Social media emerged as an important resource of information to improve the emergency situation awareness of flooding disasters. However, the online microblog text stream is unstructured and ...unbalanced obviously. Given the big, real-time, and noisy flood disaster microblog text flow, a new regional emergency situation awareness model to automatic assess flood disaster risk is proposed. Firstly, according to the established online disaster event-meta frame, a multi-label classification algorithm for the flood microbloggings is constructed based on the historical dataset. This algorithm helps to assign the relevant event-meta tags to each situation microbloggings. Second, a new machine learning method for dynamic assessment of flood risk for online microbloggings is developed. The flood event-metas are considered to be feature vectors, and the four different levels of flood risk are considered to be four classes. Then, the flood risk assessment task is innovatively transformed into a multi-classification task. By the logistic regression ordered multi-classification algorithm, the dynamic quantitative evaluation of event-meta, users and regional risks is realized. Finally, the proposed model is applied in the case of the Yuyao Flood. The results of the case study show that the Yuyao Flood’s online quantitative risk assessment results are consistent with real accumulated precipitation data, which illustrate that the proposed machine learning model could realize the bottom-up automatic disaster information collecting by processing victim user-generated content effectively. Social media is proven to supplement the deficiencies of traditional disaster statistics and provide real-time, scientific information support for the implementation of flood emergency processes.
Objective:
Gastric cancer is one of the most common malignant tumors worldwide, and for resectable tumors, the most effective treatment is surgery with chemotherapy in neoadjuvant or adjuvant ...setting. However, the majority of patients fail to achieve the ideal initial response and/or develop resistance to chemotherapy. It was reported that long noncoding RNA regulator of reprogramming (ROR) is highly associated with the progression of gastric cancer. However, the role ROR in multidrug resistance (MDR) remains unclear.
Methods:
The messenger RNA levels of 63 specimens of patients with gastric cancer were determined by real-time polymerase chain reaction analysis and were correlated with drug resistance and survival of patients. To determine the cellular functions of ROR, we generated gastric cancer MDR cells. The effect of ROR depletion on multidrug resistance-associated protein 1 (MRP1) expression and cell apoptosis were examined by immunoblotting analyses, 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, and flow cytometry.
Results:
We found that ROR expression levels are positively associated with increased MDR and poor prognosis of patients with gastric cancer. Regulator of reprogramming expression is increased in gastric cancer cells resistant to adriamycin (ADR) and vincristine (VCR). Depletion of ROR reduced MRP1 expression and increased apoptosis of drug-resistant gastric cancer cells in response to ADR and VCR treatment.
Conclusions:
We demonstrated that ROR expression promotes MRP1 expression and MDR of gastric cancer cells and is correlated with increased MDR and poor prognosis of patients with gastric cancer. Our finding highlighted the potential of targeting ROR to improve the efficacy of chemotherapy.
Active clamping circuits can effectively suppress the voltage imbalance between series-connected insulated-gate bipolar transistors (IGBTs). However, while the active clamping circuit is conducting, ...extra current is injected into the gate of the IGBT, the gate voltage increases, and the IGBT operates in the active region. Therefore, long time conduction and frequent actions of the active clamping circuit will lead to extremely high switching loss of the IGBT with high collector-emitter voltage and serious switching loss imbalance between the series-connected IGBTs, which imperils the efficiency and safety of the system, particularly in the applications of high-voltage IGBT (HV-IGBT) series connection. In this paper, a novel active clamping circuit with status feedback is proposed for series-connected HV-IGBTs. A high-speed status feedback subcircuit is designed for transforming the operation status of an active clamping circuit into optical signal and feeding it back to the control system. According to the feedback signals, the microcontroller regulates the switching-on time and switching-off time of the series-connected HV-IGBTs' drive signals timely in order to implement voltage balancing and, thus, to restrain the actions of active clamping circuits. By applying this voltage balancing method to the HV-IGBT series connection circuit, the voltage balancing performance is expected to improve, and high switching loss and serious switching loss imbalance are expected to be suppressed. Experimental results verify the validity and superiorities of the proposed voltage balancing circuit and control strategy.
Probability density machine (PDM) is a novel algorithm which was proposed recently for addressing class imbalance learning (CIL) problem. PDM can capture priori data distribution information well and ...present robust performance in various CIL applications. However, we also note that the PDM is sensitive to CIL data with varying density and/or small disjunctions which means there are two or multiple obvious sub-clusters within the same class, as on this kind of data, the estimation of conditional probability might be extremely inaccurate. To address this problem, we introduce the shared nearest neighbors (SNN) clustering technique into PDM procedure and propose a novel SNN-PDM algorithm. Specifically, the SNN can adapt varying density and capture small disjunctions existing in data distribution well. We evaluate the proposed algorithm on a large amount of CIL datasets, and the results show that the proposed SNN-PDM algorithm outperforms the PDM and several previous methods. Meanwhile, in comparison with PDM, the SNN-PDM has less time consumption.
The technology of long‐distance power supply with high‐power laser (HPL) over single‐mode fiber (SMF) is of great significance in specific environment. The nonlinear effect of fiber and photovoltaic ...conversion (PC) efficiency are the key factors restricting the application of this technology. The wide linewidth laser and cascaded long period fiber grating (CLPFG) band rejection filter are used to suppress the stimulated Brillouin scattering (SBS) and stimulated Raman scattering (SRS) effects, respectively, integrating sphere like, scattering light guide cone and thermoelectric power generation improve PC efficiency. A HPL over SMF remote power supply system is developed and tested. The injected fiber power is 10 W, the wavelength of 1550 nm laser is transmitted through 103 km single‐mode fiber, and then 26 mW power is converted for the sensor. This is also the highest level of the open literature. It is expected to be applied to the power supply of high voltage transmission line remote monitoring information system in remote areas.
Deep Q-network(DQN) is one of the standard methods to solve the Unmanned Aerial Vehicle(UAV) path planning problem. However, the way agent deepens its cognition of the environment through frequent ...random trial-and-error leads to slow convergence. This paper proposes an optimized DQN with Artificial Potential Field(APF) as prior knowledge called B-APFDQN for path planning. Replacing the traditional neural network which has only one Q-value output with a multi-output neural network to promote the training process in combination with APF. Furthermore, a SA-ε-greedy algorithm that can automatically adjust the stochastic exploration frequency with steps and successes is proposed in order to prevent the agent from falling into local optimum. We remove the nodes that do not affect the path connectivity and apply the B-spline algorithm to make the path shorter and smoother. Simulation experiments show that the proposed B-APFDQN algorithm performs better than the classical DQN, has a strong ability to avoid falling into local optimum, and the obtained paths are smooth and shorter, which proves the effectiveness of B-APFDQN in the UAV path planning problem.
It is well known that in supervised learning, active learning could effectively decrease the complexity of training instances without obvious loss of the classification performance. Generally, active ...learning is applied in the scenario that lots of instances are easy to be acquired, but labeling them is expensive and/or time-consuming. In this study, we try to implement active learning by using extreme learning machine (ELM) classifier based on three reasons as follows: (1) ELM has light computational costs, (2) ELM has strong generalization ability which is even comparable with support vector machine (SVM) and (3) ELM could be directly applied on both binary-class and multiclass problems. Specifically, an active learning algorithm based on ELM classifier named AL-ELM is proposed in this paper. During active learning, AL-ELM estimates the uncertainty of each unlabeled instance by creating a mapping relation between the actual outputs of the instance in ELM and the approximated membership probability of the same instance. In other words, ELM is converted as the equivalent Bayes classifier. On each iteration, those most uncertain instances are extracted and labeled to promote the quality of classification model. The learning procedure stops until it satisfies a pre-designed criterion. Experimental results on 20 benchmark data sets show that AL-ELM is better than or at least comparable to several state-of-the-art uncertainty-based active learning algorithms. Also, in contrast with several other algorithms, AL-ELM could effectively decrease the running time of learning procedure.
Graph convolutional networks(GCNs) have become one of the important technologies for solving graph structured data problems. GCNs utilize convolutional networks to learn node and spatial features in ...the graph, and fully fuse them for node classification tasks. Consequently, for most GCNs, “graph convolution” operation over the set of nodes is the key. Nevertheless, such an operation is frequently embedded into a fixed graph without considering the dynamic variation of the set of nodes. Immediately, the incremental learning mechanism can be considered. From this viewpoint, a Sampling Sequential Guided Graph Convolutional Network (SSGCN) is developed. Firstly, through random sampling over the set of nodes, multiple minibatch graphs can be obtained. Secondly, by the proposed sequential guidance, the weight matrices can be updated incrementally by using “graph convolution” over minibatch graphs one by one. That is, the trained weight matrix of the previous minibatch graph is saved, which in turn is used as an input for training the next minibatch graph. Finally, the prediction results from all minibatch graph learners are integrated. We conducted experiments based on the standard variance of different
τ
number of losses, and over three common citation network datasets (Cora, Citeseer and Pubmed) to evaluate the performance of SSGCN in node classification tasks. The experimental results show that, in comparison study and ablation study,in terms of both efficiency and effectiveness, the performance of SSGCN is superior to most state-of-the-art methods. In addition, SSGCN shows good convergence in visualization.
SMOTE (Synthetic Minority Oversampling TEchnique) is one of the most popular and well-known sampling algorithms for addressing class imbalance learning problem. The merits of SMOTE reflect at that in ...comparison with the random oversampling technique, it can alleviate the problem of overfitting to a large extent. However, two drawbacks of SMOTE have also been observed as follows, 1) it tends to propagate the noisy information in the procedure of oversampling; 2) it always assigns a global neighborhood parameter K but neglects the local distribution characteristics. To synchronously deal with these two problems, a grouped SMOTE algorithm with noise filtering mechanism (GSMOTE-NFM) is presented in this article. The algorithm firstly adopts Gaussian-Mixture Model (GMM) to explore the real distributions of the majority and minority classes, respectively. Then, most noisy instances can be removed by comparing the probability densities of the same instance in two different classes. Next, two new GMMs are constructed on the rest majority and minority class instances, respectively. Furthermore, all minority class instances can be divided into three different groups: safety, boundary and outlier, based on the corresponding probability density information. Finally, we assign an individual parameter K to the instances belonging to each specific group to generate new instances. We tested GSMOTE-NFM algorithm on 24 benchmark binary-class data sets with three popular classification models, and compared it with several state-of-the-art oversampling algorithms. The results indicate that our algorithm is significantly superior than the original SMOTE algorithm and several SMOTE-based modified methods.
Downhole turbine generators (DHTG) installed within drill-string are susceptible to internal and external excitation during the drilling process, causing significant dynamic loads on bearings, and ...thereby reducing the bearing’s service life. In this study, a finite element model of an unbalanced rotor-bearing system (RBS) of DHTG with multi-frequency excitations, based on the Lagrangian motion differential equation, is established. The responses of the RBS under different drill-string excitations in terms of time-domain response, whirl orbit, and spectrum are analyzed. For a constant rotor speed, lateral harmonic translational and lateral oscillation both transform the whirl orbit to quasi-periodic, while axial rotation only changes the response amplitude. Changing the duration of pulse excitation leads to different response forms. Then, the dynamic characteristics of the RBS supported by a squeeze film damper (SFD) are investigated. The results indicate that SFD effectively reduces the displacement response amplitude and bearing force near the critical speed. As the axial rotation angular velocity of the drill-string increases, the first critical speed and displacement response decrease, while the variation of lateral oscillation frequency and amplitude has limited impact on them. The established model provides a means for analyzing the dynamic characteristics of DHTG’s RBS under drill-string excitations during the design stage.