The requirements for data privacy are changing, which affects energy Internet price plans. A novel strategy combines quantitative analysis, data modeling, and computer technologies to properly grasp this dynamic relat...
详细信息
This paper investigates the application of two improved deep learning and K-nearest neighbor algorithms, respectively named as AutoDeepKNN and DeepKNR, in movie recommendation systems. We conduct experiments on two la...
详细信息
The improvement of automated control systems in various fields of human activity is the main direction of the development of Society The problem of planning a set of jobs performed using two types of resources - renew...
详细信息
The increasing need for real-time computation with low-power consumption is driving the advancement of specialized neuromorphic processors on various applications. Multi object tracking, as one of the most challenging...
详细信息
ISBN:
(纸本)9798350383638;9798350383645
The increasing need for real-time computation with low-power consumption is driving the advancement of specialized neuromorphic processors on various applications. Multi object tracking, as one of the most challenging tasks in computer vision, has gained wide attention with many solutions proposed. Nevertheless, they consume huge resources and fail to adapt to edge application scenarios with strict power and resource constraints. In this work, we propose NeuroSORT, a neuromorphic accelerator for spike-based online and real-time object tracking, which leverages spiking neural network (SNN) to solve linear assignment problem and explores the hardware acceleration on tracking algorithms. Experimental results show that the proposed accelerator reaches an accuracy of 99.43% on linear assignment task and 69.641 HOTA score on MOT17 dataset, while consuming 0.257mW energy and 0.17mm2 area. The overall power consumption is reduced by 41.1% compared with SOTA works with equivalent performance.
Aiming at the optimal operation of new power system under the large-scale application of Energy storage. This article proposes the use of multi type energy storage collaborative operation technology to improve the ove...
详细信息
ISBN:
(纸本)9798350306194;9798350306187
Aiming at the optimal operation of new power system under the large-scale application of Energy storage. This article proposes the use of multi type energy storage collaborative operation technology to improve the overall energy utilization rate of the system and further optimize the overall economy of the new power system. Firstly, a new power system configuration with multiple energy storage collaborations was established. Then, mathematical physics optimization modeling is carried out for each subsystem, aiming at the optimal economic day ahead scheduling of the new power system. Finally, considering energy storage subsidies, this article conducts a case study on the actual power system in Xinjiang, and compares and verifies the effectiveness and superiority of the model under different models in typical daily calculation scenarios such as summer, transition season, and winter. The results show that after adopting a new type of power system with multi-type energy storage collaborations, the waste wind and solar energy rate is reduced, and the low-carbon and economic performance of the power system is optimized. The utilization rate of renewable energy can be increased by 1.125%, 1.096%, and 1.678% respectively;The total revenue of the system increased by 15.84%, 20.70%, and 18.52%, respectively. It can be seen that the multi type energy storage model established in this article is of great significance for the optimization and scheduling of new power systems.
The proceedings contain 139 papers. The topics discussed include: information management technology as a tool for making effective management decisions;quantitative analysis of EEG signal profiles;an article similarit...
The proceedings contain 139 papers. The topics discussed include: information management technology as a tool for making effective management decisions;quantitative analysis of EEG signal profiles;an article similarity-based approach for planning conference sessions;a procedure for failures diagnostics of aviation radio equipment;methodological approach to the formation of information support for business risk management entities;economic and mathematical models for determining the level of maturity of an enterprise in knowledge management and project management;features of developing an online educational course for public officials: case from Ukraine;the application of optimization learning methods for multilayered neural networks;stacking neuro-neo-fuzzy system for pattern recognition and its online learning;and modelling properties of batteries using the SPICE software.
The total number of cores on a single chip is increased due to the rapidly decreasing size of transistors. In order to meet the performance demands of these designs, many designers prefer to use three-dimensional netw...
详细信息
In the ever-evolving landscape of fashion technology, the development of innovative solutions has become paramount to meet the dynamic needs of consumers and industry stakeholders. This paper introduces GARMENTO, a cu...
详细信息
ISBN:
(纸本)9783031653421;9783031653438
In the ever-evolving landscape of fashion technology, the development of innovative solutions has become paramount to meet the dynamic needs of consumers and industry stakeholders. This paper introduces GARMENTO, a customizable business-to-business (B2B) virtual clothes try-on system designed to address the evolving needs of the fashion industry. The objectives of this study encompass a comprehensive exploration of business needs in the context of virtual try-ons, an analysis of web service architecture styles to inform the design of GARMENTO, the selection of essential functionalities for inclusion in a minimum viable application, and a discussion of the implications and potential improvements for future work. By leveraging insights gained from business requirements analysis and architectural evaluations, GARMENTO aims to serve as a reference point for fashion brands seeking to implement similar virtual try-on systems, with the potential to elevate industry standards and drive innovation in the fashion technology landscape. Through ongoing refinement and exploration of future directions, GARMENTO seeks to remain at the forefront of virtual try-on technology, empowering users, enhancing user experience, and shaping the future of fashion retail.
In this paper, a remote video conferencing system based on cloud video is proposed and implemented. The system uses a mesh transfer card for MV-440 single channel high definition MPEG4 images. This paper introduces th...
详细信息
Among the most vital organs that protect the body of a human from the external environment is the skin. Early skin illness identification is essential for reducing mortality because it prevents skin cancer, and any ot...
详细信息
暂无评论