Big Machine Research Articles

Civic education reform based on deep reinforcement learning model

Abstract The integration of artificial intelligence technology into education is an inevitable trend of scientific progress and educational reform, and how to use artificial intelligence technology and ideological and political education reform is called a key research direction in the education sector. Aiming at the problems of cold start in personalized recommendation system, lack of interpretability of recommendation results, and ignoring the implicit features of the course for better acceptance of recommendation results by learners, the BPRMF model based on deep learning is proposed to be applied to the problem of recommendation of Civics and Political Science course, which not only models learners’ preferences and combines with course attribute features to generate recommendation rating ranking list and provide personalized recommendation service. Then the study of Civics education reform is conducted, mainly analyzing the change in teaching methods based on big data, machine learning, and deep learning technologies to promote secondary school students. The performance of the BPRMF model is evaluated in comparison with the BPRMF model under different k values. It is concluded that the accuracy rate of the BPRMF model is 8.9%~12.01% higher than UBCF and 8.07%~10.26% higher than IBCF, but with the increase of k value, the recall rate will gradually pull away from other models and optimize the recommendation system to some extent. This study is beneficial to ideological education in the implementation process to better utilize the opportunities, meet the challenges, and develop efficiently.

Legal aspects of functional security standardisation of the Internet of Things

IoT technologies provide smart things with the ability to make decisions in the management of physical objects using intelligence and consensus. To support the Internet of Things, technologies such as built-in devices, cloud and fog computing, big data processing, machine learning, and artificial intelligence are used to produce intelligent physical objects. A review of existing security infrastructures for IoT-based intelligent environments shows that every connected device can be a potential entry point for an attack.
 An overview of the key aspects of security standards for smart environments based on the Internet of Things has been provided in the following areas: potential solutions, intelligent environments, limits of security assessment, open issues and challenges. Additional research on the development of methodological and technological standardisation measures in the field of interoperability of heterogeneous IoT devices is an urgent task in order to start further discussions on the development of new security standards and certification infrastructure for smart environments based on the IoT.
 Based on the analysis of the existing problems of implementing the Internet of Things, the methodological and technological features of legal regulation of intellectual environments have been studied. The structures of standardisation of networks and services of the IoT environments at the regional, European and global international levels have been considered.
 The architecture of the Internet of Things environments has been defined as a multi-level, heterogeneous system with a complex topology and the use of innovative technologies. The single phenomenon of IoT security has been identified as a complex concept that includes functional security and information security with their interconnection, contradictions, challenges and risks.
 The functional security of the Internet of Things has been studied in terms of the security function, security completeness and resilience, which are subject to regulation in the technical requirements for the product being designed. An aspect model of IoT interoperability has been presented and examples of its application in terms of interrelated components (transport, syntactic, semantic, behavioural, and policy aspects) have been given.
 An assessment of generally accepted practices and risks of creating regulatory documents (standards, instructions, methodological materials) in the field of functional security of the Internet of Things has been carried out. Recommendations for the introduction of a scientifically based approach to national standardisation of IoT security and measures to address the problem of interoperability of heterogeneous IoT devices have been provided.

Opportunities and Challenges of 5G Network Technology towards Precision Medicine.

Moving away from traditional "one-size-fits-all" treatment to precision-based medicine has tremendously improved disease prognosis, accuracy of diagnosis, disease progression prediction and targeted-treatment. The current cutting-edge of 5G network technology is enabling a growing trend in precision medicine to extend its utility and value to the smart healthcare system. The 5G network technology will bring together big data, artificial intelligence and machine learning to provide essential levels of connectivity to enable a new health ecosystem towards precision medicine. In the 5G-enabled health ecosystem, its applications involve predictive and preventative measurements which enable advances in patient personalization. This review aims to discuss the opportunities, challenges and prospects posed to 5G network technology in moving forward to deliver personalized treatments and patient-centric care via precision medicine approach.

Modeling potential wetland distributions in China based on geographic big data and machine learning algorithms

ABSTRACT Climate change and human activities have reduced the area and degraded the functions and services of wetlands in China. To protect and restore wetlands, it is urgent to predict the spatial distribution of potential wetlands. In this study, the distribution of potential wetlands in China was simulated by integrating the advantages of Google Earth Engine with geographic big data and machine learning algorithms. Based on a potential wetland database with 46,000 samples and an indicator system of 30 hydrologic, soil, vegetation, and topographic factors, a simulation model was constructed by machine learning algorithms. The accuracy of the random forest model for simulating the distribution of potential wetlands in China was good, with an area under the receiver operating characteristic curve value of 0.851. The area of potential wetlands was 332,702 km2, with 39.0% of potential wetlands in Northeast China. Geographic features were notable, and potential wetlands were mainly concentrated in areas with 400–600 mm precipitation, semi-hydric and hydric soils, meadow and marsh vegetation, altitude less than 700 m, and slope less than 3°. The results provide an important reference for wetland remote sensing mapping and a scientific basis for wetland management in China.

Understanding street-level urban vibrancy via spatial-temporal Wi-Fi data analytics: Case LivingLine Shanghai

Urban vibrancy is a topic of great concern in the field of urban design and planning. However, the definition and measurement of urban vibrancy have not been consistently and clearly followed. With the development of technologies such as big data and machine learning, urban planners have adopted new methods that enable better quantitative evaluation of urban performance. This research attempts to quantify the impact on the urban vibrancy of the urban interventions introduced by the LivingLine project in a residential neighborhood renovation made in Siping Street, Shanghai. We use Wi-Fi probes to process collected mobile phone data and segment people into different categories according to commuting patterns analysis. We use a pre-trained random forest model to determine the specific locations of each person. Subsequently, we analyze the behavior patterns of people from stay points detection and trajectory analysis. Through statistical models, we apply multi-linear regression and find that urban intervention (well-curated and defined lab events deployed in the street) and people’s behavior are positively correlated, which helps us to prove the impact of urban intervention on street dynamics. The research proposes a novel, evidence-based, low-cost methodology for studying granular behavior patterns on a street level without compromising users’ data privacy.

Does it help to provide such posting content for interaction? An empirical study of physical and virtual goods branding

<p>The purpose of this study was to analyze several brands offering physical and virtual products to determine differences in content marketing, as well as the impact of content cues on brand awareness. An analytical framework examining the relationship between content messaging, cues, and positioning was also developed to investigate social media marketing and brand positioning. The study combines big data techniques, artificial intelligence and machine learning applications, data exploration, disambiguation, and model prediction techniques to observe public behavior and preferences. This study was intended to highlight the importance of functional cues (message recognition) and symbolic cues (positive emotional response) in brand communication, and the findings suggest that brands on social media platforms can use relevant messaging to stimulate brand awareness and facilitate user interaction. In summary, this study contributes to an understanding of key messaging characteristics of branding on social media, explores the differences in user behavior across brands, and documents the impact of cues on user engagement. The results demonstrate that advanced data analysis techniques can be used to extract representative keywords and determine their impact on brand interactions in the context of physical and virtual products. </p> <p> </p>

Evaluation of smart farm training for extension officers to support digitalizing era

Smart farming is an agricultural concept based on precision agriculture. It utilizes technology automation supported by big data management, machine learning or artificial intelligence, and the Internet of Things to improve the quality and quantity of agricultural production. In its implementation, extension workers play a vital role as the vanguard of this program escort. Therefore, increasing the capacity of extension workers in smart farming is very necessary. This paper evaluated several aspects of smart farming training for extension workers. This paper uses secondary data from the evaluation form of 30 participants collected from Batangkaluku Agricultural Training Centre. Results showed that male extension officers dominated the training participants (70%). The subjects/training modules can be mastered by participants with scores>3.4 out of 5. The training can increase participants’ comprehension of the material up to 2.75x higher. The satisfaction level was above 4 out of 5. The findings can help the organizing committee in improving related aspects. Increased capacity building of agriculture extension officers by such training was expected to overcome the gap in the information of technology innovation from researchers to farmers.

Future of Pharmaceutical Marketing in India-An Extensive Review

Pharmaceutical marketing is becoming more and more personal as businesses aim to adjust their goods and services to the specific requirements of each patient. This personalization is made possible by technological advancements, which make use of big data, artificial intelligence, and machine learning. Pharmaceutical marketing is also changing as a result of digitalization. To engage with clients, businesses are investing in online platforms, social media, and mobile apps. The transition to digital marketing is a result of customers' shifting habits, who are increasingly looking online for healthcare information and guidance. Another significant factor influencing the future of pharmaceutical marketing is regulatory developments. Fresh legislation are being passed by governments all over the world in order to protect patients and guarantee the efficacy and safety of medications. This is- leading to greater transparency and accountability in the industry, as well as increased competition and innovation. Patient empowerment is also a significant trend in pharmaceutical marketing, with patients becoming more involved in their own healthcare decisions. This is driven by a growing awareness of the importance of patient-centered care, as well as the increasing availability of health information online.

ESSCC: A new multi-scale and extensively applicable evaluation system for the construction of sponge cities

Sponge cities are actively being built in China to combat urban flooding, and 30 pilot cities (regions) have been established since 2015, serving as a guide for further research. In order to examine the intrinsic links between urban (regional) characteristics, urban planning, sponge city construction metrics, urban ecological carrying capacity, and sustainable development, this study integrates big data and machine learning. For the evaluation of sponge city construction schemes, we combined Artificial Hierarchical Processing (AHP), Gray Correlation Analysis (GCA), and Back Propagation Neural Networks (BPNN) into a multi-scale model-coupled qualitative and quantitative multiple models coupling system. An evaluation system for sponge cities construction (ESSCC), which can be used on a multilingual system, and a sponge city evaluation index system based on ecological carrying capacity and sustainable development have been developed. The system could be used to advance the assessment and optimization of sponge city construction plans in accordance with local conditions from the perspectives of guaranteeing ecological function, ensuring a baseline for natural resource utilization and environmental safety and quality, safeguarding ecological carrying capacity, and ensuring sustainable development. The system is expected to serve as an effective and scientific basis for plan formulation, and to offer direction and technical support for the promotion of sponge cities.

Intelligent manufacturing quality prediction model and evaluation system based on big data machine learning

This study addresses the challenges in the development of intelligent manufacturing by constructing a quality prediction model and evaluation system. To build the quality prediction model and evaluation system, we effectively investigated the construction of the intelligent manufacturing quality prediction model and evaluation system using extreme learning machine neural network and particle swarm optimization algorithms, combined with a big data machine learning system. The prediction results of the system were experimentally analysed to verify its performance. The experimental data showed that the prediction results of the system for each evaluation index of product quality were consistent with the actual product quality detection results. Importantly, the prediction results of the system can meet the requirements and are of great significance to the development of intelligent manufacturing.

A Novel Political Optimizer-Based Feature Selection with an Optimal Machine Learning Model for Financial Crisis Prediction

In today’s digital environment, business intelligence advances make it difficult to stay competitive and up to date on business trends. Decision-making in the financial industry is increasingly being powered by big data and machine learning. A decision-making process may be thought of as any sequence of processes that an individual goes through in order to select the option or course of action that is most suitable to meet their needs and necessities. The ability to anticipate the onset of a financial crisis is a significant economic phenomenon. A nation’s economic development and strength can be gauged by its capacity to provide an accurate assessment of the number of failed firms and the frequency with which they fail. The economics of the globe have been ravaged by recent global crises like as the COVID-19 pandemic and other recent environmental, financial, and economic disasters, which have marginalized efforts to construct a maintainable economy and civilization. The health and growth of a nation’s economy can be determined by precisely estimating the number of enterprises that will fail and the number that will succeed. Historically, there have been numerous strategies for constructing a successful financial crisis prediction (FPC) method. Effectively predicting business failures is a gauge of a country’s economic health. Several strategies are available for effective FCP. Classification performance, forecast accuracy, and legality are insufficient for practical use. Several of the suggested methods work for some issues. The specific dataset is not expandable. To improve classification, design a good prediction model adaptable to several datasets. An effective financial crisis prediction method (FPC) requires the right qualities. ML models can also be used to classify a company’s financial health. This research presents political optimizer-based feature selection (POFS) with optimal cascaded deep forest (OCDF) for FCP in big data environments. Hadoop Map Reduce handles huge datasets. POFS reduces computing complexity by handling feature selection. POFS is an original FCP algorithm categorization using OCDF. SFO is used to optimize CDF model parameters. A thorough simulation study was performed to evaluate POFS performance on benchmark datasets OCDFs. The results confirmed the POFS-OCDF method’s superiority over state-of-the-art approaches. With an outstanding sensitivity of 0.912, specificity of 0.953, accuracy of 0.944, F-score of 0.930, and Matthews correlation coefficient (MCC) of 0.912, the proposed POFS-OCDF technique has shown optimum results. The experimental results demonstrated that the POFS-OCDF technique outperformed other recently developed strategies on a variety of criteria. As previously stated, Sunflower optimization (SFO) is also used to tune the Cascaded Deep Forest (CDF) parameters. A detailed simulation analysis is performed based on the benchmark dataset to evaluate the higher classification efficiency of the POFS-OCDF technique. The invention of the POFS algorithm for FCP exemplifies the work’s originality.

Blockchain technology applications in waste management: Overview, challenges and opportunities

Rapid population growth and urbanisation have accelerated waste generation, and effective waste management has become a major challenge worldwide. With advances in technology and management methods, waste management strategies have begun embracing digitalisation, leveraging the Internet of Things (IoT), big data analytics, cloud/edge computing, machine learning, 5G communication, and blockchain technologies. Amongst them, the blockchain technology has the structural features of achieving information security and integrity without central guarantees. Blockchain also meets the data record/storage needs of waste management and the design of new mechanisms for effective waste management. These benefits make blockchain an attractive technology in the field of waste management, with researchers and practitioners alike investigating its broad applications to support sustainable waste management. However, this emerging technology has not yet been widely accepted by potential users. To further champion the application of blockchain technology, this review paper provides a systematic overview of the various pathways in which the technology has been applied in the waste management industry and further discusses its related challenges and opportunities via considering the promising prospect of combining blockchain technology with IoT, artificial intelligence (AI) and life cycle assessment (LCA). This review also provides insights for interpreting some emerging applications of blockchain in the field of waste management and clarifying the research paths in the context of blockchain, digitalised waste management, and circular economy.

Artificial intelligence for dementia drug discovery and trials optimization.

Drug discovery and clinical trial design for dementia have historically been challenging. In part these challenges have arisen from patient heterogeneity, length of disease course, and the tractability of a target for the brain. Applying big data analytics and machine learning tools for drug discovery and utilizing them to inform successful clinical trial design has the potential to accelerate progress. Opportunities arise at multiple stages in the therapy pipeline and the growing availability of large medical data sets opens possibilities for big data analyses to answer key questions in clinical and therapeutic challenges. However, before this goal is reached, several challenges need to be overcome and only a multi-disciplinary approach can promote data-driven decision-making to its full potential. Herein we review the current state of machine learning applications to clinical trial design and drug discovery, while presenting opportunities and recommendations that can break down the barriers to implementation.

Modeling urban scale human mobility through big data analysis and machine learning

Modeling urban scale human mobility through big data analysis and machine learning

Low Carbon Consumer Lending Fintech Product Design Report

In short, green growth will play a central role on the road to a more resilient recovery, and financial technology will be a key driver. Fintech, as an essential support in building a green financial system, will play a key role in supporting green finance to serve the real economy more efficiently.This article focuses on the design of low-carbon consumer credit as a financial technology product, given the high costs of green transformation for businesses and the financing and credit risks they face. Through big data, cloud computing, machine learning and other technologies, the product will help businesses to go green, create value for users and bring positive energy to society. In response to the national “dual carbon” target, low-carbon consumer credit will become an important driver to foster the development of emerging industries. This design differs from generic financial technology products in that the design focuses on green, economic benefits, while taking into account corporate social responsibility, and the use of machine learning to create an anti-fraud system throughout credit risk management, loan withdrawal, and detection of all aspects to ensure maximum security for users.

Approach strategies and application of metabolomics to biotechnology in plants.

Metabolomics refers to the technology for the comprehensive analysis of metabolites and low-molecular-weight compounds in a biological system, such as cells or tissues. Metabolites play an important role in biological phenomena through their direct involvement in the regulation of physiological mechanisms, such as maintaining cell homeostasis or signal transmission through protein-protein interactions. The current review aims provide a framework for how the integrated analysis of metabolites, their functional actions and inherent biological information can be used to understand biological phenomena related to the regulation of metabolites and how this information can be applied to safety assessments of crops created using biotechnology. Advancement in technology and analytical instrumentation have led new ways to examine the convergence between biology and chemistry, which has yielded a deeper understanding of complex biological phenomena. Metabolomics can be utilized and applied to safety assessments of biotechnology products through a systematic approach using metabolite-level data processing algorithms, statistical techniques, and database development. The integration of metabolomics data with sequencing data is a key step towards improving additional phenotypical evidence to elucidate the degree of environmental affects for variants found in genome associated with metabolic processes. Moreover, information analysis technology such as big data, machine learning, and IT investment must be introduced to establish a system for data extraction, selection, and metabolomic data analysis for the interpretation of biological implications of biotechnology innovations. This review outlines the integrity of metabolomics assessments in determining the consequences of genetic engineering and biotechnology in plants.

Identifying multiple soil pollutions of potentially contaminated sites based on multi-gate mixture-of-experts network

With the rapid increase in the amount and sources of big data, using big data and machine learning methods to identify site soil pollution has become a research hotspot. However, previous studies that used basic information of sites as pollution identification indexes mainly have problems of low accuracy and efficiency when conducting complex model predictions for multiple soil pollution types. In this study, we collected the environmental data of 199 sites in 6 typical industries involving heavy metal and organic pollution. After feature fusion and selection, 10 indexes based on pollution sources and pathways were used to establish the soil pollution identification index system. The Multi-gate Mixture-of-Experts network (MMoE) were constructed to carry out the multi-tasks of soil heavy metals, VOCs and SVOCs pollution identification simultaneously. The SHAP framework was used to reveal the importance of pollution identification indexes on the multiple outputs of MMoE and obtain their driving factors. The results showed that the accuracies of MMoE model were 0.600, 0.783 and 0.850 for soil heavy metals, VOCs and SVOCs pollution identifications, respectively, which were 0–20 % higher than their accuracies of BP neural networks of single tasks. The indexes of raw material containing organic compounds, enterprise scale, soil pollution traces and industry types have the different significant importance on site soil pollutions. This study proposed a more efficient and accurate method to identify site soil pollutions and their driving factors, which offers a step towards realizing intelligent identification and risk control of site soil pollution globally.

The study on systemic risk of rural finance based on macro–micro big data and machine learning

It’s the basic premise of promoting the healthy development of rural finance and strengthening macro-prudential supervision to measure the systemic risk of rural finance accurately. We establish the dynamic factor CAPM and make an all-round and multi-angle quantitative study on the systemic risk of rural finance in China by constructing macro–micro index system and using machine learning to reduce the dimension of high-dimensional data. Our results show that the dynamic factor CAPM of using macro–micro big data can evaluate systemic risk of rural finance more comprehensively and systematically, and machine learning performs well in processing high-dimensional data. In addition, China's rural financial systemic risk is stable compared with the Shanghai and Shenzhen main markets, but it is also susceptible to macro and micro influenced factors. Finally, it is pointed out that the early warning system of rural financial systemic risk could be constructed at macro and micro level, respectively.

Neonatologie in tijden van big data, machine learning en artificiële intelligentie: potentiële toepassingen gebruikmakend van continu gemonitorde vitale parameters. Een systematische review.

Neonatology in times of big data, machine learning and artificial intelligence: potential applications using continuously monitored vital signs. A systematic review Background: At the neonatal intensive care unit vital signs are continuously monitored, which yields a huge amount of values. At the moment, these are mainly used in a real-time bedside manner when values cross fixed boundaries triggering an alarm, also general trends are followed. Subtle patterns which may be a first sign of disease or clinical condition can be missed. By using scientific revolutions as big data, machine learning and artificial intelligence it may be possible to extract much more information from this amount of data. Objective: We make an overview of possible applications more thoroughly using continuously monitored vital signs in the NICU, developed by using scientific evolutions as big data, machine learning or artificial intelligence. Methods: A systematic search is carried out in four databases, PRISMA-guidelines are followed. The retained articles are analysed regarding the topic, the used methods, the results and possible implementation. Results: We included 35 articles. The investigated topics and used methods were very diverse. Only a minority of possible applications are already studied enough to enable use in daily practice. Conclusion: Applications using continuously monitored vital signs, developed by using scientific evolutions as big data, machine learning and artificial intelligence are promising and a lot of research is being carried out. Nevertheless, implementation is still very limited.

Artículo traducido] Modelo de atención farmacéutica en medicina de precisión en China

Pharmacy service is to provide individualized pharmaceutical care for patients, which should follow the current evidence-based pharmacy, and constantly verify the evidence and then produce new evidence. In pharmaceutical care, differences are often found in the efficacy and adverse reactions of drugs among individuals, even within individuals, which are closely related to patients’ genetics, liver and kidney functions, disease states, and drug interactions. Back in the 1980s, therapeutic drug monitoring (TDM) has been applied to routinely monitor the blood drug concentration of patients taking antiepileptic drugs or immunosuppressants after transplantation to provide individualized dosage recommendations and accumulate a large amount of pharmacokinetic (PK)/pharmacodynamic (PD) data. As individualized pharmaceutical care proceeds, the concept of precision medicine was introduced into pharmacy services in combination with evidence-based pharmacy, PK/PD theories, and big data to further promote the TDM technology and drugs, and carry out pharmacogenomics analysis. The TDM and pharmacogenomics have been applied gradually to the fields of antimicrobial, antitumor, and antipsychotic drugs and immunosuppressants. Based on the concept of precision pharmacy, we adopted approaches including PK/PD, quantitative pharmacology, population pharmacokinetics, and big data machine learning to provide more personalized pharmacy services, which is mainly for special patients, such as critical patients, patients with interaction risk of multiple drugs, patients with liver and renal insufficiency, pregnant women, children, and elderly patients. As the service pattern of precision pharmacy has been constructed and constantly improved, better evidence in clinical practice will be produced to provide patients with better precision pharmacy service.