Average Kappa Research Articles

ECG classification using 1-D convolutional deep residual neural network.

An electrocardiograph (ECG) is widely used in diagnosis and prediction of cardiovascular diseases (CVDs). The traditional ECG classification methods have complex signal processing phases that leads to expensive designs. This paper provides a deep learning (DL) based system that employs the convolutional neural networks (CNNs) for classification of ECG signals present in PhysioNet MIT-BIH Arrhythmia database. The proposed system implements 1-D convolutional deep residual neural network (ResNet) model that performs feature extraction by directly using the input heartbeats. We have used synthetic minority oversampling technique (SMOTE) that process class-imbalance problem in the training dataset and effectively classifies the five heartbeat types in the test dataset. The classifier's performance is evaluated with ten-fold cross validation (CV) using accuracy, precision, sensitivity, F1-score, and kappa. We have obtained an average accuracy of 98.63%, precision of 92.86%, sensitivity of 92.41%, and specificity of 99.06%. The average F1-score and Kappa obtained were 92.63% and 95.5% respectively. The study shows that proposed ResNet performs well with deep layers compared to other 1-D CNNs.

Extraction and Mapping of Cropland Parcels in Typical Regions of Southern China Using Unmanned Aerial Vehicle Multispectral Images and Deep Learning

The accurate extraction of cropland distribution is an important issue for precision agriculture and food security worldwide. The complex characteristics in southern China pose great challenges to the extraction. In this study, for the objective of accurate extraction and mapping of cropland parcels in multiple crop growth stages in southern China, we explored a method based on unmanned aerial vehicle (UAV) data and deep learning algorithms. Our method considered cropland size, cultivation patterns, spectral characteristics, and the terrain of the study area. From two aspects—model architecture of deep learning and the data form of UAV—four groups of experiments are performed to explore the optimal method for the extraction of cropland parcels in southern China. The optimal result obtained in October 2021 demonstrated an overall accuracy (OA) of 95.9%, a Kappa coefficient of 89.2%, and an Intersection-over-Union (IoU) of 95.7%. The optimal method also showed remarkable results in the maps of cropland distribution in multiple crop growth stages, with an average OA of 96.9%, an average Kappa coefficient of 89.5%, and an average IoU of 96.7% in August, November, and December of the same year. This study provides a valuable reference for the extraction of cropland parcels in multiple crop growth stages in southern China or regions with similar characteristics.

Impervious surface Mapping and its spatial–temporal evolution analysis in the Yellow River Delta over the last three decades using Google Earth Engine

The unique geographical location of the land-sea transition makes the ecological environment of the Yellow River Delta very fragile and vulnerable to human activities. As one of the characteristics of anthropogenic activities, monitoring the spatiotemporal changes of impervious surface area (ISA) is of great significance to the protection of the ecological environment in the Yellow River Delta (YRD). Based on the Landsat historical images and computing resources provided by Google Earth Engine (GEE), an ISA mapping method was developed through combining spectral, texture features and random forest algorithm, and subsequently was applied to generate the spatiotemporal distribution data of ISA of the YRD for 1992, 1998, 2004, 2010, 2016 and 2021. The experimental results demonstrated that the proposed method achieved satisfactory accuracy, with an average overall accuracy of 92.23% and an average Kappa coefficient of 0.9090. Through further time-series analysis of ISA, it found that the area of ISA in the YRD increased from the initial 394.87 km2 to 1081.74 km2 during study periods, and the annual growth rate broke through new highs, ranging from the initial 1.01 km2/year to 67.87 km2/year. According to the research results, urban development activities in the region should be strictly restricted in order to protect the ecological environment of the YRD.

Estimating the Crop Acreage of Menthol Mint Crop from Remote Sensing Satellite Imagery Using ANN

Acreage estimates are crucial for forecasting menthol mint acreage, as crop output figures fluctuate from year to year in response to fluctuations in the market price of menthol mint oil. Thus, there are yearly fluctuations in the maximum price that farmers can obtain. Since low production arises from low rates, and high production results from high prices, these acreage estimate studies may be useful in lowering uncertainty regarding menthol mints’ output. The widespread adoption of remote sensing technologies for assessing crop acreage at both the national and international levels can be attributed to their low cost, ease of use, and flexibility. The extent of an area planted with menthol mint in the Vishakhapatnam district of Andhra Pradesh, India, was estimated using Sentinel-2A satellite data for that year. After conducting a comprehensive ground survey, the area of the menthol mint crop was estimated using an adaptive maximum chance-type set of rules for taluk-level statistics. According to the research, the Bheemunipatnam taluk in the Vishakhapatnam district was the most productive in growing menthol mint. Using customer and manufacturer accuracies of 89.13% and 87.23%, along with the average accuracy (90.67%) and kappa rate (0.9), the total acreage of menthol mint crop in the study region was estimated to be around 58,000,284.70 ha (0.844). A further aim in this study was to estimate the acreage planted with early and late menthol mint. Around 26,123.50 ha and 29,911.40 ha were found to be home to early menthol mint and late menthol mint, respectively. This method shows promise for early- and late-stage crop acreage assessment of menthol mint using a localised degree of precision.

Partial articular fractures of the radial head: How to understand them using computed tomography

BackgroundThe optimal treatment for different types of displaced partial articular radial head fractures is still debatable. Fractures involving the articulating portion of the radial head can be defined also as bi-articular and are often underestimated. Moreover, the complete loss of periosteal contact between fracture fragments is a marker of instability. Available classifications do not emphasize these aspects. The purpose of the present study is to describe two assessment methods to identify fractures involving the articulating portion of the radial head and complete loss of periosteal contact with the help of 2D-3D CT scan. The second purpose is to propose a classification of the displaced partial articular radial head fractures basing on these two assessment methods. HypothesisWe hypothesize that the proposed classification is reliable. Patients and methodsBy observing the position of the bicipital tuberosity with respect to the ulna in reference to the coronal plane in the 3D-CT scan and by observing the location of the fracture fragment in the 2D axial scan, it is possible to understand if a displaced partial articular fracture involves the articulating portion of the radial head. Also, it is possible to understand the presence or absence of a complete loss of periosteal contact between the two fracture fragments by observing the coronal and sagittal 2D-CT scans. We identified 20 displaced partial articular radial head fractures on a series of 149 patients with radial head fractures. Following the above-described assessment methods, these 20 fractures were classified in three subgroups. Also, seven evaluators were asked to use these assessment methods to classify these 20 fractures in the three subgroups, in order to evaluate inter- and intra-observer agreement. ResultsEight fractures involved the non-articulating portion of the radial head with complete loss of periosteal contact, eight involved the non-articulating portion of the radial head without complete loss of periosteal contact, and four involved the articulating portion of the radial head with or without complete loss of periosteal contact. The kappa for intra-observer reliability ranged from 0.46 to 0.84. The average kappa for inter-observer reliability was 0.570 (range: 0.526 to 0.676). The Kendall's coefficient for inter-observer concordance was 0.673. DiscussionPrognostically, displaced partial fractures of the articulating portion of the radial head could differ from the other types, regardless of whether or not there is a complete loss of periosteal contact. Underestimating this fracture pattern can lead to poor results due to risk of forearm rotation blockage. Moreover, underestimating complete loss of periosteal contact in displaced partial fractures of the non-articulating portion of the radial head could lead to poor results. The described evaluation methods have moderate reliability, but can represent, along with other described methods, a good starting point to better understand and treat these insidious fractures. Level of evidenceIII; retrospective study.

Filtering Airborne LiDAR Data in Forested Environments Based on Multi-Directional Narrow Window and Cloth Simulation

Ground filtering is one of the essential steps for processing airborne light detection and ranging data in forestry applications. However, the performance of existing methods is still limited in forested areas due to the complex terrain and dense vegetation. To overcome this limitation, we proposed an improved surface-based filter based on multi-directional narrow window and cloth simulation. The innovations mainly involve two aspects as follows: (1) sufficient and uniformly distributed ground seeds are identified by merging the lowest points and line segments from the point clouds within a multi-directional narrow window; (2) complete and accurate ground points are extracted using a cyclic scheme that includes incorrect ground point elimination using the internal force adjustment of cloth simulation, terrain reconstruction with moving least-squares plane fitting, and ground point extraction based on progressively refined terrain. The proposed method was tested in five forested sites with various terrain characteristics and vegetation distributions. Experimental results showed that the proposed method could accurately separate ground points from non-ground points in different forested environments, with the average kappa coefficient of 88.51% and total error of 4.22%. Moreover, the comparative experiments proved that the proposed method performed better than the classical methods involving the slope-based, mathematical morphology-based and surface-based methods.

Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model

Motor imagery (MI) electroencephalography (EEG) signals are widely used in BCI systems. MI tasks are performed by imagining doing a specific task and classifying MI through EEG signal processing. However, it is a challenging task to classify EEG signals accurately. In this study, we propose a LSTM-based classification framework to enhance classification accuracy of four-class MI signals. To obtain time-varying data of EEG signals, a sliding window technique is used, and an overlapping-band-based FBCSP is applied to extract the subject-specific spatial features. Experimental results on BCI competition IV dataset 2a showed an average accuracy of 97% and kappa value of 0.95 in all subjects. It is demonstrated that the proposed method outperforms the existing algorithms for classifying the four-class MI EEG, and it also illustrates the robustness on the variability of inter-trial and inter-session of MI data. Furthermore, the extended experimental results for channel selection showed the best performance of classification accuracy when using all twenty-two channels by the proposed method, but an average kappa value of 0.93 was achieved with only seven channels.

Monitoring the Spatiotemporal Dynamics of Arctic Winter Snow/Ice with Moonlight Remote Sensing: Systematic Evaluation in Svalbard

Accurate monitoring of the spatiotemporal dynamics of snow and ice is essential for under-standing and predicting the impacts of climate change on Arctic ecosystems and their feedback on global climate. Traditional optical and Synthetic Aperture Radar (SAR) remote sensing still have limitations in the long-time series observation of polar regions. Although several studies have demonstrated the potential of moonlight remote sensing for mapping polar snow/ice covers, systematic evaluation on applying moonlight remote sensing to monitoring spatiotemporal dynamics of polar snow/ice covers, especially during polar night periods is highly demanded. Here we present a systematic assessment in Svalbard, Norway and using data taken from the Visible Infrared Imaging Radiometer Suite (VIIRS) on the Suomi National Polar-orbiting Partnership (SNPP) Day/Night Band (DNB) sensor to monitor the spatiotemporal dynamics of snow/ice covers during dark Arctic winters when no solar illumination available for months. We successfully revealed the spatiotemporal dynamics of snow/ice covers from 2012 to 2022 during polar night/winter periods, using the VIIRS/DNB time series data and the object-oriented Random Forests (RF) algorithm, achieving the average accuracy and kappa coefficient of 96.27% and 0.93, respectively. Our findings indicate that the polar snow/ice covers show seasonal and inter-seasonal dynamics, thus requiring more frequent observations. Our results confirm and realize the potential of moonlight remote sensing for continuous monitoring of snow/ice in the Arctic region and together with other types of remote sensing data, moonlight remote sensing will be a very useful tool for polar studies and climate change.

Bilateral Attention U-Net with Dissimilarity Attention Gate for Change Detection on Remote Sensing Imageries

This study proposes a bilateral attention U-Net with a dissimilarity attention gate (DAG) for change detection on remote sensing imageries. The proposed network is designed with a bilateral dissimilarity encoding for the DAG calculation to handle reversible input images, resulting in high detection rates regardless of the order of the two input images for change detection. The DAG exploits all the combinations of joint features to avoid spectral information loss fed into an attention gate on the decoder side. The effectiveness of the proposed method was evaluated on the KOMPSAT-3 satellite images dataset and the aerial change detection dataset (CDD). Its performance was better than that of conventional methods (specifically, U-Net, ATTUNet, and Modified-UNet++) as it achieved average F1-score and kappa coefficient (KC) values of 0.68 and 66.93, respectively, for the KOMPSAT-3 dataset. For CDD, it achieved F1-score and KC values of 0.70 and 68.74, respectively, which are also better values than those achieved by conventional methods. In addition, we found that the proposed bilateral attention U-Net can provide the same changed map regardless of whether the image order is reversed.

At-home sleep monitoring using generic ear-EEG.

A device comprising two generic earpieces with embedded dry electrodes for ear-centered electroencephalography (ear-EEG) was developed. The objective was to provide ear-EEG based sleep monitoring to a wide range of the population without tailoring the device to the individual. To validate the device ten healthy subjects were recruited for a 12-night sleep study. The study was divided into two parts; part A comprised two nights with both ear-EEG and polysomnography (PSG), and part B comprised 10 nights using only ear-EEG. In addition to the electrophysiological measurements, subjects filled out a questionnaire after each night of sleep. The subjects reported that the ear-EEG system was easy to use, and that the comfort was better in part B. The performance of the system was validated by comparing automatic sleep scoring based on ear-EEG with PSG-based sleep scoring performed by a professional trained sleep scorer. Cohen's kappa was used to assess the agreement between the manual and automatic sleep scorings, and the study showed an average kappa value of 0.71. The majority of the 20 recordings from part A yielded a kappa value above 0.7. The study was compared to a companioned study conducted with individualized earpieces. To compare the sleep across the two studies and two parts, 7 different sleeps metrics were calculated based on the automatic sleep scorings. The ear-EEG nights were validated through linear mixed model analysis in which the effects of equipment (individualized vs. generic earpieces), part (PSG and ear-EEG vs. only ear-EEG) and subject were investigated. We found that the subject effect was significant for all computed sleep metrics. Furthermore, the equipment did not show any statistical significant effect on any of the sleep metrics. These results corroborate that generic ear-EEG is a promising alternative to the gold standard PSG for sleep stage monitoring. This will allow sleep stage monitoring to be performed in a less obtrusive way and over longer periods of time, thereby enabling diagnosis and treatment of diseases with associated sleep disorders.

Three-Dimensional Orientation of the Native Anterior Cruciate Ligament in Magnetic Resonance Imaging.

The aim of this study was to describe the three-dimensional orientation of the native anterior cruciate ligament (ACL) in magnetic resonance imaging (MRI) by calculating the angles of inclination in relation to the axial plane which is given for the knee joint line in a group of healthy individuals. These could help to establish guidelines that may be used for the surgical positioning of bone tunnels during ACL reconstruction. A total of 290 MRI scans of patients with integrity of the ACL were evaluated; three observers identified the coordinates of the femoral and tibial insertion sites, then it is defined the vector and evaluated its angles with respect to axial axis and calculated the angles with trigonometric equations. The data were analyzed according to the age, sex, side, BMI, and height of the patients, and the interobserver reliability was calculated. The patient demographics were as follows: age average: 45 years old, BMI average: 27.1, 54% right knees, and 60% female. The average angle for all the measurements was 76.95 degrees (SD ± 6.8 degrees) in the sagittal plane, 81.65 degrees (SD ± 7.79 degrees) in the coronal plane and 33.17 degrees (SD ± 4.98 degrees) in the axial plane. No statistically significant differences were found between the categorical variables mentioned; moderate to substantial interobserver reliability strength was found with an average kappa of 0.791 for all measurements. The three-dimensional orientation of the native ACL in a group of healthy individuals was established. The findings can be helpful for performing anatomical reconstructions of the ACL in injured patients using as reference the average calculated angles, or measure of the contralateral non-injured knee for surgical planning; these results serve as a basis for the design of a technique that optimizes the three-dimensional position of the ACL when it undergoes reconstruction in the trend toward greater precision for better functional results. Biomechanical and clinical-surgical studies are required to further evaluate our results.

An overview of methods of left and right foot motor imagery based on Tikhonov regularisation common spatial pattern.

The motor imagery brain-computer interface (MI-BCI) provides an interactive control channel for spinal cord injury patients. However, the limitations of feature extraction algorithms may lead to low accuracy and instability in decoding electroencephalogram (EEG) signals. In this study, we examined the classification performance of an MI-BCI system by focusing on the distinction of the left and right foot kinaesthetic motor imagery tasks in five subjects. Feature extraction was performed using the common space pattern (CSP) and the Tikhonov regularisation CSP (TRCSP) spatial filters. TRCSP overcomes the CSP problems of noise sensitivity and overfitting. Moreover, support vector machine (SVM) and linear discriminant analysis (LDA) were used for classification and recognition. We constructed four combined classification methods (TRCSP-SVM, TRCSP-LDA, CSP-SVM, and CSP-LDA) and evaluated them by comparing their accuracies, kappa coefficients, and receiver operating characteristic (ROC) curves. The results showed that the TRCSP-SVM method performed significantly better than others (average accuracy 97%, average kappa coefficient 0.91, and average area under ROC curve (AUC) 0.98). Using TRCSP instead of standard CSP improved accuracy by up to 10%. This study provides insights into the classification of EEG signals. The results of this study can aid lower limb MI-BCI systems in rehabilitation training.

A QUICK SEASONAL DETECTION AND ASSESSMENT OF INTERNATIONAL SHADEGAN WETLAND WATER BODY EXTENT USING GOOGLE EARTH ENGINE CLOUD PLATFORM

Abstract. Understanding the variation of Water Extent (WE) can provide insights into Wetland conservation and management. In this study, and-inter inner-annual variations of WE were analyzed during 2019–2021 to understand the spatiotemporal changes of the International Shadegan Wetland, Iran. We utilized a thresholding process on Modified Normalized Difference Water Index (MNDWI) to extract the WE quickly and accurately using the Google Earth Engine (GEE) platform. The water surface analysis showed that: (1) WE had a downward trend from 2019 to 2021, with the overall average WE being 1405.23 km2; (2) the water area reached its peak due to the water supply to International Shadegan Wetland through the Jarahi River and upstream reservoirs at the end of 2019 and the beginning of 2020, and the largest water body appeared in Winter 2019, reaching 1953.31 km2. In contrast, the smallest water body appeared in Autumn 2021, reaching 563.56 km2; (3) The WE of the wetland showed predictable seasonal characteristics. The water area in Winter was the largest, with an average value of 1829.1 km2, while it was the smallest in Summer, with an average value of 1100.3 km2; (4) The average water area in 2019 was 1490.5 km2 whereas in 2020 and 2021 decreased by 9% and 25%, respectively, and reached 968.6 km2 and 811.9 km2. Finally, to evaluate the proposed model, its results were compared with the Random Forest (RF) classification results. Accordingly, Histogram Analysis (HA) classification achieved 94.6% of the average overall accuracy and the average Kappa coefficient of 0.93, but the RF method obtained 95.38% of the average overall accuracy and an average Kappa coefficient of 0.94.

Unsupervised SAR Image Change Detection Based on Histogram Fitting Error Minimization and Convolutional Neural Network

Synthetic aperture radar (SAR) image change detection is one of the most important applications in remote sensing. Before performing change detection, the original SAR image is often cropped to extract the region of interest (ROI). However, the size of the ROI often affects the change detection results. Therefore, it is necessary to detect changes using local information. This paper proposes a novel unsupervised change detection framework based on deep learning. The specific method steps are described as follows: First, we use histogram fitting error minimization (HFEM) to perform thresholding for a difference image (DI). Then, the DI is fed into a convolutional neural network (CNN). Therefore, the proposed method is called HFEM-CNN. We test three different CNN architectures called Unet, PSPNet and the designed fully convolutional neural network (FCNN) for the framework. The overall loss function is a weighted average of pixel loss and neighborhood loss. The weight between pixel loss and neighborhood loss is determined by the manually set parameter λ. Compared to other recently proposed methods, HFEM-CNN does not need a fragment removal procedure as post-processing. This paper conducts experiments for water and building change detection on three datasets. The experiments are divided into two parts: whole data experiments and random cropped data experiments. The complete experiments prove that the performance of the method in this paper is close to other methods on complete datasets. The random cropped data experiment is to perform local change detection using patches cropped from the whole datasets. The proposed method is slightly better than traditional methods in the whole data experiments. In experiments with randomly cropped data, the average kappa coefficient of our method on 63 patches is over 3.16% compared to other methods. Experiments also show that the proposed method is suitable for local change detection and robust to randomness and choice of hyperparameters.

Reliability and repeatability of a modified thoracolumbar spine injury classification scoring system.

On the basis of the Thoracolumbar Injury Classification and Severity Score (TLICS), an modified TLICS classification system was presented, its reliability and repeatability were assessed, and the factors influencing classification consistency were examined. Five spinal surgeons were chosen at random. The clinical data of 120 patients with thoracolumbar fractures admitted to the Department of Spine Surgery, Ningbo Sixth Hospital from December 2019 to June 2021 were categorized using the modified TLICS system. After 6 weeks, disrupt the order of data again. Using unweighted Cohen's kappa coefficients, the consistency of the modified TLICS system was assessed in five aspects: neurofunctional status, disc injury status, fracture morphology, posterior ligament complex (PLC) integrity, and treatment plan. In terms of reliability, the average kappa values for the subclasses of the modified TLICS system (neurofunctional status and disc injury status) were 0.920 and 0.815, respectively, reaching the category of complete confidence. Fracture morphology and treatment plan had average kappa values of 0.670 and 0.660, respectively, which were basically reliable. The average kappa value of PLC integrity was 0.453, which belonged to the category of moderate confidence. The average kappa coefficients of each subcategory (neurological status, disc injury status) had excellent consistency, and the kappa values were 0.936 and 0.879, respectively, which belonged to the completely credible category. The kappa values of fracture morphology and treatment plan repeatability were 0.772 and 0.749, respectively, reaching the basic credibility category. PLC integrity repeatability kappa value is low, 0.561, to moderate credibility category. The modified TLICS system is intuitive and straightforward to understand. The examination of thoracolumbar fracture injuries is more exhaustive and precise, with excellent reliability and repeatability. The examination of neurological status and disc injury status is quite reliable and consistent. The consistency of fracture morphology is slightly poor, which is basically credible; the PLC integrity consistency is poor, reaching a reliability level of moderate, which may be associated with the subjectivity of clinical evaluation of PLC.

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

Research on two-class and four-class action recognition based on EEG signals.

BMI has attracted widespread attention in the past decade, which has greatly improved the living conditions of patients with motor disorders. The application of EEG signals in lower limb rehabilitation robots and human exoskeleton has also been gradually applied by researchers. Therefore, the recognition of EEG signals is of great significance. In this paper, a CNN-LSTM neural network model is designed to study the two-class and four-class motion recognition of EEG signals. In this paper, a brain-computer interface experimental scheme is designed. Combining the characteristics of EEG signals, the time-frequency characteristics of EEG signals and event-related potential phenomena are analyzed, and the ERD/ERS characteristics are obtained. Pre-process EEG signals, and propose a CNN-LSTM neural network model to classify the collected binary and four-class EEG signals. The experimental results show that the CNN-LSTM neural network model has a good effect, and its average accuracy and kappa coefficient are higher than the other two classification algorithms, which also shows that the classification algorithm selected in this paper has a good classification effect.

A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection

Cloud detection is a fundamental step for optical satellite image applications. Although existing deep learning method can provide more accurate cloud detection result. However, performance of these methods rely on a large number of label samples, whose collection is time-consuming and high cost. In addition, cloud detection is challenging in high brightness scenes due to due to cloud and high brightness object have a similar spectral feature. In this study, we propose a cloud index driven spectral-spatial-context attention network (SSCA-net) for cloud detection, which relies on no effort to manually collect label samples and can improve the accuracy cloud detection in high brightness scenes. The label samples are automatically generated from cloud index by using dual-threshold, which is then expanded to improve the completeness of cloud mask labels. We designed SSCA-net with the spectral-spatial-context aware module and spectral-spatial-context information aggregation module, aimed to improve the accuracy cloud detection in high brightness scenes. The results show that the proposed SSCA-net achieved good performance with average overall accuracy of 97.69% and average Kappa coefficient of 92.71% on Sentinel-2 and Landsat-8 dataset. This paper provides a fresh insight into how advanced deep attention network and cloud index can be integrated to obtain high accuracy of cloud detection on high brightness scenes.

Recognition of Motor Imagery EEG Signals Based on Capsule Network

In order to fully extract the temporal and spatial features contained in motor imagery electroencephalography (EEG) signals for effective identification of motor imagery, a three-dimensional capsule network (3D-CapsNet) EEG signal recognition model is proposed, which can integrate the MI-EEG temporal dimension, channel spatial dimension and the intrinsic relationship between features to maximize the feature representation capability. Firstly, a multi-layer 3D convolution module is used to extract features in the time and inter-channel space dimensions as the low-level features. Secondly, advanced spatial features are also obtained through capsule network integration. Finally, dynamic routing connections and squash functions are applied for classification. The experimental analysis is conducted on the BCI competition IV dataset 2a. The proposed model performs well on all the subjects’ datasets, such that the average accuracy and average Kappa value of 9 subjects are 84.028% and 0.789, respectively. The experimental results confirm effectiveness of the proposed method. Additionally, accuracy of the four-class classification is improved, and the impact of individual variability is overcome to a certain extent.

Evaluation of a rapid diagnostic test for measles IgM detection; accuracy and the reliability of visual reading using sera from the measles surveillance programme in Brazil, 2015.

Laboratory-based case confirmation is an integral part of measles surveillance programmes; however, logistical constraints can delay response. Use of RDTs during initial patient contact could enhance surveillance by real-time case confirmation and accelerating public health response. Here, we evaluate performance of a novel measles IgM RDT and assess accuracy of visual interpretation using a representative collection of 125 sera from the Brazilian measles surveillance programme. RDT results were interpreted visually by a panel of six independent observers, the consensus of three observers and by relative reflectance measurements using an ESEQuant Reader. Compared to the Siemens anti-measles IgM EIA, sensitivity and specificity of the RDT were 94.9% (74/78, 87.4-98.6%) and 95.7% (45/47, 85.5-99.5%) for consensus visual results, and 93.6% (73/78, 85.7-97.9%) and 95.7% (45/47, 85.5-99.5%), for ESEQuant measurement, respectively. Observer agreement, determined by comparison between individuals and visual consensus results, and between individuals and ESEQuant measurements, achieved average kappa scores of 0.97 and 0.93 respectively. The RDT has the sensitivity and specificity required of a field-based test for measles diagnosis, and high kappa scores indicate this can be accomplished accurately by visual interpretation alone. Detailed studies are needed to establish its role within the global measles control programme.