Search

This document is an editorial for a special issue of the journal "Technologies" focused on data science and big data in various fields such as biology, physical science, and engineering. The editorial highlights the importance of analyzing large amounts of data generated by digital technologies and the need for data scientists to use artificial intelligence and machine learning to extract valuable knowledge. The special issue includes 12 papers covering topics such as machine learning techniques for customer churn prediction, agile program management in the U.S. Navy, deep learning for cybersecurity in Industry 5.0, self-directed learning during the COVID-19 era, decision tree-based neural networks for data classification, data-driven governance in technology companies, and more. The papers explore different approaches, models, and tools in the context of data science and big data. [Extracted from the article]

The goal is to use the massive amounts of data created by digital education systems to develop intelligent and adaptable learning environments that are particularly suited to each student's requirements. The rapid digitization of education systems has led to the proliferation of educational big data, presenting unprecedented opportunities to reshape learning environments into intelligent, responsive spaces that adapt to the needs of individual learners. This paper explores the integration of advanced deep learning techniques with educational big data analytics to forge the path towards futuristic smart learning ecosystems. By leveraging robust datasets derived from a myriad of educational interactions, ranging from student performance metrics to engagement patterns in digital learning platforms, we propose a multi-tiered analytical framework that harnesses the predictive power of deep learning. We commence by elucidating the scope and scale of educational big data, highlighting its potential to provide granular insights into student learning processes. The paper then delineates the architecture of a deep learning-based analytical model designed to process complex, multidimensional educational datasets. This model applies state-of-the-art algorithms to perform tasks such as predictive analytics for student performance, personalized content recommendation, and real-time engagement monitoring. Central to our discussion is the application of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and deep belief networks (DBNs) in deciphering patterns and trends that escape traditional analytical methodologies. We emphasize the capacity of these techniques to capture the subtleties of learner behavior and to facilitate the development of adaptive learning pathways. Furthermore, we address the challenges of integrating deep learning with educational big data, including issues of data privacy, computational demands, and the need for robust model interpretation. The paper presents a series of case studies that demonstrate the successful application of our proposed framework in various educational settings, from K-12 to higher education and continuous professional development. [ABSTRACT FROM AUTHOR]

The tasks of few-shot, one-shot, and zero-shot learning—or collectively "low-shot learning" (LSL)—at first glance are quite similar to the long-standing task of class imbalanced learning; specifically, they aim to learn classes for which there is little labeled data available. Motivated by this similarity, we conduct a survey to review the recent literature for works which combine these fields in one of two ways, either addressing the obstacle of class imbalance within a LSL setting, or utilizing LSL techniques or frameworks in order to combat class imbalance within other settings. In our survey of over 60 papers in a wide range of applications from January 2020 to July 2023 (inclusive), we examine and report methodologies and experimental results, find that most works report performance at or above their respective state-of-the-art, and highlight current research gaps which hold potential for future work, especially those involving the use of LSL techniques in imbalanced tasks. To this end, we emphasize the lack of works utilizing LSL approaches based on large language models or semantic data, and works using LSL for big-data imbalanced tasks. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) can radically change almost every aspect of the human experience. In the medical field, there are numerous applications of AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, this fact being supported by the exponential increase in the number of publications in which the algorithms play an important role in data analysis, pattern discovery, identification of anomalies, and therapeutic decision making. Furthermore, with technological development, there have appeared new models of machine learning (ML) and deep learning (DP) that are capable of exploring various applications of AI in cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional cardiology, and many others. In this sense, the present article aims to provide a general vision of the current state of AI use in cardiology. Results: We identified and included a subset of 200 papers directly relevant to the current research covering a wide range of applications. Thus, this paper presents AI applications in cardiovascular imaging, arithmology, clinical or emergency cardiology, cardiovascular prevention, and interventional procedures in a summarized manner. Recent studies from the highly scientific literature demonstrate the feasibility and advantages of using AI in different branches of cardiology. Conclusions: The integration of AI in cardiology offers promising perspectives for increasing accuracy by decreasing the error rate and increasing efficiency in cardiovascular practice. From predicting the risk of sudden death or the ability to respond to cardiac resynchronization therapy to the diagnosis of pulmonary embolism or the early detection of valvular diseases, AI algorithms have shown their potential to mitigate human error and provide feasible solutions. At the same time, limits imposed by the small samples studied are highlighted alongside the challenges presented by ethical implementation; these relate to legal implications regarding responsibility and decision making processes, ensuring patient confidentiality and data security. All these constitute future research directions that will allow the integration of AI in the progress of cardiology. [ABSTRACT FROM AUTHOR]

Data science has become increasingly popular due to emerging technologies, including generative AI, big data, deep learning, etc. It can provide insights from data that are hard to determine from a human perspective. Data science in finance helps to provide more personal and safer experiences for customers and develop cutting-edge solutions for a company. This paper surveys the challenges and opportunities in applying data science to finance. It provides a state-of-the-art review of financial technologies, algorithmic trading, and fraud detection. Also, the paper identifies two research topics. One is how to use generative AI in algorithmic trading. The other is how to apply it to fraud detection. Last but not least, the paper discusses the challenges posed by generative AI, such as the ethical considerations, potential biases, and data security. [ABSTRACT FROM AUTHOR]

Deep learning‐based models have become ubiquitous across a wide range of applications, including computer vision, natural language processing, and robotics. Despite their efficacy, one of the significant challenges associated with deep neural network (DNN) models is the potential risk of copyright leakage due to the inherent vulnerability of the entire model architecture and the communication burden of the large models during publishing. So far, it is still challenging for us to safeguard the intellectual property rights of these DNN models while reducing the communication time during model publishing. To this end, this paper introduces a novel approach using knowledge distillation techniques aimed at training a surrogate model to stand in for the original DNN model. To be specific, a knowledge distillation generative adversarial network (KDGAN) model is proposed to train a student model capable of achieving remarkable performance levels while simultaneously safeguarding the copyright integrity of the original large teacher model and improving communication efficiency during model publishing. Herein, comprehensive experiments are conducted to showcase the efficacy of model copyright protection, communication‐efficient model publishing, and the superiority of the proposed KDGAN model over other copyright protection mechanisms. [ABSTRACT FROM AUTHOR]

The article discusses the growth and prospects of artificial intelligence (AI) technology, particularly following the launch of ChatGPT in 2023. The global AI market is expected to reach over USD 2.5 trillion by 2032, and ChatGPT has already gained 200 million users within a year. The article emphasizes the need for research papers on deep structure AI and interdisciplinary applications of large-scale language models (LLMs). It also highlights the importance of hardware-based deep learning AI and the transparency and interpretability of deep neural networks. The article concludes by mentioning promising areas in the AI section, such as electronic interfaces, self-driving cars, emotional systems, and healthcare systems. [Extracted from the article]

The work presented in this paper makes multiple scientific contributions related to the investigation of the global fear associated with COVID-19 by performing a comprehensive analysis of a dataset comprising survey responses of participants from 40 countries. First, the results of subjectivity analysis performed using TextBlob, showed that in the responses where participants indicated their biggest concern related to COVID-19, the average subjectivity by the age group of 41–50 decreased from April 2020 to June 2020, the average subjectivity by the age group of 71–80 drastically increased from May 2020, and the age group of 11–20 indicated the least level of subjectivity between June 2020 to August 2020. Second, subjectivity analysis also revealed the percentage of highly opinionated, neutral opinionated, and least opinionated responses per age-group where the analyzed age groups were 11–20, 21–30, 31–40, 41–50, 51–60, 61–70, 71–80, and 81–90. For instance, the percentage of highly opinionated, neutral opinionated, and least opinionated responses by the age group of 11–20 were 17.92%, 16.24%, and 65.84%, respectively. Third, data analysis of responses from different age groups showed that the highest percentage of responses indicating that they were very worried about COVID-19 came from individuals in the age group of 21–30. Fourth, data analysis of the survey responses also revealed that in the context of taking precautions to prevent contracting COVID-19, the percentage of individuals in the age group of 31–40 taking precautions was higher as compared to the percentages of individuals from the age groups of 41–50, 51–60, 61–70, 71–80, and 81–90. Fifth, a deep learning model was developed to detect if the survey respondents were seeing or planning to see a psychologist or psychiatrist for any mental health issues related to COVID-19. The design of the deep learning model comprised 8 neurons for the input layer with the ReLU activation function, the ReLU activation function for all the hidden layers with 12 neurons each, and the sigmoid activation function for the output layer with 1 neuron. The model utilized the responses to multiple questions in the context of fear and preparedness related to COVID-19 from the dataset and achieved an accuracy of 91.62% after 500 epochs. Finally, two comparative studies with prior works in this field are presented to highlight the novelty and scientific contributions of this research work. [ABSTRACT FROM AUTHOR]

The application of cloud computing and big data core technologies and concepts to medical informatization can improve its flexibility and efficiency, and achieve the overall deployment and intensive management of the system. In the era of big data, the use of information management platform can optimize and standardize clinical diagnosis and treatment process, improve the quality and efficiency of diagnosis and treatment services, and improve the quality and level of scientific research, which meets the requirements of medical reform for fine management of hospitals and precise medical treatment in the era of evidence-based medicine. This paper introduces the development and application of big data analysis in the field of information technology. Through the research on the supervision of hospital medical service behavior, the top-level design is used to standardize the content of medical behavior supervision, and the effectiveness of supervision is discussed to achieve the purpose of reducing clinical paperwork. Based on the needs, the medical service behavior supervision system is proposed and constructed. Strengthen hospital medical behavior supervision through hospital big data analysis and knowledge base system support. This system can provide management with an effective monitoring and management tool, enabling them to promptly identify and solve problems that arise in medical services. By analyzing a large amount of medical data, hospitals can help predict the trend of disease occurrence in advance, thereby taking preventive and control measures in advance, and reducing the occurrence and spread of diseases. Through deep learning and analysis of patient data, personalized treatment plans can be provided for each patient to improve treatment effectiveness. [ABSTRACT FROM AUTHOR]

Background: Irregular time series (ITS) are common in healthcare as patient data is recorded in an electronic health record (EHR) system as per clinical guidelines/requirements but not for research and depends on a patient's health status. Due to irregularity, it is challenging to develop machine learning techniques to uncover vast intelligence hidden in EHR big data, without losing performance on downstream patient outcome prediction tasks. Methods: In this paper, we propose Perceiver, a cross-attention-based transformer variant that is computationally efficient and can handle long sequences of time series in healthcare. We further develop continuous patient state attention models, using Perceiver and transformer to deal with ITS in EHR. The continuous patient state models utilise neural ordinary differential equations to learn patient health dynamics, i.e., patient health trajectory from observed irregular time steps, which enables them to sample patient state at any time. Results: The proposed models' performance on in-hospital mortality prediction task on PhysioNet-2012 challenge and MIMIC-III datasets is examined. Perceiver model either outperforms or performs at par with baselines, and reduces computations by about nine times when compared to the transformer model, with no significant loss of performance. Experiments to examine irregularity in healthcare reveal that continuous patient state models outperform baselines. Moreover, the predictive uncertainty of the model is used to refer extremely uncertain cases to clinicians, which enhances the model's performance. Code is publicly available and verified at https://codeocean.com/capsule/4587224. Conclusions: Perceiver presents a computationally efficient potential alternative for processing long sequences of time series in healthcare, and the continuous patient state attention models outperform the traditional and advanced techniques to handle irregularity in the time series. Moreover, the predictive uncertainty of the model helps in the development of transparent and trustworthy systems, which can be utilised as per the availability of clinicians. [ABSTRACT FROM AUTHOR]

The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms. [ABSTRACT FROM AUTHOR]

To aid cocrystal screening, a deep forest-based cocrystal prediction model was developed in this study using data from the Cambridge Structural Database (CSD). The positive samples in the experiment came from the CSD. The negative samples were partly from the failure records in other papers, and some were randomly generated according to specific rules, resulting in a total of 8576 pairs. Compared with the models of traditional machine learning methods and simple deep neural networks models, the deep forest model has better performance and faster training speed. The accuracy is about 95% on the test set. Febuxostat cocrystal screening was also tested to verify the validity of the model. Our model correctly predicted the formation of cocrystal. It shows that our model is practically useful in practice. [ABSTRACT FROM AUTHOR]

This document is a summary of a special issue on transportation big data and its applications. The issue explores various topics related to big data in transportation, including architectures, processing methods, and utilization for tasks such as traffic pattern discovery, collision identification, and operational efficiency optimization. The issue includes sixteen papers covering a range of subjects, such as maritime traffic evaluation, urban traffic intersection extraction, and risk measurement and forecasting. The authors highlight the transformative potential of big data in transportation and express gratitude to the contributors for their insights. [Extracted from the article]

In this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem and a pre-trained Tiny-YOLOv4 model for cotton bloom detection from our past work. We feed cotton image data collected from a research field in Tifton, GA, into our cluster's distributed file system for robust file access and distributed, parallel processing. We then submit job requests to our cluster from our client to process cotton image data in a distributed and parallel fashion, from pre-processing to bloom detection and spatio-temporal map creation. Additionally, we present a comparison of our four-node cluster performance with centralized, one-, two-, and three-node clusters. This work is the first to develop a distributed computing pipeline for high-throughput cotton phenotyping in field-based agriculture. [ABSTRACT FROM AUTHOR]

In laser powder bed fusion processes, keyholes are the gaseous cavities formed where laser interacts with metal, and their morphologies play an important role in defect formation and the final product quality. The in-situ X-ray imaging technique can monitor the keyhole dynamics from the side and capture keyhole shapes in the X-ray image stream. Keyhole shapes in X-ray images are then often labeled by humans for analysis, which increasingly involves attempting to correlate keyhole shapes with defects using machine learning. However, such labeling is tedious, time-consuming, error-prone, and cannot be scaled to large data sets. To use keyhole shapes more readily as the input to machine learning methods, an automatic tool to identify keyhole regions is desirable. In this paper, a deep-learning-based computer vision tool that can automatically segment keyhole shapes out of X-ray images is presented. The pipeline contains a filtering method and an implementation of the BASNet deep learning model to semantically segment the keyhole morphologies out of X-ray images. The presented tool shows promising average accuracy of 91.24% for keyhole area, and 92.81% for boundary shape, for a range of test dataset conditions in Al6061 (and one AliSi10Mg) alloys, with 300 training images/labels and 100 testing images for each trial. Prospective users may apply the presently trained tool or a retrained version following the approach used here to automatically label keyhole shapes in large image sets. [ABSTRACT FROM AUTHOR]

Smart grids fall at the intersection of conventional energy systems and modern informatics in the present digitalized energy environment. The growing number of linked devices and sensors in these networks leads to the generation of complex structures and vast quantities of data, presenting benefits and challenges. Safeguarding these complex structures against malicious intrusions and illegal activities is an important problem. The paper's main objective is to enhance smart grid security by utilizing the data mining and Artificial Intelligence (AI) approaches. As huge amounts of data are collected from the smart grids based on tiny and smart internet of things (IoT) devices, this data poses challenges as well as provides opportunities. The challenges come from analyzing this huge data, especially in real-time. At the same time, it provides opportunities to enhance the smart grid services and protection. Therefore, to overcome these challenges, this paper proposes a feedforward deep learning approach for data mining to secure the smart grid from different anomalies and allow the system to adapt to any risk it might face. Deep learning will allow the system to adjust dynamically to emerging risks. The proposed system has been examined using Power System Attack Datasets sourced from the Mississippi State University and Oak Ridge National Laboratory. The results show a detection accuracy of 91% just using 50% of the dataset features. Different percentages of the features are examined as well. However, we concluded that 50% of the features are enough for identifying the smart grid risks based on the given dataset. [ABSTRACT FROM AUTHOR]

Distributed deep learning is a promising approach for training and deploying large and complex deep learning models. This paper presents a comprehensive workflow for deploying and optimizing the YOLACT instance segmentation model as on big data clusters. OpenVINO, a toolkit known for its high-speed data processing and ability to optimize deep learning models for deployment on a variety of devices, was used to optimize the YOLACT model. The model is then run on a big data cluster using BigDL, a distributed deep learning library for Apache Spark. BigDL provides a high-level programming interface for defining and training deep neural networks, making it suitable for large-scale deep learning applications. In distributed deep learning, input data is divided and distributed across multiple machines for parallel processing. This approach offers several advantages, including the ability to handle very large data that can be stored in a distributed manner, scalability to decrease processing time by increasing the number of workers, and fault tolerance. The proposed workflow was evaluated on virtual machines and Azure Databricks, a cloud-based platform for big data analytics. The results indicated that the workflow can scale to large datasets and deliver high performance on Azure Databricks. This study explores the benefits and challenges of using distributed deep learning on big data clusters for instance segmentation. Popular distributed deep learning frameworks are discussed, and BigDL is chosen. Overall, this study highlights the practicality of distributed deep learning for deploying and scaling sophisticated deep learning models on big data clusters. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to time series forecasting, an area of significant importance across diverse fields such as finance, meteorology, and industrial production. Time series data, characterized by its complexity involving trends, cyclicality, and random fluctuations, necessitates sophisticated methods for accurate forecasting. Traditional forecasting methods, while valuable, often struggle with the non-linear and non-stationary nature of time series data. To address this challenge, we propose an innovative model that combines signal decomposition and deep learning techniques. Our model employs Generalized Autoregressive Conditional Heteroskedasticity (GARCH) for learning the volatility in time series changes, followed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for data decomposition, significantly simplifying data complexity. We then apply Graph Convolutional Networks (GCN) to effectively learn the features of the decomposed data. The integration of these advanced techniques enables our model to fully capture and analyze the intricate features of time series data at various interval lengths. We have evaluated our model on multiple typical time-series datasets, demonstrating its enhanced predictive accuracy and stability compared to traditional methods. This research not only contributes to the field of time series forecasting but also opens avenues for the application of hybrid models in big data analysis, particularly in understanding and predicting the evolution of complex systems. [ABSTRACT FROM AUTHOR]

Energy management systems for residential and commercial buildingsmust use an appropriate and efficientmodel to predict energy consumption accurately. To deal with the challenges in powermanagement, the short-termPower Consumption (PC) prediction for household appliances plays a vital role in improving domestic and commercial energy efficiency. Big data applications and analytics have shown that data-driven load forecasting approaches can forecast PC in commercial and residential sectors and recognize patterns of electric usage in complex conditions. However, traditional Machine Learning (ML) algorithms and their features engineering procedure emphasize the practice of inefficient and ineffective techniques resulting in poor generalization. Additionally, different appliances in a home behave contrarily under distinct circumstances, making PC forecasting more challenging. To address these challenges, in this paper a hybrid architecture using an unsupervised learning strategy is investigated. The architecture integrates a one-dimensional Convolutional Neural Network (CNN) based Autoencoder (AE) and online sequential Extreme Learning Machine (ELM) for commercial and residential short-term PC forecasting. First, the load data of different buildings are collected and cleaned from various abnormalities. A subsequent step involves AE for learning a compressed representation of spatial features and sending them to the online sequential ELM to learn nonlinear relations and forecast the final load. Finally, the proposed network is demonstrated to achieve State-of-the-Art (SOTA) error metrics based on two benchmark PC datasets for residential and commercial buildings. The Mean Square Error (MSE) values obtained by the proposed method are 0.0147 and 0.0121 for residential and commercial buildings datasets, respectively. The obtained results prove that our model is suitable for the PC prediction of different types of buildings. [ABSTRACT FROM AUTHOR]

Intelligent forecasting of economic indexes has been an important demand for sustainable management of smart cities. Existing methods for this purpose were mostly established upon the basis of economic mechanism. Econometric models are the most general technical means in this area. However, in era of digital economy, increasing amount of big data has brought great change to traditional production. It is becoming more difficult for conventional technological forecasting methods to deal with multi-dimensional economic indexes. To deal with such challenge, this paper introduces the artificial intelligence algorithms to implement automatic information processing, and proposes a deep neural network-based intelligent forecasting method for multi-dimensional economic indexes in smart cities. Specifically, a deep neural network with three-layer structure is developed as the backbone methodology. For empirical analysis, the real-world data from "Chengdu–Chongqing Economic Circle" in China from 2012 to 2022 are selected as the main simulation scenario. Four major indexes are selected as the main research object: gross product (GDP), per capita GDP, GDP growth rate and the proportion of tertiary industry in GDP. The experimental results show that the proposal can well deal with such forecasting problem from a data-driven perspective, with a proper forecasting effect on historical data. [ABSTRACT FROM AUTHOR]

Thyroid cancer incidences endure to increase even though a large number of inspection tools have been developed recently. Since there is no standard and certain procedure to follow for the thyroid cancer diagnoses, clinicians require conducting various tests. This scrutiny process yields multi-dimensional big data and lack of a common approach leads to randomly distributed missing (sparse) data, which are both formidable challenges for the machine learning algorithms. This paper aims to develop an accurate and computationally efficient deep learning algorithm to diagnose the thyroid cancer. In this respect, randomly distributed missing data stemmed singularity in learning problems is treated and dimensionality reduction with inner and target similarity approaches are developed to select the most informative input datasets. In addition, size reduction with the hierarchical clustering algorithm is performed to eliminate the considerably similar data samples. Four machine learning algorithms are trained and also tested with the unseen data to validate their generalization and robustness abilities. The results yield 100% training and 83% testing preciseness for the unseen data. Computational time efficiencies of the algorithms are also examined under the equal conditions. [ABSTRACT FROM AUTHOR]

Nowadays, computational intelligence-assisted autonomous assessment of education quality has become a more and more general concern in the area of smart education management. As education quality assessment is a complicated process with multiple heterogeneous factors, it remains challenging to make effective assessment using simple information modality and criteria. To deal with this issue, this paper introduces multiscale deep learning, and proposes a novel data-driven autonomous assessment framework for education quality. In particular, four aspects of heterogeneous indicators are selected as the basic indexes and a dilated convolutional neural network structure is formulated to perform multiscale feature extraction. Then, the structural equation is adopted to make multivariate characterization and output the final assessment results. At last, some simulations are carried out on realistic education operation data to evaluate the efficiency of the proposed autonomous assessment framework. Two aspects of findings can be deduced from the results. For one thing, multisource fusion of multiple indicators well makes sense to autonomous education assessment. For another, multiscale deep learning can provide some beneficial promotion to assessment efficiency. [ABSTRACT FROM AUTHOR]

Nowadays, the increasing growth of technology contributes various organisations to storing a huge amount of records using web servers in the form of big data. The big database possesses a vast amount of relevant and irrelevant features, and the less significant features are difficult to remove which makes the process time-consuming and more complex. Hence, this paper proposes an optimisation algorithm, named the Taylor Jellyfish Search Optimisation (TaylorJSO) for selecting the relevant features. Here, an optimisation-based deep learning approach called Taylor Jellyfish Search Optimisation-Deep Maxout Network (TaylorJSO-DMN) is introduced to classify big data more effectively by selecting optimal features. In this model, the input database is preprocessed using quantile normalisation and uses the oversampling of imbalanced classes for data augmentation. In the MapReduce framework, the selection of optimal features is performed in the mapper phase, whereas in the reducer phase, the DMN is used for the classification of big data. The DMN is trained using the introduced TaylorJSO algorithm to improve the classification performance of big data classification. Moreover, the TaylorJSO-DMN model attained greater performance with a maximum of 92.5% accuracy, 91.6% sensitivity, and 92.9% specificity than other traditional approaches. [ABSTRACT FROM AUTHOR]

In this review article, we explore the transformative impact of deep learning (DL) on structural bioinformatics, emphasizing its pivotal role in a scientific revolution driven by extensive data, accessible toolkits and robust computing resources. As big data continue to advance, DL is poised to become an integral component in healthcare and biology, revolutionizing analytical processes. Our comprehensive review provides detailed insights into DL, featuring specific demonstrations of its notable applications in bioinformatics. We address challenges tailored for DL, spotlight recent successes in structural bioinformatics and present a clear exposition of DL—from basic shallow neural networks to advanced models such as convolution, recurrent, artificial and transformer neural networks. This paper discusses the emerging use of DL for understanding biomolecular structures, anticipating ongoing developments and applications in the realm of structural bioinformatics. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Accurate and objective human resources performance management evaluation methods are conducive to a comprehensive understanding of the real and objective situation of teachers, and are conducive to identifying the management, teaching and academic level of teachers, which enables teacher managers to have a clear understanding of the gaps and problems among teachers. OBJECTIVES: Aiming at the current human resources performance management evaluation method, there are evaluation indexes exist objectivity is not strong, poor precision, single method and other problems. METHODS: This research puts forward an intelligent optimisation algorithm based on the improvement of the depth of the limit of the learning machine network of human resources performance management evaluation method. (1) Through the analysis of the problems existing in the current human resources performance management, select the human resources performance management evaluation indexes, and construct the human resources performance management evaluation system; (2) Through the multi-strategy grey wolf optimization algorithm method to improve the deep learning network, and construct the evaluation model of the human resources performance management in colleges; (3) The analysis of simulation experiments verifies the high precision and real-time nature of the proposed method. RESULTS: The results show that the proposed method improves the precision of the evaluation model, improves the prediction time. CONCLUSION: This research solves the problems of low precision and non-objective system indicators of human resource performance management evaluation. [ABSTRACT FROM AUTHOR]

High-performance sparse matrix multipliers are essential for deep learning applications, and as big data analytics continues to evolve, specialized accelerators are also needed to efficiently handle sparse matrix operations. This paper proposes a modified, configurable, outer product based architecture for sparse matrix multiplication, and explores design space of the proposed architecture. The performance of various architecture configurations has been examined for input samples with similar characteristics. The proposed architecture has been implemented on Xilinx Kintex-7 FPGA using 32-bit single precision floating-point arithmetic and also in 8-bit, 16-bit and 32-bit fixed-point arithmetic formats. The effect of quantization in the proposed architecture has been analyzed extensively and the results have been reported. The performance of the proposed architecture has been compared with state-of-the-art implementations, and an improvement of 9.21% has been observed in the performance. [ABSTRACT FROM AUTHOR]

We use deep neural networks to estimate an asset pricing model for individual stock returns that takes advantage of the vast amount of conditioning information, keeps a fully flexible form, and accounts for time variation. The key innovations are to use the fundamental no-arbitrage condition as criterion function to construct the most informative test assets with an adversarial approach and to extract the states of the economy from many macroeconomic time series. Our asset pricing model outperforms out-of-sample all benchmark approaches in terms of Sharpe ratio, explained variation, and pricing errors and identifies the key factors that drive asset prices. This paper was accepted by Agostino Capponi, finance. Supplemental Material: The online appendix and data are available at https://doi.org/10.1287/mnsc.2023.4695. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to describe a methodology that was developed to support maintenance decision-making methods based on equipment condition. Condition-Based Maintenance allows to increase equipment availability and maximize investments. This is mainly due to the prevention of unexpected equipment downtime. By avoiding turning on/off industrial equipment, production flows are more efficient, allowing manufacturers to improve the quality of the end-product. The industry aims more and more to correspond satisfying customer expectations. We argue that the methodology developed in this paper adds value to the existing literature, namely because the fact that it is possible to anticipate the state of an equipment without a large amount of support data. In other words, although one could find information gaps regarding the occurrence of failures, it was possible to accurately assess the state of the equipment. This approach is robust, as it can be used in distinct equipment with different sensors, making this methodology generalizable for Condition-Based Maintenance. The paper presents the validation of the preceding through a case study on drying presses in the paper industry. To do so, three states were adopted, namely: "Proper function"; "Alert state"; and "Equipment failure". The methodology follows a series of steps, going through the collection of values from vibration sensors, imputation of values using Deep Artificial Neural Networks through on-line sensors, until reaching the last stage of classification carried out by the Hidden Markov Model. Through optimized observations from the previous steps, it was possible to define the hidden states through the Viterbi algorithm, which corresponds to the health states of the equipment. Additionally, it was possible to demonstrate that the proposed methodology can accurately characterize the condition states of the equipment based on the data obtained and can be generalized to other types of equipment. • Method classifies equipment status without prior info and predicts anomalies using ML. • Using DNN, time series data management was added to better diagnose equipment condition. • Generic method requires no technical knowledge, works online for real-time predictive maintenance. • The algorithm is generic and applicable to various equipment with different sensors. [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]

Maize silage serves as a significant source of energy and fibre for the diets of dairy and beef cattle. However, the quality of maize silage is contingent upon several crucial considerations, including dry matter loss, fermentative profile, pH level, ammonia content, and aerobic stability. These aspects are influenced by a multitude of factors and their interactions, with seasonality playing a crucial role in shaping silage quality. In this study an open-source database was utilised to assess the impact of various pre-ensiling circumstances, including the diversity of the chemical composition of the freshly harvested maize, on the silage quality. The findings revealed that seasonality exerts a profound influence on maize silage quality. Predictive models derived from the composition of freshly harvested maize demonstrated that metrics were only appropriate for screening purposes when utilizing in-field sensor technology. Moreover, this study suggests that a more comprehensive approach, incorporating additional factors and variability, is necessary to better elucidate the determinants of maize silage quality. To address this, combining data from diverse databases is highly recommended to enable the application of more robust algorithms, such as those from machine learning or deep learning, which benefit from large data sets. [ABSTRACT FROM AUTHOR]

The online learning become a choice of most educational institution which creates enormous data on learning platform. This study introduces a novel framework that leverages Big Data analytics, with a focus on sentiment analysis, to decipher student requirements and preferences regarding course offerings and content. The objective is to harness the vast amounts of unstructured feedback generated by students in the form of reviews, forum posts, and surveys to inform and enhance educational strategies. We propose a sentiment analysis model multi attention fusion with CNN-BiLSTM model, that is adept at processing natural language and identifying the polarity of sentiments expressed by students. By analyzing this sentiment data, our system can capture the nuanced preferences and needs of students. The model is trained and validated on a diverse dataset encompassing various educational domains and student demographics, ensuring robustness and generalizability of the results. The outcomes indicate that sentiment analysis is an effective tool for uncovering hidden patterns and trends in student feedback. Our findings reveal correlations between student satisfaction and specific course features, such as module content, teaching methodologies, and resource availability. Additionally, the results evaluate precision, recall, accuracy and F1-score. [ABSTRACT FROM AUTHOR]

With advancements in digital technologies such as 5G communications, big data, and cloud computing, the components of network operation systems have become increasingly complex, significantly complicating system monitoring and maintenance. Correspondingly, automated log anomaly detection has become a crucial means to ensure stable network operation and protect networks from malicious attacks or failures. Conventional machine learning and deep learning methods assume consistent distributions between the training and testing data, adhering to a closed-set recognition paradigm. Nevertheless, in realistic scenarios, systems may encounter new anomalies that were not present in the training data, especially in log anomaly detection. Inspired by evidential learning, we propose a novel anomaly detector called LogEDL, which supervises the training of the model through an evidential loss function. Unlike traditional loss functions, the evidential loss function not only focuses on correct classification but also quantifies the uncertainty of predictions. This enhances the robustness and accuracy of the model in handling anomaly detection tasks while achieving functionality similar to open-set recognition. To evaluate the proposed LogEDL method, we conduct extensive experiments on three datasets, i.e., HDFS, BGL, and Thunderbird, to detect anomalous log sequences. The experimental results demonstrate that our proposed LogEDL achieves state-of-the-art performance in anomaly detection. [ABSTRACT FROM AUTHOR]

Astronomy is entering an unprecedented era of big-data science, driven by missions like the ESA's Gaia telescope, which aims to map the Milky Way in three dimensions. Gaia's vast dataset presents a monumental challenge for traditional analysis methods. The sheer scale of this data exceeds the capabilities of manual exploration, necessitating the utilization of advanced computational techniques. In response to this challenge, we developed a novel approach leveraging deep learning to estimate the metallicity of fundamental mode (ab-type) RR Lyrae stars from their light curves in the Gaia optical G-band. Our study explores applying deep-learning techniques, particularly advanced neural-network architectures, in predicting photometric metallicity from time-series data. Our deep-learning models demonstrated notable predictive performance, with a low mean absolute error (MAE) of 0.0565, the root mean square error (RMSE) of 0.0765, and a high  R 2  regression performance of 0.9401, measured by cross-validation. The weighted mean absolute error (wMAE) is 0.0563, while the weighted root mean square error (wRMSE) is 0.0763. These results showcase the effectiveness of our approach in accurately estimating metallicity values. Our work underscores the importance of deep learning in astronomical research, particularly with large datasets from missions like Gaia. By harnessing the power of deep-learning methods, we can provide precision in analyzing vast datasets, contributing to more precise and comprehensive insights into complex astronomical phenomena. [ABSTRACT FROM AUTHOR]

Identifying cellular identities is a key use case in single-cell transcriptomics. While machine learning has been leveraged to automate cell annotation predictions for some time, there has been little progress in scaling neural networks to large data sets and in constructing models that generalize well across diverse tissues. Here, we propose scTab, an automated cell type prediction model specific to tabular data, and train it using a novel data augmentation scheme across a large corpus of single-cell RNA-seq observations (22.2 million cells). In this context, we show that cross-tissue annotation requires nonlinear models and that the performance of scTab scales both in terms of training dataset size and model size. Additionally, we show that the proposed data augmentation schema improves model generalization. In summary, we introduce a de novo cell type prediction model for single-cell RNA-seq data that can be trained across a large-scale collection of curated datasets and demonstrate the benefits of using deep learning methods in this paradigm. Identifying cellular identities is crucial in single-cell transcriptomics. Here, authors show that large-scale deep learning-based cell annotation models, trained on hundreds of cross-tissue scRNA-seq datasets, enhance prediction quality for fine-grained highly related cell types and states. [ABSTRACT FROM AUTHOR]

Short-term prediction of origin–destination (OD) flow is a primary but complex assignment to urban rail companies, which is the basis of intelligent and real-time urban rail transit (URT) operation and management. The short-term prediction of URT OD flow has three special characteristics: data lag, data dimensionality, and data malconformation, distinguishing it from other short-term prediction tasks. It is essential to propose a novel prediction algorithm that considers the special characteristics of the URT OD flow. For this purpose, based on deep learning methods and multi-source big data, a modified spatial–temporal long short-term memory (ST-LSTM) model is established. The proposed model comprises four components: (1) a temporal feature extraction module is devised to extract time information within network-wide historical OD data; (2) a spatial correlation learning module is introduced to address the data malconformation and data dimensionality problems, which provides an interpretable spatial correlation quantization method; (3) an input control-gated mechanism is originally proposed to solve the data lag problem, which combines the processed available OD flow and real-time inflow/outflow; (4) a fusion module combines historical spatial–temporal features with real-time information to achieve accurate OD flow prediction. We also further discuss the interpretability of the model in detail. The ST-LSTM model is evaluated by sufficient experiments on two large-scale actual subway datasets from Nanjing and Beijing, and the experimental results demonstrate that it can better learn the spatial–temporal correlations and exceed the rest benchmarking methods. [ABSTRACT FROM AUTHOR]

IT governance is a framework that manages the efficient use of information technology within an organization, focusing on strategic alignment, risk management, resource management, performance measurement, compliance, and value delivery. This study investigates the role of IT governance in integrating artificial intelligence (AI) in accounting and auditing operations. Data were collected from 228 participants from Saudi Arabia using a combination of convenience sampling and snowball sampling methods. The collected data were then analyzed using structural equation modeling. Unexpectedly, the results demonstrate that AI, big data analytics, cloud computing, and deep learning technologies significantly enhance accounting and auditing functions' efficiency and decision-making capabilities, leading to improved financial reporting and audit processes. The results highlight that IT governance plays a crucial role in managing the complexities of AI integration, aligning business strategies with AI-enabled technologies, and facilitating these advancements. This research fills a gap in previous research and adds significantly to the academic literature by improving the understanding of integrating AI into accounting and auditing processes. It builds on existing theoretical frameworks by investigating the role of IT governance in promoting AI adoption. The findings provide valuable insights for accounting and auditing experts, IT specialists, and organizational leaders. The study provides practical insights on deploying AI-driven technology in organizations to enhance auditing procedures and financial reporting. In a societal context, it highlights the broader implications of AI on transparency, accountability, and trust in financial reporting. Finally, the study offers practitioners, policymakers, and scholars valuable insights on leveraging AI advancements to optimize accounting and auditing operations. It highlights IT governance as an essential tool for effectively integrating AI technologies in accounting and auditing operations. However, successful implementation encounters significant organizational challenges like organizational support, training, data sovereignty, and regulatory compliance. [ABSTRACT FROM AUTHOR]

Existing sales forecasting models are not comprehensive and flexible enough to consider dynamic changes and nonlinearities in sales time-series at the store and product levels. To capture different big data characteristics in sales forecasting data, such as seasonal and trend variations, this study develops a hybrid model combining adaptive trend estimated series (ATES) with a deep neural network model. ATES is first used to model seasonal effects and incorporate holiday, weekend, and marketing effects on sales. The deep neural network model is then proposed to model residuals by capturing complex high-level spatiotemporal features from the data. The proposed hybrid model is equipped with a feature-extraction component that automatically detects the patterns and trends in time-series, which makes the forecasting model robust against noise and time-series length. To validate the proposed hybrid model, a large volume of sales data is processed with a three-dimensional data model to effectively support business decisions at the product-specific store level. To demonstrate the effectiveness of the proposed model, a comparative analysis is performed with several state-of-the-art sales forecasting methods. Here, we show that the proposed hybrid model outperforms existing models for forecasting horizons ranging from one to 12 months. [ABSTRACT FROM AUTHOR]

Corrosion brings serious losses to the economy annually. Therefore, various corrosion protection and detection techniques are widely used in the daily maintenance of large metal engineering structures. The emergence of image recognition technology has brought a more convenient and faster way for nondestructive testing. Existing image recognition technology can be divided into two categories according to the algorithm: traditional image recognition technology and image recognition technology based on deep learning. These two types of technologies have been widely used in the three fields of metal, coating, and electrochemical data images. A large amount of work has been carried out to identify defects in metals and coatings, and deep learning-based methods also show potential for identifying electrochemical data images. Matching electrochemical images with the detection of defect morphology will bring a deeper understanding of image recognition techniques for metals and coatings. A database of accumulated morphology and electrochemical parameters will make it possible to predict the life of steel and coatings using image recognition techniques. [ABSTRACT FROM AUTHOR]

In clinical datasets, missing data often occur due to various reasons including non-response, data corruption, and errors in data collection or processing. Such missing values can lead to biased statistical analyses, reduced statistical power, and potentially misleading findings, making effective imputation critical. Traditional imputation methods, such as Zero Imputation, Mean Imputation, and k-Nearest Neighbors (KNN) Imputation, attempt to address these gaps. However, these methods often fall short of accurately capturing the underlying data complexity, leading to oversimplified assumptions and errors in prediction. This study introduces a novel Imputation model employing transformer-based architectures to address these challenges. Notably, the model distinguishes between complete EEG signal amplitude data and incomplete data in two datasets: PhysioNet and CHB-MIT. By training exclusively on complete amplitude data, the TabTransformer accurately learns and predicts missing values, capturing intricate patterns and relationships inherent in EEG amplitude data. Evaluation using various error metrics and R2 score demonstrates significant enhancements over traditional methods such as Zero, Mean, and KNN imputation. The Proposed Model achieves impressive R2 scores of 0.993 for PhysioNet and 0.97 for CHB-MIT, highlighting its efficacy in handling complex clinical data patterns and improving dataset integrity. This underscores the transformative potential of transformer models in advancing the utility and reliability of clinical datasets. [ABSTRACT FROM AUTHOR]

Deep-learning algorithms for cell segmentation typically require large data sets with high-quality annotations to be trained with. However, the annotation cost for obtaining such sets may prove to be prohibitively expensive. Our work aims to reduce the time necessary to create high-quality annotations of cell images by using a relatively small well-annotated data set for training a convolutional neural network to upgrade lower-quality annotations, produced at lower annotation costs. We investigate the performance of our solution when upgrading the annotation quality for labels affected by three types of annotation error: omission, inclusion, and bias. We observe that our method can upgrade annotations affected by high error levels from 0.3 to 0.9 Dice similarity with the ground-truth annotations. We also show that a relatively small well-annotated set enlarged with samples with upgraded annotations can be used to train better-performing cell segmentation networks compared to training only on the well-annotated set. Moreover, we present a use case where our solution can be successfully employed to increase the quality of the predictions of a segmentation network trained on just 10 annotated samples. [ABSTRACT FROM AUTHOR]

Introduction: Artificial intelligence (AI) tools are increasingly being integrated into computer-aided diagnosis systems that can be applied to improve the recognition and clinical and molecular characterization of allergic diseases, including eosinophilic esophagitis (EoE). This review aims to systematically evaluate current applications of AI, machine learning (ML), and deep learning (DL) methods in EoE characterization and management. Methods: We conducted a systematic review using a registered protocol published in the International Prospective Register of Systematic Reviews (CRD42023451048). The risk of bias and applicability of eligible studies were assessed according to the prediction model study risk of bias assessment tool (PROBAST). We searched PubMed, Embase, and Web of Science to retrieve the articles. The literature review was performed in May 2023. We included original research articles (retrospective or prospective studies) published in English in peer-reviewed journals, studies whose participants were patients with EoE, and studies assessing the application of AI, ML, or DL models. Results: A total of 120 articles were found. After removing 68 duplicates, 52 articles were reviewed based on the title and abstract, and 34 were excluded. Eleven full texts were assessed for eligibility, met the inclusion criteria, and were analyzed for the systematic review. The AI models developed in three studies for identifying EoE based on endoscopic images showed high score performance with an accuracy that ranged from 0.92 to 0.97. Five studies developed AI models that histologically identified EoE with high accuracy (87% to 99%). We also found two studies where the AI model identified subgroups of patients according to their clinical and molecular features. Conclusions: AI technologies could promote more accurate evidence-based management of EoE by integrating the results of molecular signature, clinical, histology, and endoscopic features. However, the era of AI application in medicine is just beginning; therefore, further studies with model validation in the real-world environment are required. [ABSTRACT FROM AUTHOR]

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology. [ABSTRACT FROM AUTHOR]

Image retrieval methods are currently developing towards big data processing. The literature review is focused on image big data extraction with cultural heritage domain as training and testing datasets. The development of image retrieval process starts from content-based using machine algorithms, deep learning to ontology-based. Image recognition research with cultural heritage domain is conducted because of the importance of preserving and appreciating cultural heritage, in this case, cultural heritage images such as Indonesian Batik are discussed. Batik motif images are Indonesian cultural heritage that has thousands of motifs that are grouped into many classes with a non-linear hyperplane. The problem is focused on processing big data that has many classes. Currently research is evolving into knowledge-based image retrieval using ontologies due to semantic gap constraints. The results of this literature study can be the basis for developing research on the application of appropriate deep learning algorithms so as to utilize the hierarchy of classes and subclasses of image ontologies with cultural heritage domains. [ABSTRACT FROM AUTHOR]

Abstract The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms.

• 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]

[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]

The utilization of street view big data is increasingly being used to uncover visual characteristics and spatial perceptions of urban streets. However, there is a lack of studies that combine street view big data for perceptual evaluation in underdeveloped ethnic areas and better street quality. This study integrates deep learning methods to create a human–computer confrontational model for perception score, with a focus on the central city of Lhasa in Tibet. Pearson correlation analysis was conducted on six dimensions of perception data (beautiful, wealthy, safe, lively, boring and depressing) and visual elements. The streets in the top 20% for both visual elements and perceptual scores were identified to reveal areas with high visual element proportions and high perceptual scores. The spatial distribution characteristics and correlation between visual elements and street perceptions were thoroughly analyzed. The findings of this study reveal that the central city of Lhasa exhibited high percentages of visual elements in buildings (88.23%), vegetation (89.52%), and poles (3.14%). Out of the six perceptions examined, the highest scores were for boring (69.70) and depressing (67.76) perceptions, followed by beautiful (60.66) and wealthy (59.91) perceptions, with lively (56.68) and safe (50.64) perceptions receiving the lowest scores. Visual components like roads (−0.094), sidewalks (−0.031), fences (−0.036), terrain (−0.020), sky (−0.098), cars (−0.016), and poles (−0.075) were observed to have a significant deterring effect on the boring perception, while other visual elements showed a positive influence. This investigation seeks to provide valuable insights for the design and advancement of urban streets in marginalized ethnic localities, addressing a void in perception research of urban streets in such areas. [ABSTRACT FROM AUTHOR]

As big data technologies for IoT services develop, cross-service distributed learning techniques of multivariate deep learning models on IoT time-series data collected from various sources are becoming important. Vertical federated deep learning (VFDL) is used for cross-service distributed learning for multivariate IoT time-series deep learning models. Existing VFDL methods with reasonable performance require a large communication amount. On the other hand, existing communication-efficient VFDL methods have relatively low performance. We propose TT-VFDL-SIM, which can achieve improved performance over centralized training or existing VFDL methods in a communication-efficient manner. TT-VFDL-SIM derives partial tasks from the target task and applies transfer learning to them. In our task-driven transfer approach for the design of TT-VFDL-SIM, the SIM Partial Training mechanism contributes to performance improvement by introducing similar feature spaces in various ways. TT-VFDL-SIM was more communication-efficient than existing VFDL methods and achieved an average of 0.00153 improved MSE and 7.98% improved accuracy than centralized training or existing VFDL methods. [ABSTRACT FROM AUTHOR]

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a lowdimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources. [ABSTRACT FROM AUTHOR]