Real-time Retrieval Research Articles

Real-time retrieval of coseismic displacement with the variometric approach augmented by BDS3 B2b corrections

Real-time retrieval of coseismic displacement with the variometric approach augmented by BDS3 B2b corrections

MEDI-NET : CADRE BASÉ SUR LE CLOUD POUR SYSTÈME DE RÉCUPÉRATION DE DONNÉES MÉDICALES UTILISANT LE DEEP LEARNING

Medical data retrieval is becoming increasingly crucial, aiding physicians and domain experts in more effectively accessing knowledge and information related to medicine and facilitating informed decision-making. The centralized architectures need help with scalability and real-time indexing, leading to extended retrieval times and decreased efficiency. To address these issues, a novel MEdical Data retrieval using Inception resNET (MEDI-NET) has been proposed to retrieve medical data efficiently. The proposed system introduces a deep learning network for a dynamic poly-indexing model and concurrent indexing, ensuring the real-time retrieval of the latest medical records. EMRBots and MIMIC-III are the two datasets used to compare the performance of the proposed MEDI-NET approach with existing MRCG, HCAC-EHR, and FedCBMIR method, which is implemented using Python. The effectiveness of the proposed MEDI-NET approach has been determined using evaluation metrics such as precision, accuracy, recall, F1-score, indexing time, and retrieval time. Comparative analysis with existing methods demonstrates superior precision, accuracy, recall, and F1 score for the proposed method. Additionally, the proposed system exhibits reduced indexing and retrieval times, showcasing its efficiency in handling large-scale medical data. The proposed MEDI-NET approach's accuracy is 0.60 %, 9.87 %, and 21.1 % higher than the existing MRCG, HCAC-EHR, and FedCBMIR techniques, respectively.

Management and Construction of University Books and Materials Under the Background of the Internet

The rapid development and popularization of Internet technology has provided important support for the informatization reform of various industries. University books and materials have the characteristics of large quantities and difficult storage and management. Its digital storage and management platform construction can effectively realize the digital storage and real-time retrieval of books and materials, and help students and teachers to find and use books and materials more quickly. Especially in recent years, with the update of intelligent platforms and other technologies, the resource-sharing platform of university books and materials can realize more convenient book information retrieval without the limitation of time and space. This paper mainly explores the optimization path and platform construction scheme of university libraries and information management under the background of the Internet, hoping to provide some theoretical references for university library managers.

Hourly land surface temperature retrieval over the Tibetan Plateau using Geo-LightGBM framework: Fusion of Himawari-8 satellite, ERA5 and site observations

The Tibetan Plateau (TP) is highly sensitive to even minor fluctuations in land surface temperature (LST), which can result in permafrost melting and degradation of alpine grasslands, leading to serious ecological consequences. Therefore, it is crucial to have high-temporal-resolution and seamless hourly estimating and monitoring of LST for a better understanding of climate change on the TP. Here, we employed Himawari-8 satellite, Digital Elevation Model (DEM), ERA5 reanalysis and meteorological station observations data to develop a new LightGBM framework (called Geo-LightGBM) for estimating LST on the TP, and then analyzed the spatiotemporal variations of those LST. Geo-LightGBM demonstrated excellent LST estimation accuracy, with an R2 (coefficient of determination) of 0.971, RMSE (root-mean-square error) of 2.479 °C, and MAE (mean absolute error) of 1.510 °C. The estimated LST values for the year 2020 agreed well with observed values, with remarkable differences in hourly LST variations. Meanwhile, the estimated LST was more accurate than that from FY-4A. Spatially, there were two high LST centers, located in the Yarlung Zangbo River Basin and the Qaidam Basin, and a low LST center located in the central TP. The SHAP (SHapley Additive exPlanations) and correlation analyses revealed DSCS (the mean ground downward shortwave radiation under clear-sky conditions) to be the most importantly input variable for estimating LST. Spatiotemporal dummy variables (e.g., longitude, latitude, DEM) were also found to be crucial for model accuracy improvement. Our findings indicate the potential for constructing a high-precision and seamless 24-h LST real-time retrieval and monitoring platform for the TP by combining satellite and China's independently developed CLDAS (China Land Data Assimilation System) data in future.

Mapping the seamless hourly surface visibility in China: a real-time retrieval framework using a machine-learning-based stacked ensemble model

Surface visibility (SV), a key indicator of atmospheric transparency, is used widely in the fields of environmental monitoring, transportation, and aviation. However, the sparse distribution and limited number of SV monitoring sites make it difficult to fulfill the urgent need for spatiotemporally seamless fine-scale monitoring. Here, we developed the operational real-time SV retrieval (RT-SVR) framework for China that incorporates information from multiple data sources, including Chinese Land Data Assimilation System meteorological data, in situ observations, and other ancillary data. Seamless hourly SV data with 6.25-km spatial resolution are available in real time via the operational RT-SVR model, which was built using a two-layer stacked ensemble approach that combines multiple machine learning algorithms and a deep learning module. Sample-based cross-validation of the RT-SVR model on approximately 41.3 million data pairs revealed strong robustness and high accuracy, with a Pearson correlation coefficient (R) value of 0.95 and a root mean square error (RMSE) of 3.17 km. An additional hindcast-validation experiment, performed with continuous observations obtained over one year (approximately 20.8 million data pairs), demonstrated the powerful generalization capabilities of the RT-SVR model, albeit with slight degradation in performance (R = 0.85, RMSE = 5.28 km). The seamless hourly SV data with real-time update capability enable tracking of the generation, development, and dissipation of various low-SV events (e.g., fog, haze, and dust storms) in China. The developed framework might also prove useful for quantitative retrieval of aerosol-related parameters (e.g., PM2.5, PM10, and aerosol optical depth).

Near real-time retrieval of lake surface water temperature using Himawari-8 satellite imagery and machine learning techniques: a case study in the Yangtze River Basin

Lake Surface Water Temperature (LSWT) is essential for understanding and regulating various processes in lake ecosystems. Remote sensing for large-scale aquatic monitoring offers valuable insights, but its limitations call for a dynamic LSWT monitoring model. This study developed multiple machine learning models for LSWT retrieval of four representative freshwater lakes in the Yangtze River Basin using Himawari-8 (H8) remote sensing imagery and in-situ data. Based on the in situ monitoring dataset in Lake Chaohu, the dynamic LSWT retrieval models were effectively configured and validated to perform H8-based remote sensing inversion. The test results showed that six models provided satisfactory LSWT retrievals, with the Back Propagation (BP) neural network model achieving the highest accuracy with an R-squared (R2) value of 0.907, a Root Mean Square Error (RMSE) of 2.52°C, and a Mean Absolute Error (MAE) of 1.68°C. Furthermore, this model exhibited universality, performing well in other lakes within the Yangtze River Basin, including Taihu, Datonghu and Dongtinghu. The ability to derive robust LSWT estimates confirms the feasibility of real-time LSWT retrieval using synchronous satellites, offering a more efficient and accurate approach for LSWT monitoring in the Yangtze River Basin. Thus, this proposed model would serve as a valuable tool to support the implementation of more informed policies for aquatic environmental conservation and sustainable water resource management, addressing challenges such as climate change, water pollution, and ecosystem restoration.

Real-time retrieval of all-weather weighted mean temperature from FengYun-4A observations

Real-time retrieval of all-weather weighted mean temperature from FengYun-4A observations

Towards improved knowledge about water-related extremes based on news media information captured using artificial intelligence

Recent advances in machine learning have enabled near real-time retrieval of information from textual documents impacting a wide range of knowledge domains. This advantage makes of the insight extracted from text-based documents (e.g., reports and news) on water-related events an invaluable source of information that complements traditional approaches. By leveraging machine learning, we can not only characterize the event and determine its magnitude or phases of extreme weather event, but also identify its core elements. This is especially crucial in the current era of climate change, where extreme weather events such as floods or thunderstorms are becoming more frequent and unpredictable. By improving our ability to detect and analyse such events, we can enhance our alert systems and take more effective action to mitigate their impact. In this paper we discuss the role of worldwide media observation in extracting and estimating hydrological characteristics of floods, droughts, and heat waves, through the analysis of three case studies, complementing the information provided by traditional monitoring and measurement methods as an earlier but weaker signal. The results presented in this study indicate that the news media signal can be regarded as relatively good proxy of flood dynamics. It can capture the temporal dynamics of the event, and, in some cases, there could be a clear up to 1-day lag between the peak discharge values (i.e., the most extreme flood situation) and the peak in the number of published news. This lag can be attributed to the time needed by journalists to respond to the situation in publishing related news articles covering the event. Our result show that national and regional news can cover well local events. When compared to floods, drought conditions are less explicitly detected from the media. Our result show that European April 2022 drought did not produce much activity in the media while the combination of drought and extreme heat in July 2022 yielded a significant media coverage throughout the Europe. Hence, this can be attributed to the fact that hydrological drought such as low river flows do not attract much attention by the media unless there is a significant impact on the society. Therefore, media signal can be regarded as a relatively good proxy of the hydro-meteorological conditions in case there is a significant impact on the society such as extreme floods causing many casualties and large economic damage.

An efficient scheme for in-orbit remote sensing image data retrieval

The conflict between real-time retrieval of remote sensing image data (RSID) and the limited satellite network transmission resources is becoming more and more prominent. To address it, this paper proposes a novel scheme for RSID retrieval from the remote sensing satellite network, which exploits the spatio-temporal characterization (STC) of sensing images to improve data retrieval efficiency. In particular, based on the spatio-temporal characterization, a data content naming scheme is introduced and an algorithm is accordingly proposed for RSID segmentation in satellite nodes. With the naming scheme, RSID retrieval can be implemented by making use of the Named Data Networking (NDN) architecture. The study aims to investigate the effectiveness of making use of the STC of RSID for the retrieval under the NDN architecture. To the best of our knowledge, this paper is the first to exploit STC to establish connections between user demands, RSID, and data naming for NDN. As a result, the proposed scheme makes the network aware of RSID’s STC and consequently improves the data retrieval performance of the satellite network using NDN. The evaluation results show that the proposed scheme delivers about 65% and 7% higher retrieval hit rates than a retrieval scheme based on the original NDN proposal and a recently proposed scheme — CAP, respectively. In addition, comparing with these two schemes, the proposed one reduces transmission latency by about 20% and 15%, and traffic load by about 48% and 40%, all respectively. These imply that the proposed scheme outperforms in terms of higher data retrieval efficiency and better link utilization.

Deep Learning for Instance Retrieval: A Survey.

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, particularly that of searching databases for similar content - Content Based Image Retrieval (CBIR) - a long-established research area in which improved efficiency and accuracy are needed for real-time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of instance search. In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep feature extraction, feature embedding and aggregation methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, whereby we identify milestone work, reveal connections among various methods and present the commonly used benchmarks, evaluation results, common challenges, and propose promising future directions.

Real-time retrieval and repositioning of a lumen-apposing metal stent maldeployed in the pancreatic fluid collection.

Real-time retrieval and repositioning of a lumen-apposing metal stent maldeployed in the pancreatic fluid collection.

A Novel Module Based Method of Teaching Electrocardiogram Interpretation for Emergency Medicine Residents.

A Novel Module Based Method of Teaching Electrocardiogram Interpretation for Emergency Medicine Residents.

A Double Random Matrix Design Model for Fractal Art Patterns Based on Visual Characteristics

This paper adopts the method of visual characteristics of the double random matrix to conduct in-depth research and analysis on the design of fractal art patterns. For the practical application needs in fractal graphic design, a method is proposed to automatically extract the core base pattern based on fractal graphic content and generate a four-sided continuous pattern. The method first uses the Canny operator for edge detection to analyze the area of the main pattern. Then, it uses a grayscale cogeneration matrix to extract and analyze the graphic texture features, based on which the best splicing method is selected to splice the extracted pattern, and then, it achieves two splicing methods of flat row and staggered four-sided continuous pattern. The method has good practicality with low complexity and high versatility under the premise of ensuring the beauty of the generated four-sided continuous pattern. It can assist designers to design patterns, improve efficiency, and save design costs. In this paper, we improve the existing image segmentation methods, adopt two segmentation methods, namely quadratic tree segmentation and HV segmentation, propose a new local codebook selection strategy, and study the degree of self-adaptation of different methods to images in terms of segmentation methods and local codebook selection strategies. It makes the network unable to train efficiently on long text prediction problems. Finally, the improved algorithm of this paper is tested on the standard and living image libraries, and the experimental results show that the use of local codebooks makes the image coding speed significantly improved compared with the fixed fractal. In the face of the image to be retrieved, it is only necessary to perform the coding operation to obtain the fractal code to perform similarity matching, which can meet the requirement of real-time retrieval. Applying the improved distance formula, the search accuracy obtained on the test gallery is significantly better than that of the grayscale histogram algorithm.

Perancangan Sistem Informasi Bank Darah Menggunakan Basis Data NoSQL

The existence of a blood exchange transaction process through a system carried out by the community, causing storing and managing data on a large scale is now causing problems in terms of scalability for blood bank managers in Yogyakarta. The process of blood transactions carried out by PMI units and hospitals at any time, makes the structure of relations in the blood banking system more complicated. In fact, every PMI unit and hospital in Yogyakarta requires a real-time data collection and storage process, considering that access to mobility of blood transactions is carried out almost 24 hours a day. Implementing an information system using a non-relational database model, is an alternative in the process of simplifying the relational structure in data relationships, this is because the non-relational database uses a NoSQL database model that provides support for database speed so that it remains optimal. In the research conducted, an information system was created that applied a non-relational database model to a case study of a blood bank information system. Where the NoSQL database is suitable for blood bank systems because it has high performance and is non-relational with real-time data storage and retrieval processes. The research conducted resulted in a blood bank information system that was developed using the Firebase database, where this system can display some data from the database such as viewing blood stocks, hospitals, blood donor events, and other information that is carried out in real time.

On understanding the impacts of shared public transportation on urban traffic and road safety using an agent-based simulation with heterogeneous fleets: a case study of Casablanca city.

Simulation and computer modeling have a key role in understanding transportation systems. Focusing on the main system, real-time retrieval of outputs based on mutual interactions of the whole autonomous entities makes the agent-based simulation very promising. This paper deals with an agent-based simulation to investigate and evaluate the potential impacts of implementing Shared Public Transports (SPT) in urban areas. Such a system is intended to integrate the two flows of passengers and containerized freights in Public Transportation (PT) patterns towards more sustainable, efficient, and socially suitable mobility. The proposed model is coupled with a stochastic process in order to provide a range of real-world data of Casablanca city (Morocco) based on institutional surveys. In this respect, two urban transportation systems of freight are tested: (1) the conventional transportation system, (2) the SPT system with heterogeneous fleets. In an effort to sustain efficient and safe movements, this paper examines SPT performances according to a set of key evaluation metrics. Results show that PT stopping remains the most relevant factor when evaluating metrics of the number of waiting containers and waiting time of demand by rates of 82.440% and 62.580%, respectively. Such a waiting containers metric is significantly affected by the volume of demand to transport per time slot by a rate of 78.140%. Under SPT, traffic congestion is the main factor to consider in managing PT with a rate of 65.690% in order to reduce potential accidents. However, demand volume could increase the on-street illegal parking metric by 90.070%. More details are provided below.

An Internet of Things based scalable framework for disaster data management

In recent years, undesirable disasters attacked the cities frequently, leaving heavy casualties and serious economic losses. Meanwhile, disaster detection based on the Internet of Things(IoT) has become a hot spot that benefited from the established development of smart city construction. And the IoT is visibly sensitive to the management and monitoring of disasters, but massive amounts of monitoring data have brought huge challenges to data storage and data analysis. This article develops a new and much more general framework for disaster emergency management under the IoT environment. The framework is a bottom-up integration of highly scalable Raw Data Storages(RD-Stores) technology, hybrid indexing and queries technology, and machine learning technology for emergency disasters. Experimental results show that hybrid index and query technology have better performance under the condition of supporting multi-modal retrieval, and providing a better solution to offer real-time retrieval for the massive sensor sampling data in the IoT. In addition, further works to evaluate the top-level sub-application system in this framework were performed based on the GPS trajectory data of 35,000 Beijing taxis and the volumetric ground truth data of 7,500 images. The results show that the framework has desirable scalability and higher utility.

Rapid Earthquake Source Description Using Variometric-Derived GPS Displacements toward Application to the 2019 Mw 7.1 Ridgecrest Earthquake

AbstractUsing near-field high-rate Global Positioning System (GPS) displacements to invert for earthquake fault slips in real time has the potential to improve the accuracy of earthquake early warning or tsunami early warning. For such applications, real-time retrieval of high-accuracy GPS displacements is essential. Here, we report on rapid modeling of the 2019 Mw 7.1 Ridgecrest earthquake with real-time GPS displacements derived from a variometric approach with readily available broadcast ephemeris. This method calculates station variations in real time by differencing continuous phase observations and does not rely on precise orbit and clock information. The phase ambiguity is also removed, and thus the method does not suffer from a relatively long convergence time. To improve the accuracy of variometric displacements, we use a local spatial filter to decrease the influence of residual errors that cannot be removed completely by the time difference. We invert for the centroid moment tensor, static fault slips, and fault rupture process from the derived displacements. Our results show that all inverted models are available within about 65 s after the origin time of the earthquake and are comparable with models inverted by real-time precise point positioning displacements. This study highlights the great value of variometric displacements for the rapid earthquake source description with only broadcast ephemeris.

RT-RCT: an online tool for real-time retrieval of connected things

In recent years, internet of things (IoT) represents a giant and a promoter area in innovation and engineering fields. IoT devices are spread in various fields and offer advanced services which assist their users to monitor and control objects remotely. IoT has a set of special characteristics such as dynamic, variety of data and huge scale which introduces a great challenge in the field of retrieval technologies, more precisely real-time retrieval. This paper addresses the issue of real-time retrieval of connected things and tries to propose an innovative solution which allows the retrieval of these things and their descriptive data. The paper proposes an on-line tool for real-time retrieval of connected things and their descriptive data based on network port scanning technique. The performance of this tool proves to be powerful under normal conditions, however more tests must be implemented in the aim to improve the proposed solution. The tool resulted from this work appears to be promising and can be used as a reference by network administrators and IT security managers for the development of new security mechanisms and security reinforcement.

A new zenith hydrostatic delay model for real-time retrievals of GNSS-PWV

Abstract. The quality of the zenith hydrostatic delay (ZHD) could significantly affect the accuracy of the zenith wet delay (ZWD) of the Global Navigation Satellite System (GNSS) signal, and from the ZWD precipitable water vapor (PWV) can be obtained. The ZHD is usually obtained from a standard model – a function of surface pressure at the GNSS station. When PWV is retrieved from the GNSS stations that are not equipped with dedicated meteorological sensors for surface pressure measurements, blind models, e.g., the global pressure and temperature (GPT) models, are commonly used to determine the pressures for these GNSS stations. Due to the limited accuracies of the GPT models, the ZHD obtained from the model-derived pressure value is also of low accuracy, especially in mid- and high-latitude regions. To address this issue, a new ZHD model, named GZHD, was investigated for real-time retrieval of GNSS-PWV in this study. The ratio of the ZHD to the zenith total delay (ZTD) was first calculated using sounding data from 505 globally distributed radiosonde stations selected from the stations that had over 5000 samples. It was found that the temporal variation in the ratio was dominated by the annual and semiannual components, and the amplitude of the annual variation was dependent upon the geographical location of the station. Based on the relationship between the ZHD and ZTD, the new model, GZHD, was developed using the back propagation artificial neural network (BP-ANN) method which took the ZTD as an input variable. The 20-year (2000–2019) radiosonde data at 558 global stations and the 9-year (2006–2014) COSMIC-1 (Constellation Observing System for Meteorology, Ionosphere, and Climate) data, which were also globally distributed, were used as the training samples of the new model. The GZHD model was evaluated using two sets of references: the integrated ZHD obtained from sounding data and ERA5 reanalysis data. The performance of the new model was also compared with GPT3, the latest version. Results showed the new model outperformed GPT3, especially in mid- and high-latitude regions. When radiosonde-derived ZHD was used as the reference, the accuracy, which was measured by the root mean square error (RMSE) of the samples, of the GZHD-derived ZHD was about 21 % better than the GTP3-derived ones. When ERA5-derived ZHD was used as the reference, the accuracy of the GZHD-derived ZHD was about 30 % better than GPT3-derived ZHD. In addition, the real-time PWV derived from 41 GNSS stations resulting from GZHD-derived ZHD was also evaluated, and the result indicated that the accuracy of the PWV was improved by 21 %.

Discrete Semantics-Guided Asymmetric Hashing for Large-Scale Multimedia Retrieval

Cross-modal hashing technology is a key technology for real-time retrieval of large-scale multimedia data in real-world applications. Although the existing cross-modal hashing methods have achieved impressive accomplishment, there are still some limitations: (1) some cross-modal hashing methods do not make full consider the rich semantic information and noise information in labels, resulting in a large semantic gap, and (2) some cross-modal hashing methods adopt the relaxation-based or discrete cyclic coordinate descent algorithm to solve the discrete constraint problem, resulting in a large quantization error or time consumption. Therefore, in order to solve these limitations, in this paper, we propose a novel method, named Discrete Semantics-Guided Asymmetric Hashing (DSAH). Specifically, our proposed DSAH leverages both label information and similarity matrix to enhance the semantic information of the learned hash codes, and the ℓ2,1 norm is used to increase the sparsity of matrix to solve the problem of the inevitable noise and subjective factors in labels. Meanwhile, an asymmetric hash learning scheme is proposed to efficiently perform hash learning. In addition, a discrete optimization algorithm is proposed to fast solve the hash code directly and discretely. During the optimization process, the hash code learning and the hash function learning interact, i.e., the learned hash codes can guide the learning process of the hash function and the hash function can also guide the hash code generation simultaneously. Extensive experiments performed on two benchmark datasets highlight the superiority of DSAH over several state-of-the-art methods.