Anomalous Events Research Articles

Immunological resilience of a temperate catshark to a simulated marine heat wave.

Marine heatwaves (MHW) have recently been proposed as more relevant in driving population changes than the continuous increase in average temperatures associated with climate change. The causal processes underpinning MHW effects in sharks are unclear but may be linked to changes in fitness caused by physiological trade-offs that influence the immune response. Considering the scarcity of data about the immune response of sharks under anomalous warming events, the present study analyzed several fitness indices and characterized the immune response (in the blood, epigonal organ, liver, spleen, and intestine) of temperate adult small-spotted catsharks (Scyliorhinus canicula) after a 30-day exposure to a Category II MHW. The results indicated that adult small-spotted catsharks have developed coping strategies for the MHW. Specifically, among the 35 parameters investigated, only the gonad-to-body ratio (GBR) and plasma glucose showed significant increases. In contrast, igm and tumor necrosis factor receptor (tnfr) gene expression in blood cells, tnfr in the epigonal organ, and the number of monocytes significantly decreased. Although a decline in immune function in small-spotted catsharks was revealed following the MHW exposure, energy mobilization restored homeostasis and indicated a shift in energy allocation towards reproduction. Group resilience may be due to the variable tolerance of individuals, the phenotypic plasticity of cellular immunity, thermal imprinting, and/or metabolic capacity of the individuals.

A signal processing system for infrasound-based detection and tracking of tornadoes

It has been established that tornadic storms emit infrasound at infrasonic frequencies and that this sound can be detected from practically significant distances exceeding 100 km in some cases. This work describes a signal processing system that is used to ingest data from a network of infrasound arrays and produce near real-time detections and ground tracks of multiple, simultaneously active tornadic storms. Specifically, a brief review of a particular array network and corresponding hardware is presented followed by detailed descriptions of the array signal processing architecture and source geolocation system. Emphasis is placed on algorithms for multiple moving source acoustic source bearing tracking, low SNR signal detection, mitigation of errors created by anomalous acoustic events, and multiple-array data association. Performance results corresponding to simulated and recorded data are presented.

Dynamic localization of unwanted events with machine learning-based method

In environmental acoustics measurements it is necessary to separate the contribution of the investigated source from the residual noise, by means of ambient noise measurements. Source separation is a complex task, especially for wind turbine noise, where long-term measurement campaigns are required. Although data analysis procedures that provide for this task are already in use, all of them require a preliminary step for anomalous events removal, i.e. events which are not characteristic of standard residual noise. This step can be complex and very time-expensive depending on the duration of the measurements and the measurement site. Depending on the specific site and source under evaluation, the variety of sounds that can be considered as unwanted for compliance with environmental acoustic regulations is heterogeneous, ranging from road vehicles, trains and planes to human and animal sounds and more. Nowadays, it is possible to extrapolate from an audio source the features that describe its semantics using machine learning. The approach presented in this paper aims to localize in time a specific event within a measurement containing several acoustic events, in order to label it and then proceed to remove the spurious events from the measurement.

Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos.

Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system that has multiple contributions including a random batch selection mechanism to reduce interbatch correlation and a normalcy suppression block (NSB) which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block (CLB) is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. An extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate the superior anomaly detection capability of our approach.

Towards a new generation of fluvial facies models for the interpretation of ancient deposits, based on inter‐annual peak discharge variance of modern rivers

ABSTRACTFluvial facies models based on river planform are flawed and not fully fit for purpose. An alternative approach to classifying fluvial deposits is based on river discharge characteristics. A recent paper showed that the co‐efficient of variance of annual peak discharge (CVQp) correlates well with the characteristics of preserved alluvium for a suite of modern rivers. Here, the database of rivers is expanded and augmented, and the utility of this statistic confirmed. For modern rivers, plotting the running‐value of CVQp for a set interval (for example, 30 years) over a longer discharge record shows that the statistic varies both spatially and temporally. The CVQp can rise abruptly at a given location in response to a single flow event if that event is significantly larger than is common in that river. Such abrupt changes in CVQp are superimposed on longer‐term patterns of more gradual change stimulated by environmental factors or anthropogenic effects such as dam construction. If the period of calculation for CVQp is relatively short, ‘anomalous’ events appear more frequently. Sequential studies of modern rivers indicate that such anomalous events have a high probability of being preserved in the alluvial record of the river, and suggest that, over the timeframes of channel filling and abandonment, they may constitute the dominant (characteristic) portion of the record in high CVQp systems. Since flow events with strongly peaked hydrographs (flashy discharges) are more common in high CVQp systems and leave a record dominated by upper flow regime stratification styles, it follows that the alluvial record of high CVQp rivers will be dominated by upper flow regime stratification. In contrast, in lower CVQp systems the occurrence of an event that changes the running CVQp value significantly may form a distinct event deposit, and the temporarily changed CVQp is unrepresentative for the duration of the channel's life. The dominance of upper flow regime stratification, together with decreased preservation of identifiable macroform structure, increased lateral lithological heterogeneity, and in many cases increased preservation of in situ tree fossils in channel deposits of higher CVQp rivers, forms the basis for a series of new facies models for low, moderate, high and very high/ultra‐high CVQp alluvial systems and deposits. The new models can be applied to ancient successions either in combination with traditional, planform‐based models, or not. These models provide information about ancient palaeoenvironmental conditions, and changes in such conditions over time at various scales via stratigraphic investigations.

The Attribution of February Extremes over North America: A Forecast-Based Storyline Study

Abstract The importance of extreme event attribution rises as climate change causes severe damage to populations resulting from unprecedented events. In February 2019, a planetary wave shifted along the U.S.–Canadian border, simultaneously leading to troughing with anomalous cold events and ridging over Alaska and northern Canada with abnormal warm events. Also, a dry-stabilized anticyclonic circulation over low latitudes induced warm extreme events over Mexico and Florida. Most attribution studies compare the climate model simulations under natural or actual forcing conditions and assess probabilistically from a climatological point of view. However, in this study, we use multiple ensembles from an operational forecast model, promising statistical as well as dynamically constrained attribution assessment, often referred to as the storyline approach to extreme event attribution. In the globally averaged results, increasing CO2 concentrations lead to distinct warming signals at the surface, resulting mainly from diabatic heating. Our study finds that CO2-induced warming eventually affects the possibility of extreme events in North America, quantifying the impact of anthropogenic forcing over less than a week’s forecast simulation. Our study assesses the validity of the storyline approach conditional on the forecast lead times, which is hindered by rising noise in CO2 signals and the declining performance of the forecast model. The forecast-based storyline approach is valid for at least half of the land area within a 6-day lead time before the target extreme occurrence. Our attribution results highlight the importance of achieving net-zero emissions ahead of schedule to reduce the occurrence of severe heatwaves.

Multimodal and multiscale feature fusion for weakly supervised video anomaly detection

Weakly supervised video anomaly detection aims to detect anomalous events with only video-level labels. In the absence of boundary information for anomaly segments, most existing methods rely on multiple instance learning. In these approaches, the predictions for unlabeled video snippets are guided by the classification of labeled untrimmed videos. However, these methods do not account for issues such as video blur and visual occlusion, which can hinder accurate anomaly detection. To address these issues, we propose a novel weakly supervised video anomaly detection method that fuses multimodal and multiscale features. Firstly, RGB and optical flow snippets are input into pre-trained I3D to extract appearance and motion features. Then, we introduce an Attention De-redundancy (AD) module, which employs an attention mechanism to filter out task-irrelevant redundancy in these appearance and motion features. Next, to mitigate the effects of video blurring and visual occlusion, we propose a Multi-scale Feature Learning module. This module captures long-term and short-term temporal dependencies among video snippets to provide global and local guidance for blurred or occluded video snippets. Finally, to effectively utilize the discriminative features of different modalities, we propose an Adaptive Feature Fusion module. This module adaptively fuses appearance and motion features based on their respective feature weights. Extensive experimental results demonstrate that our proposed method outperforms mainstream unsupervised and weakly supervised methods in terms of AUC. Specifically, our proposed method achieves 97.00% AUC and 85.31% AUC on two benchmark datasets, i.e., ShanghaiTech and UCF-Crime, respectively.

Enhancing hotel efficiency and environmental health with biosensors and big data analytics

The hospitality industry embraces digital technologies to enhance efficiency, guest satisfaction, and environmental sustainability. Integrating biosensors and big data analytics allows hotels to monitor operational processes while maintaining high ecological health standards. However, the impact on environmental health is not fully understood, leading to suboptimal decisions and missed opportunities. This research proposes a novel Tabu Search Drove-Extended Multi-Layer Perceptron (TSD-EMLP) to evaluate the effectiveness of digital operations in hotels through the use of biosensors and big data for predicting hotel environmental conditions. Initially, smart biosensors are deployed in key areas and heating, ventilation, and air conditioning denoted as HVAC systems in the hotel, then the water quality data, noise levels, lighting quality, waste management data, operational data, financial and operational effectiveness data are collected and transmitted to the Internet of Things (IoT) cloud for further process. Interquartile Range (IQR) utilizes the IoT cloud data to remove sensor errors and anomalous events to frame outlier data for the Wavelet Packet Transform (WPT) feature extraction process to decompose sensor data into detailed frequency bands, allowing for precise analysis of complex environmental signals, TSD-EMLP model predicts the environmental health in hotels using the decomposed data. The results demonstrate reducing energy consumption, ventilation systems, indoor environment control, and guest satisfaction, improving air quality, and adjusting environmental settings based on real-time environmental conditions through TSD-EMLP optimized settings. TSD-EMLP classification model achieved high accuracy in predicting hotel environmental health, with a low improvement in guest satisfaction metrics.

Distilling Privileged Knowledge for Anomalous Event Detection From Weakly Labeled Videos.

Weakly supervised video anomaly detection (WS-VAD) aims to identify the snippets involving anomalous events in long untrimmed videos, with solely text video-level binary labels. A typical paradigm among the existing text WS-VAD methods is to employ multiple modalities as inputs, e.g., RGB, optical flow, and audio, as they can provide sufficient discriminative clues that are robust to the diverse, complicated real-world scenes. However, such a pipeline has high reliance on the availability of multiple modalities and is computationally expensive and storage demanding in processing long sequences, which limits its use in some applications. To address this dilemma, we propose a privileged knowledge distillation (KD) framework dedicated to the WS-VAD task, which can maintain the benefits of exploiting additional modalities, while avoiding the need for using multimodal data in the inference phase. We argue that the performance of the privileged KD framework mainly depends on two factors: 1) the effectiveness of the multimodal teacher network and 2) the completeness of the useful information transfer. To obtain a reliable teacher network, we propose a text cross-modal interactive learning strategy and an anomaly normal discrimination loss, which target learning task-specific cross-modal features and encourage the separability of anomalous and normal representations, respectively. Furthermore, we design both representation- and text logits-level distillation loss functions, which force the unimodal student network to distill abundant privileged knowledge from the text well-trained multimodal teacher network, in a snippet-to-video fashion. Extensive experimental results on three public benchmarks demonstrate that the proposed privileged KD framework can train a lightweight yet effective detector, for localizing anomaly events under the supervision of video-level annotations.

Prediction of Physico-Chemical Parameters of Surface Waters Using Autoregressive Moving Average Models: A Case Study of Kis-Balaton Water Protection System, Hungary

In this work, the authors provide a case study of time series regression techniques for water quality forecasting. With the constant striving to achieve the Sustainable Development Goals (SDG), the need for sensitive and reliable water management tools has become critical. Continuous online surface water quality monitoring systems that record time series data about surface water parameters are essential for the supervision of water conditions and proper water management practices. The time series data obtained from these systems can be used to develop mathematical models for the prediction of the temporal evolution of water quality parameters. Using these mathematical models, predictions can be made about future trends in water quality to pinpoint irregular behaviours in measured data and identify the presence of anomalous events. We compared the performance of regression models with different structures for the forecasting of water parameters by utilizing a data set collected from the Kis-Balaton Water Protection System (KBWPS) wetland region of Hungary over an observation period of eleven months as a case study. In our study, autoregressive integrated moving average (ARIMA) regression models with different structures have been compared based on forecasting performance. Using the resulting models, trends of the oxygen saturation, pH level, electrical conductivity, and redox potential of the water could be accurately forecast (validation data residual standard deviation between 0.09 and 20.8) while in the case of turbidity, only averages of future values could be predicted (validation data residual standard deviation of 56.3).

How Can We Teach When We Are Constantly Learning? De/Colonising Canadian Literature in Grade Seven English Language Arts

ABSTRACT In this paper, I explore the transitional spaces of teaching and writing by restorying an anomalous event in my teaching of Canadian literature in a grade seven classroom and my efforts to decolonise that teaching. Thinking with Elizabeth Ellsworth’s concept of pedagogy as it relates to knowledge in the making and the learning self, I take seriously the manner in which this pedagogy challenges the cultural myth of teacher as expert identified by Deborah Britzman. In my story of de/colonising teaching, a transitional space opens up when I become aware of the ways in which I work against the goals of decolonising in my very efforts towards them, the risks I take, and the damage I can do as I implicate myself and my students in this process. As I teach and as I write, I build from the ruins of this difficult knowledge what it means to de/colonise as an educator.

Anomalous events in the TUS orbital detector data

The main goal of the TUS experiment was to search for and study ultra high-energy cosmic rays with energies E > 70 EeV. At the same time, the TUS detector registered a number of unusual events, the origin of which was unclear. Events that are unique and not similar to EAS are the subject of the study presented in this paper. Events such as gamma-ray bursts (GRBs), out-of-aperture upward going EASs accompanied by lightning flashes, as well as terrestrial gamma-ray flashes (TGFs) are considered as their possible sources.

Moisture Transport during Anomalous Climate Events in the La Plata Basin

This paper examines the linear relationship between climate events in the La Plata Basin (LP) from 1980 to 2018 and atmospheric moisture transport from major sources using a Lagrangian approach. The standardized precipitation evapotranspiration index (SPEI-1) was utilized to assess climate events, as monthly water balance variations may be related to changes in atmospheric moisture transport. A total of 49 dry and 46 wet events were identified through sequences of negative and positive SPEI-1 values, respectively. Lagrangian analysis tracked changes in moisture uptake and supply from sources to the LP during these events. Simple linear regression analysis revealed a relationship between moisture transport from the Amazonas (AM), North Atlantic (NA), and Tocantins (TO) basins and the severity and duration of climate events. Increased moisture supply from the São Francisco basin (SF) and Eastern Brazil oceanic (EBO) sources intensified the duration and severity of wet events. Peak wet events were linked to increased moisture supply from the northern South America basins (AM, NA, and TO), while peak droughts were related to decreased moisture uptake from eastern sources (TO, SF, and EBO). Our findings highlight how the water balance in distant regions affects the LP via moisture transport, emphasizing the need for interconnected adaptive strategies.

FILO: Automated FIx-LOcus Identification for Android Framework Compatibility Issues

Keeping up with the fast evolution of mobile operating systems is challenging for developers, who have to frequently adapt their apps to the upgrades and behavioral changes of the underlying API framework. Those changes often break backward compatibility. The consequence is that apps, if not updated, may misbehave and suffer unexpected crashes if executed within an evolved environment. Being able to quickly identify the portion of the app that should be modified to provide compatibility with new API versions can be challenging. To facilitate the debugging activities of problems caused by backward incompatible upgrades of the operating system, this paper presents FILO, a technique that is able to recommend the method that should be modified to implement the fix by analyzing a single failing execution. FILO can also provide additional information and key symptomatic anomalous events that can help developers understand the reason for the failure, therefore facilitating the implementation of the fix. We evaluated FILO against 18 real compatibility problems related to Android upgrades and compared it with Spectrum-Based Localization approaches. Results show that FILO is able to efficiently and effectively identify the fix-locus in the apps.

Rapid detection of rare events from in situX-ray diffraction data using machine learning.

High-energy X-ray diffraction methods can non-destructively map the 3D microstructure and associated attributes of metallic polycrystalline engineering materials in their bulk form. These methods are often combined with external stimuli such as thermo-mechanical loading to take snapshots of the evolving microstructure and attributes over time. However, the extreme data volumes and the high costs of traditional data acquisition and reduction approaches pose a barrier to quickly extracting actionable insights and improving the temporal resolution of these snapshots. This article presents a fully automated technique capable of rapidly detecting the onset of plasticity in high-energy X-ray microscopy data. The technique is computationally faster by at least 50 times than the traditional approaches and works for data sets that are up to nine times sparser than a full data set. This new technique leverages self-supervised image representation learning and clustering to transform massive data sets into compact, semantic-rich representations of visually salient characteristics (e.g. peak shapes). These characteristics can rapidly indicate anomalous events, such as changes in diffraction peak shapes. It is anticipated that this technique will provide just-in-time actionable information to drive smarter experiments that effectively deploy multi-modal X-ray diffraction methods spanning many decades of length scales.

Event-driven weakly supervised video anomaly detection

Inspired by the observations of human working manners, this work proposes an event-driven method for weakly supervised video anomaly detection. Complementary to the conventional snippet-level anomaly detection, this work designs an event analysis module to predict the event-level anomaly scores as well. It first generates event proposals simply via a temporal sliding window and then constructs a cascaded causal transformer to capture temporal dependencies for potential events of varying durations. Moreover, a dual-memory augmented self-attention scheme is also designed to capture global semantic dependencies for event feature enhancement. The network is learned with a standard multiple instance learning (MIL) loss, together with normal-abnormal contrastive learning losses. During inference, the snippet- and event-level anomaly scores are fused for anomaly detection. Experiments show that the event-level analysis helps to detect anomalous events more continuously and precisely. The performance of the proposed method on three public datasets demonstrates that the proposed approach is competitive with state-of-the-art methods.

METAZOAN PARASITE COMMUNITY OF THE YELLOW SNAPPER LUTJANUS ARGENTIVENTRIS: FACTORS THAT INFLUENCING SPECIES COMPOSITION AND RICHNESS.

A total of 366 individuals of Lutjanus argentiventris (Peters, 1869) were collected over a 5-yr period (October 2018 to June 2022) from Acapulco Bay, Mexico. Parasite communities in Lutjanus argentiventris were quantified and analyzed to determine the main factors that generate changes in species richness and/or species composition over time. The digeneans and copepods were the best-represented parasite groups. The parasite communities were characterized by a high numerical dominance of ectoparasites, mainly isopod larvae. Species richness at the component community level (9-23 species) was similar to the reported richness in other Lutjanus spp. The parasite communities of Lutjanus argentiventris exhibited high variability in species composition, suggesting that each parasite species may respond differently to environmental changes. However, the species richness and diversity were fairly stable over time; therefore, a clear pattern of interannual variation was not observed. Variations in the community structure probably were due to factors such as host traits (e.g., feeding behavior and body size), and possible interannual differences in environmental factors amplified by the occurrence of the anomalous event of La Niña.

The Subseasonal Feedback of Extreme Anomalous Tibetan Plateau Snow Cover Events on the Atmosphere

Abstract The Tibetan Plateau snow cover exhibits notable subseasonal variability and plays a crucial role in influencing the atmosphere. This study employs numerical experiments to investigate the atmospheric feedback resulting from extreme anomalous snow cover events on the Tibetan Plateau, with a focus on both local and nonlocal atmospheric temperatures. The findings reveal that diabatic heating, directly induced by these events, leads to a local surface energy cooling response over the Tibetan Plateau, contributing to a reduction in local temperatures. This cooling effect amplifies local atmospheric temperature anomalies associated with extreme anomalous Tibetan Plateau snow cover events, constituting approximately 50% of the total final local surface air temperature anomalies. Furthermore, the Tibetan Plateau snow cover, through adiabatic processes, exerts a nonlocal influence on atmospheric temperature and circulation. The atmospheric temperature responses downstream of the Tibetan Plateau vary at different heights and regions, featuring both cold and warm anomaly responses. These variations depend on the relative contributions of horizontal advection and vertical advection in adiabatic heating. Significance Statement Snow cover is influenced by the atmosphere, and in turn, it affects the atmosphere. This study examines the feedback of extreme anomalous Tibetan Plateau snow cover events on the atmosphere at the subseasonal time scale, with a focus on atmospheric temperature. Our findings indicate that Tibetan Plateau snow cover has both local and nonlocal feedback effects on the atmosphere. In particular, extreme anomalous Tibetan Plateau snow cover amplifies local surface air temperature anomalies. The feedback contributes to approximately 50% of the total final local surface air temperature anomalies.

Censorship data-driven DNS resolution anomaly detection: An ensemble algorithm model with multivariate feature fusion

The Domain Name System (DNS), as a critical component of Internet infrastructure, is crucial for maintaining network stability and security. However, vulnerabilities in the DNS resolution process make it susceptible to various network attacks. Current DNS resolution anomaly detection methods are challenged by the scarcity of diverse anomalous sample data and the difficulty in accurately capturing such anomalies. To address those challenges, we firstly introduce a proactive anomaly detection method based on bidirectional national censorship behavior, abbreviated as CB-BiDAM. This method can collect diverse anomalous resolution data from multiple network spaces, covering common types of resolution anomalies and effectively solving the problem of sample scarcity. Further, we extract multidimensional features from four key aspects: response content, DNS attributes, resolution paths, and timing, to gain a deeper understanding of the relationship between multifaceted information in the DNS resolution process and anomalous events. Finally, based on these multidimensional features, we construct a DNS resolution anomaly detection model named DRADC, using a stacked ensemble approach. Through a series of comparative experiments, the DRADC model significantly outperforms existing machine learning algorithms in key metrics such as accuracy (97.48%), recall (96.87%), and F1 score (97.09%). Feature ablation experiments further demonstrates that incorporating multidimensional features significantly improves model performance, with a 3% increase in accuracy and a 3.5% increase in precision compared to models relying solely on response content features. By providing an accurate detection model for DNS resolution anomalies, this study aids network administrators in more effectively identifying and countering network attacks. Additionally, our research also contributes to the detection and response to domain censorship mechanisms, which is crucial for maintaining the openness and free flow of the Internet.

Acoustic Emission Detection in Noisy Environments using Linear Prediction

In non-destructive testing, acoustic emission testing is an established technique with numerous applications in academia and the industry. In nearly all applications, the detection of relevant acoustic emission signals in continuous structure-borne sound recordings is a crucial step that forms the basis for subsequent analyses and should therefore neither miss any relevant acoustic emissions nor detect too many irrelevant events. That is because, in its most prevalent form, acoustic emission testing utilizes ultrasound signals that require large amount of storage, which might be an economically limiting factor especially for structural health monitoring of large civil infrastructures. In these monitoring applications, the signal-to-noise ratio is also expected to be worse compared to more controlled laboratory conditions, as they can be often found, for example, in materials research. We therefore propose the use of linear prediction, a time series forecasting technique, to extract relevant acoustic emissions from continuous recordings. The proposed methodology utilizes the residual between the signal predicted from a linear combination of previous time steps and the actual measurement to detect any anomalous events. Since the linear predictor can be initialized using the environmental noise only, no specific knowledge of the acoustic emission signals of interest is required beforehand and hence can automatically adapt to each measurement environment. We compare our approach with a simple amplitude-based detection as it is commonly implemented in commercially available acoustic emission systems. Especially for low signal-to-noise ratios, an increase in the area under the receiver operating characteristic curve of up to 0.7 compared to the amplitude-based detection is found.