Search for: All records

Accurate instrument segmentation in the endoscopic vision of minimally invasive surgery is challenging due to complex instruments and environments. Deep learning techniques have shown competitive performance in recent years. However, deep learning usually requires a large amount of labeled data to achieve accurate prediction, which poses a significant workload. To alleviate this workload, we propose an active learning-based framework to generate synthetic images for efficient neural network training. In each active learning iteration, a small number of informative unlabeled images are first queried by active learning and manually labeled. Next, synthetic images are generated based on these selected images. The instruments and backgrounds are cropped out and randomly combined with blending and fusion near the boundary. The proposed method leverages the advantage of both active learning and synthetic images. The effectiveness of the proposed method is validated on two sinus surgery datasets and one intraabdominal surgery dataset. The results indicate a considerable performance improvement, especially when the size of the annotated dataset is small. All the code is open-sourced at: https://github.com/HaonanPeng/active_syn_generator 

We present ResilienC, a framework for resilient control of Cyber- Physical Systems subject to STL-based requirements. ResilienC uti- lizes a recently developed formalism for specifying CPS resiliency in terms of sets of (rec,dur) real-valued pairs, where rec repre- sents the system’s capability to rapidly recover from a property violation (recoverability), and dur is reflective of its ability to avoid violations post-recovery (durability). We define the resilient STL control problem as one of multi-objective optimization, where the recoverability and durability of the desired STL specification are maximized. When neither objective is prioritized over the other, the solution to the problem is a set of Pareto-optimal system trajectories. We present a precise solution method to the resilient STL control problem using a mixed-integer linear programming encoding and an a posteriori n-constraint approach for efficiently retrieving the complete set of optimally resilient solutions. In ResilienC, at each time-step, the optimal control action selected from the set of Pareto- optimal solutions by a Decision Maker strategy realizes a form of Model Predictive Control. We demonstrate the practical utility of the ResilienC framework on two significant case studies: autonomous vehicle lane keeping and deadline-driven, multi-region package delivery. 

Resiliency is the ability to quickly recover from a violation and avoid future violations for as long as possible. Such a property is of fundamental importance for Cyber-Physical Systems (CPS), and yet, to date, there is no widely agreed-upon formal treatment of CPS resiliency. We present an STL-based framework for reasoning about resiliency in CPS in which resiliency has a syntactic characterization in the form of an STL-based Resiliency Specification (SRS). Given an arbitrary STL formula φ, time bounds α and β, the SRS of φ, Rα,β (φ), is the STL formula ¬φU[0,α]G[0,β)φ, specifying that recovery from a violation of φ occur within time α (recoverability), and subsequently that φ be maintained for duration β (durability). These R-expressions, which are atoms in our SRS logic, can be combined using STL operators, allowing one to express composite resiliency specifications, e.g., multiple SRSs must hold simultaneously, or the system must eventually be resilient. We define a quantitative semantics for SRSs in the form of a Resilience Satisfaction Value (ReSV) function r and prove its soundness and completeness w.r.t. STL’s Boolean semantics. The r-value for Rα,β (φ) atoms is a singleton set containing a pair quantifying recoverability and durability. The r-value for a composite SRS formula results in a set of non-dominated recoverability-durability pairs, given that the ReSVs of subformulas might not be directly comparable (e.g., one subformula has superior durability but worse recoverability than another). To the best of our knowledge, this is the first multi-dimensional quantitative semantics for an STL-based logic. Two case studies demonstrate the practical utility of our approach. https://doi.org/10.1007/978-3-031-15839-1_7 

As various smart services are increasingly deployed in modern cities, many unexpected conflicts arise due to various physical world couplings. Existing solutions for conflict resolution often rely on centralized control to enforce predetermined and fixed priorities of different services, which is challenging due to the inconsistent and private objectives of the services. Also, the centralized solutions miss opportunities to more effectively resolve conflicts according to their spatiotemporal locality of the conflicts. To address this issue, we design a decentralized negotiation and conflict resolution framework named DeResolver, which allows services to resolve conflicts by communicating and negotiating with each other to reach a Pareto-optimal agreement autonomously and efficiently. Our design features a two-step self-supervised learning-based algorithm to predict acceptable proposals and their rankings of each opponent through the negotiation. Our design is evaluated with a smart city case study of three services: intelligent traffic light control, pedestrian service, and environmental control. In this case study, a data-driven evaluation is conducted using a large dataset consisting of the GPS locations of 246 surveillance cameras and an automatic traffic monitoring system with more than 3 million records per day to extract real-world vehicle routes. The evaluation results show that our solution achieves much more balanced results, i.e., only increasing the average waiting time of vehicles, the measurement metric of intelligent traffic light control service, by 6.8% while reducing the weighted sum of air pollutant emission, measured for environment control service, by 12.1%, and the pedestrian waiting time, the measurement metric of pedestrian service, by 33.1%, compared to priority-based solution. 

Cellular unjamming is the collective fluidization of cell motion and has been linked to many biological processes, including development, wound repair, and tumor growth. In tumor growth, the uncontrolled proliferation of cancer cells in a confined space generates mechanical compressive stress. However, because multiple cellular and molecular mechanisms may be operating simultaneously, the role of compressive stress in unjamming transitions during cancer progression remains unknown. Here, we investigate which mechanism dominates in a dense, mechanically stressed monolayer. We find that long-term mechanical compression triggers cell arrest in benign epithelial cells and enhances cancer cell migration in transitions correlated with cell shape, leading us to examine the contributions of cell–cell adhesion and substrate traction in unjamming transitions. We show that cadherin-mediated cell–cell adhesion regulates differential cellular responses to compressive stress and is an important driver of unjamming in stressed monolayers. Importantly, compressive stress does not induce the epithelial–mesenchymal transition in unjammed cells. Furthermore, traction force microscopy reveals the attenuation of traction stresses in compressed cells within the bulk monolayer regardless of cell type and motility. As traction within the bulk monolayer decreases with compressive pressure, cancer cells at the leading edge of the cell layer exhibit sustained traction under compression. Together, strengthened intercellular adhesion and attenuation of traction forces within the bulk cell sheet under compression lead to fluidization of the cell layer and may impact collective cell motion in tumor development and breast cancer progression. 

Abstract The rate of magnetic reconnection is of the utmost importance in a variety of processes because it controls, for example, the rate energy is released in solar flares, the speed of the Dungey convection cycle in Earth’s magnetosphere, and the energy release rate in harmful geomagnetic substorms. It is known from numerical simulations and satellite observations that the rate is approximately 0.1 in normalized units, but despite years of effort, a full theoretical prediction has not been obtained. Here, we present a first-principles theory for the reconnection rate in non-relativistic electron-ion collisionless plasmas, and show that the same prediction explains why Sweet-Parker reconnection is considerably slower. The key consideration of this analysis is the pressure at the reconnection site (i.e., the x-line). We show that the Hall electromagnetic fields in antiparallel reconnection cause an energy void, equivalently a pressure depletion, at the x-line, so the reconnection exhaust opens out, enabling the fast rate of 0.1. If the energy can reach the x-line to replenish the pressure, the exhaust does not open out. In addition to heliospheric applications, these results are expected to impact reconnection studies in planetary magnetospheres, magnetically confined fusion devices, and astrophysical plasmas.