Recently, the Contrastive Language Image Pre-training (CLIP) model has shown significant generalizability by optimizing the distance between visual and text features. The mainstream CLIP-based action recognition methods mitigate the low “zero-shot” generalization of the 1-of-N paradigm but also lead to a significant degradation in supervised performance. Therefore, powerful supervision and competitive “zero-shot” need to be effectively traded off. In this work, a Multimodal Independent Prompt CLIP (MIP-CLIP) model is proposed to address this challenge. On the visual side, we propose novel Video Motion Prompt (VMP) to empower the visual encoder with motion perception, which performs short- and long-term motion modelling via temporal difference operation. Next, the visual classification branch is introduced to improve the discrimination of visual features. Specifically, the temporal difference and visual classification operations of the 1-of-N paradigm are extended to CLIP to satisfy the need for strong supervised performance. On the text side, we design Class-Agnostic text prompt Template (CAT) under the constraint of Semantic Alignment (SA) module to solve the label semantic dependency problem. Finally, a Dual-branch Feature Reconstruction (DFR) module is proposed to complete cross-modal interactions for better feature matching, which uses the class confidence of the visual classification branch as input. The experiments are conducted on four widely used benchmarks (HMDB-51, UCF-101, Jester, and Kinetics-400). The results demonstrate that our method achieves excellent supervised performance while preserving competitive generalizability.

The ever-increasing demands for intuitive interactions in virtual reality have led to surging interests in facial expression recognition (FER). There are however several issues commonly seen in existing methods, including narrow receptive fields and homogenous supervisory signals. To address these issues, we propose in this paper a novel multimodal supervision-steering transformer for facial expression recognition in the wild, referred to as FER-former. Specifically, to address the limitation of narrow receptive fields, a hybrid feature extraction pipeline is designed by cascading both prevailing CNNs and transformers. To deal with the issue of homogenous supervisory signals, a heterogeneous domain-steering supervision module is proposed to incorporate text-space semantic correlations to enhance image features, based on the similarity between image and text features. Additionally, a FER-specific transformer encoder is introduced to characterize conventional one-hot label-focusing and CLIP-based text-oriented tokens in parallel for final classification. Based on the collaboration of multifarious token heads, global receptive fields with multimodal semantic cues are captured, delivering superb learning capability. Extensive experiments on popular benchmarks demonstrate the superiority of the proposed FER-former over the existing state-of-the-art methods.

Accurately predicting protein-peptide binding residues is paramount in elucidating protein functions, unraveling disease mechanisms, and advancing drug discovery. Most existing methods for predicting protein-peptide binding residues are either highly reliant on protein structural data or lack effective ways to extract valuable information from protein sequences. Furthermore, the issue of data imbalance significantly constrains the predictive performance of these methods. To address the above problems, we propose a PepPCR model based on the pre-trained protein language model ProtT5 and progressive contrastive representation learning. Specifically, the pre-trained model ProtT5 can automatically extract high-dimensional feature representations relevant to protein functions from protein sequences, while the progressive contrastive representation learning can optimize the feature representations learned by the ProtT5 model within imbalanced data. Experimental results show that the classification performance of the PepPCR model surpasses the existing state-of-the-art methods. In particular, compared with the sequence-based state-of-the-art method PepBCL, PepPCR improves Recall, AUC, and Matthews Correlation Coefficient (MCC) by 60.3%, 7.2%, and 7.5% respectively on the test set TE125, and improves Recall, AUC, and MCC by 60.3%, 4.6%, and 15.4% respectively on the test set TE639.

Cryo-Electron Microscopy (cryo-EM) is a widely used and effective method for determining the three-dimensional (3D) structure of biological molecules. For ab-initio Cryo-EM 3D reconstruction using single particle analysis (SPA), estimating the projection direction of the projection image is a crucial step. However, the existing SPA methods based on common lines are sensitive to noise. The error in common line detection will lead to a poor estimation of the projection directions and thus may greatly affect the final reconstruction results. To improve the reconstruction results, multiple candidate common lines are estimated for each pair of projection images. The key problem then becomes a combination optimization problem of selecting consistent common lines from multiple candidates. To solve the problem efficiently, a physics-inspired method based on a kinetic model is proposed in this work. More specifically, hypothetical attractive forces between each pair of candidate common lines are used to calculate a hypothetical torque exerted on each projection image in the 3D reconstruction space, and the rotation under the hypothetical torque is used to optimize the projection direction estimation of the projection image. This way, the consistent common lines along with the projection directions can be found directly without enumeration of all the combinations of the multiple candidate common lines. Compared with the traditional methods, the proposed method is shown to be able to produce more accurate 3D reconstruction results from high noise projection images. Besides the practical value, the proposed method also serves as a good reference for solving similar combinatorial optimization problems.

Three-dimensional (3D) reconstruction in single-particle cryo-electron microscopy (cryo-EM) is a critical technique for recovering and studying the fine 3D structure of proteins and other biological macromolecules, where the primary issue is to determine the orientations of projection images with high levels of noise. This paper proposes a method to determine the orientations of cryo-EM projection images using reliable common lines and spherical embeddings. First, the reliability of common lines between projection images is evaluated using a weighted voting algorithm based on an iterative improvement technique and binarized weighting. Then, the reliable common lines are used to calculate the normal vectors and local -axis vectors of projection images after two spherical embeddings. Finally, the orientations of projection images are determined by aligning the results of the two spherical embeddings using an orthogonal constraint. Experimental results on both synthetic and real cryo-EM projection image datasets demonstrate that the proposed method can achieve higher accuracy in estimating the orientations of projection images and higher resolution in reconstructing preliminary 3D structures than some common line-based methods, indicating that the proposed method is effective in single-particle cryo-EM 3D reconstruction.

Few-shot semantic segmentation (FSS) aims to segment novel classes with only a few annotated samples. Existing methods to FSS generally combine the annotated mask and the corresponding support image to generate the class-specific representation, and perform the segmentation for the query image by matching the features of the query image to these representations. However, the segmentation performance could be fragile for the lack of an effective method to handle the inappropriate use of query features and the neglection of correlation between features in support and query images. In this work, we propose a novel Disentanglement and Recombination Network (DRNet) to alleviate this problem. Concretely, we first apply the self-attention on both support foreground features and query foreground features. Then, the foreground features of the support and query branches are recombined using the cross-attention after self-attention computation, which can encourage the foreground feature alignment between branches. Finally, the prototypes are generated from the recombined foreground features and support background features, and are utilized to guide the segmentation for given images. Considering the sensitivity of prototypes related to the subtle differences among objects from different classes and the same class, we further introduce a joint learning strategy to derive accurate segmentation of both seen and unseen objects in the support image and the query image respectively. Extensive experiments on the PASCAL-5iand COCO-20idatasets demonstrate the superiority of our DRNet comparing with the recent popular methods. The code is released on https://github.com/GS-Chang-Hn/DRNet-fss.

Compared to cross-entropy in deep learning, triplet loss is less affected by the biased label information and widely used in fine-grained visual tasks. Especially in person re-identification (re-ID), triplet loss is improved with batch-hard sampling which only selects the hardest samples during the training process to reduce invalid triplets involved in the loss computation. The hardest samples’ loss computation can provide a more intense gradient descent than raw samples. However, the batch-hard triplet loss discards multiple samples with important information, which can negatively impact feature learning. Besides, the hardest samples cause loss stuck problems frequently in training. In this work, we propose a balanced triplet loss for comprehensive feature learning and stable model convergence. The balanced triplet loss only mines the hardest negative samples of each category within a mini-batch. Compared with batch-hard triplet loss, it preserves the features of all the negative categories rather than one negative category with the hardest negative sample. It achieves a balance between triplet selection and information loss. The experiments show that our method can produce competitive results in re-ID tasks. In addition, we analyze the correlation between the intensity of data mining and the granularity of feature learning and further adapt the balanced triplet loss to general fine-grained image classification. The experiments prove the adapted balanced triplet loss also outperforms cross-entropy in multiple datasets of different scales.

Cybersecurity jobs are in demand around the country in response to the rapidly growing number of cyberattacks on businesses and government entities. While there is some consensus on core technical skills needed to fill these positions, many hiring employers are not aware of or deemphasize the importance of soft skills in these positions. Using a semantic network analysis of job advertisements, this study sought to answer two research questions: what are the most critical soft skills cybersecurity employers seek? And how are the soft skills related to the hard skills based on industry expectations? This study reports the analysis of 17,929 cybersecurity job advertisements. Our results found that three categories of soft skills emerged: Knowledge management and systems, big data analytical skills, and teamwork and diversity are all highly sought after. In addition, our study findings reinforce a critical role information system is playing in cyber security.

Heterogeneous three-dimensional (3D) reconstruction in single-particle cryo-electron microscopy (cryo-EM) is a significant but very challenging technique for recovering conformational heterogeneity of proteins or other biological macromolecules and their complexes in different functional states. Heterogeneous projection image classification is an effective way for solving the heterogeneity problem in single-particle cryo-EM. Most existing heterogeneous projection image classification methods are based on supervised learning or require a large amount of a priori knowledge, such as the common lines or orientations of the projection images, which has many limitations in practical applications. In this paper, we propose an unsupervised heterogeneous cryo-EM projection image classification algorithm based on autoencoders that only needs to know the number of heterogeneous conformations in the dataset and does not require any labeling information of the projection images as well as other prior knowledge. We implement a simple autoencoder with a multi-layer perceptron that is trained in iterative mode and a complex autoencoder with a residual network that is trained in one-pass learning mode to convert heterogeneous projection images into latent variables. The extracted high-dimensional features are reduced to two dimensions by the uniform manifold approximate and projection dimensionality reduction algorithm and then cluster them using the spectral clustering algorithm. The proposed algorithm is applied to two heterogeneous cryo-EM datasets to demonstrate its classification performance. Experimental results show that the proposed algorithm can effectively extract category features of heterogeneous projection images and can classify them with high accuracy.

Single-particle cryo-electron microscopy (cryo-EM) has become one of the mainstream technologies in the field of structural biology to determine the three-dimensional (3D) structures of biological macromolecules. Heterogeneous cryo-EM projection image classification is an effective way to discover conformational heterogeneity of biological macromolecules in different functional states. However, due to the low signal-to-noise ratio of the projection images, the classification of heterogeneous cryo-EM projection images is a very challenging task. In this paper, two novel distance measures between projection images integrating the reliability of common lines, pixel intensity and class averages are designed, and then a two-stage spectral clustering algorithm based on the two distance measures is proposed for heterogeneous cryo-EM projection image classification. In the first stage, the novel distance measure integrating common lines and pixel intensities of projection images is used to obtain preliminary classification results through spectral clustering. In the second stage, another novel distance measure integrating the first novel distance measure and class averages generated from each group of projection images is used to obtain the final classification results through spectral clustering. The proposed two-stage spectral clustering algorithm is applied on a simulated and a real cryo-EM dataset for heterogeneous reconstruction. Results show that the two novel distance measures can be used to improve the classification performance of spectral clustering, and using the proposed two-stage spectral clustering algorithm can achieve higher classification and reconstruction accuracy than using RELION and XMIPP.

Reconstruction of heterogeneous cryo-electron microscopy (cryo-EM) structures is a very challenging task for discovering conformational heterogeneity of biological macro-molecules and their complexes in different functional states, where heterogeneous projection image classification is a key technology. In this paper, three heterogeneous projection image classification algorithms based on the similarity and reliability of common lines are proposed, in which the reliability of common lines is calculated according to two voting algorithms. The similarity and reliability of common lines are converted into adjacency matrices using a k-nearest neighbor algorithm and a shared nearest neighbor algorithm. The adjacency matrices are used as the input of a normalized spectral clustering algorithm to perform the classification of heterogeneous projection images. The proposed algorithms are applied to two heterogeneous cryo-EM datasets to demonstrate their classification performance. Experimental results show that the proposed algorithms can achieve higher classification accuracy in comparison with R ELION and XMIPP, indicating that they are effective in the 3D reconstruction of heterogeneous cryo-EM structures.

Clustering analysis is a data analysis technology, which divides data objects into different clusters according to the similarity between them. The density-based clustering methods can identify clusters with arbitrary shapes, but its time complexity can be very high with the increasing of the number and the dimension of the data points. The grid-based clustering methods are usually used to deal with the problem. However, the performance of these grid-based methods is often affected by the identification of the cluster center and boundary based on global thresholds. Therefore, in this paper, an adaptive grid-based clustering method is proposed, in which the definition of cluster center nodes and boundary nodes is based on relative density values between data points, without using a global threshold. First, the new definitions of the cluster center nodes and boundary nodes are given, and then the clustering results are obtained by an initial clustering process and a merging process of the ordered grid nodes according to the density values. Experiments on several synthetic and real-world datasets show the superiority of the proposed method. © 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

Correlation filter based tracking algorithms have shown favourable performance in recent years. Nonetheless, the fixed feature selection and potential model drift limit their effectiveness. In this paper, we propose a novel adaptive feature selection based tracking method which keeps the strong discriminating ability of the correlation filter. The proposed method can automatically select either the HOG feature or color feature for tracking based on the confidence scores of the features in each frame. Firstly, the response map of the color features and the HOG features are extracted respectively using correlation filter. The Lab color space is used to extract the color features which separate the luminance from the color. Secondly, the confidence region and the possible location of the target are estimated using the average peak-to-correlation energy. Thirdly, three criteria are used to select the proper feature for the current frame to perform tracking adaptively. The experimental results demonstrate that the proposed tracker performs superiorly comparing with several state-of-the-art algorithms on the OTB benchmark datasets. © 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

Simultaneous feature selection and clustering is a major challenge in unsupervised learning. In particular, there has been significant research into saliency measures for features that result in good clustering. However, as datasets become larger and more complex, there is a need to adopt a finer-grained approach to saliency by measuring it in relation to a part of a model. Another issue is learning the feature saliency and advanced model parameters. We address the first by presenting a novel Gaussian mixture model, which explicitly models the dependency of individual mixture components on each feature giving a new component-based feature saliency measure. For the second, we use Markov Chain Monte Carlo sampling to estimate the model and hidden variables. Using a synthetic dataset, we demonstrate the superiority of our approach, in terms of clustering accuracy and model parameter estimation, over an approach using a model-based feature saliency with expectation maximisation. We performed an evaluation of our approach with six synthetic trajectory datasets obtaining an average clustering accuracy of 97 percent. To demonstrate the generality of our approach, we applied it to a network traffic flow dataset obtaining an accuracy of 93 percent for intrusion detection. Finally, we performed a comparison with state-of-the-art clustering techniques using three real-world trajectory datasets of vehicle traffic. Our approach achieved an average clustering accuracy of 96 percent compared to 77-95 percent for the other techniques. In conclusion, for the datasets considered, component based feature saliency measures gave improved clustering over those based on whole models.

The single-particle reconstruction of cryo-electron microscopy is an important technique to recover the three-dimensional structure of biological macromolecules from their two-dimensional noisy projection images taken from unknown random directions. Angular reconstruction is a basic algorithm for reference free ab-initio estimation of the initial three-dimensional structure of molecules, in which the relative orientation of the particle is uniquely determined from the common lines among three projection images. However, it is difficult to detect reliable common lines due to the low signal-to-noise ratio of the projection images. In this paper, a weighted voting algorithm is proposed to detect the reliable common lines, in which the iterative improvement technique is employed. The reliability of each common line is estimated by the consistency between the voted angle and projection angle computed using the common line during the iteration. Finally, the reliable common line pairs are retained, and the spurious ones are eliminated through the binary weight correction and iterative improvement. The proposed algorithm is successfully applied to the reconstruction of the Escherichia coli 50S ribosomal subunit. Experimental results show that the proposed algorithm can improve the estimation accuracy from noisy projection images.

Recently, sparse representation has attracted increasing interest in computer vision. Sparse representation based methods, such as sparse representation classification (SRC), have produced promising results in face recognition, while the dictionary used for sparse representation plays a key role in it. How to improve the dictionary construction in sparse representation is still an open question. Principal component analysis network (PCANet), as a newly proposed deep learning method, has the advantage of simple network architecture and competitive performance for feature learning. In this paper, we have studied how to use the PCANet to improve the dictionary construction in sparse representation, and proposed a new method for face recognition. The PCANet is used to learn new features from face images, and the learned features are used as dictionary atoms to code the query face images, and then the reconstruction errors after sparse coding are used to classify the face images. It is shown that the proposed method can achieve better performance than the other five state-of-art methods for face recognition.

In this paper, a novel information hiding method is proposed to embed data in the Word documents that use OOXML format. The 2007 version and more recent versions of MS Word are all based on the OOXML format. The main document body of OOXML document consists of the text elements that correspond to the content of the document. It is found that, in the OOXML format, the printable text in an element can be “split” by separating the element into multiple elements. The digital code of the information determines if the adjacent characters in the text will be “split” or not, so as to achieve the purpose of information hiding. Since the format and all the other properties of the text in the OOXML format document is unchanged after the embedding, the embedded information is imperceptible. The code of the information is embedded circularly to enhance robustness. Experiments show that the proposed method can deal with many kinds of attacks, including “content”, “save as”, “copy” and part of “format”. The proposed method can be used in information security and copyright protection for OOXML format documents.

A robust text watermarking approach has been proposed in this paper, in which the watermarks are embedded into the text by the transformation of characters' RGB-style color in the OOXML format document. To get high watermark embedding capacity, two bits of the watermarking information are embedded between every two characters. The initial text content of the document is not changed after the embedding because of the good characteristics of OOXML format and the subtle adjustment of characters' color, which ensure the good imperceptibility of the watermarking method. Most attacks such as “copy”, “save as”, “insert” and “delete” operations can be resisted by the proposed approach, and the location of the “insert” and “delete” operations can be detected by redundant embedding of the watermarking information. The proposed approach can be applied to files in “docx” and “doc” format.

Clustering is an important unsupervised machine learning method which has played an important role in various fields. Density-based clustering methods are capable of dealing with clusters of different sizes and shapes. As suggested by Alex Rodriguez et al. in a paper published in Science in 2014, the 2D decision graph of the estimated density value versus the minimum distance from the points with higher density values for all the data points can be used to identify the cluster centroids. However, there lack automatic methods for the determination of the cluster centroids from the decision graph. In this work, a novel statistic-based method is designed to identify the cluster centroids automatically from the decision graph. So the number of clusters is also automatically determined. Experiments on several synthetic and real-world datasets show the superiority of the proposed method in centroid identification from the datasets with various distributions and dimensionalities. Furthermore, it is also shown that the proposed method can be effectively applied to image segmentation. Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

OSEK/VDX, a standard of automobile OS, has been widely adopted by many manufacturers to design and implement a vehicle-mounted OS. Currently, with increasing functionalities in vehicles, more and more complex applications are developed based on the OSEK/VDX OS. However, how to ensure the reliability of developed applications is becoming a challenge for developers. Based on our previous work, in this paper we present an efficient approach to verify the developed OSEK/VDX applications. In the presented approach, SMT-based bounded model checking technique is used to carry out verification in order to handle complex applications. Moreover, a series of optimization strategies are proposed and employed to improve the checking capability of our approach. We have implemented a tool according to the proposed approach and conducted many experiments. The experiment results show that our approach is capable of checking the safety property of large-scale OSEK/VDX applications. We also compared our approach with existing checking method, the comparison results indicate that our approach is an efficient and powerful technique in verifying OSEK/VDX applications.

Protein structure alignment plays an important role in the study of bioinformatics. Many protein structure alignment methods have been proposed. However, most of them are sequential alignment methods which are not able to detect non-sequential similarities between proteins. Although some non-sequential protein structure alignment methods have been proposed recently, their results are still not satisfactory. In this work, a new non-sequential protein structure alignment method based on Aligned Fragment Pairs (AFPs) and the maximal clique is proposed. Different from other methods, our method is based on variable length AFPs which can better represent the local structure similarities and can also greatly speed up the computations. Moreover, the spatial information of the AFPs is used to select “good” AFPs. Then, a graph is built to represent the relationship between all the “good” AFPs. If two AFPs can be aligned at the same time, an edge is added to the graph. A high quality maximal clique of the graph is found to produce the initial alignment. Finally, a greedy-like refinement algorithm is executed to get the final alignment. The experiments show that, compared with seven non-sequential methods, except DEDAL which is a non-rigid body method, and MICAN which uses secondary structure information, the proposed method usually produces more correctly aligned residue pairs than the other non-sequential alignment methods.

Protein structure prediction is one of the most important subjects in computational structural biology. In the process of protein structure prediction, many structure decoys are obtained. It has remained an unsolved and challenging problem to select the best model from the structure decoys that are closest to the native structure. One of the important methods for selecting the near-native structure is by clustering the structure decoys. The traditional methods simply use clustering methods which are usually not appropriate in the high dimensional conformation space. Here we propose a method based on maximal cliques in graph theory to solve this problem. The similarities between the decoys are first computed using TM-score, and a graph is built using the shared nearest neighbor (SNN) information among the decoys. Then the maximal cliques of the graph are found and the centroids of these maximal cliques are selected as near-native structures. The experiments show that, compared to the traditional methods, the proposed method can select better near-native structures which have higher similarities with the native structures.

Dimension reduction has become an important tool for dealing with high dimensional data. Locally linear embedding (LLE) is a nonlinear dimension reduction method which can preserve local configurations of nearest neighbors. However, finding the nearest neighbors requires the definition of a distance measure, which is a critical step in LLE. In this paper, the Rank-order distance measure is used to substitute the traditional Euclidean distance measure in order to find better nearest neighbor candidates for preserving local configurations of the manifolds. The Rank-order distance between the data points is calculated using their neighbors' ranking orders, and is shown to be able to improve the clustering of high dimensional data. The proposed method is called Rank-order based LLE (RLLE). The RLLE method is evaluated by comparing with the original LLE, ISO-LLE and IED-LLE on two handwritten datasets. It is shown that the effectiveness of a distance measure in the LLE method is closely related to whether it can be used to find good nearest neighbors. The experimental results show that the proposed RLLE method can improve the process of dimension reduction effectively, and C-index is another good candidate for evaluating the dimension reduction results. © Copyright 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.

With the growing number of known protein 3D structures, how to efficiently compare protein structures becomes an important and challenging problem in computational structural biology. So, many protein structure alignment methods have been developed in recent years. Flexible structure alignment methods are shown to be superior to rigid structure alignment methods in identifying the structure similarities between proteins which have gone through conformational changes. It is also found that the methods based on Aligned Fragment Pairs (AFP) own special advantages in balancing global structure similarities and local structure similarities. In this work, we propose a new flexible protein 3D structure alignment method based on variable-length AFPs. Different from other methods, our method owns three special features: firstly, it uses a new AFP identification algorithm based on a local coordinate system; secondly, it allows different AFPs separated by other AFPs to share the same transformation during the concatenation; thirdly, it allows different AFPs to have different lengths, which can not only reduce the total number of AFPs, and also can improve the representation of the local structure similarities. The experiments show that, compared to three other flexible structure alignment methods, FlexProt, FATCAT and FlexSnap, the proposed method can achieve similar or better results by introducing fewer twists and in much less running time due to the reduced number of AFPs.

In today’s race walking competition, the determination of whether an athlete fouls is mainly affected by a referee’s subjective judgment, leading to a high possibility of misjudgment. The purpose of this work is to determine whether race walking can be automatically recognized by accelerometers embedded in smartphones. In this work, acceleration data are collected by a smartphone app developed by ourselves. Nineteen features are extracted from the raw sensor data, and are used by an unsupervised classification method for activity recognition, named MCODE. We evaluate various data sampling rates and window lengths during feature extraction in the experiments. We also compare our method with other well-known methods on the metrics such as sensitivity, specificity and adjusted rank index. The results show that our method is viable to recognize race walking using smartphone accelerometers.

A new similarity measure for hierarchical clustering is proposed. The idea is to treat all the data points as mass points under a hypothetical gravitational force field, and derive the hierarchical clustering results by estimating the travel time between data points. The shorter the time needed to travel from one point to another, the more similar the two data points are. In order to avoid the complexity in the simulation using molecular dynamics, the potential field produced by all the data points is computed. Then the travel time between a pair of data points is estimated using the potential field. In our method, the travel time is used to construct a new similarity measure, and an edge-weighted tree of all the data points is built to improve the efficiency of the hierarchical clustering. The proposed method called Travel-Time based Hierarchical Clustering (TTHC) is evaluated by comparing with four other hierarchical clustering methods. Two real datasets and two synthetic dataset families composed of 200 randomly produced datasets are used in our Experiments. It is shown that the TTHC method can produce very competitive results, and using the estimated travel time instead of the distance between data points is capable of improving the robustness and the quality of clustering.