Search

With the rapid development of the Internet, online reviews have touched on all aspects of our lives and have provided us with much convenience. However, they may also mislead our behavior, especially the deceptive online reviews. In order to filter out deceptive online reviews more precisely, mainly based on sentence joint topic sentiment model (SJTSM), and also integrating the good ideas of sentence latent dirichlet allocation (SenLDA) and CopulaLDA, in this paper we propose a deceptive review detection framework (DRDF) that combines the word-level, chunk-level, and sentence-level topic sentiment models to extract the reviews different features, which is regarded as the vector input of a multiple-classifier to detect deceptive reviews. It not only utilizes the correlation of different level topic-sentiment model representations of a text, but also incorporates the structure and the sentiment label information of reviews. Our compared experimental result on different public datasets has shown that its performance is superior to the existing methods of deceptive review detection.

When a patient takes two or more drugs within a certain time, the efficacy of one drug may be influenced by the other. This phenomenon is called drug-drug interactions (DDIs). DDIs are important and helpful information for both medical staff and patients to make sure that the drugs co-administrated at the same time have a positive effect on therapy of patients. Many approaches have been applied into drug-drug interaction extraction tasks such as support vector machine (SVM), recurrent neural network (RNN) and long short-term memory (LSTM) in particular. However, the structures of these models are relatively shallow for DDI extraction research compared with the deep neural networks employed in the field of computer vision. However much better results can be obtained with a deep problem-specific architecture which develops hierarchical representations. Hierarchical and deep neural networks may improve DDI extraction. To address this problem, we present a hierarchical and deep neural network to enrich the feature extraction process to enhance the performance of DDI extraction. In this article, we present a deep convolutional neural network (DCNN) based on DDI extraction method. In this method, we firstly apply embedding mechanism to get the semantic and syntactic of the original biomedical literature. Then a novel architecture using small convolutions is proposed, which takes raw biomedical literature as input and operates directly at the word level to get the embedding-based convolutional features. Finally, these features are fed to softmax classifier to extract DDIs from biomedical literature. Our experimental results on the DDIExtraction 2013 corpus show that the performance of network increases as the network gets deeper and hits its peak at depth 16, which obtains a better result (an F1 score $\mathrm {o}\mathrm {f}0.845$) than other state-of-the-art methods.

On the basis of space vector modulation and direct torque control, the double six-phase transverse flux permanent magnet motor is taken as the research object. The eighteen-sector stator-flux subdivision method is proposed to reduce current harmonics and improve the characteristic of direct torque control. Control strategy of duty ratio is improved to decrease the torque ripple made by voltage vector mutation. The algorithm combination of the eighteen-sector stator-flux subdivision method and the improved duty ratio algorithm is built as the core of space-vector modulation direct-torque control. The static and dynamic characteristics of control system are simulated. The results show that the new control system can effectively improve the circular flux curve, stable rotate speed, suppress the torque ripple, and enhance the output characteristics of motor torque and rotate speed.

The space robotic system is expected to perform the on orbit servicing mission. It is a challenging task to estimate the pose of the non-cooperative spacecraft (no facilities are mounted onboard for relative pose measurement) during the phase of closing, capturing, and maintenance. In addition, the spacecraft with a high value is always very large, which pose difficulties for the cameras to photo the whole scene in close range. This paper propose a new approach using combined vision system to estimate the relative position and attitude of a large non-cooperative spacecraft in close range. Based on investigation of the characteristics of spacecraft, a series of the feature point is selected as the recognized object. Then, rendezvous camera and eye-in-hand camera share the recognition task in a collaborative behavior, i.e. each traces one or two feature points on the target. In order to fuse the information, an extended PnP model is established. Lastly, the pose estimation algorithm by solving the extended PnP problem is addressed. Results of computer simulation validate the proposed approach.

In this paper, the LEGO mobile robot separating the main body and the peripheral task kits is successfully constructed using by the 3D modeling software and by the hierarchical design method from top to bottom, with LEGO mechanical hardware as body, Lego servo motor as actuator, Lego color sensors as the detection device, Lego EV3 as main controller. The hardware performances of the LEGO mobile robot are tested with matching tasks using the EV 3 oscilloscope platform. The LEGO mobile robot is successfully controlled using by designed algorithms and LEGO Mindstorms EV 3 software platform according to FLL game rules and related tasks. At the same time, all tasks of the robot are accurately completed by regulating the path identification, the error compensation, precision control in the overall design process.

In final approach of rendezvous between a space robot and a non-cooperative target, due to the light and the folds of heat cladding materials on the target surface, the edge of target cannot be accurately extracted by classic Canny algorithm and we are unable to complete measurement of relative position and attitude. To solve this problem, the measurement method of relative position and attitude between two non-cooperative spacecrafts based on graph cut and edge information algorithm is proposed. A circular feature of the target is chosen as the recognition and measurement object. Firstly, the edge of the circular feature on the target is accurately extracted by graph cut and edge information algorithm. Secondly, the edges are ellipse fitting. Lastly, the relative position and attitude of target is obtained by fitting ellipse parameters of binocular cameras. The simulation results show that the precision of this method is better than Canny algorithm's and it can better meet the mission requirements.