The investment of time and resources for better strategies and methodologies to tackle a potential pandemic is key to deal with potential outbreaks of new variants or other viruses in the future. In this work, we recreated the scene of a year ago, 2020, when the pandemic erupted across the world for the fifty countries with more COVID-19 cases reported. We performed some experiments in which we compare state-of-the-art machine learning algorithms, such as LSTM, against online incremental machine learning algorithms to adapt them to the daily changes in the spread of the disease and predict future COVID-19 cases. To compare the methods, we performed three experiments: In the first one, we trained the models using only data from the country we predicted. In the second one, we use data from all fifty countries to train and predict each of them. In the first and second experiment, we used a static hold-out approach for all methods. In the third experiment, we trained the incremental methods sequentially, using a prequential evaluation. This scheme is not suitable for most state-of-the-art machine learning algorithms because they need to be retrained from scratch for every batch of predictions, causing a computational burden. Results show that incremental methods are a promising approach to adapt to changes of the disease over time; they are always up to date with the last state of the data distribution, and they have a significantly lower computational cost than other techniques such as LSTMs.
The research activity outlined in this PhD thesis is devoted to define a general approach, a concrete architecture and a prototype Process Management System (PMS) for the automated adaptation of dynamic processes at run-time, on the basis of a declarative specification of process tasks and relying on well-established reasoning about actions and planning techniques. The purpose is to demonstrate that the combination of procedural and imperative models with declarative elements, along with the exploitation of techniques from the field of artificial intelligence (AI), such as Situation Calculus, IndiGolog and automated planning, can increase the ability of existing PMSs of supporting dynamic processes. To this end, a prototype PMS named SmartPM, which is specifically tailored for supporting collaborative work of process participants during pervasive scenarios, has been developed. The adaptation mechanism deployed on SmartPM is based on execution monitoring for detecting failures at run-time, which does not require the definition of the adaptation strategy in the process itself (as most of the current approaches do), and on automatic planning techniques for the synthesis of the recovery procedure.
We present a new method for few-shot human motion transfer that achieves realistic human image generation with only a small number of appearance inputs. Despite recent advances in single person motion transfer, prior methods often require a large number of training images and take long training time. One promising direction is to perform few-shot human motion transfer, which only needs a few of source images for appearance transfer. However, it is particularly challenging to obtain satisfactory transfer results. In this paper, we address this issue by rendering a human texture map to a surface geometry (represented as a UV map), which is personalized to the source person. Our geometry generator combines the shape information from source images, and the pose information from 2D keypoints to synthesize the personalized UV map. A texture generator then generates the texture map conditioned on the texture of source images to fill out invisible parts. Furthermore, we may fine-tune the texture map on the manifold of the texture generator from a few source images at the test time, which improves the quality of the texture map without over-fitting or artifacts. Extensive experiments show the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively. Our code is available at https://github.com/HuangZhiChao95/FewShotMotionTransfer.
This paper uses new and recently introduced methodologies to study the similarity in the dynamics and behaviours of cryptocurrencies and equities surrounding the COVID-19 pandemic. We study two collections; 45 cryptocurrencies and 72 equities, both independently and in conjunction. First, we examine the evolution of cryptocurrency and equity market dynamics, with a particular focus on their change during the COVID-19 pandemic. We demonstrate markedly more similar dynamics during times of crisis. Next, we apply recently introduced methods to contrast trajectories, erratic behaviours, and extreme values among the two multivariate time series. Finally, we introduce a new framework for determining the persistence of market anomalies over time. Surprisingly, we find that although cryptocurrencies exhibit stronger collective dynamics and correlation in all market conditions, equities behave more similarly in their trajectories, extremes, and show greater persistence in anomalies over time.
We present a robust real-time LiDAR 3D object detector that leverages heteroscedastic aleatoric uncertainties to significantly improve its detection performance. A multi-loss function is designed to incorporate uncertainty estimations predicted by auxiliary output layers. Using our proposed method, the network ignores to train from noisy samples, and focuses more on informative ones. We validate our method on the KITTI object detection benchmark. Our method surpasses the baseline method which does not explicitly estimate uncertainties by up to nearly 9% in terms of Average Precision (AP). It also produces state-of-the-art results compared to other methods while running with an inference time of only 72 ms. In addition, we conduct extensive experiments to understand how aleatoric uncertainties behave. Extracting aleatoric uncertainties brings almost no additional computation cost during the deployment, making our method highly desirable for autonomous driving applications.
Device-to-device (D2D) and non-orthogonal multiple access (NOMA) are promising technologies to meet the challenges of the next generations of mobile communications in terms of network density and diversity for internet of things (IoT) services. This paper tackles the problem of maximizing the D2D sum-throughput in an IoT system underlaying a cellular network, through optimal channel and power allocation. NOMA is used to manage the interference between cellular users and full-duplex (FD) IoT devices. To this aim, mutual successive interference cancellation (SIC) conditions are identified to allow simultaneously the removal of the D2D devices interference at the level of the base station and the removal of the cellular users (CU) interference at the level of D2D devices. To optimally solve the joint channel and power allocation (PA) problem, a time-efficient solution of the PA problem in the FD context is elaborated. By means of graphical representation, the complex non-convex PA problem is efficiently solved in constant time complexity. This enables the global optimal resolution by successively solving the separate PA and channel assignment problems. The performance of the proposed strategy is compared against the classical state-of-the-art FD and HD scenarios, where SIC is not applied between CUs and IoT devices. The results show that important gains can be achieved by applying mutual SIC NOMA in the IoT-cellular context, in either HD or FD scenarios.
Supervised object detection has been proven to be successful in many benchmark datasets achieving human-level performances. However, acquiring a large amount of labeled image samples for supervised detection training is tedious, time-consuming, and costly. In this paper, we propose an efficient image selection approach that samples the most informative images from the unlabeled dataset and utilizes human-machine collaboration in an iterative train-annotate loop. Image features are extracted by the CNN network followed by the similarity score calculation, Euclidean distance. Unlabeled images are then sampled into different approaches based on the similarity score. The proposed approach is straightforward, simple and sampling takes place prior to the network training. Experiments on datasets show that our method can reduce up to 80% of manual annotation workload, compared to full manual labeling setting, and performs better than random sampling.
In this paper, we consider a UAV-enabled MEC platform that serves multiple mobile ground users with random movements and task arrivals. We aim to minimize the average weighted energy consumption of all users subject to the average UAV energy consumption and data queue stability constraints. To control the system operation in sequential time slots, we formulate the problem as a multi-stage stochastic optimization, and propose an online algorithm that optimizes the resource allocation and the UAV trajectory in each stage. We adopt Lyapunov optimization to convert the multi-stage stochastic problem into per-slot deterministic problems with much less optimizing variables. To tackle the non-convex per-slot problem, we use the successive convex approximation (SCA) technique to jointly optimize the resource allocation and the UAV movement. Simulation results show that the proposed online algorithm can satisfy the average UAV energy and queue stability constraints, and significantly outperform the other considered benchmark methods in reducing the energy consumption of ground users.
Electric vehicles are becoming more popular all over the world. With increasing battery capacities and a growing fast-charging infrastructure, they are becoming suitable for long distance travel. However, queues at charging stations could lead to long waiting times, making efficient route planning even more important. In general, optimal multi-objective route planning is extremely computationally expensive. We propose an adaptive charging and routing strategy, which considers driving, waiting, and charging time. For this, we developed a multi-criterion shortest-path search algorithm using contraction hierarchies. To further reduce the computational effort, we precompute shortest-path trees between the known locations of the charging stations. We propose a central charging station database (CSDB) that helps estimating waiting times at charging stations ahead of time. This enables our adaptive charging and routing strategy to reduce these waiting times. In an extensive set of simulation experiments, we demonstrate the advantages of our concept, which reduces average waiting times at charging stations by up to 97 %. Even if only a subset of the cars uses the CSDB approach, we can substantially reduce waiting times and thereby the total travel time of electric vehicles.
From global pandemics to geopolitical turmoil, leaders in logistics, product allocation, procurement and operations are facing increasing difficulty with safeguarding their organizations against supply chain vulnerabilities. It is recommended to opt for forecasting against trending based benchmark because auditing a future forecast puts more focus on seasonality. The forecasting models provide with end-to-end, real time oversight of the entire supply chain, while utilizing predictive analytics and artificial intelligence to identify potential disruptions before they occur. By combining internal and external data points, coming up with an AI-enabled modelling engine can greatly reduce risk by helping retail companies proactively respond to supply and demand variability. This research paper puts focus on creating an ingenious way to tackle the impact of COVID19 on Supply chain, product allocation, trending and seasonality. Key words: Supply chain, covid-19, forecasting, coronavirus, manufacturing, seasonality, trending, retail.