Automatic discrimination between front and back ensemble locations in HRTF-convolved binaural recordings of music

One of the greatest challenges in the development of binaural machine audition systems is the disambiguation between front and back audio sources, particularly in complex spatial audio scenes. The goal of this work was to develop a method for discriminating between front and back located ensembles in binaural recordings of music. To this end, 22, 496 binaural excerpts, representing either front or back located ensembles, were synthesized by convolving multi-track music recordings with 74 sets of head-related transfer functions (HRTF). The discrimination method was developed based on the traditional approach, involving hand-engineering of features, as well as using a deep learning technique incorporating the convolutional neural network (CNN). According to the results obtained under HRTF-dependent test conditions, CNN showed a very high discrimination accuracy (99.4%), slightly outperforming the traditional method. However, under the HRTF-independent test scenario, CNN performed worse than the traditional algorithm, highlighting the importance of testing the algorithms under HRTF-independent conditions and indicating that the traditional method might be more generalizable than CNN. A minimum of 20 HRTFs are required to achieve a satisfactory generalization performance for the traditional algorithm and 30 HRTFs for CNN. The minimum duration of audio excerpts required by both the traditional and CNN-based methods was assessed as 3 s. Feature importance analysis, based on a gradient attribution mapping technique, revealed that for both the traditional and the deep learning methods, a frequency band between 5 and 6 kHz is particularly important in terms of the discrimination between front and back ensemble locations. Linear-frequency cepstral coefficients, interaural level differences, and audio bandwidth were identified as the key descriptors facilitating the discrimination process using the traditional approach.

Fast Fractal Technique using Modified Moment Features on Domain Blocks

In this research, a new technique is suggested to reduce the long time required by the encoding process by using modified moment features on domain blocks. The modified moment features were used in accelerating the matching step of the Iterated Function System (IFS). The main disadvantage facing the fractal image compression (FIC) method is the over-long encoding time needed for checking all domain blocks and choosing the least error to get the best matched domain for each block of ranges. In this paper, we develop a method that can reduce the encoding time of FIC by reducing the size of the domain pool based on the moment features of domain blocks, followed by a comparison with threshold (the selected threshold based on experience is 0.0001). The experiment was conducted on three images with size of 512x512 pixel, resolution of 8 bits/pixel, and different block size (4x4, 8x8 and, 16x16 pixels). The resulted encoding time (ET) values achieved by the proposed method were 41.53, 39.06, and 38.16 sec, respectively, for boat , butterfly, and house images of block size 4x4 pixel. These values were compared with those obtained by the traditional algorithm for the same images with the same block size, which were 1073.85, 1102.66, and 1084.92 sec, respectively. The results imply that the proposed algorithm could remarkably reduce the ET of the images in comparison with the traditional algorithm.

Influence of Atmospheric Scattering on the Accuracy of Laser Altimetry of the GF-7 Satellite and Corrections

Satellite laser altimetry can obtain sub-meter or even centimeter-scale surface elevation data over large areas, but it is inevitably affected by scattering caused by clouds, aerosols, and other atmospheric particles. This laser ranging error caused by scattering cannot be ignored. In this study, we systematically combined existing atmospheric scattering identification technology used in satellite laser altimetry and observed that the traditional algorithm cannot effectively estimate the laser multiple scattering of the GaoFen-7 (GF-7) satellite. To solve this problem, we used data from the GF-7 satellite to analyze the importance of atmospheric scattering and propose an identification scheme for atmospheric scattering data over land and water areas. We also used a look-up table and a multi-layer perceptron (MLP) model to identify and correct atmospheric scattering, for which the availability of land and water data reached 16.67% and 26.09%, respectively. After correction using the MLP model, the availability of land and water data increased to 21% and 30%, respectively. These corrections mitigated the low identification accuracy due to atmospheric scattering, which is significant for facilitating satellite laser altimetry data processing.

A Network That Balances Accuracy and Efficiency for Lane Detection

In the automatic lane-keeping system (ALKS), the vehicle must stably and accurately detect the boundary of its current lane for precise positioning. At present, the detection accuracy of the lane algorithm based on deep learning has a greater leap than that of the traditional algorithm, and it can achieve better recognition results for corners and occlusion situations. However, mainstream algorithms are difficult to balance between accuracy and efficiency. In response to this situation, we propose a single-step method that directly outputs lane shape model parameters. This method uses MobileNet v2 and spatial CNN (SCNN) to construct a network to quickly extract lane features and learn global context information. Then, through depth polynomial regression, a polynomial representing each lane mark in the image is output. Finally, the proposed method was verified in the TuSimple dataset. Compared with existing algorithms, it achieves a balance between accuracy and efficiency. Experiments show that the recognition accuracy and detection speed of our method in the same environment have reached the level of mainstream algorithms, and an effective balance has been achieved between the two.

Improved Q -Learning Method for Multirobot Formation and Path Planning with Concave Obstacles

Aiming at the formation and path planning of multirobot systems in an unknown environment, a path planning method for multirobot formation based on improved Q -learning is proposed. Based on the leader-following approach, the leader robot uses an improved Q -learning algorithm to plan the path and the follower robot achieves a tracking strategy of gravitational potential field (GPF) by designing a cost function to select actions. Specifically, to improve the Q-learning, Q -value is initialized by environmental guidance of the target’s GPF. Then, the virtual obstacle-filling avoidance strategy is presented to fill non-obstacles which is judged to tend to concave obstacles with virtual obstacles. Besides, the simulated annealing (SA) algorithm whose controlling temperature is adjusted in real time according to the learning situation of the Q -learning is applied to improve the action selection strategy. The experimental results show that the improved Q -learning algorithm reduces the convergence time by 89.9% and the number of convergence rounds by 63.4% compared with the traditional algorithm. With the help of the method, multiple robots have a clear division of labor and quickly plan a globally optimized formation path in a completely unknown environment.

Cluster analysis of time series K-Means line loss based on DWT distance

This paper constructs an indicator system composed of inherent attributes and time characteristics of the line based on the line loss, and proposes a K-Means line loss cluster analysis model based on this indicator system. The line is classified according to the clustering results. The result is 314.51 on the CH index (Calinski Harabasz Index), 0.19 on the Silhouette Cofficient (Silhouette Cofficient), and a running time of 0.508s. Compared with the traditional algorithm, it is greatly improved. The field of line loss analysis has guiding significance.

Artificial Intelligence Algorithm-Based Computed Tomography Images in the Evaluation of the Curative Effect of Enteral Nutrition after Neonatal High Intestinal Obstruction Operation

In this study, CT image technology based on level set intelligent segmentation algorithm was used to evaluate the postoperative enteral nutrition of neonatal high intestinal obstruction and analyze the clinical treatment effect of high intestinal obstruction, so as to provide a reasonable research basis for the clinical application of neonatal high intestinal obstruction. 60 children with high intestinal obstruction treated in the hospital were selected as the research objects. Based on the postoperative enteral nutrition treatment, they were divided into control group (noncatheterization group)-parenteral nutrition support. In the observation group, gastric tube was placed through nose for nutritional support. Then, CT images based on level set segmentation algorithm were used to compare the intestinal recovery of the two groups, and the biochemical indexes and hospitalization were compared. The level set algorithm can accurately segment the lesions in CT images. The segmentation time of the level set algorithm was shorter than that of the traditional algorithm (24.34 ± 2.01 s vs. 75.21 ± 5.91 s), and the segmentation accuracy was higher than that of the traditional algorithm (84.71 ± 3.91% vs. 70.04 ± 3.71%, P < 0.05). The weight of children in the observation group (100 ± 7 g) was higher than that in the control group (54 ± 5 g), and the ICU monitoring time (12.01 ± 2.65 days) and the hospital stay (17.82 ± 3.11 days) were shorter than those in the control group (13.42 ± 2.95 days, 19.13 ± 3.22 days, all P < 0.05). The level set segmentation algorithm can accurately segment the CT image, so that the disease location and its contour can be displayed more clearly. Moreover, the nasal placement of jejunal nutrition tube can effectively improve the intestinal function of children, maintain the steady-state environment of intestinal bacterial growth, and significantly improve the clinical treatment effect, which is worthy of clinical application and promotion.

Multi-Objective UAV Trajectory Planning in Uncertain Environment

UAV trajectory planning is one of the research focuses in artificial intelligence and UAV technology. The asymmetric information, however, will lead to the uncertainty of the UAV trajectory planning; the probability theory as the most commonly used method to solve the trajectory planning problem in uncertain environment will lead to unrealistic conclusions under the condition of lacking samples, while the uncertainty theory based on uncertain measures is an efficient method to solve such problems. Firstly, the uncertainties in trajectory planning are sufficiently considered in this paper; the fuel consumption, concealment and threat degree with uncertain variables are taken as the objective functions; the constraints are analyzed according to the maneuverability; and the uncertain multi-objective trajectory planning (UMOTP) model is established. After that, this paper takes both the long-term benefits and its stability into account, and then, the expected-value and standard-deviation efficient trajectory model is established. What is more, this paper solves the Pareto front of the trajectory planning, satisfying various preferences, which avoids the defects of the trajectory obtained by traditional model only applicable to a certain specific situation. In order to obtain a better solution set, this paper proposes an improved backbones particle swarm optimization algorithm based on PSO and NSGA-II, which overcomes the shortcomings of the traditional algorithm such as premature convergence and poor robustness, and the efficiency of the algorithm is tested. Finally, the algorithm is applied to the UMOTP problem; then, the optimal trajectory set is obtained, and the effectiveness and reliability of the model is verified.

A multi-AUV cooperative navigation method

Cooperative navigation is one of the key methods for multiple autonomous underwater vehicles (AUVs) to obtain accurate positions when performing tasks underwater. In the realistic state-space model of the multi-AUV cooperative navigation system, where the system noise does not satisfy the additivity, it is necessary to augment the dimension of the state variables before nonlinear filtering. Aiming at the problem that the error of traditional algorithms increases linearly with the dimension of state-space, a cooperative navigation method based on Augmented Embedded Cubature Kalman filter (AECKF) algorithm is proposed. The experiment results show that the AECKF cooperative navigation algorithm has better positioning accuracy and stability than the traditional algorithm.

A simplified algorithm for 3D mesh model considering the influence of edge features

Aiming at the problem that most of the existing grid simplification algorithms for 3D models can not deal with a large number of boundary or non-popular grid models, this paper proposes a grid simplification algorithm for 3D models based on traditional algorithms. The algorithm mainly studies the geometric features of the model, considering the calculation methods and characteristics of edge shrinkage, and introduces the edge feature factors on the basis of the traditional algorithm, that is, the triangular area and side length factors of local area are introduced in the calculation of folding cost. In addition, the gaussian curvature characteristics of the 3D model are also included. Experimental results show that the proposed algorithm can keep the detail features of the mesh model well, and greatly reflect the quality and effect of mesh simplification after simplification.