The Unscented Kalman Filter (UKF) stands out as a versatile and dynamic algorithm, celebrated for its prowess in estimating the states of nonlinear dynamical systems within uncertain environments. However, the accuracy of UKF state estimations hinges significantly on the thoughtful selection of pivotal hyperparameters, $\alpha, \beta$, and $\kappa$, which are integral in shaping the distribution of sigma points around the current state estimate. Prevailing methods for tuning these parameters encompass heuristic approaches such as arbitrarily fix $\alpha$ at 0.001, $\kappa$ at 0, and $\beta$ at 2 for Gaussian noise, though the efficacy of such rules heavily hinges on the intricacies of the specific problem. Alternatively, the grid search technique seeks to optimize these hyperparameters, but it can become computationally burdensome, particularly when the search space is extensive and intricate. To navigate these hurdles, this paper introduces the RNN-UKF algorithm-a pioneering strategy that leverages recurrent neural networks (RNNs) to autonomously fine-tune UKF hyperparameters. The inherent adaptability of RNNs is harnessed to dynamically adjust the $\alpha, \beta$, and $\kappa$ parameters of the unscented transformation during each state estimation step, all aimed at minimizing the root mean squared error (RMSE). Demonstrated through numerical simulations, we provide compelling evidence that the RNN-UKF approach outperforms both heuristic rule of thumb and grid search techniques in terms of RMSE performance. Moreover, the RNN-UKF methodology showcases its superiority over the conventional extended Kalman filter (EKF) approach, particularly in scenarios characterized by substantial system noise.

This paper presents an eXplainable Deep Reinforcement Learning (XDRL) based strategy for solving the proposed problem of fleet-level aircraft maintenance scheduling (AMS) optimization. The XDRL-AMS considers various factors such as the aircraft’s initial status, mission requirements, maintenance resource capacity, and operational constraints to create a maintenance schedule for a specified period. The schedule aims to balance both mission readiness and cost reduction. We developed an RL environment, called AMS-Gym, using the OpenAI Gym toolkit specifically designed for this problem. AMS-Gym is highly flexible, allowing for easy extension to more complex scenarios and incorporating additional explanatory capabilities. The explainable RL capability was achieved by utilizing a decomposed reward Deep Q-Network (drDQN) algorithm. In the context of the AMS scenario, the drDQN consists of two parts: (i) a DQN that aims to maximize the mission accomplishment objective, and (ii) a DQN that aims to minimize the maintenance cost objective. As a result, the proposed drDQN strategy can generate real-time aircraft maintenance decisions, explain why those decisions were selected, and present the tradeoffs between the chosen action and non-selected alternatives. Experiment results show that the proposed drDQN performs well, providing an approximate solution to the vanilla DQN with a simpler structure while offering the ability to explain its decisions. In addition, a web-based prototype with an intuitive textual and visual user interface was developed to demonstrate the feasibility of the drDQN approach.

3D sensors such as LiDAR, stereo cameras, and radar have been used in many applications, for instance, virtual or augmented reality, real-time immersive communications, and autonomous driving systems. The output of 3D sensors is often represented in the form of point clouds. However, the massive amount of point cloud data generated from 3D sensors poses big challenges in data storage and transmission. Therefore, effective compression schemes are needed for reducing the bandwidth of wireless networks or storage space of 3D point cloud data. Several point cloud compression (PCC) algorithms have been proposed using signal processing or neural network techniques. In this study, we investigate four state-of-the-art PCC methods using two different datasets with various configurations. The objective of this study is to provide a comprehensive understanding of various approaches in PCC. The results of this paper will be helpful in developing an adaptive 3D point cloud stream compression benchmark that is efficient and benefited from different PCC techniques.

In this paper, we developed a pattern discovery and anomaly detection system using a knowledge graph constructed by integrating data from heterogeneous sources. Specifically, the knowledge graph is constructed based on data extracted from structured and unstructured sources. Besides the extracted entities and relations, the knowledge graph finds hidden relations via link prediction algorithms. Based on the constructed knowledge graph, the normalcy model for entity, action, and triplets are established. The information of the incoming streaming data is extracted and compared to the normalcy model in order to detect abnormal behaviors. In addition, we apply the lambda framework to enable a computationally scalable algorithm for pattern discovery and anomaly detection in a big data environment. Real time tweets data are used for evaluation and preliminary results show promising performance in detecting abnormal pattern and activities.

A typical method to obtain valuable information is to extract the sentiment or opinion from a message. Machine learning technologies are widely used in sentiment classification because of their ability to “learn” from the training dataset to predict or support decision making with relatively high accuracy. However, when the dataset is large, some algorithms might not scale up well. In this paper, we aim to evaluate the scalability of Naïve Bayes classifier (NBC) in large datasets. Instead of using a standard library (e.g., Mahout), we implemented NBC to achieve fine-grain control of the analysis procedure. A Big Data analyzing system is also design for this study. The result is encouraging in that the accuracy of NBC is improved and approaches 82% when the dataset size increases. We have demonstrated that NBC is able to scale up to analyze the sentiment of millions movie reviews with increasing throughput.

This paper compares different defense strategies against various attacks utilizing a dynamic game theoretic data fusion framework for cyber network defense. In our game theoretic framework, Alerts generated by Intrusion Detection Sensors (IDSs) or Intrusion Prevention Sensors (IPSs) are fed into the data refinement (Level 0) and object assessment (L1) data fusion components. High-level situation/threat assessment (L2/L3) data fusion based on Markov game model and Hierarchical Entity Aggregation (HEA) are proposed to refine the primitive prediction generated by adaptive feature/pattern recognition and capture new unknown features. A Markov (Stochastic) game method is used to estimate the belief of each possible cyber attack pattern. Game theory captures the nature of cyber conflicts: determination of the attacking-force strategies is tightly coupled to determination of the defense-force strategies and vice versa. A software tool is developed to demonstrate and compare the performance of different defense strategies used in game theoretic high level information fusion for cyber network defense situations and a simulation example shows the enhanced understating of cyber-network defense.

This paper describes how pedigree is used to support and enhance situation and threat assessment. It is based on the findings of the technology group of the Data Fusion Levels Two and Three Workshop sponsored by the Office of Naval Research held in Arlington, VA from 15-18 Nov. 2005. It identifies areas that need improvement in situation assessment and threat assessment, such as interoperability, automation, pedigree management, system usability, reliability, and uncertainty. The concept of pedigree must include "standard" metadata, lineage, plus a computational model of the quality of the information. The system must automatically propagate changes and update to derived products when source information or source-pedigree information changes. Several other processes must be automated: generate pedigree, identify and auto fill gaps, fuse pedigree, update pedigree, display of information quality and confidence. The paper concludes with suggestions for future research and development.

The strategy of data fusion has been applied in threat prediction and situation awareness and the terminology has been standardized by the Joint Directors of Laboratories (JDL) in the form of a so-called JDL data fusion model, which currently called DFIG model. Higher levels of the DFIG model call for prediction of future development and awareness of the development of a situation. It is known that Bayesian network is an insightful approach to determine optimal strategies against asymmetric adversarial opponent. However, it lacks the essential adversarial decision processes perspective. In this paper, a highly innovative data-fusion framework for asymmetric-threat detection and prediction based on advanced knowledge infrastructure and stochastic (Markov) game theory is proposed. In particular, asymmetric and adaptive threats are detected and grouped by intelligent agent and hierarchical entity aggregation in level 2 and their intents are predicted by a decentralized Markov (stochastic) game model with deception in level 3. We have verified that our proposed algorithms are scalable, stable, and perform satisfactorily according to the situation awareness performance metric