Event Recognition System Research Articles

Vamos: Middleware for best-effort third-party monitoring

As the complexity and criticality of software increase every year, so does the importance of runtime monitoring. Third-party and best-effort monitoring are especially valuable, yet under-explored areas of runtime monitoring. In this context, third-party monitoring means monitoring with a limited knowledge of the monitored software (as it has been developed by a third party). Best-effort monitoring keeps pace with the monitored software at the cost of possibly imprecise verdicts when keeping up with the monitored software would not be feasible. Most existing monitoring frameworks do not support the combination of third-party and best-effort monitoring because they either require the full access to the monitored code or the ability to process all observable events, or both.We present a middleware framework, Vamos, for the runtime monitoring of software. Vamos is explicitly designed to support third-party and best-effort scenarios. The design goals of Vamos are (i) efficiency (tracing events with low overhead), (ii) flexibility (the ability to monitor a variety of different event channels, and to connect to a wide range of monitors), and (iii) ease-of-use. To achieve its goals, Vamos combines aspects of event broker and event recognition systems with aspects of stream processing systems.We implemented a prototype toolchain for Vamos and conducted a set of experiments demonstrating the usability of the scheme. The results indicate that Vamos enables writing useful yet efficient monitors, and simplifies key aspects of setting up a monitoring system from scratch.

Flash Flood Detection and Alert System Using Machine Learning

Abstract: Floods can be considered as one among the top natural disasters that sometimes happens regularly in particular season thereby causing harm on human lives and also resultsin reducing economic growth. So, the news about the flooding events has to be spread to nearby localities in time so as to avoid further chaos. Therefore, it is crucial to build a warning system that informs the flooding event to reduce the casualties of flood disaster. Recognizing sensitive events in images, such as flood events is significant for the maintenance of normal public opinionand social stability. By now, it is still a challenging problem. In this project, we propose a novel method for recognizing flood events from images using Keras pretrained MobileNet CNN. Flooding and non-flooding images are collected and trained in theCNN network so as to build the classifier that can differentiate the input image from flooding and non-flooding categories. At first, the feature extraction is carried to develop a model that is capable of classifying flood images from normal images. Later the MobileNet CNN helps in classifying the flood images effectively with accuracy and an appropriate warning message is sent to the people in nearby localities. To enhance the efficacy of our flood event recognition system, we are integrating cutting-edge tech- nologies and methodologies. In addition to leveraging the power of Keras pretrained MobileNet CNN for image classification, we are also implementing advanced image processing techniques for better feature extraction and analysis. By incorporating thesemethods, we aim to achieve higher accuracy and reliability in identifying flood events from images.

Φ-OTDR Event Recognition System Based on Valuable Data Selection

Φ-OTDR Event Recognition System Based on Valuable Data Selection

Multi-channel hybrid parallel classification network based on Siamese network for the DAS event recognition system

Multi-channel hybrid parallel classification network based on Siamese network for the DAS event recognition system

Online semi-supervised learning of composite event rules by combining structure and mass-based predicate similarity

Symbolic event recognition systems detect event occurrences using first-order logic rules. Although existing online structure learning approaches ease the discovery of such rules in noisy data streams, they assume the existence of fully labelled training data. Splice is a recent online graph-based approach that estimates the labels of unlabelled data and makes it possible to learn such rules from semi-supervised training sequences of logical interpretations. However, Splice labelling depends significantly on the metric used to compute the distances of unlabelled examples to their labelled counterparts. Moreover, there is no guarantee about the quality of the labelling found in the local graphs that are built as the data stream in. In this paper, we propose a new online learning method, which includes an enhanced hybrid measure that combines an optimised structural distance, and a data-driven one. The former is guided by feature selection targeted to kNN classification, while the latter is a mass-based dissimilarity. Additionally, the enhanced Splice method, improves the graph construction process, by storing a synopsis of the past, in order to achieve more informed labelling on the local graphs. We evaluate our approach by learning Event Calculus theories for the tasks of human activity recognition, maritime monitoring, and fleet management. The evaluation suggests that our approach outperforms its predecessor, in terms of inferring the missing labels and improving the predictive accuracy of the underlying structure learning system.

Online event recognition over noisy data streams

Composite event recognition (CER) systems process streams of sensor data and infer composite events of interest by means of pattern matching. Data uncertainty is frequent in CER applications and results in erroneous detection. To support streaming applications, we present oPIECbd, an extension of oPIEC with a bounded memory, leveraging interval duration statistics to resolve memory conflicts. oPIECbd may achieve comparable predictive accuracy to batch reasoning, avoiding the prohibitive cost of such reasoning. Furthermore, the use of interval duration statistics allows oPIECbd to outperform significantly earlier versions of bounded oPIEC. The empirical evaluation demonstrates the efficacy of oPIECbd on a benchmark activity recognition dataset, as well as real data streams from the field of maritime situational awareness.

Multi-signal feature fusion method with an attention mechanism for the Φ-OTDR event recognition system.

Different signal representations show different unique features for classification. In this paper, a feature fusion method with attention mechanism based on multiple signal representations is proposed for Φ-OTDR event classification with buried optical fiber. Each signal representation is fused after feature extraction to get richer and better features. With the help of a layer pruning method based on attention mechanism, the network size can be kept and avoid computation increase. Experiment results show that this method with 3 signal representations can improve the recognition accuracy to 97.93%, with 3.52% improvement compared to single representation approach. It also shows higher recognition accuracy than the tradition multiple signal representations fusion methods at the input stage. Furthermore, when it is used to fuse four representations, the recognition accuracy can be further improved to 99.11%.

CORE

Complex Event Recognition (CER) systems are a prominent technology for finding user-defined query patterns over large data streams in real time. CER query evaluation is known to be computationally challenging, since it requires maintaining a set of partial matches, and this set quickly grows super-linearly in the number of processed events. We present CORE, a novel COmplex event Recognition Engine that focuses on the efficient evaluation of a large class of complex event queries, including time windows as well as the partition-by event correlation operator. This engine uses a novel automaton-based evaluation algorithm that circumvents the super-linear partial match problem: under data complexity, it takes constant time per input event to maintain a data structure that compactly represents the set of partial matches and, once a match is found, the query results may be enumerated from the data structure with output-linear delay. We experimentally compare CORE against state-of-the-art CER systems on real-world data. We show that (1) CORE's performance is stable with respect to both query and time window size, and (2) CORE outperforms the other systems by up to five orders of magnitude on different workloads.

Detection and classification of sunspots via deep convolutional neural network

Sunspots are known to be the most prominent feature of the solar photosphere. Solar activities play a vital role in Space weather which greatly affects the Earth's environment. The appearance of sunspots determines the solar activities and being observed from early eighteenth century. In this work, we have implemented a deep learning model which automatically detects sunspots from MDI and HMI image datasets. Proposed model uses Alexnet based deep convolutional networks to generate promising deep hierarchical features and proposed deep learning approach achieved excellent classification accuracies. Also, model has shown the improved result with MDI data set which is equal to 99.71%, 100%, 100%, and 100 for accuracy, precision, recall, and F-score respectively. This is to construct and build robust and reliable event recognition system to monitor solar activities which are crucial to understanding space weather and for physicists it is an aid for their research.

Symmetrically Stacked Long Short-Term Memory Networks for Fall Event Recognition Using Compact Convolutional Neural Networks-Based Tracker

In recent years, the advancement of pattern recognition algorithms, specifically the deep learning-related techniques, have propelled a tremendous amount of researches in fall event recognition systems. It is important to detect a fall incident as early as possible, whereby a slight delay in providing immediate assistance can cause severe unrecoverable injuries. One of the main challenges in fall event recognition is the imbalanced training data between fall and no-fall events, where a real-life fall incident is a sporadic event that occurs infrequently. Most of the recent techniques produce a lot of false alarms, as it is hard to train them to cover a wide range of fall situations. Hence, this paper aims to detect the exact fall frame in a video sequence, as such it will not be dependent on the whole clip of the video sequence. Our proposed approach consists of a two-stage module where the first stage employs a compact convolutional neural network tracker to generate the object trajectory information. Features of interest will be sampled from the generated trajectory paths, which will be fed as the input to the second stage. The next stage network then models the temporal dependencies of the trajectory information using symmetrical Long Short-Term Memory (LSTM) architecture. This two-stage module is a novel approach as most of the techniques rely on the detection module rather than the tracking module. The simulation experiments were tested using Fall Detection Dataset (FDD). The proposed approach obtains an expected average overlap of 0.167, which is the best performance compared to Multi-Domain Network (MDNET) and Tree-structured Convolutional Neural Network (TCNN) trackers. Furthermore, the proposed 3-layers of stacked LSTM architecture also performs the best compared to the vanilla recurrent neural network and single-layer LSTM. This approach can be further improved if the tracker model is firstly pre-tuned in offline mode with respect to a specific type of object of interest, rather than a general object.

Event Recognition System Based on Fiber Bragg Grating and mRMR-CWCs-SCN

Traditional algorithm lacks the ability to generalize across different application scenarios and how to set the stopping conditions of network iteration in Stochastic Configuration Network (SCN) is a problem. This paper proposes an event recognition system based on minimum redundancy, maximum relevance (mRMR) and a modified Stochastic Configuration Network (CWCs-SCN) for the fiber Bragg grating (FBG) sensor system. mRMR is used to analyze the importance of 14th time-frequency domain features in different application scenarios. After that, a modified SCN (CWCs-SCN) neural network is used to solve the stopping condition of the network iteration. The experiments demonstrated that the average recognition accuracy of four kind of human intrusion signal can reach to 96.7%, which is better than others traditional methods. In addition, a more compact neural network is obtained compared to SCN. To verify the generalization ability of the proposed model, it is applied to gear fault diagnosis with an accuracy of 96.3%. This imply that the proposed method in this paper has a wide application prospect.

Complex event forecasting with prediction suffix trees

Complex event recognition (CER) systems have become popular in the past two decades due to their ability to “instantly” detect patterns on real-time streams of events. However, there is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of complex event forecasting (CEF). Our framework combines two formalisms: (a) symbolic automata which are used to encode complex event patterns and (b) prediction suffix trees which can provide a succinct probabilistic description of an automaton’s behavior. We compare our proposed approach against state-of-the-art methods and show its advantage in terms of accuracy and efficiency. In particular, prediction suffix trees, being variable-order Markov models, have the ability to capture long-term dependencies in a stream by remembering only those past sequences that are informative enough. We also discuss how CEF solutions should be best evaluated on the quality of their forecasts.

Online Learning Probabilistic Event Calculus Theories in Answer Set Programming

AbstractComplex Event Recognition (CER) systems detect event occurrences in streaming time-stamped input using predefined event patterns. Logic-based approaches are of special interest in CER, since, via Statistical Relational AI, they combine uncertainty-resilient reasoning with time and change, with machine learning, thus alleviating the cost of manual event pattern authoring. We present a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online. We compare our ASP-based implementation with a Markov Logic-based one and with a number of state-of-the-art batch learning algorithms on CER data sets for activity recognition, maritime surveillance and fleet management. Our results demonstrate the superiority of our novel approach, both in terms of efficiency and predictive performance. This paper is under consideration for publication in Theory and Practice of Logic Programming (TPLP).

Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms

Abstract Near-real-time event detection is crucial for water utilities to be able to detect failure events in their water treatment works (WTW) quickly and efficiently. This paper presents a new method for an automated, near-real-time recognition of failure events at WTWs by the application of combined statistical process control and machine-learning techniques. The resulting novel hybrid CUSUM event recognition system (HC-ERS) uses two distinct detection methodologies: one for fault detection at the level of individual water quality signals and the second for the recognition of faulty processes at the WTW level. HC-ERS was tested and validated on historical failure events at a real-life UK WTW. The new methodology proved to be effective in the detection of failure events, achieving a high true-detection rate of 82% combined with a low false-alarm rate (average 0.3 false alarms per week), reaching a peak F1 score of 84% as a measure of accuracy. The new method also demonstrated higher accuracy compared with the CANARY detection methodology. When applied to real-world data, the HC-ERS method showed the capability to detect faulty processes at WTW automatically and reliably, and hence potential for practical application in the water industry.

Prosodic event detection in children’s read speech

Prosody is the supra-segmental aspect of speech that helps to convey the structure and intended meaning of lexical content unambiguously. The automatic detection of prosodic events, such as phrase boundary and word prominence, has a number of applications in discourse analysis, where a combination of syntactic and acoustic-prosodic features is typically employed. This work addresses prosodic event detection in the context of assessing oral reading skills of middle-school children. We discuss the observed characteristics of a specially created labeled data set of oral reading recordings of English stories by non-native speakers. The obtained diversity of language skills adds to the known challenges of high speaker variability in the acoustic realization of prosodic events. A combination of knowledge- and data-driven feature selection is implemented to identify a compact set of word-level features from the acoustic correlates of prosody considering different ways of incorporating the necessary temporal context. The system is benchmarked with reference to a widely known prosodic event recognition system in a speaker-independent set-up to obtain a competitive performance with greatly reduced feature dimensionality. The interpretable features enable us to use the predictor model importance scores to identify high-level speaker traits that influence the acoustic realization of prosodic events, suggesting a potential extension to systems that can extract and utilize speaker idiosyncrasies for superior prosodic event detection.

Machine learning for video event recognition

In recent years, the spread of video sensor networks both in public and private areas has grown considerably. Smart algorithms for video semantic content understanding are increasingly developed to support human operators in monitoring different activities, by recognizing events that occur in the observed scene. With the term event, we refer to one or more actions performed by one or more subjects (e.g., people or vehicles) acting within the same observed area. When these actions are performed by subjects that do not interact with each other, the events are usually classified as simple. Instead, when any kind of interaction occurs among subjects, the involved events are typically classified as complex. This survey starts by providing the formal definitions of both scene and event, and the logical architecture for a generic event recognition system. Subsequently, it presents two taxonomies based on features and machine learning algorithms, respectively, which are used to describe the different approaches for the recognition of events within a video sequence. This paper also discusses key works of the current state-of-the-art of event recognition, providing the list of datasets used to evaluate the performance of reported methods for video content understanding.

Microdroplet event recognition and volume detection system based on flexible printed circuit electrode

Changes of microdroplet volume and the occurrence of different droplet events will exert a significant influence on droplet-based microfluidics. Droplet volume is closely related to reagent consumption and hydrodynamic resistance while droplet events reflect actual microchannel conditions. Based on current research, this work was dedicated to fabricate a reliable microdroplet sensing system with event recognition and volume detection function. Signal acquisition was on the basis of capacitance coupled detection and the coplanar fork sensing electrode was fabricated by flexible printed circuit(FPC) which was tens of times cheaper than photolithography. Wave peaks will appear while ink droplets traverse over the fork electrode from above. Shape features of waveform were used to recognize some simple droplet events and the period was employed to calculate droplet volume. Through experimental verification, droplet generation and droplet merging events could be recognized and distinguished by the system. In addition, the detection error between the theoretical volume calculated from formula and the actual volume derived from image analysis was less than 0.5 nL. The sensing system possesses the potential to achieve high throughput detection and surely can be employed to recognize more complicated droplet events in the future.

A SKELETON FEATURES-BASED FALL DETECTION USING MICROSOFT KINECT V2 WITH ONE CLASS-CLASSIFIER OUTLIER REMOVAL

Abstract. The real-time and robust fall detection is one of the key components of elderly people care and monitoring systems. Depth sensors, as they became more available, occupy an increasing place in event recognition systems. Some of them can directly produce a skeletal description of the human figure for compact representation of a person’s posture. Skeleton description makes the output of source video or detailed information about the depth outside the system unnecessary and raises the privacy of the entire system. Based on a comparative study of different RGB-D cameras, the most promising model for further development was chosen - Microsoft Kinect v2. The TST Fall Detection Dataset v2 is used here as a base for experiments. The proposed algorithm is based on the skeleton features encoding on the sequence of neighboring frames and support vector machine classifier. A version of a cumulative sum method is applied for combining the individual decisions on the consecutive frames. It is offered to use the one-class classifier for detection of low-quality skeletons. The 0.958 accuracy of our fall detection procedure was obtained in the cross-validation procedure based on the removal of records of a particular person from the database (Leave-one-Person-out).

Математичні методи розпізнавання надзвичайних ситуацій в умовах невизначеності

Показано, що системи розпізнавання надзвичайних подій виявляють різні типи невизначеності: неповні потоки даних, помилки в потоках даних і невідповідні шаблони складних подій. Показано, що потоки подій, що потрапляють на вхід системи розпізнавання складних подій, характеризуються певним ступенем невизначеності. Джерела даних є неоднорідними і характеризуються різною структуризацією даних і відповідними процедурами реагування на пошкоджені блоки даних. Навіть для даних, визначених достатньо точно, система може некоректно моделювати складні події, що призводить до подальшого типу невизначеності. Отже, зазначено, що важливо розглянути методи розпізнавання складних подій, які можна віднести до невизначених. З цією метою було запропоновано відповідні модельні об'єкти. Проведений аналіз ключових моментів побудови систем розпізнавання складних подій, які здатні ефективно працювати в умовах невизначеності, охоплював методи стохастичного моделювання, моделі часового представлення та реляційні моделі. Розглянуто методики, що базуються на абстрактних автоматах, імовірнісних моделях графів, системах логіки першого порядку, мережах Петрі та прихованих мережах Петрі. Зазначено, що проміжним етапом роботи відповідних алгоритмів має бути створення ієрархії складних об'єктів, що не завжди піддаються чіткому визначенню. Виявлено низку обмежень щодо використовуваного синтаксису, моделей і ефективності, які були зіставлені з конкретними варіантами їх реалізації. Запропоновано підхід щодо переходу від детерміністичного математичного апарату до системи розпізнавання складних подій в умовах невизначеності, через введення функції вірогідності події. Розроблена методологія дала змогу виділити напрями досліджень і оцінити продуктивність використовуваних математичних методів.

Parallel online event calculus learning for complex event recognition

Logic-based event recognition systems infer occurrences of events in time using a set of event definitions in the form of first-order rules. The Event Calculus is a temporal logic that has been used as a basis in event recognition applications, providing, among others, direct connections to machine learning, via Inductive Logic Programming (ILP). OLED is a recently proposed ILP system that learns event definitions in the form of Event Calculus theories, in a single pass over a data stream. We present two strategies for parallel online learning with OLED. We evaluate our proposed approaches on three datasets from the domains of activity recognition and maritime surveillance and show that they can significantly reduce training times, while they are capable of achieving super-linear speed-ups under certain circumstances.