Deep Learning and Machine Learning for Early Detection of Stroke and Haemorrhage

Stroke and cerebral haemorrhage are the second leading causes of death in the world after ischaemic heart disease. In this work, a dataset containing medical, physiological and environmental tests for stroke was used to evaluate the efficacy of machine learning, deep learning and a hybrid technique between deep learning and machine learning on the Magnetic Resonance Imaging (MRI) dataset for cerebral haemorrhage. In the first dataset (medical records), two features, namely, diabetes and obesity, were created on the basis of the values of the corresponding features. The t-Distributed Stochastic Neighbour Embedding algorithm was applied to represent the high-dimensional dataset in a low-dimensional data space. Meanwhile,the Recursive Feature Elimination algorithm (RFE) was applied to rank the features according to priority and their correlation to the target feature and to remove the unimportant features. The features are fed into the various classification algorithms, namely, Support Vector Machine (SVM), K Nearest Neighbours (KNN), Decision Tree, Random Forest, and Multilayer Perceptron. All algorithms achieved superior results. The Random Forest algorithm achieved the best performance amongst the algorithms; it reached an overall accuracy of 99%. This algorithm classified stroke cases with Precision, Recall and F1 score of 98%, 100% and 99%, respectively. In the second dataset, the MRI image dataset was evaluated by using the AlexNet model and AlexNet + SVM hybrid technique. The hybrid model AlexNet + SVM performed is better than the AlexNet model; it reached accuracy, sensitivity, specificity and Area Under the Curve (AUC) of 99.9%, 100%, 99.80% and 99.86%, respectively.     

Performance enhancement of swarm intelligence techniques in dementia classification using dragonfly-based hybrid algorithms

Most often clinicians require automated computer-aided MRI classification techniques to substantiate the status of dementia accurately. In this research paper, dragonfly-based features are used to improve the accuracy of well-known swarm intelligence algorithms specifically particle swarm optimization, artificial bee colony, and ant colony optimization in dementia classification. Cross-sectional MRI of 65 non-dementia and 52 dementia subjects were collected from the OASIS database and analyzed. The dementia classification performance of above-mentioned three individual swarm intelligence algorithms is compared with non-swarm intelligence algorithm—Fuzzy C means. A further comparison was made on the improvisation of above-mentioned swarm intelligence algorithms while using dragonfly-based features and Fuzzy C means-based features. Although many swarm intelligence algorithms are reported in the literature, it is ingenious to use dragonfly-based features for improving the performance of individual swarm intelligence algorithms in dementia classification. With proper weight parameters, Dragonfly-particle swarm optimization hybrid classifier yields the highest accuracy of 87.18%, whereas all the above-mentioned individual classifiers yield accuracy of less than 66%.     

Marker-Based and Marker-Less Motion Capturing Video Data: Person and Activity Identification Comparison Based on Machine Learning Approaches

Biomechanics is the study of physiological properties of data and the measurement of human behavior. In normal conditions, behavioural properties in stable form are created using various inputs of subconscious/conscious human activities such as speech style, body movements in walking patterns, writing style and voice tunes. One cannot perform any change in these inputs that make results reliable and increase the accuracy. The aim of our study is to perform a comparative analysis between the marker-based motion capturing system (MBMCS) and the marker-less motion capturing system (MLMCS) using the lower body joint angles of human gait patterns. In both the MLMCS and MBMCS, we collected trajectories of all the participants and performed joint angle computation to identify a person and recognize an activity (walk and running). Using five state of the art machine learning algorithms, we obtained 44.6% and 64.3% accuracy in person identification using MBMCS and MLMCS respectively with an ensemble algorithm (two angles as features). In the second set of experiments, we used six machine learning algorithms to obtain 65.9% accuracy with the k-nearest neighbor (KNN) algorithm (two angles as features) and 74.6% accuracy with an ensemble algorithm. Also, by increasing features (6 angles), we obtained higher accuracy of 99.3% in MBMCS for person recognition and 98.1% accuracy in MBMCS for activity recognition using the KNN algorithm. MBMCS is computationally expensive and if we re-design the model of OpenPose with more body joint points and employ more features, MLMCS (low-cost system) can be an effective approach for video data analysis in a person identification and activity recognition process.     

A Hybrid Model Using Bio-Inspired Metaheuristic Algorithms for Network Intrusion Detection System

Network Intrusion Detection System (IDS) aims to maintain computer network security by detecting several forms of attacks and unauthorized uses of applications which often can not be detected by firewalls. The features selection approach plays an important role in constructing effective network IDS. Various bio-inspired metaheuristic algorithms used to reduce features to classify network traffic as abnormal or normal traffic within a shorter duration and showing more accuracy. Therefore, this paper aims to propose a hybrid model for network IDS based on hybridization bio-inspired metaheuristic algorithms to detect the generic attack. The proposed model has two objectives; The first one is to reduce the number of selected features for Network IDS. This objective was met through the hybridization of bio-inspired metaheuristic algorithms with each other in a hybrid model. The algorithms used in this paper are particle swarm optimization (PSO), multi-verse optimizer (MVO), grey wolf optimizer (GWO), moth-flame optimization (MFO), whale optimization algorithm (WOA), firefly algorithm (FFA), and bat algorithm (BAT). The second objective is to detect the generic attack using machine learning classifiers. This objective was met through employing the support vector machine (SVM), C4.5 (J48) decision tree, and random forest (RF) classifiers. UNSW-NB15 dataset used for assessing the effectiveness of the proposed hybrid model. UNSW-NB15 dataset has nine attacks type. The generic attack is the highest among them. Therefore, the proposed model aims to identify generic attacks. My data showed that J48 is the best classifier compared to SVM and RF for the time needed to build the model. In terms of features reduction for the classification, my data show that the MFO-WOA and FFA-GWO models reduce the features to 15 features with close accuracy, sensitivity and F-measure of all features, whereas MVO-BAT model reduces features to 24 features with the same accuracy, sensitivity and F-measure of all features for all classifiers.     

样本过滤的基因表达数据分类

针对单个人工神经网络稳定性差、分类精度不高的缺点,提出了基于样本过滤的人工神经网络集成算法,并用于基因表达数据分类.采用基因表达数据集Leukemia进行实验仿真,并与单个BP神经网络、Bagging神经网络集成和支持向量机进行比较.结果表明,样本过滤算法具有更好的稳定性和更高的分类精度.     

带噪语流中浊音端点检测

浊音端点检测在语音处理中占有重要地位,在语音编解码、语音识别、语音增强处理中都需要用到端点检测技术。常规的以短时能量、过零率等作为判决特征参数的方法无法在低信噪比的系统中满足应用需求。本文以信号的共振峰和基音周期检测为基础检测浊音端点,算法首先提取语音信号的第一共振峰以及基音周期信息并以此为判决依据判断浊音的起点和终点。实验证明,这种方法在噪声环境中相对于传统的基于能量检测的或AMR_WB标准中的端点检测算法有更高的正确率。     

基于SVM的高通量dPCR基因芯片荧光图像分类研究

目的 为了实现高通量dPCR基因芯片荧光图像的亮点分类与计数,提出一种基于支持向量机（SVM）的荧光图像分类与计数方法。方法 首先对荧光图像进行去噪、对比度增强等图像预处理,对预处理后荧光图像进行亮点区域提取标注,去除背景与暗点的冗余信息,利用方向梯度直方图（Histogram of Oriented Gradient, HOG）提取鉴别特征,计算合并所有样本的亮点特征得到HOG特征向量,根据已得到的HOG特征向量创建一个线性SVM分类器,利用训练好的SVM分类器对荧光图像亮点进行分类与计数。结果 对比传统算法,文中算法具有较高的分类识别精度,平均准确率高达98%以上,可以很好地实现荧光图像亮点分类与计数。结论 在有限的小样本标注数据下,文中算法具有良好的分类性能,能够有效识别荧光图像中的亮点,对其他荧光图像分类研究也具有一定参考价值。     

基于线性判别分析的决策融合脑电意识动态分类

脑电信号的识别与分类是脑机接口技术的热点研究问题,单一分类器不能很好利用特征以及分类器的适应性,导致识别的准确率很难进一步提高,基于线性判别分析的分类决策级融合策略,可用于提高脑-机接口系统的分类准确率。首先,通过分离出两种分类器的假性试验特征,从这两种方法中选择更有可能正确决策提高分类准确性;其次为了测量每个决策的不确定性,使用与所对应分类器的最大和第二大相关系数提取特征向量。基于这一思想,提出了一种新的决策选择器,该方法通过整合两种基于线性判别分析的算法选择更有可能是准确的决策,从而达到提高脑电信号分类准确度。实验结果表明,该方法通过与精度相近的算法相结合在运动想象数据分类上获得了较好的分类准确率。     

有效特征参数分类正常与病理语音

采用残差信号的特征参数——基音幅值（Pitch Amplitude,PA）和频谱平坦度（Spectral Flatness of the Residue Signal,SFR）与语音信号倒谱域特征参数——倒谱峰值突出（Cepstral Peak Prominence,CPP）来区分正常与病理语音,在萨尔布吕肯语音数据库中选择自然音调的正常与病理语音/a/进行仿真实验。统计结果表明,与正常语音相比,病理语音的PA较小,SFR更接近零,CPP也较小。结合其他传统特征参数分析对比,证明SFR、PA和CPP更能有效分类正常与病理语音。通过不同分类算法比较,得出支持向量机的分类准确率相对更高。     

Classification of brain hemorrhage computed tomography images using OzNet hybrid algorithm

Classification of brain hemorrhage computed tomography (CT) images provides a better diagnostic implementation for emergency patients. Attentively, each brain CT image must be examined by doctors. This situation is time-consuming, exhausting, and sometimes leads to making errors. Hence, we aim to find the best algorithm owing to a requirement for automatic classification of CT images to detect brain hemorrhage. In this study, we developed OzNet hybrid algorithm, which is a novel convolution neural networks (CNN) algorithm. Although OzNet achieves high classification performance, we combine it with Neighborhood Component Analysis (NCA) and many classifiers: Artificial neural networks (ANN), Adaboost, Bagging, Decision Tree, K-Nearest Neighbor (K-NN), Linear Discriminant Analysis (LDA), Naïve Bayes and Support Vector Machines (SVM). In addition, Oznet is utilized for feature extraction, where 4096 features are extracted from the fully connected layer. These features are reduced to have significant and informative features with minimum loss by NCA. Eventually, we use these classifiers to classify these significant features. Finally, experimental results display that OzNet-NCA-ANN excellent classifier model and achieves 100% accuracy with created Dataset 2 from Brain Hemorrhage CT images.     

支持向量机集成和特征选择联合算法

提出了两种基于支持向量机集成和特征选择联合算法。联合算法的核心思想是在构建基础分类器的同时选择有效特征。通过对实测舰船数据和公共数据的识别实验,证明了两种算法都可以用于舰船目标识别。算法一更适用于冗余特征较多的情况。算法二在对舰船目标识别时,选择的特征数目降低为原来特征数目的30%,正确分类率比单个支持向量机高近10%。     

Cancers classification based on deep neural networks and emotional learning approach

In the present era, enormous factors contribute to causing cancer. So cancer classification cannot rely only on doctor''s thoughts. As a result, intelligent algorithms concerning doctor''s help are inevitable. Therefore, the authors are motivated to suggest a novel algorithm to classify three cancer datasets; colon, ALL‐AML, and leukaemia cancers. Their proposed algorithm is based on the deep neural network and emotional learning process. First of all, by applying the principal component analysis, they had a feature reduction. Then, they used deep neural as a feature extraction. Then, they implemented different classifiers; multi‐layer perceptron, support vector machine (SVM), decision tree, and Gaussian mixture model. In the end, because in the real world, especially when working on systems biology, unpredictable events, and uncertainties are undeniable, the robustness of their model against uncertainties is important. So they added Gaussian noise to the input features of the first encoder in each dataset, then, they applied the stacked denoising method. Experimental results disclosed that, generally, using emotional learning increased the accuracy. In addition, the highest accuracy was gained by SVM, 91.66, 92.27, and 96.56% for colon, ALL‐AML, and leukaemia, respectively. However, GMM led to the lowest accuracy. The best accuracy gained by GMM was 60%.Inspec keywords: cancer, learning (artificial intelligence), principal component analysis, multilayer perceptrons, feature extraction, support vector machines, pattern classification, Gaussian processes, decision trees, Gaussian noise, medical computingOther keywords: colon cancer, Gaussian noise, stacked denoising method, SVM, support vector machine, emotional learning process, cancer datasets, intelligent algorithms, cancer classification, ALL‐AML, input features, Gaussian mixture model, decision tree, multilayer perceptron, feature extraction, feature reduction, principal component analysis, deep neural network, leukaemia cancers     

深度可分离卷积神经网络在自动分拣中的应用

针对传统的花卉分类算法在工业自动化分拣应用中出现模型参数过大、分拣精度不高的问题,提出一种基于深度学习的花卉识别算法。介绍了花卉分类算法在工业花卉包装分拣系统中的应用;根据实际需求,采用一种深度可分离卷积神经网络提取花卉特征,并详细分析了网络的模型结构;为了提高模型训练速度,提出了一种微调的模型训练方法。实验结果表明,所采用的花卉分类算法在工业花卉自动分拣的应用中相比传统算法,准确率更高、稳定性更好、应用更加广泛。     

Classification of mammogram images using the energy probability in frequency domain and most discriminative power coefficients

The purpose of this work is to develop a computer-aided diagnosis (CAD) system to assist radiologists in the classification of mammogram images. The CAD system is composed of three main steps. The first step is image preprocessing and segmentation with the seeded region growing algorithm applied on a localized triangular region to remove only the muscle. In the second step of the CAD system, we proposed a novel features extraction method, which consists of three stages. In the first, the discrete cosine transform (DCT) is applied on all obtained regions of interest and then only the upper left corner (ULC) of DCT coefficients is retained. Second, we have applied the energy probability to the ULCs that is used as a criterion for selecting discriminant information. At the last stage, a new Most Discriminative power coefficient algorithm has been proposed to select the most significant features. In the final step of the CAD, the support vector machines, Naive Bayes, and artificial neural network (ANN) classifiers are used to make an effective classification. The evaluation of the proposed algorithm on the mini-Mammographic Image Analysis Society database shows its efficiency over other recently proposed CAD systems in the literature, whereas an accuracy of 100% can be achieved using ANN with a small number of features.     

BHGSO: Binary Hunger Games Search Optimization Algorithm for Feature Selection Problem

In machine learning and data mining, feature selection (FS) is a traditional and complicated optimization problem. Since the run time increases exponentially, FS is treated as an NP-hard problem. The researcher’s effort to build a new FS solution was inspired by the ongoing need for an efficient FS framework and the success rates of swarming outcomes in different optimization scenarios. This paper presents two binary variants of a Hunger Games Search Optimization (HGSO) algorithm based on V- and S-shaped transfer functions within a wrapper FS model for choosing the best features from a large dataset. The proposed technique transforms the continuous HGSO into a binary variant using V- and S-shaped transfer functions (BHGSO-V and BHGSO-S). To validate the accuracy, 16 famous UCI datasets are considered and compared with different state-of-the-art metaheuristic binary algorithms. The findings demonstrate that BHGSO-V achieves better performance in terms of the selected number of features, classification accuracy, run time, and fitness values than other state-of-the-art algorithms. The results demonstrate that the BHGSO-V algorithm can reduce dimensionality and choose the most helpful features for classification problems. The proposed BHGSO-V achieves 95% average classification accuracy for most of the datasets, and run time is less than 5 sec. for low and medium dimensional datasets and less than 10 sec for high dimensional datasets.     

Detection of pneumonia in chest X‐ray images by using 2D discrete wavelet feature extraction with random forest

Pneumonia is one of the most common and fatal diseases in the world. Early diagnosis and treatment are important factors in reducing mortality caused by the aforementioned disease. One of the most important and common techniques to diagnose pneumonia disease is the X‐ray images. By evaluating these images, various machine‐learning methods are used for accuracy in diagnosis. The presented study in this article utilizes machine‐learning techniques to evaluate these X‐ray images. The diagnosis of pediatric pneumonia is classified with a proposed machine learning method by using the chest X‐ray images. The proposed system firstly utilizes a two‐dimensional discrete wavelet transform to extract features from images. The features obtained from the wavelet method are labeled as normal and pneumonia and applied to the classifier for classification. Besides, Random Forest algorithm is used for the classification technique of 5856 X‐ray images. A 10‐fold cross‐validation method is used to evaluate the success of the proposed method and to ensure that the system avoided overfitting. By using various machine learning algorithms, simulation results reveal that the Random Forest method is proposed and it gives successful results. Results also show that, at the end of the training and validation process, the proposed method achieves higher success with an accuracy of 97.11%.     

Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization

Applications of internet-of-things (IoT) are increasingly being used in many facets of our daily life, which results in an enormous volume of data. Cloud computing and fog computing, two of the most common technologies used in IoT applications, have led to major security concerns. Cyberattacks are on the rise as a result of the usage of these technologies since present security measures are insufficient. Several artificial intelligence (AI) based security solutions, such as intrusion detection systems (IDS), have been proposed in recent years. Intelligent technologies that require data preprocessing and machine learning algorithm-performance augmentation require the use of feature selection (FS) techniques to increase classification accuracy by minimizing the number of features selected. On the other hand, metaheuristic optimization algorithms have been widely used in feature selection in recent decades. In this paper, we proposed a hybrid optimization algorithm for feature selection in IDS. The proposed algorithm is based on grey wolf (GW), and dipper throated optimization (DTO) algorithms and is referred to as GWDTO. The proposed algorithm has a better balance between the exploration and exploitation steps of the optimization process and thus could achieve better performance. On the employed IoT-IDS dataset, the performance of the proposed GWDTO algorithm was assessed using a set of evaluation metrics and compared to other optimization approaches in the literature to validate its superiority. In addition, a statistical analysis is performed to assess the stability and effectiveness of the proposed approach. Experimental results confirmed the superiority of the proposed approach in boosting the classification accuracy of the intrusion in IoT-based networks.     

基于集成分类器的泡罩包装药品缺陷识别

目的 针对药品生产包装过程中常出现缺陷泡罩包装药品的问题,研究一种基于多特征构建与集成分类器的泡罩包装药品缺陷识别方法.方法 该方法通过集成2个不同的分类器算法分别对药品图像类别进行预测,并采用联合判定函数对2个预测输出值进行联合决策,得到最终分类结果.第1个分类器模型通过将图像转化到HSV颜色空间,分割出泡罩区域和药片区域,进行特征设计,并在提取多项特征参数后构建BP神经网络分类算法给定药品类别预测.第2个分类器模型应用多层卷积神经网络取代传统算法对图像特征进行提取,并输出药品图像类别的预测值.根据2个分类器的性能进行算法集成,构成最终集成分类器.结果 实验结果表明,该集成分类模型对数据集中泡罩包装药品图像进行分类识别测试,准确率达97％以上.结论 集成分类模型不仅提高了单一分类器的识别准确率,也具有更佳的稳定性.该方法取得了卓越的分类效果,具有较高应用性.     

基于核映射稀疏表示分类的轴承故障诊断

针对传统稀疏表示分类算法在低维空间分类精度难以保证问题,论文提出了基于核映射的稀疏表示分类算法。采用核映射方法获得了低维样本在高维空间的坐标,改善了样本间的线性可分度;在此基础上,利用稀疏表示分类算法获得样本在高维空间上的稀疏解。经滚动轴承故障分类实验验证：新算法对核参数具有较高的鲁棒性;可明显提高分类精度。     

CANFIS based glioma brain tumor classification and retrieval system for tumor diagnosis

Brain tumor classification and retrieval system plays an important role in medical field. In this paper, an efficient Glioma Brain Tumor detection and its retrieval system is proposed. The proposed methodology consists of two modules as classification and retrieval. The classification modules are designed using preprocessing, feature extraction and tumor detection techniques using Co‐Active Adaptive Neuro Fuzzy Inference System (CANFIS) classifier. The image enhancement can be achieved using Heuristic histogram equalization technique as preprocessing and further texture features as Local Ternary Pattern (LTP) features and Grey Level Co‐occurrence Matrix (GLCM) features are extracted from the enhanced image. These features are used to classify the brain image into normal and abnormal using CANFIS classifier. The tumor region in abnormal brain image is segmented using normalized graph cut segmentation algorithm. The retrieval module is used to retrieve the similar segmented tumor regions from the dataset for diagnosing the tumor region using Euclidean algorithm. The proposed Glioma Brain tumor classification methodology achieves 97.28% sensitivity, 98.16% specificity and 99.14% accuracy. The proposed retrieval system achieves 97.29% precision and 98.16% recall rate with respect to ground truth images.