Search

The core issue of learning-to-rank (LTR) for document retrieval lies in finding an optimal ranking policy to meet the search intent of the user. The majority of proposed LTR approaches treat the ranking as a static process, employing a fixed ranking policy to immediately assign scores to documents. By contrast, ranking is not a static but an interactive process where the user continues interacting with the document retrieval system through information exchange such as search intent (e.g., rating or clicking for the retrieved items). We model the interactive ranking process (IRP), and propose an Attention-Based Interactive LTR model (AIRank) to constitute an intent-aware flexible ranking policy to gratify the user’s need. To enhance the ranking quality, the inherent relations among documents are procured by the self-attention method to contribute to an enriched user intent representation. Furthermore, we mend the policy gradient learning method to train the AIRank in the IRP. Experiments demonstrate the effectiveness of AIRank compared to the state-of-the-art methods in terms of normalized discounted cumulative gain and expected reciprocal rank. [ABSTRACT FROM AUTHOR]

In the natural language processing family, learning representations is a pioneering study, especially in sequence-to-sequence tasks where outputs are generated, totally relying on the learning representations of source sequence. Generally, classic methods infer that each word occurring in the source sequence, having more or less influence on the target sequence, should all be considered when generating outputs. As the summarization task requires the output sequence to only retain the essence, classic full consideration of the source sequence may not work well on it, which calls for more suitable methods with the ability to discard the misleading noise words. Motivated by this, with both relevance retaining and redundancy removal in mind, we propose a summarization learning model by implementing an encoder with copious contextual information represented and a decoder with a selecting mechanism integrated. Specifically, we equip the encoder with an asynchronous bi directional parallel structure, in order to obtain abundant semantic representation. The decoder, different from the classic attention-based works, employs a self-aware context selecting mechanism to generate summary in a more productive way. We evaluate the proposed methods on three benchmark summarization corpora. The experimental results demonstrate the effectiveness and applicability of the proposed framework in relation to several well-practiced and state-of-the-art summarization methods. [ABSTRACT FROM AUTHOR]

Ultrasonic flowmeters (UFMs) based on the principle of transit time difference are widely used in process industries. The transit time difference is obtained through analyzing received acoustic signals generated by a couple of transducers located upstream and downstream respectively. The quality of received acoustic signal will directly affect the measurement accuracy of UFM. For this reason, a measurement-calculation coupled approach combining measurement tools and numerical simulation for calculating the acoustic signal of UFM is proposed in this paper. The method can predict the acoustic signals of UFM with different flowrates. First, important boundary condition (vibration velocity on transmitter transducer surface) is measured by measurement tool, which can reduce computational complexity and also avoid modeling transmitter transducers. Second, simulating the wave propagation (difficult to access experimentally) within moving medium by using the measured vibration velocity. Third, obtaining the transfer function of receiver by comparing estimated force acting on the receiver transducer surface with measured voltage signal from receiver, which can avoid modeling receiver transducer. Finally, predicting the received acoustic signal at different flowrates by using the transfer function. The rationality of predicted data was validated by comparing experimental and predicted acoustic signal on receiver transducer at different flowrates. A good agreement between simulated and experimental data was obtained, which means that the working processes of the acoustic signal generated by actual transducers inside UFMs can be accurately predicted based on this method. Analysis of the predicted results will provide good guides and advices to the design of UFMs involving actual application. [ABSTRACT FROM AUTHOR]

In a 3-D scanning task, a robot-sensor system controls a robotic arm to move a laser sensor. In order to align the coordinate system of the robotic arm and laser sensor, prior calibration is required to derive the transformation between both coordinate systems. This paper proposes a new calibration method in three steps: manual data collection, sensing data calculation, and transformation solution. First, at least four data are required to be collected by the user. The sensing data are then calculated from the collected data and adopted to provide the desired transformation. The proposed algorithm has two features: arbitrary placement of planar disk and noise tolerant. Using a planar disk, the algorithm will automatically derive the angular relationship between the disk and the sensor plane, enabling arbitrary orientation placement. Noise tolerant is guaranteed by fitting ellipses during the sensing data calculation and using a single set of sensing data in transformation solution. Experiments and comparisons are given to demonstrate the efficiency of the proposed calibration algorithm.

Note to Practitioners—This paper was motivated by the problem of calibrating a laser sensor and a positioning device (robot arm, CMM, etc.) in a robust and fast manner. Specifically, the calibration is to derive the transformation by aligning the sensors coordinate system to the positioning devices coordinate system. The proposed calibration procedure consists of two parts: manual data collection and automatic transformation calculation. During manual data collection, users only need to select four different data; whereby each data contains of two positions with the same orientation. Then, the desired transformation will be derived automatically. The calibration is designed in an efficient and robust way whereby: 1) data collection is done using a simple planar disk placed in arbitrary orientations; 2) minimum human interaction required; 3) tolerant to noise in the sensor data; and 4) easy implementation by following a proven and standard protocol. [ABSTRACT FROM PUBLISHER]

Double-threshold method is a typical and simple time-of-flight (TOF) measurement method for time-difference-based ultrasonic flowmeter. Some improvements have been proposed to suppress the cycle-skip phenomenon in double-threshold method. However, there are still some application limitations when the waveform is distorted caused by the environment change, especially the temperature change. This paper proposes a similarity judgment-based double-threshold method to deal with the cycle-skip problem. In this method, time values of three consecutive positive zero-crossing points after the feature point are acquired and five consecutive cycles after the first obtained time are saved. The TOF is automatically selected from three acquired time values according to an adaptive determination function which bases on the similarity between signals from two adjacent measurements. These operations guarantee that the obtained TOF locates on the same positive zero-crossing point in each measurement. The proposed method was validated by both numerical and experimental tests. Comparison between the proposed method and other double-threshold methods shows that the proposed method successfully eliminates cycle-skip phenomenon under different working conditions. [ABSTRACT FROM PUBLISHER]

As a widely used method in flow measurement, Gaussian quadrature is traditionally applied to determine the flowrate with multiple acoustic paths. However, it is only available to parallel path arrangement and the path position cannot be customized by users because of the nature of numerical integration principle. Accuracy of flowrate determination is greatly restricted meanwhile. In this paper, a new method based on generalized inverse of matrix (GIM) is proposed to work out the flowrate in arbitrary multipath arrangement. With an integrable model of flow distribution established, the GIM method will find the optimal weights and achieve highly accurate flowrate. Three perfect profile assumptions, including Jacobi, optimal weighted integration for circular sections, and typical power-law profile, are, respectively, adopted in this paper to explore the performance of GIM. Its effects are at first experimentally validated in parallel path arrangement of Gauss–Jacobi on a commercially available ultrasonic flowmeter. Then, four representative types that Gaussian quadrature is not feasible to are studied via numerical simulation, including a parallel and three crossed path arrangements. Performance of the proposed GIM method is verified under straight pipe, single bend, and double bend with an expander as well as on eight installation angles. Results reveal that GIM is applicable to accurate flowrate determination for arbitrary multipath arrangement and crossed paths could provide high determination accuracy and good robustness even under complicated flow field. [ABSTRACT FROM PUBLISHER]

Artificial neural network (ANN) was proposed as an effective method to help multipath ultrasonic flowmeter (UFM) reduce its measurement error when determining the flowrate of complex flow field. However, the effectiveness of the ANN method heavily depends on the network architecture specified by the designer, and also the provided initial weights and layer biases. This hinders the ANN to be widely used in actual UFMs. This paper proposes a genetic algorithm (GA) optimized ANN method (GANN) to be used in UFMs. The GA is utilized to determine ANN architecture based on its efficient parallel advantage in global search to replace traditional trial and error approach or empirical method. In addition, the initial weights and biases are optimized by GA, which is capable to avoid the network getting stuck with local minimum and qualify it for good generalization ability. Tests are implemented on numerical models simulating a six-path UFM installed downstream single or double elbows with complex flow field passing through it. Comparisons between the results of classical Gaussian quadrature, existing ANN, and proposed GANN are given for verification. The flowrate determination error of GANN is only 40% $\sim 62$ % of existing ANN, which is extremely smaller than the Gaussian quadrature method. In addition, the output of GANN is much more stable than existing ANN, as proper initial weights and layer biases will be generated by GA for iteration process even random data are given for training. [ABSTRACT FROM PUBLISHER]

An interactive surgical simulation system needs to meet three main requirements, speed, accuracy, and stability. In this paper, we present a stable and accurate method for animating mass–spring systems in real time. An integration scheme derived from explicit integration is used to obtain interactive realistic animation for a multiobject environment. We explore a predictor–corrector approach by correcting the estimation of the explicit integration in a poststep process. We introduce novel constraints on positions into the mass–spring model (MSM) to model the nonlinearity and preserve volume for the realistic simulation of the incompressibility. We verify the proposed MSM by comparing its deformations with the reference deformations of the nonlinear finite-element method. Moreover, experiments on porcine organs are designed for the evaluation of the multiobject deformation. Using a pair of freshly harvested porcine liver and gallbladder, the real organ deformations are acquired by computed tomography and used as the reference ground truth. Compared to the porcine model, our model achieves a $1.502$ mm mean absolute error measured at landmark locations for cases with small deformation (the largest deformation is $49.109$ mm) and a $3.639$ mm mean absolute error for cases with large deformation (the largest deformation is $83.137$ mm). The changes of volume for the two deformations are limited to $0.030\%$ and $0.057\%$, respectively. Finally, an implementation in a virtual reality environment for laparoscopic cholecystectomy demonstrates that our model is capable to simulate large deformation and preserve volume in real-time calculations. [ABSTRACT FROM PUBLISHER]