Active Classification With Uncertainty Comparison Queries

Noisy pairwise comparison feedback has been incorporated to improve the overall query complexity of interactively learning binary classifiers. The positivity comparison oracle is extensively used to provide feedback on which is more likely to be positive in a pair of data points. Because it is impossible to determine accurate labels using this oracle alone without knowing the classification threshold, existing methods still rely on the traditional explicit labeling oracle, which explicitly answers the label given a data point. The current method conducts sorting on all data points and uses explicit labeling oracle to find the classification threshold. However, it has two drawbacks: (1) it needs unnecessary sorting for label inference and (2) it naively adapts quick sort to noisy feedback. In order to avoid these inefficiencies and acquire information of the classification threshold at the same time, we propose a new pairwise comparison oracle concerning uncertainties. This oracle answers which one has higher uncertainty given a pair of data points. We then propose an efficient adaptive labeling algorithm to take advantage of the proposed oracle. In addition, we address the situation where the labeling budget is insufficient compared to the data set size. Furthermore, we confirm the feasibility of the proposed oracle and the performance of the proposed algorithm theoretically and empirically.

Guidelines for the validation of machine learning predictions of species interactions

1. The prediction of species interactions is gaining momentum as a way to circumvent limitations in data volume. Yet, ecological networks are challenging to predict because they are typically small and sparse. Dealing with extreme class imbalance is a challenge for most binary classifiers, and there are currently no guidelines as to how predictive models can be trained for this specific problem.2. Using simple mathematical arguments and numerical experiments in which a variety of classifiers (for supervised learning) are trained on simulated networks, we develop a series of guidelines related to the choice of measures to use for model selection, and the degree of unbiasing to apply to the training dataset.3. Neither classifier accuracy nor the ROC-AUC are informative measures for the performance of interaction prediction. PR-AUC is a fairer assessment of performance. In some cases, even standard measures can lead to selecting a more biased classifier because the effect of connectance is strong. The amount of correction to apply to the training dataset depends on network connectance, on the measure to be optimized, and only weakly on the classifier.4. These results reveal that training machines to predict networks is a challenging task, and that in virtually all cases, the composition of the training set needs to be experimented on before performing the actual training. We discuss these consequences in the context of the low volume of data.

Mine MIMO Depth Receiver: An Intelligent Receiving Model Based on Densely Connected Convolutional Networks

Multiple-input multiple-output (MIMO) systems suffer from high BER in the mining environment. In this paper, the mine MIMO depth receiver model is proposed. The model uses densely connected convolutional networks for feature extraction and constructs multiple binary classifiers to recover the original information. Compared with conventional MIMO receivers, the model has no error accumulation caused by processes such as decoding and demodulation. The experimental results show that the model has better performance than conventional decoding methods under different modulation codes and variations in the number of transmitting terminals. Furthermore, we demonstrate that the model can still achieve effective decoding and recover the original information with some data loss at the receiver.

A Machine Learning Approach to Predicting Diabetes Complications

Diabetes mellitus (DM) is a chronic disease that is considered to be life-threatening. It can affect any part of the body over time, resulting in serious complications such as nephropathy, neuropathy, and retinopathy. In this work, several supervised classification algorithms were applied for building different models to predict and classify eight diabetes complications. The complications include metabolic syndrome, dyslipidemia, neuropathy, nephropathy, diabetic foot, hypertension, obesity, and retinopathy. For this study, a dataset collected by the Rashid Center for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset consists of 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Furthermore, feature selection was performed to select the top five and ten features for each complication. The final number of records used to train and build the binary classifiers for each complication was as follows: 428—metabolic syndrome, 836—dyslipidemia, 223—neuropathy, 233—nephropathy, 240—diabetic foot, 586—hypertension, 498—obesity, 228—retinopathy. Repeated stratified k-fold cross-validation (with k = 10 and a total of 10 repetitions) was employed for a better estimation of the performance. Accuracy and F1-score were used to evaluate the models’ performance reaching a maximum of 97.8% and 97.7% for accuracy and F1-scores, respectively. Moreover, by comparing the performance achieved using different attributes’ sets, it was found that by using a selected number of features, we can still build adequate classifiers.

A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account

Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furthermore, we have published GenuineAI, a new python library, which provides the functions for conventional AUC and the proposed modified AUC along with metrics including sensitivity, specificity, recall, precision, and F1 for each point of the ROC curve.

Unified landslide hazard assessment using hurdle models: a case study in the Island of Dominica

Climatically-induced natural hazards are a threat to communities. They can cause life losses and heavy damage to infrastructure, and due to climate change, they have become increasingly frequent. This is especially in tropical regions, where major hurricanes have consistently appeared in recent history. Such events induce damage due to the high wind speed they carry, and the high intensity/duration rainfall they discharge can further induce a chain of hydro-morphological hazards in the form of widespread debris slides/flows. The way the scientific community has developed preparatory steps to mitigate the potential damage of these hydro-morphological threats includes assessing where they are likely to manifest across a given landscape. This concept is referred to as susceptibility, and it is commonly achieved by implementing binary classifiers to estimate probabilities of landslide occurrences. However, predicting where landslides can occur may not be sufficient information, for it fails to convey how large landslides may be. This work proposes using a flexible Bernoulli-log-Gaussian hurdle model to simultaneously model landslide occurrence and size per areal unit. Covariate and spatial information are introduced using a generalised additive modelling framework. To cope with the high spatial resolution of the data, our model uses a Markovian representation of the Matérn covariance function based on the stochastic partial differential equation (SPDE) approach. Assuming Gaussian priors, our model can be integrated into the class of latent Gaussian models, for which inference is conveniently performed based on the integrated nested Laplace approximation method. We use our modelling approach in Dominica, where Hurricane Maria (September 2017) induced thousands of shallow flow-like landslides passing over the island. Our results show that we can not only estimate where landslides may occur and how large they may be, but we can also combine this information in a unified landslide hazard model, which is the first of its kind.

Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities

Ischemic stroke lesion (ISL) is a brain abnormality. Studies proved that early detection and treatment could reduce the disease impact. This research aimed to develop a deep learning (DL) framework to detect the ISL in multi-modality magnetic resonance image (MRI) slices. It proposed a convolutional neural network (CNN)-supported segmentation and classification to execute a consistent disease detection framework. The developed framework consisted of the following phases; (i) visual geometry group (VGG) developed VGG16 scheme supported SegNet (VGG-SegNet)-based ISL mining, (ii) handcrafted feature extraction, (iii) deep feature extraction using the chosen DL scheme, (iv) feature ranking and serial feature concatenation, and (v) classification using binary classifiers. Fivefold cross-validation was employed in this work, and the best feature was selected as the final result. The attained results were separately examined for (i) segmentation; (ii) deep-feature-based classification, and (iii) concatenated feature-based classification. The experimental investigation is presented using the Ischemic Stroke Lesion Segmentation (ISLES2015) database. The attained result confirms that the proposed ISL detection framework gives better segmentation and classification results. The VGG16 scheme helped to obtain a better result with deep features (accuracy > 97%) and concatenated features (accuracy > 98%).

Automatic Diagnosis of Mental Healthcare Information Actionability: Developing Binary Classifiers

We aimed to develop a quantitative instrument to assist with the automatic evaluation of the actionability of mental healthcare information. We collected and classified two large sets of mental health information from certified mental health websites: generic and patient-specific mental healthcare information. We compared the performance of the optimised classifier with popular readability tools and non-optimised classifiers in predicting mental health information of high actionability for people with mental disorders. sensitivity of the classifier using both semantic and structural features as variables achieved statistically higher than that of the binary classifier using either semantic (p < 0.001) or structural features (p = 0.0010). The specificity of the optimized classifier was statistically higher than that of the classifier using structural variables (p = 0.002) and the classifier using semantic variables (p = 0.001). Differences in specificity between the full-variable classifier and the optimised classifier were statistically insignificant (p = 0.687). These findings suggest the optimised classifier using as few as 19 semantic-structural variables was the best-performing classifier. By combining insights of linguistics and statistical analyses, we effectively increased the interpretability and the diagnostic utility of the binary classifiers to guide the development, evaluation of the actionability and usability of mental healthcare information.