: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

A novel framework for anomaly detection in crowded scenes is presented. Three properties are identified as important for the design of a localized video representation suitable for anomaly detection in such scenes: 1) joint modeling of appearance and dynamics of the scene, and the abilities to detect 2) temporal, and 3) spatial abnormalities. The model for normal crowd behavior is based on mixtures of dynamic textures and outliers under this model are labeled as anomalies. Temporal anomalies are equated to events of low-probability, while spatial anomalies are handled using discriminant saliency. An experimental evaluation is conducted with a new dataset of crowded scenes, composed of 100 video sequences and five well defined abnormality categories. The proposed representation is shown to outperform various state of the art anomaly detection techniques.

/pdf/anomaly-detection-in-crowded-scenes-2ncde4zo7t.pdf

Anomaly detection in crowded scenes

Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training. We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work. The dataset is available at: http://crcv.ucf.edu/projects/real-world/

/pdf/real-world-anomaly-detection-in-surveillance-videos-4jb8p2a0v1.pdf

Real-World Anomaly Detection in Surveillance Videos

The distributed nature and dynamic topology of Wireless Sensor Networks (WSNs) introduces very special requirements in routing protocols that should be met. The most important feature of a routing protocol, in order to be efficient for WSNs, is the energy consumption and the extension of the network's lifetime. During the recent years, many energy efficient routing protocols have been proposed for WSNs. In this paper, energy efficient routing protocols are classified into four main schemes: Network Structure, Communication Model, Topology Based and Reliable Routing. The routing protocols belonging to the first category can be further classified as flat or hierarchical. The routing protocols belonging to the second category can be further classified as Query-based or Coherent and non-coherent-based or Negotiation-based. The routing protocols belonging to the third category can be further classified as Location-based or Mobile Agent-based. The routing protocols belonging to the fourth category can be further classified as QoS-based or Multipath-based. Then, an analytical survey on energy efficient routing protocols for WSNs is provided. In this paper, the classification initially proposed by Al-Karaki, is expanded, in order to enhance all the proposed papers since 2004 and to better describe which issues/operations in each protocol illustrate/enhance the energy-efficiency issues.

Energy-Efficient Routing Protocols in Wireless Sensor Networks: A Survey

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on Deep-Fakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

/pdf/faceforensics-learning-to-detect-manipulated-facial-images-535z96cczo.pdf

FaceForensics++: Learning to Detect Manipulated Facial Images

We present a novel framework for learning patterns of motion and sizes of objects in static camera surveillance. The proposed method provides a new higher-level layer to the traditional surveillance pipeline for anomalous event detection and scene model feedback. Pixel level probability density functions (pdfs) of appearance have been used for background modelling in the past, but modelling pixel level pdfs of object speed and size from the tracks is novel. Each pdf is modelled as a multivariate Gaussian mixture model (GMM) of the motion (destination location & transition time) and the size (width & height) parameters of the objects at that location. Output of the tracking module is used to perform unsupervised EM-based learning of every GMM. We have successfully used the proposed scene model to detect local as well as global anomalies in object tracks. We also show the use of this scene model to improve object detection through pixel-level parameter feedback of the minimum object size and background learning rate. Most object path modelling approaches first cluster the tracks into major paths in the scene, which can be a source of error. We avoid this by building local pdfs that capture a variety of tracks which are passing through them. Qualitative and quantitative analysis of actual surveillance videos proved the effectiveness of the proposed approach.

http://vision.eecs.ucf.edu/papers/cvpr2008/3.pdf

Learning object motion patterns for anomaly detection and improved object detection

The paper introduces an action recognition framework that uses concepts from the theory of chaotic systems to model and analyze nonlinear dynamics of human actions. Trajectories of reference joints are used as the representation of the non-linear dynamical system that is generating the action. Each trajectory is then used to reconstruct a phase space of appropriate dimension by employing a delay-embedding scheme. The properties of the reconstructed phase space are captured in terms of dynamical and metric invariants that include Lyapunov exponent, correlation integral and correlation dimension. Finally, the action is represented by a feature vector which is a combination of these invariants over all the reference trajectories. Our contributions in this paper include :1) investigation of the appropriateness of theory of chaotic systems for human action modelling and recognition, 2) a new set of features to characterize nonlinear dynamics of human actions, 3) experimental validation of the feasibility and potential merits of carrying out action recognition using methods from theory of chaotic systems.

https://crcv.ucf.edu/papers/SaadICCV07.pdf

Chaotic Invariants for Human Action Recognition

Content based video matching using spatiotemporal volumes

Wireless sensor network (WSN) gives the characteristics of an effective, feasible and fairly reliable monitoring system which shows promise for structural health monitoring (SHM) applications. Monitoring of civil structures generates a large amount of sensor data that is used for structural anomaly detection. Efficiently dealing with this large amount of data in a resource-constrained WSN is a challenge. This paper proposes a, WSN based, novel framework that triggers smart events from sensor data. These events are useful for both intelligent data recording and video camera control. The operation of this framework consists of active & passive sensing modes. In passive mode, selected nodes can intelligently interpret local sensor data to trigger appropriate events. In active mode, most of the sensing nodes perform high frequency sampling and record useful data. Unnecessary data is suppressed which improves the lifespan of the network and simplifies data management.

A framework for intelligent sensor network with video camera for structural health monitoring of bridges

Images can be manipulated for nefarious purposes to hide content or to duplicate certain objects through copy-move operations. Discovering a well-crafted copy-move forgery in images can be very challenging for both humans and machines; for example, an object on a uniform background can be replaced by an image patch of the same background. In this paper, we propose a Generative Adversarial Network with a dual-order attention model to detect and localize copy-move forgeries. In the generator, the first-order attention is designed to capture copy-move location information, and the second-order attention exploits more discriminative features for the patch co-occurrence. Both attention maps are extracted from the affinity matrix and are used to fuse location-aware and co-occurrence features for the final detection and localization branches of the network. The discriminator network is designed to further ensure more accurate localization results. To the best of our knowledge, we are the first to propose such a network architecture with the 1st-order attention mechanism from the affinity matrix. We have performed extensive experimental validation and our state-of-the-art results strongly demonstrate the efficacy of the proposed approach.

/pdf/doa-gan-dual-order-attentive-generative-adversarial-network-17zusubvbp.pdf

Arslan Basharat

Papers

Learning object motion patterns for anomaly detection and improved object detection

Chaotic Invariants for Human Action Recognition

Content based video matching using spatiotemporal volumes

A framework for intelligent sensor network with video camera for structural health monitoring of bridges

DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization