Search

Applying parallel-in-time algorithms to multiscale Hamiltonian systems to obtain stable long-time simulations is very challenging. In this paper, we present novel data-driven methods aimed at improving the standard parareal algorithm developed by Lions et al. in 2001, for multiscale Hamiltonian systems. The first method involves constructing a correction operator to improve a given inaccurate coarse solver through solving a Procrustes problem using data collected online along parareal trajectories. The second method involves constructing an efficient, high-fidelity solver by a neural network trained with offline generated data. For the second method, we address the issues of effective data generation and proper loss function design based on the Hamiltonian function. We show proof-of-concept by applying the proposed methods to a Fermi-Pasta-Ulam (FPU) problem. The numerical results demonstrate that the Procrustes parareal method is able to produce solutions that are more stable in energy compared to the standard parareal. The neural network solver can achieve comparable or better runtime performance compared to numerical solvers of similar accuracy. When combined with the standard parareal algorithm, the improved neural network solutions are slightly more stable in energy than the improved numerical coarse solutions. [ABSTRACT FROM AUTHOR]

In this paper, we study numerical solution of ruin probability of continuous time model. We develop an effective optimal adaptive particle swarm optimization-triangular neural network (PSO-TNN), which consists of three parts: particle swarm optimization algorithm (PSO) improved trigonometric function, extreme learning machine algorithm with initial conditions (IELM) and improved reduction algorithm. The results obtained that PSO-TNN is superior to triangular neural network (TNN) and physics-informed neural networks (PINNs), and PSO is superior to Aquila Optimizer (AO), Smell Agent Optimization (SAO), African vultures optimization algorithm (AVOA), Arithmetic optimization algorithm (AOA) in the optimization of neural network. Because the relationship between the number of neural networks and the mean square error is uncertain, we propose the adaptive reduction algorithm (AR). Through the comparison of numerical solutions with the analytical solutions and traditional numerical solutions, the PSO-TNN algorithm clearly reduced the mean square error and relative error. The PSO-TNN algorithm shows a clear improvement in terms of accuracy and overall efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we discuss applications of neural networks to recognizing knots and, in particular, to the unknotting problem. One of the motivations for this study is to understand how neural networks work on the example of a problem for which rigorous mathematical algorithms for its solution are known. We represent knots by rectangular Dynnikov diagrams and apply neural networks to distinguish a given diagram's class from a finite family of topological types. The data presented to the program is generated by applying Dynnikov moves to initial samples. The significance of using these diagrams and moves is that in this context the problem of determining whether a diagram is unknotted is a finite search of a bounded combinatorial space. In this way, this paper provides a foundation for further work where the neural network itself will learn to use the Dynnikov moves for knot recognition. Source code of the programs is available at https://github.com/nerusskikh/deepknots. [ABSTRACT FROM AUTHOR]

Modern smart grids are built based on top of advanced computing and networking technologies, where condition monitoring relies on secure cyberphysical connectivity. Over the network infrastructure, transported data containing confidential information, must be protected as smart grids are vulnerable and subject to various cyberattacks. Various machine learning based classifiers were proposed for intrusion detection in smart grids. However, each of them has respective advantage and disadvantages. Aiming to improve the performance of existing machine learning based classifiers, this paper proposes an adaptive deep learning algorithm with a data pre-processing module, a neural network pre-training module and a classifier module, which work together classify intrusion data types using their high-dimensional data features. The proposed Adaptive Deep Learning (ADL) algorithm obtains the number of layers and the number of neurons per layer by determining the characteristic dimension of the network traffic. With transfer learning, the proposed ADL algorithm can extract the original data dimensions and obtain new abstract features. By combining deep learning models with traditional machine learning-based classification models, the performance of classification of network traffic data is significantly improved. By using the Network Security Laboratory-Knowledge Discovery in Databases (NSL-KDD) dataset, experimental results show that the proposed ADL algorithm improves the effectiveness of existing intrusion detection methods and reduces the training time, indicating a promising candidate to enhance network security in smart grids. [ABSTRACT FROM AUTHOR]

Background: Machine Learning (ML) is becoming increasingly popular in healthcare, particularly for improving the timing and accuracy of diagnosis. ML can provide disease prediction by analyzing vast amounts of healthcare data, thereby, empowering patients and healthcare providers with information to make informed decisions about disease prevention. Due to the rising cost of treatment, one of the most important topics in clinical data analysis is the prediction and prevention of cardiovascular disease. It is difficult to manually calculate the chances of developing heart disease due to a myriad of contributing factors. Objective: The aim of this paper is to develop and compare various intelligent systems built with ML algorithms for predicting whether a person is likely to develop heart disease using the publicly available Cleveland Heart Disease dataset. This paper describes an alternative multilayer perceptron (MLP) training technique that utilizes a particle swarm optimization (PSO) algorithm for heart disease detection. Methods: The proposed MLP-PSO hybrid algorithm and ten different ML algorithms are used in this study to predict heart disease. Various classification metrics are used to evaluate the performance of the algorithms. Results: The proposed MLP-PSO outperforms all other algorithms, obtaining an accuracy of 84.61%. Conclusions: According to our findings, the current MLP-PSO classifier enables practitioners to diagnose heart disease earlier, more accurately, and more effectively. [ABSTRACT FROM AUTHOR]

Path planning is an essential component of mobile robotics. Classical path planning algorithms, such as wavefront and rapidly exploring random tree, are used heavily in autonomous robots. With the recent advances in machine learning, development of learning-based path planning algorithms has been experiencing a rapid growth. A unified path planning interface that facilitates the development and benchmarking of existing and new algorithms is needed. This paper presents PathBench, a platform for developing, visualizing, training, testing, and benchmarking of existing and future, classical and learning-based path planning algorithms in 2D and 3D grid world environments. Many existing path planning algorithms are supported, e.g. A*, Dijkstra, waypoint planning networks, value iteration networks, and gated path planning networks; integrating new algorithms is easy and clearly specified. The benchmarking ability of PathBench is explored in this paper by comparing algorithms across five different hardware systems and three different map types, including built-in PathBench maps, video game maps, and maps from real world databases. Metrics, such as path length, success rate, and computational time, were used to evaluate algorithms. Algorithmic analysis was also performed on a real-world robot to demonstrate PathBench's support for Robot Operating System. PathBench is open source1. [ABSTRACT FROM AUTHOR]

Monitoring a patient's vital signs is considered one of the most challenging problems in telehealth systems, especially when patients reside in remote locations. Companies now use IoT devices such as wearable devices to participate in telehealth systems. However, the steady adoption of wearables can result in a significant increase in the volume of data being collected and transmitted. As these devices run on limited battery power, they can run out of power quickly due to the high processing requirements of the device for data collection and transmission. Given the importance of medical data, it is imperative that all transmitted data adhere to strict integrity and availability requirements. Reducing the volume of healthcare data and the frequency of transmission can improve a device's battery life via an inference algorithm. Furthermore, this approach creates issues for improving transmission metrics related to accuracy and efficiency, which are traded-off against each other, with increasing accuracy reducing efficiency. This paper demonstrates that machine learning (ML) can be used to overcome the trade-off problem. The damped least-squares algorithm (DLSA) is used to enhance both metrics by taking fewer samples for transmission whilst maintaining accuracy. The algorithm is tested with a standard heart rate dataset to compare the metrics. The results showed that the DLSA provides the best performance, with an efficiency of 3.33 times for reduced sample data size and an accuracy of 95.6%, with similar accuracies observed in seven different sampling cases adopted for testing that demonstrate improved efficiency. This proposed method significantly improve both metrics using ML without sacrificing one metric over the other compared to existing methods with high efficiency. [ABSTRACT FROM AUTHOR]

Clinical lab tests play an important role in disease diagnose and medical treatment, the test results have been utilized widely in predictive modeling tasks in healthcare. However, in most existing works, the loss function implicitly assumes that the value of the sample used to be predicted is the only correct one. This assumption fails to hold for lab test data, which usually are within respective tolerable ranges or imprecision ranges. In addition, the historical lab test data is always organized based on their sequential position, the timestamps between the data are often neglected. In this paper, we study the issue of building robust models while simultaneously taking imprecision and timestamp of the data into account with better generalization. In particular, "IR loss" is proposed in which each data in imprecision range space has a certain probability to be the real value, participating in the loss calculation. The loss is then defined as the integral of the error of each point in the impression range space. The sampling and discretization methods are proposed for loss calculation. A heuristic learning algorithm is developed to learn the model parameters. We further apply IR loss for disease progress prediction while the input data is organized as sequence. We reformulate the prediction task with timestamp based on Long Short-Term Memory (LSTM) network. At the same time, the timestamp is readily combined with the proposed IR loss to avoid the change of predicted result caused by the change of the test values in small time range. We conducted the experiments based on two real world datasets. Experimental results show that the prediction method based on IR loss can provide more accurate prediction result for different kinds of task and diverse learning methods. Our method can also provide more stable and consistent results when test samples are generated from imprecision range and small time range. [ABSTRACT FROM AUTHOR]