Safety is a top priority for civil aviation. Data mining in digital Flight Data Recorder (FDR) or Quick Access Recorder (QAR) data, commonly referred as black box data on aircraft, has gained interest from researchers, airlines, and aviation regulation agencies for safety management. New anomaly detection methods based on supervised or unsupervised learning have been developed to monitor pilot operations and detect any risks from onboard digital flight data recorder data. However, all existing anomaly detection methods are offline learning - the models are trained once using historical data and used for all future predictions. In practice, new QAR data are generated by every flight and collected by airlines whenever a datalink is available. Offline methods cannot respond to new data in time. Though these offline models can be updated by being re-trained after adding new data to the original training set, it is time-consuming and computational costly to train a new model every time new data come in. To address this problem, we propose a novel incremental anomaly detection method to identify common patterns and detect outliers in flight operations from FDR data. The proposed method is based on Gaussian Mixture Model (GMM). An initial GMM cluster model is trained on historical offline data. Then, it continuously adapts to new incoming data points via an expectation-maximization (EM) algorithm. To track changes in flight operation patterns, only model parameters need to be saved, not the raw flight data. The proposed method was tested on two sets of simulation data. Comparable results were found from the proposed online method and a classic offline model. A real-world application of the proposed method is demonstrated using FDR data from daily operations of an airline. Results are presented and future challenges of using online learning scheme for flight data analytics are discussed.

We study the problem of a decision maker who must provide the best possible treatment recommendation based on an experiment. The desirability of the outcome distribution resulting from the policy recommendation is measured through a functional capturing the distributional characteristic that the decision maker is interested in optimizing. This could be, e.g., its inherent inequality, welfare, level of poverty or its distance to a desired outcome distribution. If the functional of interest is not quasi-convex or if there are constraints, the optimal recommendation may be a mixture of treatments. This vastly expands the set of recommendations that must be considered. We characterize the difficulty of the problem by obtaining maximal expected regret lower bounds. Furthermore, we propose two regret-optimal policies. The first policy is static and thus applicable irrespectively of the subjects arriving sequentially or not in the course of the experimental phase. The second policy can utilize that subjects arrive sequentially by successively eliminating inferior treatments and thus spends the sampling effort where it is most needed.

Coronavirus disease (COVID-19) spread forecasting is an important task to track the growth of the pandemic. Existing predictions are merely based on qualitative analyses and mathematical modeling. The use of available big data with machine learning is still limited in COVID-19 growth prediction even though the availability of data is abundance. To make use of big data in the prediction using deep learning, we use long short-term memory (LSTM) method to learn the correlation of COVID-19 growth over time. The structure of an LSTM layer is searched heuristically until the best validation score is achieved. First, we trained training data containing confirmed cases from around the globe. We achieved favorable performance compared with that of the recurrent neural network (RNN) method with a comparable low validation error. The evaluation is conducted based on graph visualization and root mean squared error (RMSE). We found that it is not easy to achieve the same quantity of confirmed cases over time. However, LSTM provide a similar pattern between the actual cases and prediction. In the future, our proposed prediction can be used for anticipating forthcoming pandemics. The code is provided here: https://github.com/cbasemaster/lstmcorona

In recent years, researchers have become increasingly interested in outlying aspect mining. Outlying aspect mining is the task of finding a set of feature(s), where a given data object is different from the rest of the data objects. Remarkably few studies have been designed to address the problem of outlying aspect mining; therefore, little is known about outlying aspect mining approaches and their strengths and weaknesses among researchers. In this work, we have grouped existing outlying aspect mining approaches in three different categories. For each category, we have provided existing work that falls in that category and then provided their strengths and weaknesses in those categories. We also offer time complexity comparison of the current techniques since it is a crucial issue in the real-world scenario. The motive behind this paper is to give a better understanding of the existing outlying aspect mining techniques and how these techniques have been developed.

Like all software systems, the execution of deep learning models is dictated in part by logic represented as data in memory. For decades, attackers have exploited traditional software programs by manipulating this data. We propose a live attack on deep learning systems that patches model parameters in memory to achieve predefined malicious behavior on a certain set of inputs. By minimizing the size and number of these patches, the attacker can reduce the amount of network communication and memory overwrites, with minimal risk of system malfunctions or other detectable side effects. We demonstrate the feasibility of this attack by computing efficient patches on multiple deep learning models. We show that the desired trojan behavior can be induced with a few small patches and with limited access to training data. We describe the details of how this attack is carried out on real systems and provide sample code for patching TensorFlow model parameters in Windows and in Linux. Lastly, we present a technique for effectively manipulating entropy on perturbed inputs to bypass STRIP, a state-of-the-art run-time trojan detection technique.

While previous approaches explore the effect of self-supervision on natural images, we show that patch-based pre-training performs poorly on document images because of their different structural properties and poor intra-sample semantic information. We propose two context-aware alternatives to improve performance on the Tobacco-3482 image classification task. We also propose a novel method for self-supervision, which makes use of the inherent multi-modality of documents (image and text), which performs better than other popular self-supervised methods, including supervised ImageNet pre-training, on document image classification scenarios with a limited amount of data.

This work examines the hypothesis that partially observable Markov decision process (POMDP) planning with human driver internal states can significantly improve both safety and efficiency in autonomous freeway driving. We evaluate this hypothesis in a simulated scenario where an autonomous car must safely perform three lane changes in rapid succession. Approximate POMDP solutions are obtained through the partially observable Monte Carlo planning with observation widening (POMCPOW) algorithm. This approach outperforms over-confident and conservative MDP baselines and matches or outperforms QMDP. Relative to the MDP baselines, POMCPOW typically cuts the rate of unsafe situations in half or increases the success rate by 50%.

We explore applying the Monte Carlo Tree Search (MCTS) algorithm in a notoriously difficult task: tuning programs for high-performance deep learning and image processing. We build our framework on top of Halide and show that MCTS can outperform the state-of-the-art beam-search algorithm. Unlike beam search, which is guided by greedy intermediate performance comparisons between partial and less meaningful schedules, MCTS compares complete schedules and looks ahead before making any intermediate scheduling decision. We further explore modifications to the standard MCTS algorithm as well as combining real execution time measurements with the cost model. Our results show that MCTS can outperform beam search on a suite of 16 real benchmarks.

Modern algorithms in the domain of Deep Reinforcement Learning (DRL) demonstrated remarkable successes; most widely known are those in game-based scenarios, from ATARI video games to Go and the StarCraft~\textsc{II} real-time strategy game. However, applications in the domain of modern Cyber-Physical Systems (CPS) that take advantage a vast variety of DRL algorithms are few. We assume that the benefits would be considerable: Modern CPS have become increasingly complex and evolved beyond traditional methods of modelling and analysis. At the same time, these CPS are confronted with an increasing amount of stochastic inputs, from volatile energy sources in power grids to broad user participation stemming from markets. Approaches of system modelling that use techniques from the domain of Artificial Intelligence (AI) do not focus on analysis and operation. In this paper, we describe the concept of Adversarial Resilience Learning (ARL) that formulates a new approach to complex environment checking and resilient operation: It defines two agent classes, attacker and defender agents. The quintessence of ARL lies in both agents exploring the system and training each other without any domain knowledge. Here, we introduce the ARL software architecture that allows to use a wide range of model-free as well as model-based DRL-based algorithms, and document results of concrete experiment runs on a complex power grid.

It feels like drones were built for this moment. The coronavirus pandemic has forced everyone to spend the majority of their time indoors and, where possible, maintain a healthy distance from anyone that doesn't live in the same building. Companies have introduced numerous measures to minimize the threat and spread of infection. Countless stores have acrylic screens, for instance, and many delivery drivers leave orders at your doorstep. But a robot -- or specifically, a drone -- offers a potentially safer and quicker method of exchanging goods and services. It's no wonder, then, that so many commercial UAV (unmanned aerial vehicle) operators are flourishing at the moment. In a time of crisis, they're keen to step forward and showcase the impact that drone deliveries can have on society.