Early detection of emergency events from social media: A new text clustering approach

Emergency events need early detection, quick response, and accuracy recover. In the era of big data, social media users can be seen as social sensors to monitor real time emergency events. This paper proposed an integrated approach to early detect all the four kinds of emergency events including natural disasters, man-made accidents, public health events and social security events. First, the BERT-Att-BiLSTM model is used to detect emergency related posts from the massive and irrelevant data. Then, the 3W attribute information (What, Where and When) of the emergency event is extracted. With the 3W attribute information, we create an unsupervised dynamical event clustering algorithm based on text-similarity and combine it with the supervised logistical regression model to cluster posts into different events. The experiments on Sina Weibo data demonstrate the superiority of the proposed framework. Case studies on some real emergency events show the proposed framework has good performance and high timeliness. Practical applications of the framework have also been discussed, following by some future directions for improvement.

The ECB’s 2019 Liquidity Stress Test: An Event Study Evaluating the Impact on Owners and Creditors

The liquidity stress test (LiST) 2019 by the European Central Bank (ECB) examines the liquidity situation of banks, which is novel at the European level. Therefore, a well-founded empirical analysis is necessary to derive implications for the capital market. This paper investigates the impact on stock returns and credit default swap (CDS) spread changes of the participating banks using an event study methodology. This approach allows for conclusions about the entire capital market. A major problem with the sample, event clustering, is addressed with appropriate test statistics. The paper provides evidence of the absence of a capital market reaction, which could be the goal of supervisors, namely, being able to assess the banking sector and providing general information without triggering panic.

Understanding Contrail Business Processes through Hierarchical Clustering: A Multi-Stage Framework

Real-world business processes are dynamic, with event logs that are generally unstructured and contain heterogeneous business classes. Process mining techniques derive useful knowledge from such logs but translating them into simplified and logical segments is crucial. Complexity is increased when dealing with business processes with a large number of events with no outcome labels. Techniques such as trace clustering and event clustering, tend to simplify the complex business logs but the resulting clusters are generally not understandable to the business users as the business aspects of the process are not considered while clustering the process log. In this paper, we provided a multi-stage hierarchical framework for business-logic driven clustering of highly variable process logs with extensively large number of events. Firstly, we introduced a term contrail processes for describing the characteristics of such complex real-world business processes and their logs presenting contrail-like models. Secondly, we proposed an algorithm Novel Hierarchical Clustering (NoHiC) to discover business-logic driven clusters from these contrail processes. For clustering, the raw event log is initially decomposed into high-level business classes, and later feature engineering is performed exclusively based on the business-context features, to support the discovery of meaningful business clusters. We used a hybrid approach which combines rule-based mining technique with a novel form of agglomerative hierarchical clustering for the experiments. A case-study of a CRM process of the UK’s renowned telecommunication firm is presented and the quality of the proposed framework is verified through several measures, such as cluster segregation, classification accuracy, and fitness of the log. We compared NoHiC technique with two trace clustering techniques using two real world process logs. The discovered clusters through NoHiC are found to have improved fitness as compared to the other techniques, and they also hold valuable information about the business context of the process log.

Hawkes process modeling of COVID-19 with mobility leading indicators and spatial covariates

Hawkes processes are used in machine learning for event clustering and causal inference, while they also can be viewed as stochastic versions of popular compartmental models used in epidemiology. Here we show how to develop accurate models of COVID-19 transmission using Hawkes processes with spatial-temporal covariates. We model the conditional intensity of new COVID-19 cases and deaths in the U.S. at the county level, estimating the dynamic reproduction number of the virus within an EM algorithm through a regression on Google mobility indices and demographic covariates in the maximization step. We validate the approach on short-term forecasting tasks, showing that the Hawkes process outperforms several benchmark models currently used to track the pandemic, including an ensemble approach and a SEIR-variant. We also investigate which covariates and mobility indices are most important for building forecasts of COVID-19 in the U.S.

Does the seismic cycle slip toward randomness?

<p>Seismology and paleoseismology seem to be two distant sisters when we address earthquake time-interval distributions. One observation stands out; an apparent discrepancy in time-interval models, i.e. periodic to cluster, within similar tectonic context. As a departure point, we will use the Himalayan context where according to instrumental or paleoseismic catalogues, time-interval distributions are presented as Poisson to periodic. We report on a new 6000-year lake-sediment seismic record and perform statistical analyses to show that time intervals between large (M≥6.5) earthquakes are robustly described by a Poisson distribution, while second-order fluctuations imply event clustering. These patterns are calibrated against an instrumental catalogue for the entire Himalaya; we show that both catalogues are inconsistent with periodic models. Throughout this presentation, we will compare the Himalayan results with paleoseismic catalogues from three distinct tectonic settings (Indonesia, New-Zealand and Jordan). Each of them displays a close to Poisson distribution, in consonance with instrumental catalogues results. Our results imply that the occurrence of major seismic events is as uncertain as smaller events on any time scale, increasing drastically previous estimate of the seismic hazard.</p>

An Experimental Analysis of Modified EEECARP

Designing various energy-saving routing protocols for real-time internet of things (IoT) applications in modern secure wireless sensor networks (MS-WSN) is a tough task. Many hierarchical protocols for WSNs were not well scalable to large-scale IoT applications. Low energy adaptive two-level-CH clustering hierarchy (LEATCH) is an optimized technique reduces the energy-utilization of few cluster heads, but the LEATCH is not suitable for scalable and dynamic routing. For dynamic routing in MS-WSN, energy efficiency and event clustering adaptive routing protocol (EEECARP) with event-based dynamic clustering and relay communication by selecting intermediates nodes as relay-nodes is necessary. However, EEECARP cannot consider the hop-count, different magnitude ecological conditions, and energy wastage in cluster formation while collisions occur. So, the authors propose the modified EEECARP to address these issues for better dynamic event clustering adaptive routing to improve the lifetime of MS-WSNs. The experimental outcomes show that proposed protocol achieves better results than EEECARP and LEATCH.

EEECARP

WSN is a promising approach for variety of different real time applications. Different Routing protocols for WSNs are very effective challenge in present days because of scalability, efficient energy utilization and robustness in large number of wireless sensor networks with consists of more number of sensor nodes. LEATCH is a traditional routing protocol for energy optimization in WSNs. However, LEATCH cannot scale performance for large scale wireless sensor networks and difficulty to apply effective utilization of real time wireless sensor networks. So, in this paper the authors propose to develop a novel Energy Efficiency and Event Clustering Adaptive Routing Protocol (EEECARP) for WSN. The main designing feature of their proposed approach is as follows: Energy Efficiency, Dynamic Event Clustering and multi hop relay configuration with residual energy available on relay nodes in wireless sensor networks. The simulation results show that authors' routing protocol achieves convenient and effective better performance in formation of clusters with relay sensor nodes in wireless sensor networks.

A Novel Hybrid Adaptive Filter to Improve Video Keyframe Clustering to Support Event Resolution in Cricket Videos

Automated summary generation of sports videos poses many challenges of detecting exciting events of a game. In our research, we focus on the table of content-based video summarization for cricket videos to facilitate efficient indexing of cricket events. Initially, we have identified event boundaries accurately to detect the event start and end points. To distinguish the different types of events, we need to analyze the sequence of the camera focus area. By observing the characteristics, we have categorized the camera focus area into several categories. To overcome the challenge of low accuracy we have introduced a novel algorithm for adaptive filtering for the comparison of hue histogram. The results prove that this algorithm is sufficient for accurate image clustering and this may be used in other sports event clustering as well.