Remaining Useful Life Prediction Based on Deep Learning: A Survey.

Remaining useful life (RUL) is a metric of health state for essential equipment. It plays a significant role in health management. However, RUL is often random and unknown. One type of physics-based method builds a mathematical model for RUL using prior principles, but this is a tough task in real-world applications. Another type of method estimates RUL from available information through condition and health monitoring; this is known as the data-driven method. Traditional data-driven methods require significant human effort in designing health features to represent performance degradation, yet the prediction accuracy is limited. With breakthroughs in various application scenarios in recent years, deep learning techniques provide new insights into this problem. Over the past few years, deep-learning-based RUL prediction has attracted increasing attention from the academic community. Therefore, it is necessary to conduct a survey on deep-learning-based RUL prediction. To ensure a comprehensive survey, the literature is reviewed from three dimensions. Firstly, a unified framework is proposed for deep-learning-based RUL prediction and the models and approaches in the literature are reviewed under this framework. Secondly, detailed estimation processes are compared from the perspective of different deep learning models. Thirdly, the literature is examined from the perspective of specific problems, such as scenarios where the collected data consist of limited labeled data. Finally, the main challenges and future directions are summarized.

Adversarial style discrepancy minimization for unsupervised domain adaptation.

Mainstream unsupervised domain adaptation (UDA) methods align feature distributions across different domains via adversarial learning. However, most of them focus on global distribution alignment, ignoring the fine-grained domain discrepancy. Besides, they generally require auxiliary models, bringing extra computation costs. To tackle these issues, this study proposes an UDA method that differentiates individual samples without the help of extra models. To this end, we introduce a novel discrepancy metric, termed style discrepancy, to distinguish different target samples. We also propose a paradigm for adversarial style discrepancy minimization (ASDM). Specifically, we fix the parameters of the feature extractor and maximize style discrepancy to update the classifier, which helps detect more hard samples. Adversely, we fix the parameters of the classifier and minimize the style discrepancy to update the feature extractor, pushing those hard samples near the support of the source distribution. Such adversary helps to progressively detect and adapt more hard samples, leading to fine-grained domain adaptation. Experiments on different UDA tasks validate the effectiveness of ASDM. Overall, without any extra models, ASDM reaches a 46.9% mIoU in the GTA5 to Cityscapes benchmark and an 84.7% accuracy in the VisDA-2017 benchmark, outperforming many existing adversarial-learning-based methods.

A Joint 2D-3D Complementary Network for Stereo Matching.

Stereo matching is an important research field of computer vision. Due to the dimension of cost aggregation, current neural network-based stereo methods are difficult to trade-off speed and accuracy. To this end, we integrate fast 2D stereo methods with accurate 3D networks to improve performance and reduce running time. We leverage a 2D encoder-decoder network to generate a rough disparity map and construct a disparity range to guide the 3D aggregation network, which can significantly improve the accuracy and reduce the computational cost. We use a stacked hourglass structure to refine the disparity from coarse to fine. We evaluated our method on three public datasets. According to the KITTI official website results, Our network can generate an accurate result in 80 ms on a modern GPU. Compared to other 2D stereo networks (AANet, DeepPruner, FADNet, etc.), our network has a big improvement in accuracy. Meanwhile, it is significantly faster than other 3D stereo networks (5× than PSMNet, 7.5× than CSN and 22.5× than GANet, etc.), demonstrating the effectiveness of our method.

[Estimation of evapotranspiration and crop coefficient in Dajiuhu peatland of Shennongjia based on FAO56 Penman-Monteith]. / 基于FAO56 Penman-Monteithå ¬å¼ä¼°ç®—ç¥žå†œæž¶å¤§ä¹æ¹–æ³¥ç‚­æ¹¿åœ°è’¸æ•£åŠä½œç‰©ç³»æ•°.

We collected evapotranspiration data of Dajiuhu peatland in Shennongjia from 2016 to 2017 with eddy covariance method and estimated the value of crop coefficient (Kc) using FAO56 Penman-Monteith equation and the linear relationship between actual evapotranspiration (ETa) and referenced evapotranspiration (ET0). We analyzed the characteristics of referenced evapotranspiration and its main influencing factors and calculated the crop coefficient of the wetland dominated by Sphagnum. The results showed that the daily averaged ETa were 1.63 and 1.38 mm·d-1 in 2016 and 2017, the daily averaged ET0 were 1.61 and 1.23 mm·d-1 in 2016 and 2017. Environmental factors influencing ET0 included net radiation, air temperature, vapor pressure deficit, wind speed, and relative humidity. The Kc values for the growing seasons of 2016, 2017, and 2016-2017 were 0.95 (R2 of linear regression between ETa and ET0 was 0.96), 1.03 (R2=0.95), and 0.98 (R2=0.95). The Kc values in 2016, 2017, and 2016-2017 were 0.92 (R2=0.94), 0.95 (R2=0.89), and 0.93 (R2=0.92). Kc was effective in the range of 0.92-1.03 for the wetland dominated by Sphagnum. The identified parameters could be widely used in studies on climate change, ecosystem services, and water management in peatlands.

Research on Chinese medical named entity recognition based on collaborative cooperation of multiple neural network models.

Medical named entity recognition (NER) in Chinese electronic medical records (CEMRs) has drawn much research attention, and plays a vital prerequisite role for extracting high-value medical information. In 2018, China Health Information Processing Conference (CHIP2018) organized a medical NER academic competition aiming to extract three types of malignant tumor entity from CEMRs. Since the three types of entity are highly domain-specific and interdependency, extraction of them cannot be achieved with a single neural network model. Based on comprehensive study of the three types of entity and the entity interdependencies, we propose a collaborative cooperation of multiple neural network models based approach, which consists of two BiLSTM-CRF models and a CNN model. In order to tackle the problem that target scene dataset is small and entity distributions are sparse, we introduce non-target scene datasets and propose sentence-level neural network model transfer learning. Based on 30,000 real-world CEMRs, we pre-train medical domain-specific Chinese character embeddings with word2vec, GloVe and ELMo, and apply them to our approach respectively to validate effects of pre-trained language models in Chinese medical NER. Also, as control experiments, we apply Gated Recurrent Unit to our approach. Finally, our approach achieves an overall F1-score of 87.60%, which is the state-of-the-art performance to the best of our knowledge. In addition, our approach has won the champion of the medical NER academic competition organized by 2019 China Conference on Knowledge Graph and Semantic Computing, which proves the outstanding generalization ability of our approach.

A hybrid approach for named entity recognition in Chinese electronic medical record.

BACKGROUND: With the rapid spread of electronic medical records and the arrival of medical big data era, the application of natural language processing technology in biomedicine has become a hot research topic. METHODS: In this paper, firstly, BiLSTM-CRF model is applied to medical named entity recognition on Chinese electronic medical record. According to the characteristics of Chinese electronic medical records, obtain the low-dimensional word vector of each word in units of sentences. And then input the word vector to BiLSTM to realize automatic extraction of sentence features. And then CRF performs sentence-level word tagging. Secondly, attention mechanism is added between the BiLSTM and the CRF to construct Attention-BiLSTM-CRF model, which can leverage document-level information to alleviate tagging inconsistency. In addition, this paper proposes an entity auto-correct algorithm to rectify entities according to historical entity information. At last, a drug dictionary and post-processing rules are well-built to rectify entities, to further improve performance. RESULTS: The final F1 scores of the BiLSTM-CRF and Attention-BiLSTM-CRF model on given test dataset are 90.15 and 90.82% respectively, both of which are higher than 89.26%, which is the best F1 score on the test dataset except ours. CONCLUSION: Our approach can be used to recognize medical named entity on Chinese electronic medical records and achieves the state-of-the-art performance on the given test dataset.

An Evolutionary Algorithm with Double-Level Archives for Multiobjective Optimization.

Existing multiobjective evolutionary algorithms (MOEAs) tackle a multiobjective problem either as a whole or as several decomposed single-objective sub-problems. Though the problem decomposition approach generally converges faster through optimizing all the sub-problems simultaneously, there are two issues not fully addressed, i.e., distribution of solutions often depends on a priori problem decomposition, and the lack of population diversity among sub-problems. In this paper, a MOEA with double-level archives is developed. The algorithm takes advantages of both the multiobjective-problem-level and the sub-problem-level approaches by introducing two types of archives, i.e., the global archive and the sub-archive. In each generation, self-reproduction with the global archive and cross-reproduction between the global archive and sub-archives both breed new individuals. The global archive and sub-archives communicate through cross-reproduction, and are updated using the reproduced individuals. Such a framework thus retains fast convergence, and at the same time handles solution distribution along Pareto front (PF) with scalability. To test the performance of the proposed algorithm, experiments are conducted on both the widely used benchmarks and a set of truly disconnected problems. The results verify that, compared with state-of-the-art MOEAs, the proposed algorithm offers competitive advantages in distance to the PF, solution coverage, and search speed.

FPGA accelerator for protein secondary structure prediction based on the GOR algorithm.

BACKGROUND: Protein is an important molecule that performs a wide range of functions in biological systems. Recently, the protein folding attracts much more attention since the function of protein can be generally derived from its molecular structure. The GOR algorithm is one of the most successful computational methods and has been widely used as an efficient analysis tool to predict secondary structure from protein sequence. However, the execution time is still intolerable with the steep growth in protein database. Recently, FPGA chips have emerged as one promising application accelerator to accelerate bioinformatics algorithms by exploiting fine-grained custom design. RESULTS: In this paper, we propose a complete fine-grained parallel hardware implementation on FPGA to accelerate the GOR-IV package for 2D protein structure prediction. To improve computing efficiency, we partition the parameter table into small segments and access them in parallel. We aggressively exploit data reuse schemes to minimize the need for loading data from external memory. The whole computation structure is carefully pipelined to overlap the sequence loading, computing and back-writing operations as much as possible. We implemented a complete GOR desktop system based on an FPGA chip XC5VLX330. CONCLUSIONS: The experimental results show a speedup factor of more than 430x over the original GOR-IV version and 110x speedup over the optimized version with multi-thread SIMD implementation running on a PC platform with AMD Phenom 9650 Quad CPU for 2D protein structure prediction. However, the power consumption is only about 30% of that of current general-propose CPUs.

Relationship of adrenomedullin expression and microvessel density and prognosis in smooth muscle tumor of uterus.

The aim of this paper was to investigate the relationship between the expression of adrenomedullin (ADM) and microvessel density (MVD) and prognosis in smooth muscle tumor of uterus. The expression of ADM was detected using immunohistochemical staining in specimens from 15 normal controls, 28 cases of uterine leiomyoma (LE) and 19 cases of uterine leiomyosarcoma (LES). The MVD was assayed by immunostainting with CD34. There was a positive correlation between the ADM expression and MVD in LE and LES respectively (r s = 0.823, P < 0.01; r s = 0.793, P < 0.01). The expression of ADM in LE was statistically lower than that in LES (P < 0.05). There was a positive correlation between the ADM expression and mitotic figures in LES (P < 0.05): the more mitotic figures, the higher levels of the ADM expression and poor prognosis. The ADM is an important angiogenic factor in smooth muscle tumor of uterus. The ADM can be used as an accessory marker in estimating the malignant potency of LE and judging the prognosis of LES, and as a novel molecular target of anti-angiogenic and anticarcinogenic strategies.