In this work, we propose a method to efficiently compute label posteriors of a base flat classifier in the presence of few validation examples within a bottom-up hierarchical inference framework. A stand-alone validation set (not used to train the base classifier) is preferred for posterior estimation to avoid overfitting the base classifier, however a small validation set limits the number of features one can effectively use. We propose a simple, yet robust, logit vector compression approach based on generalized logits and label confusions for the task of label posterior estimation within the context of hierarchical classification. Extensive comparative experiments with other compression techniques are provided across multiple sized validation sets, and a comparison with related hierarchical classification approaches is also conducted. The proposed approach mitigates the problem of not having enough validation examples for reliable posterior estimation while maintaining strong hierarchical classification performance.
Epilepsy affects 50 million people worldwide and is one of the most common serious neurological disorders. Seizure detection and classification is a valuable tool for diagnosing and maintaining the condition. An automated classification algorithm will allow for accurate diagnosis. Utilising the Temple University Hospital (TUH) Seizure Corpus, six seizure types are compared; absence, complex partial, myoclonic, simple partial, tonic and tonic- clonic models. This study proposes a method that utilises unique features with a novel parallel classifier - Parallel Genetic Naive Bayes (NB) Seizure Classifier (PGNBSC). The PGNBSC algorithm searches through the features and by reclassifying the data each time, the algorithm will create a matrix for optimum search criteria. Ictal states from the EEGs are segmented into 1.8 s windows, where the epochs are then further decomposed into 13 different features from the first intrinsic mode function (IMF). The features are compared using an original NB classifier in the first model. This is improved upon in a second model by using a genetic algorithm (Binary Grey Wolf Optimisation, Option 1) with a NB classifier. The third model uses a combination of the simple partial and complex partial seizures to provide the highest classification accuracy for each of the six seizures amongst the three models (20%, 53%, and 85% for first, second, and third model, respectively).
Autism spectrum disorder ASD is a neurodevelopmental disorder associated with challenges in communication, social interaction, and repetitive behaviors. Getting a clear diagnosis for a child is necessary for starting early intervention and having access to therapy services. However, there are many barriers that hinder the screening of these kids for autism at an early stage which might delay further the access to therapeutic interventions. One promising direction for improving the efficiency and accuracy of ASD detection in toddlers is the use of machine learning techniques to build classifiers that serve the purpose. This paper contributes to this area and uses the data developed by Dr. Fadi Fayez Thabtah to train and test various machine learning classifiers for the early ASD screening. Based on various attributes, three models have been trained and compared which are Decision tree C4.5, Random Forest, and Neural Network. The three models provided very good accuracies based on testing data, however, it is the Neural Network that outperformed the other two models. This work contributes to the early screening of toddlers by helping identify those who have ASD traits and should pursue formal clinical diagnosis.
Time-series data classification is central to the analysis and control of autonomous systems, such as robots and self-driving cars. Temporal logic-based learning algorithms have been proposed recently as classifiers of such data. However, current frameworks are either inaccurate for real-world applications, such as autonomous driving, or they generate long and complicated formulae that lack interpretability. To address these limitations, we introduce a novel learning method, called Boosted Concise Decision Trees (BCDTs), to generate binary classifiers that are represented as Signal Temporal Logic (STL) formulae. Our algorithm leverages an ensemble of Concise Decision Trees (CDTs) to improve the classification performance, where each CDT is a decision tree that is empowered by a set of techniques to generate simpler formulae and improve interpretability. The effectiveness and classification performance of our algorithm are evaluated on naval surveillance and urban-driving case studies.
In recent years, hypercomplex-inspired neural networks (HCNNs) have been used to improve deep learning architectures due to their ability to enable channel-based weight sharing, treat colors as a single entity, and improve representational coherence within the layers. The work described herein studies the effect of replacing existing layers in an Axial Attention network with their representationally coherent variants to assess the effect on image classification. We experiment with the stem of the network, the bottleneck layers, and the fully connected backend, by replacing them with representationally coherent variants. These various modifications lead to novel architectures which all yield improved accuracy performance on the ImageNet300k classification dataset. Our baseline networks for comparison were the original real-valued ResNet, the original quaternion-valued ResNet, and the Axial Attention ResNet. Since improvement was observed regardless of which part of the network was modified, there is a promise that this technique may be generally useful in improving classification accuracy for a large class of networks.
Citrus juices and fruits are commodities with great economic potential in the international market, but productivity losses caused by mites and other pests are still far from being a good mark. Despite the integrated pest mechanical aspect, only a few works on automatic classification have handled images with orange mite characteristics, which means tiny and noisy regions of interest. On the computational side, attention-based models have gained prominence in deep learning research, and, along with weakly supervised learning algorithms, they have improved tasks performed with some label restrictions. In agronomic research of pests and diseases, these techniques can improve classification performance while pointing out the location of mites and insects without specific labels, reducing deep learning development costs related to generating bounding boxes. In this context, this work proposes an attention-based activation map approach developed to improve the classification of tiny regions called Two-Weighted Activation Mapping, which also produces locations using feature map scores learned from class labels. We apply our method in a two-stage network process called Attention-based Multiple Instance Learning Guided by Saliency Maps. We analyze the proposed approach in two challenging datasets, the Citrus Pest Benchmark, which was captured directly in the field using magnifying glasses, and the Insect Pest, a large pest image benchmark. In addition, we evaluate and compare our models with weakly supervised methods, such as Attention-based Deep MIL and WILDCAT. The results show that our classifier is superior to literature methods that use tiny regions in their classification tasks, surpassing them in all scenarios by at least 16 percentage points. Moreover, our approach infers bounding box locations for salient insects, even training without any location labels.
Adam is applied widely to train neural networks. Different kinds of Adam methods with different features pop out. Recently two new adam optimizers, AdaBelief and Padam are introduced among the community. We analyze these two adam optimizers and compare them with other conventional optimizers (Adam, SGD + Momentum) in the scenario of image classification. We evaluate the performance of these optimization algorithms on AlexNet and simplified versions of VGGNet, ResNet using the EMNIST dataset. (Benchmark algorithm is available at \hyperref[https://github.com/chuiyunjun/projectCSC413]{https://github.com/chuiyunjun/projectCSC413}).
Signal recognition is a spectrum sensing problem that jointly requires detection, localization in time and frequency, and classification. This is a step beyond most spectrum sensing work which involves signal detection to estimate "present" or "not present" detections for either a single channel or fixed sized channels or classification which assumes a signal is present. We define the signal recognition task, present the metrics of precision and recall to the RF domain, and review recent machine-learning based approaches to this problem. We introduce a new dataset that is useful for training neural networks to perform these tasks and show a training framework to train wideband signal recognizers.
The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture in studies, or as baselines when new architectures are proposed. Yet there has been significant progress on best practices for training neural networks since the inception of the ResNet architecture in 2015. Novel optimization & data-augmentation have increased the effectiveness of the training recipes. In this paper, we re-evaluate the performance of the vanilla ResNet-50 when trained with a procedure that integrates such advances. We share competitive training settings and pre-trained models in the timm open-source library, with the hope that they will serve as better baselines for future work. For instance, with our more demanding training setting, a vanilla ResNet-50 reaches 80.4% top-1 accuracy at resolution 224x224 on ImageNet-val without extra data or distillation. We also report the performance achieved with popular models with our training procedure.
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversarially robust classifiers on simple datasets such as MNIST, but this robustness has not been observed on more complex datasets like CIFAR-10. Additionally, on natural image datasets, previous results have suggested a trade-off between the likelihood of the data and classification accuracy. In this work, we investigate score-based generative models as classifiers for natural images. We show that these models not only obtain competitive likelihood values but simultaneously achieve state-of-the-art classification accuracy for generative classifiers on CIFAR-10. Nevertheless, we find that these models are only slightly, if at all, more robust than discriminative baseline models on out-of-distribution tasks based on common image corruptions. Similarly and contrary to prior results, we find that score-based are prone to worst-case distribution shifts in the form of adversarial perturbations. Our work highlights that score-based generative models are closing the gap in classification accuracy compared to standard discriminative models. While they do not yet deliver on the promise of adversarial and out-of-domain robustness, they provide a different approach to classification that warrants further research.
In this work, we study the task of classifying legal texts written in the Greek language. We introduce and make publicly available a novel dataset based on Greek legislation, consisting of more than 47 thousand official, categorized Greek legislation resources. We experiment with this dataset and evaluate a battery of advanced methods and classifiers, ranging from traditional machine learning and RNN-based methods to state-of-the-art Transformer-based methods. We show that recurrent architectures with domain-specific word embeddings offer improved overall performance while being competitive even to transformer-based models. Finally, we show that cutting-edge multilingual and monolingual transformer-based models brawl on the top of the classifiers' ranking, making us question the necessity of training monolingual transfer learning models as a rule of thumb. To the best of our knowledge, this is the first time the task of Greek legal text classification is considered in an open research project, while also Greek is a language with very limited NLP resources in general.
We present our entry to the 2021 PhysioNet/CinC challenge - a waveform transformer model to detect cardiac abnormalities from ECG recordings. We compare the performance of the waveform transformer model on different ECG-lead subsets using approximately 88,000 ECG recordings from six datasets. In the official rankings, team prna ranked between 9 and 15 on 12, 6, 4, 3 and 2-lead sets respectively. Our waveform transformer model achieved an average challenge metric of 0.47 on the held-out test set across all ECG-lead subsets. Our combined performance across all leads placed us at rank 11 out of 39 officially ranking teams.
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence into a fixed-length speaker embedding. To adapt the framework to speaker recognition, we propose a single-utterance classification variant with CE or AAM softmax loss, and an utterance-pair classification variant with BCE loss. Our best performing variant, w2v2-aam, achieves a 1.88% EER on the extended voxceleb1 test set compared to 1.69% EER with an ECAPA-TDNN baseline. Code is available at https://github.com/nikvaessen/w2v2-speaker.
The importance of the neighborhood for training a local surrogate model to approximate the local decision boundary of a black box classifier has been already highlighted in the literature. Several attempts have been made to construct a better neighborhood for high dimensional data, like texts, by using generative autoencoders. However, existing approaches mainly generate neighbors by selecting purely at random from the latent space and struggle under the curse of dimensionality to learn a good local decision boundary. To overcome this problem, we propose a progressive approximation of the neighborhood using counterfactual instances as initial landmarks and a careful 2-stage sampling approach to refine counterfactuals and generate factuals in the neighborhood of the input instance to be explained. Our work focuses on textual data and our explanations consist of both word-level explanations from the original instance (intrinsic) and the neighborhood (extrinsic) and factual- and counterfactual-instances discovered during the neighborhood generation process that further reveal the effect of altering certain parts in the input text. Our experiments on real-world datasets demonstrate that our method outperforms the competitors in terms of usefulness and stability (for the qualitative part) and completeness, compactness and correctness (for the quantitative part).
Temporal expressions in text play a significant role in language understanding and correctly identifying them is fundamental to various retrieval and natural language processing systems. Previous works have slowly shifted from rule-based to neural architectures, capable of tagging expressions with higher accuracy. However, neural models can not yet distinguish between different expression types at the same level as their rule-based counterparts. In this work, we aim to identify the most suitable transformer architecture for joint temporal tagging and type classification, as well as, investigating the effect of semi-supervised training on the performance of these systems. Based on our study of token classification variants and encoder-decoder architectures, we present a transformer encoder-decoder model using the RoBERTa language model as our best performing system. By supplementing training resources with weakly labeled data from rule-based systems, our model surpasses previous works in temporal tagging and type classification, especially on rare classes. Our code and pre-trained experiments are available at: https://github.com/satya77/Transformer_Temporal_Tagger
Margin-based losses, especially one-class classification loss, have improved the generalization capabilities of countermeasure systems (CMs), but their reliability is not tested with spoofing attacks degraded with channel variation. Our experiments aim to tackle this in two ways: first, by investigating the impact of various codec simulations and their corresponding parameters, namely bit-rate, discontinuous transmission (DTX), and loss, on the performance of the one-class classification-based CM system; second, by testing the efficacy of the various settings of margin-based losses for training and evaluating our CM system on codec simulated data. Multi-conditional training (MCT) along with various data-feeding and custom mini-batching strategies were also explored to handle the added variability in the new data setting and to find an optimal setting to carry out the above experiments. Our experimental results reveal that a strict restrain over the embedding space degrades the performance of the one-class classification model. MCT relatively improves performance by 35.55\%, and custom mini-batching captures more generalized features for the new data setting. Whereas varying the codec parameters made a significant impact on the performance of the countermeasure system.
Support Vector Machine (SVM) is a robust machine learning model that shows high accuracy with different classification problems, and is widely used for various embedded applications. However , implementation of embedded SVM classifiers is challenging, due to the inherent complicated computations required. This motivates implementing the SVM on hardware platforms for achieving high performance computing at low cost and power consumption. Melanoma is the most aggressive form of skin cancer that increases the mortality rate. We aim to develop an optimized embedded SVM classifier dedicated for a low-cost handheld device for early detection of melanoma at the primary healthcare. In this paper, we propose a hardware/software co-design for implementing the SVM classifier onto FPGA to realize melanoma detection on a chip. The implemented SVM on a recent hybrid FPGA (Zynq) platform utilizing the modern UltraFast High-Level Synthesis design methodology achieves efficient melanoma classification on chip. The hardware implementation results demonstrate classification accuracy of 97.9%, and a significant hardware acceleration rate of 21 with only 3% resources utilization and 1.69W for power consumption. These results show that the implemented system on chip meets crucial embedded system constraints of high performance and low resources utilization, power consumption, and cost, while achieving efficient classification with high classification accuracy.
This paper introduces a study on tweet sentiment classification. Our task is to classify a tweet as either positive or negative. We approach the problem in two steps, namely embedding and classifying. Our baseline methods include several combinations of traditional embedding methods and classification algorithms. Furthermore, we explore the current state-of-the-art tweet analysis model, BERTweet, and propose a novel approach in which features are engineered from the hidden states and attention matrices of the model, inspired by empirical study of the tweets. Using a multi-layer perceptron trained with a high dropout rate for classification, our proposed approach achieves a validation accuracy of 0.9111.
Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on large data sets, due to their discrete parameters and structures. Ensemble methods and fuzzy/soft rules are commonly used to improve performance, but they sacrifice the model interpretability. To obtain both good scalability and interpretability, we propose a new classifier, named Rule-based Representation Learner (RRL), that automatically learns interpretable non-fuzzy rules for data representation and classification. To train the non-differentiable RRL effectively, we project it to a continuous space and propose a novel training method, called Gradient Grafting, that can directly optimize the discrete model using gradient descent. An improved design of logical activation functions is also devised to increase the scalability of RRL and enable it to discretize the continuous features end-to-end. Exhaustive experiments on nine small and four large data sets show that RRL outperforms the competitive interpretable approaches and can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios. Our code is available at: https://github.com/12wang3/rrl.
Machine Learning (ML) can substantially improve the efficiency and effectiveness of organizations and is widely used for different purposes within Software Engineering. However, the selection and implementation of ML techniques rely almost exclusively on accuracy criteria. Thus, for organizations wishing to realize the benefits of ML investments, this narrow approach ignores crucial considerations around the anticipated costs of the ML activities across the ML lifecycle, while failing to account for the benefits that are likely to accrue from the proposed activity. We present findings for an approach that addresses this gap by enhancing the accuracy criterion with return on investment (ROI) considerations. Specifically, we analyze the performance of the two state-of-the-art ML techniques: Random Forest and Bidirectional Encoder Representations from Transformers (BERT), based on accuracy and ROI for two publicly available data sets. Specifically, we compare decision-making on requirements dependency extraction (i) exclusively based on accuracy and (ii) extended to include ROI analysis. As a result, we propose recommendations for selecting ML classification techniques based on the degree of training data used. Our findings indicate that considering ROI as additional criteria can drastically influence ML selection when compared to decisions based on accuracy as the sole criterion