Self-adaptive Clustering Research Articles

A Semisupervised Approach for Industrial Anomaly Detection via Self-Adaptive Clustering

With the rapid development of the Industrial Internet of Things (IIoT), log-based anomaly detection has become vital for smart industrial construction that has prompted many researchers to contribute. To detect anomalies based on log data, semi-supervised approaches stand out from supervised and unsupervised approaches because they only require a portion of labeled data and are relatively stable. However, the state-of-the-art semi-supervised approaches still suffer from two main problems: manual parameter setting and unsatisfactory performance with high false positives. We propose AdaLog, an integrated semi-supervised approach based on self-adaptive clustering, for industrial anomaly detection. In particular, the clustering step performs automatic label probability estimation by distinguishing twelve situations so that the label probability of each unlabeled data can be carefully calculated, leading to high accuracy. In addition, AdaLog employs a pre-trained model to learn contextual information comprehensively and a transformer-based model to detect anomalies efficiently. To alleviate class imbalance, an undersampling method is incorporated. The results on three popular datasets demonstrate that AdaLog significantly outperforms three state-of-the-art semi-supervised approaches by 17.8%–2,489.8% on average in terms of F1-score, and is even superior to two supervised approaches in most cases with average improvements of 10.9%–23.8%.

SIRN: An iterative reasoning network for transmission lines based on scene prior knowledge

High-accuracy positioning and identification of transmission line components is the premise for their status detection and fault diagnosis. However, due to the limitations of imbalance object scale and distribution in aerial images, the problem of detecting dense-tiny objects still needs to be solved. Considering the prior knowledge of fixed connection scenes, we proposed a novel method named scene iterative reasoning network (SIRN) based on self-adaptive clustering and local scene knowledge. It consists of the coarse-grained detector (CGD), scene self-adaptive clustering (SSAC) subnetwork, and scene structure iterative reasoning (SSIR) subnetwork. The CGD was proposed to obtain global coarse detection results. Then, the SSAC subnetwork utilized unsupervised self-adaptive clustering to obtain accurate dense regions based on the CGD results. Finally, the SSIR subnetwork was designed to extract and fuse the scene semantic structure information of local regions for realizing accurate dense-tiny object detection. In summary, the SIRN model utilizes an iterative inference strategy to detect dense regions accurately. By leveraging scene structure information, the model effectively transforms the challenge of detecting dense objects into an advantage, resulting in precise detection. The SIRN model is compatible with single-stage and two-stage object detection models, achieving a notable mean average precision (mAP) improvement ranging from 4.4% to 12.2% compared to the baseline models. Compared to other state-of-the-art object detection models, SIRN demonstrates significant advantages in accuracy and error rate metrics. In addition, qualitative and quantitative experiments show that the SIRN model considerably enhanced the detection of dense-tiny objects. The code is available at https://github.com/CharmingWang/SIRN.

Hierarchical Graph Pooling With Self-Adaptive Cluster Aggregation

Graph neural network (GNN) introduces deep neural networks into graph structure data. It has achieved advanced performance in many fields, such as traffic prediction, recommendation systems, and computer vision, which has received extensive attention from the academic community. Most of the existing research on GNNs focuses on graph convolution, while graph pooling is usually ignored. Although there are also some graph pooling methods, most of the current pooling methods are based on top-k node selection. In the top-k-based pooling method, unselected nodes will be directly discarded, which will cause the loss of feature information during the pooling process. In this article, we propose a novel graph pooling operator, called hierarchical graph pooling with self-adaptive cluster aggregation (HGP-SACA), which uses a sparse and differentiable method to capture the graph structure. Before using top-k for cluster selection, the unselected clusters and the selected clusters in the neighbor perform an n-hop feature information aggregation. The merged clusters which contain neighborhood clusters are used for top-k selection, which can enhance the function of the unselected clusters. Through extensive theoretical analysis and experimental verification on multiple data sets, our experimental results show that combining the existing GNN architecture with HGP-SACA can achieve state-of-the-art results on multiple graph classification benchmarks, which proves the effectiveness of our proposed model.

Research on self-adaptive clustering algorithms for large data sparse networks based on information entropy

With the advent of the era of artificial intelligence and information technology, a large number of data and information pour into all walks of life. These data packages include many online and offline data such as text files, audio and video. However, so many data are unnecessary in real life. The application of data clustering algorithm based on artificial intelligence technology can solve such problems very well. However, the traditional clustering algorithm relies too much on manual operation when choosing clustering centers, which greatly reduces the efficiency of the whole algorithm. At the same time, the traditional clustering algorithm based on sparse network has too many coefficients in its coefficient matrix design, so it can not aggregate the relevant data well. This paper will measure the correlation of related data based on information entropy, and innovatively improve the existing sparse data network model. A model training algorithm based on multi-strategy pattern optimization is proposed to realize the automatic selection of clustering centers and reduce the training time of the algorithm. In terms of data clustering correlation, this paper proposes an optimized adaptive clustering algorithm based on the joint model of sparse subspace clustering algorithm model and the norm of adaptive subspace segmentation. In the experimental part, this paper compares the proposed algorithm with the traditional density peak clustering algorithm. The experimental results show that the proposed algorithm has obvious advantages in text data collection and classification, image data collection and filtering.

A two-stage framework for automated operational modal identification

Automated operational modal analysis (OMA) is attractive and has been extensively used to replace traditional OMA, which requires much empirical observation and engineers’ judgment. Still, the uncertainties on modal parameters and spurious modes are challenging to estimate under the field conditions. For addressing this challenge, this research proposed an automated modal identification approach. The proposed approach consists of two steps: (1) modal analysis using covariance-driven stochastic subspace algorithm; (2) automated interpretation of the stabilization diagram. An additional uncertainty criterion is employed to initially remove as many spurious modes as possible. A novel threshold calculation for clustering is proposed with incorporating uncertainty of modal parameters and the weighting factor. An improved self-adaptive clustering with new distance calculation is used to group physical modes, followed by the final step of robust outlier detection to select outlying modes. The proposed automated approach requires minimum human intervention. Two field tests of the footbridge and a post-tensioned concrete bridge are used to verify the proposed approach. A modal tracking was used for continuously measured data for demonstrating the applicability of the approach. Results show the proposed approach has fairly good performance and be suitable for automated OMA and long-term health monitoring.

Self-Adaptive Clustering of Dynamic Multi-Graph Learning

In the process of graph clustering, the quality requirements for the structure of data graph are very strict, which will directly affect the final clustering results. Enhancing data graph is the key step to improve the performance of graph clustering. In this paper, we propose a self-adaptive clustering method to obtain a dynamic fine-tuned sparse graph by learning multiple static original graph with different sparsity degrees. By imposing a constrainted rank on the corresponding Laplacian matrix, the method utilizes the eigenvectors of the Laplacian matrix to create a new and simple data sparse matrix to have exactly k connected components, so that the method can quickly and directly learn the clustering results. The experimental results on synthetic and multiple public datasets verify that the proposed method is meaningful and beneficial to discover the real cluster distribution of datasets.

Fair Self-Adaptive Clustering for Hybrid Cellular-Vehicular Networks

Due to the increasing number of car-centered connected services, making efficient use of limited radio resources is critical in vehicular communications. Hybrid vehicular networks dispose of multiple Radio Access Technologies (RATs) like cellular and vehicle-to-vehicle (V2V) networks, with complementary characteristics that allow for developing smarter network traffic distribution methods. This paper proposes a self-adaptive clustering system for ensuring a suitable trade-off between data aggregation (over the cellular network) and communication congestion due to cluster management (within the V2V network). The system's algorithms use a distributive justice approach for selecting cluster heads, to improve fairness among car drivers and hence help the social acceptability of self-adaptive clustering. Simulation results show that this approach significantly improves fairness over time without affecting network performance. This solution can thus optimize the usage of radio resources, reducing cellular access costs, without the need for uniformization among different mobile operators' access plans.

An Affinity Propagation-Based Self-Adaptive Clustering Method for Wireless Sensor Networks.

A wireless sensor network (WSN) is an essential component of the Internet of Things (IoTs) for information exchange and communication between ubiquitous smart objects. Clustering techniques are widely applied to improve network performance during the routing phase for WSN. However, existing clustering methods still have some drawbacks such as uneven distribution of cluster heads (CH) and unbalanced energy consumption. Recently, much attention has been paid to intelligent clustering methods based on machine learning to solve the above issues. In this paper, an affinity propagation-based self-adaptive (APSA) clustering method is presented. The advantage of K-medoids, which is a traditional machine learning algorithm, is combined with the affinity propagation (AP) method to achieve more reasonable clustering performance. AP is firstly utilized to determine the number of CHs and to search for the optimal initial cluster centers for K-medoids. Then the modified K-medoids is utilized to form the topology of the network by iteration. The presented method effectively avoids the weakness of the traditional K-medoids in aspects of the homogeneous clustering and convergence rate. Simulation results show that the proposed algorithm outperforms some latest work such as the unequal cluster-based routing scheme for multi-level heterogeneous WSN (UCR-H), the low-energy adaptive clustering hierarchy using affinity propagation (LEACH-AP) algorithm, and the energy degree distance unequal clustering (EDDUCA) algorithm.

Self-Adaptive Clustering and Load-Bandwidth Management for Uplink Enhancement in Heterogeneous Vehicular Networks

Due to the diversity of traffic scenes and high mobility of vehicles, the propagation environment between moving vehicles and road side access points can be highly dynamic, which causes unstable uplink connectivity and time-varying uplink data rates in vehicular networks. In this paper, we study the uplink performance of heterogenous vehicular networks, which integrate dedicated short-range communications (DSRCs) and Long Term Evolution vehicle-to-everything (LTE V2X) into a single vehicular network to provide high reliability, low latency, and wide area coverage. Here, we adopt a cluster-based approach, in which DSRC and LTE are utilized to provide vehicle-to-vehicle communications between vehicles within a cluster and vehicle-to-infrastructure communications between vehicles and access points, respectively. Specifically, a self-adaptive clustering method is proposed based on the iterative self-organizing data analysis technique algorithm, in which the number of clusters can automatically adjust to the optimal value according to the mobility information. Also, a joint load-bandwidth management scheme is proposed to distribute traffic load and bandwidth resources between DSRC and LTE. Simulation results show that the proposed algorithm outperforms the traditional section-based and ${K}$ -means clustering methods, and a tradeoff between average uplink data rate and signaling overhead can be achieved.

Research on Weibo Hotspot Finding Based on Self-Adaptive Incremental Clustering

Weibo, also known as micro-blog, with its extremely low threshold of information release and interactive communication mode, has become the primary source and communication form of Internet hotspots. However, characterized as a kind of short text, the sparsity in semantic features, plus its colloquial and diversified expressions makes clustering analysis more difficult. In order to solve the above problems, we use the Biterm topic model (BTM) to extract features from the corpus and use vector space model (VSM) to strengthen the features to reduce the vector dimension and highlight the main features. Then, an improved Weibo feature-incorporated incremental clustering algorithm and the Weibo buzz calculation formula are proposed to describe the buzz of Weibo, and then the discovery of hotspots can be reasonably made. The experimental results show that the incremental clustering algorithm presented in this paper can effectively improve the accuracy of clustering in different dimensions. Meanwhile, the calculation formula of Weibo buzz reasonably describes the evolution process of Weibo buzz from a qualitative point of view, which can help discover the hotspots effectively.

Self-adapted clustering of solute atoms into a confined two-dimensional prismatic platelet with an ellipse-like quasi-unit cell.

This paper reports a new structured prismatic platelet, self-assembled by an ellipse-like quasi-unit cell, precipitated in Mg-In-Yb and Mg-In-Ca ternary alloys and aged isothermally at 200°C using aberration-corrected high-angle annular dark-field scanning transmission electron microscopy combined with density functional theory computations. The ordered stacking of solute atoms along the [0001]α direction based on elliptically shaped self-adapted clustering leads to the generation of the quasi-unit cell. The bonding of these ellipse-like quasi-unit-cell rods by the Mg atomic columns along the 〈〉α directions formed a two-dimensional planar structure, which has three variants with a {}α habit plane and full coherence with the α-Mg matrix. This finding is important for understanding the clustering and stacking behaviors of solute atoms in condensed matter, and is expected to guide the future design of novel high-strength Mg alloys strengthened by such high-density prismatic platelets.

Fast Self-Adaptive Clustering Algorithm Based on Exemplar Score Strategy

Fast Self-Adaptive Clustering Algorithm Based on Exemplar Score Strategy

Informative image selection for crowdsourcing-based mobile location recognition

With the prevalence of smartphones, the demand of recognizing the location through their camera and sensors is paid abundant attentions. For constructing a location recognition image database, the crowdsourcing technology is introduced to collect images associated with other sensory data. However, as abundant crowdsourced images evolve, it is essential to select high-quality images to decrease the burden of storage when designing an offline location recognition system directly on mobile devices. To address this problem, we propose an image selection framework, i.e., Informative image Selection Framework (ISF), considering both the diversity in spatial distribution and representativeness of images with high quality. First, for the images corresponding to the same object, we propose the Self-adaptive Space Clustering algorithm to group them into several clusters for maintaining high diversity of the image database. Second, for every cluster, we propose the Crucial Part Feature Detection algorithm to detect representative images. Extensive experiments demonstrate that ISF is effective and efficient for image selection, outperforming other similar image selection schemes around 5%.

Knowledge-leveraged transfer fuzzy C-Means for texture image segmentation with self-adaptive cluster prototype matching

We study a novel fuzzy clustering method to improve the segmentation performance on the target texture image by leveraging the knowledge from a prior texture image. Two knowledge transfer mechanisms, i.e. knowledge-leveraged prototype transfer (KL-PT) and knowledge-leveraged prototype matching (KL-PM) are first introduced as the bases. Applying them, the knowledge-leveraged transfer fuzzy C-means (KL-TFCM) method and its three-stage-interlinked framework, including knowledge extraction, knowledge matching, and knowledge utilization, are developed. There are two specific versions: KL-TFCM-c and KL-TFCM-f, i.e. the so-called crisp and flexible forms, which use the strategies of maximum matching degree and weighted sum, respectively. The significance of our work is fourfold: 1) Owing to the adjustability of referable degree between the source and target domains, KL-PT is capable of appropriately learning the insightful knowledge, i.e. the cluster prototypes, from the source domain; 2) KL-PM is able to self-adaptively determine the reasonable pairwise relationships of cluster prototypes between the source and target domains, even if the numbers of clusters differ in the two domains; 3) The joint action of KL-PM and KL-PT can effectively resolve the data inconsistency and heterogeneity between the source and target domains, e.g. the data distribution diversity and cluster number difference. Thus, using the three-stage-based knowledge transfer, the beneficial knowledge from the source domain can be extensively, self-adaptively leveraged in the target domain. As evidence of this, both KL-TFCM-c and KL-TFCM-f surpass many existing clustering methods in texture image segmentation; and 4) In the case of different cluster numbers between the source and target domains, KL-TFCM-f proves higher clustering effectiveness and segmentation performance than does KL-TFCM-c.

Obstacle regions extraction method for unmanned aerial vehicles based on space–time tensor descriptor

Obstacle avoidance is an important and challenging task for the autonomous flight of unmanned aerial vehicles. Obstacle regions extraction from image sequences is a critical prerequisite in obstacle avoidance. We propose an obstacle regions extraction method based on space–time tensor descriptor. In our method, first, the space–time tensor descriptor is defined and a criterion function based on the descriptor of extracting space–time interest points (STIPs) is designed. Then a self-adaptive clustering of STIPs approach is presented to locate the possible obstacle regions. Finally, an improved level set algorithm is applied with the result of clustering to extract the obstacle regions. We demonstrate the experiments of obstacle regions extraction by our method on image sequences. Sequences are captured in indoor simulative obstacle avoidance environments and outdoor real flight obstacle avoidance environments. Experimental results validate that our method can effectively complete extraction and segmentation of obstacle region with captured images. Compared with the state-of-the-art methods, our method performs well to extract the contours of obstacle regions on the whole and significantly improves segmentation speed.

Self-Adaptive Clustering Based on Local Density by Descending Search

Self-Adaptive Clustering Based on Local Density by Descending Search

Density Self-Adaptive Hybrid Clustering Routing Protocol for Wireless Sensor Networks

Energy efficiency is of major concern in wireless sensor networks, especially in difficult node deployment environments. Clustering is an effective method to save energy consumption and prolong the network lifetime. There are two kinds of clustering methods in hierarchical routing protocols, namely distributed control and centralized control. In the distributed strategy, the algorithm has good scalability, but it can easily lead to an uneven distribution of cluster heads. When the centralized strategy is used, the network is balanced and robust, but the overhead of clustering is large and the network latency is increased. In our proposed protocol, named DAHC, a mixture algorithm of distributed and centralized control is used to select a cluster head (CH). Simultaneously, we propose a novel approach to judge the cluster density and adjust according to the preset threshold. The simulation results show that our methods can evenly distribute the energy load on all nodes, save the energy consumption of communication and extend the network lifetime concurrently.

A Self-adaptive Spectral Clustering Based on Geodesic Distance and Shared Nearest Neighbors

A Self-adaptive Spectral Clustering Based on Geodesic Distance and Shared Nearest Neighbors

Colour image segmentation using self-adaptive watershed and affinity propagation clustering

In this paper, we propose a method for colour image segmentation using self-adaptive watershed and affinity propagation clustering. Firstly, the input image is smoothed by the spectrum envelope filter, the colour gradient is computed on the smoothed image and regional minima are marked using self-adaptive H-minima transformation method. The watershed transform is used to segment the marked gradient image we get in the previous step. Then, affinity propagation clustering is applied to optimise the segmentation using colour moments computed on each local region. Since colour gradient and colour moments are used, the proposed algorithm makes the best of colour information. Experimental results show that the proposed algorithm is more suitable for colour image segmentation, can achieve good segmentation performance and overcomes the over-segmentation problem in watershed.

Data Evolvement Analysis Based on Topology Self-Adaptive Clustering algorithm

Along with the fast advance of internet technique, internet users have to deal with tremendous data every day. To our common sense, one of the most useful knowledge provided for users is about the transfer of the information reflected by two data sets collected at different time stages. This task aims at exploiting the knowledge such as what information newly appears, what information is antiquated, and what information maintains unchanged. It is formally entitled as data evolvement analysis . Clustering is a good solution to this issue. By analyzing the clustering results formed at different time stages, it is simple to acquire the transfer of the information. Unfortunately, aforementioned plan is impractical, since it needs to perform clustering algorithm once more, every time input data are updated. Obviously, it is time-consuming. Therefore, we need to devise a dynamic clustering algorithm. It automatically adjusts its structure to express this transfer. For this reason, a novel T opology S elf- A daptive C lustering algorithm (abbreviated as TSAC) is proposed in this paper. This algorithm comes from S elf O rganizing M apping algorithm (abbreviated as SOM), whereas, it doesn't need to make any assumption about neuron topology beforehand. Besides, when input data are updated, its topology remodeled meanwhile. For further elevating its performance, it imports minimum spanning tree to preserve its topology order, which is never performed by any traditional SOM based topology adaptive algorithm. For clearly measuring the range of the transfer, it partitions data space into several grids, and then calculates the density of each grid to quantify the transfer. Experiment results demonstrate that TSAC can automatically tune its topology along with the change of input data. By this algorithm and in addition to grid structure, the transfer of the information can be legibly visualized. DOI: http://dx.doi.org/10.5755/j01.itc.41.2.974