Using histopathological images to automatically classify cancer is a difficult task for accurately detecting cancer, especially to identify metastatic cancer in small image patches obtained from larger digital pathology scans. Computer diagnosis technology has attracted wide attention from researchers. In this paper, we propose a noval method which combines the deep learning algorithm in image classification, the DenseNet169 framework and Rectified Adam optimization algorithm. The connectivity pattern of DenseNet is direct connections from any layer to all consecutive layers, which can effectively improve the information flow between different layers. With the fact that RAdam is not easy to fall into a local optimal solution, and it can converge quickly in model training. The experimental results shows that our model achieves superior performance over the other classical convolutional neural networks approaches, such as Vgg19, Resnet34, Resnet50. In particular, the Auc-Roc score of our DenseNet169 model is 1.77% higher than Vgg19 model, and the Accuracy score is 1.50% higher. Moreover, we also study the relationship between loss value and batches processed during the training stage and validation stage, and obtain some important and interesting findings.
The recently introduced locally orderless tensor network (LoTeNet) for supervised image classification uses matrix product state (MPS) operations on grids of transformed image patches. The resulting patch representations are combined back together into the image space and aggregated hierarchically using multiple MPS blocks per layer to obtain the final decision rules. In this work, we propose a non-patch based modification to LoTeNet that performs one MPS operation per layer, instead of several patch-level operations. The spatial information in the input images to MPS blocks at each layer is squeezed into the feature dimension, similar to LoTeNet, to maximise retained spatial correlation between pixels when images are flattened into 1D vectors. The proposed multi-layered tensor network (MLTN) is capable of learning linear decision boundaries in high dimensional spaces in a multi-layered setting, which results in a reduction in the computation cost compared to LoTeNet without any degradation in performance.
Quality of image always plays a vital role in in-creasing object recognition or classification rate. A good quality image gives better recognition or classification rate than any unprocessed noisy images. It is more difficult to extract features from such unprocessed images which in-turn reduces object recognition or classification rate. To overcome problems occurred due to low quality image, typically pre-processing is done before extracting features from the image. Our project proposes an image pre-processing method, so that the performance of selected Machine Learning algorithms or Deep Learning algorithms increases in terms of increased accuracy or reduced the number of training images. In the later part, we compare the performance results by using our method with the previous used approaches.
This paper analyses how well a Fast Fully Convolutional Network (FastFCN) semantically segments satellite images and thus classifies Land Use/Land Cover(LULC) classes. Fast-FCN was used on Gaofen-2 Image Dataset (GID-2) to segment them in five different classes: BuiltUp, Meadow, Farmland, Water and Forest. The results showed better accuracy (0.93), precision (0.99), recall (0.98) and mean Intersection over Union (mIoU)(0.97) than other approaches like using FCN-8 or eCognition, a readily available software. We presented a comparison between the results. We propose FastFCN to be both faster and more accurate automated method than other existing methods for LULC classification.
The classification of different fine hand movements from EEG signals represents a relevant research challenge, e.g., in brain-computer interface applications for motor rehabilitation. Here, we analyzed two different datasets where fine hand movements (touch, grasp, palmar and lateral grasp) were performed in a self-paced modality. We trained and tested a newly proposed convolutional neural network (CNN), and we compared its classification performance into respect to two well-established machine learning models, namely, a shrinked-LDA and a Random Forest. Compared to previous literature, we took advantage of the knowledge of the neuroscience field, and we trained our CNN model on the so-called Movement Related Cortical Potentials (MRCPs)s. They are EEG amplitude modulations at low frequencies, i.e., (0.3, 3) Hz, that have been proved to encode several properties of the movements, e.g., type of grasp, force level and speed. We showed that CNN achieved good performance in both datasets and they were similar or superior to the baseline models. Also, compared to the baseline, our CNN requires a lighter and faster pre-processing procedure, paving the way for its possible use in an online modality, e.g., for many brain-computer interface applications.
Attention maps are a popular way of explaining the decisions of convolutional networks for image classification. Typically, for each image of interest, a single attention map is produced, which assigns weights to pixels based on their importance to the classification. A single attention map, however, provides an incomplete understanding since there are often many other maps that explain a classification equally well. In this paper, we introduce structured attention graphs (SAGs), which compactly represent sets of attention maps for an image by capturing how different combinations of image regions impact a classifier's confidence. We propose an approach to compute SAGs and a visualization for SAGs so that deeper insight can be gained into a classifier's decisions. We conduct a user study comparing the use of SAGs to traditional attention maps for answering counterfactual questions about image classifications. Our results show that the users are more correct when answering comparative counterfactual questions based on SAGs compared to the baselines.
The classification of sleep stages is the first and an important step in the quantitative analysis of polysomnographic recordings. Sleep stage scoring relies heavily on visual pattern recognition by a human expert and is time consuming and subjective. Thus, there is a need for automatic classification. In this work we developed machine learning algorithms for sleep classification: random forest (RF) classification based on features and artificial neural networks (ANNs) working both with features and raw data. We tested our methods in healthy subjects and in patients. Most algorithms yielded good results comparable to human interrater agreement. Our study revealed that deep neural networks (DNNs) working with raw data performed better than feature-based methods. We also demonstrated that taking the local temporal structure of sleep into account a priori is important. Our results demonstrate the utility of neural network architectures for the classification of sleep.
Online power system event identification and classification is crucial to enhancing the reliability of transmission systems. In this paper, we develop a deep neural network (DNN) based approach to identify and classify power system events by leveraging real-world measurements from hundreds of phasor measurement units (PMUs) and labels from thousands of events. Two innovative designs are embedded into the baseline model built on convolutional neural networks (CNNs) to improve the event classification accuracy. First, we propose a graph signal processing based PMU sorting algorithm to improve the learning efficiency of CNNs. Second, we deploy information loading based regularization to strike the right balance between memorization and generalization for the DNN. Numerical studies results based on real-world dataset from the Eastern Interconnection of the U.S power transmission grid show that the combination of PMU based sorting and the information loading based regularization techniques help the proposed DNN approach achieve highly accurate event identification and classification results.
One of the most rising issues in recent machine learning research is One-Class Classification which considers data set composed of only one class and outliers. It is more reasonable than traditional Multi-Class Classification in dealing with some problematic data set or special cases. Generally, classification accuracy and interpretability for user are considered as trade-off in OCC methods. Classifier based on Hyper-Rectangle (H-RTGL) is a sort of classifier that can be a remedy for such trade-off and uses H-RTGL formulated by conjunction of geometric rules called interval. This interval can be basis of interpretability since it can be easily understood by user. However, existing H-RTGL based OCC classifiers have limitations that (i) most of them cannot reflect density of target class and (ii) that considering density has primitive interval generation method, and (iii) there exists no systematic procedure for hyperparameter of H-RTGL based OCC classifier, which influences classification performance of classifier. Based on these remarks, we suggest One-Class Hyper-Rectangle Descriptor based on density (1-HRD_d) with more elaborate interval generation method including parametric and nonparametric approaches. In addition, we designed Genetic Algorithm (GA) that consists of chromosome structure and genetic operators for systematic generation of 1-HRD_d by optimization of hyperparameter. Our work is validated through a numerical experiment using actual data set with comparison of existing OCC algorithms along with other H-RTGL based classifiers.
Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research shows it is possible to improve BERT's performance on various tasks by augmenting the model with additional information. In this work, we use probing tasks as introspection techniques to identify linguistic information not well-represented in various layers of BERT, but important for the AD detection task. We supplement these linguistic features in which representations from BERT are found to be insufficient with hand-crafted features externally, and show that jointly fine-tuning BERT in combination with these features improves the performance of AD classification by upto 5\% over fine-tuned BERT alone.
In this work, we present an ensemble of descriptors for the classification of transmission electron microscopy images of viruses. We propose to combine handcrafted and deep learning approaches for virus image classification. The set of handcrafted is mainly based on Local Binary Pattern variants, for each descriptor a different Support Vector Machine is trained, then the set of classifiers is combined by sum rule. The deep learning approach is a densenet201 pretrained on ImageNet and then tuned in the virus dataset, the net is used as features extractor for feeding another Support Vector Machine, in particular the last average pooling layer is used as feature extractor. Finally, classifiers trained on handcrafted features and classifier trained on deep learning features are combined by sum rule. The proposed fusion strongly boosts the performance obtained by each stand-alone approach, obtaining state of the art performance.
In this work, we briefly revise the reduced dilation-erosion perceptron (r-DEP) models for binary classification tasks. Then, we present the so-called linear dilation-erosion perceptron (l-DEP), in which a linear transformation is applied before the application of the morphological operators. Furthermore, we propose to train the l-DEP classifier by minimizing a regularized hinge-loss function subject to concave-convex restrictions. A simple example is given for illustrative purposes.
Herein we define a measure of similarity between classification distributions that is both principled from the perspective of statistical pattern recognition and useful from the perspective of machine learning practitioners. In particular, we propose a novel similarity on classification distributions, dubbed task similarity, that quantifies how an optimally-transformed optimal representation for a source distribution performs when applied to inference related to a target distribution. The definition of task similarity allows for natural definitions of adversarial and orthogonal distributions. We highlight limiting properties of representations induced by (universally) consistent decision rules and demonstrate in simulation that an empirical estimate of task similarity is a function of the decision rule deployed for inference. We demonstrate that for a given target distribution, both transfer efficiency and semantic similarity of candidate source distributions correlate with empirical task similarity.
Mathematical morphology (MM) is a theory of non-linear operators used for the processing and analysis of images. Morphological neural networks (MNNs) are neural networks whose neurons compute morphological operators. Dilations and erosions are the elementary operators of MM. From an algebraic point of view, a dilation and an erosion are operators that commute respectively with the supremum and infimum operations. In this paper, we present the \textit{linear dilation-erosion perceptron} ($\ell$-DEP), which is given by applying linear transformations before computing a dilation and an erosion. The decision function of the $\ell$-DEP model is defined by adding a dilation and an erosion. Furthermore, training a $\ell$-DEP can be formulated as a convex-concave optimization problem. We compare the performance of the $\ell$-DEP model with other machine learning techniques using several classification problems. The computational experiments support the potential application of the proposed $\ell$-DEP model for binary classification tasks.
Robustness is of central importance in machine learning and has given rise to the fields of domain generalization and invariant learning, which are concerned with improving performance on a test distribution distinct from but related to the training distribution. In light of recent work suggesting an intimate connection between fairness and robustness, we investigate whether algorithms from robust ML can be used to improve the fairness of classifiers that are trained on biased data and tested on unbiased data. We apply Invariant Risk Minimization (IRM), a domain generalization algorithm that employs a causal discovery inspired method to find robust predictors, to the task of fairly predicting the toxicity of internet comments. We show that IRM achieves better out-of-distribution accuracy and fairness than Empirical Risk Minimization (ERM) methods, and analyze both the difficulties that arise when applying IRM in practice and the conditions under which IRM will likely be effective in this scenario. We hope that this work will inspire further studies of how robust machine learning methods relate to algorithmic fairness.
The Federated Learning setting has a central server coordinating the training of a model on a network of devices. One of the challenges is variable training performance when the dataset has a class imbalance. In this paper, we address this by introducing a new loss function called Fed-Focal Loss. We propose to address the class imbalance by reshaping cross-entropy loss such that it down-weights the loss assigned to well-classified examples along the lines of focal loss. Additionally, by leveraging a tunable sampling framework, we take into account selective client model contributions on the central server to further focus the detector during training and hence improve its robustness. Using a detailed experimental analysis with the VIRTUAL (Variational Federated Multi-Task Learning) approach, we demonstrate consistently superior performance in both the balanced and unbalanced scenarios for MNIST, FEMNIST, VSN and HAR benchmarks. We obtain a more than 9% (absolute percentage) improvement in the unbalanced MNIST benchmark. We further show that our technique can be adopted across multiple Federated Learning algorithms to get improvements.
Objective: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but similar database, even if that database contains the same classes. This problem is caused by domain-shift and can be solved using two approaches: domain adaptation and domain generalization. Simply, domain adaptation methods can access data from unseen domains during training; whereas in domain generalization, the unseen data is not available during training. Hence, domain generalization concerns models that perform well on inaccessible, domain-shifted data. Method: Our proposed domain generalization method represents an unseen domain using a set of known basis domains, afterwhich we classify the unseen domain using classifier fusion. To demonstrate our system, we employ a collection of heart sound databases that contain normal and abnormal sounds (classes). Results: Our proposed classifier fusion method achieves accuracy gains of up to 16% for four completely unseen domains. Conclusion: Recognizing the complexity induced by the inherent temporal nature of biosignal data, the two-stage method proposed in this study is able to effectively simplify the whole process of domain generalization while demonstrating good results on unseen domains and the adopted basis domains. Significance: To our best knowledge, this is the first study that investigates domain generalization for biosignal data. Our proposed learning strategy can be used to effectively learn domain-relevant features while being aware of the class differences in the data.
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cluttered MNIST, Large CIFAR-10 and Large CIFAR-100 datasets which are resized to 128 in both width and height.
It is challenging to visually detect heart disease from the electrocardiographic (ECG) signals. Implementing an automated ECG signal detection system can help diagnosis arrhythmia in order to improve the accuracy of diagnosis. In this paper, we proposed, implemented, and compared an automated system using two different frameworks of the combination of convolutional neural network (CNN) and long-short term memory (LSTM) for classifying normal sinus signals, atrial fibrillation, and other noisy signals. The dataset we used is from the MIT-BIT Arrhythmia Physionet. Our approach demonstrated that the cascade of two deep learning network has higher performance than the concatenation of them, achieving a weighted f1 score of 0.82. The experimental results have successfully validated that the cascade of CNN and LSTM can achieve satisfactory performance on discriminating ECG signals.
Correlated outcomes are common in many practical problems. In some settings, one outcome is of particular interest, and others are auxiliary. To leverage information shared by all the outcomes, traditional multi-task learning (MTL) minimizes an averaged loss function over all the outcomes, which may lead to biased estimation for the target outcome, especially when the MTL model is mis-specified. In this work, based on a decomposition of estimation bias into two types, within-subspace and against-subspace, we develop a robust transfer learning approach to estimating a high-dimensional linear decision rule for the outcome of interest with the presence of auxiliary outcomes. The proposed method includes an MTL step using all outcomes to gain efficiency, and a subsequent calibration step using only the outcome of interest to correct both types of biases. We show that the final estimator can achieve a lower estimation error than the one using only the single outcome of interest. Simulations and real data analysis are conducted to justify the superiority of the proposed method.