atlas (TCGA) colorectal cancer cohort demonstrate that the proposed TransSurv outperforms the existing methods and improves the prognosis prediction of colorectal cancer.
2 March 2024 in Reliability Engineering & System Safety