ApproxNet: Content and Contention-Aware Video Object Classification System for Embedded Clients

Videos take a lot of time to transport over the network, hence running analytics on the live video on embedded or mobile devices has become an important system driver. Considering such devices, e.g., surveillance cameras or AR/VR gadgets, are resource constrained, although there has been significant work in creating lightweight deep neural networks (DNNs) for such clients, none of these can adapt to changing runtime conditions, e.g., changes in resource availability on the device, the content characteristics, or requirements from the user. In this article, we introduce ApproxNet, a video object classification system for embedded or mobile clients. It enables novel dynamic approximation techniques to achieve desired inference latency and accuracy trade-off under changing runtime conditions. It achieves this by enabling two approximation knobs within a single DNN model rather than creating and maintaining an ensemble of models, e.g., MCDNN [MobiSys-16]. We show that ApproxNet can adapt seamlessly at runtime to these changes, provides low and stable latency for the image and video frame classification problems, and shows the improvement in accuracy and latency over ResNet [CVPR-16], MCDNN [MobiSys-16], MobileNets [Google-17], NestDNN [MobiCom-18], and MSDNet [ICLR-18].

Cross-Modality Transfer Learning for Image-Text Information Management

In the past decades, information from all kinds of data has been on a rapid increase. With state-of-the-art performance, machine learning algorithms have been beneficial for information management. However, insufficient supervised training data is still an adversity in many real-world applications. Therefore, transfer learning (TF) was proposed to address this issue. This article studies a not well investigated but important TL problem termed cross-modality transfer learning (CMTL). This topic is closely related to distant domain transfer learning (DDTL) and negative transfer. In general, conventional TL disciplines assume that the source domain and the target domain are in the same modality. DDTL aims to make efficient transfers even when the domains or the tasks are entirely different. As an extension of DDTL, CMTL aims to make efficient transfers between two different data modalities, such as from image to text. As the main focus of this study, we aim to improve the performance of image classification by transferring knowledge from text data. Previously, a few CMTL algorithms were proposed to deal with image classification problems. However, most existing algorithms are very task specific, and they are unstable on convergence. There are four main contributions in this study. First, we propose a novel heterogeneous CMTL algorithm, which requires only a tiny set of unlabeled target data and labeled source data with associate text tags. Second, we introduce a latent semantic information extraction method to connect the information learned from the image data and the text data. Third, the proposed method can effectively handle the information transfer across different modalities (text-image). Fourth, we examined our algorithm on a public dataset, Office-31. It has achieved up to 5% higher classification accuracy than “non-transfer” algorithms and up to 9% higher than existing CMTL algorithms.

Differentially Private Medical Texts Generation Using Generative Neural Networks

Technological advancements in data science have offered us affordable storage and efficient algorithms to query a large volume of data. Our health records are a significant part of this data, which is pivotal for healthcare providers and can be utilized in our well-being. The clinical note in electronic health records is one such category that collects a patient’s complete medical information during different timesteps of patient care available in the form of free-texts. Thus, these unstructured textual notes contain events from a patient’s admission to discharge, which can prove to be significant for future medical decisions. However, since these texts also contain sensitive information about the patient and the attending medical professionals, such notes cannot be shared publicly. This privacy issue has thwarted timely discoveries on this plethora of untapped information. Therefore, in this work, we intend to generate synthetic medical texts from a private or sanitized (de-identified) clinical text corpus and analyze their utility rigorously in different metrics and levels. Experimental results promote the applicability of our generated data as it achieves more than 80\% accuracy in different pragmatic classification problems and matches (or outperforms) the original text data.

A semi-supervised Bayesian mixture modelling approach for joint batch correction and classification

Systematic differences between batches of samples present significant challenges when analysing biological data. Such batch effects are well-studied and are liable to occur in any setting where multiple batches are assayed. Many existing methods for accounting for these have focused on high-dimensional data such as RNA-seq and have assumptions that reflect this. Here we focus on batch-correction in low-dimensional classification problems. We propose a semi-supervised Bayesian generative classifier based on mixture models that jointly predicts class labels and models batch effects. Our model allows observations to be probabilistically assigned to classes in a way that incorporates uncertainty arising from batch effects. We explore two choices for the within-class densities: the multivariate normal and the multivariate t. A simulation study demonstrates that our method performs well compared to popular off-the-shelf machine learning methods and is also quick; performing 15,000 iterations on a dataset of 500 samples with 2 measurements each in 7.3 seconds for the MVN mixture model and 11.9 seconds for the MVT mixture model. We apply our model to two datasets generated using the enzyme-linked immunosorbent assay (ELISA), a spectrophotometric assay often used to screen for antibodies. The examples we consider were collected in 2020 and measure seropositivity for SARS-CoV-2. We use our model to estimate seroprevalence in the populations studied. We implement the models in C++ using a Metropolis-within-Gibbs algorithm; this is available in the R package at https://github.com/stcolema/BatchMixtureModel. Scripts to recreate our analysis are at https://github.com/stcolema/BatchClassifierPaper.

An Empirical Comparison of Portuguese and Multilingual BERT Models for Auto-Classification of NCM Codes in International Trade

Classification problems are common activities in many different domains and supervised learning algorithms have shown great promise in these areas. The classification of goods in international trade in Brazil represents a real challenge due to the complexity involved in assigning the correct category codes to a good, especially considering the tax penalties and legal implications of a misclassification. This work focuses on the training process of a classifier based on bidirectional encoder representations from transformers (BERT) for tax classification of goods with MCN codes which are the official classification system for import and export products in Brazil. In particular, this article presents results from using a specific Portuguese-language-pretrained BERT model, as well as results from using a multilingual-pretrained BERT model. Experimental results show that Portuguese model had a slightly better performance than the multilingual model, achieving an MCC 0.8491, and confirms that the classifiers could be used to improve specialists’ performance in the classification of goods.

Intuitionistic fuzzy-valued neutrosophic multi-sets and numerical applications to classification

A single-valued neutrosophic multi-set is characterized by a sequence of truth membership degrees, a sequence of indeterminacy membership degrees and a sequence of falsity membership degrees. Nature of a single-valued neutrosophic multi-set allows us to consider multiple information in the truth, indeterminacy and falsity memberships which is pretty useful in multi-criteria group decision making. In this paper, we consider sequences of intuitionistic fuzzy values instead of numbers to define the concept of intuitionistic fuzzy-valued neutrosophic multi-set. In this manner, such a set gives more powerful information. We also present some set theoretic operations and a partial order for intuitionistic fuzzy-valued neutrosophic sets and provide some algebraic operations between intuitionistic fuzzy-valued neutrosophic values. Then, we develop two types of weighted aggregation operators with the help of intuitionistic fuzzy t-norms and t-conorms. By considering some well-known additive generators of ordinary t-norms, we give the Algebraic weighted arithmetic and geometric aggregation operators and the Einstein weighted arithmetic and geometric aggregation operators that are the particular cases of the weighted aggregation operators defined via general t-norms and t-conorms. We also define a simplified neutrosophic valued similarity measure and we use a score function for simplified neutrosophic values to rank similarities of intuitionistic fuzzy-valued neutrosophic multi-values. Finally, we give an algorithm to solve classification problems using intuitionistic fuzzy-valued neutrosophic multi-values and proposed aggregation operators and we apply the theoretical part of the paper to a real classification problem.

Meta-Heuristic Parameter Optimization for ANN and Real-Time Applications of ANN

Artificial neural networks (ANN) are often more suitable for classification problems. Even then, training of ANN is a surviving challenge task for large and high dimensional natured search space problems. These hitches are more for applications that involves process of fine tuning of ANN control parameters: weights and bias. There is no single search and optimization method that suits the weights and bias of ANN for all the problems. The traditional heuristic approach fails because of their poorer convergence speed and chances of ending up with local optima. In this connection, the meta-heuristic algorithms prove to provide consistent solution for optimizing ANN training parameters. This chapter will provide critics on both heuristics and meta-heuristic existing literature for training neural networks algorithms, applicability, and reliability on parameter optimization. In addition, the real-time applications of ANN will be presented. Finally, future directions to be explored in the field of ANN are presented which will of potential interest for upcoming researchers.

Multiple graph fusion based on Riemannian geometry for motor imagery classification

In motor imagery-based brain-computer interfaces (BCIs), the spatial covariance features of electroencephalography (EEG) signals that lie on Riemannian manifolds are used to enhance the classification performance of motor imagery BCIs. However, the problem of subject-specific bandpass frequency selection frequently arises in Riemannian manifold-based methods. In this study, we propose a multiple Riemannian graph fusion (MRGF) model to optimize the subject-specific frequency band for a Riemannian manifold. After constructing multiple Riemannian graphs corresponding to multiple bandpass frequency bands, graph embedding based on bilinear mapping and graph fusion based on mutual information were applied to simultaneously extract the spatial and spectral features of the EEG signals from Riemannian graphs. Furthermore, with a support vector machine (SVM) classifier performed on learned features, we obtained an efficient algorithm, which achieves higher classification performance on various datasets, such as BCI competition IIa and in-house BCI datasets. The proposed methods can also be used in other classification problems with sample data in the form of covariance matrices.