Event Detection In Networks Research Articles

Statistical methods utilizing structural properties of time-evolving networks for event detection

Statistical methods utilizing structural properties of time-evolving networks for event detection

A Review of Research on Social Network Event Detection Methods

In recent years, with the development of technological infrastructure and the use of tech products, internet usage has become widespread globally. Significant advancements have been made in the use of social networks, which are now more readily accessible through Internet and Web 3.0 technologies such as Facebook, Twitter, and Instagram. Consequently, over the past decade, numerous researchers have been developing methods for event detection based on data collected from social media platforms. The methodologies devised for discovering events are typically modular in design and novel in terms of scale and speed. To review the research in this field, we have compiled existing works on social network event detection and conducted a comprehensive and in-depth survey. Methods for social network event detection are elaborated and categorized, with performance evaluations conducted using relevant metrics. Finally, we offer perspectives on future directions.

Dependency Structure-Enhanced Graph Attention Networks for Event Detection

Existing models on event detection share three-fold limitations, including (1) insufficient consideration of the structures between dependency relations, (2) limited exploration of the directed-edge semantics, and (3) issues in strengthening the event core arguments. To tackle these problems, we propose a dependency structure-enhanced event detection framework. In addition to the traditional token dependency parsing tree, denoted as TDG, our model considers the dependency edges in it as new nodes and constructs a dependency relation graph (DRG). DRG allows the embedding representations of dependency relations to be updated as nodes rather than edges in a graph neural network. Moreover, the levels of core argument nodes in the two graphs are adjusted by dependency relation types in TDG to enhance their status. Subsequently, the two graphs are further encoded and jointly trained in graph attention networks (GAT). Importantly, we design an interaction strategy of node embedding for the two graphs and refine the attention coefficient computational method to encode the semantic meaning of directed edges. Extensive experiments are conducted to validate the effectiveness of our method, and the results confirm its superiority over the state-of-the-art baselines. Our model outperforms the best benchmark with the F1 score increased by 3.5 and 3.4 percentage points on ACE2005 English and Chinese corpus.

Anomaly Detection Using CNN with I3D Feature Extraction

Anomaly detection is a critical task in various fields such as surveillance, healthcare, and industrial monitoring, aiming to identify patterns that deviate significantly from normal behavior.Video anomaly detection is inherently difficult due to visual complexity and variability. This work proposes a unique anomaly detection technique leveraging Convolutional Neural Networks (CNN) with Inflated 3D Convolutional Networks (I3D) for feature extraction. This involves training the CNN on a large dataset to learn normal behavior, enabling it to identify anomalies by recognizing deviations from learned patterns. Furthermore, our approach exhibits promising results in detecting various types of anomalies, including sudden changes, abnormal trajectories, and rare events. Upon detection of such activity, mail(notification) can be raised concerned people who can take immediate action.This research contributes a significant advancement in the field of anomaly detection, and holds potential for applications in surveillance, security, and industrial monitoring systems. Keywords—Anomaly detection,I3D(Inflated3D) feature extraction,Convolutional neural network, Spatio-Temporal Features,Normal and abnormal event detection.

Finding Subgraphs with Maximum Total Density and Limited Overlap in Weighted Hypergraphs

Finding dense subgraphs in large (hyper)graphs is a key primitive in a variety of real-world application domains, encompassing social network analytics, event detection, biology, and finance. In most such applications, one typically aims at finding several (possibly overlapping) dense subgraphs, which might correspond to communities in social networks or interesting events. While a large amount of work is devoted to finding a single densest subgraph, perhaps surprisingly, the problem of finding several dense subgraphs in weighted hypergraphs with limited overlap has not been studied in a principled way, to the best of our knowledge. In this work, we define and study a natural generalization of the densest subgraph problem in weighted hypergraphs, where the main goal is to find at most k subgraphs with maximum total aggregate density, while satisfying an upper bound on the pairwise weighted Jaccard coefficient, i.e., the ratio of weights of intersection divided by weights of union on two nodes sets of the subgraphs. After showing that such a problem is NP-Hard, we devise an efficient algorithm that comes with provable guarantees in some cases of interest, as well as, an efficient practical heuristic. Our extensive evaluation on large real-world hypergraphs confirms the efficiency and effectiveness of our algorithms.

Weighted bidirectional gated recurrent network for event detection

Weighted bidirectional gated recurrent network for event detection

MSED: A Multi-Modal Sleep Event Detection Model for Clinical Sleep Analysis.

Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations (r2 = 0.73, r2 = 0.77, r2 = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size. Source code for training and inference is available at https://github.com/neergaard/msed.git.

Data Gathering Scheme for Event Detection and Recognition in Low Power Wide Area Networks

Data Gathering Scheme for Event Detection and Recognition in Low Power Wide Area Networks

Generative and non-parametric model for real-time event detection in social networks based on textual analysis

One of the things that is followed in monitoring systems is the detection of rare events in real time among the multitude of common events in social networks. Considering the lack of recognition and unavailability of rare events, their detection is considered a challenge. In this research, a new architecture and approach based on generative adversarial network infrastructure was presented to detect common and rare events in real time. In this research, the attempt is to provide a new approach to the performance of architectures based on deep generative adversarial networks, a way to solve various problems without supervision with a semi-supervisory approach and adversarial generative infrastructure. This architecture is based on the automatic extraction and use of video input data features. The results of the equal error rate in the UCSDped1 and UCSDped2 datasets were 2.0 and 17.0, respectively, in the performance characteristic curve.

A Multi-Hop Graph Neural Network for Event Detection via a Stacked Module and a Feedback Network

Event detection is an important subtask of information extraction, aiming to identify triggers and recognize event types in text. Previous state-of-the-art studies using graph neural networks (GNNs) are mainly applied to obtain long distance features of text and have achieved impressive performance. However, these methods face the issues of over-smoothing and semantic feature destruction, when containing multiple GNN layers. For the reasons, this paper proposes an improved GNN model for event detection. The model first proposes a stacked module to enrich node representation to alleviate the over-smoothing. The module aggregates multi-hop neighbors with different weights by stacking different GNNs in each hidden layer, so that the representation of nodes no longer tends to be similar. Then, a feedback network is designed with a gating mechanism to retain effective semantic information in the propagation process of the model. Finally, experimental results demonstrate that our model achieves competitive results in many indicators compared with state-of-the-art methods.

Out-of-Distribution (OOD) Detection Based on Deep Learning: A Review

Out-of-Distribution (OOD) detection separates ID (In-Distribution) data and OOD data from input data through a model. This problem has attracted increasing attention in the area of machine learning. OOD detection has achieved good intrusion detection, fraud detection, system health monitoring, sensor network event detection, and ecosystem interference detection. The method based on deep learning is the most studied in OOD detection. In this paper, related basic information on OOD detection based on deep learning is described, and we categorize methods according to the training data. OOD detection is divided into supervised, semisupervised, and unsupervised. Where supervised data are used, the methods are categorized according to technical means: model-based, distance-based, and density-based. Each classification is introduced with background, examples, and applications. In addition, we present the latest applications of OOD detection based on deep learning and the problems and expectations in this field.

Energy Allocation for Stochastic Event Detection in Rechargeable Sensor Networks

Wireless rechargeable sensor networks have been applied to all aspects of the real world today. Though sensors can collect energy from the environment, the energy collection cannot support sensors to work continuously as usual. Energy scheduling problems have to be solved. In this paper, we study the energy allocation problem of a rechargeable sensor network that can monitor multiple random events. It is assumed that each event follows a Poisson process, the energy received by the sensor is random, and each sensor has a chance to be assigned to detect one or more events. In the paper, we also introduce multi-objective nonlinear programming to solve the problems of nonlinearity and energy. Two algorithms are also proposed to obtain the programming’s Pareto optimal solution. At last, we conduct a number of practical simulations to verify our results.

Event Detection and Identification in Distribution Networks Based on Invertible Neural Networks and Pseudo Labels

Anomalous event detection and identification are important to support situational awareness and security analysis in power grids. Particularly, the distribution network is with complicated topology, variable load behaviors, and integration of nonlinear distributed generators (DGs), which is difficult to implement complete modeling mathematically. With the deployment of advanced measurement devices such as μPMUs in distribution networks, massive data containing rich system status information becomes available. In this paper, a framework for event detection, localization, and classification is studied to extract event features from measurements in distribution networks. Specifically, a method based on an invertible neural network (INN) is employed to model the complex distributions of normal-state measurements offline in a flexible way. It then establishes explicit likelihoods as the indicator to enable real-time event detection. Furthermore, a Jacobian-based method is utilized for spatial localization. Finally, as the events in practical power grids are mostly recorded unlabeled, the pseudo label (PL) based approach, superior in the separating ability for events under a low labeling rate, and is used to implement event classification. Several typical types of events simulated in the IEEE 34-bus system and real-world cases in a low-voltage system verify the effectiveness and superiorities of the framework.

A Comprehensive Study of Event Detection in WPCN Networks with Noisy Measurements.

Various aspects of the detection of events in wireless powered communication networks (WPCN) are studied and analyzed under the assumption of highly noisy sensor measurements. In WPCN, networks sensor nodes’ stored energy is a scarce resource and must be treated sparingly. Frequent false alarm detections force superfluous transmissions, thus depleting nodes’ energy storage. This has an adverse effect on the probability of successful transmission of the information message and its delay in case of a true positive detection. In this work, the detection problem is approached using an optimal stopping framework, where the involved likelihoods are highly unstable due to the noisy measurements. A classical AR filter is adopted in order to smooth the posterior likelihoods prior to their usage in the detection phase and its performance is contrasted to that of a novel Beta Particle Filter smoother. The effects of the smoothing filters on the achieved false alarm rate and detection delay are examined using numerical and simulation results. Moreover, the assessment of the detection process takes into account critical WPCN parameters, such as the charging efficiency and the location of the sensors, thus aiding the system design.

Cuckoo search in threshold optimization for better event detection in social networks

Cuckoo search in threshold optimization for better event detection in social networks

An In-Depth Study and Improvement of Isolation Forest

Historically, anomalies detection was an important issue for industrial applications such as the detection of a manufacturing failure or defect. It is still a current topic that tries to meet the ever increasing demand in different fields such as intrusion detection, fraud detection, ecosystem change detection or event detection in sensor networks. That’s why anomalies detection remains a research topic of great interest for various research communities. In this paper, we focused on Isolation Forest (IForest), a well known, efficient anomalies detection algorithm. We provided a deep and complete view on IForest. We evaluated the impact of its input parameters (number of trees, sample size and decision threshold) on the efficiency of the detection and on the execution time. We discussed the benefit of including some anomalies into the training phase. To address the limits of IForest, we performed different experiments on commonly used real datasets and also on synthetic datasets with non trivial distributions. We designed multidimensional datasets where anomalies are carried by several dimensions simultaneously. Moreover, we used a varying density and distance between anomalies and normal data, for a variable similarity between these two data classes. We compared the performance of IForest against its improved version called Extended IForest. Finally, we designed and validated a new extension of IForest, based on the different individual trees decisions instead of a global forest decision that we call Majority Voting IForest (MVIForest). The experiments show that MVIForest has a shorter execution time than IForest, with almost the same accuracy.

Event detection in temporal social networks using a higher-order network model.

Event detection is one of the most important areas of complex network research. It aims to identify abnormal points in time corresponding to social events. Traditional methods of event detection, based on first-order network models, are poor at describing the multivariate sequential interactions of components in complex systems and at accurately identifying anomalies in temporal social networks. In this article, we propose two valid approaches, based on a higher-order network model, namely, the recovery higher-order network algorithm and the innovation higher-order network algorithm, to help with event detection in temporal social networks. Given binary sequential data, we take advantage of chronological order to recover the multivariate sequential data first. Meanwhile, we develop new multivariate sequential data using logical sequence. Through the efficient modeling of multivariate sequential data using a higher-order network model, some common multivariate interaction patterns are obtained, which are used to determine the anomaly degree of a social event. Experiments in temporal social networks demonstrate the significant performance of our methods finally. We believe that our methods could provide a new perspective on the interplay between event detection and the application of higher-order network models to temporal networks.

Context-aware Distance Measures for Dynamic Networks

Dynamic networks are widely used in the social, physical, and biological sciences as a concise mathematical representation of the evolving interactions in dynamic complex systems. Measuring distances between network snapshots is important for analyzing and understanding evolution processes of dynamic systems. To the best of our knowledge, however, existing network distance measures are designed for static networks. Therefore, when measuring the distance between any two snapshots in dynamic networks, valuable context structure information existing in other snapshots is ignored. To guide the construction of context-aware distance measures, we propose a context-aware distance paradigm, which introduces context information to enrich the connotation of the general definition of network distance measures. A Context-aware Spectral Distance (CSD) is then given as an instance of the paradigm by constructing a context-aware spectral representation to replace the core component of traditional Spectral Distance (SD). In a node-aligned dynamic network, the context effectively helps CSD gain mainly advantages over SD as follows: (1) CSD is not affected by isospectral problems; (2) CSD satisfies all the requirements of a metric, while SD cannot; and (3) CSD is computationally efficient. In order to process large-scale networks, we develop a kCSD that computes top- k eigenvalues to further reduce the computational complexity of CSD. Although kCSD is a pseudo-metric, it retains most of the advantages of CSD. Experimental results in two practical applications, i.e., event detection and network clustering in dynamic networks, show that our context-aware spectral distance performs better than traditional spectral distance in terms of accuracy, stability, and computational efficiency. In addition, context-aware spectral distance outperforms other baseline methods.

An approach of Bursty event detection in social networks based on topological features

An approach of Bursty event detection in social networks based on topological features

FGCAN: Filter-based Gated Contextual Attention Network for event detection

Contextual information is widely used in natural language processing and is important for event detection. How to make full use of contextual information is a challenging problem. Traditional event detection methods mainly use sentence-level information to identify event triggers and classify them into specific types. Event trigger is defined as the word or phrase that most clearly expresses an event occurrence. However, the information used for detecting events is usually spread across multiple sentences, and sentence-level information is often insufficient to resolve ambiguities for some types of events. In this paper, we propose a novel Filter-based Gated Contextual Attention Network model called FGCAN, which is augmented with hierarchical contextualized representations to utilize both sentence-level and document-level information. In document level, we construct a gated contextual attention layer to extract document-level information by considering the relatedness between the current and other sentences and dynamically incorporate it into words. In this way, we can get cross-sentence clues without designing complex inference rules. In sentence level, we feed sentences into the classifier to get global information of them, and devise a rule-based filter algorithm to rectify the prediction of each word based on the probability ranking of the sentence labels, which is highly interpretable. These two mechanisms focusing on different scopes of contextual information can complement each other. The experimental results on the widely used ACE 2005 and KBP 2015 datasets show that our approach outperforms the state-of-the-art methods and the two components are effective in using contextual information.