World Big Data Research Articles

Intelligent Anti-Money Laundering Transaction Pattern Recognition System Based on Graph Neural Networks

This paper presents a new Intelligent Anti-Money Laundering Transaction Pattern Recognition System based on Graph Neural Networks (GNNs). The proposed system addresses the limitations of traditional anti-money laundering (AML) by leveraging the power of image representation and deep learning techniques. We introduce general methods for creating financial networks based on different shapes, including structural and physical. A custom GNN architecture is designed, featuring heterogeneous graph convolution, listening mechanisms, and physical models to capture the exchange patterns. The system uses advanced engineering techniques to extract both local and global features of financial performance. The analysis of the world's big data shows that the best performance of our method, achieved 35.2% Money Laundering Detection Rate (MLDR) in the top 1% of business flag, do better way. The model interpretation is improved by analyzing the SHAP value, providing insight into the decision-making process. Case studies show the system's ability to uncover financial transactions, including deposits from cryptocurrency exchanges and smurfing operations. This research contributes to the advancement of AML practices by introducing more accurate, flexible, and effective solutions for investigating financial crimes in complex financial systems more.

Image classification-based transfer learning framework for image detection of IoT devices

For artificial intelligence (AI) applications, centralized learning on a cloud server and local learning on an internet-of-things device may suffer from data privacy leakage due to data sharing and inaccurate prediction due to limited computing resources. Transfer learning has been proposed as one potential solution to the world's big data problems. Transfer learning eliminates the need for each internet-of-things device to share local data with the cloud server during the training process. Instead, it can go through the training process on its own, using a cloud server's pre-trained model with high accuracy. As a result, despite its limited computing resources, the internet of things device can still predict with high accuracy. This paper proposes a transfer learning model for improving image detection accuracy on IoT devices with restricted computation. To obtain accurate image classification, a deep learning approach based on convolutional neural networks is used. The proposed method with freeze and unfreeze approaches achieves a higher validation accuracy (up to 43.6%) and a lower validation loss (up to 6.5 times) than the non-transfer learning method, according to simulation results using three relevant internet-of-things datasets.

How the National Health Insurance Coverage policy changed the use of lenvatinib for adult patients with advanced hepatocellular carcinoma: a retrospective cohort analysis with real world big data

BackgroundTo establish a long-term mechanism to control the cost burden of drugs, the Chinese government organized seven rounds of price negotiations for the national reimbursement drug list (NRDL) from 2016 to the end of 2022. The study aimed to evaluate the impact of the National Health Insurance Coverage (NHIC) policy on the use of lenvatinib as the first-line treatment for advanced hepatocellular carcinoma (HCC) within a specific medical insurance region from the micro perspective of individual patient characteristics.MethodsThe data of HCC patients that received lenvatinib from September 2019 to August 2022 was retrieved from the Medical and Health Big Data Center and longitudinally analyzed. Contingency table chi-square statistics and binary logistic regression analysis were used to compare the differences in the categorical variables. Interrupted time-series (ITS) regression analysis was performed to evaluate the changes in the utilization of lenvatinib over 36 months. Multiple linear regression was used to analyze the impact of receiving lenvatinib on the total hospitalization expenses of hospitalized patients with advanced HCC.ResultsA total of 12,659 patients with advanced HCC were included in this study. The usage rate of lenvatinib increased from 6.19% to 15.28% over 36 months (P < 0.001). By controlling the other factors, consistent with this, the probability of patients with advanced HCC receiving lenvatinib increased by 2.72-fold after the implementation of the NHIC policy (OR = 2.720, 95% CI:2.396–3.088, P < 0.001). Older, residency in rural areas, lack of fixed income, treatment at hospitals below the tertiary level, and coverage by urban-rural residents’ basic medical insurance (URRBMI) were the factors affecting the use of lenvatinib among patients with advanced HCC (P < 0.05). After the implementation of the NHIC policy, the total hospitalization expenses increased (Beta=-0.040, P < 0.001). However, compared to patients who received lenvatinib, the total hospitalization expenses were higher for those who did not receive the drug (US$5022.07 ± US$5488.70 vs. US$3701.63 ± US$4330.70, Beta = 0.062, P < 0.001).ConclusionsThe NHIC policy has significantly increased the utilization of lenvatinib. In addition, we speculate that establishing multi-level medical insurance systems for economically disadvantaged patients would be beneficial in improving the effectiveness of the NHIC policy in the real world.

M266 Establishment of biological variation and age-related reference interval model of 22 common biochemical analytes in elderly through real world big data mining

M266 Establishment of biological variation and age-related reference interval model of 22 common biochemical analytes in elderly through real world big data mining

Econometric Assessment of Institutional Quality in Mitigating Global Climate-Change Risk

Background: Environmental deterioration is the alarming situation that results from rapid urbanization and development. The rising temperature and climate volatility are accounted for by the massive carbon dioxide (CO2) emissions. The research on climate-change mitigation is trying to curtail the situations before they become irreversible and unmanageable. This study explores the role of institutions in mitigating climate change by moderating the impact of environmental quality on climate change risk. Methodology: Global data sets have been collected from world big data depositories like the World Economic Forum (WEF), the World Development Indicators (WDI), and the International Country Risk Guide (ICRG). Countries that are listed in WEF were used as the sample of the study. An analysis was based on 114 countries that are based on the availability of data. For estimation, descriptive statistics, correlation analysis, change effects, and a Panel Feasible Generalized Least Squares (FGLS) model were used for estimating the results. Results: The global assessment indicates that CO2 emissions increase the climate risk, but its impact can be reduced by increasing the quality of institutions. Additionally, an increase in renewable energy consumption and economic growth reduces the climate risk. Implications: It is an instrumental study that empirically investigated the role of institutions in reducing climate risk by moderating CO2 emissions. The results of this study will help policymakers to formulate policies regarding environmental protection.

Analysis of Qingkailing Injection in treatment of combined medication features of 2 147 cases of upper respiratory tract infection

Acute upper respiratory infection is one of the common infectious diseases,especially in the elderly people. Qingkailing Injection has the effect of clearing away heat and detoxifying. It can be used for external wind heat,upper respiratory tract infection,viral cold,etc. Based on 2 147 cases of upper respiratory tract infection patients using Qingkailing Injection in the medical electronic data warehouse of the information system of 16 large class-A hospitals constructed by the Institute of Basic Research in Clinical Medicine,China Academy of Chinese Medical Sciences,description analysis,Apriori calculation and recurrent network analysis were used to analyze the effect of Qingkailing Injection on upper respiratory tract infection. The clinical characteristics and the law of combined use of drugs can provide reference for the mining of clinical diagnosis and treatment characteristics and the construction of optimal and effective programs and paths. 2 147 patients with upper respiratory tract infection who used Qingkailing Injection were mostly middle-aged and elderly people over 45 years old,often combined with hypertension,ischemic cerebrovascular disease,coronary heart disease,diabetes,etc.; in treatment,it was more common to use Qingkailing Injection in combination with hormones,antipyretics and analgesics,antibiotics,nutritional support agents,antitussive,expectorant and antiasthmatic drugs,as well as traditional Chinese medicine Jiebiao agents and blood management agents. The combination of potassium chloride injection and cephalosporin injection is the most commonly used in combination with two kinds of Western medicine( 33. 2%); the combination of Shuanghuanglian and Ganmao Qingre Granules is the most commonly used in combination with two kinds of traditional Chinese medicine( 9. 13%); through the calculation of complex network group module,it is found that Qingkailing Injection is often associated with antibiotics,antipyretic and analgesic drugs,antitussive,expectorant and antiasthmatic drugs,antiviral drugs and anti infection drugs. Drugs,nutritional support agents,bronchodilators,immunomodulators and other chemical drugs are often used in combination with Chinese medicine,such as Jiebiao agents,expectorants,Qingre agents,resuscitation agents,Qufeng agents,tonics,Liqi agents,which may be related to both the treatment of upper respiratory tract infection and the basic diseases of middle-aged and elderly patients,with the theoretical characteristics of &quot; combination of disease and syndrome,corresponding formula and syndrome&quot;. Based on the real world big data complex network group module mining results provide clues for the clinical optimization scheme and path construction,and provide signals and ideas for further causal research.

A Topology Based Spatio-Temporal Map Algebra for Big Data Analysis

Continental and global datasets based on earth observations or computational models challenge the existing map algebra approaches. The available datasets differ in their spatio-temporal extents and their spatio-temporal granularity, which makes it difficult to process them as time series data in map algebra expressions. To address this issue we introduce a new map algebra approach that is topology based. This topology based map algebra uses spatio-temporal topological operators (STTOP and STTCOP) to specify spatio-temporal operations between topological related map layers of different time-series data. We have implemented several topology based map algebra tools in the open source geoinformation system GRASS GIS and its open source cloud processing engine actinia. We demonstrate the application of our topology based map algebra by solving real world big data problems using a single algebraic expression. This included the massively parallel computation of the NDVI from a series of 100 Sentinel2A scenes organized as earth observation data cubes. The processing was performed and benchmarked on a many core computer setup and in a distributed container environment. The design of our topology based map algebra allows us to deploy it as a standardized service in the EU Horizon 2020 project openEO.

Techniques, Tools and Applications of Graph Analytic

Graphs have acute significance because of poly-tropic nature and have wide spread real world big data appli-cations, e.g., search engines, social media, knowledge discovery, network systems, etc. Major challenge is to develop efficient systems to store, process and analyze large graphs generated by these applications. Graph analytic is important research area in big data graphs dealing with efficient extraction of useful knowledge and interesting patterns from rapidly growing big data streams. Tremendously huge and complex data of graph applications requires specially designed graph databases having special data structures and effective features for data modeling and querying. The manipulation of large size of data requires effective scalable and distributed computational techniques for efficient graph partitioning and communication. Researchers have proposed different analytical techniques, storage structures, and processing models. This study provides insight of different graph analytical techniques and compares existing graph storage and computational technologies. This work also assesses the perfor-mance, strengths and limitations of various graph databases and processing models.

Network analysis of surgical innovation: Measuring value and the virality of diffusion in robotic surgery.

BackgroundExisting surgical innovation frameworks suffer from a unifying limitation, their qualitative nature. A rigorous approach to measuring surgical innovation is needed that extends beyond detecting simply publication, citation, and patent counts and instead uncovers an implementation-based value from the structure of the entire adoption cascades produced over time by diffusion processes. Based on the principles of evidence-based medicine and existing surgical regulatory frameworks, the surgical innovation funnel is described. This illustrates the different stages through which innovation in surgery typically progresses. The aim is to propose a novel and quantitative network-based framework that will permit modeling and visualizing innovation diffusion cascades in surgery and measuring virality and value of innovations.Materials and methodsNetwork analysis of constructed citation networks of all articles concerned with robotic surgery (n = 13,240, Scopus®) was performed (1974–2014). The virality of each cascade was measured as was innovation value (measured by the innovation index) derived from the evidence-based stage occupied by the corresponding seed article in the surgical innovation funnel. The network-based surgical innovation metrics were also validated against real world big data (National Inpatient Sample–NIS®).ResultsRankings of surgical innovation across specialties by cascade size and structural virality (structural depth and width) were found to correlate closely with the ranking by innovation value (Spearman’s rank correlation coefficient = 0.758 (p = 0.01), 0.782 (p = 0.008), 0.624 (p = 0.05), respectively) which in turn matches the ranking based on real world big data from the NIS® (Spearman’s coefficient = 0.673;p = 0.033).ConclusionNetwork analysis offers unique new opportunities for understanding, modeling and measuring surgical innovation, and ultimately for assessing and comparing generative value between different specialties. The novel surgical innovation metrics developed may prove valuable especially in guiding policy makers, funding bodies, surgeons, and healthcare providers in the current climate of competing national priorities for investment.

Abstract PR409

Background & Objectives: With growing aging populations and increasing unmber of patients undergoing surgery, there are increased surgical complications that may not only influence quality of life of the patients but also cause additional economic burden to the family. A large number of clinical data are available nowaday, especially for elderly patients. However, these data have not been well developed for bettter perioperative management of the patients. All these may shed light on the potential role of real world big data study (RWBDS) of elderly patients in better evaluation and management of perioperative patients. It is of major importance to take advantage of large clincal data so as to obtain useful information for prognostic improvement of aged patients, which is also in line with the principles of health care economics. As an important part of a large clinical database, the perioperative database may provide solid and reliable basis for clinical practice. Therefore, we propose to establish a Perioperative Management and Outcome database of elderly patients so as to better management and improve the prognosis of elderly patients that scheduled for surgery. Our study may also provide evidence for future research and medical decision making. Materials & Methods: This is a multicenter, prospective, observational study in China. It is sponsored by Perioperative database project for geriatric patient information of Anesthesia of Chinese Society of Anesthesiology in South Center. Approximately 5,000 patients with gastrointestinal cancer (≥60 years) that scheduled for elective surgery will be selected from seven to ten large tertiary hospitals during April 2016 to May 2017. Clinical data, including age, gender, body mass index (BMI), medical history, anesthesia assessment, compound disease and etc, will be eatracted prospectively from the web-based registry form at preoperative days 2-7. The perioperative parameters and potential complications will be monitored on preoperative day 1, intraoperatively, and on postiperative day 7 or at the time of discharge of the patients. The patients will be followed up for clinical status and complications at 1, 6 and 12 months by phone call. Statistical analysis will be performed to identify the potential factors that influence the prioperative management and prognosis of the patients. Results: The primary endpoints of the study are the mortality and incidence of complications after surgery. The secondary end-points include cognitive function and quality of life of the patients on postoperative day 30, as well as potential prognostic factors. Conclusion: Perioperative Management and Outcome database of old patients is a large-scale nationwide registry in China. Rich data obtained from this prospective registry may help to evaluate the quality of perioperative care and thus provide better clinical care of elderly patients in China. Disclosure of Interest: None declared

Abstract PR410

Background & Objectives: With growing aging populations and patients undergoing surgery, the number of major surgery and critically ill patients has increased gradually, which in turn results in increased number of surgical complications that influence quality of life of patients and even cause additional economic burden to the family. All these may shed light on the potential role of real world big data study (RWBDS) of old patients in understanding and management of diseases. Since there are a large number of clinical data, especially in elderly patients, which, however, have not been well utilized to bettter management of the patients scheduled for surgery. It is essential to take advantage of large clincail data to obtain useful data to improve the prognosis of aged patients that in line with the principles of health economics. As an important part of a large clinical database, the perioperative databases may provide solid and reliable evidence for clinical practice. Therefore, we propose to establish the Perioperative Management and Outcome database of elderly patients so as to improve the perioperative management and prognosis of old patients that scheduled for surgery, which may also provide evidence for future research and medical decision making. Materials & Methods: This study is a multicenter, prospective, observational study in China sponsored by Perioperative database project for geriatric patients information of Anesthesia of Chinese Society of Anesthesiology in South Center. Around 5,000 patients with gastrointestinal cancer (≥60 years) that scheduled for elective surgerys will be selected from seven to ten large tertiary hospitals during April 2016 to May 2017. Clinical data, including age, gender, body mass index (BMI), medical history, anesthesia assessment and compound disease, and etc, will be collected prospectively using web-based registry form at preoperative days 2-7. The perioperative parameters and potential complications were monitored at preoperative day 1, during the operation, and at postiperative day 7 or discharge of patients. The patients were followed up for clinical conditions and complications by phone call 1, 6 and 12 months after surgery. Statistical analysis will be performed to identify the potential risk factors of the disease in Chinese old patients with gastrointestinal cancer. Results: The primary endpoints of the study are the prognosis and complications of the patients. The secondary end-points are cognitive function and quality of life of patients, as well as prognostic factors. Conclusion: Perioperative Management and Outcome database of old patients is a large-scale nationwide registry in China. Rich data collected from this prospective registry may provide the opportunity to evaluate the quality of perioperative care and provide better clinical care of elderly patients in China. Disclosure of Interest: None declared

A Proposed Architecture for Big Data Driven Supply Chain Analytics

Advancement in information and communication technology (ICT) has given rise to explosion of data in every field of operations. Working with the enormous volume of data (or Big Data, as it is popularly known as) for extraction of useful information to support decision making is one of the sources of competitive advantage for organizations today. Enterprises are leveraging the power of analytics in formulating business strategy in every facet of their operations to mitigate business risk. Volatile global market scenario has compelled the organizations to redefine their supply chain management (SCM). In this paper, we have delineated the relevance of Big Data and its importance in managing end to end supply chains for achieving business excellence. A Big Data-centric architecture for SCM has been proposed that exploits the current state of the art technology of data management, analytics and visualization. The security and privacy requirements of a Big Data system have also been highlighted and several mechanisms have been discussed to implement these features in a real world Big Data system deployment in the context of SCM. Some future scope of work has also been pointed out. Keyword: Big Data, Analytics, Cloud, Architecture, Protocols, Supply Chain Management, Security, Privacy.

METEOROLOGICAL DATA ANALYSIS USING HDINSIGHT WITH RTVS

Weather prediction is a vital application in meteorology and has been one of the most scientifically and technologically challenging problems across the world. As per survey weather reports generated are huge in amount and in unstructured format. There is need for analysis of real time weather data for giving predictions. Data Mining is the computer assisted process of digging through and analyzing enormous sets of data and then extracting the meaningful data. In today’s world Big Data processing is the need of an hour. Ability to represent and query data with little and no apparent structure arises in several fields. We have focused on three main algorithms that are important for prediction on any kind of data. Meteorological data analysis is a system which considers real time data while making predictions and giving out weather forecasts. It should be scalable, portable and should work on variety of client systems. It should be able to handle Big Data and give outputs according to visualization effect entered by the end user. The developer must have greatest privilege over all other users, including the weather forecasting personnel and authenticated users. Till date, various weather mobile applications have been developed using clustering and regression algorithms, but real time analysis is still a big challenge. There is also need of more accurate predictions based on any type of dataset. We propose a solution to this by using R programming language for analysis of weather data using Microsoft Azure HDInsight for good long term predictions. This solution can also be as a SMART CITY application.