As human society evolves, the demand for optimized and energy-efficient lighting solutions in buildings has intensified, driven by increasing energy consumption and the limitations of traditional systems in meeting th...
详细信息
The evolution in the generations of smart applications has led to great challenges in terms of providing low latency and high computing efficiency. One of the most important of these applications is for smart homes, t...
详细信息
ISBN:
(纸本)9798350361261;9798350361278
The evolution in the generations of smart applications has led to great challenges in terms of providing low latency and high computing efficiency. One of the most important of these applications is for smart homes, through which various connected devices can be controlled by smart and efficient systems to achieve high service quality. In this paper, we propose a smart home controller based on fog computing, where home services are migrated from the cloud to the fog servers at the edge of the network. We propose an exact algorithm called Optimal Migration Algorithm (OMA) that allocates unified fog computing servers to different services. Moreover, to deal with large-scale networks, we propose an efficient algorithm called Efficient Migration Algorithm (EMA). The performance evaluation shows that the proposed optimization solutions are efficient in terms of migration cost, time, and end-to-end latency.
The proceedings contain 21 papers. The special focus in this conference is on High-Performance computingsystems and Technologies in Scientific Research, Automation of control and Production. The topics include: Adapt...
ISBN:
(纸本)9783031510564
The proceedings contain 21 papers. The special focus in this conference is on High-Performance computingsystems and Technologies in Scientific Research, Automation of control and Production. The topics include: Adaptive Methods for the Structural Optimization of Neural Networks and Their Ensemble for Data Analysis;self-adaptation Method for Evolutionary Algorithms Based on the Selection Operator;application of U-Net Architecture Neural Network for Segmentation of Brain Cell Images Stained with Trypan Blue;language Model Architecture Based on the Syntactic Graph of Analyzed Text;classic and Modern Methods of Automatic Parking control of Self-driving Cars;application of Smoothing Technique to Model Predictive Traffic Signal control;design Features of the Frequency-controlled Electric Drive for Positioning Mechanisms;Development of a Mathematical Model to Study the Energy Indicators of Electric Drives Using the DFC-IM System;intelligent Data Analysis for Materials Obtained Using Selective Laser Melting Technology;speech Enhancement Based on Two-Stage Neural Network with Structured State Space for Sequence Transformation;fourier Chromagrams for Fingerprinting, Verification and Authentication of Digital Audio Recordings;methodology of Expert-Agent Cognitive Modeling for Preventing Impact on Critical Information Infrastructure;designing a Graphics Accelerator with Heterogeneous Architecture;spectrophotometer for Field Studies;comparative Study of Practical Implementation of Time Delay Estimation Methods on Single Board Computer;study of the Functional Characteristics of TiNi Coatings by the Computer-Aided Simulation Using Parallel computing;on Hierarchical Convergence of the Heterogeneous Multiscale Finite Element Method Using Polyhedral Supports;parallelization of Finite-Volume Numerical Methods of Computational Fluid Dynamics by Means of Shared Memory computingsystems.
The eight papers included in this special issue represent a selection of extended contributions presented at the 17th internationalconference on Soft computing Models in Industrial and Environmental Applications, SOC...
详细信息
The eight papers included in this special issue represent a selection of extended contributions presented at the 17th internationalconference on Soft computing Models in Industrial and Environmental Applications, SOCO 2022 held in Salamanca, Spain, September 6th-8th, 2022, and organized by the BISITE group at University of Salamanca. SOCO 2022 internationalconference represents a collection or set of computational techniques in machine learning, computer science and some engineering disciplines which investigate, simulate, and analyse very complex issues and phenomena. This special issue is aimed at practitioners, researchers, and postgraduate students who are engaged in developing and applying advanced intelligentsystems principles to solve real-world problems in the mentioned fields.
The complexity of financial systems and the rapid increase in data volume are making the use of intelligentcomputing and trustworthy machine learning more important in finance. This paper discusses how intelligent co...
详细信息
ISBN:
(纸本)9798350377859;9798350377842
The complexity of financial systems and the rapid increase in data volume are making the use of intelligentcomputing and trustworthy machine learning more important in finance. This paper discusses how intelligentcomputing can be applied within complex financial systems and takes a deeper look at the theory behind trustworthy machine learning and how it is used in finance. By combining the structure of complex networks with the computing power of machine learning, the paper also explores the inner workings of large neural networks and considers how to apply the theory of dynamic systems to the tuning of these networks, to improve intelligentcomputing in complex financial systems. Experiments based on the "scientific intelligence + machine conjecture" approach were carried out for risk assessment and market forecasting. The results show that these technologies can improve how financial institutions manage risk, help investors get more reliable information about market trends, and meet the transparency needed for regulatory compliance. The use of intelligentcomputing and trustworthy machine learning in complex financial systems points to a future with lots of potential for innovation and new opportunities.
This paper analyzes theoretical analysis of the altitude impact and make a simulation in order to compare the statistics constant altitude and the real-time measured altitude which is from inertial navigation system i...
详细信息
The proceedings contain 22 papers. The topics discussed include: SDN-based optimized controller deployment strategy for satellite network;multi-UAV enabled maritime relay and edge-computing service migration;a TDoA-ba...
ISBN:
(纸本)9798350374377
The proceedings contain 22 papers. The topics discussed include: SDN-based optimized controller deployment strategy for satellite network;multi-UAV enabled maritime relay and edge-computing service migration;a TDoA-based single-LED VLP system assisted by circular photodiodes array receiver;research on parabolic cores and high refractive index ring assisted fibers;FUFQ: a heterogeneous-based full-amplitude quantum simulator;design of network topology control algorithm for multi-agent systems;aerial reconfigurable intelligent surface-assisted secrecy energy-efficient communication based on deep reinforcement learning;conceptual design to achieve stable communication performance in OWC systems with dimming control;and an improved label propagation algorithm for undirected weighted networks.
The introduction of FPGAs in High-Performance Embedded computing and Artificial Intelligence still faces challenges regarding the difficulty of getting started. It requires hardware knowledge, familiarity with multipl...
详细信息
ISBN:
(纸本)9798350349603;9798350349597
The introduction of FPGAs in High-Performance Embedded computing and Artificial Intelligence still faces challenges regarding the difficulty of getting started. It requires hardware knowledge, familiarity with multiple tooling, libraries and frameworks and long synthesis times. To encourage the usage of FPGAs, this work proposes an ecosystem that includes a library with a set of pre-built accelerators for common Digital Signal Processing and Artificial Intelligence workloads, an engine for runtime arbitrary-precision quantisation and an agnostic API, allowing the development of FPGA-accelerated user applications while abstracting the details about the FPGA design and implementation. Our approach is based on hardware reuse, introducing software resource management of a series of pre-built IP cores, allowing low-end FPGAs to be used as hardware accelerators and multiple applications to share resources. Our work is better than managed FPGA standalone applications with Vitis HLS-based quantisation, accelerating 1.22x, thanks to our quantisation engine, which accelerates 5.12x the quantisation and 13.30x the de-quantisation, while keeping close the accelerator execution times.
While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulat...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulation. This paper proposes a pipeline for improving imitation learning performance with a small human demonstration budget. We apply our approach to assembly tasks that require precisely grasping, reorienting, and inserting multiple parts over long horizons and multiple task phases. Our pipeline combines expressive policy architectures and various techniques for dataset expansion and simulation-based data augmentation. These help expand dataset support and supervise the model with locally corrective actions near bottleneck regions requiring high precision. We demonstrate our pipeline on four furniture assembly tasks in simulation, enabling a manipulator to assemble up to five parts over nearly 2500 time steps directly from RGB images, outperforming imitation and data augmentation baselines. Project website: https://***/.
In this paper, a real-time energy-optimal strategy exploiting preview information resulting from connectivity and autonomous vehicle (CAV) technology is verified by experimental analyses linked with on-board computing...
详细信息
ISBN:
(纸本)9798350399462
In this paper, a real-time energy-optimal strategy exploiting preview information resulting from connectivity and autonomous vehicle (CAV) technology is verified by experimental analyses linked with on-board computing methods on a real vehicle-in-the-loop testbed with virtual road and traffic light system. An energy-optimal deceleration planning/following system (EDPS) as a service-oriented technology for electrified vehicles utilizing preview information is applied to a microcontroller, where the data access route and location on the given system architecture are optimized to shorten computing time. Also, two types of multicore strategies are comparatively analyzed to efficiently operate computing resources of the embedded controller as well as to distribute computing loads, and the strategy comparisons indicate that a function-level task partition considering target cores in advance can practically reduce computing loads. In the vehicle-in-the-loop simulations (VILS) with a realistic driving on the virtual road and CAV technology-based information, the embedded EDPS planning results illustrate that the energy-optimal speed profiles are properly computed on a commercial automotive microcontroller while stably processing real-time data input/output and optimal planning within the given time constraints.
暂无评论