Two-level Learning Research Articles

Scaled boundary finite element based two-level learning approach for structural flaw identification

A comprehensive framework that combines classification and regression techniques through machine learning (ML) algorithms to address the inverse problem of flaw identification and quantification is proposed. The framework uses the scaled boundary finite element method (SBFEM) and quadtree (octree mesh in 3D) to compute displacements for various flaw shapes and specified boundary conditions. The flaw data, such as their numbers, location, and size, along with the displacement data, serve as the input for ML models. A random forest model is used to predict the number of flaws, while an artificial neural network (ANN) employing a fully connected multi-layer perceptron is utilized to predict flaw locations and sizes. The framework underwent rigorous testing to identify the number and location of multiple flaws (circular and elliptical) in 2D structures. The accuracy of the classification and regression models for flaw detection, ranging from one to four circular flaws, is observed to be 98%. As an extension of its capabilities, the proposed model successfully identifies multiple flaws and their features in 3D structures as well with 98% accuracy, demonstrating the robustness of the proposed approach.

Accurate classification of land use and land cover using a boundary-specific two-level learning approach augmented with auxiliary features in Google Earth Engine.

Land use land cover (LULC) classification using remote sensing images is a valuable resource in various fields such as climate change, urban development, and land degradation monitoring. The city of Madurai in India is known for its diverse geographical elements and rich heritage, which includes the cultural sport of "Jallikattu": whose main competitor, the zebusare deeply affected by the conversion of their waterbodies and pastures into concrete jungles. Hence, monitoring land degradation is vital in preserving the geography and cultural heritage of the study area, Madurai. The "Landsat 8 Operational Land Imager tier_2 collection_2 Level_2 Surface Reflectance" image was taken for this study. The LULC classification is performed based on the following classes: forest, agriculture, urban, water bodies, uncultivated land, and bare land. The objective of the study is to incorporate auxiliary features to spectral and textural features along with a simple non-iterative clustering (SNIC) segmentation algorithm and implement a boundary-specific two-level learning approach based on support vector machines (SVM) and k nearest neighbors (kNN) classification algorithms. The overall accuracy (OA) of 95.78% and 0 .94 Kappa score (K) were obtained using a boundary-specific two-level model augmented with auxiliary feature and SNIC algorithm in comparison to PB, OB, and OBS, which achieve OA (K) of 81% (0.76), 91% (0.89), and 94.42% (0.92), respectively. The results demonstrate a notable enhancement in overall classification accuracy when augmenting the features and refining classification decisions using a boundary-specific two-level learning approach.

Intelligent routing algorithm for wireless sensor networks dynamically guided by distributed neural networks

Using reinforcement learning to adjust the power balance of sensor nodes dynamically is an essential approach for extending the lifetime of wireless sensor networks (WSNs), which makes sensor nodes adapt to changing environments by calculating optimal decision solutions in real time. However, as WSN grows, error propagation cannot keep up with topological changes in the networks, which prevents the sensor nodes’ routing decisions from being timely optimized. In this paper, we propose the DNN-HR algorithm, which optimizes the reinforcement learning process of WSN in three ways. First, this paper constructs a two-level learning structure. Discrete nodes perform reinforcement learning during the interaction with their neighboring nodes. Simultaneously, the neural networks that fit the V values guide the underlying nodes’ learning. Second, the algorithm divides the sensor networks into two-level subspaces according to their geographic locations, and cluster heads are elected in each subspace to form weight incremental propagation trees. Third, each sensor node sends the weight increments it learned to its first-level cluster head. At the first-level cluster head, the weight increments sent by multiple nodes are received and accumulated, and then the results are sent to the second-level cluster head. The base station acquires the weight increments of all the second-level cluster heads and then broadcasts the updated neural network weights to all the WSN nodes. Experiments determine the appropriate heuristic parameters. Compared to other algorithms, the experiments show that our proposed scheme significantly improves the packet delivery rate, node survival rate, and energy standard deviation of nodes.

Demand Side Management and Peer-to-Peer Energy Trading for Industrial Users Using Two-Level Multi-Agent Reinforcement Learning

Over the past few years, with more concerns on energy equity, energy security and environmental sustainability, peer-to-peer (P2P) energy trading market has increasingly attracted attention to energy users. With the rising electricity price and the growing public doubt to unsustainable development, more efforts are given to the integration between P2P energy trading and industrial practice. To date, the current research work has emphasized electricity cost reduction using demandside management (DSM) and P2P energy trading market to promote energy sharing and create a win–win situation for all industrial market participants. However, less attention has been given to evaluating industrial production. With this attention, this paper formulates a cost minimization problem for multiple discrete manufacturers, where DSM and P2P energy trading market are integrated to optimize manufacturing productivity and energy consumption. Moreover, this paper proposes a two-level reinforcement learning (RL) method to obtain the optimal DSM and energy trading strategies for discrete manufacturers. Unlike the existing RL approaches, the proposed method depicts a twolevel learning approach, where the upper-level program suggests a production plan for the manufacturer to improve the cost return, while the lower-level program optimizes the net benefits. Further, to verify the performance of the proposed method, simulations are conducted based on four different case studies, including different weather and load conditions. Numerical results demonstrate that the proposed algorithm provides a better production plan with enhanced learning speed and economic benefits compared to the existing RL approaches.

A Modified Particle Swarm Optimization Algorithm for Optimizing Artificial Neural Network in Classification Tasks

Artificial neural networks (ANNs) have achieved great success in performing machine learning tasks, including classification, regression, prediction, image processing, image recognition, etc., due to their outstanding training, learning, and organizing of data. Conventionally, a gradient-based algorithm known as backpropagation (BP) is frequently used to train the parameters’ value of ANN. However, this method has inherent drawbacks of slow convergence speed, sensitivity to initial solutions, and high tendency to be trapped into local optima. This paper proposes a modified particle swarm optimization (PSO) variant with two-level learning phases to train ANN for image classification. A multi-swarm approach and a social learning scheme are designed into the primary learning phase to enhance the population diversity and the solution quality, respectively. Two modified search operators with different search characteristics are incorporated into the secondary learning phase to improve the algorithm’s robustness in handling various optimization problems. Finally, the proposed algorithm is formulated as a training algorithm of ANN to optimize its neuron weights, biases, and selection of activation function based on the given classification dataset. The ANN model trained by the proposed algorithm is reported to outperform those trained by existing PSO variants in terms of classification accuracy when solving the majority of selected datasets, suggesting its potential applications in challenging real-world problems, such as intelligent condition monitoring of complex industrial systems.

Two-Level Machine Learning Driven Intrusion Detection Model for IoT Environments

Two-Level Machine Learning Driven Intrusion Detection Model for IoT Environments

A Two-Level Learning Based Approach for Fake Portrait Video Tracing

A Two-Level Learning Based Approach for Fake Portrait Video Tracing

A two level learning model for authorship authentication.

Nowadays, forensic authorship authentication plays a vital role in identifying the number of unknown authors as a result of the world’s rapidly rising internet use. This paper presents two-level learning techniques for authorship authentication. The learning technique is supplied with linguistic knowledge, statistical features, and vocabulary features to enhance its efficiency instead of learning only. The linguistic knowledge is represented through lexical analysis features such as part of speech. In this study, a two-level classifier has been presented to capture the best predictive performance for identifying authorship. The first classifier is based on vocabulary features that detect the frequency with which each author uses certain words. This classifier’s results are fed to the second one which is based on a learning technique. It depends on lexical, statistical and linguistic features. All of the three sets of features describe the author’s writing styles in numerical forms. Through this work, many new features are proposed for identifying the author’s writing style. Although, the proposed new methodology is tested for Arabic writings, it is general and can be applied to any language. According to the used machine learning models, the experiment carried out shows that the trained two-level classifier achieves an accuracy ranging from 94% to 96.16%.

Stock Market Forecasting Model From Multi News Data Source Using a Two-Level Learning Algorithm

Stock prediction retains the attention of a large part of the community. The emergence of new indicators mostly extracted from the web makes this domain of research challenging and in a continuous evolution. The present work tries to address the question of how to model financial news from multi-data source for the purpose of forecasting stock movement. We combined different news sources to enhance the accuracy of stock movement prediction. Data are collected from four financial news websites and proceeded individually by Support Vector Machine (SVM) algorithm then we aggregate outputs using an Artificial Neural Network (ANN) algorithm. Experiments were conducted and the results have shown that the designed two-level learning SVC&ANN algorithm has achieved better accuracy than simple news analysis models using a single information source.

Level-wise driving knowledge induction for embedded automatic train driving system

Automatic driving of trains can significantly reduce the energy cost and enhance the operating efficiency and safety. The automatic train driving system has to be an embedded system that can run onboard with low power, which necessitates an efficient inference model. In this article, a level-wise driving knowledge induction approach is proposed for embedded automatic train driving systems. The coincident driving patterns in the records of drivers with different experience levels suggest the suitability of a driving experience knowledge rule induction approach. We design a two-level learning approach to obtain both the driving experience pattern in fuzzy rule-based knowledge form and the detailed parameters of velocity and gear by regression learning methods. With 8.93% energy consumption reduction compared with average human drivers, the experiments indicate the effectiveness of our approach.

EEG-Based Driving Fatigue Detection Using a Two-Level Learning Hierarchy Radial Basis Function.

Electroencephalography (EEG)-based driving fatigue detection has gained increasing attention recently due to the non-invasive, low-cost, and potable nature of the EEG technology, but it is still challenging to extract informative features from noisy EEG signals for driving fatigue detection. Radial basis function (RBF) neural network has drawn lots of attention as a promising classifier due to its linear-in-the-parameters network structure, strong non-linear approximation ability, and desired generalization property. The RBF network performance heavily relies on network parameters such as the number of the hidden nodes, number of the center vectors, width, and output weights. However, global optimization methods that directly optimize all the network parameters often result in high evaluation cost and slow convergence. To enhance the accuracy and efficiency of EEG-based driving fatigue detection model, this study aims to develop a two-level learning hierarchy RBF network (RBF-TLLH) which allows for global optimization of the key network parameters. Experimental EEG data were collected, at both fatigue and alert states, from six healthy participants in a simulated driving environment. Principal component analysis was first utilized to extract features from EEG signals, and the proposed RBF-TLLH was then employed for driving status (fatigue vs. alert) classification. The results demonstrated that the proposed RBF-TLLH approach achieved a better classification performance (mean accuracy: 92.71%; area under the receiver operating curve: 0.9199) compared to other widely used artificial neural networks. Moreover, only three core parameters need to be determined using the training datasets in the proposed RBF-TLLH classifier, which increases its reliability and applicability. The findings demonstrate that the proposed RBF-TLLH approach can be used as a promising framework for reliable EEG-based driving fatigue detection.

Community Preserving Network Embedding Based on Memetic Algorithm

Network embedding aims to embed network nodes into a low-dimensional and continuous vector space, which can benefit various downstream network analysis tasks. As it is an emerging topic in recent years, a variety of methods have been proposed to learn representations by preserving a network topology structure. However, it still remains challenging to incorporate a community structure into network embedding, which is ignored by most of the methods. In this paper, we present a novel memetic algorithm for network embedding, which is termed as MemeRep. As a matter of fact, the community structure is preserved by optimizing the modularity density. In our methods, genetic algorithm is adopted to optimize a population of solutions, and a problem-specific local search procedure with the two-level learning strategies is designed to accelerate the optimization process. The first-level learning strategy enables each node to learn from its neighbors, while the second-level learning strategy expands the learning area, which enables each node to learn from communities. Experiments on real-world and computer-generated networks show that the proposed algorithm outperforms several state-of-the-art methods in visualization, node classification, and community detection.

Users First: A Robust Two-Level Learning of Power Control in Uplink Ultra-Dense HetNets

In this article, power control of uplink connection in the ultra-dense heterogeneous networks (HetNets), which are studied as different types of access points (APs), is investigated. It is demonstrated that an efficient performance of users during the uplink transmission is limited to the issue of per-user power control. Although the per-user power control allows users to transmit with full power to maintain a stable connection, it also causes a higher outage probability during the uplink transmission. In light of this, we propose a robust distributed energy-efficient scheme for uplink power control in HetNets, which confronts the per-user power control problem and coordination of the multi-user interferences. Therefore, firstly, Jarvic-Patric (JP) algorithm is adopted for the users' clustering. Unlike the traditional JP algorithm, conditions for the formation of users' clustering are extended with a term named the degree of membership in this article. Secondly, the distributed energy efficiency (EE) problem is formulated as the mean-metric of the EE, i.e., a sum of users' cooperative EE functions to address the cooperation problem among clustered interfering users at the local level and coordination of multi-user interferences at a global level. The formulation of the EE problem in this fashion reveals the interdependence of power optimization at local and global levels, which brings about the necessity of joint optimization. Hence, we propose a novel 2-level distributed cooperative learning (DCL) scheme, where users act as self-organized agents and optimize power control at local and global levels jointly. In the 2-level DCL scheme, clustered users are engaged in the cooperative game of power control at the local level to maximize the cooperative EE. Meantime, users communicate with each other to learn an online power control at the global level. Besides, a popular performance metric for a machine learning scheme named regret is demonstrated for the 2-level DCL scheme. Finally, the numerical results demonstrate that the proposed scheme significantly improves the EE compared to existing works.

RETRACTED: Research on sports planning and stability control of humanoid robot table tennis

The humanoid robot has the human shape and has great advantages in assisting human life and work. The ability to work, especially in a dynamic, unstructured environment, is an important prerequisite for humanoid robots to assist humans in their mission. Table tennis hitting involves a variety of key technologies such as visual inspection, trajectory planning, and artificial intelligence. It is an important research example that can reflect the ability of humanoid robots. First, according to the requirements of humanoid robots in the human living environment and the requirements of coordinating table tennis batting movements throughout the body, a method of establishing a humanoid robot model was analyzed, and a control system was designed to meet the needs of rapid table tennis batting. Second, a motion model construction and optimization algorithm based on intelligent learning training is proposed. Based on the parameter knowledge base established by the multiple trajectories of table tennis, a kind of electromagnetic mechanism and D-optimality regularized orthogonal minima are introduced. Design a two-pass method (regularized orthogonal least squares method + D-optimality) to learn the two-level learning method, which is used to learn the key parameters of the table tennis model. Third, for human-like robotic table tennis fast-moving, it is necessary to satisfy both the task and the stability requirements and to propose a stability-optimized whole-system coordinated trajectory planning method. The effectiveness of the proposed humanoid robot table tennis hitting motion planning and stability control method is verified by experiments.

Vulnerability Indexing to Saltwater Intrusion from Models at Two Levels using Artificial Intelligence Multiple Model (AIMM)

Unplanned groundwater exploitation in coastal aquifers results in water decline and consequently triggers saltwater intrusion (SWI). This study formulates a novel modeling strategy based on GALDIT method using Artificial Intelligence (AI) models for mapping the vulnerability to SWI. This AI-based modeling strategy is a two-level learning process, where vulnerability to SWI at Level 1 can be predicted by such models as Artificial Neural Network (ANN), Sugeno Fuzzy Logic (SFL), and Neuro-Fuzzy (NF); and their outputs serve as the input to the model at Level 2, such as Support Vector Machine (SVM). This model is applied to Urmia aquifer, west coast of Lake Urmia, where both are currently declining. The construction of the above four models both at Levels 1 and 2 provide tools for mapping the SWI vulnerability of the study area. Model performances in the paper are studied using RMSE and R2 metrics, where the models at Level 1 are found to be fit-for-purpose and the SVM at Level 2 is improved particularly with respect to the reduced scale of scatters in the results. Evaluating the result and groundwater samples by Piper diagram confirms the correspondence of SWI status with vulnerability index.

Redundancy reduction based node classification with attribute augmentation

Node classification for attributed graphs has attracted more and more researchers, it is very useful when labeled data are expensive and hard to obtain. However, most existing methods either only focus on node attribute data or are designed for working in single mode, resulting in omitting extra information and impairing classification performance. In view of this, in this work, we propose a semi-supervised method that can effectively incorporate various available prior information to augment the attribute matrix. This approach adds a two-level learning strategy to select and find those discriminative attributes for classification, and an augmentation step to combining various information, thereby reducing the redundancy exists between attributes and strengthening the community structure. It provides a unified way that can preserve both the node and edge information of the network. Finally, we use the classical classifier SVM to partition the induced augmented graph, we compare our method with 5 state-of-the-art methods on 4 data sets, the results confirm the effectiveness of our method.

Snippets: Tools for teaching on two levels

There are times when the opportunity to create a novel approach to teaching presents itself. This is true of the following innovative approach to teaching difficult concepts using a dual level method to enhance comprehension by undergraduate nursing students. The purpose of this case study was to use short video recordings called Snippets, which were previously recorded by the instructor as a new two-level learning activity to augment nursing students’ grasp of difficult concepts in a conventional didactic classroom, and to determine whether there was a difference in student satisfaction between didactic real-time presentations and didactic recorded 15-to-30 minute sessions with faculty present in the classroom. A mixed methods approach was used. Although there was no statistically significant difference in students’ satisfaction between the two methods of lecture as reported by survey methods, content analysis supported using Snippets as an ‘accessible’ strategy for teaching on two levels to enhance learning. It is useful teaching strategy available to faculty in conventional nursing programs to augment learning for particularly difficult conceptual material.

Low‐dose computed tomography scheme incorporating residual learning‐based denoising with iterative reconstruction

Low-dose computed tomography has been highly desirable because of the health concern about excessive radiation dose, but also challenging due to insufficient or noisy projection data. Compared with post-processing methods by directly denoising filtered back-projection images, iterative reconstruction achieves excellent performance but consumes a large number of iterations. In this Letter, a two-stage method is proposed by incorporating residual learning-based denoising with iterative reconstruction. First, an intermediate image is reconstructed by compressed sensing iterative reconstruction. Then, the image is denoised by a deep neural network. Specially, a network performing two-level residual learning is designed to strengthen denoising effect. Experimental results show that the proposed method outperforms iterative reconstruction with better numeric results and comparable visual performance while consuming fewer iterations.

Urban Commerce Distribution Analysis Based on Street View and Deep Learning

Urban commerce and its distribution have always been an important part of urban research. However, most previous studies were based on statistical data and did not reflect real street experience. Thanks to the Street View image and deep learning technology, researchers are able to carry out large scale studies from real human visual experience. In this article, we aim at sensing the commercial spaces in cities. In order to achieve this ultimate goal, deep learning is applied to process the raw data of Street View image. We disassemble the goal into three tasks: firstly, obtaining all the Street View images in a specific area; then classifying the Street View images according to the commercial facilities in it; and finally creating a visualization of the detected data into a map. For the first task, we get the road network coordinate information from the openstreetmap (OSM) website, set the sampling point on the road, and then download the Street View images of the sampling points' coordinate through the API provided by Baidumap. For the second task, we adopt a two-level learning strategy rather than directly using Deep Convolutional Neural Network for classification. For the final task, we choose the heat map as the expression of the results and draw the map by the existing GIS software. Furthermore, the results from this study can be conveniently combined with other data because of the use of street-network-based data structure. An application of this method combines with street-network data, the calculation of a city's 15-minute commercial service circle coverage is also shown in this study.

A two-level learning strategy based memetic algorithm for enhancing community robustness of networks

Community structure is a natural and inherent property of complex networks which can reflect their potential functionality. When the robustness of a network is improved, its community structure should be preserved as much as possible. However, most earlier studies only considered enhancing the network robustness and ignored the analysis of the community structure, which may alter the original topological structure and functionality of networks. In this paper, we propose a new memetic algorithm (MA-CR) with a two-level learning strategy to enhance the community robustness of networks, while maintaining the degree distribution and community structure. The proposed MA-CR is a hybrid global-local heuristic search methodology which adopts genetic algorithm as the global search and the proposed two-level learning strategy as the local search. The two-level learning strategy is designed based on the potential characteristics of the node structure and community structure of networks, which aims at mitigating two-level targeted attacks. Experiments on synthetic scale-free networks as well as real-world networks demonstrate the effectiveness and stability of the proposed algorithm as compared with several state-of-the-art algorithms.