Correct Label Research Articles

Cost analysis of screening methods to find non-compliant models using the example of tumble dryers

The European energy label was established to reduce energy consumption in Europe. All classes and values on the energy label are stated by the supplier. The task of market surveillance is to ensure correct labels and to validate their values through compliance tests. However, this can only be done for a small fraction of all models on the market, since physical tests are expensive. Screening methods can be used to narrow down the number of critical products before compliance tests are done to decrease the costs of finding non-compliant models. This study shows a mathematical approach to analyze the cost benefits of screening methods to find non-compliant models. Furthermore, the analysis presented has been applied to 18 screening methods for tumble dryers. The performance test for tumble dryers consists of seven test runs. All screening methods evaluated are composed of a reduced number of test runs. The most efficient screening method reduces the surveillance costs by 40%.

From DNA barcoding to personalized nutrition: the evolution of food traceability

A genuine nutritional product is pivotal for getting proper health benefits and preventing pathologies. However, with the increase in global trading of raw and processed food products, reliable authentication is essential for correct labelling to ensure consumer safety. The use of DNA-based tools has become a prospective solution in the near future to solve this problem. Currently, technologies exploiting DNA polymorphism between species are able to characterize the food composition of pure (DNA barcoding) or multi-species (DNA metabarcoding) food items, and the application of this technology has started entering into food regulations. Here, we provide a brief overview of the history, success, and forthcoming applications of such approaches, while also considering the influence of food on human microbiota and the emerging trends toward the adoption of a ‘personalized nutrition’.

Simultaneous 3D Motion Detection, Long-Term Tracking and Model Reconstruction for Multi-Objects

Motion detection and object tracking play important roles in unsupervised human–machine interaction systems. Nevertheless, the human–machine interaction would become invalid when the system fails to detect the scene objects correctly due to occlusion and limited field of view. Thus, robust long-term tracking of scene objects is vital. In this paper, we present a 3D motion detection and long-term tracking system with simultaneous 3D reconstruction of dynamic objects. In order to achieve the high precision motion detection, an optimization framework with a novel motion pose estimation energy function is provided in the proposed method by which the 3D motion pose of each object can be estimated independently. We also develop an accurate object-tracking method which combines 2D visual information and depth. We incorporate a novel boundary-optimization segmentation based on 2D visual information and depth to improve the robustness of tracking significantly. Besides, we also introduce a new fusion and updating strategy in the 3D reconstruction process. This strategy brings higher robustness to 3D motion detection. Experiments results show that, for synthetic sequences, the root-mean-square error (RMSE) of our system is much smaller than Co-Fusion (CF); our system performs extremely well in 3D motion detection accuracy. In the case of occlusion or out-of-view on real scene data, CF will suffer the loss of tracking or object-label changing, by contrast, our system can always keep the robust tracking and maintain the correct labels for each dynamic object. Therefore, our system is robust to occlusion and out-of-view application scenarios.

Cerebellar Gray Matter and Olfactory Performance.

The role of the cerebellum in the chemical senses is still poorly understood. This voxel-based morphometry (VBM) study investigated associations between gray matter volume (GMV) in subregions of the cerebellum and olfactory performance. VBM data from 48 men were analyzed. The participants were tested with a standardized olfactory test that measured olfactory threshold, discrimination, and identification ability. The investigated sample covered a wide range of olfactory performance, including individuals with a reduced sense of smell (anosmia and hyposmia) and normosmia. The computed regression analyses revealed a positive association between olfactory identification performance and GMV in lobule VI. This cerebellar subregion is involved in higher-order cognitive functions (language and memory), which are necessary prerequisites for correct odor labeling. Odor detection and discrimination were unrelated to cerebellar GMV.

Improved Segmentation with Dynamic Threshold Adjustment for Phonocardiography Recordings.

In this study with the intent to segment phonocardiography (PCG) recordings, an algorithm that processes a feature vector obtained by jointly using wavelet transform and mel scaled energy spectrum of the PCG signal is proposed. The feature vector is processed by a peak detection algorithm which results in a set of peaks that meet some certain criteria and will be exploited in the succeeding stages of the algorithm. Heart sounds are labeled by convolving circularly a template and a fragment of the feature vector which is picked up with the guidance of the peaks. At the final stage, the algorithm tries to detect and correct erroneous labels. The performance of the algorithm was tested on both normal heart sounds and abnormal heart sounds; 80 records in total. As a result of these tests, for normal heart sounds S1 and S2 sounds were detected with 99,51% recall and 97,28% precision, while with 97,59% recall and 92,53% precision for abnormal heart sounds.

1D and 2D-HSQC NMR: Two Methods to Distinguish and Characterize Heparin From Different Animal and Tissue Sources.

The US Food and Drug Administration has encouraged the reintroduction of bovine heparin drug product to the US market to mitigate the risks of heparin shortages and potential adulteration or contamination of the primary source which is porcine heparin. Here, a 1D-NMR method was applied to compare heparin sodium of bovine intestinal origin with that of bovine lung, porcine, or ovine intestinal origin. The results showed that a simple 1D test using NMR signal intensity ratios among diagnostic signals of the proton spectra uniquely identified the origin of heparin and concomitantly could be used to assure the correct sample labeling. However, a limitation of the use of only mono-dimensional spectra is that these spectra may not provide sufficiently detailed information on the composition of heparin batches to adequately determine the quality of this complex product. As an alternative, a higher resolution quantitative 2D-HSQC method was used to calculate the percentage of mono- and disaccharides, distinguish the origin of heparin and, simultaneously, assess the heparin composition. The 2D-HSQC method is proposed to provide sufficient information to evaluate the quality of industrial production process used to make the drug substance. Together, the 1D and 2D data produced by these measurements can be used to assure the identity and purity of this widely used drug.

Disaster Area Detection from Synthetic Aperture Radar Images Using Convolutional Autoencoder and One-class SVM

In recent years, research on detecting disaster areas from synthetic aperture radar (SAR) images has been conducted. When machine learning is used for disaster area detection, a large number of training data are required; however, we cannot obtain so much training data with correct class labels. Therefore, in this research, we propose an anomaly detection system that finds abnormal areas that deviate from normal ones. The proposed method uses a convolutional autoencoder (CAE) for feature extraction and one-class support vector machine (OCSVM) for anomaly detection.

Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability

Abstract Common variable star classifiers are built with the singular goal of producing the correct class labels, leaving much of the multi-task capability of deep neural networks unexplored. We present a periodic light curve classifier that combines a recurrent neural network autoencoder for unsupervised feature extraction and a dual-purpose estimation network for supervised classification and novelty detection. The estimation network optimizes a Gaussian mixture model in the reduced-dimension feature space, where each Gaussian component corresponds to a variable class. An estimation network with a basic structure of a single hidden layer attains a cross-validation classification accuracy of ∼99%, which is on par with the conventional workhorses, random forest classifiers. With the addition of photometric features, the network is capable of detecting previously unseen types of variability with precision 0.90, recall 0.96, and an F 1 score of 0.93. The simultaneous training of the autoencoder and estimation network is found to be mutually beneficial, resulting in faster autoencoder convergence, as well as superior classification and novelty detection performance. The estimation network also delivers adequate results even when optimized with pre-trained autoencoder features, suggesting that it can readily extend existing classifiers to provide added novelty detection capabilities.

Correction to: Characterizing the cultural evolutionary process from eco-cultural niche models: niche construction during the Neolithic of the Struma River Valley (c. 6200–4900 BC)

The lists of archeological settlements represented by Figures 3 & 4 in the original online first publication were unfortunately mislabelled by the author. Amended figures with the correct labelling have since been submitted.

A computationally bio-inspired framework of brain activities based on cognitive processes for estimating the depth of anesthesia.

This paper develops a computationally bio-inspired framework of brain activities based on concepts, such as sensory register (SR), encoding, emotion, short-term memory (STM), selective attention, working memory (WM), forgetting, long-term memory (LTM), sustained memory (SM), and response selection for estimating the depth of anesthesia (DOA) using electroencephalogram (EEG) signals. Different brain regions, such as the thalamus, cortex, neocortex, amygdala, striatum, basal ganglia, cerebellum, and hippocampus, are considered for developing a cognitive architecture and a computationally bio-inspired framework. A clinical study was managed on twenty-two patients corresponding to three anesthetic states, including awake state, moderate anesthesia, and general anesthesia. The proposed approach utilizes a multiple of dynamically reconfigurable neural networks with radial basis function (RBF) and its associated data processing mechanisms. The emotion effect in the model, dynamic RBFs in WM and LTMs, and adjusting the adaptive weights in the last layer are the main innovations of the proposed approach. In the proposed approach, various incoming information is entered into the model. The correct labeling process of EEG signals is performed by qualitative and quantitative analyses of peripheral parameters. Then, an SR is used to accumulate the pre-processed EEG segment for a period of 2.3s. Feature extraction is performed in the encoding stage as a primary perception. The output of this stage can be transferred to STM and WM with a bottom-up involuntary attentional capture. LTM and SM are a fairly permanent reservoir for information which is passed from WM using a top-down voluntary attention mechanism. Finally, weighting factors in SM and LTMs outputs are determined and then response selection is used by winner-take-all (WTA) strategy. The results indicate that the proposed approach can classify in different anesthetic states with an average accuracy of 89.2%. Results also indicate that the combined use of the above elements can effectively decipher the cognitive process task. A final comparison between the obtained results and the previous method on the same database indicate the effectiveness of the proposed approach for estimating DOA.

Deep Learning Method for Automated Classification of Anteroposterior and Posteroanterior Chest Radiographs.

Ensuring correct radiograph view labeling is important for machine learning algorithm development and quality control of studies obtained from multiple facilities. The purpose of this study was to develop and test the performance of a deep convolutional neural network (DCNN) for the automated classification of frontal chest radiographs (CXRs) into anteroposterior (AP) or posteroanterior (PA) views. We obtained 112,120 CXRs from the NIH ChestX-ray14 database, a publicly available CXR database performed in adult (106,179 (95%)) and pediatric (5941 (5%)) patients consisting of 44,810 (40%) AP and 67,310 (60%) PA views. CXRs were used to train, validate, and test the ResNet-18 DCNN for classification of radiographs into anteroposterior and posteroanterior views. A second DCNN was developed in the same manner using only the pediatric CXRs (2885 (49%) AP and 3056 (51%) PA). Receiver operating characteristic (ROC) curves with area under the curve (AUC) and standard diagnostic measures were used to evaluate the DCNN's performance on the test dataset. The DCNNs trained on the entire CXR dataset and pediatric CXR dataset had AUCs of 1.0 and 0.997, respectively, and accuracy of 99.6% and 98%, respectively, for distinguishing between AP and PA CXR. Sensitivity and specificity were 99.6% and 99.5%, respectively, for the DCNN trained on the entire dataset and 98% for both sensitivity and specificity for the DCNN trained on the pediatric dataset. The observed difference in performance between the two algorithms was not statistically significant (p = 0.17). Our DCNNs have high accuracy for classifying AP/PA orientation of frontal CXRs, with only slight reduction in performance when the training dataset was reduced by 95%. Rapid classification of CXRs by the DCNN can facilitate annotation of large image datasets for machine learning and quality assurance purposes.

An easy and green tool for olive oils labelling according to the contents of hydroxytyrosol and tyrosol derivatives: Extraction with a natural deep eutectic solvent and direct spectrophotometric analysis

Natural deep eutectic solvents (NADES) are a green, promising class of solvents. Phenolic compounds are among the targets of NADES’ use in foods. A health claim is admitted by European Regulations for olive oils (OOs) containing at least 250 mg kg−1 of selected polyphenols (hydroxytyrosol and its derivatives, included tyrosol, HTD), but their determination involves analytical issues that are being currently debated. A NADES based on glucose and lactic acid was here used to develop a green and rapid tool for correct labelling of OOs. 163 OOs were submitted to liquid/liquid extraction with the NADES. Regression and classification approaches were adopted to relate features of the UV spectra of extracts to HTD content. The models allowed to assess HTD content for screening purposes (R2prediction = 0.84, RMSEP = 35.5 mg kg−1). For labelling purposes, oils could be labelled according to health claim limits with an error of 0.6%.

Robust labeling of human motion markers in the presence of occlusions

Human motion capture by optical sensors produces snapshots of the motion of a cloud of points that need to be labeled in order to carry out ensuing motion analysis for medical or other purposes. We generate the labeling of instantaneous captures of the cloud of points, discarding temporal correlations, in the presence of occlusions. Our approach proposes an ensemble of weak classifiers defined over geometrical features extracted from small subsets of the cloud of points. We apply an Adaboost strategy to select a minimal ensemble of weak classifiers achieving a target correct labeling detection accuracy. Furthermore, we use these features to generate the labeling of the points in the cloud even in the presence of occlusions.To deal with the occlusions of markers we search for ensembles of partial labeling solvers which can provide partial consistent labelings which cover the unoccluded markers. We test two greedy search approaches and a genetic algorithm in the search for the optimal ensemble of partial solvers We demonstrate the approach on a real dataset obtained from the measurement of gait motion of persons, with available ground truth labeling. Results are encouraging, achieving high accuracy label generation at a reduced computational cost.

Self-Supervised Voltage Sag Source Identification Method Based on CNN

A self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and AutoEncoder. The convolution layer and pool layer in CNN are used to extract the voltage sag characteristics, and the self-supervised network training process is realized based on the principle of AE. In the constructed mode, features which reflect the data characteristics are used rather than artificial features, thus improving the accuracy of practical application. It is unnecessary to input a lot of correct labels before the self-supervised training process. The model can meet the requirements of sag source identification on timeliness, practicability, diversity, and versatility in the context of modern big data. In this study, three-phase asymmetric sag sources in sag sources are classified into more detailed categories according to different fault phases. Therefore, the proposed method can not only identify the voltage sag source, but also accurately determine the specific fault phase. Finally, the optimal parameters of the model are recognized through a case study, and a self-supervised CNN model is established based on the data type of voltage sag. This model extracts features and identifies sag sources through the measured sag data. The superiority of the proposed method is verified by a comparison.

Three‐dimensional‐based landmark tracker employing a superpixels method for neuroscience, biomechanics, and biology studies

AbstractExamining locomotion has improved our basic understanding of motor control and aided in treating motor impairment. Mice and rats are premier models of human disease and increasingly the model systems of choice for basic neuroscience. High frame rates (250 Hz) are needed to quantify the kinematics of these running rodents. Manual tracking, especially for multiple markers, becomes time‐consuming and impossible for large sample sizes. Therefore, the need for automatic segmentation of these markers has grown in recent years. Here, we address this need by presenting a method to segment the markers using the simple linear iterative clustering superpixel method. The two‐dimensional coordinates on the image plane are projected to a three‐dimensional (3D) domain using direct linear transform and a 3D Kalman filter has been used to predict the position of markers based on the speed and position of markers from the previous frames. A probabilistic function is used to find the best match from among superpixels. The method is evaluated for different difficulties for tracking of the markers, and it achieves 95% correct labeling of markers. Finally, the method was used to analyze data from an ongoing study seeking to improve recovery from spinal cord injury in rats

LCC: Towards efficient label completion and correction for supervised medical image learning in smart diagnosis

Smart technology brings convenience to our lives, and smart medical diagnosis plays a particularly important role in smart cities and the smart world. In smart diagnosis, high-quality image labels are essential for supervised medical image learning. The correctness of labels has a substantial influence on smart disease diagnosis. However, the labelling of disease images by professional doctors is a time-consuming and labour-intensive project; therefore, obtaining correct and high-quality labels is a difficult task. This paper proposes a deep convolutional neural network (CNN)-based label completion and correction method (LCC) for supervised medical image learning in smart diagnosis. We use a small number of labelled images in a dataset to train a model, and design a strategy to complement most of the unlabelled data and correct noise label data, and then use the results of completion and correction to continually modify the model to achieve better results. We take the diagnosis of Seborrheic Keratosis (SK) and Flat Wart (FW) as examples; the experimental results show that this strategy can use limited labelled data to complete the labels for most of the unlabelled data and correct some noise labels in the dataset, which improves the accuracy rate of the model to identify diseases.

Deep associative neural network for associative memory based on unsupervised representation learning

This paper presents a deep associative neural network (DANN) based on unsupervised representation learning for associative memory. In brain, the knowledge is learnt by associating different types of sensory data, such as image and voice. The associative memory models which imitate such a learning process have been studied for decades but with simpler architectures they fail to deal with large scale complex data as compared with deep neural networks. Therefore, we define a deep architecture consisting of a perception layer and hierarchical propagation layers. To learn the network parameters, we define a probabilistic model for the whole network inspired from unsupervised representation learning models. The model is optimized by a modified contrastive divergence algorithm with a novel iterated sampling process. After training, given a new data or corrupted data, the correct label or corrupted part is associated by the network. The DANN is able to achieve many machine learning problems, including not only classification, but also depicting the data given a label and recovering corrupted images. Experiments on MNIST digits and CIFAR-10 datasets demonstrate the learning capability of the proposed DANN.

The effects of concurrent cognitive task load on recognising faces displaying emotion

Two independent experiments (N = 30 and N = 24) investigated the effects of concurrent task loads on the recognition of faces displaying emotions. The study aimed to explore a possible resolution for an apparently discrepant finding in the literature regarding the impact of such loads on recognition of facial emotions. Faces displaying different emotions were presented, with or without a concurrent load, until the facial stimuli were correctly labelled to criterion in terms of the displayed emotion. Participants were then presented with elements from the faces (i.e. eyebrows, eyes, and mouth). When participants had to complete the concurrent task as well as the facial recognition task, they did not respond equally to the separate facial elements, and over-selected to the mouth when recognising facial expressions of emotion. The findings relating to the impact of the concurrent load tasks on correct labelling of the facial elements with respect to the emotional faces are discussed in terms of the impact of cognitive load on the production of over-selectivity and the recognition of faces displaying emotions in complex situations, and the implications for those with a developmental disability.

Reconstruction Regularized Deep Metric Learning for Multi-Label Image Classification.

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively. To capture the relationships between image features and labels, we aim to learn a two-way deep distance metric over the embedding space from two different views, i.e., the distance between one image and its labels is not only smaller than those distances between the image and its labels' nearest neighbors but also smaller than the distances between the labels and other images corresponding to the labels' nearest neighbors. Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. Our model can be trained in an end-to-end manner. Experimental results on publicly available image data sets corroborate the efficacy of our method compared with the state of the arts.

Cross-task perceptual learning of object recognition in simulated retinal implant perception.

The perception gained by retina implants (RI) is limited, which asks for a learning regime to improve patients' visual perception. Here we simulated RI vision and investigated if object recognition in RI patients can be improved and maintained through training. Importantly, we asked if the trained object recognition can be generalized to a new task context, and to new viewpoints of the trained objects. For this purpose, we adopted two training tasks, a labelling task where participants had to choose the correct label out of other distracting labels for the presented object, and a reverse labelling task where participants had to choose the correct object out of other distracting objects to match the presented label. Our results showed that, despite of the task order, recognition performance was improved in both tasks and lasted at least for a week. The improved object recognition, however, can be transferred only from the labelling task to the reverse labelling task but not vice versa. Additionally, the trained object recognition can be transferred to new viewpoints of the trained objects only in the labelling task but not in the reverse labelling task. Training with the labelling task is therefore recommended for RI patients to achieve persistent and flexible visual perception.