Kinds Of Anomalies Research Articles

A Novel Anomaly Detection for Streaming Data using LSTM Autoencoders

The high-volume and velocity data stream generated from devices and applications from different domains grows steadily and is valuable for big data research. One of the most important topics is anomaly detection for streaming data, which has attracted attention and investigation in plenty of areas, e.g., the sensor data anomaly detection, predictive maintenance, event detection. Those efforts could potentially avoid large amount of financial costs in the manufacture. However, different from traditional anomaly detection tasks, anomaly detection in streaming data is especially difficult due to that data arrives along with the time with latent distribution changes, so that a single stationary model doesn’t fit streaming data all the time. An anomaly could become normal during the data evolution, therefore it is necessary to maintain a dynamic system to adapt the changes. In this work, we propose a LSTMs-Autoencoder anomaly detection model for streaming data. This is a mini-batch based streaming processing approach. We experimented with streaming data that containing different kinds of anomalies as well as concept drifts, the results suggest that our model can sufficiently detect anomaly from data stream and update model timely to fit the latest data property.. Index Terms: About four key words or phrases in alphabetical order, separated by commas.

Excitation of plasmonic and photonic modes in metallic lamellar gratings

We study the optical properties of metallic lamellar gratings with sub-wavelength period as a function of the groove depth and width, in situations in which there is only one propagating order (order zero or specular). The reflected light is calculated with an integral equation method for periodic surfaces. Under p-polarized illumination, different kinds of anomalies are observed as the angle of incidence or the grating parameters are changed. These are due to the excitation of surface plasmon polaritons (SPPs) and their interaction with the plasmonic and photonic modes supported by the grating grooves. We find that the propagation constant of the SPPs supported by shallow gratings is affected by the presence of the corrugations. As the groove depth increases, the formation of an energy gap inhibits the excitation of SPPs. However, for grooves deeper than about half a wavelength, new resonances appear. These are due to the coupling of the SPP excitations with the photonic and plasmonic modes supported by the grating grooves.

Tensor-Based ECG Anomaly Detection toward Cardiac Monitoring in the Internet of Health Things.

Advanced heart monitors, especially those enabled by the Internet of Health Things (IoHT), provide a great opportunity for continuous collection of the electrocardiogram (ECG), which contains rich information about underlying cardiac conditions. Realizing the full potential of IoHT-enabled cardiac monitoring hinges, to a great extent, on the detection of disease-induced anomalies from collected ECGs. However, challenges exist in the current literature for IoHT-based cardiac monitoring: (1) Most existing methods are based on supervised learning, which requires both normal and abnormal samples for training. This is impractical as it is generally unknown when and what kind of anomalies will occur during cardiac monitoring. (2) Furthermore, it is difficult to leverage advanced machine learning approaches for information processing of 1D ECG signals, as most of them are designed for 2D images and higher-dimensional data. To address these challenges, a new sensor-based unsupervised framework is developed for IoHT-based cardiac monitoring. First, a high-dimensional tensor is generated from the multi-channel ECG signals through the Gramian Angular Difference Field (GADF). Then, multi-linear principal component analysis (MPCA) is employed to unfold the ECG tensor and delineate the disease-altered patterns. Obtained principal components are used as features for anomaly detection using machine learning models (e.g., deep support vector data description (deep SVDD)) as well as statistical control charts (e.g., Hotelling chart). The developed framework is evaluated and validated using real-world ECG datasets. Comparing to the state-of-the-art approaches, the developed framework with deep SVDD achieves superior performances in detecting abnormal ECG patterns induced by various types of cardiac disease, e.g., an F-score of 0.9771 is achieved for detecting atrial fibrillation, 0.9986 for detecting right bundle branch block, and 0.9550 for detecting ST-depression. Additionally, the developed framework with the T2 control chart facilitates personalized cycle-to-cycle monitoring with timely detected abnormal ECG patterns. The developed framework has a great potential to be implemented in IoHT-enabled cardiac monitoring and smart management of cardiac health.

A case of an acute coronary syndrome associated with anomalous origin of the left main coronary artery, with a right coronary sinus origin

We present a case whose left main coronary artery (LMCA) arose from the right sinus of Valsalva, which is a very rare congenital anomaly. In a 48-year-old male, coronary angiographic (CAG) examination revealed LMCA arising from the right sinus of Valsalva. Although this kind of anomaly has generally been accepted to have a benign course, it may cause sudden death. In this case report, we present a patient who was admitted to our clinic with Acute Coronary Syndrome (ACS) and was found to have LMCA originating from the right sinus of Valsalva in the CAG. A percutaneous coronary angioplasty was performed with stent placement in the critical stenosis in the left anterior descending (LAD) coronary artery.

Anomalies Detection Through Smartphone Sensors: A Review

With smartphones being so ubiquitous, more connected and largely fitted with several types of sensors such as GPS, microphones, cameras, magnetometers, accelerometers, etc; there is an increasing opportunity in the development of smartphone-based sensor systems. In this article, we propose a short survey on the use of smartphone sensors in the detection of various kinds of anomalies in several fields namely environment, agriculture, healthcare and road/traffic conditions. We also list the main advantages and limitations of the use of smartphone sensors systems in such fields.

Detection of data anomalies at the edge of pervasive IoT systems

Validation of input data is essential in any computer system, but perhaps particularly important in pervasive IoT systems such as smart homes, smart cars, wearable health monitors, etc. In such systems, actions taken based on invalid inputs could have severe consequences. In this paper, we present statistical techniques for identifying data anomalies at the gateway that connects an edge network to its associated cloud services. We address two kinds of anomalies in environmental sensor data: data bias anomalies and sensor cut-off anomalies. In simulation experiments, we evaluate the effectiveness of applying control charts, a statistical process monitoring technique, to both kinds of anomalies. Our results show that using control charts as statistical methods for anomaly detection in IoT systems not only provides high performance in terms of accuracy and power (probability of detecting the anomaly), but also offers a graphical tool to monitor the IoT sensor data.

Application of Improved Asynchronous Advantage Actor Critic Reinforcement Learning Model on Anomaly Detection.

Anomaly detection research was conducted traditionally using mathematical and statistical methods. This topic has been widely applied in many fields. Recently reinforcement learning has achieved exceptional successes in many areas such as the AlphaGo chess playing and video gaming etc. However, there were scarce researches applying reinforcement learning to the field of anomaly detection. This paper therefore aimed at proposing an adaptable asynchronous advantage actor-critic model of reinforcement learning to this field. The performances were evaluated and compared among classical machine learning and the generative adversarial model with variants. Basic principles of the related models were introduced firstly. Then problem definitions, modelling processes and testing were detailed. The proposed model differentiated the sequence and image from other anomalies by proposing appropriate neural networks of attention mechanism and convolutional network for the two kinds of anomalies, respectively. Finally, performances with classical models using public benchmark datasets (NSL-KDD, AWID and CICIDS-2017, DoHBrw-2020) were evaluated and compared. Experiments confirmed the effectiveness of the proposed model with the results indicating higher rewards and lower loss rates on the datasets during training and testing. The metrics of precision, recall rate and F1 score were higher than or at least comparable to the state-of-the-art models. We concluded the proposed model could outperform or at least achieve comparable results with the existing anomaly detection models.

Studies on the Seismic Behaviour of Setback Building

Setback is kind of anomaly (irregularity) which can inductee various kinds irregularities for example, mathematical, mass or firmness anomalies and this along vertical side. The current examination is restricted to fortified cement outlined structures intended for seismic burdens (DL, LL and EL). The seismic conduct of G+10, G+15, G+20 and G+25 structures with and without misfortunes were contemplated. The models we re examined utilizing Response Spectrum technique in ETABS. The impact of Setback is contemplated considering the boundaries, for example, storey displacements, storey floats & storey shears are correlated with the structure without a setback.

Critical zone of the branching crack model for earthquakes: Inherent randomness, earthquake predictability, and precursor modelling

The branching crack model for earthquakes was developed by Vere-Jones and Kagan in the 1970s and the 1980s, respectively. With some simple and rational assumptions, its simulation results explain the Gutenberg-Richter magnitude-frequency relationship and the Omori-Utsu aftershock decay formula. By introducing the concept of the critical zone, this model can be connected with the asperity model, the barrier model, and the nucleation model through a parameter – criticality. Particularly, the size of the critical zone determines the maximum magnitude of potential earthquakes and the source of their anomalies. The key to earthquake forecasting is to determine whether the concerned area is in a critical state and how large the critical zone is. We discuss what kinds of anomalies are meaningful as candidates of earthquake precursors. Finally, we outline modelling strategies for earthquake precursors with low probability gains that are due to the inherent randomness of earthquake source processes.

Adet Kanaması: Dört Kuşağın Bilgi ve Deneyimleri

Makale adet kanamasının farklı kuşak kadınlar tarafından nasıl deneyimlendiği, adet görme bilgisinin ve deneyiminin kadınlar arasında nasıl aktarıldığı/paylaşıldığı sorularını temel alarak dört kuşak aile üyesiyle yapılan derinlemesine mülakatlar etrafında şekilleniyor. Bu çalışma, büyük anneanne, anneanne, anne ve kız çocuğundan müteşekkil dört aile üyesinin deneyimin ifadeleri olarak adet görmeye yükledikleri sembolik anlamlara, bu konudaki bilgilerine, adet kanaması için kullandıkları maddi nesnelere ve adet kanaması esnasındaki pratiklerine odaklanıyor. Bilgi paylaşımının ve deneyim aktarımının genellikle anne-kız çocuğu arasında, iki kuşakla sınırlı olduğu aile üyelerinin adet kanamasını deneyimleri, mevcut erkek egemen kültür nedeniyle ortaklaşırken, dönemsel farklılıklar, kent yaşamı, eğitim seviyesi, modernleşme gibi faktörler nedeniyle birbirinden ayrılıyor. Normal bedenin adet görmeyen beden, daha doğrusu erkek bedeni olduğu kabulüyle inşa edilen adet görme adabı, kadınların adet kanamasını gizlemesini ve suskunlukla örtmesini temel alıyor. Bu kurallar aynı ailenin dört kuşak üyesi arasında kısmen farklılaşsa da paylaşılmaya devam ediyor.

Comparative Study of One-Class Based Anomaly Detection Techniques for a Bicomponent Mixing Machine Monitoring

One critical point to improve the economic and technical results of every industrial process lies on the fact of achieving a good optimization, and applying a smart maintenance plan. In this context, the tools development for detecting the appearance of any kind of anomaly represents an important challenge. For this reason, the implementation of classifiers for anomaly detection tasks has been a significant trend in the scientific community. However, since the behavior of the potential anomalies that may occur in a plant is unknown, it is necessary to generate artificial outliers to assess these classifiers. This paper proposes the performance checking of different intelligent one-class techniques to detect anomalies in an industrial plant, used to obtain the main material for wind generator blades production. These classifiers are tested using anomaly data generated, giving successful results.

Automatic recognition of plasma relevant events: Implications for ITER

This work makes a proposal about the use of big data techniques for the automatic recognition and classification of plasma relevant events in huge databases of nuclear fusion devices. A relevant event can be any kind of anomaly (or perturbation) in the plasma evolution. This is revealed in the temporal evolution signals as (typically) abrupt variations (for instance in amplitude, noise, or sudden presence/suppression of patterns with periodical structure). A general algorithm based on five steps is presented here for the automatic location and unsupervised classification of plasma events: dataset selection, location of anomalies in individual signals, definition of multi-signal patterns, unsupervised clustering of multi-signal patterns and creation of supervised classifiers. It is important to note that the algorithm implementation is for off-line analysis but supervised classifiers could be implemented under real-time conditions.

Cd2+ + Cr6+ causes toxic effects on chromosomal development of microspore in Carthamus tinctorius.

Intra-category hybrids of Carthamus tinctorius were analyzed for the genetic toxicity in detail for effect of Cd2+ + Cr6+ on reproductive biology of Carthamus tinctorius. Five partially tolerant and five non-tolerant accessions of Carthamus tinctorius after screening were crossed to produce intra-category hybrid. These two heavy metals in combination influenced antagonistically first as well as second meiotic divisions inducing various kinds of anomalies and reduced the number of pollen grains per anther and significantly increased pollen sterility. A differential response for the amount of meiotic irregularity was recorded between different treated sets of hybrids in (Cd + Cr) treated sets. This could be due to differential response of the genotypes for the same concentration of (Cd + Cr). These two heavy metals in combination reduced the number of pollen grains per anther and significantly increased pollen sterility.

Emulating topological currents arising from a dipolar parity anomaly in two-dimensional optical lattices

Dipolar parity anomaly can be induced by spatiotemporally weak-dependent energy-momentum separation of paired Dirac points in two-dimensional Dirac semimetals. Here we reveal topological currents arising from this kind of anomaly. A corresponding lattice model is proposed to emulate the topological currents by using two-component ultracold atoms in a two-dimensional optical Raman lattice. In our scheme, the topological currents can be generated by varying on-site coupling between the two atomic components in time and tuned via the laser fields. Moreover, we show that the topological particle currents can directly be detected from measuring the drift of the center of mass of the atomic gases.

Computerized categorization of TLD glow curve anomalies using multi-class classification support vector machines

A novel method for automatic categorization of thermoluminescent dosimeter (TLD) glow curve (GC) anomalies is presented. This automatic categorization will improve the metrological process of dose estimation by enhancing both its repeatability and its accuracy. Moreover, it will help external dosimetry laboratories to forecast some of the malfunctions of their TLD readers. A degenerated automatic approach was previously used in order to differentiate between a regular GC and an anomalous one, without being able to distinguish between different types of anomalies. That approach is now substantially extended to implicitly enable the categorization of GCs into five different kinds of anomalies. The machine learning algorithm applied for this purpose is support vector machines (SVM). The SVM algorithm categorizes TLD GCs into either a ‘good’ GC or into five types of TLD GC anomalies. When applied on an uncategorized GC, SVM associates it with a classification probability for each of the six categories. Results show an accuracy rate between 87.5% and 89% for the correct categorization of GCs to either of the six classes, depending on the presence of 'spikes' class in the data.

Hyperbolic Discounting and Its Consequences: Empirical Analysis on the Base of Surveys

During this cross-cultural research regarding time preferences the credibility of hyperbolic discounting model is examined. This paper is based on the comparison between the exponential discounting model and hyperbolic model and proposal of different modifications to the existing concepts. Different kind of anomalies, which bring up the necessity of the extension of the hyperbolic discounting model, are mentioned. This paper is aimed at exploring the discount model, the process of decisionmaking and the formation of the individuals’ subjective discount rate from the standpoint of behavioral economics by including in the model such psychological factors as cultural and economic environment and risk aversion. These supplements lead to more complex and credible discount model. The term of procrastination is considered as a direct implementation of hyperbolic discounting. Furthermore, the potential drawbacks occurred during the experimental part are highlighted and possible solutions are proposed. Empirical analysis is based on the surveys.

IMPROVEMENT OF DOSE ESTIMATION PROCESS USING ARTIFICIAL NEURAL NETWORKS.

We present here for the first time a fast and reliable automatic algorithm based on artificial neural networks for the anomaly detection of a thermoluminescence dosemeter (TLD) glow curves (GCs), and compare its performance with formerly developed support vector machine method. The GC shape of TLD depends on numerous physical parameters, which may significantly affect it. When integrated into a dosimetry laboratory, this automatic algorithm can classify 'anomalous' (having any kind of anomaly) GCs for manual review, and 'regular' (acceptable) GCs for automatic analysis. The new algorithm performance is then compared with two kinds of formerly developed support vector machine classifiers-regular and weighted ones-using three different metrics. Results show an impressive accuracy rate of 97% for TLD GCs that are correctly classified to either of the classes.

A Fuzzy Shape-Based Anomaly Detection and Its Application to Electromagnetic Data

The problem of data analytics in real-world electromagnetic (EM) applications poses a lot of algorithmic constraints. The process of big datasets, the requirement of prior knowledge, unknown location of anomalies, and variable length patterns are all issues that need to be addressed. In this application, we address those issues by proposing a fuzzy shape-based method with anomaly detection. This method is evaluated against 12 benchmark datasets of different kinds of anomalies and provides promising results based on the use of a new performance metric that takes into account the distance between the predicted and actual anomalies. Real-world EM data from the Earth's magnetic field are provided by the SWARM satellite constellation relating to regions in China, Greece and Peru. The seismic events that occurred in those regions are compared against the SWARM data. Moreover, three other methods: GrammarViz, HOT-SAX, and CUSUM-EWMA are also applied to further investigate the possible linkages of EM anomalies with seismic events. The findings further our understanding of real-world data analytics in EM data and seismicity. Some proposals regarding the limitations of available data for the real-world datasets are also presented.

Deep learning approaches for video-based anomalous activity detection

The pervasive use of cameras at indoor and outdoor premises on account of recording the activities has resulted into deluge of long video data. Such surveillance videos are characterized by single or multiple entities (persons, objects) performing sequential/concurrent activities. It is often interesting to detect suspicious behavior of such entities in an automated manner without any intervention of human personnel, and to this end, anomalous activity detection from surveillance videos is an important research domain in Computer Vision. Detecting the anomalous activities from videos is very challenging due to equivocal nature of anomalies, context at which events took place, lack of ample size of anomalous ground truth training data and also other factors associated with variation in environment conditions, illumination conditions and working status of capturing cameras. Though automated visual surveillance is one of the highly sought-after research domains, use of deep learning techniques for anomalous activity detection is still in nascent stage. Deep learning models like convolution neural networks, auto-encoders, Long Short Term Memory network models have achieved remarkable performance on different domains like image classification, object detection, speech processing, and expediting towards achieving excellence in anomaly detection tasks. This paper aims at studying and analyzing deep learning techniques for video-based anomalous activity detection. As outcome of the study, the graphical taxonomy has been put forth based on kinds of anomalies, level of anomaly detection, and anomaly measurement for anomalous activity detection. The focus has been given on various anomaly detection frameworks having deep learning techniques as their core methodology. Deep learning approaches from both the perspectives of accuracy oriented anomaly detection and real-time processing oriented anomaly detection are compared. This paper also sheds light upon research issues and challenges, application domains, benchmarked datasets and future directions in the domain of deep learning based anomaly detection.

Семантика для гиперклассической логики и проблема отрицания в формальном языке

The application of game-theoretic semantics for first-order logic is based on a certain kind of semantic assumptions, directly related to the asymmetry of the definition of truth and lies as the winning strategies of the Verifier (Abelard) and the Counterfeiter (Eloise). This asymmetry becomes apparent when applying GTS to IFL. The legitimacy of applying GTS when it is transferred to IFL is based on the adequacy of GTS for FOL. But this circumstance is not a reason to believe that one can hope for the same adequacy in the case of IFL. Then the question arises if GTS is a natural semantics for IFL. Apparently, the intuitive understanding of negation in natural language can be explicated in formal languages in various ways, and the result of an incomplete grasp of the concept in these languages can be considered a certain kind of anomalies, in view of the apparent simplicity of the explicated concept. Comparison of the theoretical-model and game theoretic semantics in application to two kinds of language – the first-order language and friendly-independent logic – allows to discover the causes of the anomaly and outline ways to overcome it.