In the management of data space, data quality is very important to realize the value of data. How to improve data quality and tap the potential value of data, this paper proposes a five-dimensional scale of data quali...
In the management of data space, data quality is very important to realize the value of data. How to improve data quality and tap the potential value of data, this paper proposes a five-dimensional scale of data quality based on manufacturing multi-value chain collaborative data space, which includes five dimensions of data generation, data acquisition, pre-access processing, architecture construction and data access, which effectively makes up for the shortcomings of current literature. Meanwhile, the improved CRITIC model weighting method and the combined weighting model of principal component weighting method were established to calculate the data quality index and sub-index, and the data quality level and sub-index level of manufacturing enterprises in Beijing were evaluated. By developing and analyzing the scale of data quality, we provide practical experience for value mining of collaborative data space data of multi-value chain in manufacturing industry.
The Internet of Things (IoT) for medical purposes offers a number of benefits, including the aptitude to follow the individual's physical state over a range of time intervals and transmitting data in real time. Us...
The Internet of Things (IoT) for medical purposes offers a number of benefits, including the aptitude to follow the individual's physical state over a range of time intervals and transmitting data in real time. Using gadgets like glucose meters, heart monitoring implants, Electrocardiogram (ECG), blood pressure monitors, Electroencephalography (EEG) and Electromyography (EMG) wearable strategies, medical personnel can gather local patient wellness data and make choices based on it. The IoT devices' weak authentication and encryption procedures make them readily hackable and may expose users to a number of risks, some of which could be fatal. The Quality of Service (QoS) needs for healthcare IoT devices, such as dependability, authorization, identity and security, cannot be met by current algorithms using machine learning or blockchain approaches operating in the cloud computing environment. Henceforth the proposed work develops an advanced Fog computing (FC) to oppose advance cloud computing at an edge of networks together with Block chain topology. Fog computing has been emphasized as promising method for low-cost remote monitoring, limiting down on latency, and boosting efficiency, while blockchain has been touted for guaranteeing the security of private data, building a decentralized database, and improving data interoperability. The problem of healthcare IoT device recognition, permission and confirmation for scalability often broadcast of data in a distributed setting can be handled by merging FC with block chain. So, leveraging FC and blockchain, a creative solution to the aforementioned issue.
With the development of information technology, China has launched various business processes of power informatization equipment in distribution or transmission grid informatization construction, laying the intelligen...
With the development of information technology, China has launched various business processes of power informatization equipment in distribution or transmission grid informatization construction, laying the intelligent foundation of China’s current power business informatization. Automatically mining and identifying performance degradation evolution patterns from the massive operation process data of complex equipment which is used to analyze the dynamic health status of equipment and guide equipment maintenance has become a research hotspot in the field of safety and reliability. Our research takes Yunnan Power Grid Company’s power mobile equipment Internet of Things (IOT) data terminal and data center in integrated management system as the research object. We analyzes its construction method, data storage and processing, optimization algorithm and application advantages based on big data background. It carries out integrated power system management, provides good data interaction guarantee and achieves the overall goal of digital construction and transformation of power grid construction. The use of the latest technology platform, and combined with intelligent algorithms, the development of powerful computing power mobile equipment IoT data terminals and integrated management system has become a strategic trend of the current layout of China’s power industry.
A rain scanner for rainfall monitoring had been developed using marine radar. Rainfall monitoring as a part of atmospheric observation was conducted using this rain scanner in near real time. Rain scanner could produc...
详细信息
Huge information evaluation, the use of synthetic Intelligence, is a manner of using AI structures to automate the system of extracting meaningful insights from massive sets of statistics. A combination of AI-driven a...
Huge information evaluation, the use of synthetic Intelligence, is a manner of using AI structures to automate the system of extracting meaningful insights from massive sets of statistics. A combination of AI-driven algorithms and hardware may be used to quickly perceive styles in unlabeled information that could otherwise take vast quantities of time to extract. This paper presents a method and framework for Automating Big data Analysis using Artificial Intelligence (AI). With the increasing volume and complexity of big data, traditional manual analysis methods are becoming inefficient and often result in inaccurate or incomplete insights. To address this challenge, we propose a systematic approach that leverages AI techniques such as machine learning and natural language processing to automate the process of data analysis. Our framework includes measures for data preprocessing, feature selection, model building, and result interpretation, and adapts to different types and sources of big data. We demonstrate the effectiveness of our approach through experiments on real-world datasets and compare the results with manual analysis methods. The proposed automated approach not only improves the speed and accuracy of big data analysis, but also reduces the human effort and expertise required. This has the potential to greatly enhance decision-making processes in various industries and domains that deal with large amounts of data. These talents can be used to permit higher choice-making and create extra efficient, automatic approaches to conducting huge-scale data analysis.
With the development of agricultural modernization, the traditional agricultural production model has been gradually subverted, and traditional planting is no longer the main way to increase farmers' income. Under...
详细信息
With the development of agricultural modernization, the traditional agricultural production model has been gradually subverted, and traditional planting is no longer the main way to increase farmers' income. Under the traditional mode, farmland management and control mainly rely on planting experience, fertilization technology, production mode, etc., which cannot adapt to the modern environment, improve production efficiency, and promote farmers' income. Based on the application of mobile and intelligent platforms, real-time information collection, storage and analysis can be realized. In order to reduce the use of chemical fertilizer and other substances in agricultural production and improve the level of agricultural environmental management and sustainable development capability, this paper designed a GIS based mobile data collection system for agricultural green development. Based on modern information technologies such as Internet of Things and cloud computing, the system converts relevant data into geographic information maps and remote sensing images, and combines Sql database to achieve data intelligent analysis capability, which can query and analyze the collected data in real time and efficiently.
Coupled matrix and tensor factorizations (CMTF) have emerged as an effective data fusion tool to jointly analyze data sets in the form of matrices and higher-order tensors. The PARAFAC2 model has shown to be a promisi...
详细信息
Coupled matrix and tensor factorizations (CMTF) have emerged as an effective data fusion tool to jointly analyze data sets in the form of matrices and higher-order tensors. The PARAFAC2 model has shown to be a promising alternative to the CANDECOMP/PARAFAC (CP) tensor model due to its flexibility and capability to handle irregular/ragged tensors. While fusion models based on a PARAFAC2 model coupled with matrix/tensor decompositions have been recently studied, they are limited in terms of possible regularizations and/or types of coupling between data sets. In this paper, we propose an algorithmic framework for fitting PARAFAC2-based CMTF models with the possibility of imposing various constraints on all modes and linear couplings, using Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM). Through numerical experiments, we demonstrate that the proposed algorithmic approach accurately recovers the underlying patterns using various constraints and linear couplings.
The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary atte...
详细信息
The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use of visual cue is not only feasible, but also effective due to its noise robustness, and becoming popular. However, it is difficult to guarantee that such parallel visual cue is always available in real-world applications where visual occlusion or intermittent communication can occur. In this paper, we study the audio-visual speaker extraction algorithms with intermittent visual cue. We propose a joint speaker extraction and visual embedding inpainting framework to explore the mutual benefits. To encourage the interaction between the two tasks, they are performed alternately with an interlacing structure and optimized jointly. We also propose two types of visual inpainting losses and study our proposed method with two types of popularly used visual embeddings. The experimental results show that we outperform the baseline in terms of signal quality, perceptual quality, and intelligibility.
Distributed MIMO radar is known to achieve superior sensing performance by employing widely separated antennas. However, it is challenging to implement a low-complexity distributed MIMO radar due to the complex operat...
详细信息
Distributed MIMO radar is known to achieve superior sensing performance by employing widely separated antennas. However, it is challenging to implement a low-complexity distributed MIMO radar due to the complex operations at both the receivers and the fusion center. This work proposes a low-bit quantized distributed MIMO (LiQuiD-MIMO) radar to significantly reduce the burden of signal acquisition and data transmission. In the LiQuiD-MIMO radar, the widely-separated receivers are restricted to operating with low-resolution ADCs and deliver the low-bit quantized data to the fusion center. At the fusion center, the induced quantization distortion is explicitly compensated via digital processing. By exploiting the inherent structure of our problem, a quantized version of the robust principal component analysis (RPCA) problem is formulated to simultaneously recover the low-rank target information matrices as well as the sparse data transmission errors. The least squares-based method is then employed to estimate the targets’ positions and velocities from the recovered target information matrices. Numerical experiments demonstrate that the proposed LiQuiD-MIMO radar, configured with the developed algorithm, can achieve accurate target parameter estimation.
The multi-agent task allocation presents a fundamental challenge in the field of multi-agent systems, especially in uncertain environments. Although extensive research has been conducted on the multi-agent task alloca...
The multi-agent task allocation presents a fundamental challenge in the field of multi-agent systems, especially in uncertain environments. Although extensive research has been conducted on the multi-agent task allocation in deterministic environments, discussions around the multi-agent task allocation in uncertain environments are relatively scarce. In reality, uncertain data is more common in practical decision-making processes. To address the multi-agent task allocation problem in uncertain environments, this study frames it as a noisy optimization problem and proposes a novel Multi-Granular Differential Evolution (MGDE) algorithm to solve it. MGDE combines the powerful differential evolution (DE) with the granular-ball computing which has high robustness in noise. The proposed MGDE is compared with other three state-of-the-art algorithms on 12 scenarios encompassing 6 agent and task quantity combinations and 2 uncertainty levels. Experimental results demonstrate the superior performance of MGDE.
暂无评论