Reinforcement Learning Based Quantization Strategy Optimal Assignment Algorithm for Mixed Precision

The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to databit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determinethe optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantizationcan effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In thispaper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bitwidth is proposed, and reinforcement learning is used to automatically predict the mixed precision that meets theconstraints of hardware resources. In the state-space design, the standard deviation of weights is used to measurethe distribution difference of data, the execution speed feedback of simulated neural network accelerator inferenceis used as the environment to limit the action space of the agent, and the accuracy of the quantization model afterretraining is used as the reward function to guide the agent to carry out deep reinforcement learning training. Theexperimental results show that the proposed method obtains a suitable model layer-by-layer quantization strategyunder the condition that the computational resources are satisfied, and themodel accuracy is effectively improved.The proposed method has strong intelligence and certain universality and has strong application potential in thefield of mixed precision quantization and embedded neural network model deployment.

Learning Vector Quantization Neural Network Method for Network Intrusion Detection

A new intrusion detection method based on learning vector quantization （LVQ） with low overhead and high efficiency is presented. The computer vision system employs LVQ neural networks as classifier to recognize intrusion. The recognition process includes three stages： （1） feature selection and data normalization processing;（2） learning the training data selected from the feature data set; （3） identifying the intrusion and generating the result report of machine condition classification. Experimental results show that the proposed method is promising in terms of detection accuracy, computational expense and implementation for intrusion detection.

Machine Learning and Artificial Neural Network for Predicting Heart Failure Risk

Heart failure is now widely spread throughout the world.Heart disease affects approximately 48%of the population.It is too expensive and also difficult to cure the disease.This research paper represents machine learning models to predict heart failure.The fundamental concept is to compare the correctness of various Machine Learning(ML)algorithms and boost algorithms to improve models’accuracy for prediction.Some supervised algorithms like K-Nearest Neighbor(KNN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF),Logistic Regression(LR)are considered to achieve the best results.Some boosting algorithms like Extreme Gradient Boosting(XGBoost)and Cat-Boost are also used to improve the prediction using Artificial Neural Networks(ANN).This research also focuses on data visualization to identify patterns,trends,and outliers in a massive data set.Python and Scikit-learns are used for ML.Tensor Flow and Keras,along with Python,are used for ANN model train-ing.The DT and RF algorithms achieved the highest accuracy of 95%among the classifiers.Meanwhile,KNN obtained a second height accuracy of 93.33%.XGBoost had a gratified accuracy of 91.67%,SVM,CATBoost,and ANN had an accuracy of 90%,and LR had 88.33%accuracy.

A STUDY OF METHODS FOR IMPROVING LEARNING VECTOR QUANTIZATION

Learning Vector Quantization(LVQ)originally proposed by Kohonen(1989)is aneurally-inspired classifier which pays attention to approximating the optimal Bayes decisionboundaries associated with a classification task.With respect to several defects of LVQ2 algorithmstudied in this paper,some‘soft’competition schemes such as‘majority voting’scheme andcredibility calculation are proposed for improving the ability of classification as well as the learningspeed.Meanwhile,the probabilities of winning are introduced into the corrections for referencevectors in the‘soft’competition.In contrast with the conventional sequential learning technique,a novel parallel learning technique is developed to perform LVQ2 procedure.Experimental resultsof speech recognition show that these new approaches can lead to better performance as comparedwith the conventional

Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.

Identification of dynamic systems using support vector regression neural networks

A novel adaptive support vector regression neural network （SVR-NN） is proposed, which combines respectively merits of support vector machines and a neural network. First, a support vector regression approach is applied to determine the initial structure and initial weights of the SVR-NN so that the network architecture is easily determined and the hidden nodes can adaptively be constructed based on support vectors. Furthermore, an annealing robust learning algorithm is presented to adjust these hidden node parameters as well as the weights of the SVR-NN. To test the validity of the proposed method, it is demonstrated that the adaptive SVR-NN can be used effectively for the identification of nonlinear dynamic systems. Simulation results show that the identification schemes based on the SVR-NN give considerably better performance and show faster learning in comparison to the previous neural network method.

State of the art in applications of machine learning in steelmaking process modeling

With the development of automation and informatization in the steelmaking industry,the human brain gradually fails to cope with an increasing amount of data generated during the steelmaking process.Machine learning technology provides a new method other than production experience and metallurgical principles in dealing with large amounts of data.The application of machine learning in the steelmaking process has become a research hotspot in recent years.This paper provides an overview of the applications of machine learning in the steelmaking process modeling involving hot metal pretreatment,primary steelmaking,secondary refining,and some other aspects.The three most frequently used machine learning algorithms in steelmaking process modeling are the artificial neural network,support vector machine,and case-based reasoning,demonstrating proportions of 56%,14%,and 10%,respectively.Collected data in the steelmaking plants are frequently faulty.Thus,data processing,especially data cleaning,is crucially important to the performance of machine learning models.The detection of variable importance can be used to optimize the process parameters and guide production.Machine learning is used in hot metal pretreatment modeling mainly for endpoint S content prediction.The predictions of the endpoints of element compositions and the process parameters are widely investigated in primary steelmaking.Machine learning is used in secondary refining modeling mainly for ladle furnaces,Ruhrstahl–Heraeus,vacuum degassing,argon oxygen decarburization,and vacuum oxygen decarburization processes.Further development of machine learning in the steelmaking process modeling can be realized through additional efforts in the construction of the data platform,the industrial transformation of the research achievements to the practical steelmaking process,and the improvement of the universality of the machine learning models.

Total organic carbon content logging prediction based on machine learning:A brief review

The total organic carbon content usually determines the hydrocarbon generation potential of a formation.A higher total organic carbon content often corresponds to a greater possibility of generating large amounts of oil or gas.Hence,accurately calculating the total organic carbon content in a formation is very important.Present research is focused on precisely calculating the total organic carbon content based on machine learning.At present,many machine learning methods,including backpropagation neural networks,support vector regression,random forests,extreme learning machines,and deep learning,are employed to evaluate the total organic carbon content.However,the principles and perspectives of various machine learning algorithms are quite different.This paper reviews the application of various machine learning algorithms to deal with total organic carbon content evaluation problems.Of various machine learning algorithms used for TOC content predication,two algorithms,the backpropagation neural network and support vector regression are the most commonly used,and the backpropagation neural network is sometimes combined with many other algorithms to achieve better results.Additionally,combining multiple algorithms or using deep learning to increase the number of network layers can further improve the total organic carbon content prediction.The prediction by backpropagation neural network may be better than that by support vector regression;nevertheless,using any type of machine learning algorithm improves the total organic carbon content prediction in a given research block.According to some published literature,the determination coefficient(R^(2))can be increased by up to 0.46 after using machine learning.Deep learning algorithms may be the next breakthrough direction that can significantly improve the prediction of the total organic carbon content.Evaluating the total organic carbon content based on machine learning is of great significance.

Machine-Learning-Enabled Obesity Level Prediction Through Electronic Health Records

Obesity is a critical health condition that severely affects an individual’s quality of life andwell-being.The occurrence of obesity is strongly associated with extreme health conditions,such as cardiac diseases,diabetes,hypertension,and some types of cancer.Therefore,it is vital to avoid obesity and or reverse its occurrence.Incorporating healthy food habits and an active lifestyle can help to prevent obesity.In this regard,artificial intelligence(AI)can play an important role in estimating health conditions and detecting obesity and its types.This study aims to see obesity levels in adults by implementing AIenabled machine learning on a real-life dataset.This dataset is in the form of electronic health records(EHR)containing data on several aspects of daily living,such as dietary habits,physical conditions,and lifestyle variables for various participants with different health conditions(underweight,normal,overweight,and obesity type I,II and III),expressed in terms of a variety of features or parameters,such as physical condition,food intake,lifestyle and mode of transportation.Three classifiers,i.e.,eXtreme gradient boosting classifier(XGB),support vector machine(SVM),and artificial neural network(ANN),are implemented to detect the status of several conditions,including obesity types.The findings indicate that the proposed XGB-based system outperforms the existing obesity level estimation methods,achieving overall performance rates of 98.5%and 99.6%in the scenarios explored.

基于LVQ神经网络的水果图像分割研究

由于传统边沿检测算子在水果颜色多样、亮度不均匀时,难以分割得到完整、无噪声的二值图像且依赖优化的阈值,本研究提出了一种基于LVQ神经网络的水果图像分割方案。首先将彩色图像转变为灰度图像;然后对Canny算子获得的边沿图像随机选取一些像素作为网络的学习监督信号,仅以灰度图像中相同位置像素3×3邻域的Kirsch算子梯度值作为输入,训练权值;最后重新将原灰度图像的Kirsch算子梯度值输入到训练好的网络中,获得封闭的边沿并填充得到二值图像。考察了14幅像素为640×480的水果图像,结果表明:网络在很宽广的阈值范围内(0.001~0.99)分割得到完整、一致的二值图像;面积误差最小为0.9%,最大为8.83%,不依赖于优化的阈值,不需要对原始图像滤波预处理。与没有阈值及滤波的算法相比,本方案的误差和时间复杂度均更低;与设置了阈值和/或滤波的算法相比,本方案与之相当,甚至效果更优。

A Comparative Study of Support Vector Machine and Artificial Neural Network for Option Price Prediction

Option pricing has become one of the quite important parts of the financial market. As the market is always dynamic, it is really difficult to predict the option price accurately. For this reason, various machine learning techniques have been designed and developed to deal with the problem of predicting the future trend of option price. In this paper, we compare the effectiveness of Support Vector Machine (SVM) and Artificial Neural Network (ANN) models for the prediction of option price. Both models are tested with a benchmark publicly available dataset namely SPY option price-2015 in both testing and training phases. The converted data through Principal Component Analysis (PCA) is used in both models to achieve better prediction accuracy. On the other hand, the entire dataset is partitioned into two groups of training (70%) and test sets (30%) to avoid overfitting problem. The outcomes of the SVM model are compared with those of the ANN model based on the root mean square errors (RMSE). It is demonstrated by the experimental results that the ANN model performs better than the SVM model, and the predicted option prices are in good agreement with the corresponding actual option prices.

基于相空间重构与GSA-LVQ的有载调压变压器分接开关机械故障诊断

针对有载调压变压器分接开关机械故障诊断准确率不高以及潜在机械故障不能及时被发现的问题,提出了一种基于互补集合经验模态分解(CEEMD)、相空间重构结合万有引力搜索法(GSA)改进学习矢量量化神经网络(LVQ)的有载分接开关机械故障诊断新方法。采用CEEMD对振动信号进行时频域分解,然后通过C-C算法确定延迟时间和嵌入维数,对反映不同频率特征的固有模态函数(IMF)进行相空间重构,并提取反映混沌特征的两个特征量李雅普诺夫指数和关联维数构成特征向量。利用GSA优化LVQ,解决网络对初始连接权值敏感的问题,增强网络对有载分接开关机械故障分类识别性能。通过对有载分接开关机械状态的实验分析,证明了相空间重构结合GSA-LVQ算法的可行性和有效性。

Machine learning methods for rockburst prediction-state-of-the-art review

One of the most serious mining disasters in underground mines is rockburst phenomena.They can lead to injuries and even fatalities as well as damage to underground openings and mining equipment.This has forced many researchers to investigate alternative methods to predict the potential for rockburst occurrence.However,due to the highly complex relation between geological,mechanical and geometric parameters of the mining environment,the traditional mechanics-based prediction methods do not always yield precise results.With the emergence of machine learning methods,a breakthrough in the prediction of rockburst occurrence has become possible in recent years.This paper presents a state-ofthe-art review of various applications of machine learning methods for the prediction of rockburst potential.First,existing rockburst prediction methods are introduced,and the limitations of such methods are highlighted.A brief overview of typical machine learning methods and their main features as predictive tools is then presented.The current applications of machine learning models in rockburst prediction are surveyed,with related mechanisms,technical details and performance analysis.

A Comprehensive Investigation of Machine Learning Feature Extraction and ClassificationMethods for Automated Diagnosis of COVID-19 Based on X-ray Images

The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,which makes it challenging and a big issue to improve approaches for efficient identification of COVID-19 disease.In this study,an automatic prediction of COVID-19 identification is proposed to automatically discriminate between healthy and COVID-19 infected subjects in X-ray images using two successful moderns are traditional machine learning methods(e.g.,artificial neural network(ANN),support vector machine(SVM),linear kernel and radial basis function(RBF),k-nearest neighbor(k-NN),Decision Tree(DT),andCN2 rule inducer techniques)and deep learningmodels(e.g.,MobileNets V2,ResNet50,GoogleNet,DarkNet andXception).A largeX-ray dataset has been created and developed,namely the COVID-19 vs.Normal(400 healthy cases,and 400 COVID cases).To the best of our knowledge,it is currently the largest publicly accessible COVID-19 dataset with the largest number of X-ray images of confirmed COVID-19 infection cases.Based on the results obtained from the experiments,it can be concluded that all the models performed well,deep learning models had achieved the optimum accuracy of 98.8%in ResNet50 model.In comparison,in traditional machine learning techniques, the SVM demonstrated the best result for an accuracy of 95% and RBFaccuracy 94% for the prediction of coronavirus disease 2019.

Deep Learning Based Automated Detection of Diseases from Apple Leaf Images

In Agriculture Sciences, detection of diseases is one of the mostchallenging tasks. The mis-interpretations of plant diseases often lead towrong pesticide selection, resulting in damage of crops. Hence, the automaticrecognition of the diseases at earlier stages is important as well as economicalfor better quality and quantity of fruits. Computer aided detection (CAD)has proven as a supportive tool for disease detection and classification, thusallowing the identification of diseases and reducing the rate of degradationof fruit quality. In this research work, a model based on convolutional neuralnetwork with 19 convolutional layers has been proposed for effective andaccurate classification of Marsonina Coronaria and Apple Scab diseases fromapple leaves. For this, a database of 50,000 images has been acquired bycollecting images of leaves from apple farms of Himachal Pradesh (H.P)and Uttarakhand (India). An augmentation technique has been performedon the dataset to increase the number of images for increasing the accuracy.The performance analysis of the proposed model has been compared with thenew two Convolutional Neural Network (CNN) models having 8 and 9 layersrespectively. The proposed model has also been compared with the standardmachine learning classifiers like support vector machine, k-Nearest Neighbour, Random Forest and Logistic Regression models. From experimentalresults, it has been observed that the proposed model has outperformed theother CNN based models and machine learning models with an accuracy of99.2%.

Deep Learning Multimodal for Unstructured and Semi-Structured Textual Documents Classicatio

Due to the availability of a huge number of electronic text documents from a variety of sources representing unstructured and semi-structured information,the document classication task becomes an interesting area for controlling data behavior.This paper presents a document classication multimodal for categorizing textual semi-structured and unstructured documents.The multimodal implements several individual deep learning models such as Deep Neural Networks(DNN),Recurrent Convolutional Neural Networks(RCNN)and Bidirectional-LSTM(Bi-LSTM).The Stacked Ensemble based meta-model technique is used to combine the results of the individual classiers to produce better results,compared to those reached by any of the above mentioned models individually.A series of textual preprocessing steps are executed to normalize the input corpus followed by text vectorization techniques.These techniques include using Term Frequency Inverse Term Frequency(TFIDF)or Continuous Bag of Word(CBOW)to convert text data into the corresponding suitable numeric form acceptable to be manipulated by deep learning models.Moreover,this proposed model is validated using a dataset collected from several spaces with a huge number of documents in every class.In addition,the experimental results prove that the proposed model has achieved effective performance.Besides,upon investigating the PDF Documents classication,the proposed model has achieved accuracy up to 0.9045 and 0.959 for the TFIDF and CBOW features,respectively.Moreover,concerning the JSON Documents classication,the proposed model has achieved accuracy up to 0.914 and 0.956 for the TFIDF and CBOW features,respectively.Furthermore,as for the XML Documents classication,the proposed model has achieved accuracy values up to 0.92 and 0.959 for the TFIDF and CBOW features,respectively.

Using Neural Networks to Predict Secondary Structure for Protein Folding

Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate prediction results. The goal of this paper is to develop and implement an intelligent based system to predict secondary structure of a protein from its primary amino acid sequence by using five models of Neural Network (NN). These models are Feed Forward Neural Network (FNN), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN), Convolutional Neural Network (CNN), and CNN Fine Tuning for PSSP. To evaluate our approaches two datasets have been used. The first one contains 114 protein samples, and the second one contains 1845 protein samples.

Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data

Traditional geostatistical estimation techniques have been used predominantly by the mining industry for ore reserve estimation. Determination of mineral reserve has posed considerable challenge to mining engineers due to the geological complexities of ore body formation. Extensive research over the years has resulted in the development of several state-of-the-art methods for predictive spatial mapping, which could be used for ore reserve estimation;and recent advances in the use of machine learning algorithms (MLA) have provided a new approach for solving the prob-lem of ore reserve estimation. The focus of the present study was on the use of two MLA for estimating ore reserve: namely, neural networks (NN) and support vector machines (SVM). Application of MLA and the various issues involved with using them for reserve estimation have been elaborated with the help of a complex drill-hole dataset that exhibits the typical properties of sparseness and impreciseness that might be associated with a mining dataset. To investigate the accuracy and applicability of MLA for ore reserve estimation, the generalization ability of NN and SVM was compared with the geostatistical ordinary kriging (OK) method.

Yarn Properties Prediction Based on Machine Learning Method

Although many works have been done to construct prediction models on yarn processing quality,the relation between spinning variables and yarn properties has not been established conclusively so far.Support vector machines(SVMs),based on statistical learning theory,are gaining applications in the areas of machine learning and pattern recognition because of the high accuracy and good generalization capability.This study briefly introduces the SVM regression algorithms,and presents the SVM based system architecture for predicting yarn properties.Model selection which amounts to search in hyper-parameter space is performed for study of suitable parameters with grid-research method.Experimental results have been compared with those of artificial neural network(ANN)models.The investigation indicates that in the small data sets and real-life production,SVM models are capable of remaining the stability of predictive accuracy,and more suitable for noisy and dynamic spinning process.

Application of Feature Extraction through Convolution Neural Networks and SVM Classifier for Robust Grading of Apples

This paper proposes a novel grading method of apples,in an automated grading device that uses convolutional neural networks to extract the size,color,texture,and roundness of an apple.The developed machine learning method uses the ability of learning representative features by means of a convolutional neural network(CNN),to determine suitable features of apples for the grading process.This information is fed into a one-to-one classifier that uses a support vector machine(SVM),instead of the softmax output layer of the CNN.In this manner,Yantai apples with similar shapes and low discrimination are graded using four different approaches.The fusion model using both CNN and SVM classifiers is much more accurate than the simple k-nearest neighbor(KNN),SVM,and CNN model when used separately for grading,and the learning ability and the generalization ability of the model is correspondingly increased by the combined method.Grading tests are carried out using the automated grading device that is developed in the present work.It is verified that the actual effect of apple grading using the combined CNN-SVM model is fast and accurate,which greatly reduces the manpower and labor costs of manual grading,and has important commercial prospects.