DeFFusion: CNN-based Continuous Authentication Using Deep Feature Fusion

Smartphones have become crucial and important in our daily life, but the security and privacy issues have been major concerns of smartphone users. In this article, we present DeFFusion, a CNN-based continuous authentication system using Deep Feature Fusion for smartphone users by leveraging the accelerometer and gyroscope ubiquitously built into smartphones. With the collected data, DeFFusion first converts the time domain data into frequency domain data using the fast Fourier transform and then inputs both of them into a designed CNN, respectively. With the CNN-extracted features, DeFFusion conducts the feature selection utilizing factor analysis and exploits balanced feature concatenation to fuse these deep features. Based on the one-class SVM classifier, DeFFusion authenticates current users as a legitimate user or an impostor. We evaluate the authentication performance of DeFFusion in terms of impact of training data size and time window size, accuracy comparison on different features over different classifiers and on different classifiers with the same CNN-extracted features, accuracy on unseen users, time efficiency, and comparison with representative authentication methods. The experimental results demonstrate that DeFFusion has the best accuracy by achieving the mean equal error rate of 1.00% in a 5-second time window size.

A Statistical Language Model for Pre-Trained Sequence Labeling: A Case Study on Vietnamese

By defining the computable word segmentation unit and studying its probability characteristics, we establish an unsupervised statistical language model (SLM) for a new pre-trained sequence labeling framework in this article. The proposed SLM is an optimization model, and its objective is to maximize the total binding force of all candidate word segmentation units in sentences under the condition of no annotated datasets and vocabularies. To solve SLM, we design a recursive divide-and-conquer dynamic programming algorithm. By integrating SLM with the popular sequence labeling models, Vietnamese word segmentation, part-of-speech tagging and named entity recognition experiments are performed. The experimental results show that our SLM can effectively promote the performance of sequence labeling tasks. Just using less than 10% of training data and without using a dictionary, the performance of our sequence labeling framework is better than the state-of-the-art Vietnamese word segmentation toolkit VnCoreNLP on the cross-dataset test. SLM has no hyper-parameter to be tuned, and it is completely unsupervised and applicable to any other analytic language. Thus, it has good domain adaptability.

One-Shot Relation Learning for Knowledge Graphs via Neighborhood Aggregation and Paths Encoding

The relation learning between two entities is an essential task in knowledge graph (KG) completion that has received much attention recently. Previous work almost exclusively focused on relations widely seen in the original KGs, which means that enough training data are available for modeling. However, long-tail relations that only show in a few triples are actually much more common in practical KGs. Without sufficiently large training data, the performance of existing models on predicting long-tail relations drops impressively. This work aims to predict the relation under a challenging setting where only one instance is available for training. We propose a path-based one-shot relation prediction framework, which can extract neighborhood information of an entity based on the relation query attention mechanism to learn transferable knowledge among the same relation. Simultaneously, to reduce the impact of long-tail entities on relation prediction, we selectively fuse path information between entity pairs as auxiliary information of relation features. Experiments in three one-shot relation learning datasets show that our proposed framework substantially outperforms existing models on one-shot link prediction and relation prediction.

Combining Self-supervised Learning and Active Learning for Disfluency Detection

Spoken language is fundamentally different from the written language in that it contains frequent disfluencies or parts of an utterance that are corrected by the speaker. Disfluency detection (removing these disfluencies) is desirable to clean the input for use in downstream NLP tasks. Most existing approaches to disfluency detection heavily rely on human-annotated data, which is scarce and expensive to obtain in practice. To tackle the training data bottleneck, in this work, we investigate methods for combining self-supervised learning and active learning for disfluency detection. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled data and propose two self-supervised pre-training tasks: (i) a tagging task to detect the added noisy words and (ii) sentence classification to distinguish original sentences from grammatically incorrect sentences. We then combine these two tasks to jointly pre-train a neural network. The pre-trained neural network is then fine-tuned using human-annotated disfluency detection training data. The self-supervised learning method can capture task-special knowledge for disfluency detection and achieve better performance when fine-tuning on a small annotated dataset compared to other supervised methods. However, limited in that the pseudo training data are generated based on simple heuristics and cannot fully cover all the disfluency patterns, there is still a performance gap compared to the supervised models trained on the full training dataset. We further explore how to bridge the performance gap by integrating active learning during the fine-tuning process. Active learning strives to reduce annotation costs by choosing the most critical examples to label and can address the weakness of self-supervised learning with a small annotated dataset. We show that by combining self-supervised learning with active learning, our model is able to match state-of-the-art performance with just about 10% of the original training data on both the commonly used English Switchboard test set and a set of in-house annotated Chinese data.

A Comparative Study of Energy Big Data Analysis for Product Management in a Smart Factory

Energy has been obtained as one of the key inputs for a country's economic growth and social development. Analysis and modeling of industrial energy are currently a time-insertion process because more and more energy is consumed for economic growth in a smart factory. This study aims to present and analyse the predictive models of the data-driven system to be used by appliances and find out the most significant product item. With repeated cross-validation, three statistical models were trained and tested in a test set: 1) General Linear Regression Model (GLM), 2) Support Vector Machine (SVM), and 3) boosting Tree (BT). The performance of prediction models measured by R2 error, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Variation (CV). The best model from the study is the Support Vector Machine (SVM) that has been able to provide R2 of 0.86 for the training data set and 0.85 for the testing data set with a low coefficient of variation, and the most significant product of this smart factory is Skelp.

Memorizing All for Implicit Discourse Relation Recognition

Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clues from explicit connectives. An implicit discourse relation recognizer has to carefully tackle the semantic similarity of sentence pairs and the severe data sparsity issue. In this article, we learn token embeddings to encode the structure of a sentence from a dependency point of view in their representations and use them to initialize a baseline model to make it really strong. Then, we propose a novel memory component to tackle the data sparsity issue by allowing the model to master the entire training set, which helps in achieving further performance improvement. The memory mechanism adequately memorizes information by pairing representations and discourse relations of all training instances, thus filling the slot of the data-hungry issue in the current implicit discourse relation recognizer. The proposed memory component, if attached with any suitable baseline, can help in performance enhancement. The experiments show that our full model with memorizing the entire training data provides excellent results on PDTB and CDTB datasets, outperforming the baselines by a fair margin.

Leveraging Automatic High-Level Synthesis Resource Sharing to Maximize Dynamical Voltage Overscaling with Error Control

Approximate Computing has emerged as an alternative way to further reduce the power consumption of integrated circuits (ICs) by trading off errors at the output with simpler, more efficient logic. So far the main approaches in approximate computing have been to simplify the hardware circuit by pruning the circuit until the maximum error threshold is met. One of the critical issues, though, is the training data used to prune the circuit. The output error can significantly exceed the maximum error if the final workload does not match the training data. Thus, most previous work typically assumes that training data matches with the workload data distribution. In this work, we present a method that dynamically overscales the supply voltage based on different workload distribution at runtime. This allows to adaptively select the supply voltage that leads to the largest power savings while ensuring that the error will never exceed the maximum error threshold. This approach also allows restoring of the original error-free circuit if no matching workload distribution is found. The proposed method also leverages the ability of High-Level Synthesis (HLS) to automatically generate circuits with different properties by setting different synthesis constraints to maximize the available timing slack and, hence, maximize the power savings. Experimental results show that our proposed method works very well, saving on average 47.08% of power as compared to the exact output circuit and 20.25% more than a traditional approximation method.

COVID-GAN+: Estimating Human Mobility Responses to COVID-19 through Spatio-temporal Generative Adversarial Networks with Enhanced Features

Estimating human mobility responses to the large-scale spreading of the COVID-19 pandemic is crucial, since its significance guides policymakers to give Non-pharmaceutical Interventions, such as closure or reopening of businesses. It is challenging to model due to complex social contexts and limited training data. Recently, we proposed a conditional generative adversarial network (COVID-GAN) to estimate human mobility response under a set of social and policy conditions integrated from multiple data sources. Although COVID-GAN achieves a good average estimation accuracy under real-world conditions, it produces higher errors in certain regions due to the presence of spatial heterogeneity and outliers. To address these issues, in this article, we extend our prior work by introducing a new spatio-temporal deep generative model, namely, COVID-GAN+. COVID-GAN+ deals with the spatial heterogeneity issue by introducing a new spatial feature layer that utilizes the local Moran statistic to model the spatial heterogeneity strength in the data. In addition, we redesign the training objective to learn the estimated mobility changes from historical average levels to mitigate the effects of spatial outliers. We perform comprehensive evaluations using urban mobility data derived from cell phone records and census data. Results show that COVID-GAN+ can better approximate real-world human mobility responses than prior methods, including COVID-GAN.

GaitSense: Towards Ubiquitous Gait-Based Human Identification with Wi-Fi

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi-based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectories, sufficient training data, and identification of already known users. In this article, we present GaitSense , a Wi-Fi-based human identification system, to overcome the above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitSense first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitSense reduces the training efforts in new deployment scenarios by transfer learning and data augmentation techniques. GaitSense also enables a distinct feature of illegal user identification by anomaly detection, making the system readily available for real-world deployment. Our implementation and evaluation with commodity Wi-Fi devices demonstrate a consistent identification accuracy across various deployment scenarios with little training samples, pushing the limit of gait recognition with Wi-Fi signals.

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.