Graph convolutional networks (GCNs) have been widely studied to address graph data representation and learning. In contrast to traditional convolutional neural networks (CNNs) that employ many various (spatial) convolution filters to obtain rich feature descriptors to encode complex patterns of image data, GCNs, however, are defined on the input observed graph G(X,A) and usually adopt the single fixed spatial convolution filter for graph data feature extraction. This limits the capacity of the existing GCNs to encode the complex patterns of graph data. To overcome this issue, inspired by depthwise separable convolution and DropEdge operation, we first propose to generate various graph convolution filters by randomly dropping out some edges from the input graph A . Then, we propose a novel graph-dropping convolution layer (GDCLayer) to produce rich feature descriptors for graph data. Using GDCLayer, we finally design a new end-to-end network architecture, that is, a graph-dropping convolutional network (GDCNet), for graph data learning. Experiments on several datasets demonstrate the effectiveness of the proposed GDCNet.

Recently, Graph Neural Networks (GNNs) have made remarkable achievements in semi-supervised classification tasks. Nevertheless, GNNs usually rely on a specific graph convolution which has high computational complexity. To overcome this issue, recent works attempt to implicitly use adjacency matrix to guide message propagation in multi-layer perception (MLP) via neighboring contrastive loss. However, existing works accomplish implicit message passing only, without considering multi-order graph topology information. In this paper, we propose a novel method called Multiple Layer Graph Regularized Perception (MLGP). The main advantage of MLGP is to incorporate multi-order neighboring information into MLP. Further, inspired by gated mechanism, we design a linear gating to capture important features of nodes. More discriminant features can be obtained to alleviate over-smoothing. MLGP is more effective and more robust than existing works when dealing with large-scale graph data and noisy adjacency information. The comparative experiment results show that our model achieves better performance and strong robustness.

this study aims at identifying potential industry-University-research institution collaborations partners (IURC) efficaciously and analyzes the conditions and dynamics in the IURC process, based on knowledge potential and the knowledge spillover theory. Furthermore, a new identification method is constructed that takes into account the law of scientific research cooperation and economic factors. The method utilizes multisource data, combining bibliometric and econometrics analyses to achieve the network core of the existing collaboration network, and institution competitiveness in the innovation chain. Empirical analysis of the genetic engineering vaccine field shows that throughout the distribution characteristics of creative technologies from different institutions, the analysis based on the innovation chain can identify more complementarities between institutions. Compared to previous studies, this study emulates the real conditions of IURC. The rule of technological innovation can be better revealed, potential partners of IURC can be more easily identified, and the conclusion has a higher value in consultation. In particular, diverse informative indices can assist researchers in deriving appropriate partners for research and development cooperation.

Cryptography may mitigate the privacy problem in biometric recognition systems. However, cryptography technologies lack error-tolerance and biometric samples cannot be reproduced exactly, rising the robustness problem. The biometric template protection system needs a good feature extraction algorithm to be a good classifier. But, an even effective feature extractor can give a very low-quality biometric channel (i.e. high Bit Error Rate (BER)). Using the Spectral Minutiae method to identify fingerprints is one of the examples, which gives a BER of 40 ~ 50% to most of the matching channels. Therefore, we propose a concatenated coding scheme based on erasure codes to achieve a robust and secure biometric recognition system. The key idea is to transmit more packets than needed for decoding and allow the erasure-encoded packet suffering high BER to be discarded. The erasure decoder can reconstruct the secret key by collecting enough surviving packets. By applying the spectral minutiae method in the FVC2000-DB2 fingerprint database, the unprotected system achieves an EER of 3.7% and our proposed coding scheme reaches an EER of 4.6% with a 798-bit secret key.

Spectral Minutiae (SM) representation enables the combination of minutiae-based fingerprint recognition systems with template protection schemes based on fuzzy commitment, but it requires error-correcting codes that can handle high bit error rates (i.e. above 40%). In this paper, we propose a 3-Layer coding scheme based on erasure codes for the SM-based biometric recognition system. Our approach is inspired by the fact that the Packet Error Rate (PER) is proportional to the Bit Error Rate (BER). Each packet is encoded by an Error Detection Code (EDC) and an Error Correction Code (ECC). The packet can only survive if it successfully passes the ECC and EDC decoder. With the erasure code, the system can reconstruct the secret key by only using the survived packets. By applying SM to the FVC2000-DB2 fingerprint database, the unprotected system achieves an EER of around 6% while our proposed coding scheme reaches an EER of approximately 6.5% with a 1032-bit secret key.

Similar to biometric fingerprint recognition, characteristic minutiae points - here end - and branch points - can be extracted from skeletonized veins to distinguish individuals. An approach to extract those vein minutiae and to transform them into a fixed-length, translation and scale in variant representation where rotations can be easily compensated is presented in this paper. The proposed solution based on spectral minutiae is evaluated against other comparison strategies on three different datasets of wrist and palm vein samples. It shows a competitive biometric performance while producing features that are compatible with state-of-the-art template protection systems.

A fixed-length binary representation of a fingerprint has the advantages of a fast operation and a small template storage. For many biometric template protection schemes, a binary string is also required as input. The spectral minutiae representation is a method to represent a minutiae set as a fixed-length real-valued feature vector. In order to be able to apply the spectral minutiae representation with a template protection scheme, we introduce two novel methods to quantize the spectral minutiae features into binary strings: Spectral Bits and Phase Bits. The experiments on the FVC2002 database show that the binary representations can even outperformed the spectral minutiae real-valued features.

Prepulse inhibition (PPI) refers to the reduction in startle reaction towards a startle-eliciting “pulse” stimulus when it is shortly preceded by a sub-threshold “prepulse” stimulus. PPI deficits have been seen in patients with schizophrenia and animal models of this mental disorder. The goal of this study was to provide an alternative method for the analysis of PPI data. The new method is expected to be more reliable and sensitive than the existing conventional method. We applied the Kernel density estimation (KDE) in the analysis of PPI data. KDE is a non-parametric method of estimating the probability density function of a random variable and is widely used in inferring population statistics based on limited, noisy samples of continuous random variables. Our results showed that the KDE method performed better than the conventional method and offered some advantages which are of significant in the post-session analysis of PPI data and in performing animal experiments.

Most fingerprint recognition systems are based on the use of a minutiae set, which is an unordered collection of minutiae locations and orientations suffering from various deformations such as translation, rotation, and scaling. The spectral minutiae representation introduced in this paper is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require a fixed-length feature vector. This paper introduces the concept of algorithms for two representation methods: the location-based spectral minutiae representation and the orientation-based spectral minutiae representation. Both algorithms are evaluated using two correlation-based spectral minutiae matching algorithms. We present the performance of our algorithms on three fingerprint databases. We also show how the performance can be improved by using a fusion scheme and singular points.