Supervised Learning Process Research Articles

Automatic berthing using supervised learning and reinforcement learning

Although various studies have been conducted on automatic berthing, including offline optimization and online control, real-time berthing control remains a difficult problem. Online control methods without reference trajectories are promising for real-time berthing control. We used reinforcement learning (RL), which is a type of machine learning, to obtain an online control law without reference trajectories. As online control for automatic berthing is difficult, obtaining an appropriate control law with naive reinforcement learning is difficult. Furthermore, almost all existing online control methods do not consider port geometries. This study proposes a method for obtaining online berthing control laws by combining supervised learning (SL) and RL. We first trained the controller using offline-calculated trajectories and then further trained it using RL. Owing to the SL process, the proposed method can start the RL process with a good control policy. We evaluated the control law performance of the proposed method in a simulation environment that considered port geometries and wind disturbances. The experimental results show that the proposed method can achieve a higher success rate and lower safety risk than the naive SL and RL algorithms.

Automated Design Error Debugging of Digital VLSI Circuits

As the complexity and scope of VLSI designs continue to grow, fault detection processes in the pre-silicon stage have become crucial to guaranteeing reliability in IC design. Most fault detection algorithms can be solved by transforming them into a satisfiability (SAT) problem decipherable by SAT solvers. However, SAT solvers consume significant computational time, as a result of the search space explosion problem. This ever- increasing amount of data can be handled via machine learning techniques known as deep learning algorithms. In this paper, we propose a new approach utilizing deep learning for fault detection (FD) of combinational and sequential circuits in a type of stuck-at-faults. The goal of the proposed semi-supervised FD model is to avoid the search space explosion problem by taking advantage of unsupervised and supervised learning processes. First, the unsupervised learning process attempts to extract underlying concepts of data using Deep sparse autoencoder. Then, the supervised process tends to describe rules of classification that are applied to the reduced features for detecting different stuck-at faults within circuits. The FD model proposes good performance in terms of running time about 187 × compared to other FD algorithm based on SAT solvers. In addition, it is compared to common classical machine learning models such as Decision Tree (DT), Random Forest (RF) and Gradient Boosting (GB) classifiers, in terms of validation accuracy. The results show a maximum validation accuracy of the feature extraction process at 99.93%, using Deep sparse autoencoder for combinational circuits. For sequential circuits, stacked sparse autoencoder presents 99.95% as average validation accuracy. The fault detection process delivers around 99.6% maximum validation accuracy for combinational circuits from ISCAS’85 and 99.8% for sequential circuits from ISCAS’89 benchmarks. Moreover, the proposed FD model has achieved a running time of about 1.7x, compared to DT classifier and around 1.6x, compared to RF classifier and GB machine learning classifiers, in terms of validation accuracy in detecting faults occurred in eight different digital circuits. Furthermore, the proposed model outperforms other FD models, based on Radial Basis Function Network (RBFN), achieving 97.8% maximum validation accuracy.

Quantification of Intra-Muscular Adipose Infiltration in Calf/Thigh MRI Using Fully and Weakly Supervised Semantic Segmentation.

Purpose: Infiltration of fat into lower limb muscles is one of the key markers for the severity of muscle pathologies. The level of fat infiltration varies in its severity across and within patients, and it is traditionally estimated using visual radiologic inspection. Precise quantification of the severity and spatial distribution of this pathological process requires accurate segmentation of lower limb anatomy into muscle and fat. Methods: Quantitative magnetic resonance imaging (qMRI) of the calf and thigh muscles is one of the most effective techniques for estimating pathological accumulation of intra-muscular adipose tissue (IMAT) in muscular dystrophies. In this work, we present a new deep learning (DL) network tool for automated and robust segmentation of lower limb anatomy that is based on the quantification of MRI’s transverse (T2) relaxation time. The network was used to segment calf and thigh anatomies into viable muscle areas and IMAT using a weakly supervised learning process. A new disease biomarker was calculated, reflecting the level of abnormal fat infiltration and disease state. A biomarker was then applied on two patient populations suffering from dysferlinopathy and Charcot–Marie–Tooth (CMT) diseases. Results: Comparison of manual vs. automated segmentation of muscle anatomy, viable muscle areas, and intermuscular adipose tissue (IMAT) produced high Dice similarity coefficients (DSCs) of 96.4%, 91.7%, and 93.3%, respectively. Linear regression between the biomarker value calculated based on the ground truth segmentation and based on automatic segmentation produced high correlation coefficients of 97.7% and 95.9% for the dysferlinopathy and CMT patients, respectively. Conclusions: Using a combination of qMRI and DL-based segmentation, we present a new quantitative biomarker of disease severity. This biomarker is automatically calculated and, most importantly, provides a spatially global indication for the state of the disease across the entire thigh or calf.

Learning Laparoscope Actions via Video Features for Proactive Robotic Field-of-View Control

Smart laparoscope motion control for adjusting surgical field-of-view is an increasingly hot topic in robot-assisted surgery. Previous off-the-shelf methods have been conducted in reactive ways which heavily rely on human input signals, e.g., gaze or voice, thus cannot avoid cognitive burdens to surgeons. In this paper, we introduce a novel proactive framework that learns the motion strategy from clinical surgical videos to achieve autonomous laparoscope control in surgery. In specific, we first propose a robust estimation method to acquire laparoscope motion in dynamic surgical scenes, which provides the basis for later supervised learning process. To imitate operating manners in different surgical domains, we design consistent dynamic image-level motion features that consist of semantic segmentation and dense optical flow. A sequence-to-sequence recurrent network is proposed to learn the connection between previous and future motion features at multiple temporal scales within a time-dependent sliding window. Then a laparoscope action head is built to convert the motion features into three-dimensional actions, hence establishing an end-to-end laparoscope motion imitation network. We have extensively validated the proposed proactive field-of-view control framework on both our <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ex-vivo</i> phantom-based robotic platform, as well as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-vivo</i> videos collected from real clinical videos. Our promising results demonstrate the feasibility to directly learn laparoscope behavioral actions from collected video data of experienced surgical assistants.

APPLICATION OF FINITE DIFFERENCE METHOD FOR MEASUREMENT SIMULATION IN ULTRASOUND TRANSMISSION TOMOGRAPHY

In this work, we present a computer simulation model that generates the propagation of sound waves to solve a forward problem in ultrasound transmission tomography. The simulator can be used to create data sets used in the supervised learning process. A solution to the "free-space" boundary problem was proposed, and the memory consumption was significantly optimized from O(n2) to O(n). The given method of simulating wave scattering enables the control of the noise extinction time within the tomographic probe and the permeability of the sound wave. The presented version of the script simulates the classic variant of a circular probe with evenly distributed sensors around the circumference.

Conception, Development and Validation of Classification Methods for Coding Support of Rare Diseases Using Artificial Intelligence.

Automated coding of diseases can support hospitals in the billing of inpatient cases with the health insurance funds. This paper describes the implementation and evaluation of classification methods for two selected Rare Diseases. Different classifiers of an off-the-shelf system and an own application are applied in a supervised learning process and comparatively examined for their suitability and reliability. Using Natural Language Processing and Machine Learning, disease entities are recognized from unstructured historical patient records and new billing cases are coded automatically. The results of the performed classifications show that even with small datasets (≤ 200), high correctness (F1 score ∼0.8) can be achieved in predicting new cases.

Active Learning Algorithm Based on Fast Optimization of Support Vectors

For the solution to the problems of being difficult to gain mass class-labeled samples in the supervised learning process and of reducing the cost of data labeling, a fast optimization of support vectors based on convex hull vector is proposed with the learning mechanism of Support Vector Machine (SVM). By means of calculating the hull vectors of the sample set, label those chosen hull vectors that are largest possible to be support vectors, and also add the unlabeled samples with high confidence coefficient of classifiers to the training sample set. The very information beneficial to the learner in the unlabeled samples set will be exploited. Hence, the thick convex hull method and the modified weighted SVM are separately directed for the nonlinear separable problem and the unbalanced training sample set. Via experimental testing on the UCI data set, the results demonstrate that the algorithm harvests SVM classifiers of higher classification accuracy and better generalization performance with fewer labeled samples, so as to cut down the labeling cost of samples for SVM training and learning.

EssayGAN: Essay Data Augmentation Based on Generative Adversarial Networks for Automated Essay Scoring

In large-scale testing and e-learning environments, automated essay scoring (AES) can relieve the burden upon human raters by replacing human grading with machine grading. However, building AES systems based on deep learning requires a training dataset consisting of essays that are manually rated with scores. In this study, we introduce EssayGAN, an automatic essay generator based on generative adversarial networks (GANs). To generate essays rated with scores, EssayGAN has multiple generators for each score range and one discriminator. Each generator is dedicated to a specific score and can generate an essay rated with that score. Therefore, the generators can focus only on generating a realistic-looking essay that can fool the discriminator without considering the target score. Although ordinary-text GANs generate text on a word basis, EssayGAN generates essays on a sentence basis. Therefore, EssayGAN can compose not only a long essay by predicting a sentence instead of a word at each step, but can also compose a score-rated essay by adopting multiple generators dedicated to the target score. Since EssayGAN can generate score-rated essays, the generated essays can be used in the supervised learning process for AES systems. Experimental results show that data augmentation using augmented essays helps to improve the performance of AES systems. We conclude that EssayGAN can generate essays not only consisting of multiple sentences but also maintaining coherence between sentences in essays.

The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans.

Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances of survival, improving the cancer early detection capacity is crucial, for which computed tomography (CT) scans represent a key role. The manual evaluation of the CTs is a time-consuming task and computer-aided diagnosis (CAD) systems can help relieve that burden. The segmentation of the lung is one of the first steps in these systems, yet it is very challenging given the heterogeneity of lung diseases usually present and associated with cancer development. In our previous work, a segmentation model based on a ResNet34 and U-Net combination was developed on a cross-cohort dataset that yielded good segmentation masks for multiple pathological conditions but misclassified some of the lung nodules. The multiple datasets used for the model development were originated from different annotation protocols, which generated inconsistencies for the learning process, and the annotations are usually not adequate for lung cancer studies since they did not comprise lung nodules. In addition, the initial datasets used for training presented a reduced number of nodules, which was showed not to be enough to allow the segmentation model to learn to include them as a lung part. In this work, an objective protocol for the lung mask’s segmentation was defined and the previous annotations were carefully reviewed and corrected to create consistent and adequate ground-truth masks for the development of the segmentation model. Data augmentation with domain knowledge was used to create lung nodules in the cases used to train the model. The model developed achieved a Dice similarity coefficient (DSC) above 0.9350 for all test datasets and it showed an ability to cope, not only with a variety of lung patterns, but also with the presence of lung nodules as well. This study shows the importance of using consistent annotations for the supervised learning process, which is a very time-consuming task, but that has great importance to healthcare applications. Due to the lack of massive datasets in the medical field, which consequently brings a lack of wide representativity, data augmentation with domain knowledge could represent a promising help to overcome this limitation for learning models development.

Deep-Learning-Based Predictive Control of Battery Management for Frequency Regulation

This paper proposes a deep-learning-based optimal battery management scheme for frequency regulation (FR) by integrating model predictive control (MPC), supervised learning (SL), reinforcement learning (RL), and high-fidelity battery models. By taking advantage of deep neural networks (DNNs), the derived DNN-approximated policy is computationally efficient in online implementation. The design procedure of the proposed scheme consists of two sequential processes: (1) the SL process, in which we first run a simulation with an MPC embedding a low-fidelity battery model to generate a training data set, and then, based on the generated data set, we optimize a DNN-approximated policy using SL algorithms; (2) the RL process, in which we utilize RL algorithms to improve the performance of the DNN-approximated policy by balancing short-term economic incentives and long-term battery degradation. The SL process speeds up the subsequent RL process by providing a good initialization. By utilizing RL algorithms, one prominent property of the proposed scheme is that it can learn from the data generated by simulating the FR policy on the high-fidelity battery simulator to adjust the DNN-approximated policy, which is originally initialized using a low-fidelity battery model. A case study using real-world data of FR signals and prices is performed. Simulation results show that, compared to conventional MPC schemes, the proposed deep-learning-based scheme can effectively achieve higher economic benefits of FR participation while maintaining lower online computational cost.

A Contrastive Predictive Coding-Based Classification Framework for Healthcare Sensor Data.

Supervised learning technologies have been used in medical-data classification to improve diagnosis efficiency and reduce human diagnosis errors. A large amount of manually annotated data are required for the fully supervised learning process. However, annotating data information will consume a large amount of manpower and resources. Self-supervised learning has great advantages in solving this problem. Self-supervised learning mainly uses pretext tasks to mine its own supervised information from large-scale unsupervised data. And this constructed supervised information is used to train the network to learn valuable representations for downstream tasks. This study designs a general and efficient model for the diagnosis and classification of medical sensor data based on contrastive predictive coding (CPC) in self-supervised learning, called TCC, which consists of two steps. The first step is to design a pretext task based on the idea of CPC, which aims to extract effective features between different categories using its encoder. The second step designs a downstream classification task with lower time and space complexity to perform a supervised type of training using the features extracted by the encoder of the pretext task. Finally, to demonstrate the performance of the proposed framework in this paper, we compare the proposed framework with recent state-of-the-art works. Experiments comparing the proposed framework with supervised learning are also set up under the condition of different proportions of labeled data.

Simple Models in Complex Worlds: Occam\u2019s Razor and Statistical Learning Theory

The idea that “simplicity is a sign of truth”, and the related “Occam’s razor” principle, stating that, all other things being equal, simpler models should be preferred to more complex ones, have been long discussed in philosophy and science. We explore these ideas in the context of supervised machine learning, namely the branch of artificial intelligence that studies algorithms which balance simplicity and accuracy in order to effectively learn about the features of the underlying domain. Focusing on statistical learning theory, we show that situations exist for which a preference for simpler models (as modeled through the addition of a regularization term in the learning problem) provably slows down, instead of favoring, the supervised learning process. Our results shed new light on the relations between simplicity and truth approximation, which are briefly discussed in the context of both machine learning and the philosophy of science.

A Simple Data Preprocessing and Postprocessing Techniques for SVM Classifier of Remote Sensing Multispectral Image Classification

Present scenario of the remote sensing domain deals with how to utilize the data for different purposes like classification, target detection, disaster management, change detection, flood monitoring, deforestation, etc. Now due to improvements in the sensor technology very high spatial and spectral resolutions data are available. Over a decade various new advanced research papers have been projected in the literature for spatial and spectral classification of such high-resolution remote sensing images. Thematic information investigation of the earth&#x0027;s surface image is possible by the classification technique and the most frequently used method for this purpose is multispectral classification using a supervised learning process. In the supervised learning process, the specialist challenges to discover exact sites in the remotely sensed data that represent homogeneous examples of the known land cover type. The most recommended method for the classification of remote sensing (RS) images is the support vector machine (SVM) because of its high accuracy but any classifier depends on good quality training samples. The collection of authentic training samples of different classes is a critical issue when the whole classification result is important. This paper presents a pre-processing technique based on local statistics for generation-correction of training samples with quadrant division. A simple filter-based post-processing technique is proposed for the improvement of classification accuracy. We study rigorously how the proposed pre-processing technique has affected the result of classification accuracy for different kernels SVM classifiers. Also, we have presented the comparison results between the proposed method and other different classifiers in the literature.

Influence of Examinations on Principals’ Instructional Leadership Practices in Public Secondary Schools in Nakuru County, Kenya

Examinations have been seen as a measuring tool for both quality of education and the principals’ effort in schools. Principals being the managers of the school and instructional leaders have been made accountable for the tests scores achieved by the students hence creating pressure on them. The target of this research therefore, was to explore on whether influence of examinations affect the principals’ instructional leadership practices in Nakuru County Nakuru North sub-county. This research was anchored on four objectives: - To investigate the influence of examinations on the principals’ role of allocating instructional resources, to determine the influence of examinations on the principals’ role of monitoring learners’ academic progress. This study was anchored on transactional leadership theory that was described by Max Weber (1947) and Bernard Bass (1981) which focuses on organizing, controlling and short-term planning. It incorporates providing of resources, motivation and directing followers to attain goals. The study used descriptive study design since it enables one to get detailed opinion which can be used to facilitate generalization of findings with large population. The target population comprised 35 public secondary principals, 497 teachers and 19, 625 students from all public secondary schools in Nakuru North sub-county. Through simple random sampling 18 public secondary schools were sampled which led to 18 public secondary school principals being sampled. Stratified and simple random sampling techniques were used to sample 149 teachers. Stratified and systematic sampling techniques were used to sample 1962 students to take part in the study. Data was gathered using questionnaires and interview schedules. Piloting of these tools was conducted in four schools which were within the researcher’s target population to determine content and face validity. The reliability coefficient was arbitrated using Pearson Moment Correlation Coefficient, with the help of SPSS and Microsoft Excel. Descriptive statistics was employed in analyzing quantitative data through measuring of frequencies, percentages and means and presented in tables, graphs and charts. Qualitative data was analyzed through data being; organized based on objectives, coded based on similarities, validated and finally logical conclusions were made. The study established that examination influenced principals to allocate instructional resources that focus on formative and summative assessments; examinations were found to encourage principals to monitor academic progress of the students. However, in some schools the principals were not able to monitor academic progress. Examinations were also found to influence principals’ supervision of teaching process whereby principals supervised learning process in order to post good academic results. Principals motivated their teachers by taking them to field trips, giving teachers money and organizing professional development seminars. In supposition, the researcher found that examination influence principal’s instructional leadership in public secondary schools in Nakuru North Sub County. The study recommends that the ministry of education should organize academic trips for the teachers after posting good academic results. Principals should monitor academic progress of the students regularly to ensure students acquire relevant learning outcomes. Contemporary teacher motivation strategies should be embraced to ensure schools do not permit examinations cheating as a result of monetary rewards. Ministry of education should ensure learning is not based on rote learning and examination scores but skills as well as knowledge acquisition.

Machine Learning application for selecting efficient Loan Applicants in Private Banks of Bangladesh

Machine Learning Applications have been well accepted for various financial processes throughout the world. Supervised Learning processes for objective classification by Naïve Bayes classifiers have been supporting many definitive segregation processes. Various banks in Bangladesh have found challenging moments to identify financially and ethically qualified loan applicants. In this research process, we have confirmed the safe applicant’s list using definitive variable measures through identifiable questions. Our research process has successfully segregated the given applicants using Naïve Bayes classifier with the proof of lowering loan default rate from an average of 23.26%% to 11.76% and development of financial ratios as performance indicators of these banks through various financial ratios as indicators of these banks.

Ferroelectric P(VDF-TrFE) wrapped InGaAs nanowires for ultralow-power artificial synapses

The gallop of artificial intelligence ignites urgent demand on information processing systems with ultralow power consumption, reliable multi-parameter control and high operation efficiency. Here, the poly(vinylidene fluoride-trifluoroethylene) (P(VDF-TrFE)) wrapped InGaAs nanowire (NW) artificial synapses capable to operate with record-low subfemtojoule power consumption are presented. The essential synaptic behaviors are mimicked and modulated effectively by adjusting the thickness of top P(VDF-TrFE) films. Moreover, the long-term depression is realized by applying visible light (450 nm) because of the negative photoconductivity of InGaAs nanowires. Combined with optimal P(VDF-TrFE) films, the synaptic devices have the more linear long-term potentiation/depression characteristics and the faster supervised learning process simulated by hardware neural networks. The Pavlovian conditioning is also performed by combining electrical and infrared stimuli. Evidently, these ultralow-operating-power synapses are demonstrated with the brain-like behaviors, effective function modulation, and more importantly, the synergistic photoelectric modulation, which illustrates the promising potentials for neuromorphic computing systems.

Generative Adversarial Networks used for latent space Optimization: a comparative study for the Classification of Partial Discharge Sources

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. The main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. In our previous study, it was shown that more than 85% of stator failure mechanisms indicate the presence of Partial Discharges (PD) activity. PD are minute sparks that occur within voids inside high voltage insulation or in the air around the insulating system. Each PD event does not cause immediate failure, but it will slowly erode the insulation system and will lead to breakdown in years to decades. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Québec has been collecting more than 33.000 unlabeled PD measurement files over the last decades including two types of measurement instruments. One of the instruments used is the Partial Discharge Analyzer (PDA). PDs have several different sources and each source is characterized by a specific signature. It is therefore essential to be able to automatically recognize the nature of the DPs in order to anticipate possible degradation. Expert rules to characterize these PD signals exist but these rules cannot be used as an automatic classification tool. Indeed, for certain ambiguous cases (conflict between classes) or the presence of several signatures at the same time (multi-classes), the expert's judgement remains essential.&#x0D; A Variationel AutoEncoder (VAE) is used for dimension reduction and projection into a 2D latent space to analyze the training data and then classify it. The 2D latent space of the VAE allows the data space to be restructured and reorganized to anticipate the performance of the classifier. The problem is how to optimize this latent space and thus obtain the best distribution of the different sources of PDs to maximize the chances of good responses from the classifier? To our knowledge, there is currently no method in the literature that clearly answers this question. What is certain, however, is that the optimization of the VAE learning is directly related to the quality of the learning base, i.e. a large size and a perfectly balanced database (all the cases are present and sufficiently represented). The objective of this paper is to compare the quality of the latent space obtained from the experts' rules with a latent space obtained directly from the input signal in an « End-to-End » approach.&#x0D; The first method concerns an original unsupervised deep learning method for PD recognition. Instead of labelling the PD measurement files by the expert for a supervised learning process, we use the rules developed by the experts of Hydro-Québec to create a feature vector from recognizable PD signatures. Indeed, labelling a sufficient quantity of signatures for a supervised approach is very time-consuming and therefore cannot be implemented. This is a common problem in the industry where more and more operational data is available but cannot be labelled by experts, who are busy with other tasks. Expert knowledge is then injected into a characteristic and feature vector. In the second method, several Generative Adversarial Networks (GANs) associated with several types of PDs are thus used to generate artificial signals in order to increase the size of the learning base and especially to balance it. A new latent space is thus obtained from the learning of the VAE exclusively carried out on data generated by the GANs.&#x0D; Validation tests based on the 33,000 measurements with metrics for evaluating the performances of the various latent spaces are used.

PENGARUH TRANSFORMASI DATA PADA METODE LEARNING VECTOR QUANTIZATION TERHADAP AKURASI KLASIFIKASI DIAGNOSIS PENYAKIT JANTUNG

Learning Vector Quantization (LVQ) is a type of Artificial Neural Network with a supervised learning process based on competitive learning. Despite the absence of assumptions in LVQ is an advantage, it can be a problem when the predictor variables have big different ranges.This problems can be overcome by equalizing the range of all variables by data transformation so that all variables have relatively same effect. Heart Disease UCI dataset which used in this study is transformed by several transformation methods, such as minmax, decimal scaling, z-score, mean-MAD, sigmoid, and softmax. The result show that the six transformed data can provide better LVQ classification accuracy than the raw data which has 75.99% for training performance accuracy. LVQ classification accuracy with data transformation of minmax, decimal scaling, z-score, mean-MAD, sigmoid, and softmax are 89.16%, 88.22%, 89.7%, 90.1%, 88.17% and 92.18%. Based on the One-way ANOVA test and DMRT post hoc test known that there are significant differences between the results of the classification with data transformations and raw data in 0,05 significant level of α. It is also known that the best data transformation methods are softmax for training and sigmoid for testing. Keywords: heart disease, neural network, learning vector quantization, classification, data transformation

Joint pairwise graph embedded sparse deep belief network for fault diagnosis

An enhanced intelligent diagnosis method is proposed based on a joint pairwise graph embedded sparse deep belief network with partial least square fine-tuning (J-PDBN). In this novel framework, the joint pairwise graph embedded sparse deep belief network (DBN) is considered as an unsupervised learning method to realize fast parameters initialization and to extract data features. It combines the advantages of both the pairwise graph and sparse representation, which can preserve the manifold structure of the original data and generate discriminant features. The partial least square (PLS) is used to optimize the parameters to eliminate the gradient diffusion in the supervised learning process. The J-PDBN-based fault diagnosis is implemented by both the unsupervised learning method and PLS fine-tuning, which contributes to better classification capabilities. Finally, gearbox and bearing fault diagnosis experiments are conducted. The results show that the total recognition rates of the proposed method are 93.65% in the gearbox case and 95.96% in the bearing case, which are higher than those of other methods. Specifically, the testing accuracy is approximately 10% higher than those of the DBN network for both cases. This validates the effectiveness and superiority of the proposed method.

Novel Study of Machine Learning Algorithms with Supervised Learning Approach to Solve Real Time Big Data Applications Using Hadoop and Spark

This review focuses on different machine learning algorithms, descriptions, pros and cons of the algorithms. It also includes task of machine learning and supervised learning process, tools, techniques and programming language to build machine learning model. Machine learning is a building computational art craft, which learns through time from experience. Machine learning is learning from data and it turns input data to information (mapping input value to output value using label data). The objective of machine learning is building the algorithm that can learn from past data without the help of human experts. The learning algorithm contains task T, performance measure P and training experience T. Machine learning algorithm categorized as supervised, unsupervised and reinforcement learning. Supervised machine learning has two tasks, which are classification and regression. Hadoop with Spark and Python programing language most commonly used to build machine learning model. Information gain and Gain ratio, Gini index and Random forest algorithm used to measure feature importance. From this study most of supervised learning algorithms used k-fold cross validation techniques to split the data set in to training set and testing set. Standard value of k will be five or ten but it didn’t fixed, because it depends on the size of data set. The machine learning model performance mainly evaluated using classification accuracy, precision, recall, area under the curve and F-measure (F-score). Generally machine learning algorithms depend on the nature of the data, because the performance of the learning algorithms affected by data set. Therefore it is impossible to say the prediction accuracy of one algorithm is best over others. As each machine learning algorithms have pros and cons, designing of hybrid algorithms might be overcome this problem.