Neuroimage‐based clinical prediction using machine learning tools

Classification of structural brain magnetic resonance (MR) images is a crucial task for many neurological phenotypes that machine learning tools are increasingly developed and applied to solve this problem in recent years. In this study binary classification of T1‐weighted structural brain MR images are performed using state‐of‐the‐art machine learning algorithms when there is no information about the clinical context or specifics of neuroimaging. Image derived features and clinical labels that are provided by the International Conference on Medical Image Computing and Computer‐Assisted Intervention 2014 machine learning challenge are used. These morphological summary features are obtained from four different datasets (each N > 70) with clinically relevant phenotypes and automatically extracted from the MR imaging scans using FreeSurfer, a freely distributed brain MR image processing software package. Widely used machine learning tools, namely; back‐propagation neural network, self‐organizing maps, support vector machines and k‐nearest neighbors are used as classifiers. Clinical prediction accuracy is obtained via cross‐validation on the training data (N = 150) and predictions are made on the test data (N = 100). Classification accuracy, the fraction of cases where prediction is accurate and area under the ROC curve are used as the performance metrics. Accuracy and area under curve metrics are used for tuning the training hyperparameters and the evaluation of the performance of the classifiers. Performed experiments revealed that support vector machines show a better success compared to the other methods on clinical predictions using summary morphological features in the absence of any information about the phenotype. Prediction accuracy would increase greatly if contextual information is integrated into the system. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 89–97, 2017     

Metabolomic approach to evaluate the toxicological effects of nonylphenol with rat urine

Metabolomics has focused on toxicological applications to (1) understand the mechanisms of toxicity, (2) identify novel biomarkers of toxicity, and (3) provide in vivo assessment in animal models through simple and fast methods to date. The toxicological effects of nonylphenol (NP) were evaluated after intraperitoneal injection of rats with 0, 50, and 250 mg kg(-1) day(-1) NP for four consecutive days. In the nontargeted approach, different extraction conditions were introduced to investigate the effects of NP on rats through gas chromatography/mass spectrometry (GC/MS). The GC/MS data obtained were further analyzed with partial least-squares discriminant analysis to compare toxicological effects between control and treated groups. The targeted approach was also used in combination with GC/MS to quantify endocrine hormones and to identify possible biomarkers in rat urine under optimal extraction conditions. In addition, we considered the metabolic trajectory to examine the metabolite profiles and patterns related to steroid metabolism in rats that were treated with NP, considering both treatment amount and time. The data suggest that tetrahydrocorticosterone and 5alpha-tetrahydrocorticosterone are possible urinary biomarkers of NP-induced toxicity. This metabolomic approach is a promising tool to assist with screening in toxicological studies.     

M-IDM: A Multi-Classification Based Intrusion Detection Model in Healthcare IoT

In recent years, the application of a smart city in the healthcare sector via loT systems has continued to grow exponentially and various advanced network intrusions have emerged since these loT devices are being connected. Previous studies focused on security threat detection and blocking technologies that rely on testbed data obtained from a single medical IoT device or simulation using a well-known dataset, such as the NSL-KDD dataset. However, such approaches do not reflect the features that exist in real medical scenarios, leading to failure in potential threat detection. To address this problem, we proposed a novel intrusion classification architecture known as a Multi-class Classification based Intrusion Detection Model (M-IDM), which typically relies on data collected by real devices and the use of convolutional neural networks (i.e., it exhibits better performance compared with conventional machine learning algorithms, such as naïve Bayes, support vector machine (SVM)). Unlike existing studies, the proposed architecture employs the actual healthcare IoT environment of National Cancer Center in South Korea and actual network data from real medical devices, such as a patient’s monitors (i.e., electrocardiogram and thermometers). The proposed architecture classifies the data into multiple classes: Critical, informal, major, and minor, for intrusion detection. Further, we experimentally evaluated and compared its performance with those of other conventional machine learning algorithms, including naïve Bayes, SVM, and logistic regression, using neural networks.     

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 Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

主成分分析的入侵检测方法研究

直接将入侵检测算法应用在粗糙数据上,其入侵检测分析的效率非常低.为解决该问题,提出了一种基于主成分分析的入侵检测方法.该方法通过提取网络连接中的相关信息,对它进行解码,并将解码的网络连接记录与已知的网络连接记录数据进行比较,发现记录中的变化和连接记录分布的主成分,最后将机器学习方法和主成分分析方法结合实现入侵检测.实验结果表明该方法应用到各种不同KDD99入侵检测数据集中可以有效减少学习时间、降低各种数据集的表示空间,提高入侵检测效率.     

Detection and Inhibition of Bacteria on a Dual‐Functional Silver Platform

Detection and inhibition of bacteria are universally required in clinics and daily life for health care. Developing a dual‐functional material is challenging and in demand, engaging advanced applications for both defined bioanalysis and targeted biotoxicity. Herein, magnetic silver nanoshells are designed as a multifunctional platform for the detection and inhibition of bacteria. The optimized magnetic silver nanoshells enable direct laser desorption/ionization mass spectrometry based metabolic analysis of bacteria (≈10 µL^?1), in complex biofluids. The serum infection process (0–10 h) is monitored by statistics toward clinical classification. Moreover, magnetic silver nanoshells facilitate surface adhesion on bacteria due to nanoscale surface roughness and thus display long‐term antibacterial effects. Bacteria metabolism is studied with metabolic biomarkers (e.g., malate and lysine) identified during inhibition, showing cell membrane destruction and dysfunctional protein synthesis mechanisms. This work not only guides the design of material‐based approaches for bioanalysis and biotoxicity, but contributes to bacteria‐related diagnosis by using specific metabolic biomarkers for sensitive detection and new insights by monitoring metabolomic change of bacteria for antibacterial applications.     

An Efficient Internet Traffic Classification System Using Deep Learning for IoT

Internet of Things (IoT) defines a network of devices connected to the internet and sharing a massive amount of data between each other and a central location. These IoT devices are connected to a network therefore prone to attacks. Various management tasks and network operations such as security, intrusion detection, Quality-of-Service provisioning, performance monitoring, resource provisioning, and traffic engineering require traffic classification. Due to the ineffectiveness of traditional classification schemes, such as port-based and payload-based methods, researchers proposed machine learning-based traffic classification systems based on shallow neural networks. Furthermore, machine learning-based models incline to misclassify internet traffic due to improper feature selection. In this research, an efficient multilayer deep learning based classification system is presented to overcome these challenges that can classify internet traffic. To examine the performance of the proposed technique, Moore-dataset is used for training the classifier. The proposed scheme takes the pre-processed data and extracts the flow features using a deep neural network (DNN). In particular, the maximum entropy classifier is used to classify the internet traffic. The experimental results show that the proposed hybrid deep learning algorithm is effective and achieved high accuracy for internet traffic classification, i.e., 99.23%. Furthermore, the proposed algorithm achieved the highest accuracy compared to the support vector machine (SVM) based classification technique and k-nearest neighbours (KNNs) based classification technique.     

A Network Traffic Classification Model Based on Metric Learning

Attacks on websites and network servers are among the most critical threats in network security. Network behavior identification is one of the most effective ways to identify malicious network intrusions. Analyzing abnormal network traffic patterns and traffic classification based on labeled network traffic data are among the most effective approaches for network behavior identification. Traditional methods for network traffic classification utilize algorithms such as Naive Bayes, Decision Tree and XGBoost. However, network traffic classification, which is required for network behavior identification, generally suffers from the problem of low accuracy even with the recently proposed deep learning models. To improve network traffic classification accuracy thus improving network intrusion detection rate, this paper proposes a new network traffic classification model, called ArcMargin, which incorporates metric learning into a convolutional neural network (CNN) to make the CNN model more discriminative. ArcMargin maps network traffic samples from the same category more closely while samples from different categories are mapped as far apart as possible. The metric learning regularization feature is called additive angular margin loss, and it is embedded in the object function of traditional CNN models. The proposed ArcMargin model is validated with three datasets and is compared with several other related algorithms. According to a set of classification indicators, the ArcMargin model is proofed to have better performances in both network traffic classification tasks and open-set tasks. Moreover, in open-set tasks, the ArcMargin model can cluster unknown data classes that do not exist in the previous training dataset.     

An Effective Classifier Model for Imbalanced Network Attack Data

Recently, machine learning algorithms have been used in the detection and classification of network attacks. The performance of the algorithms has been evaluated by using benchmark network intrusion datasets such as DARPA98, KDD’99, NSL-KDD, UNSW-NB15, and Caida DDoS. However, these datasets have two major challenges: imbalanced data and high-dimensional data. Obtaining high accuracy for all attack types in the dataset allows for high accuracy in imbalanced datasets. On the other hand, having a large number of features increases the runtime load on the algorithms. A novel model is proposed in this paper to overcome these two concerns. The number of features in the model, which has been tested at CICIDS2017, is initially optimized by using genetic algorithms. This optimum feature set has been used to classify network attacks with six well-known classifiers according to high f1-score and g-mean value in minimum time. Afterwards, a multi-layer perceptron based ensemble learning approach has been applied to improve the models’ overall performance. The experimental results show that the suggested model is acceptable for feature selection as well as classifying network attacks in an imbalanced dataset, with a high f1-score (0.91) and g-mean (0.99) value. Furthermore, it has outperformed base classifier models and voting procedures.     

Sample handling for mass spectrometric proteomic investigations of human sera

Proteomic investigations of sera are potentially of value for diagnosis, prognosis, choice of therapy, and disease activity assessment by virtue of discovering new biomarkers and biomarker patterns. Much debate focuses on the biological relevance and the need for identification of such biomarkers while less effort has been invested in devising standard procedures for sample preparation and storage in relation to model building based on complex sets of mass spectrometric (MS) data. Thus, development of standardized methods for collection and storage of patient samples together with standards for transportation and handling of samples are needed. This requires knowledge about how sample processing affects MS-based proteome analyses and thereby how nonbiological biased classification errors are avoided. In this study, we characterize the effects of sample handling, including clotting conditions, storage temperature, storage time, and freeze/thaw cycles, on MS-based proteomics of human serum by using principal components analysis, support vector machine learning, and clustering methods based on genetic algorithms as class modeling and prediction methods. Using spiking to artificially create differentiable sample groups, this integrated approach yields data that--even when working with sample groups that differ more than may be expected in biological studies--clearly demonstrate the need for comparable sampling conditions for samples used for modeling and for the samples that are going into the test set group. Also, the study emphasizes the difference between class prediction and class comparison studies as well as the advantages and disadvantages of different modeling methods.     

Screening of biomarkers in rat urine using LC/electrospray ionization-MS and two-way data analysis

Biofluids, like urine, form very complex matrixes containing a large number of potential biomarkers, that is, changes of endogenous metabolites in response to xenobiotic exposure. This paper describes a fast and sensitive method of screening biomarkers in rat urine. Biomarkers for phospholipidosis, induced by an antidepressant drug, were studied. Urine samples from rats exposed to citalopram were analyzed using solid-phase extraction (SPE) and liquid chromatography mass spectrometry (LC/MS) analysis detecting negative ions. A fast iterative method, called Gentle, was used for the automatic curve resolution, and metabolic fingerprints were obtained. After peak alignment principal component analysis (PCA) was performed for pattern recognition, PCA loadings were studied as a means of discovering potential biomarkers. In this study a number of potential biomarkers of phospholipidosis in rats are discussed. They are reported by their retention time and base peak, as their identification is not within the scope of the study. In addition to the fact that it was possible to differentiate control samples from dosed samples, the data were very easy to interpret, and signals from xenobiotic-related substances were easily removed without affecting the endogenous compounds. The proposed method is a complement or an alternative to NMR for metabolomic applications.     

Performance of Lung Cancer Prediction Methods Using Different Classification Algorithms

In 2018, 1.76 million people worldwide died of lung cancer. Most of these deaths are due to late diagnosis, and early-stage diagnosis significantly increases the likelihood of a successful treatment for lung cancer. Machine learning is a branch of artificial intelligence that allows computers to quickly identify patterns within complex and large datasets by learning from existing data. Machine-learning techniques have been improving rapidly and are increasingly used by medical professionals for the successful classification and diagnosis of early-stage disease. They are widely used in cancer diagnosis. In particular, machine learning has been used in the diagnosis of lung cancer due to the benefits it offers doctors and patients. In this context, we performed a study on machine-learning techniques to increase the classification accuracy of lung cancer with 32 × 56 sized numerical data from the Machine Learning Repository web site of the University of California, Irvine. In this study, the precision of the classification model was increased by the effective employment of pre-processing methods instead of direct use of classification algorithms. Nine datasets were derived with pre-processing methods and six machine-learning classification methods were used to achieve this improvement. The study results suggest that the accuracy of the k-nearest neighbors algorithm is superior to random forest, naïve Bayes, logistic regression, decision tree, and support vector machines. The performance of pre-processing methods was assessed on the lung cancer dataset. The most successful pre-processing methods were Z-score (83% accuracy) for normalization methods, principal component analysis (87% accuracy) for dimensionality reduction methods, and information gain (71% accuracy) for feature selection methods.     

A novel learning-based switching median filter for suppression of impulse noise in highly corrupted colour images

A novel switching median filter integrated with a learning-based noise detection method is proposed for suppression of impulse noise in highly corrupted colour images. Noise detection employs a new machine learning algorithm, called margin setting (MS), to detect noise pixels. MS detection is achieved by classifying noise and clean pixels with a decision surface. MS detection yields very high detection accuracy, i.e. a zero miss detection rate and a fairly low over detection rate for a wide range of noise levels. After noise detection, a new filter scheme called the noise-free two-stage (NFTS) filter is triggered. NFTS corrects the noise pixels using the median of the noise-free pixels in two stages. The results of experiments have demonstrated that the MS based NFTS (MSN) filter is superior to the support vector machine and neural network for denoising highly corrupted images, in terms of noise suppression and detail preservation.     

DDoS Detection in SDN using Machine Learning Techniques

Software-defined network (SDN) becomes a new revolutionary paradigm in networks because it provides more control and network operation over a network infrastructure. The SDN controller is considered as the operating system of the SDN based network infrastructure, and it is responsible for executing the different network applications and maintaining the network services and functionalities. Despite all its tremendous capabilities, the SDN face many security issues due to the complexity of the SDN architecture. Distributed denial of services (DDoS) is a common attack on SDN due to its centralized architecture, especially at the control layer of the SDN that has a network-wide impact. Machine learning is now widely used for fast detection of these attacks. In this paper, some important feature selection methods for machine learning on DDoS detection are evaluated. The selection of optimal features reflects the classification accuracy of the machine learning techniques and the performance of the SDN controller. A comparative analysis of feature selection and machine learning classifiers is also derived to detect SDN attacks. The experimental results show that the Random forest (RF) classifier trains the more accurate model with 99.97% accuracy using features subset by the Recursive feature elimination (RFE) method.     

Metabolomic analysis and visualization engine for LC-MS data

Metabolomic analysis by liquid chromatography-high-resolution mass spectrometry results in data sets with thousands of features arising from metabolites, fragments, isotopes, and adducts. Here we describe a software package, Metabolomic Analysis and Visualization ENgine (MAVEN), designed for efficient interactive analysis of LC-MS data, including in the presence of isotope labeling. The software contains tools for all aspects of the data analysis process, from feature extraction to pathway-based graphical data display. To facilitate data validation, a machine learning algorithm automatically assesses peak quality. Users interact with raw data primarily in the form of extracted ion chromatograms, which are displayed with overlaid circles indicating peak quality, and bar graphs of peak intensities for both unlabeled and isotope-labeled metabolite forms. Click-based navigation leads to additional information, such as raw data for specific isotopic forms or for metabolites changing significantly between conditions. Fast data processing algorithms result in nearly delay-free browsing. Drop-down menus provide tools for the overlay of data onto pathway maps. These tools enable animating series of pathway graphs, e.g., to show propagation of labeled forms through a metabolic network. MAVEN is released under an open source license at http://maven.princeton.edu.     

Learning from data: a tutorial with emphasis on modern pattern recognition methods

The purposes of this tutorial are twofold. First, it reviews the classical statistical learning scenario by highlighting its fundamental taxonomies and its key aspects. The second aim of the paper is to introduce some modern (ensembles) methods developed inside the machine learning field. The tutorial starts by putting the topic of supervised learning into the broader context of data analysis and by reviewing the classical pattern recognition methods: those based on class-conditional density estimation and the use of the Bayes theorem and those based on discriminant functions. The fundamental topic of complexity control is treated in some detail. Ensembles techniques have drawn considerable attention in recent years: a set of learning machines increases classification accuracy with respect to a single machine. Here, we introduce boosting, in which classifiers adaptively concentrate on the harder examples located near to the classification boundary and output coding, where a set of independent two-class machines solves a multiclass problem. The first successful applications of these methods to data produced by the Pico-2 electronic nose (EN), developed at the University of Brescia, Brescia, Italy, are also briefly shown.     

Enhanced Deep Autoencoder Based Feature Representation Learning for Intelligent Intrusion Detection System

In the era of Big data, learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system (IDS). Owing to the lack of accurately labeled network traffic data, many unsupervised feature representation learning models have been proposed with state-of-the-art performance. Yet, these models fail to consider the classification error while learning the feature representation. Intuitively, the learnt feature representation may degrade the performance of the classification task. For the first time in the field of intrusion detection, this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder (DAE) for learning the robust feature representation and one-class support vector machine (OCSVM) for finding the more compact decision hyperplane for intrusion detection. Specially, the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously. This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection. Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model. First, the ablation evaluation on benchmark dataset, NSL-KDD validates the design decision of the proposed model. Next, the performance evaluation on recent intrusion dataset, UNSW-NB15 signifies the stable performance of the proposed model. Finally, the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.     

Warranty and discrete preventive maintenance

In this paper two machine learning algorithms, decision trees (DT) and Hamming clustering (HC), are compared in building approximate reliability expression (RE). The main idea is to employ a classification technique, trained on a restricted subset of data, to produce an estimate of the RE, which provides reasonably accurate values of the reliability. The experiments show that although both methods yield excellent predictions, the HC procedure achieves better results with respect to the DT algorithm.     

Discrete Wavelet Transmission and Modified PSO with ACO Based Feed Forward Neural Network Model for Brain Tumour Detection

In recent years, the development in the field of computer-aided diagnosis (CAD) has increased rapidly. Many traditional machine learning algorithms have been proposed for identifying the pathological brain using magnetic resonance images. The existing algorithms have drawbacks with respect to their accuracy, efficiency, and limited learning processes. To address these issues, we propose a pathological brain tumour detection method that utilizes the Weiner filter to improve the image contrast, 2D- discrete wavelet transformation (2D-DWT) to extract the features, probabilistic principal component analysis (PPCA) and linear discriminant analysis (LDA) to normalize and reduce the features, and a feed-forward neural network (FNN) and modified particle swarm optimization (MPSO) with ant colony optimization (ACO) to improve the accuracy, stability, and overcome fitting issues in the classification of brain magnetic resonance images. The proposed method achieves better results than other existing algorithms.