Fog computing is an emerging distributedcomputing model for the realization of the Internet of Things (IoT). It extends computing and caching functions to the edge of wireless networks. Unmanned Aerial Vehicles (UAVs...
详细信息
Simulations are an important part of analyzing and understanding systems, including not only technical but also bio-mechanical subjects such as the musculoskeletal apparatus of the human body. Detailed, biophysical si...
详细信息
ISBN:
(数字)9781665471770
ISBN:
(纸本)9781665471770
Simulations are an important part of analyzing and understanding systems, including not only technical but also bio-mechanical subjects such as the musculoskeletal apparatus of the human body. Detailed, biophysical simulations are complex and require a substantial amount of computational resources. With the advent of mobile AR devices such as the Microsoft HoloLens, new challenges arise to run or represent the results of such complex simulations on resource-constrained devices. In this paper we propose a deep-learning-based mobile simulation approach for the contraction of a human muscle model on an AR device (MS HoloLens 2). To elaborate, we present a two-step workflow consisting of simulating the deformation of the 3D geometry of the biceps, of which a subset of points can be interpolated back to full resolution. This allows to either offload the full simulation, just communicating the subset of nodal points, or to use a lower-quality local simulation restricted to the subset. Interpolation is done locally in both cases. The interpolation model consists of a dense, single hidden layer neural network. A mesh simplification method is combined with a genetic algorithm to determine the optimal subset of mesh nodes to interpolate from. In purely local execution, our simulation and interpolation model is able to accurately predict the position of 2809 nodal points based on as few as 30, while using 97.78 % less energy and evaluating up to 1.23 times faster compared to the local reference model. In an ideal distributed scenario energy consumption decreases by 99 % and evaluation time is up to 32.42 times faster. For the latter, it also reduces communication-data to 1.2 % of the full resolution mesh.
We study the problem of floor identification for radiofrequency (RF) signal samples obtained in a crowdsourced manner, where the signal samples are highly heterogeneous and most samples lack their floor labels. We pro...
详细信息
ISBN:
(数字)9781665471770
ISBN:
(纸本)9781665471770
We study the problem of floor identification for radiofrequency (RF) signal samples obtained in a crowdsourced manner, where the signal samples are highly heterogeneous and most samples lack their floor labels. We propose GRAFICS, a graph embedding-based floor identification system. GRAFICS first builds a highly versatile bipartite graph model, having APs on one side and signal samples on the other. GRAFICS then learns the low-dimensional embeddings of signal samples via a novel graph embedding algorithm named E-LINE. GRAFICS finally clusters the node embeddings along with the embeddings of a few labeled samples through a proximity-based hierarchical clustering, which eases the floor identification of every new sample. We validate the effectiveness of GRAFICS based on two large-scale datasets that contain RF signal records from 204 buildings in Hangzhou, China, and five buildings in Hong Kong. Our experiment results show that GRAFICS achieves highly accurate prediction performance with only a few labeled samples (96% in both micro- and macro-F scores) and significantly outperforms several state-of-the-art algorithms (by about 45% improvement in micro-F score and 53% in macro-F score).
Microseismic detection events are critical in monitoring subsurface activities, including hydraulic fracturing, enhanced oil recovery, carbon dioxide, or natural gas geological storage and reservoir characterization, ...
详细信息
ISBN:
(纸本)9783031669644;9783031669651
Microseismic detection events are critical in monitoring subsurface activities, including hydraulic fracturing, enhanced oil recovery, carbon dioxide, or natural gas geological storage and reservoir characterization, to guarantee safe and efficient energy extraction. This presents significant challenges as it generates large amounts of data. Despite the recent machine learning techniques being increasingly integrated into fiber-optic distributed acoustic sensor (DAS) systems to enhance their intelligent recognition capabilities, there is still a need to solve this. In some research, it has been observed that computational speed is time-consuming and overfitting, thus necessitating a more extensive investigation of this analysis. This study proposes a novel approach using DAS data to enhance microseismic event detection's precision, overfitting issue, and interpretability. This approach utilizes a specifically designed neural network architecture. The deep learning approach is highly effective for the real-time management of the substantial amounts of data recorded by DAS equipment. Three phases of research methodology are proposed. The contribution of this research is that spiking neural network architecture for microseismic detection will bring advancements in microseismic monitoring.
The following paper describes a concept for a grasping application which utilizes technologies from the fields of distributedcomputing, robotics and Digital Twins in the sense of Industry 4.0. Hereby, the goal of the...
详细信息
ISBN:
(数字)9781665499965
ISBN:
(纸本)9781665499965
The following paper describes a concept for a grasping application which utilizes technologies from the fields of distributedcomputing, robotics and Digital Twins in the sense of Industry 4.0. Hereby, the goal of the application is to have a computer vision system detect toy bricks which a robot has to pick and pass to a user. The application is divided into loosely coupled and distributed services that communicate with one another using a message broker.
In the domain of safety critical real-time computing, the ever increasing demand for processing power and robust safety guarantees has fueled the development of solutions to support the development of multicore and mu...
详细信息
ISBN:
(纸本)9798350324983
In the domain of safety critical real-time computing, the ever increasing demand for processing power and robust safety guarantees has fueled the development of solutions to support the development of multicore and multi-CPU distributed software architectures. These architectures offer the potential for achieving enhanced computational power by exploiting the high-level of hardware parallelism, but they also raise significant challenges in ensuring temporal guarantees, such as the absence of deadlocks and race conditions, compliance with time budgets, etc. In this paper we present our ongoing work of developing a workflow for developing multi-CPU software applications from high level requirements down to the integrated system. The workflow is supported by several models and is specified with the FTG+PM formalism. We illustrate the workflow using two industrial applications from the aeronautical domain.
We present a simple algorithmic framework for designing efficient distributed algorithms for the fundamental symmetry breaking problem of Maximal Independent Set (MIS) in the sleeping model [Chatterjee et al, PODC 202...
详细信息
ISBN:
(数字)9781665471770
ISBN:
(纸本)9781665471770
We present a simple algorithmic framework for designing efficient distributed algorithms for the fundamental symmetry breaking problem of Maximal Independent Set (MIS) in the sleeping model [Chatterjee et al, PODC 2020]. In the sleeping model, only the rounds in which a node is awake are counted for the awake complexity, while sleeping rounds are ignored. This is motivated by the fact that a node spends resources only in its awake rounds and hence the goal is to minimize the awake complexity. Our framework allows us to design distributed MIS algorithms that have O (polyloglog(n)) (worst-case) awake complexity in certain important graph classes which satisfy the so-called adjacency property. Informally, the adjacency property guarantees that the graph can be partitioned into an appropriate number of classes so that each node has at least one neighbor belonging to every class. Graphs that can satisfy the adjacency property are random graphs with large clustering coefficient such as random geometric graphs as well as line graphs of regular (or near regular) graphs. We first apply our framework to design two randomized distributed MIS algorithms for random geometric graphs of arbitrary dimension d (even non-constant). The first algorithm has O(polyloglog n) (worst-case) awake complexity with high probability, where n is the number of nodes in the graph.' This means that any node in the network spends only O(polyloglog n) awake rounds;this is almost exponentially better than the (traditional) time complexity of O(log n) rounds (where there is no distinction between awake and sleeping rounds) known for distributed MIS algorithms on general graphs or even the faster O(root log n/log log n ) rounds known for Erdos-Renyi random graphs. log log n However, the (traditional) time complexity of our first algorithm is quite large-essentially proportional to the degree of the graph. Our second algorithm has a slightly worse awake complexity of O(d polyloglog n), but achieves a sig
Given their nature, many control applications that arise from the integration of Operation Technologies (OT) and Information Technologies (IT) are built on top of highly reliable real-time (RT) distributed Control Sys...
详细信息
An increasingly prominent issue in recent times is the utilization of the Internet of Things (IoT) for home automation systems. Home automation, also known as smart home technology, refers to the wireless and intellig...
详细信息
The paper represents the result of developments of the Institute of Cybernetics of NAS of Ukraine in the field of smart systems for precision agriculture, environmental protection and healthcare. Main conceptions, str...
详细信息
暂无评论