Anomalous Event Recognition in Videos Based on Joint Learning of Motion and Appearance with Multiple Ranking Measures

Given the scarcity of annotated datasets, learning the context-dependency of anomalous events as well as mitigating false alarms represent challenges in the task of anomalous activity detection. We propose a framework, Deep-network with Multiple Ranking Measures (DMRMs), which addresses context-dependency using a joint learning technique for motion and appearance features. In DMRMs, the spatial-time-dependent features are extracted from a video using a 3D residual network (ResNet), and deep motion features are extracted by integrating the motion flow maps’ information with the 3D ResNet. Afterward, the extracted features are fused for joint learning. This data fusion is then passed through a deep neural network for deep multiple instance learning (DMIL) to learn the context-dependency in a weakly-supervised manner using the proposed multiple ranking measures (MRMs). These MRMs consider multiple measures of false alarms, and the network is trained with both normal and anomalous events, thus lowering the false alarm rate. Meanwhile, in the inference phase, the network predicts each frame’s abnormality score along with the localization of moving objects using motion flow maps. A higher abnormality score indicates the presence of an anomalous event. Experimental results on two recent and challenging datasets demonstrate that our proposed framework improves the area under the curve (AUC) score by 6.5% compared to the state-of-the-art method on the UCF-Crime dataset and shows AUC of 68.5% on the ShanghaiTech dataset.

Music Theory’s Therapeutic Imperative and the Tyranny of the Normal

Traditional music theory rationalizes abnormal musical elements (like dissonant or chromatic tones or formal anomalies) with respect to normal ones. It is thus allied with a medical model of disability, understood as a deficit or defect located within an individual body, and requiring remediation or cure. A newer sociocultural model of disability understands it as a culturally stigmatized deviance from normative standards for bodily appearance and functioning, analogous to (and intersectional with) race, gender, and sexuality as a source of affirmative political and cultural identity. The sociocultural model of disability suggests the possibility of a disablist music theory, one that subverts the traditional therapeutic imperative and resists the tyranny of the normal. Disablist music theory is music theory without norms, and without a commitment to wholeness, unity, coherence, and completeness—those fantasies of a normal, healthy body. Instead, disablist theory brings the seemingly anomalous event to the center of the discussion and revels in the commotion and discombobulation that result: it makes the normal strange. In the process, it opens up our sense of what music theory is and might be.

Understanding changes in environmental time series with time-frequency causality analysis

<p>Understanding causal effect relationships between the different variables in dynamical systems is an important and challenging problem in different areas of research such as attribution of climate change, brain neural connectivity analysis, psychology, among many others. These relationships are guided by the process generating them. Hence, detecting changes or new patterns in the causal effect relationships can be used not only for the detection but also for the diagnosis and attribution of changes in the underlying process.</p><p>Time series of environmental time series most often contain multiple periodical components, e.g. daily and seasonal cycles, induced by the meteorological forcing variables. This can significantly mask the underlying endogenous causality structure when using time-domain analysis and therefore results in several spurious links. Filtering these periodic components as preprocessing step might degrade causal inference. This motivates the use of time-frequency processing techniques such as Wavelet or short-time Fourier transform where the causality structure can be examined at each frequency component and on multiple time scales.</p><p>In this study, we use a parametric time-frequency representation of vector autoregressive Granger causality for causal inference. We first show that causal inference using time-frequency domain analysis outperforms time-domain analysis when dealing with time series that contain periodic components, trends, or noise. The proposed approach allows for the estimation of the causal effect interaction between each pair of variables in the system on multiple time scales and hence for excluding links that result from periodic components.</p><p>Second, we investigate whether anomalous events can be identified based on the observed changes in causal relationships. We consider two representative examples in environmental systems: land-atmosphere ecosystem and marine climate. Through these two examples, we show that an anomalous event can indeed be identified as the event where the causal intensities differ according to a distance measure from the average causal intensities. Two different methods are used for testing the statistical significance of the causal-effect intensity at each frequency component.</p><p>Once the anomalous event is detected, the driver of the event can be identified based on the analysis of changes in the obtained causal effect relationships during the time duration of the event and consequently provide an explanation of the detected anomalous event. Current research efforts are directed towards the extension of this work by using nonlinear state-space models, both statistical and deep learning-based ones.</p>

The Reliability Model of Artificial Monitoring on the Anomalous Event in Expressway Tunnels and Monte Carlo Simulation

Artificial monitoring remains to be a major way to detect anomalous events in expressway tunnels. To estimate the reliability of artificial monitoring on anomalous events in expressway tunnels, the video surveillance and mobile inspection based reliability models of artificial monitoring on the anomalous event in the expressway tunnel were built, and Monte Carlo method was applied to calculate the probability and mean time to detect the anomalous event at the specific time. The results showed that the Monte Carlo method could simulate video surveillance and mobile inspection, and obtain the probability distribution and mean time of detecting anomalous events. The mean time to spot the anomalous event was in reverse relation with the number of inspectors, the time of mobile inspection, and the reliability probability of the monitoring pre-warning system in tunnels and was in positive relationships with the departure interval. Combined with the actual operation cost, the model serves as a basis for the artificial monitoring package.

Anomalies Detection and Proactive Defence of Routers Based on Multiple Information Learning

Routers are of great importance in the network that forward the data among the communication devices. If an attack attempts to intercept the information or make the network paralyzed, it can launch an attack towards the router and realize the suspicious goal. Therefore, protecting router security has great importance. However, router systems are notoriously difficult to understand or diagnose for their inaccessibility and heterogeneity. A common way of gaining access to the router system and detecting the anomaly behaviors is to inspect the router syslogs or monitor the packets of information flowing to the routers. These approaches just diagnose the routers from one aspect but do not correlate multiple logs. In this paper, we propose an approach to detect the anomalies and faults of the routers with multiple information learning. First, we do the offline learning to transform the benign or corrupted user actions into the syslogs. Then, we construct the log correlation among different events. During the detection phase, we calculate the distance between the event and the cluster to decide if it is an anomalous event and we use the attack chain to predict the potential threat. We applied our approach in a university network which contains Huawei, Cisco and Dlink routers for three months. We aligned our experiment with former work as a baseline for comparison. Our approach obtained 89.6% accuracy in detecting the attacks, which is 5.1% higher than the former work. The results show that our approach performs in limited time as well as memory usages and has high detection and low false positives.