Online Classification Research Articles

An in-process multi-feature data fusion nondestructive testing approach for wire arc additive manufacturing

PurposeThe major problem that limits the widespread use of WAAM technology is the forming quality. However, most of the current research focuses on post-process detections that are time-consuming, expensive and destructive. This paper aims to achieve the on-line detection and classification of the common defects, including hump, deposition collapse, deviation, internal pore and surface slag inclusion.Design/methodology/approachThis paper proposes an in-process multi-feature data fusion nondestructive testing method based on the temperature field of the WAAM process. A thermal imager is used to collect the temperature data of the deposition layer in real-time. Efficient processing methods are proposed in this paper, such as the temperature stack algorithm, width extraction algorithm and a classification model based on a residual neural network. Some features closely related to the forming quality were extracted, containing the profile image and width curve of the deposition layer and abnormal temperature features in longitudinal and cross-sections. These features are used to achieve the detection and classification of defects.FindingsThermal non-destructive testing is a potentially superior technology for in-process detection in the industrial field. Based on the temperature field, extracting the most relevant features of the defect information is crucial. This paper pushes current infrared (IR) monitoring methods toward real-time detection and proposes an in-process multi-feature data fusion non-destructive testing method based on the temperature field of the WAAM process.Originality/valueIn this paper, the single-layer and multi-layer WAAM samples are preset with various defects, such as hump, deposition collapse, deviation, pore and slag inclusion. A multi-feature nondestructive testing methodology is proposed to realize the in-process detection and classification of the defects. A temperature stack algorithm is proposed, which improves the detection accuracy of profile change and solves the problem of uneven temperature from arc striking to arc extinguishing. The combination of residual neural network greatly improves the accuracy and efficiency of detection.

Control of Newly-Designed Wearable Robotic Hand Exoskeleton Based on Surface Electromyographic Signals.

The human hand plays a role in a variety of daily activities. This intricate instrument is vulnerable to trauma or neuromuscular disorders. Wearable robotic exoskeletons are an advanced technology with the potential to remarkably promote the recovery of hand function. However, the still face persistent challenges in mechanical and functional integration, with real-time control of the multiactuators in accordance with the motion intentions of the user being a particular sticking point. In this study, we demonstrated a newly-designed wearable robotic hand exoskeleton with multijoints, more degrees of freedom (DOFs), and a larger range of motion (ROM). The exoskeleton hand comprises six linear actuators (two for the thumb and the other four for the fingers) and can realize both independent movements of each digit and coordinative movement involving multiple fingers for grasp and pinch. The kinematic parameters of the hand exoskeleton were analyzed by a motion capture system. The exoskeleton showed higher ROM of the proximal interphalangeal and distal interphalangeal joints compared with the other exoskeletons. Five classifiers including support vector machine (SVM), K-near neighbor (KNN), decision tree (DT), multilayer perceptron (MLP), and multichannel convolutional neural networks (multichannel CNN) were compared for the offline classification. The SVM and KNN had a higher accuracy than the others, reaching up to 99%. For the online classification, three out of the five subjects showed an accuracy of about 80%, and one subject showed an accuracy over 90%. These results suggest that the new wearable exoskeleton could facilitate hand rehabilitation for a larger ROM and higher dexterity and could be controlled according to the motion intention of the subjects.

Research on Brand Database Construction System Using Computer Statistics and Big Data

The clothing brand database is an important channel for designers to obtain fashion trends. The diversification of clothing types and artistic styles provides a variety of ideas for the classification of clothing brands. In the process of establishing a clothing brand database, we need to sum up a set of key phrases used to describe clothing brands in view of the single shortcomings of the existing clothing brand online classification query system. At the same time, we take the actual needs of the brand clothing industry development as the starting point, based on the SSI framework technology, to achieve a clothing customization information platform suitable for small batches and multiple brands, targeting user experience, and achieving rapid response. The test shows that the design of the brand clothing database construction platform meets the expected functional requirements. The design ideas and implementation methods of the system are effective and feasible. The design and implementation of the platform effectively opened the relevant information system modules of the clothing brand. This will have important reference value for promoting the intelligent manufacturing and business model transformation of clothing enterprises, and promoting the standardization and customization of clothing enterprises under the environment of industrialization 4.0.

Thermal Monitoring of Underground Medium Voltage Cables Based on Machine Learning Techniques

In this paper a monitoring system for Medium Voltage (MV) cables is presented and simulated. It consists of a classification tool capable of identifying the working temperature of several sections of underground cables starting from the Frequency Response Analysis (FRA). This means that the monitoring procedure can be applied during normal network operation with a low intrusive level and allows the localization of the cable section in the worst working conditions. Starting from this information it is possible to organize the maintenance operations and avoid the occurrence of catastrophic failures. The monitoring method shown in this paper focuses on the relationship between cable temperature and conductor resistance. The online classification of the working temperature is carried out through two different machine learning techniques: Support Vector Machine (SVM) and Complex Neural Network (CNN). Both the single-fault hypothesis and the multiple-fault hypothesis are studied; in the first case the classification results are always higher than 95%, while in the more complex situation the classification rate decreases slightly. To make the simulation procedure as general as possible, Simulink-Simscape blocks, called “Three-phase AC power cable”, are used in this paper.

From the Editor’s Desk

Dear Readers Belfast-born William Thomson (better known as Lord Kelvin) said ‘If you cannot measure it, you cannot improve it’ and this remains as true today as it was over 100 years ago. Measurement in headache medicine is challenged with a lack of gold standard testing for diagnoses, relying instead on symptom criteria much of the time rather than neurobiological features. In this inaugural edition of Headache Medicine Connections Dr. Pravin Thomas and colleagues introduce the World Headache Society Classification of Headache Disorders, representing an exciting multidimensional user-friendly and up-to-date approach to the challenge of headache classification, an area in need of advancement. The reader will immediately notice the multi-axial construct, allowing separate axes for patient narrative, biomarkers and validated impairment scales which together gives a lot more information than diagnosis-based classification alone. The WHS classification is designed to be used by healthcare workers of any level of experience and the WHS classification committee endeavor to update the online classification document as needed enabling timely sculpting of their new classification. Users are encouraged to give feedback directly to the WHS. Expunged are artificial constructs of treatment response defined disorders (treatment response as a sine qua non for diagnosis), acute/chronic designation and even primary/secondary headache. The reader will also notice the absence of diagnostic-like criteria in the classification, avoiding erroneously using the classification for diagnosis in practice which is a fundamental mistake. It is important to comment on the basic differences between a classification and diagnostic criteria. Classifications typically exhibit high specificity at the expense of sensitivity to identify a well-defined group, as this suits the clinical study of populations especially interventional studies. In this situation there is a desire to minimize false positive cases at the expense of missing some genuine cases (lower sensitivity) with a view to keeping non-cases out of a particular cohort. Classifications are focused then on populations, whereas diagnostic criteria involve the aggregation of symptoms, signs and testing found in clinical practice that allow formulation of a diagnosis for an individual patient. The WHS classification committee see a role for criteria that do not involve stipulating strict requirements, a position that will likely lead to criticism, however there is much that can be accomplished with this multi-axial and more user-friendly classification system nevertheless. A lot has yet to be understood about the physiology of headache disorders and we still rely on symptom-based diagnoses. There is also a lot to learn yet about the impact of headache disorders on the individual, made more important with this new classification. The addition of patient narrative and impairment ratings gives more scope for epidemiologic study and presents a classification friendly to clinical practice. The WHS look forward to commentary on the new classification. While new classifications may draw criticism, this may be the disruptive innovation needed to move headache medicine forward. Editor in Chief Brian E McGeeney

Investigating operational country-level crop monitoring with Sentinel~1 and~2 imagery

ABSTRACT In this paper, we propose an operational solution for the yearly classification of crop parcels at national scale (namely France) for Land Parcel Identification System updating, under the Common Agricultural Policy (CAP) umbrella. Our pipeline is based on the open-source framework and fed with both time series of Sentinel-1 radar and Sentinel-2 optical images, with complementary contributions. Three conceivable scenarios are investigated with two sets of nomenclatures (17 and 43 classes): early, on-line, and late classifications. Experiments performed on 2017 show very satisfactory results (82–97%), locally almost on-par with state-of-the-art deep-based methods. We can conclude our framework offers a strong basis for country-scale operational deployment for 2020+ CAP.

Environmental Attitudes and Willingness to Purchase Online—Classification Approach

During the last several years, a tremendous increase in the popularity of online shopping has been observed. There are several possible reasons behind it, some of them, like competitive pricing, convenience or low cost of information search, considered to be extrinsic, others—like ease of use of this channel, pleasure related to it or willingness to reduce social interactions—intrinsic. The purpose of this research is to evaluate another factor, i.e., consumers’ environmental attitudes, in the perspective of their possible relation with the perception and willingness to use online and conventional shopping channels. In order to achieve this, a self-reporting questionnaire was developed and the data from a representative sample of 1000 Polish Internet users was gathered. The research procedure included cluster analysis, whose objective was to identify groups of customers with similar composition of environmental attitudes and next, a set of Kruskal–Wallis tests, aimed at identifying differences in opinions on channels between these clusters. The research proved that large groups of consumers with consistent sets of environmental attitudes exist and the scope of differences between such clusters is not reduced to a unidimensional, “positive–negative” continuum. Furthermore, there are significant differences between clusters in the declared willingness to use online and conventional shopping channels—groups more environmentally-oriented are more willing to purchase online and trust online shops, although they neither perceive conventional retail in a more negative way nor directly prefer online over conventional channels. The nature of such a phenomenon is open to explanation and interpretation, nevertheless, the research proves that environmental attitudes should be included in future models of consumers’ channel choice.

An online weighted sequential extreme learning machine for class imbalanced data streams

When general online classification algorithms deal with imbalanced data streams, there are always some problems, such as over fitting phenomenon caused by insufficient simple learning and instability of training model. In this paper, we introduce online sequential extreme learning machine (OSELM) as the basic theory model, and combine with the cost-sensitive strategy, then propose a cost-sensitive learning based online sequential extreme learning machine algorithm (C-OSELM). Firstly, in order to solve the problem that minority classes are easily misclassified due to class imbalance, use cost-sensitive strategy, by assigning different penalty parameters to various samples, a weighting matrix is constructed to improve the misclassification cost, thereby effectively alleviating the excessive deviation of decision surface. On this basis, in order to solve the problem that the penalty parameter is too single and the algorithm is not universal, the cost adjustment function is introduced to optimize the weight parameters to select the appropriate weight. Finally, 16 class II imbalanced datasets are used for comparison and verification. The experimental results show that the classification performances of the proposed C-OSELM algorithm are better than other comparative algorithms.

A probabilistic approach to online classification of bicycle crashes

When a bicycle crash takes place, it is paramount for an emergency center to recognize the physical state of the cyclist as early as possible. However, an injured bicyclist may be incapable of making a phone call to the emergency center. In this study, we propose an online approach to classify bicycle crashes based on signals from an onboard inertial measurement unit (IMU), which can be used as a trigger function for an automatic emergency system. For this purpose, we define several bicycle crash features according to the kinematic properties of bicycle accidents. The input signals (variables) influencing the individual crash features are determined by the ANOVA method (analysis of variance). With the determined input signals, probabilistic models for each crash feature are trained on the base of logit models and 20,000 km naturalistic driving data including 20 real crashes. In addition, further crash and corner case data has been collected for the model training. A decision tree describing all probabilistic crash features is used to classify different kinematic events and crash scenarios. A series of driving tests with a crash-dummy and a crash-car are performed to verify the proposed crash classification approach, showing a sensitivity of 96.8%, a specificity of 99.6% and an accuracy of 99.5% of the trained model.

Framework for Intelligent Swimming Analytics with Wearable Sensors for Stroke Classification.

Intelligent approaches in sports using IoT devices to gather data, attempting to optimize athlete’s training and performance, are cutting edge research. Synergies between recent wearable hardware and wireless communication strategies, together with the advances in intelligent algorithms, which are able to perform online pattern recognition and classification with seamless results, are at the front line of high-performance sports coaching. In this work, an intelligent data analytics system for swimmer performance is proposed. The system includes (i) pre-processing of raw signals; (ii) feature representation of wearable sensors and biosensors; (iii) online recognition of the swimming style and turns; and (iv) post-analysis of the performance for coaching decision support, including stroke counting and average speed. The system is supported by wearable inertial (AHRS) and biosensors (heart rate and pulse oximetry) placed on a swimmer’s body. Radio-frequency links are employed to communicate with the heart rate sensor and the station in the vicinity of the swimming pool, where analytics is carried out. Experiments were carried out in a real training setup, including 10 athletes aged 15 to 17 years. This scenario resulted in a set of circa 8000 samples. The experimental results show that the proposed system for intelligent swimming analytics with wearable sensors effectively yields immediate feedback to coaches and swimmers based on real-time data analysis. The best result was achieved with a Random Forest classifier with a macro-averaged of 95.02%. The benefit of the proposed framework was demonstrated by effectively supporting coaches while monitoring the training of several swimmers.

On-line Detection and Classification of PMSM Stator Winding Faults Based on Stator Current Symmetrical Components Analysis and the KNN Algorithm

The significant advantages of permanent magnet synchronous motors, such as very good dynamic properties, high efficiency and power density, have led to their frequent use in many drive systems today. However, like other types of electric motors, they are exposed to various types of faults, including stator winding faults. Stator winding faults are mainly inter-turn short circuits and are among the most common faults in electric motors. In this paper, the possibility of using the spectral analysis of symmetrical current components to extract fault symptoms and the machine-learning-based K-Nearest Neighbors (KNN) algorithm for the detection and classification of the PMSM stator winding fault is presented. The impact of the key parameters of this classifier on the effectiveness of stator winding fault detection and classification is presented and discussed in detail, which has not been researched in the literature so far. The proposed solution was verified experimentally using a 2.5 kW PMSM, the construction of which was specially prepared for carrying out controlled inter-turn short circuits.

Online domain adaptation for continuous cross-subject liver viability evaluation based on irregular thermal data

Accurate evaluation of liver viability during its procurement is a challenging issue and has traditionally been addressed by taking an invasive biopsy of the liver. Recently, people have started to investigate the non-invasive evaluation of liver viability during its procurement using liver surface thermal images. However, existing works include the background noise in the thermal images and do not consider the cross-subject heterogeneity of livers, thus the viability evaluation accuracy can be affected. In this article, we propose to use the irregular thermal data of the pure liver region, and the cross-subject liver evaluation information (i.e., the available viability label information in cross-subject livers), for the real-time evaluation of a new liver’s viability. To achieve this objective, we extract features of irregular thermal data based on tools from Graph Signal Processing (GSP), and propose an online Domain Adaptation (DA) and classification framework using the GSP features of cross-subject livers. A multiconvex block coordinate descent-based algorithm is designed to jointly learn the domain-invariant features during online DA and the classifier. Our proposed framework is applied to the liver procurement data, and classifies the liver viability accurately.

Robust Multisensor Fusion for the Development of EEG Controlled Vehicle

Stroke survivors or patients suffering from paralyses face a lot of challenges when it comes to mobility. Autonomous vehicle technologies can help to increase the accessibility for persons having limited mobility. The design of such vehicle requires a network of sensors along with sensor fusion system to accurately map the surrounding environment necessary for its safe driving. This study proposes a brain-actuated intelligent vehicle with network of sonars and vision-based sensors which can be controlled by either using Steady-State Visual Evoked Potential brain signals or joystick. For electroencephalogram signal detection, four frequencies were flickered and displayed using a GUI on LCD screen and signals were recorded having 1000 Hz sampling frequency. These signals were segmented into 2-second window size with 50% overlap and features were extracted by using canonical correlation analysis. In addition, a low-level navigation control system consisting of smart sensor network was also implemented to maximize safety of the user. Data from various sensors was sent to the intelligent control unit for sensor fusion in order to improve the performance and robustness of the designed vehicle. The results were evaluated for both offline and online classification. For offline control, the accuracy of 96% was achieved with 104.48 bits/min while 95% accuracy was achieved for run-time control. The results show that the proposed system has improved accuracy as well as information transfer rate is concerned as compared to the existing systems.

Nuclear Fusion Pattern Recognition by Ensemble Learning

Nuclear fusion is the process by which two or more atomic nuclei join together to form a single heavier nucleus. This is usually accompanied by the release of large quantities of energy. This energy could be cheaper, cleaner, and safer than other technology currently in use. Experiments in nuclear fusion generate a large number of signals that are stored in huge databases. It is impossible to do a complete analysis of this data manually, and it is essential to automate this process. That is why machine learning models have been used to this end in previous years. In the literature, several popular algorithms can be found to carry out the automatic classification of signals. Among these, ensemble methods provide a good balance between success rate and internal information about models. Specifically, AdaBoost algorithm will allow obtaining an explicit set of rules that explains the class for each input data, adding interpretability to the models. In this paper, an innovative approach to perform an online classification, that is, to identify the discharge before it actually ends, using interpretable models is presented. In order to evaluate and reveal the benefits of rule-based models, an illustrative example has been implemented to perform an online classification of five different signals of the TJ-II stellarator fusion device located in Madrid, Spain.

Self-attentive deep learning method for online traffic classification and its interpretability

Traffic classification is one of the fundamental tasks in computer networking. This task aims to associate network traffic to a specific class according to the requirements (e.g., QoS provisioning). Online classification, which refers to the situations where flows need to be classified in real time, is an essential technique for this topic. In recent academic research, traffic classification methods based on machine learning (ML) or deep learning (DL) have been proposed. However, most of these methods take flow-level data as input, which requires observing the entire or large portion of a flow and violates the restrictions of online classification. Furthermore, the DL-based methods scarcely discuss the interpretability (e.g., which features are learned by DL, where is the discrimination power from). The lack of interpretability makes people question their reliability and may hinder their further applications. In this paper, we propose a self-attentive method (SAM) for traffic classification. We properly design a neural network whose input can be more fine-grained (i.e., packet-level). This neural network outputs classification results (∼2ms per packet) and consequently satisfies the requirements of online classification. Furthermore, a new technique called self-attention mechanism is utilized for interpretability exploration. By assigning attentive weights to different parts of the input, the self-attention mechanism allows us to understand how the DL model learns discriminative features from the input. According to experimental results, SAM outperforms the current state-of-the-art schemes, improving classification accuracy by ∼8% (protocol classification), ∼5% (application classification), and ∼13% (traffic type classification). The code is available at https://github.com/xgr19/SAM-for-Traffic-Classification.

Online Machine Learning System of Power Quality Information Technology Based on Big Data

Power quality monitoring has the characteristics of large amount of collected data and high collection frequency. Long-term monitoring will form power quality big data, while conventional data storage and processing methods are difficult to effectively use big data and explore the value of big data. This paper proposes an online machine learning recognition and classification method for power quality disturbances based on inherent modal function singular value decomposition and least square support vector machines. Aiming at the characteristics of power quality data in distribution networks, this thesis proposes a power quality big data storage scheme based on Mongo DB + Redis, designs a power quality big data processing process, and builds an online machine learning system based on the Apache Spark power quality big data calculation framework.

Power System Event Identification Based on Deep Neural Network With Information Loading

Online power system event identification and classification are crucial to enhancing the reliability of transmission systems. In this paper, we develop a deep neural network (DNN) based approach to identify and classify power system events by leveraging real-world measurements from hundreds of phasor measurement units (PMUs) and labels from thousands of events. Two innovative designs are embedded into the baseline model built on convolutional neural networks (CNNs) to improve the event classification accuracy. First, we propose a graph signal processing based PMU sorting algorithm to improve the learning efficiency of CNNs. Second, we deploy information loading based regularization to strike the right balance between memorization and generalization for the DNN. Numerical results based on real-world dataset from the Eastern Interconnection of the U.S power transmission grid show that the combination of PMU based sorting and the information loading based regularization techniques help the proposed DNN approach achieve highly accurate event identification and classification results.

Semi-Supervised Classification of the State of Operation in Self-Lubricating Journal Bearings Using a Random Forest Classifier

For a tribological experiment involving a steel shaft sliding in a self-lubricating bronze bearing, a semi-supervised machine learning method for the classification of the state of operation is proposed. During the translatory oscillating motion, the system may undergo different states of operation from normal to critical, showing self-recovering behaviour. A Random Forest classifier was trained on individual cycles from the lateral force data from four distinct experimental runs in order to distinguish between four states of operation. The labelling of the individual cycles proved to be crucial for a high prediction accuracy of the trained RF classifier. The proposed semi-supervised approach allows choosing within a range between automatically generated labels and full manual labelling by an expert user. The algorithm was at the current state used for ex post classification of the state of operation. Considering the results from the ex post analysis and providing a sufficiently sized training dataset, online classification of the state of operation of a system will be possible. This will allow taking active countermeasures to stabilise the system or to terminate the experiment before major damage occurs.

Multi-Sensor Fusion for Online Detection and Classification of Table Tennis Strokes

Multi-Sensor Fusion for Online Detection and Classification of Table Tennis Strokes

Towards accurate estimation for visual object tracking with multi-hierarchy feature aggregation

Many methods achieve the visual object tracking task with deep learning technologies. As the deep features of different levels contain various semantic information and functions, this paper presents a multi-hierarchy feature aggregation approach to tackle the specific issues in the tracking task, which consists of two aspects. On one hand, this paper integrates the features captured by the offline and online classifiers at the score level, which constructs complementary roles of these classifiers to enhance the stability of classification. Besides, the proposed offline classifier is continuously optimized with different levels of features to reinforce classification constraints. On the other hand, we design a butterfly attention module to promote the capacity of multi-hierarchy feature aggregation in the regression network, which aims to fuse and strengthen the multi-scale features by attending to their spatial information. It can capture more spatial contexts by utilizing the self-attention mechanism during the fusion procedure, and preserve the hierarchy of the features during the strengthening process. Extensive experiments on four public datasets, i.e., VOT2018, OTB100, NFS and LaSOT datasets, demonstrate the effectiveness of the proposed methods.