Kernel-like impurity detection according to colour band spectral image using GA/SVM

Kernel-like impurities (KLIs) have the similar colour, shape, texture and specific gravity with sound kernels. The amount of the KLIs is an important parameter for evaluating the quality of wheat. However, it is difficult to classify KLIs from sound kernels with normal methods because of these similar features. In this study, a machine vision system with a linear colour charged coupled device used to acquire images of kernels and a software package developed to extract various features from the images were used to classify 1169 sound kernels and 896 KLIs. Three methods—genetic algorithm (GA)/support vector machine (SVM), principal components analysis/SVM and linear discriminant analysis—were applied for the classification. The performance of GA/SVM for detecting KLIs was very outstanding, and the accuracy of testing sets could reach 99.34%. GA/SVM has the potential to improve the KLI classification accuracy in machine vision system. It is feasible to extract a small quantity of useful features without any extra image or data processing for online KLI classification.     

Pre-trained convolutional neural networks as feature extractors for diagnosis of breast cancer using histopathology

Several researchers are trying to develop different computer-aided diagnosis system for breast cancer employing machine learning (ML) methods. The inputs to these ML algorithms are labeled histopathological images which have complex visual patterns. So, it is difficult to identify quality features for cancer diagnosis. The pre-trained Convolutional Neural Networks (CNNs) have recently emerged as an unsupervised feature extractor. However, a limited investigation has been done for breast cancer recognition using histopathology images with CNN as a feature extractor. This work investigates ten different pre-trained CNNs for extracting the features from breast cancer histopathology images. The breast cancer histopathological images are obtained from publicly available BreakHis dataset. The classification models for the different feature sets, which are obtained using different pre-trained CNNs in consideration, are developed using a linear support vector machine. The proposed method outperforms the other state of art methods for cancer detection, which can be observed from the results obtained.     

基于融合特征的短语音汉语声调自动识别方法

提出一种基于韵律特征(基频、时长)和梅尔倒谱系数(Mel-Frequency Cepstral Coefficient,MFCC)特征的融合特征进行短语音汉语声调识别的方法,旨在利用两种特征的优势提高短语音汉语声调识别率。该融合特征包括7个根据不同模型得到的韵律特征和统计参数以及4个从每个音段的梅尔倒谱系数计算得来的对数化后验概率,使用高斯混合模型表示4个声调的倒谱特征的分布。实验分两步:第一步,将基于韵律特征和倒谱特征的分类器在决策阶段混合起来进行声调分类,分别赋予两个分类器权重,计算倒谱特征和韵律特征在声调分类任务中的权重;第二步,将基于字的韵律特征和基于帧的倒谱特征结合起来生成融合特征的超向量,使用融合特征进行汉语声调识别,根据准确率、未加权平均召回率(Unweigted Average Recall,UAR)和科恩卡帕(Cohen’s Kappa)系数3个指标,比较并评估5种分类器(两种设置的高斯混合模型,后向传播神经网络,支持向量机和卷积神经网络(Convolutional Neural Network,CNN))在不平衡数据集上的分类效果。实验结果表明:(1)倒谱特征方法能够提高汉语声调的识别率,该特征在总体分类任务中的权重为0.11;(2)基于融合特征的深度学习(CNN)方法对声调的识别率最高,为87.6%,与高斯混合模型的基线系统相比,提高了5.87%。该研究证明了倒谱特征法能够提供与韵律特征法互补的信息,从而提高短语音汉语声调识别率;同时,该方法可以运用到韵律检测和副语言信息检测等相关研究中。     

Breast Cancer Detection in Saudi Arabian Women Using Hybrid Machine Learning on Mammographic Images

Breast cancer (BC) is the most common cause of women’s deaths worldwide. The mammography technique is the most important modality for the detection of BC. To detect abnormalities in mammographic images, the Breast Imaging Reporting and Data System (BI-RADs) is used as a baseline. The correct allocation of BI-RADs categories for mammographic images is always an interesting task, even for specialists. In this work, to detect and classify the mammogram images in BI-RADs, a novel hybrid model is presented using a convolutional neural network (CNN) with the integration of a support vector machine (SVM). The dataset used in this research was collected from different hospitals in the Qassim health cluster of Saudi Arabia. The collection of all categories of BI-RADs is one of the major contributions of this paper. Another significant contribution is the development of a hybrid approach through the integration of CNN and SVM. The proposed hybrid approach uses three CNN models to obtain ensemble CNN model results. This ensemble model saves the values to integrate them with SVM. The proposed system achieved a classification accuracy, sensitivity, specificity, precision, and F1-score of 93.6%, 94.8%, 96.9%, 96.6%, and 95.7%, respectively. The proposed model achieved better performance compared to previously available methods.     

Detection and classification of large bowel obstruction from X-ray images using machine learning algorithms

Large bowel obstruction (LBO) occurs when there is a blockage or twisting in the large bowel that prevents wastes and gas from passing through. If left untreated, the blockage cuts off blood supply to the colon, causing sections of it to die which results in high rates of morbidity and fatality. The examination of clinical symptoms of LBO involves careful inspection of the cecum and colon. Radiologists use X-rays to inspect the clinical signs. Some research has been done to automate the detection of related abdominal and intestinal diseases. However, all these studies concentrate only on detecting Crohn's, ulcerative colitis, Acute Appendicitis, colorectal cancer, celiac diseases, liver diseases, and chronic kidney diseases. Automatic detection and classification of LBO has not been given due attention so far to the best of the authors knowledge. To address this challenge, we have designed a model for the detection and classification of LBO. The models development comprises of stages such as preprocessing, detection, segmentation, feature extraction, and classification. We used YOLOv3 for detection and used a gray scale level co-occurrence matrix (GLCM), and a convolutional neural network for feature extraction, while support vector machine (SVM) and softmax were used for classification. The proposed model achieved a diagnostic accuracy of 89% when feature extraction methods such as CNN and median filter with softmax classifier were used. CNN and Gaussian filter with soft max classifier achieved 91%, while CNN and anisotropic filter with soft max classifier achieved 92%. GLCM with threshold segmentation and Gaussian filter with SVM classifier achieved 87%, while CNN with watershed segmentation and Gaussian filter with SVM classifier achieved 97% and CNN-GLCM with watershed segmentation and anisotropic diffusion filter with SVM classifier achieved 98% for detection and classification of LBO. Finally, this paper presented a performance analysis of various machine learning approaches for detection and classification of LBO. Hence, our model is designed to assist human experts (Radiologists) in diagnosing LBO.     

Traffic Sign Recognition Method Integrating Multi-Layer Features and Kernel Extreme Learning Machine Classifier

Traffic sign recognition (TSR), as a critical task to automated driving and driver assistance systems, is challenging due to the color fading, motion blur, and occlusion. Traditional methods based on convolutional neural network (CNN) only use an end-layer feature as the input to TSR that requires massive data for network training. The computation-intensive network training process results in an inaccurate or delayed classification. Thereby, the current state-of-the-art methods have limited applications. This paper proposes a new TSR method integrating multi-layer feature and kernel extreme learning machine (ELM) classifier. The proposed method applies CNN to extract the multi-layer features of traffic signs, which can present sufficient details and semantically abstract information of multi-layer feature maps. The extraction of multi-scale features of traffic signs is effective against object scale variation by applying a new multi-scale pooling operation. Further, the extracted features are combined into a multi-scale multi-attribute vector, which can enhance the feature presentation ability for TSR. To efficiently handle nonlinear sampling problems in TSR, the kernel ELM classifier is adopted for efficient TSR. The kernel ELM has a more powerful function approximation capability, which can achieve an optimal and generalized solution for multiclass TSR. Experimental results demonstrate that the proposed method can improve the recognition accuracy, efficiency, and adaptivity to complex travel environments in TSR.     

A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition

Identifying fruit disease manually is time-consuming, expert-required, and expensive; thus, a computer-based automated system is widely required. Fruit diseases affect not only the quality but also the quantity. As a result, it is possible to detect the disease early on and cure the fruits using computer-based techniques. However, computer-based methods face several challenges, including low contrast, a lack of dataset for training a model, and inappropriate feature extraction for final classification. In this paper, we proposed an automated framework for detecting apple fruit leaf diseases using CNN and a hybrid optimization algorithm. Data augmentation is performed initially to balance the selected apple dataset. After that, two pre-trained deep models are fine-tuning and trained using transfer learning. Then, a fusion technique is proposed named Parallel Correlation Threshold (PCT). The fused feature vector is optimized in the next step using a hybrid optimization algorithm. The selected features are finally classified using machine learning algorithms. Four different experiments have been carried out on the augmented Plant Village dataset and yielded the best accuracy of 99.8%. The accuracy of the proposed framework is also compared to that of several neural nets, and it outperforms them all.     

Analysis and classification of oral tongue squamous cell carcinoma based on Raman spectroscopy and convolutional neural networks

ABSTRACT

To detect oral tongue squamous cell carcinoma (OTSCC) using fibre optic Raman spectroscopy, we present a classification model based on convolutional neural networks (CNN) and support vector machines (SVM). 24 samples Raman spectra of OTSCC and para-carcinoma tissues from 12 patients were collected and analysed. In our proposed model, CNN is used as a feature extractor for forming a representative vector. Then the derived features are fed into an SVM classifier, which is used for OTSCC classification. Experimental results demonstrated that the area under the receiver operating characteristic curve was 99.96% and the classification error was zero (sensitivity: 99.54%, specificity: 99.54%). To show the superiority of this model, comparison results with the state-of-the-art methods showed it can obtain a competitive accuracy. These findings may pay a way to apply the proposed model in the fibre optic Raman instruments for intra-operative evaluation of OTSCC resection margins.     

Brain Tumor Detection and Classification Using PSO and Convolutional Neural Network

Tumor detection has been an active research topic in recent years due to the high mortality rate. Computer vision (CV) and image processing techniques have recently become popular for detecting tumors in MRI images. The automated detection process is simpler and takes less time than manual processing. In addition, the difference in the expanding shape of brain tumor tissues complicates and complicates tumor detection for clinicians. We proposed a new framework for tumor detection as well as tumor classification into relevant categories in this paper. For tumor segmentation, the proposed framework employs the Particle Swarm Optimization (PSO) algorithm, and for classification, the convolutional neural network (CNN) algorithm. Popular preprocessing techniques such as noise removal, image sharpening, and skull stripping are used at the start of the segmentation process. Then, PSO-based segmentation is applied. In the classification step, two pre-trained CNN models, alexnet and inception-V3, are used and trained using transfer learning. Using a serial approach, features are extracted from both trained models and fused features for final classification. For classification, a variety of machine learning classifiers are used. Average dice values on datasets BRATS-2018 and BRATS-2017 are 98.11 percent and 98.25 percent, respectively, whereas average jaccard values are 96.30 percent and 96.57% (Segmentation Results). The results were extended on the same datasets for classification and achieved 99.0% accuracy, sensitivity of 0.99, specificity of 0.99, and precision of 0.99. Finally, the proposed method is compared to state-of-the-art existing methods and outperforms them.     

Medical Diagnosis Using Machine Learning: A Statistical Review

Decision making in case of medical diagnosis is a complicated process. A large number of overlapping structures and cases, and distractions, tiredness, and limitations with the human visual system can lead to inappropriate diagnosis. Machine learning (ML) methods have been employed to assist clinicians in overcoming these limitations and in making informed and correct decisions in disease diagnosis. Many academic papers involving the use of machine learning for disease diagnosis have been increasingly getting published. Hence, to determine the use of ML to improve the diagnosis in varied medical disciplines, a systematic review is conducted in this study. To carry out the review, six different databases are selected. Inclusion and exclusion criteria are employed to limit the research. Further, the eligible articles are classified depending on publication year, authors, type of articles, research objective, inputs and outputs, problem and research gaps, and findings and results. Then the selected articles are analyzed to show the impact of ML methods in improving the disease diagnosis. The findings of this study show the most used ML methods and the most common diseases that are focused on by researchers. It also shows the increase in use of machine learning for disease diagnosis over the years. These results will help in focusing on those areas which are neglected and also to determine various ways in which ML methods could be employed to achieve desirable results.     

Plant Disease Diagnosis and Image Classification Using Deep Learning

Indian agriculture is striving to achieve sustainable intensification, the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem. Modern farming employs technology to improve productivity. Early and accurate analysis and diagnosis of plant disease is very helpful in reducing plant diseases and improving plant health and food crop productivity. Plant disease experts are not available in remote areas thus there is a requirement of automatic low-cost, approachable and reliable solutions to identify the plant diseases without the laboratory inspection and expert's opinion. Deep learning-based computer vision techniques like Convolutional Neural Network (CNN) and traditional machine learning-based image classification approaches are being applied to identify plant diseases. In this paper, the CNN model is proposed for the classification of rice and potato plant leaf diseases. Rice leaves are diagnosed with bacterial blight, blast, brown spot and tungro diseases. Potato leaf images are classified into three classes: healthy leaves, early blight and late blight diseases. Rice leaf dataset with 5932 images and 1500 potato leaf images are used in the study. The proposed CNN model was able to learn hidden patterns from the raw images and classify rice images with 99.58% accuracy and potato leaves with 97.66% accuracy. The results demonstrate that the proposed CNN model performed better when compared with other machine learning image classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree and Random Forest.     

Classification of motor imagery electroencephalography signals using continuous small convolutional neural network

As an important part of brain-computer interface (BCI), the electroencephalography (EEG) technology of motor imagery (MI) has been gradually recognized for its great theoretical value and practical application. In this study, in view of the different MI tasks corresponding to active region of the EEG signals, we adopt a two-dimensional form including time, frequency, and electrode location information, then we design a classification method containing continuous small convolutional neural network (CSCNN). This method is mainly used for feature extraction through continuous small convolutional kernels and one rectangle convolutional kernel, and the softmax classifier for classification. In the experiment, classification accuracy and kappa value are used as evaluation criteria to verify the effectiveness of the method proposed in this study. For classification accuracy, BCI competition IV data set 2b is used to compare with the other five classification methods (CNN, CNN-SAE, stacked autoencoder [SAE], support vector machine [SVM], and one-dimensional convolution combined with gated recurrent unit [1DCGRU]). The results demonstrate that the overall accuracy of CSCNN is higher than other methods, and CSCNN obtains an average accuracy of 82.8%. For kappa value, BCI competition IV data set 2b is used to compare with the other three methods (filter bank common spatial pattern [FBCSP], Twin SVM, and CNN-SAE). The performance of CSCNN is better with an average value of 0.663. Overall, the results show that CSCNN maintains a small number of parameters and improves the classification accuracy.     

Efficient classification of chronic kidney disease by using multi-kernel support vector machine and fruit fly optimization algorithm

In recent days, the gigantic generation of medical data from smart healthcare applications requires the development of big data classification methodologies. Medical data classification can be utilized for visualizing the hidden patterns and finding the presence of disease from the medical data. In this article, we present an efficient multi-kernel support vector machine (MKSVM) and fruit fly optimization algorithm (FFOA) for disease classification. Initially, FFOA is employed to choose the finest features from the available set of features. The selected features from the medical dataset are processed and provided to the MKSVM for medical data classification purposes. The proposed chronic kidney disease (CKD) classification method has been simulated in MATLAB. Next, testing of the dataset takes place using the own benchmark CKD dataset from UCI machine learning repositories such as Kidney chronic, Cleveland, Hungarian, and Switzerland. The performance of the proposed CKD classification method is elected by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, false positive rate, and false negative rate. The investigational outcome specifies that the proposed CKD classification method achieves maximum classification precision value of 98.5% for chronic kidney dataset, 90.42904% for Cleveland, 89.11565% for Hungarian, and 86.17886% for Switzerland dataset than existing hybrid kernel SVM, fuzzy min-max GSO neural network, and SVM methods.     

Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization

Human gait recognition (HGR) has received a lot of attention in the last decade as an alternative biometric technique. The main challenges in gait recognition are the change in in-person view angle and covariant factors. The major covariant factors are walking while carrying a bag and walking while wearing a coat. Deep learning is a new machine learning technique that is gaining popularity. Many techniques for HGR based on deep learning are presented in the literature. The requirement of an efficient framework is always required for correct and quick gait recognition. We proposed a fully automated deep learning and improved ant colony optimization (IACO) framework for HGR using video sequences in this work. The proposed framework consists of four primary steps. In the first step, the database is normalized in a video frame. In the second step, two pre-trained models named ResNet101 and InceptionV3 are selected and modified according to the dataset's nature. After that, we trained both modified models using transfer learning and extracted the features. The IACO algorithm is used to improve the extracted features. IACO is used to select the best features, which are then passed to the Cubic SVM for final classification. The cubic SVM employs a multiclass method. The experiment was carried out on three angles (0, 18, and 180) of the CASIA B dataset, and the accuracy was 95.2, 93.9, and 98.2 percent, respectively. A comparison with existing techniques is also performed, and the proposed method outperforms in terms of accuracy and computational time.     

Multimodal magnetic resonance imaging for Alzheimer's disease diagnosis using hybrid features extraction and ensemble support vector machines

Magnetic resonance imaging (MRI) is increasingly used in the diagnosis of Alzheimer's disease (AD) in order to identify abnormalities in the brain. Indeed, cortical atrophy, a powerful biomarker for AD, can be detected using structural MRI (sMRI), but it cannot detect impairment in the integrity of the white matter (WM) preceding cortical atrophy. The early detection of these changes is made possible by the novel MRI modality known as diffusion tensor imaging (DTI). In this study, we integrate DTI and sMRI as complementary imaging modalities for the early detection of AD in order to create an effective computer-assisted diagnosis tool. The fused Bag-of-Features (BoF) with Speeded-Up Robust Features (SURF) and modified AlexNet convolutional neural network (CNN) are utilized to extract local and deep features. This is applied to DTI scalar metrics (fractional anisotropy and diffusivity metric) and segmented gray matter images from T1-weighted MRI images. Then, the classification of local unimodal and deep multimodal features is first performed using support vector machine (SVM) classifiers. Then, the majority voting technique is adopted to predict the final decision from the ensemble SVMs. The study is directed toward the classification of AD versus mild cognitive impairment (MCI) versus cognitively normal (CN) subjects. Our proposed method achieved an accuracy of 98.42% and demonstrated the robustness of multimodality imaging fusion.     

Classification of Alzheimer disease among susceptible brain regions

Statistical and machine learning techniques are frequently employed in the study of neuroimaging data for finding Alzheimer disease (AD) in clinical studies and in additional inquiries about research settings. AD affects the whole brain and as a result the quality of life, where most affected regions are the hippocampus (HP), middle temporal gyrus (MTG), entorhinal cortex, and posterior cingulate cortex (PCC). We used well-known classification methods to diagnose the affected regions of the brain at different stages of age using biomarker modalities and functional magnetic resonance imaging (fMRI) at the resting state, and later marked the affected brain region on MRI. We have used well-known support vector machine (SVM), Fisher's linear discriminant analysis, artificial neural network, and logistic regression for the classification of AD. In the context of receiver operating characteristic (ROC) curves, an SVM provided the best classification among AD stages. Moreover, analysis showed development of AD.     

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto-encoders

Diabetic retinopathy (DR) and Diabetic Macular Edema (DME) are severe diseases that affect the eyes due to damage in blood vessels. Computer-aided automated grading will help clinicians conduct disease diagnoses at ease. Experiments of automated image processing with deep learning techniques using CNN produce promising results, especially in the medical imaging domain. However, the disease grading tasks in retinal images using CNN struggle to retain high-quality information at the output. A novel deep learning model based on variational auto-encoder to grade DR and DME abnormalities in retinal images is proposed. The objective of the proposed model is to extract the most relevant retinal image features efficiently. It focuses on addressing less relevant candidate region generation and translational invariance present in images. The experiments are conducted in IDRID dataset and evaluated using accuracy, U-kappa, sensitivity, specificity and precision metrics. The results outperform compared with other state-of-art techniques.     

Magnetic resonance brain image classification based on weighted‐type fractional Fourier transform and nonparallel support vector machine

To classify brain images into pathological or healthy is a key pre‐clinical state for patients. Manual classification is tiresome, expensive, time‐consuming, and irreproducible. In this study, we aimed to present an automatic computer‐aided system for brain‐image classification. We used 90 T2‐weighted images obtained by magnetic resonance images. First, we used weighted‐type fractional Fourier transform (WFRFT) to extract spectrums from each magnetic resonance image. Second, we used principal component analysis (PCA) to reduce spectrum features to only 26. Third, those reduced spectral features of different samples were combined and were fed into support vector machine (SVM) and its two variants: generalized eigenvalue proximal SVM and twin SVM. A 5 × 5‐fold cross‐validation results showed that this proposed “WFRFT + PCA + generalized eigenvalue proximal SVM” yielded sensitivity of 99.53%, specificity of 92.00%, precision of 99.53%, and accuracy of 99.11%, which are comparable with the proposed “WFRFT + PCA + twin SVM” and better than the proposed “WFRFT + PCA + SVM.” Besides, all three proposed methods were superior to eight state‐of‐the‐art algorithms. Thus, WFRFT is effective, and the proposed methods can be used in practical. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 317–327, 2015     

Digital Twin-Based Automated Fault Diagnosis in Industrial IoT Applications

In recent years, Digital Twin (DT) has gained significant interest from academia and industry due to the advanced in information technology, communication systems, Artificial Intelligence (AI), Cloud Computing (CC), and Industrial Internet of Things (IIoT). The main concept of the DT is to provide a comprehensive tangible, and operational explanation of any element, asset, or system. However, it is an extremely dynamic taxonomy developing in complexity during the life cycle that produces a massive amount of engendered data and information. Likewise, with the development of AI, digital twins can be redefined and could be a crucial approach to aid the Internet of Things (IoT)-based DT applications for transferring the data and value onto the Internet with better decision-making. Therefore, this paper introduces an efficient DT-based fault diagnosis model based on machine learning (ML) tools. In this framework, the DT model of the machine is constructed by creating the simulation model. In the proposed framework, the Genetic algorithm (GA) is used for the optimization task to improve the classification accuracy. Furthermore, we evaluate the proposed fault diagnosis framework using performance metrics such as precision, accuracy, F-measure, and recall. The proposed framework is comprehensively examined using the triplex pump fault diagnosis. The experimental results demonstrated that the hybrid GA-ML method gives outstanding results compared to ML methods like Logistic Regression (LR), Naïve Bayes (NB), and Support Vector Machine (SVM). The suggested framework achieves the highest accuracy of 95% for the employed hybrid GA-SVM. The proposed framework will effectively help industrial operators make an appropriate decision concerning the fault analysis for IIoT applications in the context of Industry 4.0.