Multilayer Classifier Research Articles

A taxonomy of service identification approaches for legacy software systems modernization

The success of modernizing legacy software systems to Service-Oriented Architecture (SOA) depends on Service Identification Approaches (SIAs), which identify reusable functionalities that could become services. The literature describes several SIAs. However, the selection of an identification approach that is suitable for a practitioner is difficult because it depends on several factors, including the goal of modernization, the available legacy artifacts, the organization’s development process, the desired output, and the usability of the approach. Accordingly, to select a suitable service identification approach, a practitioner must have a comprehensive view of existing techniques.We report a systematic literature review (SLR) that covers 41 SIAs based on software-systems analyses. Based on this SLR, we create a taxonomy of SIAs and build a multi-layer classification of existing identification approaches. We start from a high-level classification based on the used inputs, the applied processes, the given outputs, and the usability of the SIAs. We then divide each category into a fine-grained taxonomy that helps practitioners in selecting a suitable approach for identifying services in legacy software systems. We build our SLR based on our experience with legacy software modernization, on discussions and experiences working with industrial partners, and analyses of existing SIAs. We validate the correctness and the coverage of our review with industrial experts who modernize(d) legacy software systems to SOA. The results show that our classification conforms to the industrial experts’ experiences. We also show that most of the studied SIAs are still at their infancy. Finally, we identify the main challenges that SIAs need to address, to improve their quality.

Characterizing and classifying neuroendocrine neoplasms through microRNA sequencing and datamining.

Neuroendocrine neoplasms (NENs) are clinically diverse and incompletely characterized cancers that are challenging to classify. MicroRNAs (miRNAs) are small regulatory RNAs that can be used to classify cancers. Recently, a morphology-based classification framework for evaluating NENs from different anatomical sites was proposed by experts, with the requirement of improved molecular data integration. Here, we compiled 378 miRNA expression profiles to examine NEN classification through comprehensive miRNA profiling and data mining. Following data preprocessing, our final study cohort included 221 NEN and 114 non-NEN samples, representing 15 NEN pathological types and 5 site-matched non-NEN control groups. Unsupervised hierarchical clustering of miRNA expression profiles clearly separated NENs from non-NENs. Comparative analyses showed that miR-375 and miR-7 expression is substantially higher in NEN cases than non-NEN controls. Correlation analyses showed that NENs from diverse anatomical sites have convergent miRNA expression programs, likely reflecting morphological and functional similarities. Using machine learning approaches, we identified 17 miRNAs to discriminate 15 NEN pathological types and subsequently constructed a multilayer classifier, correctly identifying 217 (98%) of 221 samples and overturning one histological diagnosis. Through our research, we have identified common and type-specific miRNA tissue markers and constructed an accurate miRNA-based classifier, advancing our understanding of NEN diversity.

WiFi-based driver’s activity recognition using multi-layer classification

The driver’s activity monitoring has gained more consideration in advanced vehicular technology because of its abundant benefits for driving assistance systems. The driver’s activity recognition may also provide vital information about the state of driver attentiveness causing a substantial reduction in the number of fatal accidents. This paper aims to design an innovative framework to characterize in-vehicle activities using ubiquitous WiFi devices for the safety benefits of drivers. In our presented device-free system, driver’s activities are investigated as multi-class classification problem leveraging Channel State Information (CSI) of WiFi signals. In this novel approach, we have examined the capability of the Sparse Least Square Support Vector Machine (SLS-SVM) with Baye’s maximum likelihood estimation for better discrimination of in-vehicle activities. In this framework, multiple classifiers are arranged in a multi-layer hierarchy for higher scalability as compared to conventional single-layer methods. This sophisticated scheme leads to address the problem of driver’s activity recognition with significant improvement in performance. The proposed low-cost solution can provide an average recognition accuracy of 91.5% for valuable insight into the design of an autonomous driving system.

Isolated Keyword Spotting in Multilingual Environment using ANN and MFCC

The performance and analysis of Keyword Spotting system (KWS) are applied when the training and testing in a multilingual environment. This paper exhibits an approach for building up a multilingual KWS framework for Assamese, English and Hindi language dependent on feed-forward neural system. Mel Frequency Cepstral Coefficient (MFCC) has been utilized for highlight extraction which gives a lot of highlight vectors from recorded sound examples. Neural Network backpropagation model is utilized to improve the acknowledgment execution on the recently made multilingual database utilizing the multi-layer feed-forward neural system classifier.

Isolated Keyword Spotting in Multilingual Environment using ANN and MFCC

The performance and analysis of Keyword Spotting system (KWS) are applied when the training and testing in a multilingual environment. This paper exhibits an approach for building up a multilingual KWS framework for Assamese, English and Hindi language dependent on feed-forward neural system. Mel Frequency Cepstral Coefficient (MFCC) has been utilized for highlight extraction which gives a lot of highlight vectors from recorded sound examples. Neural Network backpropagation model is utilized to improve the acknowledgment execution on the recently made multilingual database utilizing the multi-layer feed-forward neural system classifier.

Graph Embedding-Based Wireless Link Scheduling With Few Training Samples

Link scheduling in device-to-device (D2D) networks is usually formulated as a non-convex combinatorial problem, which is generally NP-hard and difficult to get the optimal solution. Traditional methods to solve this problem are mainly based on mathematical optimization techniques, where accurate channel state information (CSI), usually obtained through channel estimation and feedback, is needed. To overcome the high computational complexity of the traditional methods and eliminate the costly channel estimation stage, machine leaning (ML) has been introduced recently to address the wireless link scheduling problems. In this article, we propose a novel graph embedding based method for link scheduling in D2D networks. We first construct a fully-connected directed graph for the D2D network, where each D2D pair is a node while interference links among D2D pairs are the edges. Then we compute a low-dimensional feature vector for each node in the graph. The graph embedding process is based on the distances of both communication and interference links, therefore without requiring the accurate CSI. By utilizing a multi-layer classifier, a scheduling strategy can be learned in a supervised manner based on the graph embedding results for each node. We also propose an unsupervised manner to train the graph embedding based method to further reinforce the scalability and develop a K-nearest neighbor graph representation method to reduce the computational complexity. Extensive simulation demonstrates that the proposed method is near-optimal compared with the existing state-of-art methods but is with only hundreds of training network layouts. It is also competitive in terms of scalability and generalizability to more complicated scenarios.

Multilayer Fractional-Order Machine Vision Classifier for Rapid Typical Lung Diseases Screening on Digital Chest X-Ray Images

Lung diseases can result in acute breathing problems and prevent the human body from acquiring enough oxygen. These diseases, such as pneumonia (P), pleural effusion (Ef), lung cancer, pneumothorax (Pt), pulmonary fibrosis (F), infiltration (In) and emphysema (E), adversely affect airways, alveoli, blood vessels, pleura and other parts of the respiratory system. The death rates of P and lung cancer are higher than those of other typical lung diseases. In visualization examination, chest radiography, such as anterior-posterior or lateral image viewing, is a straightforward approach used by clinicians/radiologists to diagnose and locate possible lung abnormalities rapidly. However, a chest X-ray image of patients may show multiple abnormalities associated with coexisting conditions, such as P, E, F, Pt, atelectasis, lung cancer or surgical interventions, which further complicate diagnosis. In addition, poor-quality X-ray images and manual inspection have limitations in digital image-automated classification. Hence, this study intends to propose a multilayer machine vision classifier to automatically identify the possible class of lung diseases within a bounding region of interest (ROI) on a chest X-ray image. For digital image texture analysis, a two-dimensional (2D) fractional-order convolution (FOC) operation with a fractional-order parameter, $v =0.3-0.5$ , is used to enhance the symptomatic feature and remove unwanted noises. Then, maximum pooling is performed to reduce the dimensions of feature patterns and accelerate complex computations. A multilayer machine vision classifier with radial Bayesian network and gray relational analysis is used to screen subjects with typical lung diseases. Anterior-posterior chest X-ray images from the NIH chest X-ray database (NIH Clinical Center) are enrolled. For digital chest X-ray images, with $K$ -fold cross-validation, the proposed multilayer machine vision classifier is applied to facilitate the diagnosis of typical lung diseases on specific bounding ROIs, as promising results with mean recall (%), mean precision (%), mean accuracy (%) and mean F1 score of 98.68%, 82.42%, 83.57% and 0.8981, respectively, for assessing the performance of proposed multilayer classifier for rapidly screening lung lesions on digital chest X-ray images.

A Complete Automatic Target Recognition System of Low Altitude, Small RCS and Slow Speed (LSS) Targets Based on Multi-Dimensional Feature Fusion.

Low altitude, small radar cross-section (RCS), and slow speed (LSS) targets, for example small unmanned aerial vehicles (UAVs), have become increasingly significant. In this paper, we propose a new automatic target recognition (ATR) system and a complete ATR chain based on multi-dimensional features and multi-layer classifier system using L-band holographic staring radar. We consider all steps of the processing required to make a classification decision out of the raw radar data, mainly including preprocessing for the raw measured Doppler data including regularization and main frequency alignment, selection, and extraction of effective features in three dimensions of RCS, micro-Doppler, and motion, and multi-layer classifier system design. We design creatively a multi-layer classifier system based on directed acyclic graph. Helicopters, small fixed-wing, and rotary-wing UAVs, as well as birds are considered for classification, and the measured data collected by L-band radar demonstrates the effectiveness of the proposed complete ATR classification system. The results show that the ATR classification system based on multi-dimensional features and k-nearest neighbors (KNN) classifier is the best, compared with support vector machine (SVM) and back propagation (BP) neural networks, providing the capability of correct classification with a probability of around 97.62%.

Underwater Moving Target Classification Using Multilayer Processing of Active Sonar System

The task of detecting and classifying highly maneuverable and unidentified underwater targets in complex environments is significant in active sonar systems. Previous studies have applied many detection schemes to this task using signals above a preset threshold to separate targets from clutter; this is because a high signal-to-noise ratio (SNR) target has sufficient feature vector components to be separated out. However, in real environments, the received target return’s SNR is not always above the threshold. Therefore, a target detection algorithm is needed for varied target SNR conditions. When the clutter energy is too strong, false detection can occur, and the probability of detection is reduced due to the weak target signature. Furthermore, since a long pulse repetition interval is used for long-range detection and ambient noise tends to be high, classification processing for each ping is needed. This paper proposes a multilayer classification algorithm applicable to all signals in real underwater environments above the noise level without thresholding and verifies the algorithm’s classification performance. We obtained a variety of experimental data by using a real underwater target and a hull-mounted active sonar system operated on Korean naval ships in the East Sea, Korea. The detection performance of the proposed algorithm was evaluated in terms of the classification rate and false alarm rate as a function of the SNR. Since experimental environment data, including the sea state, target maneuvering patterns, and sound speed, were available, we selected 1123 instances of ping data from the target over all experiments and randomly selected 1000 clutters based on the distribution of clutters for each ping. A support vector machine was employed as the classifier, and 80% of the data were selected for training, leaving the remaining data for testing. This process was carried out 1000 times. For the performance analysis and discussions, samples of scatter diagrams and feature characteristics are shown and classification tables and receiver operation characteristic (ROC) curves are presented. The results show that the proposed algorithm is effective under a variety of target strengths and ambient noise levels.

MULTI-LAYER CLASSIFIER FOR MINIMIZING FALSE INTRUSION

Intrusion detection is one of the standard stages to protect computers in network security framework from several attacks. False alarms problem is critical in intrusion detection, which motivates many researchers to discover methods to minify false alarms. This paper proposes a procedure for classifying the type of intrusion according to multi-operations and multi-layer classifier for handling false alarms in intrusion detection. The proposed system is tested using on KDDcup99 benchmark. The performance showed that results obtained from three consequent classifiers are better than a single classifier. The accuracy reached 98% based on 25 features instead of using all features of KDDCup99 dataset.

MULTI-LAYER CLASSIFIER FOR MINIMIZING FALSE INTRUSION

Intrusion detection is one of the standard stages to protect computers in network security framework from several attacks. False alarms problem is critical in intrusion detection, which motivates many researchers to discover methods to minify false alarms. This paper proposes a procedure for classifying the type of intrusion according to multi-operations and multi-layer classifier for handling false alarms in intrusion detection. The proposed system is tested using on KDDcup99 benchmark. The performance showed that results obtained from three consequent classifiers are better than a single classifier. The accuracy reached 98% based on 25 features instead of using all features of KDDCup99 dataset.

Detection of atrial fibrillation and other abnormal rhythms from ECG using a multi-layer classifier architecture

Objective: Atrial fibrillation (AF) and other types of abnormal heart rhythm are related to multiple fatal cardiovascular diseases that affect the quality of human life. Hence the development of an automated robust method that can reliably detect AF, in addition to other non-sinus and sinus rhythms, would be a valuable addition to medicine. The present study focuses on developing an algorithm for the classification of short, single-lead electrocardiogram (ECG) recordings into normal, AF, other abnormal rhythms and noisy classes. Approach: The proposed classification framework presents a two-layer, three-node architecture comprising binary classifiers. PQRST markers are detected on each ECG recording, followed by noise removal using a spectrogram power based novel adaptive thresholding scheme. Next, a feature pool comprising time, frequency, morphological and statistical domain ECG features is extracted for the classification task. At each node of the classification framework, suitable feature subsets, identified through feature ranking and dimension reduction, are selected for use. Adaptive boosting is selected as the classifier for the present case. The training data comprises 8528 ECG recordings provided under the PhysioNet 2017 Challenge. F1 scores averaged across the three non-noisy classes are taken as the performance metric. Main result: The final five-fold cross-validation score achieved by the proposed framework on the training data has high accuracy with low variance (0.8254 0.0043). Significance: Further, the proposed algorithm has achieved joint first place in the PhysioNet/Computing in Cardiology Challenge 2017 with a score of 0.83 computed on a hidden test dataset.

Frequency Feature Learning from Vibration Information of GIS for Mechanical Fault Detection.

The reliability of gas insulated switchgear (GIS) is very important for the safe operation of power systems. However, the research on potential faults of GIS is mainly focused on partial discharge, and the research on the intelligent detection technology of the mechanical state of GIS is very scarce. Based on the abnormal vibration signals generated by a GIS fault, a fault diagnosis method consisting of a frequency feature extraction method based on coherent function (CF) and a multi-layer classifier was developed in this paper. First, the Fourier transform was used to analyze the differences and consistency in the frequency spectrum of signals. Secondly, the frequency domain commonalities of the vibration signals were extracted by using CF, and the vibration characteristics were screened twice by using the correlation threshold and frequency threshold to further select the vibration features for diagnosis. Then, a multi-layer classifier composed of two one-class support vector machines (OCSVMs) and one support vector machine (SVM) was designed to classify the faults of GIS. Finally, the feasibility of the feature extraction method was verified by experiments, and compared with other classification methods, the stability and reliability of the proposed classifier were verified, which indicates that the fault diagnosis method promotes the development of an intelligent detection technology of the mechanical state in GIS.

A Novel Multi-Layer Classification Ensemble Approach for Location Prediction of Social Users

Information-disclosure by social-users has increased enormously. Using this information for accurate location-prediction is challenging. Thus, a novel Multi-Layer Ensemble Classification scheme is proposed. It works on un-weighted/weighted majority voting, using novel weight-assignment function. Base learners are selected based on their individual performances for training the model. Main motive is to develop an efficient approach for check-ins-based location-classification of social-users. The proposed model is implemented on Foursquare datasets where a classification accuracy of 94% is achieved, which is higher than other state-of-the-art techniques. Apart from tracking locations of social-users, proposed framework can be useful for detecting malicious users present in various expert and intelligent-system.

Multi-layer Classification and Segmentation using Ensemble Learning for Opinion Mining

In recent years, social media has become the prime place for advertisements, activities, campaigns, protests etc. It provides a platform for the people to express their views and beliefs to the masses. The user beliefs, practices and interests are of great importance to organizations and provide insight into the minds of users. Data Mining is one such tool that enables these organizations to extract relevant information from user data, which can be analyzed to create a knowledge set and determine user opinion that allows companies to create products tailored to the user. Data Mining of Twitter and other social platforms is of a great importance because, its large user base is a goldmine of public opinions and views which if analyzed properly, can potentially be used to predict campaign results and product assessments and likeability. This project proposes a classification scheme that aims to perform Segmentation based Twitter Opinion Mining using Ensemble Learning. The proposed scheme is able to detect and filter out bots and uses text segmentation for effective text classification and part of speech tagging.

Research on Multi-layer Classification Method of Network Traffic Based on Machine Learning

According to the network traffic characteristic group, this paper designs a kind of network traffic classification with coarse and fine two layers. The first layer based on the experience attribute selection and the fast multilayer clustering method, constructs the unsupervised classifier, which realizes the coarse classification of the network traffic dataset and forms the data subset; the second layer, based on the selected subset of data, constructs a strong supervised classifier, which realizes the fine classification of the network traffic data set, according to the ensemble learning method. Theoretical analysis and experiments show that this method can not only improve the accuracy of network traffic classification, but also reduce the time of classification greatly, which is important to improve the accuracy of small class classification of imbalanced network traffic data.

Dynamic Multi-layer Ensemble Classification Framework for Social Venues Using Binary Particle Swarm Optimization

Multi-layer ensemble frameworks perform much better as compared to individual classifiers. However, selection of a classifier and its placement, impacts the overall performance of ensemble framework. This problem becomes very difficult, if there are more classifiers and layers. To address these problems in this paper, we design “Binary Particle Swarm Optimization” method for selection and placement of right classifiers in multi-layer ensemble model. Proposed classifier weight-assignment method is implemented to prioritize the selected classifiers. The model is simulated for the classification of social-user check-ins in Location-Based Social Network datasets. The experimental results show that the proposed ensemble model outperforms the state-of-the-art ensemble methods in the literature. It can be used by security firms, high level decision makers and various governmental organizations for tracking malicious users.

Multimodal Object Classification Models Inspired by Multisensory Integration in the Brain.

Two multimodal classification models aimed at enhancing object classification through the integration of semantically congruent unimodal stimuli are introduced. The feature-integrating model, inspired by multisensory integration in the subcortical superior colliculus, combines unimodal features which are subsequently classified by a multimodal classifier. The decision-integrating model, inspired by integration in primary cortical areas, classifies unimodal stimuli independently using unimodal classifiers and classifies the combined decisions using a multimodal classifier. The multimodal classifier models are implemented using multilayer perceptrons and multivariate statistical classifiers. Experiments involving the classification of noisy and attenuated auditory and visual representations of ten digits are designed to demonstrate the properties of the multimodal classifiers and to compare the performances of multimodal and unimodal classifiers. The experimental results show that the multimodal classification systems exhibit an important aspect of the “inverse effectiveness principle” by yielding significantly higher classification accuracies when compared with those of the unimodal classifiers. Furthermore, the flexibility offered by the generalized models enables the simulations and evaluations of various combinations of multimodal stimuli and classifiers under varying uncertainty conditions.

Early Detection of Alzheimer’s Using Digital Image Processing Through Iridology, An Alternative Method

Over the years, alternative medicine has carried out numerous systematic studies of the eye, proposing as an analytical support to the iridology, which studies the alterations of the iris in correspondence with the organs of the human body. This is why it presents the opportunity to investigate and learn about certain neuronal diseases, specifically Alzheimer's based on digital image processing. For this, the use of mathematical models based on specialized software (Matlab), determines the characteristics of the iris establishing criteria or patterns to determine the existence or not of Alzheimer's. For this we have: i) The Fourier Transform to normalize the image; ii) The Hough Transform to locate circles in an image. In addition some learning methods based on three multi-layer classifiers were used: ZeroR, Naive Bayes and Multi-layer Perceptron. Finally, to distinguish between the different types of pathologies, several samples must be used and well identified, that is, the data must be consistent and with a good resolution to avoid influencing the results.

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.