Unreliable Network Conditions Research Articles

Evaluating V2X-Based Vehicle Control under Unreliable Network Conditions, Focusing on Safety Risk

Evaluating V2X-Based Vehicle Control under Unreliable Network Conditions, Focusing on Safety Risk

LoRe: A Programming Model for Verifiably Safe Local-first Software

Local-first software manages and processes private data locally while still enabling collaboration between multiple parties connected via partially unreliable networks. Such software typically involves interactions with users and the execution environment (the outside world). The unpredictability of such interactions paired with their decentralized nature make reasoning about the correctness of local-first software a challenging endeavor. Yet, existing solutions to develop local-first software do not provide support for automated safety guarantees and instead expect developers to reason about concurrent interactions in an environment with unreliable network conditions. We propose LoRe , a programming model and compiler that automatically verifies developer-supplied safety properties for local-first applications. LoRe combines the declarative data flow of reactive programming with static analysis and verification techniques to precisely determine concurrent interactions that violate safety invariants and to selectively employ strong consistency through coordination where required. We propose a formalized proof principle and demonstrate how to automate the process in a prototype implementation that outputs verified executable code. Our evaluation shows that LoRe simplifies the development of safe local-first software when compared to state-of-the-art approaches and that verification times are acceptable.

VerSA: Verifiable Secure Aggregation for Cross-Device Federated Learning

In privacy-preserving cross-device federated learning, users train a global model on their local data and submit encrypted local models, while an untrusted central server aggregates the encrypted models to obtain an updated global model. Prior work has demonstrated how to verify the correctness of aggregation in such a setting. However, such verification relies on strong assumptions, such as a trusted setup among all users under unreliable network conditions, or it suffers from expensive cryptographic operations, such as bilinear pairing. In this paper, we scrutinize the verification mechanism of prior work and propose a model recovery attack, demonstrating that most local models can be leaked within a reasonable time (e.g., <inline-formula><tex-math notation="LaTeX">$98\%$</tex-math></inline-formula> of encrypted local models are recovered within 21 h). Then, we propose <small>VerSA</small> , a verifiable secure aggregation protocol for cross-device federated learning. <small>VerSA</small> does not require any trusted setup for verification between users while minimizing the verification cost by enabling both the central server and users to utilize only a lightweight pseudorandom generator to prove and verify the correctness of model aggregation. We experimentally confirm the efficiency of <small>VerSA</small> under diverse datasets, demonstrating that <small>VerSA</small> is orders of magnitude faster than verification in prior work.

Computing Resource Provisioning at the Edge: An Overbooking-Enabled Trading Paradigm

The arrival of the Internet of Things (IoT) era calls for cost-effective resource provisioning techniques to secure necessary computing resources in supporting dynamic and computation-intensive applications on diverse IoT devices, where resource trading in edge networks brings a viable prospect. While conventional onsite spot trading may facilitate this paradigm, the inherent extra latency of onsite decision making and unreliable network significantly limit resource trading efficiency and the eventual resource utilization rate. More importantly, the “no show” of confirmed resource buyers incurred by unreliable network conditions, can result in negative impacts on trading performance and resource usage. To this end, resource overbooking is adopted that provides an effective solution in handling “no shows” while substantially improving resource utilization rate. In this article, an interesting overbooking-enabled resource trading paradigm in mobile edge networks is proposed, allowing pre-negotiated forward contracts between the edge server (seller) and a number of overbooked smart devices (buyers), which will be fulfilled during future trading. Specifically, a framework associated with the proposed trading paradigm is introduced first to provide a comprehensive view of the relevant key issues. Then a case study is presented that elaborates how the proposed trading can be implemented in practice. Extensive simulation results and analysis demonstrate that the overbooking-enabled trading paradigm achieves both time and energy efficiency, as well as substantial resource utilization and profit improvements.

Enhanced shared experiences in heterogeneous network with generative AI

COVID-19 has made the immersive experiences such as video conferencing, virtual reality/augmented reality, the most important modes of exchanging information. Despite much advancement in the network bandwidth and codec techniques, the current system still suffers from glitches, lags and poor video quality, especially under unreliable network conditions. In this paper, we propose the method of a video streaming pipeline to provide better video quality under erratic network conditions. We propose an environment where the participants can interact with each other through video conferencing by only sending the audio in the network. We propose a Multimodal Adaptive Normalization (MAN)-based architecture to synthesize a talking person video of arbitrary length using as input: an audio signal and a single image of a person. The architecture uses multimodal adaptive normalization, keypoint heatmap predictor, optical flow predictor and class activation map-based layers to learn movements of expressive facial components and hence generates a highly expressive talking-head video of the given person. We demonstrate the effectiveness of proposed streaming that dynamically controls the Quality of Experience (QoE) as per the requirements.

The AI-Medic: an artificial intelligent mentor for trauma surgery

ABSTRACT Telementoring generalist surgeons as they treat patients can be essential when in situ expertise is not available. However, unreliable network conditions, poor infrastructure, and lack of remote mentors availability can significantly hinder remote intervention. To guide medical practitioners when mentors are unavailable, we present the AI-Medic, the initial steps towards an intelligent artificial system for autonomous medical mentoring. A Deep Learning model is used to predict medical instructions from images of surgical procedures. An encoder-decoder model was trained to predict medical instructions given a view of a surgery. The training was done using the Dataset for AI Surgical Instruction (DAISI), a dataset including images and instructions providing step-by-step demonstrations of 290 different surgical procedures from 20 medical disciplines. The predicted instructions were evaluated using cumulative BLEU scores and input from expert physicians. The evaluation was performed under two settings: with and without providing the model with prior information from test set procedures. According to the BLEU scores, the predicted and ground truth instructions were as high as % similar. Additionally, expert physicians subjectively assessed the algorithm subjetively and considered that the predicted descriptions were related to the images. This work provides a baseline for AI algorithms assisting in autonomous medical mentoring.

Thin-slice vision: inference of confidence measure from perceptual video quality

There has been considerable research on thin-slice judgments, but no study has demonstrated the predictive validity of confidence measures when assessors watch videos acquired from communication systems, in which the perceptual quality of videos could be degraded by limited bandwidth and unreliable network conditions. This paper studies the relationship between high-level thin-slice judgments of human behavior and factors that contribute to perceptual video quality. Based on a large number of subjective test results, it has been found that the confidence of a single individual present in all the videos, called speaker’s confidence (SC), could be predicted by a list of features that contribute to perceptual video quality. Two prediction models, one based on artificial neural network and the other based on a decision tree, were built to predict SC. Experimental results have shown that both prediction models can result in high correlation measures.

Adaptive Sensor Node Sleep Scheduling for Quality-of-Experience Enhancement

Focusing on a user's quality-of-experience (QoE) has become important, because of the growing space of sensor-dependent applications and low-cost sensor design. QoE is typically affected by two quantities: the quality-of-information (QoI) received and the lifetime-of-service. Therefore, QoE is defined as a sensor network's ability to consistently offer assured QoI for an expected lifetime when operating on a limited energy resource, such as a battery. However, dynamic factors, such as varying user requirements, unpredictable sensor environment, unreliable network conditions, and limited energy resource, affecting both QoI and lifetime-of-service, make it challenging to achieve a good QoE. In our previous work, we presented a SNR-based QoI metric which addresses the impact of several of these factors on QoI. In this paper, we design a QoE metric that quantifies the relationship between energy conservation, QoI received by a user, and an application's quality expectation. Further, we develop an adaptive sleep schedule mechanism to demonstrate the usefulness of this metric. Finally, simulation results presented show the effectiveness of our mechanism in achieving QoE improvement.

From Autonomy to Cooperative Traded Control of Humanoid Manipulation Tasks with Unreliable Communication

In this paper, we present our system design, operational procedure, testing process, field results, and lessons learned for the valve-turning task of the DARPA Robotics Challenge (DRC). We present a software framework for cooperative traded control that enables a team of operators to control a remote humanoid robot over an unreliable communication link. Our system, composed of software modules running on-board the robot and on a remote workstation, allows the operators to specify the manipulation task in a straightforward manner. In addition, we have defined an operational procedure for the operators to manage the teleoperation task, designed to improve situation awareness and expedite task completion. Our testing process, consisting of hands-on intensive testing, remote testing, and remote practice runs , demonstrates that our framework is able to perform reliably and is resilient to unreliable network conditions. We analyze our approach, field tests, and experience at the DRC Trials and discuss lessons learned which may be useful for others when designing similar systems.

Bayesian framework for bilateral teleoperation systems over unreliable network

SUMMARYIn this paper, we present a novel stochastic framework for network-based bilateral teleoperation systems. A Bayesian approach, which provides robust tracking performance in real-world applications, is proposed to estimate and predict the stochastic variables and compensate for the unreliable network conditions. Combining with a practical approach in transport and application layers of the Internet, this paper demonstrates a high performance and efficient prediction and estimation method for bilateral teleoperation system. Experimental results show that the proposed Bayesian approach estimates and predicts true position and force data over unreliable network conditions, and therefore, improves the performance of overall teleoperation systems.

Fault tolerant decentralised [formula omitted]-Means clustering for asynchronous large-scale networks

The K-Means algorithm for cluster analysis is one of the most influential and popular data mining methods. Its straightforward parallel formulation is well suited for distributed memory systems with reliable interconnection networks, such as massively parallel processors and clusters of workstations. However, in large-scale geographically distributed systems the straightforward parallel algorithm can be rendered useless by a single communication failure or high latency in communication paths. The lack of scalable and fault tolerant global communication and synchronisation methods in large-scale systems has hindered the adoption of the K-Means algorithm for applications in large networked systems such as wireless sensor networks, peer-to-peer systems and mobile ad hoc networks. This work proposes a fully distributed K-Means algorithm (EpidemicK-Means) which does not require global communication and is intrinsically fault tolerant. The proposed distributed K-Means algorithm provides a clustering solution which can approximate the solution of an ideal centralised algorithm over the aggregated data as closely as desired. A comparative performance analysis is carried out against the state of the art sampling methods and shows that the proposed method overcomes the limitations of the sampling-based approaches for skewed clusters distributions. The experimental analysis confirms that the proposed algorithm is very accurate and fault tolerant under unreliable network conditions (message loss and node failures) and is suitable for asynchronous networks of very large and extreme scale.