Adaptive Learning Method Research Articles

Adaptive Latent Graph Representation Learning for Image-Text Matching.

Image-text matching is a challenging task due to the modality gap. Many recent methods focus on modeling entity relationships to learn a common embedding space of image and text. However, these methods suffer from distractions of entity relationships such as irrelevant visual regions in an image and noisy textual words in a text. In this paper, we propose an adaptive latent graph representation learning method to reduce the distractions of entity relationships for image-text matching. Specifically, we use an improved graph variational autoencoder to separate the distracting factors and latent factor of relationships and jointly learn latent textual graph representations, latent visual graph representations, and a visual-textual graph embedding space. We also introduce an adaptive cross-attention mechanism to perform feature attending on the latent graph representations across images and texts, thus further narrowing the modality gap to boost the matching performance. Extensive experiments on two public datasets, Flickr30K and COCO, show the effectiveness of our method.

A Comparative Study of Situation Awareness-Based Decision-Making Model Reinforcement Learning Adaptive Automation in Evolving Conditions

Situation-awareness-based decision-making (SABDM) models constructed using cognitive maps and goal-direct task analysis techniques have been successfully used in decision support systems in safety-critical and mission-critical environments such as air traffic control and electrical energy distribution. Reinforcement learning (RL) and other machine learning techniques are used to automate situational awareness mental model parameter adjustments, reducing the expert work on the initial configuration and long-term maintenance without affecting the mental model’s structure and maintaining the situation-awareness-based decision-making model’s cognitive and explainability characteristics. Real-world models should evolve to cope with changes in the environmental conditions. This study evaluates the application of reinforcement learning as an online adaptive technique to adjust the situational-awareness mental model’s parameters under evolving conditions. We conducted evaluation experiments using real-world public datasets to compare the performance of the SABDM model with that of the reinforcement learning adaptation technique (SABDM/RL) and other adaptive machine learning methods under distinct concept drift evolving conditions. We measured the techniques’ overall and dynamic performance to understand how well they adapt to evolving environmental conditions. The experiments show that SABDM/RL performs similarly to modern online adaptive machine learning classification methods with the support of concept drift detection techniques while maintaining the mental model strength of the situation awareness-based systems.

Adaptive Fusion Feature Transfer Learning Method For NILM

Non-invasive load monitoring (NILM) aims to extract the power consumption of individual appliances from a smart meter that measures the total power consumption of all appliances. At present, deep learning methods have achieved leading results. However, the need for a large number of training data and the poor generalization ability of models limit the further development of NILM. To break through these limitations, this paper proposes an adaptive fusion feature transfer learning method. Firstly, to provide rich features for feature transfer, multiple feature extraction branches are used to extract temporal and spatial features from different perspectives. These features are fused for adaptive adjustment. Secondly, the attention mechanism is used to adapt the features extracted from the model of the source task so that they are more conducive to the model of the target task. Finally, abundant simulation experiments are performed for appliance transfer and house transfer, respectively. It is verified that the proposed method can achieve better results than the existing method by using only a small amount of training data and retraining a part of the new model.

An Adaptive Learning Method Based on Knowledge Graph

An Adaptive Learning Method Based on Knowledge Graph

Adaptive Dendritic Cell-Negative Selection Method for Earthquake Prediction

Earthquake prediction (EQP) is an extremely difficult task, which has been overcome by adopting various technologies, with no further transformation so far. The negative selection algorithm (NSA) is an artificial intelligence method based on the biological immune system. It is widely used in anomaly detection due to its advantages of requiring little normal data to detect anomalies, including historical seismic-events-based EQP. However, NSA can suffer from the undesirable effect of data drift, resulting in outdated normal patterns learned from data. To tackle this problem, the data changes must be detected and processed, stimulating fast algorithmic adaptation strategies. This study proposes a dendritic cell algorithm (DCA)-based adaptive learning method for drift detection and negative selection algorithm (DC-NSA) that dynamically adapts to new input data. First, this study adopts the Gutenberg–Richter (GR) law and other earthquake distribution laws to preprocess input data. Then, the NSA is employed for EQP, and then, the dendritic cell algorithm (DCA) is employed to detect changes to trigger gradient descent strategies and update the self-set in NSA. Finally, the proposed approach is implemented to predict the earthquakes of MW > 5 in Sichuan and the surroundings during the next month. The experimental results demonstrate that our proposed DC-NSA is superior to the existing state-of-the-art EQP approaches.

MATHNECT: Mathematics Motion Based Learning for Primary School

Courseware is now widely used in the process of learning and teaching, particularly at the primary school level and in mathematics classes. Students become less interested in learning mathematics because it involves abstract and complex concepts. Difficulty learning math is a profound and acknowledged difficulty among students throughout the generations. The way of teaching and learning mathematics has remained relatively the same in our education system. Students are unable to provide their entire focus in class because of the current educational system, which is sometimes boring and relies solely on the whiteboard as a medium of instruction. However, with today's technological advancements, this problem may be overcome. It can be used to enhance the current educational system by utilizing current technology. One of them is Kinect, this device is a motion-tracking technology that allows users to interact with applications by moving their bodies. The main objective of this Mathnect is to develop a motion-based learning environment by utilizing Kinect technology as a learning aid to improve student concentration and attention in mathematics class. This project is developed using a methodology ADDIE. The methodology of analysis employed in this phase, which includes content analysis, should be focused on the compatibility of the content and the target users. The game will be focusing on teaching simple mathematics number, which it will cover on basic numbers among primary school students. Thus, by implementing this project in primary schools, our educational environment can be improved to produce new adaptive learning methods. This Mathnect is beneficial for educators, students, and parents to be used in the classroom and can also be used for self-based learning. As a result, students will not be bored in the classroom at any time.

Remaining Useful Life Prediction Based on Multi-Representation Domain Adaptation

All current deep learning-based prediction methods for remaining useful life (RUL) assume that training and testing data have similar distributions, but the existence of various operating conditions, failure modes, and noise lead to insufficient data with similar distributions during the training process, thereby reducing RUL prediction performance. Domain adaptation can effectively solve this problem by learning the cross-domain invariant features of the source domain and target domain to reduce the distribution difference. However, most domain adaptive methods extract the source domain and target domain features into a single space for feature alignment, which may leave out effective information and affect the accuracy of prediction. To address this problem, we propose a data-driven approach named long short-term memory network and multi-representation domain adaptation (LSTM-MRAN). We standardize and process the degraded sensor data with a sliding time window, use LSTM to extract features from the degraded data, and mine the time series information between the data. Then, we use multiple substructures in multi-representation domain adaptation to extract features of the source domain and target domain from different spaces and align features by minimizing conditional maximum mean difference (CMMD) loss functions. The effectiveness of the method is verified by the CMAPSS dataset. Compared with methods without domain adaptation and other transfer learning methods, the proposed method provides more reliable RUL prediction results under datasets with different operating conditions and failure modes.

ReNAP: Relation network with adaptiveprototypical learning for few-shot classification

Traditional deep learning-based image classification methods often fail to recognize a new class that does not exist in the training dataset, particularly when the new class only has a small number of samples. Such a challenging and new learning problem is referred to as few-shot learning. In few-shot learning, the relation network (RelationNet) is a powerful method. However, in RelationNet and its state-of-the-art variants, the prototype of each class is obtained by a simple summation or average over the labeled samples. These simple sample statistics cannot accurately capture the distinct characteristics of the diverse classes of real-world images. To address this problem, in this paper, we propose the Relation Network with Adaptive Prototypical Learning method (ReNAP), which can learn the class prototypes adaptively and provide more accurate representations of the classes. More specifically, ReNAP embeds an adaptive prototypical learning module constructed by a convolutional network into RelationNet. Our ReNAP achieves superior classification performances to RelationNet and other state-of-the-art methods on four widely used benchmark datasets, FC100, CUB-200-2011, Stanford-Cars, and Stanford-Dogs.

An adaptive learning method for the fusion information of electronic nose and hyperspectral system to identify the egg quality

Data fusion technology based on the multi-sensor system can obtain the holistic properties of samples. However, multi-sensor data fusion will bring more redundant information, which will lead to low classification performance. In this work, a multi-data-fusion-attention network (MDFA-Net) is proposed, combined with the electronic nose (e-nose) and hyperspectral system to identify the egg quality. Firstly, the gas information and spectral information of eggs are obtained under different feeding conditions. Secondly, a feature adaptive learning (FAL) unit is designed to select effective information and enhance the ability of feature expression. Thirdly, based on the FAL unit, a decision network is formed to identify the fusion information of e-nose and hyperspectral system. Finally, compared with other deep learning network models, the accuracy of MDFA-Net is 99.88%, the precision is 99.87%, the recall is 99.88%, and the F 1 -score is 99.90%, which shows better classification performance and stability. • E-nose and hyperspectral system are applied to gain the quality information of egg. • An FAL unit is proposed to fuse the gas and spectral information. • Attention mechanism is proposed to adaptively focus on important features. • An MDFA-Net is proposed to achieve the decision of fusion information.

Robust cross-network node classification via constrained graph mutual information

The recent methods for cross-network node classification mainly exploit graph neural networks (GNNs) as feature extractor to learn expressive graph representations across the source and target graphs. However, GNNs are vulnerable to noisy factors, such as adversarial attacks or perturbations on the node features or graph structure, which can cause a significant negative impact on their learning performance. To this end, we propose a robust graph domain adaptive learning framework RGDAL which exploits an information-theoretic principle to filter the noisy factors for cross-network node classification. Specifically, RGDAL utilizes graph convolutional network (GCN) with constrained graph mutual information and an adversarial learning component to learn noise-resistant and domain-invariant graph representations. To overcome the difficulties of estimating the mutual information for the non independent and identically distributed (non-i.i.d.) graph structured data, we design a dynamic neighborhood sampling strategy that can discretize the graph and incorporate the graph structural information for mutual information estimation. Experimental results on two real-world graph datasets demonstrate that RGDAL shows better robustness for cross-network node classification compared with the SOTA graph adaptive learning methods.

Dynamic transfer partial least squares for domain adaptive regression

The traditional soft sensor models are based on the independent and identical distribution assumption, which are difficult to adapt to changes in data distribution under multiple operating conditions, resulting in model performance deterioration. The domain adaptive transfer learning methods learn knowledge in different domains by means of distribution alignment, which can reduce the impact of data distribution differences, and effectively improve the generalization ability of the model. However, most of the existing models established by domain adaptation methods are static models, which cannot reflect the dynamic characteristics of the system, and have limited prediction accuracy when applied to dynamic system modeling under multiple operating conditions. The dynamic system modeling methods can effectively extract the dynamic characteristics of the data, but they cannot deal with the concept drift problem caused by the change of data distribution. This paper proposes a new dynamic transfer partial least squares method, which maps the high-dimensional process data into the low-dimensional latent variable subspace, establishes the dynamic regression relationship between the latent variables and the labels, and realizes the systematic dynamic modeling, at the same time, the model adds regular terms for distribution alignment and structure preservation, which realizes dynamic alignment of data distribution difference. The effectiveness of the proposed method is validated on three publicly available industrial process datasets.

Subgraph Adaptive Structure-Aware Graph Contrastive Learning

Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.

Robust PPG Peak Detection Using Dilated Convolutional Neural Networks.

Accurate peak determination from noise-corrupted photoplethysmogram (PPG) signal is the basis for further analysis of physiological quantities such as heart rate. Conventional methods are designed for noise-free PPG signals and are insufficient for PPG signals with low signal-to-noise ratio (SNR). This paper focuses on enhancing PPG noise-resiliency and proposes a robust peak detection algorithm for PPG signals distorted due to noise and motion artifact. Our algorithm is based on convolutional neural networks (CNNs) with dilated convolutions. We train and evaluate the proposed method using a dataset collected via smartwatches under free-living conditions in a home-based health monitoring application. A data generator is also developed to produce noisy PPG data used for model training and evaluation. The method performance is compared against other state-of-the-art methods and is tested with SNRs ranging from 0 to 45 dB. Our method outperforms the existing adaptive threshold, transform-based, and machine learning methods. The proposed method shows overall precision, recall, and F1-score of 82%, 80%, and 81% in all the SNR ranges. In contrast, the best results obtained by the existing methods are 78%, 80%, and 79%. The proposed method proves to be accurate for detecting PPG peaks even in the presence of noise.

Adaptive Multi-Modal Fusion Framework for Activity Monitoring of People With Mobility Disability.

The development of activity recognition based on multi-modal data makes it possible to reduce human intervention in the process of monitoring. This paper proposes an efficient and cost-effective multi-modal sensing framework for activity monitoring, it can automatically identify human activities based on multi-modal data, and provide help to patients with moderate disabilities. The multi-modal sensing framework for activity monitoring relies on parallel processing of videos and inertial data. A new supervised adaptive multi-modal fusion method (AMFM) is used to process multi-modal human activity data. Spatio-temporal graph convolution network with adaptive loss function (ALSTGCN) is proposed to extract skeleton sequence features, and long short-term memory fully convolutional network (LSTM-FCN) module with adaptive loss function is adapted to extract inertial data features. An adaptive learning method is proposed at the decision level to learn the contribution of the two modalities to the classification results. The effectiveness of the algorithm is demonstrated on two public multi-modal datasets (UTD-MHAD and C-MHAD) and a new multi-modal dataset H-MHAD collected from our laboratory. The results show that the performance of the AMFM approach on three datasets is better than the performance of the video or the inertial-based single-modality model. The class-balanced cross-entropy loss function further improves the model performance based on the H-MHAD dataset. The accuracy of action recognition is 91.18%, and the recall rate of falling activity is 100%. The results illustrate that using multiple heterogeneous sensors to realize automatic process monitoring is a feasible alternative to the manual response.

RAKSHA - The Smart Security System

Web-based technology has improved drastically in the past decade. As a result, security technology has become a major help to protect our daily life. In this project, we propose a robust security based on face recognition system with security for gas and fire. In particular, we develop this system to give access into a room for authenticated users and help us in the condition where there is LPG gas leak or fire catch. The classifier is trained by using a new adaptive learning method. The training data are initially collected from live images. The accuracy of the classifier is incrementally improved as the user starts using the system. A novel method has been introduced to improve the classifier model by human interaction and social media. By using a deep learning framework- TensorFlow, it will be easy to reuse the framework to adopt with many devices and applications. In addition to face Security system, we are going with Pin conformation, OTP and Finger print series.

An adaptive graph learning method for automated molecular interactions and properties predictions

Improving drug discovery efficiency is a core and long-standing challenge in drug discovery. For this purpose, many graph learning methods have been developed to search potential drug candidates with fast speed and low cost. In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized their architectures and hyperparameters, making them lose advantage in repurposing to new data generated in drug discovery. Here we propose a flexible method that can adapt to any dataset and make accurate predictions. The proposed method employs an adaptive pipeline to learn from a dataset and output a predictor. Without any manual intervention, the method achieves far better prediction performance on all tested datasets than traditional methods, which are based on hand-designed neural architectures and other fixed items. In addition, we found that the proposed method is more robust than traditional methods and can provide meaningful interpretability. Given the above, the proposed method can serve as a reliable method to predict molecular interactions and properties with high adaptability, performance, robustness and interpretability. This work takes a solid step forward to the purpose of aiding researchers to design better drugs with high efficiency.

Event-triggered adaptive integral reinforcement learning method for zero-sum differential games of nonlinear systems with incomplete known dynamics

Event-triggered adaptive integral reinforcement learning method for zero-sum differential games of nonlinear systems with incomplete known dynamics

A weighted adaptive transfer learning for tool tip dynamics prediction of different machine tools

In the batch machining of manufacturing enterprises, there are always different machine tools of the same type used. Due to the influence of the uncertain degree of deterioration during the service period and other factors, there are great differences between different machine tools of the same type. These factors lead to different tool tip dynamics even for the same tool-tool holder assembly under the same conditions, thus affecting the prediction of stability in the milling process. In this paper, a weighted adaptive joint distribution adaptation transfer learning method was proposed to predict the position-speed dependent tool tip dynamics of different machine tools that had different service time. Firstly, a machine tool was selected as the source machine tool, and the corresponding tool tip dynamics were identified as the source data through different position-speed milling tests. Then, for the new same type of machine tools, that was, the target machine tools, only a few different position-speed combinations milling tests need to be carried out for the same tool, so as to identify the tool tip dynamics as the target data. Subsequently, a Kriging regression model for predicting the position-speed dependent tool tip dynamics of the target machine tool was trained by the proposed transfer learning method. Compared with the prediction results of the current transfer learning method, it was found that the average test errors of the natural frequency and damping ratio of the proposed method were minimum, which were 0.48% and 7.2% respectively. Finally, the accuracy and effectiveness of the proposed method were verified by the actual milling experiments.

Domain adaptation based transfer learning approach for solving PDEs on complex geometries

In machine learning, if the training data is independently and identically distributed as the test data then a trained model can make an accurate predictions for new samples of data. Conventional machine learning has a strong dependence on massive amounts of training data which are domain specific to understand their latent patterns. In contrast, Domain adaptation and Transfer learning methods are sub-fields within machine learning that are concerned with solving the inescapable problem of insufficient training data by relaxing the domain dependence hypothesis. In this contribution, this issue has been addressed and by making a novel combination of both the methods we develop a computationally efficient and practical algorithm to solve boundary value problems based on nonlinear partial differential equations. We adopt a meshfree analysis framework to integrate the prevailing geometric modelling techniques based on NURBS and present an enhanced deep collocation approach that also plays an important role in the accuracy of solutions. We start with a brief introduction on how these methods expand upon this framework. We observe an excellent agreement between these methods and have shown that how fine-tuning a pre-trained network to a specialized domain may lead to an outstanding performance compare to the existing ones. As proof of concept, we illustrate the performance of our proposed model on several benchmark problems.

The study of statistical features of the evolution of complex physical systems using adaptive machine learning methods

In this work, we discuss various machine learning methods and their implementation in the field of complex physical systems for the analysis of experimental data. These methods: classical machine learning, neural nets and deep learning allow greatly outperforming classical analysis methods by giving the algorithm the ability to “learn” and perform tasks adapting to the data provided and search. Neural nets and deep learning approaches are used to search for hidden patterns of the suggested input data that can’t be analyzed using common methods. This variety of methods can be applied to study collective phenomena in plasma and thermonuclear fusion on the basis of experimental data of physical experiments with a higher level of performance than classical approaches.