Search

Numerous experiments have demonstrated that long non-coding RNA (lncRNA) play an important role in various systems of the human body. LncRNA deletions or mutations can cause human disease. The prediction of lncRNA-disease associations is conducive to the diagnosis and prevention of complex diseases. As we all know, it is a time-consuming and expensive process to predict lncRNA-disease associations via biological experiments. However, the computation methods can effectively discover lncRNA-disease associations with less human and material resources. In this paper, we propose a neural network-based matrix factorization model to predict lncRNA-disease associations, which is called NeuMFLDA. NeuMFLDA first converts the one-hot encoding of disease or lncRNA into word vector via the embedding layer. Then combined with the memorization of the conventional matrix factorization and the generalization of the multi-layer perceptron, the lncRNA-disease associations can be predicted more accurately. In addition, as opposed to conventional pointwise loss function, a new pairwise loss function is proposed to update our model parameters. Our new loss function optimizes the model from the perspective of ranking priority, which is more in line with the solution to the lncRNA-disease associations prediction task. Experiments show that NeuMFLDA reaches average AUCs of 0.904± 0.003 and 0.918± 0.002 in the framework of 5-fold cross validation and Leave-one-out cross validation, which is superior to three the-state-of-art methods. In case studies, 9, 9 and 8 out of top-10 candidate lncRNAs are verified by recently published literatures for hepatocelluar carcinoma, kidney cancer and ovarian cancer, respectively. In short, NeuMFLDA is an effective tool for predicting lncRNA-disease associations.

The brightness of low-temperature polycrystalline silicon and metal-oxide (LTPO) active-matrix organic light-emitting diode (AMOLED) display under low-refresh-rate driving condition tends to increase during pixel voltage holding time of each frame even though there is no critical leakage current path from the storage capacitor. We have found that the main cause of the brightness increase is electron trapping into the gate insulator of driving thin-film transistor (DTFT) which operates in the saturation mode prone to hot carrier injection. We propose a novel driving method to suppress the brightness variation by applying a high voltage to the source and drain of the DTFT during the non-emitting time which is inserted periodically for dimming the organic light-emitting diode (OLED) display. Our experimental results show that the brightness variation can be reduced from 3.7 % to 1.4 % at the 63rd gray level by the proposed DTFT reset scheme.

In high-reliability applications, DC/DC converters should realize high-efficiency and fast-transient in harsh environments. Thus, the circuit parameter design and the reliability design are both critical. The secondary-side control circuit has a faster transient and a simpler gate-drive than the primary-side control circuit, which has been used for over twenty years. However, the detailed design procedure and analysis of the high-reliability secondary-side control circuit have not been presented in the literature. This article introduces a secondary-side control circuit design and its small-signal modeling procedure with a peak-current-mode-control (PCMC) forward converter. The reliability design and evaluation for thick-film converter are demonstrated. A 100-watt prototype is manufactured, and its steady-state waveforms and transient waveforms are tested and then compared with other high-reliability products. The experimental results show that the peak efficiency reaches 90.6%; the load transient response is 330mV/ $560~\mu \text{s}$ ; and the mean-time-between-failure (MTBF) value is 481 kilo-hours, proving the fast-transient and high-reliability features of the secondary-side control circuit.

A single-pixel imaging (SPI) system is often applied to a specific scenario. The target object images may belong to a specific category and have some common features. Fourier or Hadamard illumination patterns can be sub-optimal since they are fixed and non-adaptive. We propose a novel scheme for designing and optimizing the illumination patterns adaptively from an image dictionary by extracting the common features using principal component analysis (PCA), with enhanced imaging efficiency.

We design and integrate four optical phased arrays (OPAs) in a single chip. Each OPA possesses different output grating period. Furthermore, we use optical switches to select one or more OPAs for beam scanning. We demonstrate the longitudinal scanning by tuning the laser wavelength. The experimental results show that the scanning range of the four-lines chip reaches 28.54° when the wavelength ranges from 1520 nm to 1570 nm, and the eight-lines one reaches 19.04° with wavelength range of 1520 nm-1540 nm. We greatly improve the wavelength tuning efficiency for longitudinal scanning.

Real-time flood forecasting of small- and medium-sized rivers in areas with scarce hydrological data is an urgent problem that needs to be solved. Traditional hydrological model parameters cannot be fully trained owing to a lack of data; thus, results obtained by such models are not satisfactory. We need a new way to solve the forecasting problem for small- and medium-sized rivers. We found that the time series of some feature variables have evident change trajectories in spatial dimension, and the change of some feature variables in the spatial dimension has a decisive influence on flooding processes, such as the spatial distribution of rainfall. To reflect the change of feature variables in spatial dimension with to solve the problem of the lack of hydrological data, we constructed a rainfall-flow pattern composed of a spatial-temporal dynamic time warping algorithm and multi-feature algorithm to measure the similarity of hydrological time series. In the experimental watersheds, we used rainfall-flow patterns to forecast the short-term flood streamflow, and satisfactory results were obtained. This suggests that the algorithm is suitable for hydrological studies and improves the accuracy of real-time flood forecasting for longer forecast periods.

One of the main difficulties in solving many-objective optimization is the lack of selection pressure. For an optimization problem, its main purpose is to obtain a nondominated solution set with better convergence and diversity. In this paper, two estimation methods are proposed to convert a many-objective optimization problem into a simple bi-objective optimization problem, that is, the convergence and diversity estimation methods, so as to greatly improve the probability of certain dominance relation between solutions, and then increase the selection pressure. Based on the proposed estimation methods, a new many-objective evolutionary algorithm, termed ABOEA, is proposed. In the convergence estimation method, we use a modified ASF function to solve the performance degradation of the traditional norm distance on the irregular Pareto front. In the diversity estimation method, we innovatively propose a diversity estimation method based on the angle between solutions. Empirical experimental results demonstrate that the proposed algorithm shows its competitiveness against the state-of-art algorithms in solving many-objective optimization problems. Two estimation methods proposed in this paper can greatly improve the performance of algorithms in solving many-objective optimization problems.

Frequent itemset mining is a fundamental problem in data mining area because frequent itemsets have been extensively used in reasoning, classifying, clustering, and so on. To mine frequent itemsets, previous algorithms based on a prefix tree structure have to construct many prefix trees, which is very time-consuming. In this paper, we propose a novel frequent itemset mining algorithm called DPT (Dynamic Prefix Tree) which uses only one prefix tree. We first introduce the concept of the post-conditional database of an itemset, and analyze the distribution of an itemset's post-conditional database in a prefix tree representing a database. Subsequently, we illuminate how DPT adjusts the prefix tree to mine frequent itemsets and give three optimization techniques. An interesting advantage of DPT is that the algorithm can directly output a prefix tree representing all frequent itemsets after slight modifications. Using only one dynamic prefix tree, DPT avoids the high cost of constructing many prefix trees and thus gains significant performance improvement. Experimental results show that DPT remarkably outperforms previous algorithms with respect to running time and memory usage, and that a prefix tree representing all frequent itemsets DPT outputs can be used more efficient than a list representing them previous algorithms output.

Hierarchical topic models, such as hierarchical Latent Dirichlet Allocation (hLDA)and its variations, can organize topics into a hierarchy automatically. On the other hand, there are lots of documents associated with hierarchical label information. Incorporating these information into the topic modeling process can help users to obtain a more reasonable hierarchical structure. However, after analyzing various real-world datasets, we find that these hierarchical labels are ambiguous and conflicting in some levels, which introduces error and restriction to the latent topic and the hierarchical structure exploration process. We call it the horizontal topic expansion problem. To address this problem, in this paper, we propose a novel hierarchical topic model named horizontal and vertical hierarchical topic model (HV-HTM), which aims to incorporate the observed hierarchical label information into the topic generation process, while keeping the flexibility of horizontal and vertical expansion of the hierarchical structure in the modeling process. We conduct experiments on BBC news and Yahoo! Answers datasets and evaluate the effectiveness of HV-HTM on three evaluation metrics. The experimental results show that HV-HTM has a significant improvement on topic modeling, compared to the state-of-the-art models, and it can also obtain a more interpretable hierarchical structure.

The range query of moving objects in a road network is widely used in battlefield environment, intelligent transportation systems, and mobile phone location. It has gradually become a research hotspot in the field of spatiotemporal data management. Most of the existing research on range query of moving objects in the road network is based on the premise of dense sampling of the device and complete storage of data. It ignores the uncertainty of discrete location data caused by a blind area of actual devices and limited memory, which cannot guarantee the accuracy of the range query. In this paper, the processing framework of probabilistic range query of moving objects in the road network is constructed. A spatiotemporal index structure is proposed based on the framework. This index can effectively represent time weights and the relationship between road sections. The probabilistic range query algorithm of moving objects in the road network with an uncertain trajectory caused by sampling frequency is designed and implemented. The experiments verify that the method proposed in this paper can improve query efficiency and ensure query accuracy.

The MOOC Discussion Forum is the place where students and teachers communicate, often plagued by information overload and confusion. Posts that students used to express confusion and demanded teachers' attention are most likely to be overwhelmed by the amount of noise in the forum. Therefore, how to pay attention to urgent posts in time has become a critical problem to be solved. In this paper, we present a new hybrid neural network for identifying “urgent” posts that require immediate attention from instructors. We proposed a semantic and structure extraction part including convolutional neural network (CNN) and gated recurrent unit (GRU), which can simultaneously learn the semantic information and structural information of sentences. In addition, Due to a lot of noise such as spelling mistakes and emoticons in the forum comment text, we propose to use Character-level Convolutional Networks (Char-CNN) to capture these special information. Finally, the semantic and structural information learned by the semantic and structural extraction part is merged with the character information learned by Char-CNN, and the attention mechanism to learn their weights, the final representation of the sentence can be obtained. In our experiments, we achieve urgent posts classification with a micro F-score of 91.8%, 91.3% and 88.4% on the Stanford MOOCPosts dataset, outperforming the state-of-the-art approach by 1.8%, 2.4% and 1.5% respectively. This work can help teachers prioritize their responses and better manage numerous posts. Teachers can answer learner questions in a timely manner and help reduce dropout rates and improve completion rates.

Recent advances in stream-flow prediction using Recurrent Neural Networks (RNN) or Long Short-Term Memory (LSTM) have prompted their exploration in the field of hydrology. Predicting hydrological time series is of great importance, but is very challenging as it is influenced by many complex factors such as dynamic spatio-temporal feature correlation and nonlinear meteorological-hydrological. In this context, we propose a framework based on dynamic spatio-temporal attention (DSTA) to predict the stream-flow of a hydrological station over several days. It consists of three main modules: a spatial module, a temporal module, and a trend input module. Experiments were carried out on real data sets from four watersheds in the mainstream of the Yangtze River and proved that our method is superior to the six baseline methods.

With consideration of both the operating properties from cryogenic MOSFETs and refrigerating costs from cryogenic refrigerators, this paper attempts to carry out the experimental tests and performance evaluations of state-of-the-art 650-V class MOSFETs, and thus to explore a possible design guideline for cryogenic power conversions at liquid nitrogen temperature. Three cryogenic operating behaviors of on-state resistances and breakdown voltages of five types of commercial power MOSFETs and on-state voltage across their built-in reverse diodes are tested from 300 K to 77 K. The measured on-state resistances obtained in low-current tests show almost double-exponential functional relations with the operating temperatures, while the other two cryogenic parameters are directly or inversely proportional to the operating temperatures. Moreover, cryogenic on-state resistance behaviors in high-current tests from 20 A to 90 A are also found to have double-exponential functional relations with the operating currents. Based on the experimental results and their fitted temperature-dependent and current-dependent functions, integrated evaluation of overall energy efficiency involved with refrigerating cost is presented to form a feasible design guideline for cryogenic power conversions. Finally, two 40-kW and 4-MW boost choppers are conceptually designed and discussed to verify the proposed design guideline for the use in various MOSFET-based cryogenic power conversions.

Cloud storage has become a widely accepted data storage model in recent years. With the development of cloud storage applications in various fields, cloud storage security issues have aroused people's special attention. In this paper, taking aim at ensuring data reliability and satisfying QoS requirements for different users, a method named hierarchical storage-based data disaster recovery strategy was proposed. Cloud computing fault tolerance model is constructed by grading the storage resources of cloud service providers according to the service level to meet the different QoS requirements of the cloud users. On this basis, some storage levels are classified to improve resource utilization. The correctness of the classification strategy is analyzed theoretically, finally, the effectiveness of the proposed strategy is validated by emulation experiment. This paper has the theoretical and practical value to improve the overall experience of users.

Computer aided detection and diagnosis system (CAD) is designed to improve the efficiency and quality of medical diagnosis. The existing CAD system tries to realize a diagnosis process in an automatic way to replace the doctor's diagnosis work completely, but it is difficult to capture the doctor's detection and diagnosis needs and goals accurately due to lack of doctor's experience. Thus, the accuracy is not up to the doctor's manual diagnosis results, and it is a tedious and cumbersome job to use the system because it requires manual intervention, which leads to the fact that CAD system was difficult to be widely used. This paper analyzes the characteristics of doctors' diagnosis tasks deeply, and makes the reasonable allocation of tasks between the doctor and computer. Then the perceptual control theory is introduced into the task model, a PTT task model is proposed to make it express uncertainty of the doctor's diagnosis tasks, and it can be used as a reference for future uncertainty task analysis. Therefore, an interactive CAD tasks framework is put forward with the assistant decision support provided for doctors by means of Bayesian network model and conceptual graph semantic matching method to diagnose tasks. In addition, effective support is provided for interface development staffs to design interactive systems that are suitable for the physicians' diagnostic tasks. The experimental results show that the method not only improves the accuracy and efficiency of the medical diagnosis, but also improves the usability of the system design.

Understanding the actions of other people is a key component of social interaction. This paper used an electroencephalography and functional near infrared spectroscopy (EEG-fNIRS) bimodal system to investigate the temporal-spatial features of action intention understanding. We measured brain activation while participants observed three actions: 1) grasping a cup for drinking; 2) grasping a cup for moving; and 3) no meaningful intention. Analysis of EEG maximum standardized current density revealed that brain activation transitioned from the left to the right hemisphere. EEG-fNIRS source analysis results revealed that both the mirror neuron system and theory of mind network are involved in action intention understanding, and the extent to which these two systems are engaged appears to be determined by the clarity of the observed intention. These findings indicate that action intention understanding is a complex and dynamic process.

In the above article [1], there is a missing grant number for the third funding acknowledgment “the Key Agricultural Programs of Science and Technology and Innovation of Xiangyang,” and we append “under Grant 2020ABA002240” to the acknowledgment as above.