Labeled Data Set Research Articles

A hybrid approach for noise reduction-based optimal classifier using genetic algorithm: A case study in plant disease prediction

Plant diseases can cause significant losses to agricultural productivity; therefore, their early prediction is much needed. So far, many machine learning-based plant disease prediction models have been recommended, but these models face a problem of noisy class label dataset that degrades the performance. Noisy class label dataset results from the improper assignment of positive class labels into negative class data samples or vice versa. Hence, a precise and noise-free plant disease model is required for a better prediction. The current study proposes noise reduction-based hybridized classifiers for plant disease prediction. One tomato and four soybean disease datasets have been selected to conduct the proposed research. The Adaptive Sampling-based Class Label Noise Reduction (AS-CLNR) method has been used along with the Support Vector Machine (SVM) approach for noise reduction. The noise-minimized datasets have been fed into the Extreme Learning Machine (ELM), Decision Tree (DT), and Random Forest (RF) classifiers whose parameters are optimized using Genetic Algorithm (GA) for developing plant disease prediction models. The performances of all these models viz. Hybrid SVM-GA-ELM, Hybrid SVM-GA-DT, and Hybrid SVM-GA-RF have been evaluated using Accuracy, Area under ROC Curve, and F1-Score metrics. Further, these classifiers have been ranked using the statistical Friedman Test in which the Hybrid SVM-GA-RF classifier performed the best. Lastly, the Nemenyi test has also been performed to find out if significant differences exist between various classifiers or not. It was found that 33.33% of the total pairs of hybrid classifiers show a remarkably different performance from one another.

Diagnosis of Brain Tumor Using Light Weight Deep Learning Model with Fine-Tuning Approach

Brain cancer is a rare and deadly disease with a slim chance of survival. One of the most important tasks for neurologists and radiologists is to detect brain tumors early. Recent claims have been made that computer-aided diagnosis-based systems can diagnose brain tumors by employing magnetic resonance imaging (MRI) as a supporting technology. We propose transfer learning approaches for a deep learning model to detect malignant tumors, such as glioblastoma, using MRI scans in this study. This paper presents a deep learning-based approach for brain tumor identification and classification using the state-of-the-art object detection framework YOLO (You Only Look Once). The YOLOv5 is a novel object detection deep learning technique that requires limited computational architecture than its competing models. The study used the Brats 2021 dataset from the RSNA-MICCAI brain tumor radio genomic classification. The dataset has images annotated from RSNA-MICCAI brain tumor radio genomic competition dataset using the make sense an AI online tool for labeling dataset. The preprocessed data is then divided into testing and training for the model. The YOLOv5 model provides a precision of 88 percent. Finally, our model is tested across the whole dataset, and it is concluded that it is able to detect brain tumors successfully.

Towards continuous consistency axiom

Development of new algorithms in the area of machine learning, especially clustering, comparative studies of such algorithms as well as testing according to software engineering principles requires availability of labeled data sets. While standard benchmarks are made available, a broader range of such data sets is necessary in order to avoid the problem of overfitting. In this context, theoretical works on axiomatization of clustering algorithms, especially axioms on clustering preserving transformations are quite a cheap way to produce labeled data sets from existing ones. However, the frequently cited axiomatic system of Kleinberg:2002, as we show in this paper, is not applicable for finite dimensional Euclidean spaces, in which many algorithms like $k$-means, operate. In particular, the so-called outer-consistency axiom fails upon making small changes in datapoint positions and inner-consistency axiom is valid only for identity transformation in general settings. Hence we propose an alternative axiomatic system, in which Kleinberg's inner consistency axiom is replaced by a centric consistency axiom and outer consistency axiom is replaced by motion consistency axiom. We demonstrate that the new system is satisfiable for a hierarchical version of $k$-means with auto-adjusted $k$, hence it is not contradictory. Additionally, as $k$-means creates convex clusters only, we demonstrate that it is possible to create a version detecting concave clusters and still the axiomatic system can be satisfied. The practical application area of such an axiomatic system may be the generation of new labeled test data from existent ones for clustering algorithm testing. %We propose the gravitational consistency as a replacement which does not have this deficiency.

Performance of a Convolutional Neural Network- Based Artificial Intelligence Algorithm for Automatic Cephalometric Landmark Detection.

The aim of this study is to develop an artificial intelligence model to detect cephalometric landmark automatically en- abling the automatic analysis of cephalometric radiographs which have a very important place in dental practice and is used routinely in the diagnosis and treatment of dental and skeletal disorders. In this study, 1620 lateral cephalograms were obtained and 21 landmarks were included. The coordinates of all landmarks in the 1620 films were obtained to establish a labeled data set: 1360 were used as a training set, 140 as a validation set, and 180 as a testing set. A convolutional neural network-based artificial intelligence algorithm for automatic cephalometric landmark detection was developed. Mean radial error and success detection rate within the range of 2 mm, 2.5 mm, 3 mm, and 4 mm were used to eval- uate the performance of the model. Presented artificial intelligence system (CranioCatch, Eskişehir, Turkey) could detect 21 anatomic landmarks in a lateral ceph- alometric radiograph. The highest success detection rate scores of 2 mm, 2.5 mm, 3 mm, and 4 mm were obtained from the sella point as 98.3, 99.4, 99.4, and 99.4, respectively. The mean radial error ± standard deviation value of the sella point was found as 0.616 ± 0.43. The lowest success detection rate scores of 2 mm, 2.5 mm, 3 mm, and 4 mm were obtained from the Gonion point as 48.3, 62.8, 73.9, and 87.2, respectively. The mean radial error ± standard deviation value of Gonion point was found as 8.304 ± 2.98. Although the success of the automatic landmark detection using the developed artificial intelligence model was not in- sufficient for clinical use, artificial intelligence-based cephalometric analysis systems seem promising to cephalometric analysis which provides a basis for diagnosis, treatment planning, and following-up in clinical orthodontics practice.

A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification.

Specific emitter identification (SEI) refers to distinguishing emitters using individual features extracted from wireless signals. The current SEI methods have proven to be accurate in tackling large labeled data sets at a high signal-to-noise ratio (SNR). However, their performance declines dramatically in the presence of small samples and a significant noise environment. To address this issue, we propose a complex self-supervised learning scheme to fully exploit the unlabeled samples, comprised of a pretext task adopting the contrastive learning concept and a downstream task. In the former task, we design an optimized data augmentation method based on communication signals to serve the contrastive conception. Then, we embed a complex-valued network in the learning to improve the robustness to noise. The proposed scheme demonstrates the generality of handling the small and sufficient samples cases across a wide range from 10 to 400 being labeled in each group. The experiment also shows a promising accuracy and robustness where the recognition results increase at 10–16% from 10–15 SNR.

Drill Bit Failure Forensics Using 2D Bit Images Captured at the Rig Site

Summary Identifying the root cause of damage of a pulled bit as soon as possible will aid in preparation for future drilling operations. Today, bit damage analyses are often time-consuming, delayed, subjective, and error prone. A novel automated forensics approach is presented in this paper for polycrystalline diamond compact (PDC) bit damage root cause analysis using 2D bit photos that can be easily captured on a phone or camera at the rigsite. A labeled data set consisting of 125 actual bit images and 800 synthetic images was first created with the cutters appropriately identified and labeled. Using this data set, a convolutional neural network (CNN) along with other image processing techniques was applied to first identify the individual cutters and their positions on the bit and then to quantify the damage to the cutters. A cutter detection accuracy of over 97% and a damage quantification accuracy of 97% were achieved. A separate classifier was then trained to directly identify the root cause of failure from the bit images. This classifier utilized a separate data set that consisted of multiple bit images from 25 distinct bit runs. This data set was labeled into different types of failure mechanisms through analysis by a subject-matter expert. The trained classifier developed could properly identify the root causes of failure when the bit photo quality met certain minimum standards. One key observation was that bit images are not always captured appropriately, and this reduces the accuracy of the proposed methodology. By identifying the potential root causes of PDC damage through image processing, drilling parameters can be optimized to prolong future bit life.

Unsupervised seismic facies classification using deep convolutional autoencoder

With the increased size and complexity of seismic surveys, manual labeling of seismic facies has become a significant challenge. Application of automatic methods for seismic facies interpretation could significantly reduce the manual labor and subjectivity of a particular interpreter present in conventional methods. A recently emerged group of seismic interpretation techniques is based on deep neural networks. These approaches are data-driven and require large labeled data sets for network training. We have developed a deep convolutional autoencoder for unsupervised seismic facies classification, which does not require manually labeled examples. The facies maps are generated by clustering the deep-feature vectors obtained from the input data. Our method yields accurate results on real data and provides them instantaneously, which allows an interpreter to identify the dominant seismic features. The proposed approach opens possibilities to analyze geologic patterns in real time without human intervention.

IMPROVING CNN-BASED BUILDING SEMANTIC SEGMENTATION USING OBJECT BOUNDARIES

Abstract. Semantic segmentation is an active area of research with a wide range of applications including autonomous driving, digital mapping, urban monitoring, land use analysis and disaster management. For the past few years approaches based on Convolutional Neural Networks, especially end-to-end approaches based on architectures like the Fully Convolutional Networks (FCN) and UNet, have made great progress and are considered the current state-of-the-art. Nevertheless, there is still room for improvement as CNN-based supervised-learning models require a very large amount of labelled data in order to generalize effectively to new data and the segmentation results often lack detail, mostly in areas near the boundaries between objects. In this work we leverage the semantic information provided by the objects’ boundaries to improve the quality and detail of an encoder-decoder model’s semantic segmentation output. We use a UNet-based model with ResNet as an encoder for our backbone architecture in which we incorporate a decoupling module that separates the boundaries from the main body of the objects and thus learns explicit representations for both body and edges of each object. We evaluate our proposed approach on the Inria Aerial Image Labelling dataset and compare the results to a more traditional Unet-based architecture. We show that the proposed approach marginally outperforms the baseline on the mean precision, F1-score and IoU metrics by 1.1 to 1.6%. Finally, we examine certain cases of misclassification in the ground truth data and discuss how the trained models perform in such cases.

Generating a labeled data set to train machine learning algorithms for lithologic classification of drill cuttings

Despite significant developments in the past few years in the application of machine learning algorithms for the lithologic classification of rock samples, publicly available labeled data sets are very scarce. We open source a fully labeled data set containing more than 16,000 scanning electron microscopy (SEM) images of drill cutting samples—mounted on thin sections—from a low-permeability reservoir in western Canada. We develop a simplified image processing workflow to segment and isolate the rock chips into individual SEM images, which in turn are used to identify, classify, and quantify rock types based on textural characteristics. In addition, using this data set, we explore the use of convolutional neural networks (CNNs) as a baseline tool for acceleration and automatization of rock-type classification. Without significant modifications to popular CNN models, we obtain an accuracy of approximately 90% for the test set. Results demonstrate the potential of CNN as a fast approach for lithologic classification in low-permeability siltstone reservoirs. In addition to making the data set publicly available, we believe our workflow to segment and isolate drill cutting samples in individual images of rock chips will facilitate future research of drill cuttings properties (e.g., lithology, porosity, and particle size) using machine learning algorithms.

Two-stage generative adversarial networks for binarization of color document images

Document image enhancement and binarization methods are often used to improve the accuracy and efficiency of document image analysis tasks such as text recognition. Traditional non-machine-learning methods are constructed on low-level features in an unsupervised manner but have difficulty with binarization on documents with severely degraded backgrounds. Convolutional neural network (CNN)based methods focus only on grayscale images and on local textual features. In this paper, we propose a two-stage color document image enhancement and binarization method using generative adversarial neural networks. In the first stage, four color-independent adversarial networks are trained to extract color foreground information from an input image for document image enhancement. In the second stage, two independent adversarial networks with global and local features are trained for image binarization of documents of variable size. For the adversarial neural networks, we formulate loss functions between a discriminator and generators having an encoder–decoder structure. Experimental results show that the proposed method achieves better performance than many classical and state-of-the-art algorithms over the Document Image Binarization Contest (DIBCO) datasets, the LRDE Document Binarization Dataset (LRDE DBD), and our shipping label image dataset. We plan to release the shipping label dataset as well as our implementation code at github.com/opensuh/DocumentBinarization/.

Deep Reinforcement Learning with Automated Label Extraction from Clinical Reports Accurately Classifies 3D MRI Brain Volumes.

Image classification is probably the most fundamental task in radiology artificial intelligence. To reduce the burden of acquiring and labeling data sets, we employed a two-pronged strategy. We automatically extracted labels from radiology reports in Part 1. In Part 2, we used the labels to train a data-efficient reinforcement learning (RL) classifier. We applied the approach to a small set of patient images and radiology reports from our institution. For Part 1, we trained sentence-BERT (SBERT) on 90 radiology reports. In Part 2, we used the labels from the trained SBERT to train an RL-based classifier. We trained the classifier on a training set of [Formula: see text] images. We tested on a separate collection of [Formula: see text] images. For comparison, we also trained and tested a supervised deep learning (SDL) classification network on the same set of training and testing images using the same labels. Part 1: The trained SBERT model improved from 82 to [Formula: see text] accuracy. Part 2: Using Part 1's computed labels, SDL quickly overfitted the small training set. Whereas SDLshowed the worst possible testing set accuracy of 50%, RL achieved [Formula: see text] testing setaccuracy, with a [Formula: see text]-value of [Formula: see text]. We have shown the proof-of-principle application of automated label extraction from radiological reports. Additionally, we have built on prior work applying RL to classification using these labels, extending from 2D slices to entire 3D image volumes. RL has again demonstrated a remarkable ability to train effectively, in a generalized manner, and based on small training sets.

Comparison of residual and dense neural network approaches for building extraction from high-resolution aerial images

Applications including change detection, disaster management, and urban planning require precise building information, and therefore automatic building extraction has become a significant research topic. With the improvements in sensor and satellite technologies, more data has become available, and with the increased computational power, deep learning methods have emerged as successful tools. In this study, U-Net and FPN architectures using four different backbones (ResNet-50, ResNeXt-50, SE-ResNext-50, and DenseNet-121), and an Attention Residual U-Net approach were used for building extraction from high-resolution aerial images. Two publicly available datasets, Inria Aerial Image Labeling Dataset and Massachusetts Buildings Dataset were used to train and test the models. According to the results, Attention Residual U-Net model has the highest F1 score with 0.8154, IoU score with 0.7102, and test accuracy with 94.51% on the Inria dataset. On the Massachusetts dataset, FPN Dense-Net-121 model has the highest F1 score with 0.7565 and IoU score with 0.6188, and Attention Residual U-Net model has the highest test accuracy with 92.43%. It has been observed that, FPN with DenseNet backbone can be a better choice when working with small size datasets. On the other hand, Attention Residual U-Net approach achieved higher success when a sufficiently large dataset is provided.

Comparative research on different backbone architectures of DeepLabV3+ for building segmentation

Rapid urban growth and globalization affect land use in cities, and the need for automatic interpretation of remote sensing images is constantly increasing. Deep neural networks are becoming widespread in high-resolution aerial and satellite image sources in Earth observation missions. Various convolutional neural network (CNN) architectures have been implemented in building extraction, but it is still challenging to distinguish building class from other man-made classes in public datasets. Here, we present comparative research for automatic building extraction on different data sources using DeepLabV3+ architecture with ResNet-18, ResNet-50, Xception, and MobileNetv2 models. The CNNs are implemented on Inria Aerial Image Labeling, Massachusetts Buildings, and Wuhan University Building Extraction Datasets in terms of evaluation metrics and training and testing time consumption. Our implementation of the DeepLabV3 + ResNet-50 model performed F1-score of 97.44% in Massachusetts Building dataset and intersection over union as 80.75% in Inria dataset, higher than at least 3% than the previous studies.

Multi-Source Selection Transfer Learning with Privacy-Preserving

Transfer learning has ability to create learning task of weakly labeled or unlabeled target domain by using knowledge of source domain to help, which can effectively improve the performance of target learning task. At present, the increased awareness of privacy protection restricts access to data sources and poses new challenges to the development of transfer learning. However, the research on privacy protection in transfer learning is very rare. The existing work mainly uses differential privacy technology and does not consider the distribution difference between data sources, or does not consider the conditional probability distribution of data, which causes negative transfer to harm the effect of algorithm. Therefore, this paper proposes multi-source selection transfer learning algorithm with privacy-preserving MultiSTLP, which is used in scenarios where target domain contains unlabeled data sets with only a small amount of group probability information and multiple source domains with a large number of labeled data sets. Group probability means that the class label of each sample in target data set is unknown, but the probability of each class in a given data group is available, and multiple source domains indicate that there are more than two source domains. The number of data set contains more than two data sets of source domain and one data set of target domain. The algorithm adapts to the marginal probability distribution and conditional probability distribution differences between domains, and can protect the privacy of target data and improve classification accuracy by fusing the idea of multi-source transfer learning and group probability into support vector machine. At the same time, it can select the representative dataset in source domains to improve efficiency relied on speeding up the training process of algorithm. Experimental results on several real datasets show the effectiveness of MultiSTLP, and it also has some advantages compared with the state-of-the-art transfer learning algorithm.

Improving image classification robustness using self‐supervision

Self‐supervised learning allows training of neural networks without immense, high‐quality or labelled data sets. We demonstrate that self‐supervision furthermore improves robustness of models using small, imbalanced or incomplete data sets which pose severe difficulties to supervised models. For small data sets, the accuracy of our approach is up to 12.5% higher using MNIST and 15.2% using Fashion‐MNIST compared to random initialization. Moreover, self‐supervision influences the way of learning itself, which means that in case of small or strongly imbalanced data sets, it can be prevented that classes are not or insufficiently learned. Even if input data are corrupted and large image regions are missing from the training set, self‐supervision significantly improves classification accuracy (up to 7.3% for MNIST and 2.2% for Fashion‐MNIST). In addition, we analyse combinations of data manipulations and seek to generate a better understanding of how pretext accuracy and downstream accuracy are related. This is not only important to ensure optimal pretraining but also for training with unlabelled data in order to find an appropriate evaluation measure. As such, we make an important contribution to learning with realistic data sets and making machine learning accessible to application areas that require expensive and difficult data collection.

Automatic Spread‐F Detection Using Deep Learning

AbstractSpread‐F (SF) is a feature that can be visually observed on ionograms when the ionosonde signals are significantly impacted by plasma irregularities in the ionosphere. Depending on the scale of the plasma irregularities, radio waves of different frequencies are impacted differently when the signals pass through the ionosphere. An automated method for detecting SF in ionograms is presented in this study. Through detecting the existence of SF in ionograms, we can help identify instances of plasma irregularities that are potentially affecting the high‐frequency radio‐wave systems. The ionogram images from Jicamarca observatory in Peru, during the years 2008–2019, are used in this study. Three machine learning approaches have been carried out: supervised learning using Support Vector Machines, and two neural network‐based learning methods: autoencoder and transfer learning. Of these three methods, the transfer learning approach, which uses convolutional neural network architectures, demonstrates the best performance. The best existing architecture that is suitable for this problem appears to be the ResNet50. With respect to the training epoch number, the ResNet50 showed the greatest change in the metric values for the key metrics that we were tracking. Furthermore, on a test set of 2050 ionograms, the model based on the ResNet50 architecture provides an accuracy of 89%, recall of 87%, precision of 95%, as well as Area Under the Curve of 96%. The work also provides a labeled data set of around 28,000 ionograms, which is extremely useful for the community for future machine learning studies.

Transfer Learning Improves Accelerometer-Based Child Activity Recognition via Subject-Independent Adult-Domain Adaption.

Wearable activity recognition can collate the type, intensity, and duration of each child's physical activity profile, which is important for exploring underlying adolescent health mechanisms. Traditional machine-learning-based approaches require large labeled data sets; however, child activity data sets are typically small and insufficient. Thus, we proposed a transfer learning approach that adapts adult-domain data to train a high-fidelity, subject-independent model for child activity recognition. Twenty children and twenty adults wore an accelerometer wristband while performing walking, running, sitting, and rope skipping activities. Activity classification accuracy was determined via the traditional machine learning approach without transfer learning and with the proposed subject-independent transfer learning approach. Results showed that transfer learning increased classification accuracy to 91.4% as compared to 80.6% without transfer learning. These results suggest that subject-independent transfer learning can improve accuracy and potentially reduce the size of the required child data sets to enable physical activity monitoring systems to be adopted more widely, quickly, and economically for children and provide deeper insights into injury prevention and health promotion strategies.

Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Building footprint has a significant role in urban design and management but, extracting the building feature is still challenging due to significant variations in scale and shape. Convolution neural networks (CNN) have shown effective results in extracting the high-level and discriminative urban features from high-resolution remote sensing imagery. The traditional CNN architecture has been modified two-scale input based architecture, known as Dual-scale CNN (Du-CNN). However, the repetitive usage of pooling operation leads to a fuzzy boundary of the extracted features. This paper has proposed the MRF-based fusion strategy to take full use of the blurred boundary and define the conditional relationship between classification maps. In the Preliminary stage, we have designed a Du-CNN framework to extract the building feature at different scales. Du-CNN contains a multiple-size asymmetric filter to provide the variation in the receptive field and the depth-wise convolution in the skip connection block for efficient computation. Finally, the classification maps of both CNN sub-architectures are fused using a Modified Markov random field (MMRF). The proposed MMRF technique inherits the properties of Classical MRF with the extension of overlap potential for associating additional terms between the inter-decision layer. The model was tested on Inria Aerial image labeling dataset and Mnih dataset. Experimental result has shown the superior performance of the proposed strategy for extracting the complex building architecture.

Microscopic Imaging and Labeling Dataset for the Detection of Pneumocystis jirovecii Using Methenamine Silver Staining Method

Pneumocystis jirovecii pneumonia is one of the diseases that most affects immunocompromised patients today, and under certain circumstances, it can be fatal. On the other hand, more and more automatic tools based on artificial intelligence are required every day to help diagnose diseases and thus optimize the resources of the healthcare system. It is therefore important to develop techniques and mechanisms that enable early diagnosis. One of the most widely used techniques in diagnostic laboratories for the detection of its etiological agent, Pneumocystis jirovecii, is optical microscopy. Therefore, an image dataset of 29 different patients is presented in this work, which can be used to detect whether a patient is positive or negative for this fungi. These images were taken in at least four random positions on the specimen holder. The dataset consists of a total of 137 RGB images. Likewise, it contains realistic, annotated, and high-quality microscope images. In addition, we provide image segmentation and labeling that can also be used in numerous studies based on artificial intelligence implementation. The labeling was also validated by an expert, allowing it to be used as a reference in the training of automatic algorithms with supervised learning methods and thus to develop diagnostic assistance systems. Therefore, the dataset will open new opportunities for researchers working in image segmentation, detection, and classification problems related to Pneumocystis jirovecii pneumonia diagnosis.

AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network.

Building contour extraction from high-resolution remote sensing images is a basic task for the reasonable planning of regional construction. Recently, building segmentation methods based on the U-Net network have become popular as they largely improve the segmentation accuracy by applying ‘skip connection’ to combine high-level and low-level feature information more effectively. Meanwhile, researchers have demonstrated that introducing an attention mechanism into U-Net can enhance local feature expression and improve the performance of building extraction in remote sensing images. In this paper, we intend to explore the effectiveness of the primeval attention gate module and propose the novel Attention Gate Module (AG) based on adjusting the position of ‘Resampler’ in an attention gate to Sigmoid function for a building extraction task, and a novel Attention Gates U network (AGs-Unet) is further proposed based on AG, which can automatically learn different forms of building structures in high-resolution remote sensing images and realize efficient extraction of building contour. AGs-Unet integrates attention gates with a single U-Net network, in which a series of attention gate modules are added into the ‘skip connection’ for suppressing the irrelevant and noisy feature responses in the input image to highlight the dominant features of the buildings in the image. AGs-Unet improves the feature selection of the attention map to enhance the ability of feature learning, as well as paying attention to the feature information of small-scale buildings. We conducted the experiments on the WHU building dataset and the INRIA Aerial Image Labeling dataset, in which the proposed AGs-Unet model is compared with several classic models (such as FCN8s, SegNet, U-Net, and DANet) and two state-of-the-art models (such as PISANet, and ARC-Net). The extraction accuracy of each model is evaluated by using three evaluation indexes, namely, overall accuracy, precision, and intersection over union. Experimental results show that the proposed AGs-Unet model can improve the quality of building extraction from high-resolution remote sensing images effectively in terms of prediction performance and result accuracy.