Learning feature alignment and dual correlation for few‐shot image classification

Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples.To perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample features.Most FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment strategy.However,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation calculations.Therefore,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation computation.Moreover,a dual correlation module to learn the hard and soft correlations was developed by the authors.This module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled features.Using both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for classification.Experimental results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.

A Network Traffic Classification Model Based on Metric Learning

Attacks on websites and network servers are among the most critical threats in network security.Network behavior identification is one of the most effective ways to identify malicious network intrusions.Analyzing abnormal network traffic patterns and traffic classification based on labeled network traffic data are among the most effective approaches for network behavior identification.Traditional methods for network traffic classification utilize algorithms such as Naive Bayes,Decision Tree and XGBoost.However,network traffic classification,which is required for network behavior identification,generally suffers from the problem of low accuracy even with the recently proposed deep learning models.To improve network traffic classification accuracy thus improving network intrusion detection rate,this paper proposes a new network traffic classification model,called ArcMargin,which incorporates metric learning into a convolutional neural network(CNN)to make the CNN model more discriminative.ArcMargin maps network traffic samples from the same category more closely while samples from different categories are mapped as far apart as possible.The metric learning regularization feature is called additive angular margin loss,and it is embedded in the object function of traditional CNN models.The proposed ArcMargin model is validated with three datasets and is compared with several other related algorithms.According to a set of classification indicators,the ArcMargin model is proofed to have better performances in both network traffic classification tasks and open-set tasks.Moreover,in open-set tasks,the ArcMargin model can cluster unknown data classes that do not exist in the previous training dataset.

Fundamental error in tree-based machine learning model selection for reservoir characterisation

Over the past two decades,machine learning techniques have been extensively used in predicting reservoir properties.While this approach has significantly contributed to the industry,selecting an appropriate model is still challenging for most researchers.Relying solely on statistical metrics to select the best model for a particular problem may not always be the most effective approach.This study encourages researchers to incorporate data visualization in their analysis and model selection process.To evaluate the suitability of different models in predicting horizontal permeability in the Volve field,wireline logs were used to train Extra-Trees,Ridge,Bagging,and XGBoost models.The Random Forest feature selection technique was applied to select the relevant logs as inputs for the models.Based on statistical metrics,the Extra-Trees model achieved the highest test accuracy of 0.996,RMSE of 19.54 mD,and MAE of 3.18 mD,with XGBoost coming in second.However,when the results were visualised,it was discovered that the XGBoost model was more suitable for the problem being tackled.The XGBoost model was a better predictor within the sandstone interval,while the Extra-Trees model was more appropriate in non-sandstone intervals.Since this study aims to predict permeability in the reservoir interval,the XGBoost model is the most suitable.These contrasting results demonstrate the importance of incorporating data visualisation techniques as an evaluation metric.Given the heterogeneity of the subsurface,relying solely on statistical metrics may not be sufficient to determine which model is best suited for a particular problem.

Identification of Similar Air Traffic Scenes with Active Metric Learning

The rapid growth of air traffic has continuously increased the workload of controllers,which has become an important factor restricting sector capacity.If similar traffic scenes can be identified,the historical decision-making experience may be used to help controllers decide control strategies quickly.Considering that there are many traffic scenes and it is hard to label them all,in this paper,we propose an active SVM metric learning(ASVM2L)algorithm to measure and identify the similar traffic scenes.First of all,we obtain some traffic scene samples correctly labeled by experienced air traffic controllers.We design an active sampling strategy based on voting difference to choose the most valuable unlabeled samples and label them.Then the metric matrix of all the labeled samples is learned and used to complete the classification of traffic scenes.We verify the effectiveness of ASVM2L on standard data sets,and then use it to measure and classify the traffic scenes on the historical air traffic data set of the Central South Sector of China.The experimental results show that,compared with other existing methods,the proposed method can use the information of traffic scene samples more thoroughly and achieve better classification performance under limited labeled samples.

A Hybrid Machine Learning Approach for Improvised QoE in Video Services over 5G Wireless Networks

Video streaming applications have grown considerably in recent years.As a result,this becomes one of the most significant contributors to global internet traffic.According to recent studies,the telecommunications industry loses millions of dollars due to poor video Quality of Experience(QoE)for users.Among the standard proposals for standardizing the quality of video streaming over internet service providers(ISPs)is the Mean Opinion Score(MOS).However,the accurate finding of QoE by MOS is subjective and laborious,and it varies depending on the user.A fully automated data analytics framework is required to reduce the inter-operator variability characteristic in QoE assessment.This work addresses this concern by suggesting a novel hybrid XGBStackQoE analytical model using a two-level layering technique.Level one combines multiple Machine Learning(ML)models via a layer one Hybrid XGBStackQoE-model.Individual ML models at level one are trained using the entire training data set.The level two Hybrid XGBStackQoE-Model is fitted using the outputs(meta-features)of the layer one ML models.The proposed model outperformed the conventional models,with an accuracy improvement of 4 to 5 percent,which is still higher than the current traditional models.The proposed framework could significantly improve video QoE accuracy.

Detecting Design Patterns in Object-Oriented Program Source Code by Using Metrics and Machine Learning

Detecting well-known design patterns in object-oriented program source code can help maintainers understand the design of a program. Through the detection, the understandability, maintainability, and reusability of object-oriented programs can be improved. There are automated detection techniques;however, many existing techniques are based on static analysis and use strict conditions composed on class structure data. Hence, it is difficult for them to detect and distinguish design patterns in which the class structures are similar. Moreover, it is difficult for them to deal with diversity in design pattern applications. To solve these problems in existing techniques, we propose a design pattern detection technique using source code metrics and machine learning. Our technique judges candidates for the roles that compose design patterns by using machine learning and measurements of several metrics, and it detects design patterns by analyzing the relations between candidates. It suppresses false negatives and distinguishes patterns in which the class structures are similar. As a result of experimental evaluations with a set of programs, we confirmed that our technique is more accurate than two conventional techniques.

A Fast Calculation of Metric Scores for Learning Bayesian Network

Frequent counting is a very so often required operation in machine learning algorithms. A typical machine learning task, learning the structure of Bayesian network （BN） based on metric scoring, is introduced as an example that heavily relies on frequent counting. A fast calculation method for frequent counting enhanced with two cache layers is then presented for learning BN. The main contribution of our approach is to eliminate comparison operations for frequent counting by introducing a multi-radix number system calculation. Both mathematical analysis and empirical comparison between our method and state-of-the-art solution are conducted. The results show that our method is dominantly superior to state-of-the-art solution in solving the problem of learning BN.

Geometry Flow-Based Deep Riemannian Metric Learning

Deep metric learning(DML)has achieved great results on visual understanding tasks by seamlessly integrating conventional metric learning with deep neural networks.Existing deep metric learning methods focus on designing pair-based distance loss to decrease intra-class distance while increasing interclass distance.However,these methods fail to preserve the geometric structure of data in the embedding space,which leads to the spatial structure shift across mini-batches and may slow down the convergence of embedding learning.To alleviate these issues,by assuming that the input data is embedded in a lower-dimensional sub-manifold,we propose a novel deep Riemannian metric learning(DRML)framework that exploits the non-Euclidean geometric structural information.Considering that the curvature information of data measures how much the Riemannian(nonEuclidean)metric deviates from the Euclidean metric,we leverage geometry flow,which is called a geometric evolution equation,to characterize the relation between the Riemannian metric and its curvature.Our DRML not only regularizes the local neighborhoods connection of the embeddings at the hidden layer but also adapts the embeddings to preserve the geometric structure of the data.On several benchmark datasets,the proposed DRML outperforms all existing methods and these results demonstrate its effectiveness.

Recognition of Group Activities Using Complex Wavelet Domain Based Cayley-Klein Metric Learning

A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric learning.Non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and multi-resolution.An improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient features.The extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization problem.The group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric learning.Experimental results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.

EM-Gaze:eye context correlation and metric learning for gaze estimation

In recent years,deep learning techniques have been used to estimate gaze-a significant task in computer vision and human-computer interaction.Previous studies have made significant achievements in predicting 2D or 3D gazes from monocular face images.This study presents a deep neural network for 2D gaze estimation on mobile devices.It achieves state-of-the-art 2D gaze point regression error,while significantly improving gaze classification error on quadrant divisions of the display.To this end,an efficient attention-based module that correlates and fuses the left and right eye contextual features is first proposed to improve gaze point regression performance.Subsequently,through a unified perspective for gaze estimation,metric learning for gaze classification on quadrant divisions is incorporated as additional supervision.Consequently,both gaze point regression and quadrant classification perfor-mances are improved.The experiments demonstrate that the proposed method outperforms existing gaze-estima-tion methods on the GazeCapture and MPIIFaceGaze datasets.

Exponential Continuous Non-Parametric Neural Identifier With Predefined Convergence Velocity

This paper addresses the design of an exponential function-based learning law for artificial neural networks(ANNs)with continuous dynamics.The ANN structure is used to obtain a non-parametric model of systems with uncertainties,which are described by a set of nonlinear ordinary differential equations.Two novel adaptive algorithms with predefined exponential convergence rate adjust the weights of the ANN.The first algorithm includes an adaptive gain depending on the identification error which accelerated the convergence of the weights and promotes a faster convergence between the states of the uncertain system and the trajectories of the neural identifier.The second approach uses a time-dependent sigmoidal gain that forces the convergence of the identification error to an invariant set characterized by an ellipsoid.The generalized volume of this ellipsoid depends on the upper bounds of uncertainties,perturbations and modeling errors.The application of the invariant ellipsoid method yields to obtain an algorithm to reduce the volume of the convergence region for the identification error.Both adaptive algorithms are derived from the application of a non-standard exponential dependent function and an associated controlled Lyapunov function.Numerical examples demonstrate the improvements enforced by the algorithms introduced in this study by comparing the convergence settings concerning classical schemes with non-exponential continuous learning methods.The proposed identifiers overcome the results of the classical identifier achieving a faster convergence to an invariant set of smaller dimensions.

Metric Learning for Semantic Metric Learning for Semantic⁃Based Clothes Retrieval

Existing clothes retrieval methods mostly adopt binary supervision in metric learning.For each iteration,only the clothes belonging to the same instance are positive samples,and all other clothes are“indistinguishable”negative samples,which causes the following problem.The relevance between the query and candidates is only treated as relevant or irrelevant,which makes the model difficult to learn the continu-ous semantic similarities between clothes.Clothes that do not belong to the same instance are completely considered irrelevant and are uni-formly pushed away from the query by an equal margin in the embedding space,which is not consistent with the ideal retrieval results.Moti-vated by this,we propose a novel method called semantic-based clothes retrieval(SCR).In SCR,we measure the semantic similarities be-tween clothes and design a new adaptive loss based on these similarities.The margin in the proposed adaptive loss can vary with different se-mantic similarities between the anchor and negative samples.In this way,more coherent embedding space can be learned,where candidates with higher semantic similarities are mapped closer to the query than those with lower ones.We use Recall@K and normalized Discounted Cu-mulative Gain(nDCG)as evaluation metrics to conduct experiments on the DeepFashion dataset and have achieved better performance.

Vehicle Matching Based on Similarity Metric Learning

With the development of new media technology,vehicle matching plays a further significant role in video surveillance systems.Recent methods explored the vehicle matching based on the feature extraction.Meanwhile,similarity metric learning also has achieved enormous progress in vehicle matching.But most of these methods are less effective in some realistic scenarios where vehicles usually be captured in different times.To address this cross-domain problem,we propose a cross-domain similarity metric learning method that utilizes theGANto generate vehicle imageswith another domain and propose the two-channel Siamese network to learn a similarity metric from both domains(i.e.,Day pattern or Night pattern)for vehicle matching.To exploit properties and relationships among vehicle datasets,we first apply the domain transformer to translate the domain of vehicle images,and then utilize the two-channel Siamese network to extract features from both domains for better feature similarity learning.Experimental results illustrate that our models achieve improvements over state-of-the-arts.

Software Defect Prediction Using Supervised Machine Learning and Ensemble Techniques: A Comparative Study

An essential objective of software development is to locate and fix defects ahead of schedule that could be expected under diverse circumstances. Many software development activities are performed by individuals, which may lead to different software bugs over the development to occur, causing disappointments in the not-so-distant future. Thus, the prediction of software defects in the first stages has become a primary interest in the field of software engineering. Various software defect prediction (SDP) approaches that rely on software metrics have been proposed in the last two decades. Bagging, support vector machines (SVM), decision tree (DS), and random forest (RF) classifiers are known to perform well to predict defects. This paper studies and compares these supervised machine learning and ensemble classifiers on 10 NASA datasets. The experimental results showed that, in the majority of cases, RF was the best performing classifier compared to the others.

Rock mass structural recognition from drill monitoring technology in underground mining using discontinuity index and machine learning techniques

A procedure to recognize individual discontinuities in rock mass from measurement while drilling(MWD)technology is developed,using the binary pattern of structural rock characteristics obtained from in-hole images for calibration.Data from two underground operations with different drilling technology and different rock mass characteristics are considered,which generalizes the application of the methodology to different sites and ensures the full operational integration of MWD data analysis.Two approaches are followed for site-specific structural model building:a discontinuity index(DI)built from variations in MWD parameters,and a machine learning(ML)classifier as function of the drilling parameters and their variability.The prediction ability of the models is quantitatively assessed as the rate of recognition of discontinuities observed in borehole logs.Differences between the parameters involved in the models for each site,and differences in their weights,highlight the site-dependence of the resulting models.The ML approach offers better performance than the classical DI,with recognition rates in the range 89%to 96%.However,the simpler DI still yields fairly accurate results,with recognition rates 70%to 90%.These results validate the adaptive MWD-based methodology as an engineering solution to predict rock structural condition in underground mining operations.

Deep Learning Aided SCL Decoding of Polar Codes with Shifted-Pruning

Recently,a generalized successive cancellation list(SCL)decoder implemented with shiftedpruning(SP)scheme,namely the SCL-SP-ωdecoder,is presented for polar codes,which is able to shift the pruning window at mostωtimes during each SCL re-decoding attempt to prevent the correct path from being eliminated.The candidate positions for applying the SP scheme are selected by a shifting metric based on the probability that the elimination occurs.However,the number of exponential/logarithm operations involved in the SCL-SP-ωdecoder grows linearly with the number of information bits and list size,which leads to high computational complexity.In this paper,we present a detailed analysis of the SCL-SP-ωdecoder in terms of the decoding performance and complexity,which unveils that the choice of the shifting metric is essential for improving the decoding performance and reducing the re-decoding attempts simultaneously.Then,we introduce a simplified metric derived from the path metric(PM)domain,and a custom-tailored deep learning(DL)network is further designed to enhance the efficiency of the proposed simplified metric.The proposed metrics are both free of transcendental functions and hence,are more hardware-friendly than the existing metrics.Simulation results show that the proposed DL-aided metric provides the best error correction performance as comparison with the state of the art.

A Local Quadratic Embedding Learning Algorithm and Applications for Soft Sensing

Inspired by the tremendous achievements of meta-learning in various fields,this paper proposes the local quadratic embedding learning(LQEL)algorithm for regression problems based on metric learning and neural networks(NNs).First,Mahalanobis metric learning is improved by optimizing the global consistency of the metrics between instances in the input and output space.Then,we further prove that the improved metric learning problem is equivalent to a convex programming problem by relaxing the constraints.Based on the hypothesis of local quadratic interpolation,the algorithm introduces two lightweight NNs;one is used to learn the coefficient matrix in the local quadratic model,and the other is implemented for weight assignment for the prediction results obtained from different local neighbors.Finally,the two sub-mod els are embedded in a unified regression framework,and the parameters are learned by means of a stochastic gradient descent(SGD)algorithm.The proposed algorithm can make full use of the information implied in target labels to find more reliable reference instances.Moreover,it prevents the model degradation caused by sensor drift and unmeasurable variables by modeling variable differences with the LQEL algorithm.Simulation results on multiple benchmark datasets and two practical industrial applications show that the proposed method outperforms several popular regression methods.

Hybrid Deep Learning-Improved BAT Optimization Algorithm for Soil Classification Using Hyperspectral Features

Now a days,Remote Sensing(RS)techniques are used for earth observation and for detection of soil types with high accuracy and better reliability.This technique provides perspective view of spatial resolution and aids in instantaneous measurement of soil’s minerals and its characteristics.There are a few challenges that is present in soil classification using image enhancement such as,locating and plotting soil boundaries,slopes,hazardous areas,drainage condition,land use,vegetation etc.There are some traditional approaches which involves few drawbacks such as,manual involvement which results in inaccuracy due to human interference,time consuming,inconsistent prediction etc.To overcome these draw backs and to improve the predictive analysis of soil characteristics,we propose a Hybrid Deep Learning improved BAT optimization algorithm(HDIB)for soil classification using remote sensing hyperspectral features.In HDIB,we propose a spontaneous BAT optimization algorithm for feature extraction of both spectral-spatial features by choosing pure pixels from the Hyper Spectral(HS)image.Spectral-spatial vector as training illustrations is attained by merging spatial and spectral vector by means of priority stacking methodology.Then,a recurring Deep Learning(DL)Neural Network(NN)is used for classifying the HS images,considering the datasets of Pavia University,Salinas and Tamil Nadu Hill Scene,which in turn improves the reliability of classification.Finally,the performance of the proposed HDIB based soil classifier is compared and analyzed with existing methodologies like Single Layer Perceptron(SLP),Convolutional Neural Networks(CNN)and Deep Metric Learning(DML)and it shows an improved classification accuracy of 99.87%,98.34%and 99.9%for Tamil Nadu Hills dataset,Pavia University and Salinas scene datasets respectively.

Weed Classification Using Particle Swarm Optimization and Deep Learning Models

Weed is a plant that grows along with nearly allfield crops,including rice,wheat,cotton,millets and sugar cane,affecting crop yield and quality.Classification and accurate identification of all types of weeds is a challenging task for farmers in earlier stage of crop growth because of similarity.To address this issue,an efficient weed classification model is proposed with the Deep Convolutional Neural Network(CNN)that implements automatic feature extraction and performs complex feature learning for image classification.Throughout this work,weed images were trained using the proposed CNN model with evolutionary computing approach to classify the weeds based on the two publicly available weed datasets.The Tamil Nadu Agricultural University(TNAU)dataset used as afirst dataset that consists of 40 classes of weed images and the other dataset is from Indian Council of Agriculture Research–Directorate of Weed Research(ICAR-DWR)which contains 50 classes of weed images.An effective Particle Swarm Optimization(PSO)technique is applied in the proposed CNN to automa-tically evolve and improve its classification accuracy.The proposed model was evaluated and compared with pre-trained transfer learning models such as GoogLeNet,AlexNet,Residual neural Network(ResNet)and Visual Geometry Group Network(VGGNet)for weed classification.This work shows that the performance of the PSO assisted proposed CNN model is significantly improved the success rate by 98.58%for TNAU and 97.79%for ICAR-DWR weed datasets.

Predicting Future Cryptocurrency Prices Using Machine Learning Algorithms

Cryptocurrency price prediction has garnered significant attention due to the growing importance of digital assets in the financial landscape. This paper presents a comprehensive study on predicting future cryptocurrency prices using machine learning algorithms. Open-source historical data from various cryptocurrency exchanges is utilized. Interpolation techniques are employed to handle missing data, ensuring the completeness and reliability of the dataset. Four technical indicators are selected as features for prediction. The study explores the application of five machine learning algorithms to capture the complex patterns in the highly volatile cryptocurrency market. The findings demonstrate the strengths and limitations of the different approaches, highlighting the significance of feature engineering and algorithm selection in achieving accurate cryptocurrency price predictions. The research contributes valuable insights into the dynamic and rapidly evolving field of cryptocurrency price prediction, assisting investors and traders in making informed decisions amidst the challenges posed by the cryptocurrency market.