In this paper we present a three-stream algorithm for real-time action recognition and a new dataset of handwash videos, with the intent of aligning action recognition with real-world constraints to yield effective conclusions. A three-stream fusion algorithm is proposed, which runs both accurately and efficiently, in real-time even on low-powered systems such as a Raspberry Pi. The cornerstone of the proposed algorithm is the incorporation of both spatial and temporal information, as well as the information of the objects in a video while using an efficient architecture, and Optical Flow computation to achieve commendable results in real-time. The results achieved by this algorithm are benchmarked on the UCF-101 as well as the HMDB-51 datasets, achieving an accuracy of 92.7% and 64.9% respectively. An important point to note is that the algorithm is novel in the aspect that it is also able to learn the intricate differences between extremely similar actions, which would be difficult even for the human eye. Additionally, noticing a dearth in the number of datasets for the recognition of very similar or fine-grained actions, this paper also introduces a new dataset that is made publicly available, the Hand Wash Dataset with the intent of introducing a new benchmark for fine-grained action recognition tasks in the future.
We present a real-time multivariate anomaly detection algorithm for data streams based on the Probabilistic Exponentially Weighted Moving Average (PEWMA). Our formulation is resilient to (abrupt transient, abrupt distributional, and gradual distributional) shifts in the data. The novel anomaly detection routines utilize an incremental online algorithm to handle streams. Furthermore, our proposed anomaly detection algorithm works in an unsupervised manner eliminating the need for labeled examples. Our algorithm performs well and is resilient in the face of concept drifts.
Link streams offer a good model for representing interactions over time. They consist of links $(b,e,u,v)$, where $u$ and $v$ are vertices interacting during the whole time interval $[b,e]$. In this paper, we deal with the problem of enumerating maximal cliques in link streams. A clique is a pair $(C,[t_0,t_1])$, where $C$ is a set of vertices that all interact pairwise during the full interval $[t_0,t_1]$. It is maximal when neither its set of vertices nor its time interval can be increased. Some of the main works solving this problem are based on the famous Bron-Kerbosch algorithm for enumerating maximal cliques in graphs. We take this idea as a starting point to propose a new algorithm which matches the cliques of the instantaneous graphs formed by links existing at a given time $t$ to the maximal cliques of the link stream. We prove its validity and compute its complexity, which is better than the state-of-the art ones in many cases of interest. We also study the output-sensitive complexity, which is close to the output size, thereby showing that our algorithm is efficient. To confirm this, we perform experiments on link streams used in the state of the art, and on massive link streams, up to 100 million links. In all cases our algorithm is faster, mostly by a factor of at least 10 and up to a factor of $10^4$. Moreover, it scales to massive link streams for which the existing algorithms are not able to provide the solution.
With the development of Web 3.0 which emphasizes decentralization, blockchain technology ushers in its revolution and also brings numerous challenges, particularly in the field of cryptocurrency. Recently, a large number of criminal behaviors continuously emerge on blockchain, such as Ponzi schemes and phishing scams, which severely endanger decentralized finance. Existing graph-based abnormal behavior detection methods on blockchain usually focus on constructing homogeneous transaction graphs without distinguishing the heterogeneity of nodes and edges, resulting in partial loss of transaction pattern information. Although existing heterogeneous modeling methods can depict richer information through metapaths, the extracted metapaths generally neglect temporal dependencies between entities and do not reflect real behavior. In this paper, we introduce Time-aware Metapath Feature Augmentation (TMFAug) as a plug-and-play module to capture the real metapath-based transaction patterns during Ponzi scheme detection on Ethereum. The proposed module can be adaptively combined with existing graph-based Ponzi detection methods. Extensive experimental results show that our TMFAug can help existing Ponzi detection methods achieve significant performance improvements on the Ethereum dataset, indicating the effectiveness of heterogeneous temporal information for Ponzi scheme detection.
Artificial Intelligence (AI) and machine learning have been increasingly adopted for forecasting real-time travel demand. These AI-based travel demand forecasting models, though generate highly-accurate predictions, may produce prediction biases and thus raise fairness issues. Using such models for decision-making, we may develop transportation policies that could exacerbate social inequalities. However, limited studies have been focused on addressing the fairness issues of AI-based travel demand forecasting models. Therefore, in this study, we propose a novel methodology to develop fairness-aware travel demand forecasting models, which are highly accurate and fair. Specifically, we add a fairness regularization term, i.e., the correlation between prediction accuracy and the protected attribute such as race or income, into the loss function of the travel demand forecasting model. We include an interactive weight coefficient to both accuracy loss term and fairness loss term. The travel demand forecasting models can thus simultaneously account for prediction accuracy and fairness. An empirical analysis is conducted using real-world ridesourcing-trip data in Chicago. Results show that our proposed methodology effectively addresses the accuracy-fairness trade-off. It can significantly enhance fairness for multiple protected attributes (i.e., race, education, age and income) by only sacrificing a small accuracy drop. This study provides transportation professionals a new type of decision-support tool to achieve fair and accurate travel demand forecasting.
LiDAR object detection algorithms based on neural networks for autonomous driving require large amounts of data for training, validation, and testing. As real-world data collection and labeling are time-consuming and expensive, simulation-based synthetic data generation is a viable alternative. However, using simulated data for the training of neural networks leads to a domain shift of training and testing data due to differences in scenes, scenarios, and distributions. In this work, we quantify the sim-to-real domain shift by means of LiDAR object detectors trained with a new scenario-identical real-world and simulated dataset. In addition, we answer the questions of how well the simulated data resembles the real-world data and how well object detectors trained on simulated data perform on real-world data. Further, we analyze point clouds at the target-level by comparing real-world and simulated point clouds within the 3D bounding boxes of the targets. Our experiments show that a significant sim-to-real domain shift exists even for our scenario-identical datasets. This domain shift amounts to an average precision reduction of around 14 % for object detectors trained with simulated data. Additional experiments reveal that this domain shift can be lowered by introducing a simple noise model in simulation. We further show that a simple downsampling method to model real-world physics does not influence the performance of the object detectors.
Code comments are significantly helpful in comprehending software programs and also aid developers to save a great deal of time in software maintenance. Code comment generation aims to automatically predict comments in natural language given a code snippet. Several works investigate the effect of integrating external knowledge on the quality of generated comments. In this study, we propose a solution, namely APIContext2Com, to improve the effectiveness of generated comments by incorporating the pre-defined Application Programming Interface (API) context. The API context includes the definition and description of the pre-defined APIs that are used within the code snippets. As the detailed API information expresses the functionality of a code snippet, it can be helpful in better generating the code summary. We introduce a seq-2-seq encoder-decoder neural network model with different sets of multiple encoders to effectively transform distinct inputs into target comments. A ranking mechanism is also developed to exclude non-informative APIs, so that we can filter out unrelated APIs. We evaluate our approach using the Java dataset from CodeSearchNet. The findings reveal that the proposed model improves the best baseline by 1.88 (8.24 %), 2.16 (17.58 %), 1.38 (18.3 %), 0.73 (14.17 %), 1.58 (14.98 %) and 1.9 (6.92 %) for BLEU1, BLEU2, BLEU3, BLEU4, METEOR, ROUGE-L respectively. Human evaluation and ablation studies confirm the quality of the generated comments and the effect of architecture and ranking APIs.
The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN) autoencoding architecture with demonstrations on complex fluid flow applications. To address the first goal of interpretability, the GNN autoencoder achieves reduction in the number nodes in the encoding stage through an adaptive graph reduction procedure. This reduction procedure essentially amounts to flowfield-conditioned node sampling and sensor identification, and produces interpretable latent graph representations tailored to the flowfield reconstruction task in the form of so-called masked fields. These masked fields allow the user to (a) visualize where in physical space a given latent graph is active, and (b) interpret the time-evolution of the latent graph connectivity in accordance with the time-evolution of unsteady flow features (e.g. recirculation zones, shear layers) in the domain. To address the goal of unstructured mesh compatibility, the autoencoding architecture utilizes a series of multi-scale message passing (MMP) layers, each of which models information exchange among node neighborhoods at various lengthscales. The MMP layer, which augments standard single-scale message passing with learnable coarsening operations, allows the decoder to more efficiently reconstruct the flowfield from the identified regions in the masked fields. Analysis of latent graphs produced by the autoencoder for various model settings are conducted using using unstructured snapshot data sourced from large-eddy simulations in a backward-facing step (BFS) flow configuration with an OpenFOAM-based flow solver at high Reynolds numbers.
Pseudospectral collocation methods have proven to be powerful tools to solve optimal control problems. While these methods generally assume the dynamics is given in the first order form $\dot{x} = f (x, u, t)$, where x is the state and u is the control vector, robotic systems are typically governed by second order ODEs of the form $\ddot{q} = g(q, \dot{q}, u, t)$, where q is the configuration. To convert the second order ODE into a first order one, the usual approach is to introduce a velocity variable v and impose its coincidence with the time derivative of q. Lobatto methods grant this constraint by construction, as their polynomials describing the trajectory for v are the time derivatives of those for q, but the same cannot be said for the Gauss and Radau methods. This is problematic for such methods, as then they cannot guarantee that $\ddot{q} = g(q, \dot{q}, u, t)$ at the collocation points. On their negative side, Lobatto methods cannot be used to solve initial value problems, as given the values of u at the collocation points they generate an overconstrained system of equations for the states. In this paper, we propose a Legendre-Gauss collocation method that retains the advantages of the usual Lobatto, Gauss, and Radau methods, while avoiding their shortcomings. The collocation scheme we propose is applicable to solve initial value problems, preserves the consistency between the polynomials for v and q, and ensures that $\ddot{q} = g(q, \dot{q}, u, t)$ at the collocation points.
Simultaneous localization and mapping (SLAM) are essential in numerous robotics applications, such as autonomous navigation. Traditional SLAM approaches infer the metric state of the robot along with a metric map of the environment. While existing algorithms exhibit good results, they are still sensitive to measurement noise, sensor quality, and data association and are still computationally expensive. Alternatively, some navigation and mapping missions can be achieved using only qualitative geometric information, an approach known as qualitative spatial reasoning (QSR). We contribute a novel probabilistic qualitative localization and mapping approach in this work. We infer both the qualitative map and the qualitative state of the camera poses (localization). For the first time, we also incorporate qualitative probabilistic constraints between camera poses (motion model), improving computation time and performance. Furthermore, we take advantage of qualitative inference properties to achieve very fast approximated algorithms with good performance. In addition, we show how to propagate probabilistic information between nodes in the qualitative map, which improves estimation performance and enables inference of unseen map nodes - an important building block for qualitative active planning. We also conduct a study that shows how well we can estimate unseen nodes. Our method particularly appeals to scenarios with few salient landmarks and low-quality sensors. We evaluate our approach in simulation and on a real-world dataset and show its superior performance and low complexity compared to the state-of-the-art. Our analysis also indicates good prospects for using qualitative navigation and planning in real-world scenarios.