Stochastic Learning Approach Research Articles

Identification of internal voids in pavement based on improved knowledge distillation technology

Investigating methods for the detection of internal voids within road structures is a critical measure to ensure the safety and integrity of roadway operations. The purpose of this research is to investigate on the identification method of internal voids in pavement based on improved knowledge distillation technology. Ground penetrating radar data in three dimensions were extensively collected to capture the internal voids present within roadways, and this data was subsequently validated through in-situ verification. The echo characteristics of ground penetrating radar for areas with road voids were analyzed, and a dataset containing 1700 images of these internal voids was established. A YOLOv8 model improvement method was proposed, and a model for the detection of internal road voids was constructed based on the improved YOLO v8 framework. To further refine the model's performance, a knowledge distillation method based on multiple guidance from teacher assistants was developed. A stochastic learning approach was integrated, resulting in the establishment of a model optimized by this stochastic learning scheme for the identification of internal road voids. The results demonstrate that the presence of overfitting during the training phase of the void identification model can restrict its performance within a certain domain. The proposed stochastic learning-optimized, multi-teacher assistant guided knowledge distillation model, adeptly harnesses the performance benefits of both the teacher and assistant models by means of knowledge transfer, consequently achieving a significant improvement in the detection of internal road voids.

Outage-Minimization Coordinated Multi-Point for Millimeter-Wave OFDM With Random Blockages

We consider millimeter-wave (mmWave) orthogonal frequency division multiplexing (OFDM) systems subjected to random propagation path blockages and propose a new Coordinated multi-point (CoMP) transmission scheme that minimizes the outage probability of users with respect to given target data rates. To this end, a stochastic sum-outage-probability minimization problem is formulated for joint beamforming design, data rate allocation, and power allocation over subcarriers. In order to solve this problem efficiently, a block statistic learning approach is introduced using training data generated from <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> knowledge of path blockage probabilities. To initialize the stochastic learning solver, the novel initial beamforming is also proposed based on the upper bound of the original objective function, which improves convergence without tuning hyper-parameters. Numerical results confirm the effectiveness of the proposed block stochastic learning approach in terms of both convergence behavior and outage probability. Furthermore, these results confirm that the proposed approach with only blockage probabilities is comparable to the outage performance of a CoMP sum rate maximization (SRM) transmission scheme with perfect channel state information (CSI) and perfect knowledge of blockages.

A review of recent advances and applications of machine learning in tribology.

In tribology, a considerable number of computational and experimental approaches to understand the interfacial characteristics of material surfaces in motion and tribological behaviors of materials have been considered to date. Despite being useful in providing important insights on the tribological properties of a system, at different length scales, a vast amount of data generated from these state-of-the-art techniques remains underutilized due to lack of analysis methods or limitations of existing analysis techniques. In principle, this data can be used to address intractable tribological problems including structure-property relationships in tribological systems and efficient lubricant design in a cost and time effective manner with the aid of machine learning. Specifically, data-driven machine learning methods have shown potential in unraveling complicated processes through the development of structure-property/functionality relationships based on the collected data. For example, neural networks are incredibly effective in modeling non-linear correlations and identifying primary hidden patterns associated with these phenomena. Here we present several exemplary studies that have demonstrated the proficiency of machine learning in understanding these critical factors. A successful implementation of neural networks, supervised, and stochastic learning approaches in identifying structure-property relationships have shed light on how machine learning may be used in certain tribological applications. Moreover, ranging from the design of lubricants, composites, and experimental processes to studying fretting wear and frictional mechanism, machine learning has been embraced either independently or integrated with optimization algorithms by scientists to study tribology. Accordingly, this review aims at providing a perspective on the recent advances in the applications of machine learning in tribology. The review on referenced simulation approaches and subsequent applications of machine learning in experimental and computational tribology shall motivate researchers to introduce the revolutionary approach of machine learning in efficiently studying tribology.

Stochastic Learning Approach for Binary Optimization: Application to Bayesian Optimal Design of Experiments

We present a novel stochastic approach to binary optimization for optimal experimental design (OED) for Bayesian inverse problems governed by mathematical models such as partial differential equations. The OED utility function, namely, the regularized optimality criterion, is cast into a stochastic objective function in the form of an expectation over a multivariate Bernoulli distribution. The probabilistic objective is then solved by using a stochastic optimization routine to find an optimal observational policy. The proposed approach is analyzed from an optimization perspective and also from a machine learning perspective with correspondence to policy gradient reinforcement learning. The approach is demonstrated numerically by using an idealized two-dimensional Bayesian linear inverse problem, and validated by extensive numerical experiments carried out for sensor placement in a parameter identification setup.

Network modeling and Internet of things for smart and connected health systems—a case study for smart heart health monitoring and management

Heart disease is a leading cause of death in the US. Recent advances in the Internet of Things (IoT) provide a great opportunity to realize smart and connected health systems through IoT monitoring and sensor-based data analytics of cardiac disorders. However, big data arising from the large-scale IoT system pose a significant challenge for efficient and effective sensory information processing and decision making. Very little has been done to glean pertinent information about the disease-altered cardiac activity in the context of large-scale IoT network. In this study, we propose a parallel computing framework for multi-level network modeling and monitoring of cardiac dynamics to realize the potential of IoT-enabled smart health management. Specifically, dissimilarities among cardiac signals are firstly characterized among heartbeats for an individual patient, as well as among representative heartbeats for different patients. Then, a stochastic learning approach is developed to optimize the embedding of cardiac signals into a beat-to-beat network model, as well as a patient-to-patient network model. Further, we develop a parallel computing algorithm to improve the computational efficiency. Finally, a statistical process monitoring scheme is designed to harness network features for real-time monitoring and anomaly detection of cardiac activities. Experimental results show the proposed methodology has strong potential to realize a smart and interconnected system for cardiac health management in the context of large-scale IoT network.

Stochastic parallel extreme artificial hydrocarbon networks: An implementation for fast and robust supervised machine learning in high-dimensional data

Artificial hydrocarbon networks (AHN) – a supervised learning method inspired on organic chemical structures and mechanisms – have shown improvements in predictive power and interpretability in comparison with other well-known machine learning models. However, AHN are very time-consuming that are not able to deal with large data until now. In this paper, we introduce the stochastic parallel extreme artificial hydrocarbon networks (SPE-AHN), an algorithm for fast and robust training of supervised AHN models in high-dimensional data. This training method comprises a population-based meta-heuristic optimization with defined individual encoding and objective function related to the AHN-model, an implementation in parallel-computing, and a stochastic learning approach for consuming large data. We conducted three experiments with synthetic and real data sets to validate the training execution time and performance of the proposed algorithm. Experimental results demonstrated that the proposed SPE-AHN outperforms the original-AHN method, increasing the speed of training more than 10,000x times in the worst case scenario. Additionally, we present two case studies in real data sets for solar-panel deployment prediction (regression problem), and human falls and daily activities classification in healthcare monitoring systems (classification problem). These case studies showed that SPE-AHN improves the state-of-the-art machine learning models in both engineering problems. We anticipate our new training algorithm to be useful in many applications of AHN like robotics, finance, medical engineering, aerospace, and others, in which large amounts of data (e.g. big data) is essential.

Distributed Opportunistic Spectrum Access in an Unknown and Dynamic Environment: A Stochastic Learning Approach

In this paper, the problem of distributed throughput maximization in an opportunistic spectrum access network with multiple secondary users (SUs) and multiple primary channels is investigated. To address the challenges in designing efficient solutions in a dynamic and unknown environment, we formulate the optimization problem as a noncooperative game, which is further proved to be an ordinal potential game. We then propose a best-response-based algorithm to achieve the Nash equilibrium points (NEPs) of the formulated game, given that there exists a coordinator for SUs to work in a round-robin fashion and a common control channel for SUs to exchange their information. To further relieve the system overhead due to information exchange among SUs, we design a new stochastic learning automata (SLA)-based algorithm, called N-SLA, which can converge to the pure-strategy NEPs of the formulated ordinal potential game in a fully distributed way. To our best knowledge, we are the first to address the convergence issue of the SLA-based algorithms for general ordinal potential games. Simulation results validate the effectiveness of our proposed algorithms.

Environmental data stream mining through a case-based stochastic learning approach

Environmental data stream mining is an open challenge for Data Science. Common methods used are static because they analyze a static set of data, and provide static data-driven models. Environmental systems are dynamic and generate a continuous data stream. Dynamic methods coping with the temporal nature of data must be provided in Data Science. Our proposal is to model each environmental information unit, timely generated, as a new case/experience in a Case-Based Reasoning (CBR) system. This contribution aims to incrementally build and manage a Dynamic Adaptive Case Library (DACL). In this paper, a stochastic method for the learning of new cases and management of prototypes to create and manage the DACL in an incremental way is introduced. This stochastic method works with two main moments. An evaluation of the method has been carried using a data stream of air quality of the city of Obregon, Sonora. México, with good results. In addition, other datasets have been mined to ensure the generality of the approach.

Opportunistic Spectrum Access with Dynamic Users: Directional Graphical Game and Stochastic Learning

This paper investigates the channel selection problem with dynamic users and the asymmetric interference relation in distributed opportunistic spectrum access systems. Since users transmitting data are based on their traffic demands, they dynamically compete for the channel occupation. Moreover, the heterogeneous interference range leads to asymmetric interference relation. The dynamic users and asymmetric interference relation bring about new challenges such as dynamic random systems and poor fairness. In this article, we will focus on maximizing the tradeoff between the achievable utility and access cost of each user, formulate the channel selection problem as a directional graphical game and prove it as an exact potential game presenting at least one pure Nash equilibrium point. We show that the best NE point maximizes both the personal and system utility, and employ the stochastic learning approach algorithm for achieving the best NE point. Simulation results show that the algorithm converges, presents near-optimal performance and good fairness, and the directional graphical model improves the systems throughput performance in different asymmetric level systems.

Self-Organized Relay Selection for Cooperative Transmission in Vehicular Ad-Hoc Networks

Cooperation is a promising paradigm to improve spatial diversity in vehicular ad-hoc networks. In this paper, we pose a fundamental question: How the greediness and selfishness of individual nodes impact cooperation dynamics in vehicular ad-hoc networks. We map the self-interest-driven relay selection decision-making problem to an automata game formulation and present a noncooperative game-theoretic analysis. We show that the relay selection game is an ordinal potential game. A decentralized self-organized relay selection algorithm is proposed based on a stochastic learning approach where each player evolves toward a strategic equilibrium state in the sense of Nash. Furthermore, we study the exact outage behavior of the multirelay decode-and-forward cooperative communication network. Closed-form solutions are derived for the actual outage probability of this multirelay system in both independent and identically distributed channels and generalized channels, which need not assume an asymptotic or high signal-to-noise ratio. Two tight approximations with low computational complexity are also developed for the lower bound of the outage probability. With the exact closed-form outage probability, we further develop an optimization model to determine optimal power allocations in the cooperative network, which can be combined with the decentralized learning-based relay selection. The analysis of the exact and approximative outage behaviors and the convergence properties of the proposed algorithm toward a Nash equilibrium state are verified theoretically and numerically. Simulation results are also given to demonstrate that the resulting cooperative network induced by the proposed algorithm achieves high energy efficiency, transmission reliability, and network-wide fairness performance.

A Stochastic Learning Approach for Construction of Brick Structures with a Ground Robot

In this paper, we describe an architectural framework by which a mobile robot can learn how to autonomously assemble solid 3D brick structures according to user-specified designs. The policies of actions to perform the construction task are obtained from a simulation environment using Reinforcement Learning (RL) and Particle Swarm Optimization (PSO) approaches. The proposed planning architecture is used to simultaneously solve three problems: 1) to generate feasible construction policies, 2) to define the set of maneuvers for the vehicle to carry out the assembly task, and 3) to obtain the set of trajectories for handling and mounting parts while avoiding fixed obstacles. During the learning process the power limitation of the ground robot is taken into account. Simulation results show that the set of learned actions may efficiently perform the construction procedures without resulting in conditions which prevent the fulfillment of the assembly procedures. The synthesis of this system opens the way to the development of intelligent construction approaches using ground robots.

Game Theoretic Max-logit Learning Approaches for Joint Base Station Selection and Resource Allocation in Heterogeneous Networks

This paper investigates the problem of joint base station selection and resource allocation in an orthogonal frequency division multiple access (OFDMA) heterogeneous cellular network. The original throughput maximization problem is NP-hard and we propose solving it by using game theoretic stochastic learning approaches. To this end, we first transform the original problem into a tractable form, which has a weighted utility function. Then we prove that an exact potential game applies and it exists the best Nash equilibria which is a near optimal solution of the original problem when an efficient solution method of the weights is employed. To obtain the optimal solution, we redesign the utility function by leveraging a state space to formulate the original problem into an ordinal state based potential game, which is proved that it exists a recurrent state equilibrium point that maximizes system throughput. Furthermore, we propose two different variants of Max-logit learning algorithm based on these two games respectively: one is a simultaneous learning algorithm with less information exchange, which achieves the best Nash equilibria point of the exact potential game and the other is an efficient learning algorithm for the ordinal state based potential game, which can converge to the global optimization solution. Finally, numerical results are given to validate that theoretical findings.

Optimized sampling distribution based on nonparametric learning for improved compressive sensing performance

In this work, an optimized nonparametric learning approach for obtaining the data-guided sampling distribution is proposed, where a probability density function (pdf) is learned in a nonparametric manner based on past measurements from similar types of signals. This learned sampling distribution is then used to better optimize the sampling process based on the underlying signal characteristics. A realization of this stochastic learning approach for compressive sensing of imaging data is introduced via a stochastic Monte Carlo optimization strategy to learn a nonparametric sampling distribution based on visual saliency. Experiments were performed using different types of signals such as fluorescence microscopy images and laser range measurements. Results show that the proposed optimized sampling method which is based on nonparametric stochastic learning outperforms significantly the previously proposed approach. The proposed method is achieves higher reconstruction signal to noise ratios at the same compression rates across all tested types of signals.