A gated recurrent unit model to predict Poisson’s ratio using deep learning

Static Poisson’s ratio(vs)is crucial for determining geomechanical properties in petroleum applications,namely sand production.Some models have been used to predict vs;however,the published models were limited to specific data ranges with an average absolute percentage relative error(AAPRE)of more than 10%.The published gated recurrent unit(GRU)models do not consider trend analysis to show physical behaviors.In this study,we aim to develop a GRU model using trend analysis and three inputs for predicting n s based on a broad range of data,n s(value of 0.1627-0.4492),bulk formation density(RHOB)(0.315-2.994 g/mL),compressional time(DTc)(44.43-186.9 μs/ft),and shear time(DTs)(72.9-341.2μ s/ft).The GRU model was evaluated using different approaches,including statistical error an-alyses.The GRU model showed the proper trends,and the model data ranges were wider than previous ones.The GRU model has the largest correlation coefficient(R)of 0.967 and the lowest AAPRE,average percent relative error(APRE),root mean square error(RMSE),and standard deviation(SD)of 3.228%,1.054%,4.389,and 0.013,respectively,compared to other models.The GRU model has a high accuracy for the different datasets:training,validation,testing,and the whole datasets with R and AAPRE values were 0.981 and 2.601%,0.966 and 3.274%,0.967 and 3.228%,and 0.977 and 2.861%,respectively.The group error analyses of all inputs show that the GRU model has less than 5% AAPRE for all input ranges,which is superior to other models that have different AAPRE values of more than 10% at various ranges of inputs.

Alzheimer’s Disease Stage Classification Using a Deep Transfer Learning and Sparse Auto Encoder Method

Alzheimer’s Disease(AD)is a progressive neurological disease.Early diagnosis of this illness using conventional methods is very challenging.Deep Learning(DL)is one of the finest solutions for improving diagnostic procedures’performance and forecast accuracy.The disease’s widespread distribution and elevated mortality rate demonstrate its significance in the older-onset and younger-onset age groups.In light of research investigations,it is vital to consider age as one of the key criteria when choosing the subjects.The younger subjects are more susceptible to the perishable side than the older onset.The proposed investigation concentrated on the younger onset.The research used deep learning models and neuroimages to diagnose and categorize the disease at its early stages automatically.The proposed work is executed in three steps.The 3D input images must first undergo image pre-processing using Weiner filtering and Contrast Limited Adaptive Histogram Equalization(CLAHE)methods.The Transfer Learning(TL)models extract features,which are subsequently compressed using cascaded Auto Encoders(AE).The final phase entails using a Deep Neural Network(DNN)to classify the phases of AD.The model was trained and tested to classify the five stages of AD.The ensemble ResNet-18 and sparse autoencoder with DNN model achieved an accuracy of 98.54%.The method is compared to state-of-the-art approaches to validate its efficacy and performance.

Implicit Continuous User Authentication for Mobile Devices based on Deep Reinforcement Learning

The predominant method for smart phone accessing is confined to methods directing the authentication by means of Point-of-Entry that heavily depend on physiological biometrics like,fingerprint or face.Implicit continuous authentication initiating to be loftier to conventional authentication mechanisms by continuously confirming users’identities on continuing basis and mark the instant at which an illegitimate hacker grasps dominance of the session.However,divergent issues remain unaddressed.This research aims to investigate the power of Deep Reinforcement Learning technique to implicit continuous authentication for mobile devices using a method called,Gaussian Weighted Cauchy Kriging-based Continuous Czekanowski’s(GWCK-CC).First,a Gaussian Weighted Non-local Mean Filter Preprocessing model is applied for reducing the noise pre-sent in the raw input face images.Cauchy Kriging Regression function is employed to reduce the dimensionality.Finally,Continuous Czekanowski’s Clas-sification is utilized for proficient classification between the genuine user and attacker.By this way,the proposed GWCK-CC method achieves accurate authen-tication with minimum error rate and time.Experimental assessment of the pro-posed GWCK-CC method and existing methods are carried out with different factors by using UMDAA-02 Face Dataset.The results confirm that the proposed GWCK-CC method enhances authentication accuracy,by 9%,reduces the authen-tication time,and error rate by 44%,and 43%as compared to the existing methods.

Xception-Fractalnet:Hybrid Deep Learning Based Multi-Class Classification of Alzheimer’s Disease

Neurological disorders such as Alzheimer’s disease(AD)are very challenging to treat due to their sensitivity,technical challenges during surgery,and high expenses.The complexity of the brain structures makes it difficult to distinguish between the various brain tissues and categorize AD using conventional classification methods.Furthermore,conventional approaches take a lot of time and might not always be precise.Hence,a suitable classification framework with brain imaging may produce more accurate findings for early diagnosis of AD.Therefore in this paper,an effective hybrid Xception and Fractalnet-based deep learning framework are implemented to classify the stages of AD into five classes.Initially,a network based on Unet++is built to segment the tissues of the brain.Then,using the segmented tissue components as input,the Xception-based deep learning technique is employed to extract high-level features.Finally,the optimized Fractalnet framework is used to categorize the disease condition using the acquired characteristics.The proposed strategy is tested on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset that accurately segments brain tissues with a 98.45%of dice similarity coefficient(DSC).Additionally,for themulticlass classification of AD,the suggested technique obtains an accuracy of 99.06%.Moreover,ANOVA statistical analysis is also used to evaluate if the groups are significant or not.The findings show that the suggested model outperforms various stateof-the-art methods in terms of several performance metrics.

Prediction of the Wastewater’s pH Based on Deep Learning Incorporating Sliding Windows

To protect the environment,the discharged sewage’s quality must meet the state’s discharge standards.There are many water quality indicators,and the pH(Potential of Hydrogen)value is one of them.The natural water’s pH value is 6.0–8.5.The sewage treatment plant uses some data in the sewage treatment process to monitor and predict whether wastewater’s pH value will exceed the standard.This paper aims to study the deep learning prediction model of wastewater’s pH.Firstly,the research uses the random forest method to select the data features and then,based on the sliding window,convert the data set into a time series which is the input of the deep learning training model.Secondly,by analyzing and comparing relevant references,this paper believes that the CNN(Convolutional Neural Network)model is better at nonlinear data modeling and constructs a CNN model including the convolution and pooling layers.After alternating the combination of the convolutional layer and pooling layer,all features are integrated into a full-connected neural network.Thirdly,the number of input samples of the CNN model directly affects the prediction effect of the model.Therefore,this paper adopts the sliding window method to study the optimal size.Many experimental results show that the optimal prediction model can be obtained when alternating six convolutional layers and three pooling layers.The last full-connection layer contains two layers and 64 neurons per layer.The sliding window size selects as 12.Finally,the research has carried out data prediction based on the optimal CNN deep learning model.The predicted pH of the sewage is between 7.2 and 8.6 in this paper.The result is applied in the monitoring system platform of the“Intelligent operation and maintenance platform of the reclaimed water plant.”

Decoding degeneration:the implementation of machine learning for clinical detection of neurodegenerative disorders

Machine learning represents a growing subfield of artificial intelligence with much promise in the diagnosis,treatment,and tracking of complex conditions,including neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases.While no definitive methods of diagnosis or treatment exist for either disease,researchers have implemented machine learning algorithms with neuroimaging and motion-tracking technology to analyze pathologically relevant symptoms and biomarkers.Deep learning algorithms such as neural networks and complex combined architectures have proven capable of tracking disease-linked changes in brain structure and physiology as well as patient motor and cognitive symptoms and responses to treatment.However,such techniques require further development aimed at improving transparency,adaptability,and reproducibility.In this review,we provide an overview of existing neuroimaging technologies and supervised and unsupervised machine learning techniques with their current applications in the context of Alzheimer’s and Parkinson’s diseases.

Detection of Alzheimer’s disease onset using MRI and PET neuroimaging:longitudinal data analysis and machine learning

The scientists are dedicated to studying the detection of Alzheimer’s disease onset to find a cure, or at the very least, medication that can slow the progression of the disease. This article explores the effectiveness of longitudinal data analysis, artificial intelligence, and machine learning approaches based on magnetic resonance imaging and positron emission tomography neuroimaging modalities for progression estimation and the detection of Alzheimer’s disease onset. The significance of feature extraction in highly complex neuroimaging data, identification of vulnerable brain regions, and the determination of the threshold values for plaques, tangles, and neurodegeneration of these regions will extensively be evaluated. Developing automated methods to improve the aforementioned research areas would enable specialists to determine the progression of the disease and find the link between the biomarkers and more accurate detection of Alzheimer’s disease onset.

Estimation of Gaussian overlapping nuclear pulse parameters based on a deep learning LSTM model

A long short-term memory(LSTM)neural network has excellent learning ability applicable to time series of nuclear pulse signals.It can accurately estimate parameters associated with amplitude,time,and so on,in digitally shaped nuclear pulse signals—especially signals from overlapping pulses.By learning the mapping relationship between Gaussian overlapping pulses after digital shaping and exponential pulses before shaping,the shaping parameters of the overlapping exponential nuclear pulses can be estimated using the LSTM model.Firstly,the Gaussian overlapping nuclear pulse(ONP)parameters which need to be estimated received Gaussian digital shaping treatment,after superposition by multiple exponential nuclear pulses.Secondly,a dataset containing multiple samples was produced,each containing a sequence of sample values from Gaussian ONP,after digital shaping,and a set of shaping parameters from exponential pulses before digital shaping.Thirdly,the Training Set in the dataset was used to train the LSTM model.From these datasets,the values sampled from the Gaussian ONP were used as the input data for the LSTM model,and the pulse parameters estimated by the current LSTM model were calculated by forward propagation.Next,the loss function was used to calculate the loss value between the network-estimated pulse parameters and the actual pulse parameters.Then,a gradient-based optimization algorithm was applied,to feedback the loss value and the gradient of the loss function to the neural network,to update the weight of the LSTM model,thereby achieving the purpose of training the network.Finally,the sampled value of the Gaussian ONP for which the shaping parameters needed to be estimated was used as the input data for the LSTM model.After this,the LSTM model produced the required nuclear pulse parameter set.In summary,experimental results showed that the proposed method overcame the defect of local convergence encountered in traditional methods and could accurately extract parameters from multiple,severely overlapping Gaussian pulses,to achieve optimal estimation of nuclear pulse parameters in the global sense.These results support the conclusion that this is a good method for estimating nuclear pulse parameters.

Classification of Short Time Series in Early Parkinson’s Disease With Deep Learning of Fuzzy Recurrence Plots

There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.

Implementation of a Smartphone as a Wearable and Wireless Accelerometer and Gyroscope Platform for Ascertaining Deep Brain Stimulation Treatment Efficacy of Parkinson’s Disease through Machine Learning Classification

Parkinson’s disease manifests in movement disorder symptoms, such as hand tremor. There exists an assortment of therapy interventions. In particular deep brain stimulation offers considerable efficacy for the treatment of Parkinson’s disease. However, a considerable challenge is the convergence toward an optimal configuration of tuning parameters. Quantified feedback from a wearable and wireless system consisting of an accelerometer and gyroscope can be enabled through a novel software application on a smartphone. The smartphone with its internal accelerometer and gyroscope can record the quantified attributes of Parkinson’s disease and tremor through mounting the smartphone about the dorsum of the hand. The recorded data can be then wirelessly transmitted as an email attachment to an Internet derived resource for subsequent post-processing. The inertial sensor data can be consolidated into a feature set for machine learning classification. A multilayer perceptron neural network has been successfully applied to attain considerable classification accuracy between deep brain stimulation “On” and “Off” scenarios for a subject with Parkinson’s disease. The findings establish the foundation for the broad objective of applying wearable and wireless systems for the development of closed-loop optimization of deep brain stimulation parameters in the context of cloud computing with machine learning classification.

Automatic Alzheimer’s Disease Recognition from MRI Data Using Deep Learning Method

Alzheimer’s Disease (AD), the most common form of dementia, is an incurable neurological condition that results in a progressive mental deterioration. Although definitive diagnosis of AD is difficult, in practice, AD diagnosis is largely based on clinical history and neuropsychological data including magnetic resource imaging (MRI). Increasing research has been reported on applying machine learning to AD recognition in recent years. This paper presents our latest contribution to the advance. It describes an automatic AD recognition algorithm that is based on deep learning on 3D brain MRI. The algorithm uses a convolutional neural network (CNN) to fulfil AD recognition. It is unique in that the three dimensional topology of brain is considered as a whole in AD recognition, resulting in an accurate recognition. The CNN used in this study consists of three consecutive groups of processing layers, two fully connected layers and a classification layer. In the structure, every one of the three groups is made up of three layers, including a convolutional layer, a pooling layer and a normalization layer. The algorithm was trained and tested using the MRI data from Alzheimer’s Disease Neuroimaging Initiative. The data used include the MRI scanning of about 47 AD patients and 34 normal controls. The experiment had shown that the proposed algorithm delivered a high AD recognition accuracy with a sensitivity of 1 and a specificity of 0.93.

Least Squares Method from the View Point of Deep Learning II: Generalization

The least squares method is one of the most fundamental methods in Statistics to estimate correlations among various data. On the other hand, Deep Learning is the heart of Artificial Intelligence and it is a learning method based on the least squares method, in which a parameter called learning rate plays an important role. It is in general very hard to determine its value. In this paper we generalize the preceding paper [K. Fujii: Least squares method from the view point of Deep Learning: Advances in Pure Mathematics, 8, 485-493, 2018] and give an admissible value of the learning rate, which is easily obtained.

Preliminary Network Centric Therapy for Machine Learning Classification of Deep Brain Stimulation Status for the Treatment of Parkinson’s Disease with a Conformal Wearable and Wireless Inertial Sensor

The concept of Network Centric Therapy represents an amalgamation of wearable and wireless inertial sensor systems and machine learning with access to a Cloud computing environment. The advent of Network Centric Therapy is highly relevant to the treatment of Parkinson’s disease through deep brain stimulation. Originally wearable and wireless systems for quantifying Parkinson’s disease involved the use a smartphone to quantify hand tremor. Although originally novel, the smartphone has notable issues as a wearable application for quantifying movement disorder tremor. The smartphone has evolved in a pathway that has made the smartphone progressively more cumbersome to mount about the dorsum of the hand. Furthermore, the smartphone utilizes an inertial sensor package that is not certified for medical analysis, and the trial data access a provisional Cloud computing environment through an email account. These concerns are resolved with the recent development of a conformal wearable and wireless inertial sensor system. This conformal wearable and wireless system mounts to the hand with the profile of a bandage by adhesive and accesses a secure Cloud computing environment through a segmented wireless connectivity strategy involving a smartphone and tablet. Additionally, the conformal wearable and wireless system is certified by the FDA of the United States of America for ascertaining medical grade inertial sensor data. These characteristics make the conformal wearable and wireless system uniquely suited for the quantification of Parkinson’s disease treatment through deep brain stimulation. Preliminary evaluation of the conformal wearable and wireless system is demonstrated through the differentiation of deep brain stimulation set to “On” and “Off” status. Based on the robustness of the acceleration signal, this signal was selected to quantify hand tremor for the prescribed deep brain stimulation settings. Machine learning classification using the Waikato Environment for Knowledge Analysis (WEKA) was applied using the multilayer perceptron neural network. The multilayer perceptron neural network achieved considerable classification accuracy for distinguishing between the deep brain stimulation system set to “On” and “Off” status through the quantified acceleration signal data obtained by this recently developed conformal wearable and wireless system. The research achievement establishes a progressive pathway to the future objective of achieving deep brain stimulation capabilities that promote closed-loop acquisition of configuration parameters that are uniquely optimized to the individual through extrinsic means of a highly conformal wearable and wireless inertial sensor system and machine learning with access to Cloud computing resources.

An Automated Deep Learning Based Muscular Dystrophy Detection and Classification Model

Muscular Dystrophy (MD) is a group of inherited muscular diseases that are commonly diagnosed with the help of techniques such asmuscle biopsy, clinical presentation, and Muscle Magnetic Resonance Imaging(MRI). Among these techniques, Muscle MRI recommends the diagnosis ofmuscular dystrophy through identification of the patterns that exist in musclefatty replacement. But the patterns overlap among various diseases whereasthere is a lack of knowledge prevalent with regards to disease-specific patterns.Therefore, artificial intelligence techniques can be used in the diagnosis ofmuscular dystrophies, which enables us to analyze, learn, and predict forthe future. In this scenario, the current research article presents an automated muscular dystrophy detection and classification model using SynergicDeep Learning (SDL) method with extreme Gradient Boosting (XGBoost),called SDL-XGBoost. SDL-XGBoost model has been proposed to act as anautomated deep learning (DL) model that examines the muscle MRI dataand diagnose muscular dystrophies. SDL-XGBoost model employs Kapur’sentropy based Region of Interest (RoI) for detection purposes. Besides, SDLbased feature extraction process is applied to derive a useful set of featurevectors. Finally, XGBoost model is employed as a classification approach todetermine proper class labels for muscle MRI data. The researcher conductedextensive set of simulations to showcase the superior performance of SDLXGBoost model. The obtained experimental values highlighted the supremacyof SDL-XGBoost model over other methods in terms of high accuracy being96.18% and 94.25% classification performance upon DMD and BMD respectively. Therefore, SDL-XGBoost model can help physicians in the diagnosis of muscular dystrophies by identifying the patterns of muscle fatty replacementin muscle MRI.

Distinction of an Assortment of Deep Brain Stimulation Parameter Configurations for Treating Parkinson’s Disease Using Machine Learning with Quantification of Tremor Response through a Conformal Wearable and Wireless Inertial Sensor

Deep brain stimulation offers an advanced means of treating Parkinson’s disease in a patient specific context. However, a considerable challenge is the process of ascertaining an optimal parameter configuration. Imperative for the deep brain stimulation parameter optimization process is the quantification of response feedback. As a significant improvement to traditional ordinal scale techniques is the advent of wearable and wireless systems. Recently conformal wearable and wireless systems with a profile on the order of a bandage have been developed. Previous research endeavors have successfully differentiated between deep brain stimulation “On” and “Off” status through quantification using wearable and wireless inertial sensor systems. However, the opportunity exists to further evolve to an objectively quantified response to an assortment of parameter configurations, such as the variation of amplitude, for the deep brain stimulation system. Multiple deep brain stimulation amplitude settings are considered inclusive of “Off” status as a baseline, 1.0 mA, 2.5 mA, and 4.0 mA. The quantified response of this assortment of amplitude settings is acquired through a conformal wearable and wireless inertial sensor system and consolidated using Python software automation to a feature set amenable for machine learning. Five machine learning algorithms are evaluated: J48 decision tree, K-nearest neighbors, support vector machine, logistic regression, and random forest. The performance of these machine learning algorithms is established based on the classification accuracy to distinguish between the deep brain stimulation amplitude settings and the time to develop the machine learning model. The support vector machine achieves the greatest classification accuracy, which is the primary performance parameter, and K-nearest neighbors achieves considerable classification accuracy with minimal time to develop the machine learning model.

改进YOLOX-s的密集垃圾检测方法

针对密集堆放的多种类垃圾检测存在识别率低、定位不够准确和待测目标被误检、漏检问题,提出了一种融合多头自注意力机制改进YOLOX-s的垃圾检测方法。在特征提取网络嵌入SwinTransformer模块,引入基于滑窗操作的多头自注意力机制,使得网络兼顾全局特征信息和重点特征信息,减少误检现象;在预测输出网络中使用可变形卷积,对初始预测框进行精细化处理,提高定位精度;在EIoU损失的基础上引入加权系数,提出加权IoU-EIoU损失,自适应调整训练时不同阶段不同损失的关注程度,进一步加快训练网络的收敛速度。在公开204类垃圾检测数据集中进行测试,结果表明,所提改进算法的平均精度均值分别可达80.5%和92.5%,优于当前流行目标检测算法,且检测速度快,满足实时性需求。

HR-SCNet在儿童发育性髋关节发育不良诊断中的应用研究

目的:构建基于HR-SCNet网络的计算机辅助诊断模型(CAD),提高发育性髋关节发育不良(DDH)诊断效率。方法:收集某儿童医院DDH患者的骨盆正位X线片,构建包含不同疾病程度的DDH数据集,通过对多尺度特征图空间重构与通道重构,精确定位髋关节8个关键点,并实现DDH的精准诊断。结果:在关键点定位及国际髋关节发育不良协会(IHDI)分型诊断结果中表现较高的准确率,其中IHDIⅠ分型准确率为91.86%,与高年资临床医生诊断结果相似。结论:HR-SCNet模型能够准确定位髋关节关键点并实现DDH的分类诊断,可大幅提升DDH筛查及诊断效率。

基于改进YOLOX-s算法的航天太阳电池缺陷检测

针对航天太阳电池表面缺陷检测问题,提出基于机器视觉与深度学习的缺陷检测方法。通过航天太阳电池缺陷检测系统获取图像,并依据企业电池片缺陷的分类标准构建航天太阳电池缺陷数据集。采用切片技术获取包含缺陷目标的子图像数据集,解决卷积和下采样操作信息丢失而导致召回率低的问题。针对不同缺陷采取适当的图像增强方式进行扩充数据集,以避免训练过程中因数据集不足导致的过拟合问题。采用深度可分离卷积、优化损失函数、双线性插值上采样及引入注意力机制等方法对YOLOX-s算法进行改进,以获得综合效果最佳的航天太阳电池缺陷检测模型。通过不同数据集训练及检测精度指标对比,以及消融实验验证改进模型的有效性。通过改进模型与同类主流模型对比实验,验证改进模型在航天太阳电池缺陷检测方面的优越性。

基于去偏置项SoftMax和紧致度量损失函数的牛脸识别方法

为了实现精准畜牧业生产及畜牧业保险理赔中牛只身份的准确识别,试验提出了基于去偏置项SoftMax和紧致度量损失函数的牛脸识别方法,即采用深度卷积神经网络(deep convolutional neural networks,DCNNs)模型提取特征,利用去偏置项SoftMax损失函数优化特征空间中的特征分布,提高特征线性可分辨性,解决特征归一化后在投影超平面上的重叠问题;采用紧致度量损失函数结合去偏置项SoftMax损失函数联合监督模型训练,使同类特征与类内特征的平均距离最小化,提高特征聚类的紧凑性和可辨识性,同时兼顾了类内样本分布的多样性;最后试验将本算法(去偏置项SoftMax和紧致度量损失函数联合监督算法)与ArcFace损失函数、标准SoftMax损失函数、去偏置项SoftMax损失函数、标准SoftMax损失函数结合紧致度量损失函数进行了性能对分分析。结果表明:本算法的识别准确率在所有模型中最高,为97.61%;且能对高相似度牛脸正确识别。说明基于去偏置项SoftMax和紧致度量损失函数的牛脸识别方法可满足牧场牛只身份识别要求。

Application of sparse S transform network with knowledge distillation in seismic attenuation delineation

Time-frequency analysis is a successfully used tool for analyzing the local features of seismic data.However,it suffers from several inevitable limitations,such as the restricted time-frequency resolution,the difficulty in selecting parameters,and the low computational efficiency.Inspired by deep learning,we suggest a deep learning-based workflow for seismic time-frequency analysis.The sparse S transform network(SSTNet)is first built to map the relationship between synthetic traces and sparse S transform spectra,which can be easily pre-trained by using synthetic traces and training labels.Next,we introduce knowledge distillation(KD)based transfer learning to re-train SSTNet by using a field data set without training labels,which is named the sparse S transform network with knowledge distillation(KD-SSTNet).In this way,we can effectively calculate the sparse time-frequency spectra of field data and avoid the use of field training labels.To test the availability of the suggested KD-SSTNet,we apply it to field data to estimate seismic attenuation for reservoir characterization and make detailed comparisons with the traditional time-frequency analysis methods.