Search

Depth perception capability is one of the essential requirements for various autonomous driving platforms. However, accurate depth estimation in a real-world setting is still a challenging problem due to high computational costs. In this paper, we propose a lightweight depth completion network for depth perception in real-world environments. To effectively transfer a teacher's knowledge, useful for the depth completion, we introduce local similarity-preserving knowledge distillation (LSPKD), which allows similarities between local neighbors to be transferred during the distillation. With our LSPKD, a lightweight student network is precisely guided by a heavy teacher network, regardless of the density of the ground-truth data. Experimental results demonstrate that our method is effective to reduce computational costs during both training and inference stages while achieving superior performance over other lightweight networks.

Background: In modern structural bioinformatics, comparison of molecular structures aimed to identify and assess similarities and differences between them is one of the most commonly performed procedures. It gives the basis for evaluation of in silico predicted models. It constitutes the preliminary step in searching for structural motifs. In particular, it supports tracing the molecular evolution. Faced with an ever-increasing amount of available structural data, researchers need a range of methods enabling comparative analysis of the structures from either global or local perspective., Results: Herein, we present a new, superposition-independent method which processes pairs of RNA 3D structures to identify their local similarities. The similarity is considered in the context of structure bending and bonds' rotation which are described by torsion angles. In the analyzed RNA structures, the method finds the longest continuous segments that show similar torsion within a user-defined threshold. The length of the segment is provided as local similarity measure. The method has been implemented as LCS-TA algorithm (Longest Continuous Segments in Torsion Angle space) and is incorporated into our MCQ4Structures application, freely available for download from http://www.cs.put.poznan.pl/tzok/mcq/ ., Conclusions: The presented approach ties torsion-angle-based method of structure analysis with the idea of local similarity identification by handling continuous 3D structure segments. The first method, implemented in MCQ4Structures, has been successfully utilized in RNA-Puzzles initiative. The second one, originally applied in Euclidean space, is a component of LGA (Local-Global Alignment) algorithm commonly used in assessing protein models submitted to CASP. This unique combination of concepts implemented in LCS-TA provides a new perspective on structure quality assessment in local and quantitative aspect. A series of computational experiments show the first results of applying our method to comparison of RNA 3D models. LCS-TA can be used for identifying strengths and weaknesses in the prediction of RNA tertiary structures.

Aiming at the problem of instability caused by the randomness of node starting order and updating labels in the label propagation algorithm, this paper proposed a new label propagation algorithm for detection of complex network community (Density Peaks and Node Similarity, DPNS-LPA）. It includes the determination of community center and label propagation of peripheral nodes. Firstly, the method defined the local similarity index of nodes which was characterized by the hub depressed index, Jaccard index and the structural characteristics of nodes with degree 1,and this index was used to measure the distance between nodes and solve the random selection of the same maximum label. Then introduced the improved density peak clustering algorithm to find community centers and determined the number of communities. Finally, obtained the final community division result based on the label propagation of the community center and peripheral nodes. Experimental results on artificial networks and real networks show that the standardized mutual information, modularity and D-Score index values are superior to the comparison algorithms. The proposed algorithm can effectively discover community structure in complex networks, and has higher robustness. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) have broad application prospects in various industries, and node localization technology is the foundation of WSN applications. Recently, many range-free node localization algorithms have been proposed, but most of them suffer from low accuracy. In order to improve the localization accuracy, in this paper we proposed the node localization algorithm based on multi-hop distance vector and error correction (MDV-EC). In terms of distance estimation, firstly the MDV-EC algorithm calculates the neighbor distance according to node neighbor relationship, then estimates the distance between unknown node and anchor node in multi-hop manner, and finally calibrates the distance refer to distance correction coefficient. In view of similarity of localization errors of nodes in similar regions, an error correction scheme is also investigated, which corrects the node initial estimated locations of nodes refer to the localization error vector of nearby anchor node. Simulation results show that our proposed MDV-EC has better performance than the other two algorithms in terms of node localization accuracy, and the error correction scheme can effectively reduce the localization errors. [ABSTRACT FROM AUTHOR]

One of the popular categories of community detection methods are label propagation-based algorithms. Label propagation-based algorithms use local criteria and have a near-linear time complexity. However, these algorithms have problems such as low accuracy, instability, and high computational time in comparison with other local methods. This article presents a fast and simple label diffusion method (FSLD), using local criteria to discover communities accurately in large-scale networks. In FSLD method, community formation is initially started from a low-degree periphery node and then it diffuses its label from outer to inner side of community in a multi-level way. In next step, using a label updating step, all nodes from high-degree to low-degree have the potential to update and finalize their label to obtain initial communities. The experimental results reveal the higher accuracy and performance of the proposed FSLD algorithm in comparison to other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Considering the 3D propagation characteristics of seismic waves, theoretically, 3D surface-related multiples elimination (3D SRME) can suppress multiples with high accuracy. However, 3D SRME has strict requirements for acquisition geometry, which makes it difficult to be implemented in practice. In the process of 3D SRME, the multiple contribution gather (MCG) is a collection of wavefields with different propagation paths. The accuracy of the multiple propagation paths in the MCGs can be directly characterized by the inclination of the wavefields, which can achieve the weighted superposition of the wavefields. The direct summation of the sparse MCGs in the crossline direction produces serious spatial aliasing, which can easily cause the contamination of primaries. Based on the kinematic characteristics of multiple propagation, MCGs can be considered as a set of hyperbolas with temporal and spatial characteristics. Then, the direct summation of the sparse MCGs can be transformed into a process of superposition along the hyperbolic integration paths. However, as the stable phase points of the events, the apexes of the hyperbola have different spatial distributions in complex geological structures. Such hyperbolic stacking paths are difficult to be controlled by conventional Radon transform or constrained inversion. In this paper, we modify the apex-shifted hyperbolic Radon transform (ASHRT) to implement the summation of crossline MCGs with variable stable phase points along the hyperbolic integration paths. Improved ASHRT uses local similarity to locate the position of stable phase points, which can improve the stability of the algorithm and the efficiency of the computation. The proposed method is demonstrated on a 3D synthetic data set, as well as on a 3D marine data set, effectively avoiding the spatial aliasing caused by sparse crossline MCGs and improving the accuracy of multiple suppression. [ABSTRACT FROM AUTHOR]

In this paper, we proposed methods to accurately predict pixel values by effectively using local similarity, curved surface characteristics, and edge characteristics present in an image. Furthermore, to hide more confidential data in a cover image using the prediction image composed of precisely predicted pixel values, we proposed an effective data hiding technique that applied the prediction image to the conventional reversible data hiding technique. Precise prediction of pixel values greatly increases the frequency at the peak point in the histogram of the difference sequence generated using the cover and prediction images. This considerably increases the amount of confidential data that can be hidden in the cover image. The proposed reversible data hiding algorithm (ARDHA) can hide up to 24.5% more confidential data than the existing algorithm. Moreover, it is not possible to determine the presence of hidden confidential data in stego-images, as they possess excellent visual quality. The confidential data can be extracted from the stego-image without loss, and the original cover image can be restored from the stego-image without distortion. Therefore, the proposed algorithm can be effectively used in digital image watermarking, military, and medical applications. [ABSTRACT FROM AUTHOR]

Community structure detection algorithm is employed in a vast amount of study to partition a network into some loosely coupled sub-networks of smaller scale. It is an effective tool to analyze and control some large-scale networks such as power grids. This paper proposes a novel algorithm based on local similarity to detect the community structure in complex network. Firstly, a new similarity index between nodes is defined to model the topological closeness of local connections in networks. Then nodes sharing high similarity are gathered to form the community structure. The results suggest the emergence of the bridging nodes and kernels within the community detection process. This proposed method performs well when it is introduced to seek out the actual community structure, kernels and bridging nodes in some benchmark networks. Thirdly, the proposed algorithm lends itself to many applications, such as detecting communities in several IEEE standard power grids and investigating the roles of bridging nodes in cascading failures. Experimentally, the proposed algorithm outperforms some other similarity indices and clustering methods. Finally, a detailed comparison helps us get the conclusion that the traditional label propagation algorithm is a special case of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Local similarity computation between two sequences permits detecting all the relevant alignments present between subsequences thereof. A well-known dynamic programming algorithm works in time O(mn), m and n being the lengths of the subsequences. The algorithm is rather slow when applied over many sequence pairs. In this paper we present the first bit-parallel computation of the score matrix, for a simplified choice of scores. If the computer word has w bits, then the resulting algorithm works in O(mn log min(m, n, w)/w) time, achieving up to 8-fold speedups in practice. Some DNA comparison applications use precisely the simplified scores we handle, and thus our algorithm is directly applicable. In others, our method could be used as a raw filter to discard most of the strings, so the classical algorithm can be focused only on the substring pairs that can yield relevant results. [ABSTRACT FROM AUTHOR]

• A novel fast and accurate Spark-based parallel community detection algorithm is proposed. • The proposed PLDLS algorithm uses label diffusion of core nodes along with a new label selection method. • Multi-factor criteria for computing nodes importance is used to select core nodes. • A fast and parallel merge phase is utilized to obtain more dense and accurate communities. • The result of PLDLS completely is robust, stable and scalable in comparison with other examined methods. Parallel and distributed community detection in large-scale complex networks, such as social networks, is a challenging task. Parallel and distributed algorithm with high accuracy and low computational complexity is one of the essential issues in the community detection field. In this paper, we propose a novel fast, and accurate Spark-based parallel label diffusion and label selection-based (PLDLS) community detection algorithm with two-step of label diffusion of core nodes along with a new label selection (propagation) method. We have used multi-factor criteria for computing node's importance and adopted a new method for selecting core nodes. In the first phase, utilizing the fact that nodes forming triangles, tend to be in the same community, parallel label diffusion of core nodes is performed to diffuse labels up to two levels. In the second phase, through an iterative and parallel process, the most appropriate labels are assigned to the remaining nodes. PLDLS proposes an improved robust version of LPA by putting aside randomness parameter tuning. Furthermore, we utilize a fast and parallel merge phase to get even more dense and accurate communities. Conducted experiments on real-world and artificial networks, indicates the better accuracy and low execution time of PLDLS in comparison with other examined methods. [ABSTRACT FROM AUTHOR]