Search

Abstract Background Our current understanding of the pathophysiology and management of sepsis is associated with a lack of progress in clinical trials, which partly reflects insufficient appreciation of the heterogeneity of this syndrome. Consequently, more patient-specific approaches to treatment should be explored. Aims To summarize the current evidence on precision medicine in sepsis, with an emphasis on translation from theory to clinical practice. A secondary objective is to develop a framework enclosing recommendations on management and priorities for further research. Sources A global search strategy was performed in the MEDLINE database through the PubMed search engine (last search December 2017). No restrictions of study design, time, or language were imposed. Content The focus of this Position Paper is on the interplay between therapies, pathogens, and the host. Regarding the pathogen, microbiologic diagnostic approaches (such as blood cultures (BCs) and rapid diagnostic tests (RDTs)) are discussed, as well as targeted antibiotic treatment. Other topics include the disruption of host immune system and the use of biomarkers in sepsis management, patient stratification, and future clinical trial design. Lastly, personalized antibiotic treatment and stewardship are addressed (Fig. 1). Implications A road map provides recommendations and future perspectives. RDTs and identifying drug-response phenotypes are clear challenges. The next step will be the implementation of precision medicine to sepsis management, based on theranostic methodology. This highly individualized approach will be essential for the design of novel clinical trials and improvement of care pathways. [ABSTRACT FROM AUTHOR]

Today, with the non-stop expansion of urbanization, mapping urban areas and monitoring their dynamic changes have become challenges for governments and also a hot topic for researchers. Remote sensing imageries play a key role in urban studies, the extraction of urban built-up areas, and monitoring their changes. A variety of studies have proposed methods for the extraction of regional, national, and global built-up areas. However, the majority of them used limited features and applied a manual sample selection strategy for classification, leading to time-consuming and low-efficient algorithms. This paper proposes a fully automatic procedure to real-time extract built-up areas by integrating the Luojia 1–01 nighttime lights (NTL) images, Sentinel-2 multispectral data, Sentinel-1 Radar images, and SRTM elevation data in cloud-computing Google Earth Engine. Firstly, potential built-up areas (PBA) and non-built-up areas (NBA) are obtained by applying Otsu and multi-level thresholding to some of the extracted spectral-textural-spatial (STS) features and by applying logical rules. Secondly, built-up and non-built-up samples are automatically selected and are used to train a Support Vector Machine (SVM) supervised classifier and to classify the hybrid feature set so that a preliminary classified map (PCM) can be obtained. Thirdly, the PCMs are automatically corrected using the non-built-up area, and morphological operations in the so-called post-classification to provide a refined classified map (RCM) and final built-up map. Four study areas in Northern America, Europe (Scandinavia), the Middle East, and Eastern Asia were selected to test the proposed method. Also, five state-of-the-art built-up products, accompanied by Google Earth images, were used as the reference data. The results indicate that the proposed method can accurately and automatically select samples and map built-up areas with a spatial resolution of 10 m. Its performance is validated with an average overall accuracy of 94.4% and an average Kappa coefficient of 0.89 and by visual comparison of our method results with other reference data. The proposed method has significant potential to be used in real-time extracting built-up areas and in monitoring their dynamic changes on national and global scales. [ABSTRACT FROM AUTHOR]

The tremendous growth of event dissemination over social networks makes it very challenging to accurately discover and track exciting events, as well as their evolution and scope over space and time. People have migrated to social platforms and messaging apps, which represent an opportunity to create a more accurate prediction of social developments by translating event related streams to meaningful insights. However, the huge spread of 'noise' from unverified social media sources makes it difficult to accurately detect and track events. Over the last decade, multiple surveys on event detection from social media have been presented, with the aim of highlighting the different NLP, data management and machine learning techniques used to discover specific types of events, such as social gatherings, natural disasters, and emergencies, among others. However, these surveys focus only on a few dimensions of event detection, such as emphasizing on knowledge discovery form single modality or single social media platform or applied only to one specific language. In this survey paper, we introduce multiple perspectives for event detection in the big social data era. This survey paper thoroughly investigates and summarizes the significant progress in social event detection and visualization techniques, by emphasizing crucial challenges ranging from the management, fusion, and mining of big social data, to the applicability of these methods to different platforms, multiple languages and dialects rather than a single language, and with multiple modalities. The survey also focuses on advanced features required for event extraction, such as spatial and temporal scopes, location inference from multi-modal data (i.e., text or image), and semantic analysis. Application-oriented challenges and opportunities are also discussed. Finally, quantitative and qualitative experimental procedures and results to illustrate the effectiveness and gaps in existing works are presented. • Classifying event detection with textual, spatial, temporal, and semantic features. • Defining event spatio-temporal evolution by considering incremental architectures. • Investigating fusion techniques from multiple data sources and multiple modalities. • Discussing various languages and dialects or language-independent mechanisms. • Presenting big data processing tools for scalable and efficient event detection. [ABSTRACT FROM AUTHOR]

• Gas turbine life management monitors and assesses turbine status and conditions. • Inlet and exit air passages impact gas turbine performance, not physical attributes. • Study gap: An incomplete gas-turbine model limits big data's predictive analysis. • Big data analytics drive optimized informed integrated health monitoring decisions for gas turbines. • Data mining extends gas turbine life by forecasting faults for the future. In addition to power generation, gas turbines (GT) are crucial components in many engineering applications, including those for aircraft, ships, and other machinery that needs a prime mover. One of the main concerns was predicting a comprehensive GT model, including intake, exit, and power-generator characteristics. Hence, this study provides a comprehensive review of GT's main components, parameters, faults, and predicting models using machine learning and data mining applications. Forty-four publications between 2014 and 2023 were chosen for this review study based on the primary keywords associated with the paper title. This study focuses solely on the GT model prediction aspects, considering the significance of field distribution, applications of data mining, research goals, benefits, constraints, and contributions to aviation, the oil and gas industry, and marine propulsion fields. Based on the examined studies, ANN, ELM, and KF applications show promise for potential GT life management. The typical limitations of GT life prediction, as observed in 93.2% of the review papers, involved the absence of a comprehensive GT model that incorporates all vibration factors and the use of substantial amounts of real data for predictive modelling. Another notable finding that underscores the knowledge gap in this area is the utilization of complete GT units to monitor unit life and facilitate life management. Apparently, the development of GT life management is still riddled with several limitations, which call for more improvement. [ABSTRACT FROM AUTHOR]

• Treat a problem of the imbalanced customer churn classification. • A new multi-strategy collaborative processing method IADASYN-FLCatBoost is proposed. • The traditional ADASYN algorithm is improved and an IADASYN algorithm is proposed. • The Focal Loss function is embedded into the CatBoost to form a new FLCatBoost. • Empirical analysis shows the proposed method performs better than similar methods. The rapid advancement of big data and artificial intelligence heralds a dual-edged era of opportunities and challenges for the banking sector. Indeed, enhancing a model's capability to accurately classify imbalanced datasets represents a critical challenge within the field of customer churn prediction (CCP). In this paper, to address the challenges presented by the problem of imbalanced customer classification, a new multi-strategy collaborative processing method named IADASYN-FLCatBoost is proposed from dual perspectives: data and algorithm. At the data level, the traditional Adaptive Synthetic (ADASYN) sampling is improved, that is, the LOF (Local Outlier Factor) algorithm is introduced to eliminate outliers, and the classification features are specially processed to synthesize new minority class samples, thus an improved ADASYN (IADASYN) algorithm is obtained. At the algorithm level, the Focal Loss is embedded into the CatBoost ensemble learning framework to form a new Focal Loss-CatBoost (FLCatBoost) to make a focal-aware, cost-sensitive version of imbalanced customer churn prediction. Moreover, the empirical analysis is conducted in conjunction with the credit card customer dataset obtained from the Kaggle platform. The results of the staged comparison experiments show that the proposed method IADASYN-FLCatBoost in this paper shows the best prediction performance. Comparing the proposed method with 5 other imbalanced classification algorithms and 20 classifiers composed of classical sampling methods and ensemble learning algorithms, it is verified that the classification effect of the proposed method performs best, and the values of Recall , F 1 score, G-mean and Area under Precision-Recall curve (AUPRC) have been significantly improved. In addition, further verification of the model also proves that the proposed method has certain generalizability and is still valid for other banks and customer churn datasets of other industries. [ABSTRACT FROM AUTHOR]

The selection of optimal design and the most efficient operational parameters for energy devices constitute a priority task for sustainable development and increasing energy efficiency within the net-zero emissions strategy. This is particularly important in adsorption cooling and desalination systems with poor performance due to unfavourable heat transfer conditions in conventional packed beds of adsorption chillers (ACs). Therefore, looking for additional ways of performance improvement is still challenging, especially covering different design variants and operational strategies. The existing complex, time-consuming and costly analytical, numerical and experimental methods, usually focused on a specific design and operating parameters of conventional packed adsorption beds, cannot tackle these comprehensive problems. Since artificial intelligence (AI) based models are considered tools that sometimes may overcome the shortcomings of the programmed computing approach and the experimental procedures, the paper introduces automated machine learning (AutoML) as a general approach for the design and optimization study of adsorption cooling and desalination systems. The double-effect, i.e. specific cooling capacity (SCP) and specific daily water production (SDWP) of various adsorption chillers (ACs) operating in large-, pilot- and small-scale adsorption cooling and desalination systems, is considered in the study. The paper also presents a novel big data optimization procedure for selecting the best operating and design strategy in adsorption cooling and desalination technology. Finally, a new concept of fluidized bed-type application in adsorption chillers is proposed, which allows for enhancing the performance of ACs. The presented approach can be referred to as a complementary design technique in adsorption cooling and desalination systems, besides the existing complex analytical and time-consuming numerical methods and expensive experiments. • Double-effect desalination and cooling production in adsorption chillers (AC) are evaluated • The new approach allows considering various cooling and desalination adsorption systems. • The novel concept of fluidized bed application in adsorption systems is proposed. • The developed models constitute powerful tools for optimizing ACs systems' performance. [ABSTRACT FROM AUTHOR]

• This paper provides an in-depth review of the latest deep learning methods for use in big data analytics. • Explain the importance of deep learning, its taxonomy, and big data analytics techniques. • Explores deep learning approaches in IoT data applications, including their complexities and limitations. • Suggests using deep learning techniques in many data-intensive applications and benchmarked frameworks and datasets. • A comparison of established approaches with deep learning methods in big data analytics is offered. Deep learning (DL), as one of the most active machine learning research fields, has achieved great success in numerous scientific and technological disciplines, including speech recognition, image classification, language processing, big data analytics, and many more. Big data analytics (BDA), where raw data is often unlabeled or uncategorized, can greatly benefit from DL because of its ability to analyze and learn from enormous amounts of unstructured data. This survey paper tackles a comprehensive overview of state-of-the-art DL techniques applied in BDA. The main target of this survey is intended to illustrate the significance of DL and its taxonomy and detail the basic techniques used in BDA. It also explains the DL techniques used in big IoT data applications as well as their various complexities and challenges. The survey presents various real-world data-intensive applications where DL techniques can be applied. In particular, it concentrates on the DL techniques in accordance with the BDA type for each application domain. Additionally, the survey examines DL benchmarked frameworks used in BDA and reviews the available benchmarked datasets, besides analyzing the strengths and limitations of each DL technique and their suitable applications. Further, a comparative analysis is also presented by comparing existing approaches to the DL methods used in BDA. Finally, the challenges of DL modeling and future directions are discussed. [ABSTRACT FROM AUTHOR]

Big data has been continuously generated from the rapidly developing of cloud/fog/edge computing, Internet of Things (IoT) and 5G technology. This big data not only brings great benefits and opportunities to human beings but also brings many risks and challenges. One major challenge is how to represent and treat higher-order and heterogeneous data from multi-sources. Tensors are emerging as powerful tools for representation and modeling of this data. Tensor decomposition can be used to extract potentially useful information from this data. Thus, it has attracted much attention from the big data community. The main target of this paper is to propose a novel data fusion framework to solve several main challenges of CPSS data applications, including CPSS big data representation, fusion, efficient computing, storage, robustness, and security issues. In this paper, we use many graphics to visualize complex tensor decomposition and transformation processes. The visualization may help the readers better understand tensor and tensor decomposition. It also provides a general guideline and a good starting point for those who are interested in tensor and tensor decomposition. Specifically, we first introduce the most extensively used matrix and tensor decomposition methods. Second, the current popular data fusion methods are reviewed and summarized. Third, we propose a novel tensor-network-conversion-based data fusion approach which can simultaneously analyze multiple matrices and multiple tensors. To better understand this approach, we give a brief review of tensor network. Fourth, based on the proposed approach, a novel CPSS big data fusion framework is proposed in this paper. Meanwhile, we verify it by a concise case study. Finally, some challenges and open problems of the proposed framework are discussed. The discussion also includes some exciting future research directions in the big data fusion field. • We review popular matrix decomposition, data fusion and tensor decomposition methods. • A novel Tensor-Network-Conversion-based data fusion approach (TNC) is proposed in this paper. • Our approach can simultaneously analyze multiple matrices and multiple tensors. • Based on the proposed approach, we propose a novel CPSS big data fusion framework. • A concise case study is used to verify the proposed framework. [ABSTRACT FROM AUTHOR]

Recently, smart data has attracted great attention in the smart city community since it can provide valuable information to support intelligent services such as planning, monitoring, and decision making. However, it imposes a big challenge to explore smart data from big data gathered from smart city with various advanced fusion and analysis approaches. This paper proposes an incremental tensor-based fuzzy c-means approach (IT-FCM) for obtaining smart data from continuously generated big data. Specifically, a weighted version of the tensor-based fuzzy c-means approach (T-FCM) is firstly proposed to cluster the dataset that combines the previous cluster centroids and the new generated data. Aiming to improve the clustering efficiency, the old data objects are represented by the centroids to avoid repeat clustering. Furthermore, this paper presents an edge-cloud-aided clustering scheme to fuse big data from different sources and perspectives and further to implement co-clustering on the fused datasets for exploring smart data. Finally, the proposed IT-FCM approach is evaluated by comparing with T-FCM regarding clustering accuracy and efficiency on two different datasets in the experiments. The results state that IT-FCM outperforms T-FCM in clustering streaming big data in terms of accuracy and efficiency for obtaining smart data. • An edge-cloud-aided computing system for co-clustering is presented. • An edge-cloud-aided computing system for co-clustering is presented. • Experiments are conducted to evaluate the presented approach. [ABSTRACT FROM AUTHOR]

In many computing applications, there is a need to estimate different features of large data sets, such as the number of distinct elements or the similarity with other data sets. This can be efficiently implemented using probabilistic data structures known as sketches; for example, Hyperloglog is widely used for cardinality estimate and Minhash for similarity estimate. Many of these sketches rely on computing hash functions on the elements and counting the number of consecutive leading zeros (or ones) to identify the minimum (or maximum) hash value for data updating. This functionality usually accounts for the most demanding part of the sketch implementation; an efficient and low power hash computation and leading zero counting are therefore required for high performance. A novel but important observation is exploited in this paper; namely the trailing hash bits are rarely used in these sketches (e.g., the leading zeros counting stops once the first one is found, which usually occurs after a few bits). Based on this feature, a so-called Two-Step Hashing (TSH) scheme is proposed in this paper to significantly reduce the power consumption. Therefore rather than computing all hash bits (as in the traditional scheme), TSH computes a few leading hash bits in a first step and the trailing hash bits in the second step, that is only required when the leading bits are all zeros (or ones). Hence, in most cases only a fraction of the hash bits is computed, so significantly reducing the power dissipation of hash computations when they are used to check the number of consecutive leading zeros, or the minimum value. The use of TSH for sketches with both single and multiple pipeline implementations are considered; evaluation results based on HyperLogLog (HLL) as a sketch with a Cyclic Redundancy Check hash function show that TSH saves up to 75.9 % (78.7 %) power dissipation in a single (multiple) pipeline implementation. • A so-called Two-Step Hashing (TSH) scheme is designed for efficiently implementing cardinality and similarity sketches. • The second step of the TSH scheme is rarely triggered only when the first step cannot make a decision for the sketches. • TSH scheme can be employed in sketches with both single and multiple pipeline implementations. • Evaluation results show that TSH saves up to 75.9% (78.7%) power dissipation in a single (multiple) pipeline implementation. [ABSTRACT FROM AUTHOR]

Large-scale data clustering is a crucial task in addressing big data challenges. However, existing approaches often struggle to efficiently and effectively identify different types of big data, making it a significant challenge. In this paper, we propose a novel sample-based clustering algorithm, which is very simple but extremely efficient, and runs in about O (n × r) expected time, where n is the size of the dataset and r is the category number. The method is based on two key assumptions: (1) The data of each sufficient sample should have similar data distribution, as well as category distribution, to the entire data set; (2) the representative of each category in all sufficient samples conform to Gaussian distribution. It processes data in two stages, one is to classify data in each local sample independently, and the other is to globally classify data by assigning each point to the category of its nearest representative category center. The experimental results show that the proposed algorithm is effective, which outperforms other current variants of clustering algorithm. [ABSTRACT FROM AUTHOR]

In the Big Data era, context-aware mobile recommender systems are crucial in assisting citizens and tourists in making informed decisions, providing a suitable way for users to find the relevant data. These systems should be proactive, able to detect the ideal time and location to provide recommendations for a specific item or activity. To accomplish this, push-based recommender systems can be employed, utilizing context rules to determine when a recommendation should be initiated. However, there is very limited reported experience in defining and implementing such systems and a complete generic solution that adapts flexibly to the preferences of users and protects their privacy is still missing. In this paper, we present a novel approach where appropriate types of recommendations are provided automatically, without the need for user input. Our proposal allows users to easily activate, deactivate, customize, and create rules for improved personalization. Additionally, the module that, based on the context, decides the types of recommendations required is executed on the user's mobile device, reducing wireless communication and safeguarding the user's privacy, as context data are evaluated locally. To illustrate the approach, we have developed R-Rules, a prototype for Android devices focused on the triggering of recommendation rules, which provides a friendly user interface that facilitates user personalization. We have evaluated various technological options and demonstrated the feasibility, performance, and scalability of the proposal, as well as its suitability to users' needs. • Generic architecture for mobile push-based recommendations. • Decision module executing on the user device: privacy and wireless savings. • Flexible user-defined rules to decide when to fire a specific type of recommendation. • Android prototype and extensive experimental evaluation. [ABSTRACT FROM AUTHOR]

• A comprehensive and up-to-date review of deep learning-based encryption for digital images is presented. • A detail overview of image encryption using deep learning models along with recent applications are discussed. • Comparative analysis of the reviewed methods and their limitations are discussed to guide future directions. With the innovation of high-throughput big data storage technology and the construction of digital information systems in media applications, images are the common and most popular media carriers and are generated and transmitted in huge quantities. Due to the significant advantages and high value of digital image content, there is an urgent demand to protect their privacy and prevent leakage. In the past few years, deep learning models have brought more options for image encryption algorithm design. This paper offers a comprehensive survey of recent digital image encryption using deep learning models. First, a strong motivation for image encryption using deep learning models along with recent applications is introduced. Next, various state-of-the-art deep learning-based encryption techniques are discussed. The technical summary of different popular techniques is then given in tabular form. Lastly, by deeply investigating existing deep learning-based encryption, we establish some important research challenges and possible solutions, including standard security metrics. [Display omitted] [ABSTRACT FROM AUTHOR]

• The RS image retrieval methods and applications are comprehensively reviewed. • The opportunities and challenges of RS image retrieval are briefly introduced. • The evaluation datasets and metrics of RS image retrieval are summarized. • Performances on two kinds of classic RS image retrieval tasks are discussed. • Insightful discussions and prospects for future work are delivered. The blooming proliferation of aeronautics and astronautics platforms, together with the ever-increasing remote sensing imaging sensors on these platforms, has led to the formation of rapidly-growing earth observation data with the characteristics of large volume, large variety, large velocity, large veracity and large value, which raises awareness about the importance of large-scale image processing, fusion and mining. Unconsciously, we have entered an era of big earth data, also called remote sensing (RS) big data. Although RS big data provides great opportunities for a broad range of applications such as disaster rescue, global security, and so forth, it inevitably poses many additional processing challenges. As one of the most fundamental and important tasks in RS big data mining, image retrieval (i.e., image information mining) from RS big data has attracted continuous research interests in the last several decades. This paper mainly works for systematically reviewing the emerging achievements for image retrieval from RS big data. And then this paper further discusses the RS image retrieval based applications including fusion-oriented RS image processing, geo-localization and disaster rescue. To facilitate the quantitative evaluation of the RS image retrieval technique, this paper gives a list of publicly open datasets and evaluation metrics, and briefly recalls the mainstream methods on two representative benchmarks of RS image retrieval. Considering the latest advances from multiple domains including computer vision, machine learning and knowledge engineering, this paper points out some promising research directions towards RS big data mining. From this survey, engineers from industry may find skills to improve their RS image retrieval systems and researchers from academia may find ideas to conduct some innovative work. [ABSTRACT FROM AUTHOR]

In the era of Big Data, the Internet has become one of the main data sources: Data can be collected for relatively low costs and can be used for a wide range of purposes. To be able to timely support solid decisions in any field, it is essential to increase data production efficiency, data accuracy, and reliability. In this framework, our paper aims at identifying an optimized and flexible method to collect and, at the same time, geolocate social media information over a whole country. In particular, the target of this paper is to compare three alternative methods to collect data from the social media Twitter. This is achieved considering four main comparison criteria: Collection time, dataset size, pre-processing phase load, and geographic distribution. Our findings regarding Great Britain identify one of these methods as the best option, since it is able to collect both the highest number of tweets per hour and the highest percentage of unique tweets per hour. Furthermore, this method reduces the computational effort needed to pre-process the collected tweets (e.g., showing the lowest collection times and the lowest number of duplicates within the geographical areas) and enhances the territorial coverage (if compared to the population distribution). At the same time, the effort required to set up this method is feasible and less prone to the arbitrary decisions of the researcher. [ABSTRACT FROM AUTHOR]

With the promotion of emerging technologies in the era of big data, there has been a diversification in user participation in product requirement development. This has resulted in many complex, diverse, and rapidly iterated user requirements, greatly reducing the applicability of traditional requirement development methods. In this paper, to address the complex and ever-changing relationships among users, requirements, products, and requirement development teams in the product development process, a multilayer dynamic heterogeneous network node influence analysis method is constructed for product requirement development. This method establishes a product requirement development framework based on a multilayer dynamic heterogeneous network consisting of a user layer, requirement layer, component layer, and expert layer in terms of three dimensions: requirement development, requirement evaluation, and time. Based on this framework, indicators such as comprehensive node significance, layer significance, and node influence are designed. To address the issues encountered in small sample data testing, three measurement models are further designed in this paper, effectively improving the sampling efficiency of the multilayer dynamic heterogeneous network. Additionally, calculation models for the comprehensive node influence and comprehensive node influence variation rate are improved and constructed, and corresponding algorithms are designed. This method is applied in an experimental study of product requirement development for new energy vehicles, providing high-quality recommendations for new energy vehicle requirement developers, including functional requirements and product components that need close and timely attention. Moreover, accuracy tests show that the proposed algorithm achieves an average accuracy rate of 0.8611, which is significantly higher than those of other network node centrality measurement methods. This demonstrates the advanced nature and applicability of the proposed method in the field of product requirement development, providing a new way for requirement developers to improve work efficiency. [ABSTRACT FROM AUTHOR]

In today's competitive world, gathering precise context knowledge is a critical barrier for industry practitioners, professionals, and researchers in supply chain management, impeding their capacity to acquire expertise and give effective management awareness. In this regard, this study aimed to identify the data-driven capabilities of supply chain management. Realising the abovementioned issues, the existing literature on supply chain management needs to be further reviewed to explore the data-driven capabilities for sustainable supply chains. The study presented a systematic literature review on a data-driven sustainable supply chain to achieve this goal. One hundred ninety-seven documents from various publications were identified for bibliometric and network analysis from the Scopus database using specific keywords related to the research concept published during 2013–2023 through inclusion and exclusion criteria. The emerging themes were identified using the "R" package and reviewed the papers were reviewed in theme directions. The study showed that implementing data-driven and sustainable technologies could assist strategic decision-making. Also, Data-driven solutions can effectively improve sustainability in supply chain network operations performance. The study demonstrates that big data can contribute to achieving sustainability goals through bibliometric analysis and critique of previous papers published in the specialised field. [ABSTRACT FROM AUTHOR]

Hospitals use medical cyber-physical systems (MCPS) more often to give patients quality continuous care. MCPS isa life-critical, context-aware, networked system of medical equipment. It has been challenging to achieve high assurance in system software, interoperability, context-aware intelligence, autonomy, security and privacy, and device certifiability due to the necessity to create complicated MCPS that are safe and efficient. The MCPS system is shown in the paper as a newly developed application case study of artificial intelligence in healthcare. Applications for various CPS-based healthcare systems are discussed, such as telehealthcare systems for managing chronic diseases (cardiovascular diseases, epilepsy, hearing loss, and respiratory diseases), supporting medication intake management, and tele-homecare systems. The goal of this study is to provide a thorough overview of the essential components of the MCPS from several angles, including design, methodology, and important enabling technologies, including sensor networks, the Internet of Things (IoT), cloud computing, and multi-agent systems. Additionally, some significant applications are investigated, such as smart cities, which are regarded as one of the key applications that will offer new services for industrial systems, transportation networks, energy distribution, monitoring of environmental changes, business and commerce applications, emergency response, and other social and recreational activities.The four levels of an MCPS's general architecture—data collecting, data aggregation, cloud processing, and action—are shown in this study. Different encryption techniques must be employed to ensure data privacy inside each layer due to the variations in hardware and communication capabilities of each layer. We compare established and new encryption techniques based on how well they support safe data exchange, secure computing, and secure storage. Our thorough experimental study of each method reveals that, although enabling innovative new features like secure sharing and safe computing, developing encryption approaches significantly increases computational and storage overhead. To increase the usability of newly developed encryption schemes in an MCPS and to provide a comprehensive list of tools and databases to assist other researchers, we provide a list of opportunities and challenges for incorporating machine intelligence-based MCPS in healthcare applications in our paper's conclusion. [ABSTRACT FROM AUTHOR]

The network structure exhibits a variety of changes over time. Fusing this structure and the development of communities in dynamic networks plays an important role in analyzing the evolution and development of the entire network. How to ensure the division of the community structure in social network big data, as well as ensure the continuity of the community between the current time and previous time period, are issues that need to be explored. This problem can be solved by fusing the three characteristics of temporal variability, stability, and continuity in dynamic social network communities, and by adopting the multi-objective optimization method to detect community structures in dynamic networks. The probability fusion method is added to the initial step of the algorithm to generate suitable network partitions and ensure fast convergence and high accuracy. Two neighboring fusion strategies are proposed that are suitable for communities: the neighbor diversity strategy and the neighbor crowd strategy. These two strategies make different changes to the candidate network partitions. A continuity metric for dynamic community evolution is formulated to compare the similarity of the dynamic network communities of two consecutive time steps. Experiments on synthetic datasets and actual datasets prove that the proposed method in this paper provides better performance than existing methods. [ABSTRACT FROM AUTHOR]

Facial phenotypes are extensively studied in medical and biological research, serving as critical markers that potentially indicate underlying genetic traits or medical conditions. With the recent advancements in big data, algorithms, and hardware, deep facial diagnosis, which employs deep learning techniques to systematically examine facial phenotypes and identify signs of certain diseases or medical conditions, has attracted significant attention and research, gradually emerging as a promising tool in precision medicine. Primarily limited by the scarcity of data for training facial diagnosis models, the accuracy of facial diagnosis for various conditions remains low up to now. In the past decade, RGB-D cameras, measuring depth information along with standard RGB capabilities, have proven superior in processing spatial details with more stability and accuracy. Motivated by the facts mentioned above, in this paper, we propose a Simulated Multimodal Framework, which effectively improves the computer-aided facial diagnosis performance of state-of-the-art models in experiments under different conditions. The underlying principle is to leverage the simulated depth by generative models to improve the performance of RGB image recognition. Furthermore, as a rapid and non-invasive tool for disease screening and detection, our proposal demonstrated an average accuracy improvement of over 20% compared to practicing physicians in the study. • Deep facial diagnosis offers rapid, non-invasive disease detection and screening. • Simulated Multimodal Framework effectively leverages estimated face depth. • Fine-grained bilinear classification boosts facial diagnosis with limited data. • Our proposal markedly elevates facial diagnosis performance in RGB mode. • AI surpasses practicing physicians with over 20% accuracy boost in the study. [ABSTRACT FROM AUTHOR]

• The equilibrium distribution and dynamic subspace approximation (EDDSA) is proposed. • The double subspace transformation is introduced into EDDSA. • The divergence problem in EDDSA is minimized using dynamical change strategy. Nowadays, big data analysis has become an important approach in social information network. However, the social information may not be distributed independently and identically (i.i.d.), which can be addressed using domain adaptation. However, most of the existing domain adaptation methods are designed to align cross-domain distributions. The label information of the samples in the target domain is completely unavailable. Thus, the class-conditional distribution differences cannot be well measured, and the effect of feature distortion on distribution alignment in the original feature space is difficult to handle. This paper proposes a domain adaptation learning based on the Equilibrium Distribution and Dynamic Subspace Approximation (EDDSA) to alleviate these problems. First, EDDSA learns to project the source and target domains into associated feature spaces, and dynamically approximates two subspaces to overcome the feature distortion problem. Second, the balanced distribution alignment term is introduced to dynamically weight the importance of the conditional and marginal distributions. Through many experiments, EDDSA is superior to most traditional methods. [ABSTRACT FROM AUTHOR]

Imbalanced class distributions in machine learning, where the minority class is often under-represented, pose a substantial challenge. Synthetic Minority Over-sampling Technique (SMOTE) has been widely employed to address this issue by generating synthetic minority samples through interpolation. Despite its popularity, SMOTE exhibits certain drawbacks caused by the implementation of random interpolation samples. In this paper, we introduce a new data level technique for oversampling, called Fuzzy C-Means Center-SMOTE (FCM-CSMOTE), which generates synthetic samples in each cluster using its center considered as the memory of the main data components. We demonstrate that the proposed selective strategy has a very low probability to generate noise. The experimental results demonstrate that the proposed method performs better than the state-of-the-art approaches on 21 real unbalanced data sets (regular and large size data set) in terms of several metrics, including Geometric Mean (GM), F-Measure (FM), Area Under the Curve (AUC), and Accuracy. [ABSTRACT FROM AUTHOR]

Carbon markets are widely recognized as effective strategies for regulating carbon emissions from the enterprises of the high-carbon industry. Accurate monitoring of emissions in these enterprises is crucial for ensuring fair and trusted carbon trading. However, traditional monitoring methods have encountered various challenges including poor accuracy, low frequency, significant hysteresis and weak credibility. Addressing these concerns, this paper introduces a novel, multi-trusted, high-frequency monitoring approach for the measurement of both direct and indirect carbon emissions of enterprises, utilizing externally available multi-source big data, vertical federated long short-term memory network with a self-attention mechanism (VF-LSTMSA) and additive homomorphic encryption. The efficacy of this model is thoroughly assessed via case studies on six hourly datasets from the power and steel sectors. Our principal findings include: (1) In the current scenario, the proposed VF-LSTMSA model demonstrates superior federated efficiency, improving with the inclusion of more federated participants. (2) The VF-LSTMSA model surpasses other prevalent AI models, achieving a Mean Absolute Percentage Error (MAPE) of less than 9% across power and steel datasets. (3) The advanced high-frequency carbon emission monitoring method exhibits errors of +0.28%, +1.29%, and −0.41% in the current scenario monitoring task, suggesting that the model effectively leverages multi-source externally available big data to precisely monitor the target enterprise's carbon emissions while safeguarding multi-party data security. These findings suggest that the proposed monitoring method can accurately track corporate hourly carbon emissions, significantly improving the carbon trading and verification processes for enterprises [ABSTRACT FROM AUTHOR]

Schemaless databases, and document-oriented databases in particular, are preferred to relational ones for storing heterogeneous data with variable schemas and structural forms. However, the absence of a unique schema adds complexity to analytical applications, in which a single analysis often involves large sets of data with different schemas. In this paper we propose an original approach to OLAP on collections stored in document-oriented databases. The basic idea is to stop fighting against schema variety and welcome it as an inherent source of information wealth in schemaless sources. Our approach builds on four stages: schema extraction, schema integration, FD enrichment, and querying; these stages are discussed in detail in the paper. To make users aware of the impact of schema variety, we propose a set of indicators inspired by the definition of attribute density. Finally, we experimentally evaluate our approach in terms of efficiency and effectiveness. • The inherent variety of documents hinders proper OLAP analyses. • We propose an approximated OLAP approach that captures and exploits schema variety. • A multidimensional view is given by detecting approximated functional dependencies. • We propose indicators to predict and evaluate the quality of OLAP queries. • We show that the approach improves the coverage and precision of OLAP queries. [ABSTRACT FROM AUTHOR]

Problems from a wide variety of application domains can be modeled as "nondeterministic finite automaton" (NFA) and hence, efficient execution of NFAs can improve the performance of several key applications. However, traditional architectures, such as CPU and GPU are not inherently suited for executing NFAs, and hence, special-purpose architectures are required for accelerating them. Micron's automata processor (AP) exploits massively parallel in-memory processing capability of DRAM for executing NFAs and hence, it can provide orders of magnitude performance improvement compared to traditional architectures. In this paper, we present a survey of techniques that propose architectural optimizations to AP and use it for accelerating problems from various application domains. This paper will be useful not only for computer architects and processor-designers, but also for researchers in the field of bioinformatics, data-mining, machine learning and others. [ABSTRACT FROM AUTHOR]

Background: Computer-aided diagnosis (CAD) can assist physicians in effective and efficient diagnostic decision-making. CAD systems are currently essential tools in some areas of clinical practice. In addition, it is one of the established fields of study in the interface of medicine and computer science. There are, however, still some critical challenges that CAD systems face.Methods: This paper first describes a new literature review protocol, the Dynamic PRISMA approach based on the well-known PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) approach. This new approach enhances the traditional approach by integrating a feedback mechanism module. As a result of the literature review, this paper identifies seven major challenges that occur today in CAD and inhibit the next major developments.Results: The seven challenges described in this paper involve some technical weaknesses in the interface of medicine and computer science. These challenges are related to various algorithmic limitations, the difficulty of medical professionals to adopt new systems, problems when dealing with patient data, and the lack of guidelines and standardization regarding many aspects of CAD. This paper also describes some of the recent research developments towards these challenges.Conclusion: If these seven key challenges are addressed properly, then the ways for dealing with them will become the R&D pillars needed to bring CAD to the next level. This would require additional well-coordinated collaboration between researchers and practitioners in the fields of medicine and computer science. [ABSTRACT FROM AUTHOR]

Highlights • This paper suggests two methods based on AI tools for medical image segmentation. • The first method uses CBR to guide a region-growing process for segmentation. • The second method based on Deep Learning performs segmentation with a small data set. • Both methods were tested on CT-scans images from children with tumoral kidneys. • They provided accurate enough results to consider an automatic. segmentation Abstract Most often, image segmentation is not fully automated and a user is required to lead the process in order to obtain correct results. In a medical context, segmentation can furnish much information to surgeons, but this task is rarely executed. Artificial Intelligence (AI) is a powerful approach for devising a viable solution to fully automated treatment. In this paper, we have focused on kidneys deformed by nephroblastoma. However, a frequent medical constraint is encountered which is a lack of sufficient data with which to train our system. In function of this constraint, two AI approaches were used to segment these structures. First, a Case Based Reasoning (CBR) approach was defined which can enhance the growth of regions for segmentation of deformed kidneys using an adaptation phase to modify coordinates of recovered seeds. This CBR approach was confronted with manual region growing and a Convolutional Neural Network (CNN). The CBR system succeeded in performing the best segmentation for the kidney with a mean Dice of 0.83. Deep Learning was then examined as a possible solution, using the latest performing networks for image segmentation. However, for relevant efficiency, this method requires a large data set. An option would be to manually segment only certain representative slices from a patient and then use them to train a Convolutional Neural Network (CNN) how to segment. In this article the authors propose an evaluation of a CNN for medical image segmentation following different training sets with a variable number of manual segmentations. To choose slices to train the CNN, an Overlearning Vector for Valid Sparse SegmentatIONs (OV 2 ASSION) was used, with the notion of gap between two slices from the training set. This protocol made it possible to obtain reliable segmentations of per patient with a small data set and to determine that only 26% of initial segmented slices are required to obtain a complete segmentation of a patient with a mean Dice of 0.897. [ABSTRACT FROM AUTHOR]

[Display omitted] • Winning strategies from the CRDDC, with over 90 teams from 20+ countries, are analyzed. • Cross-country collaboration in the challenge develops effective road damage detection models for 6 countries. • Multidimensional analysis of dataset and model selection provides valuable insights for future research. • Information fusion of multi-country datasets and multiple views is found crucial for robust model training. • The findings empower researchers to optimize approaches for automatic road inspection globally. Monitoring road conditions is crucial for safe and efficient transportation infrastructure, but developing effective models for automatic road damage detection is challenging requiring large-scale annotated datasets. Cross-country collaboration provide access to diverse datasets and insights into factors affecting road damage detection models. This paper presents a review of winning strategies of the Crowdsensing-based Road Damage Detection Challenge (CRDDC) held in 2022 as a Big Data Cup, with 90+ teams from 20+ countries proposing solutions for six countries: India, Japan, the Czech Republic, Norway, the United States, and China. The best solution achieved an F1-score of 77 % for all six countries, which is 2.7 % better than the 2nd ranked solution. This study explores the impact of factors influencing dataset and model selection by CRDDC winners. The study's insights can guide future research in making data-related choices and developing more effective road damage detection models accounting for the diverse road conditions across different countries. [ABSTRACT FROM AUTHOR]

MapReduce is a popular paradigm in distributed computing, but it is not efficient when executing iterative algorithms over a distributed big dataset due to its heavy data communication overhead. Non-MapReduce computing is an alternative for improving computing efficiency and data scalability when using iterative algorithms to process big distributed datasets on clusters. In this paper, we investigate Non-MapReduce approach in distributed computing and use Spark implementations of machine learning algorithms to discuss the problems of MapReduce in executing iterative algorithms over a big distributed dataset and the advantages of Non-MapReduce for the same tasks. We present a method to build a new machine learning library made of sequential algorithms for distributed computing. We use experiment results to show comparisons of computing efficiency and data scalability of MapReduce and Non-MapReduce in executing six machine learning algorithms over big datasets. [ABSTRACT FROM AUTHOR]

The visual exploration of geospatial vector data has become an increasingly important part of the management and analysis of geospatial vector big data (GVBD). With the rapid growth of data scale, it is difficult to realize efficient visual exploration of GVBD by current visualization technologies even if parallel distributed computing technology is adopted. To fill the gap, this paper proposes a visual exploration approach of GVBD on the web map. In this approach, we propose the display-driven computing model and combine the traditional data-driven computing method to design an adaptive real-time visualization algorithm. At the same time, we design a pixel-quad-R tree spatial index structure. Finally, we realize the multilevel real-time interactive visual exploration of GVBD in a single machine by constructing the index offline to support the online computation for visualization, and all the visualization results can be calculated in real-time without the external cache occupation. The experimental results show that the approach outperforms current mainstream visualization methods and obtains the visualization results at any zoom level within 0.5 s, which can be well applied to multilevel real-time interactive visual exploration of the billion-scale GVBD. • A Pixel-Quad-R-tree structure is designed to support the efficient visual exploration of geospatial vector big data (GVBD), the index can adapt to the computational requirements in the subsequent tile drawing process and provide efficient data organization support for GVBD visual exploration. • The PQR-tree-based Adaptive Tile Drawing (PATD) algorithm is proposed, PATD adaptively adopts the optimal pixel generation strategy to determine and achieve efficient visualization performance on a single machine. Meanwhile, the visualization results at each zoom level can be generated in real-time without pre-computation for caching. • An open-source visual exploration tool of GVBD is designed, which can browse data in real-time. Users can either zoom out to inspect the overall distribution or zoom in to view the individual details. Moreover, the tool also supports real-time interactive customization of data styles. [ABSTRACT FROM AUTHOR]

• We propose a hospital selection approach. • Online reviews of general and specialized hospitals are collected and processed. • We classify topics and sentiments using logistics regression, light GBM, and BERT. • Preference scores of hospitals are obtained using the weighted TOPSIS method. • Sensitivity analysis is given to validate the effectiveness of the method. In the era of big data, publicly available data from official hospital sources and data from online reviews are easy to influence a patient's decision in choosing a hospital. However, existing research has rarely comprehensively considered the combined influence of these two factors. This paper proposes a hospital selection approach based on a fuzzy multi-criterion decision-making method, which considers sentiment evaluation values of unstructured data from online reviews and structured data of public indexes simultaneously. First, online reviews of general and specialized hospitals are collected and processed to get evaluation attributes of hospital and attribute weights. Then, text reviews are taken to classify topics and sentiments using logistic regression, light gradient boosting machine, and bidirectional encoder representations from transformers. The results of sentiment analysis are quantified using triangular fuzzy numbers to express evaluation values of hospitals. Based on patients' preferences for online reviews and structured data on publicly available attributes of hospitals, final preference scores of hospitals are obtained using the fuzzy technique for order preference by similarity to ideal solution method. A case study is performed to illustrate the applicability of the proposed method. Robustness analysis from patient perspective and hospital perspective are executed to validate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Big data industry development and carbon dioxide emissions reduction are the crucial driver and objective functions of economic growth, respectively. Whether the two types of corresponding policies can achieve the "win-win" effect is the key to green development transformation in the future. However, little attention has been paid to the influence of big data industry development on carbon dioxide emissions. Based on the quasi-natural experiment in China's national big data comprehensive experimental area, the paper identifies the causal effect between big data industry development and carbon dioxide emissions. Specifically, the panel data of 282 cities in China spanning from 2010 to 2019 are used in regression analysis. The study reveals that the big data industry development has a substantial impact in reducing carbon dioxide emissions. Meanwhile, the findings are confirmed by a set of rigorous robustness checks. The heterogeneity analyses suggest that the effect of inhibiting carbon dioxide emissions due to the big data industry development is more significant in eastern & central China, and large-sized cities. In addition, the big data industry reduces carbon dioxide emissions through the effects of industrial structure optimization, technological innovation, and resource allocation. Our findings contribute to the nexus between big data industry development and carbon dioxide emissions. In light of these findings, the paper recommends that governments integrate economic growth and environmental protection policies by promoting big data industry development. • The paper provides a novel insight into the CO 2 emission from the perspective of big data industry. • Based on quasi-natural experiment, the paper has identified the causal effect between the big data industry development and CO 2 emissions with the Difference-in-Difference (DID) methodology. • Big data industry development effectively stimulate the reduction of CO 2 emissions. [ABSTRACT FROM AUTHOR]

Big Data will revolutionize modern industry by improving process optimization, facilitating insight discovery, and improving decision-making. This big data revolution presents a multitude of possibilities and challenges in evolving from traditional batch processes to smart batch processes. This tremendous potential requires the ability to extract value from vast amounts of industrial process data. Using a new three-dimensional (3D) perspective of time, batch, and operational context, this paper explores smart batch processes with higher efficiency, greater profitability, and longer sustainability. First, we review the traditional one-dimensional (1D) perspective on batch processes and summarize the existing two-dimensional (2D) perspectives on batch processes, i.e., modeling, monitoring, control, and optimization methods. Based on those results, the spotlight will focus on how big data can be used to achieve smart batch processes using the 3D perspective. This will include detailed discussions of definitions and concepts, operational mechanisms, and the benefits and advantages of smart batch processes. For further implementation of the 3D perspective, we present several monitoring and control methodologies. Next, we analyze several challenges and issues in implementing smart batch processes in the era of Big Data. In conclusion, we provide both a novel viewpoint and encouragement for future research into batch process automation from the 3D perspective. [ABSTRACT FROM AUTHOR]

Big data and time series are typical features of modern industrial process data. Effective time series modeling methods are required for ensuring the normal and stable operation of industrial processes. However, the existing time series prediction methods usually cannot take important historical data features long ago into consideration. In this paper, we proposed a new attention-mechanism based dynamic-inner partial least squares long short-term memory (ADiPLS-LSTM) method to predict the time series data. First, the DiPLS method is applied to extract the dynamic features in the selected data group, and the attention-mechanism is used then to define the importance of the responded features. The product of the extracted dynamic features and the attention-mechanism results is regarded as the input of LSTM to predict the future time information. The proposed method uses both the recent data information and important data information in a long run, which helps to obtain more accurate prediction results. The effectiveness of the ADiPLS-LSTM method is verified by the data of a 660MW coal-fired boiler. Compared with BPNN, LSTM, and DiPLS-LSTM, the proposed method also advances in time series data prediction and interpretability. • The receive field of LSTM is usually very limited, and the interpretability is weak • DiPLS can extract dynamic features between input and output • The existing prediction methods cannot take important historical data features. • A new novel ADiPLS-LSTM method is proposed in this paper. • Application results confirm the effectiveness and reliability of the proposed method. [ABSTRACT FROM AUTHOR]

With the rapid development of economy and the frequent occurrence of air pollution incidents, the problem of air pollution has become a hot issue of concern to the whole people. The air quality big data is generally characterized by multi-source heterogeneity, dynamic mutability, and spatial–temporal correlation, which usually uses big data technology for air quality analysis after data fusion. In recent years, various models and algorithms using big data techniques have been proposed. To summarize these methodologies of air quality study, in this paper, we first classify air quality monitoring by big data techniques into three categories, consisting of the spatial model, temporal model and spatial–temporal model. Second, we summarize the typical methods by big data techniques that are needed in air quality forecasting into three folds, which are statistical forecasting model, deep neural network model, and hybrid model, presenting representative scenarios in some folds. Third, we analyze and compare some representative air pollution traceability methods in detail, classifying them into two categories: traditional model combined with big data techniques and data-driven model. Finally, we provide an outlook on the future of air quality analysis with some promising and challenging ideas. • The air quality early warning system are systematically reviewed. • Some air quality analysis methods by big data techniques are overviewed. • The difficulties and some ideas of air quality research are discussed briefly. [ABSTRACT FROM AUTHOR]

With the progress of artificial intelligence, big data and functional neuroimaging technologies, brain computing has rapidly advanced our understanding of brain intelligence and brain disorders. We argue that existing data analytical methods have become insufficient for brain computing when dealing with multiple brain big data sources, because such methods mainly focus on flattening strategies and fail to work well for systematic understanding of the constituent elements of cognition, emotion and disease, as well as the intra- and inter-relations within and among themselves. To address this problem, we present in this paper a novel multi-source brain computing platform by Data-Brain driven systematic fusion. First, we formalize a series of behaviors surrounding the Brain Informatics-based investigation process, and present a conceptual model to systematically represent content and context of functional neuroimaging data. Then, we propose the systematic brain computing framework with multi-aspect fusion and inference to understand brain specificity and give uncertainty quantification, as well as its inspiration and applications for translational studies on brain health. In particular, a graph matching-based task search algorithm is introduced to help systematic experimental design and data sampling with multiple cognitive tasks. The study increases the interpretability and transparency of brain computing findings by inferring and testing multiple hypotheses taking into consideration the effect of evidence combination. Finally, multiple sources of knowledge (K), information (I) and data (D) are driven by a KID loop as the thinking space to inspire never-ending learning and multi-dimensional interactions in the connected social–cyber–physical spaces. Experimental results have demonstrated the efficacy of the proposed brain computing method with systematic fusion. [Display omitted] • Brain informatics-guided systematic fusion and brain investigation. • Brain big data integration and analytics based on the extensible Data-Brain. • Multi-source fusion of data, information and knowledge for brain computing. • Fusion and inference to interpret multiple uncertainties of brain computing findings. • Predictive model to build a bridge between brain computing and smart health services. [ABSTRACT FROM AUTHOR]

The Rotation Forest classifier is a successful ensemble method for a wide variety of data mining applications. However, the way in which Rotation Forest transforms the feature space through PCA, although powerful, penalizes training and prediction times, making it unfeasible for Big Data. In this paper, a MapReduce Rotation Forest and its implementation under the Spark framework are presented. The proposed MapReduce Rotation Forest behaves in the same way as the standard Rotation Forest, training the base classifiers on a rotated space, but using a functional implementation of the rotation that enables its execution in Big Data frameworks. Experimental results are obtained using different cloud-based cluster configurations. Bayesian tests are used to validate the method against two ensembles for Big Data: Random Forest and PCARDE classifiers. Our proposal incorporates the parallelization of both the PCA calculation and the tree training, providing a scalable solution that retains the performance of the original Rotation Forest and achieves a competitive execution time (in average, at training, more than 3 times faster than other PCA-based alternatives). In addition, extensive experimentation shows that by setting some parameters of the classifier (i.e., bootstrap sample size, number of trees, and number of rotations), the execution time is reduced with no significant loss of performance using a small ensemble. • A MapReduce version of Rotation Forest ensemble classifier is presented. • The algorithm is implemented for the Spark framework as part of the Spark ML API. • Thorough experiments on cloud-based environments are conducted. • Better performance than Random Forest or PCARDE is achieved for Big Data problems. • Good tradeoff between accuracy and execution time is demonstrated. [ABSTRACT FROM AUTHOR]