F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement

With the increasing demand for audio communication and online conference, ensuring the robustness of Acoustic Echo Cancellation (AEC) under the complicated acoustic scenario including noise, reverberation and nonlinear distortion has become a top issue. Although there have been some traditional methods that consider nonlinear distortion, they are still inefficient for echo suppression and the performance will be attenuated when noise is present. In this paper, we present a real-time AEC approach using complex neural network to better modeling the important phase information and frequency-time-LSTMs (F-T-LSTM), which scan both frequency and time axis, for better temporal modeling. Moreover, we utilize modified SI-SNR as cost function to make the model to have better echo cancellation and noise suppression (NS) performance. With only 1.4M parameters, the proposed approach outperforms the AEC-challenge baseline by 0.27 in terms of Mean Opinion Score (MOS).

Attitude Reconstruction from Inertial Measurement: Mitigating Runge Effect for Dynamic Applications

Time-equispaced inertial measurements are practically used as inputs for motion determination. Polynomial interpolation is a common technique of recovering the gyroscope signal but is subject to a fundamentally numerical stability problem due to the Runge effect on equispaced samples. This paper reviews the theoretical results of Runge phenomenon in related areas and proposes a straightforward borrowing-and-cutting (BAC) strategy to depress it. It employs the neighboring samples for higher-order polynomial interpolation but only uses the middle polynomial segment in the actual time interval. The BAC strategy has been incorporated into attitude computation by functional iteration, leading to accuracy benefit of several orders of magnitude under the classical coning motion. It would potentially bring significant benefits to the inertial navigation computation under sustained dynamic motions.

Text analysis and deep learning: A network approach

Much information available to applied researchers is contained within written language or spoken text. Deep language models such as BERT have achieved unprecedented success in many applications of computational linguistics. However, much less is known about how these models can be used to analyze existing text. We propose a novel method that combines transformer models with network analysis to form a self-referential representation of language use within a corpus of interest. Our approach produces linguistic relations strongly consistent with the underlying model as well as mathematically well-defined operations on them, while reducing the amount of discretionary choices of representation and distance measures. It represents, to the best of our knowledge, the first unsupervised method to extract semantic networks directly from deep language models. We illustrate our approach in a semantic analysis of the term "founder". Using the entire corpus of Harvard Business Review from 1980 to 2020, we find that ties in our network track the semantics of discourse over time, and across contexts, identifying and relating clusters of semantic and syntactic relations. Finally, we discuss how this method can also complement and inform analyses of the behavior of deep learning models.

Fast Projection onto the Capped Simplex withApplications to Sparse Regression in Bioinformatics

We consider the problem of projecting a vector onto the so-called k-capped simplex, which is a hyper-cube cut by a hyperplane. For an n-dimensional input vector with bounded elements, we found that a simple algorithm based on Newton's method is able to solve the projection problem to high precision with a complexity roughly about O(n), which has a much lower computational cost compared with the existing sorting-based methods proposed in the literature. We provide a theory for partial explanation and justification of the method. We demonstrate that the proposed algorithm can produce a solution of the projection problem with high precision on large scale datasets, and the algorithm is able to significantly outperform the state-of-the-art methods in terms of runtime (about 6-8 times faster than a commercial software with respect to CPU time for input vector with 1 million variables or more). We further illustrate the effectiveness of the proposed algorithm on solving sparse regression in a bioinformatics problem. Empirical results on the GWAS dataset (with 1,500,000 single-nucleotide polymorphisms) show that, when using the proposed method to accelerate the Projected Quasi-Newton (PQN) method, the accelerated PQN algorithm is able to handle huge-scale regression problem and it is more efficient (about 3-6 times faster) than the current state-of-the-art methods.

An Open Access Dataset of Tweets related to Exoskeletons and 100 Research Questions

The exoskeleton technology has been rapidly advancing in the recent past due to its multitude of applications in assisted living, military, healthcare, firefighting, and industries. With the projected increase in the diverse uses of exoskeletons in the next few years in these application domains and beyond, it is crucial to study, interpret, and analyze user perspectives, public opinion, reviews, and feedback related to exoskeletons, for which a comprehensive dataset is necessary. The Internet of Everything (IOE) era of today's living, characterized by people spending more time on the Internet than ever before, holds the potential for developing such a dataset by the mining of relevant web behavior data from social media communications, which have increased exponentially in the last few years. Twitter, one such social media platform, is highly popular amongst all age groups, who communicate on diverse topics including but not limited to news, current events, politics, emerging technologies, family, relationships, and career opportunities, via tweets, while sharing their views, opinions, perspectives, and feedback towards the same. To address this research challenge by utilizing the potential of the IOE style of living, this paper makes multiple scientific contributions to this field. First, it presents a novel approach of mining tweets that is not bound by any restrictions on the number of days during which the tweets can be mined. Second, by application of this approach, it presents an open-access dataset of approximately 20,000 tweets related to exoskeletons, that were posted over a period of 231 days. Finally, based on an exploratory review of 108 emerging works in this field and its interrelated disciplines, the paper discusses multiple interdisciplinary applications of this dataset and presents 100 research questions for researchers to study, analyze, evaluate, and investigate.

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently, as it could be beneficial for various label-scarce real-world scenarios (e.g., robot control, autonomous driving, medical imaging, etc.). Despite the significant progress in this field, current works mainly focus on a single-source single-target setting, which cannot handle more practical settings of multiple targets or even unseen targets. In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. We present a novel framework based on three main design principles: discover, hallucinate, and adapt. The scheme first clusters compound target data based on style, discovering multiple latent domains (discover). Then, it hallucinates multiple latent target domains in source by using image-translation (hallucinate). This step ensures the latent domains in the source and the target to be paired. Finally, target-to-source alignment is learned separately between domains (adapt). In high-level, our solution replaces a hard OCDA problem with much easier multiple UDA problems. We evaluate our solution on standard benchmark GTA to C-driving, and achieved new state-of-the-art results.

Understanding the merging behavior patterns and evolutionary mechanism at freeway on-ramps

Understanding the merging behavior patterns at freeway on-ramps is important for assistanting the decisions of autonomous driving. This study develops a primitive-based framework to identify the driving patterns during merging processes and reveal the evolutionary mechanism at freeway on-ramps in congested traffic flow. The Nonhomogeneous Hidden Markov Model is introduced to decompose the merging processes into primitives containing semantic information. Then, the time-series K-means clustering is utilized to gather these primitives with variable-length time series into interpretable merging behavior patterns. Different from traditional state segmentation methods (e.g. Hidden Markov Model), the model proposed in this study considers the dependence of transition probability on exogenous variables, thereby revealing the influence of covariates on the evolution of driving patterns. This approach is evaluated in the merging area at a freeway on-ramp using the INTERACTION dataset. Results demonstrate that the approach provides an insight about the complicated merging processes. The findings about interpretable merging behavior patterns as well as the evolutionary mechanism can be used to design and improve the merging decision-making for autonomous vehicles.

Confidence-Aware Active Feedback for Efficient Instance Search

Relevance feedback is widely used in instance search (INS) tasks to further refine imperfect ranking results, but it often comes with low interaction efficiency. Active learning (AL) technique has achieved great success in improving annotation efficiency in classification tasks. However, considering irrelevant samples' diversity and class imbalance in INS tasks, existing AL methods cannot always select the most suitable feedback candidates for INS problems. In addition, they are often too computationally complex to be applied in interactive INS scenario. To address the above problems, we propose a confidence-aware active feedback (CAAF) method that can efficiently select the most valuable feedback candidates to improve the re-ranking performance. Specifically, inspired by the explicit sample difficulty modeling in self-paced learning, we utilize a pairwise manifold ranking loss to evaluate the ranking confidence of each unlabeled sample, and formulate the INS process as a confidence-weighted manifold ranking problem. Furthermore, we introduce an approximate optimization scheme to simplify the solution from QP problems with constraints to closed-form expressions, and selects only the top-K samples in the initial ranking list for INS, so that CAAF is able to handle large-scale INS tasks in a short period of time. Extensive experiments on both image and video INS tasks demonstrate the effectiveness of the proposed CAAF method. In particular, CAAF outperforms the first-place record in the public large-scale video INS evaluation of TRECVID 2021.

ViT Cane: Visual Assistant for the Visually Impaired

Blind and visually challenged face multiple issues with navigating the world independently. Some of these challenges include finding the shortest path to a destination and detecting obstacles from a distance. To tackle this issue, this paper proposes ViT Cane, which leverages a vision transformer model in order to detect obstacles in real-time. Our entire system consists of a Pi Camera Module v2, Raspberry Pi 4B with 8GB Ram and 4 motors. Based on tactile input using the 4 motors, the obstacle detection model is highly efficient in helping visually impaired navigate unknown terrain and is designed to be easily reproduced. The paper discusses the utility of a Visual Transformer model in comparison to other CNN based models for this specific application. Through rigorous testing, the proposed obstacle detection model has achieved higher performance on the Common Object in Context (COCO) data set than its CNN counterpart. Comprehensive field tests were conducted to verify the effectiveness of our system for holistic indoor understanding and obstacle avoidance.

An algorithm for a fairer and better voting system

The major finding, of this article, is an ensemble method, but more exactly, a novel, better ranked voting system (and other variations of it), that aims to solve the problem of finding the best candidate to represent the voters. We have the source code on GitHub, for making realistic simulations of elections, based on artificial intelligence for comparing different variations of the algorithm, and other already known algorithms. We have convincing evidence that our algorithm is better than Instant-Runoff Voting, Preferential Block Voting, Single Transferable Vote, and First Past The Post (if certain, natural conditions are met, to support the wisdom of the crowds). By also comparing with the best voter, we demonstrated the wisdom of the crowds, suggesting that democracy (distributed system) is a better option than dictatorship (centralized system), if those certain, natural conditions are met. Voting systems are not restricted to politics, they are ensemble methods for artificial intelligence, but the context of this article is natural intelligence. It is important to find a system that is fair (e.g. freedom of expression on the ballot exists), especially when the outcome of the voting system has social impact: some voting systems have the unfair inevitability to trend (over time) towards the same two major candidates (Duverger's law).