Breaking of brightness consistency in optical flow with a lightweight CNN network

Sparse optical flow is widely used in various computer vision tasks, however assuming brightness consistency limits its performance in High Dynamic Range (HDR) environments. In this work, a lightweight network is used to extract illumination robust convolutional features and corners with strong invariance. Modifying the typical brightness consistency of the optical flow method to the convolutional feature consistency yields the light-robust hybrid optical flow method. The proposed network runs at 190 FPS on a commercial CPU because it uses only four convolutional layers to extract feature maps and score maps simultaneously. Since the shallow network is difficult to train directly, a deep network is designed to compute the reliability map that helps it. An end-to-end unsupervised training mode is used for both networks. To validate the proposed method, we compare corner repeatability and matching performance with origin optical flow under dynamic illumination. In addition, a more accurate visual inertial system is constructed by replacing the optical flow method in VINS-Mono. In a public HDR dataset, it reduces translation errors by 93\%. The code is publicly available at https://github.com/linyicheng1/LET-NET.

Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology

An invasive species of grass known as "buffelgrass" contributes to severe wildfires and biodiversity loss in the Southwest United States. We tackle the problem of predicting buffelgrass "green-ups" (i.e. readiness for herbicidal treatment). To make our predictions, we explore temporal, visual and multi-modal models that combine satellite sensing and deep learning. We find that all of our neural-based approaches improve over conventional buffelgrass green-up models, and discuss how neural model deployment promises significant resource savings.

A Reliable and Resilient Framework for Multi-UAV Mutual Localization

This paper presents a robust and secure framework for achieving accurate and reliable mutual localization in multiple unmanned aerial vehicle (UAV) systems. Challenges of accurate localization and security threats are addressed and corresponding solutions are brought forth and accessed in our paper with numerical simulations. The proposed solution incorporates two key components: the Mobility Adaptive Gradient Descent (MAGD) and Time-evolving Anomaly Detectio (TAD). The MAGD adapts the gradient descent algorithm to handle the configuration changes in the mutual localization system, ensuring accurate localization in dynamic scenarios. The TAD cooperates with reputation propagation (RP) scheme to detect and mitigate potential attacks by identifying UAVs with malicious data, enhancing the security and resilience of the mutual localization

Terahertz Communications and Sensing for 6G and Beyond: A Comprehensive View

The next-generation wireless technologies, commonly referred to as the sixth generation (6G), are envisioned to support extreme communications capacity and in particular disruption in the network sensing capabilities. The terahertz (THz) band is one potential enabler for those due to the enormous unused frequency bands and the high spatial resolution enabled by both short wavelengths and bandwidths. Different from earlier surveys, this paper presents a comprehensive treatment and technology survey on THz communications and sensing in terms of the advantages, applications, propagation characterization, channel modeling, measurement campaigns, antennas, transceiver devices, beamforming, networking, the integration of communications and sensing, and experimental testbeds. Starting from the motivation and use cases, we survey the development and historical perspective of THz communications and sensing with the anticipated 6G requirements. We explore the radio propagation, channel modeling, and measurements for THz band. The transceiver requirements, architectures, technological challenges, and approaches together with means to compensate for the high propagation losses by appropriate antenna and beamforming solutions. We survey also several system technologies required by or beneficial for THz systems. The synergistic design of sensing and communications is explored with depth. Practical trials, demonstrations, and experiments are also summarized. The paper gives a holistic view of the current state of the art and highlights the issues and challenges that are open for further research towards 6G.

KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation

In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the advantage of analyzing documents to extract meaningful patterns of words without the need of pretraining. To leverage topic modeling's unsupervised insights extraction on text classification tasks, we develop the Knowledge Distillation Semi-supervised Topic Modeling (KDSTM). KDSTM requires no pretrained embeddings, few labeled documents and is efficient to train, making it ideal under resource constrained settings. Across a variety of datasets, our method outperforms existing supervised topic modeling methods in classification accuracy, robustness and efficiency and achieves similar performance compare to state of the art weakly supervised text classification methods.

Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning

Social determinants of health (SDOH) documented in the electronic health record through unstructured text are increasingly being studied to understand how SDOH impacts patient health outcomes. In this work, we utilize the Social History Annotation Corpus (SHAC), a multi-institutional corpus of de-identified social history sections annotated for SDOH, including substance use, employment, and living status information. We explore the automatic extraction of SDOH information with SHAC in both standoff and inline annotation formats using GPT-4 in a one-shot prompting setting. We compare GPT-4 extraction performance with a high-performing supervised approach and perform thorough error analyses. Our prompt-based GPT-4 method achieved an overall 0.652 F1 on the SHAC test set, similar to the 7th best-performing system among all teams in the n2c2 challenge with SHAC.

Urban Spatiotemporal Data Synthesis via Neural Disaggregation

The level of granularity of open data often conflicts the benefits it can provide. Less granular data can protect individual privacy, but to certain degrees, sabotage the promise of open data to promote transparency and assist research. Similar in the urban setting, aggregated urban data at high-level geographic units can mask out the underline particularities of city dynamics that may vary at lower areal levels. In this work, we aim to synthesize fine-grained, high resolution urban data, by breaking down aggregated urban data at coarse, low resolution geographic units. The goal is to increase the usability and realize the values as much as possible of highly aggregated urban data. To address the issue of simplicity of some traditional disaggregation methods -- 1) we experimented with numerous neural-based models that are capable of modeling intricate non-linear relationships among features. Neural methods can also leverage both spatial and temporal information concurrently. We showed that all neural methods perform better than traditional disaggregation methods. Incorporating the temporal information further enhances the results. 2) We proposed a training approach for disaggregation task, Chain-of-Training (COT), that can be incorporated into any of the training-based models. COT adds transitional disaggregation steps by incorporating intermediate geographic dimensions, which enhances the predictions at low geographic level and boosts the results at higher levels. 3) We adapted the idea of reconstruction (REC) from super-resolution domain in our disaggregation case -- after disaggregating from low to high geographic level, we then re-aggregate back to the low level from our generated high level values. Both strategies improved disaggregation results on three datasets and two cities we tested on.

A Secure and Robust Approach for Distance-Based Mutual Positioning of Unmanned Aerial Vehicles

Unmanned aerial vehicle (UAV) is becoming increasingly important in modern civilian and military applications. However, its novel use cases is bottlenecked by conventional satellite and terrestrial localization technologies, and calling for complementary solutions. Multi-UAV mutual positioning can be a potential answer, but its accuracy and security are challenged by inaccurate and/or malicious measurements. This paper proposes a novel, robust, and secure approach to address these issues.

LeafAI: query generator for clinical cohort discovery rivaling a human programmer

Objective: Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. Materials and Methods: The task of query creation from eligibility criteria requires solving several text-processing problems, including named entity recognition and relation extraction, sequence-to-sequence transformation, normalization, and reasoning. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologies. To enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability of LeafAI to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. Results: LeafAI matched a mean 43% of enrolled patients with 27,225 eligible across 8 clinical trials, compared to 27% matched and 14,587 eligible in queries by a human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Conclusions: Our work contributes a state-of-the-art data model-agnostic query generation system capable of conditional reasoning using a knowledge base. We demonstrate that LeafAI can rival a human programmer in finding patients eligible for clinical trials.

Adapting to Skew: Imputing Spatiotemporal Urban Data with 3D Partial Convolutions and Biased Masking

We adapt image inpainting techniques to impute large, irregular missing regions in urban settings characterized by sparsity, variance in both space and time, and anomalous events. Missing regions in urban data can be caused by sensor or software failures, data quality issues, interference from weather events, incomplete data collection, or varying data use regulations; any missing data can render the entire dataset unusable for downstream applications. To ensure coverage and utility, we adapt computer vision techniques for image inpainting to operate on 3D histograms (2D space + 1D time) commonly used for data exchange in urban settings. Adapting these techniques to the spatiotemporal setting requires handling skew: urban data tend to follow population density patterns (small dense regions surrounded by large sparse areas); these patterns can dominate the learning process and fool the model into ignoring local or transient effects. To combat skew, we 1) train simultaneously in space and time, and 2) focus attention on dense regions by biasing the masks used for training to the skew in the data. We evaluate the core model and these two extensions using the NYC taxi data and the NYC bikeshare data, simulating different conditions for missing data. We show that the core model is effective qualitatively and quantitatively, and that biased masking during training reduces error in a variety of scenarios. We also articulate a tradeoff in varying the number of timesteps per training sample: too few timesteps and the model ignores transient events; too many timesteps and the model is slow to train with limited performance gain.