Search

We propose a flexible low complexity design (FLCD) of coded distributed computing (CDC) with empirical evaluation on Amazon Elastic Compute Cloud (Amazon EC2). CDC can expedite MapReduce like computation by trading increased map computations to reduce communication load and shuffle time. A main novelty of FLCD is to utilize the design freedom in defining map and reduce functions to develop asymptotic homogeneous systems to support varying intermediate values (IV) sizes under a general MapReduce framework. Compared to existing designs with constant IV sizes, FLCD offers greater flexibility in adapting to network parameters and significantly reduces the implementation complexity by requiring fewer input files and shuffle groups. The FLCD scheme is the first proposed low-complexity CDC design that can operate on a network with an arbitrary number of nodes and computation load. We perform empirical evaluations of the FLCD by executing the TeraSort algorithm on an Amazon EC2 cluster. This is the first time that theoretical predictions of the CDC shuffle time are validated by empirical evaluations. The evaluations demonstrate a 2.0 to 4.24x speedup compared to conventional uncoded MapReduce, a 12% to 52% reduction in total time, and a wider range of operating network parameters compared to existing CDC schemes., 13 pages, 4 figures

Cloud deployment architectures have become a preferable computation model of Big Data (BD) operations. Their scalability, flexibility, and cost-effectiveness motivated this trend. In a such deployment model, the data are no longer physically maintained under the user’s direct control, which raises new security concerns. In this context, BD security plays a decisive role in the widespread adoption of cloud architectures. However, it is challenging to develop a comprehensive security plan unless it is based on a preliminary analysis that ensures a realistic secure assembly and addresses domain-specific vulnerabilities. This article presents a novel security-by-design framework for BD frameworks deployment over cloud computing (BigCloud). In particular, it relies on a systematic security analysis methodology and a completely automated security assessment framework. Our framework enables the mapping of BigCloud security domain knowledge to the best practices in the design phase. We validated the proposed framework by implementing an Apache Hadoop stack use case. The study findings demonstrate its effectiveness in improving awareness of security aspects and reducing security design time. It also evaluates the strengths and limitations of the proposed framework, from which it highlights the main existing and open challenges in the BigCloud-related area.

The Internet of Things (IoT) aids an interconnection between systems, humans, and services to develop computation-intensive autonomous applications. Service-oriented architecture (SOA) concepts have been used as defacto software architecture to develop IoT-based systems. Though SOA facilitates various benefits, several challenges exist for integration with IoT-based systems, including configurability, interoperability, and manageability. The ontology-based approach provides a semantically enriched and rigorous platform for interoperating different heterogeneous IoT-based systems and applications. The semantic modelling research has focused on IoT resource management without concerning the method of accessing and utilizing IoT information. In this context, an IoT-based large-scale SOA (IoT-LSS) ontology is proposed that supports interoperability, heterogeneity, flexibility, manageability, extendibility, scalability. This ontology integrates the concept of large-scale SOA (LSS) with semantic sensor network (SSN) ontology. Clinical decision support system (CDSS) ontology has considered as a case study to illustrate the proposed ontology. A detailed comparative analysis between the proposed system and several existing IoT-based service ontologies has been performed based on different characteristics. This analysis shows that IoT-LSS supports dynamic features and exposes to service with its different mechanisms. This article presents an ontological framework for the IoT service-based environment to efficiently use for service composition mechanisms in the large service domain.

The Internet of Things (IoT) has been growing over the past few years due to its flexibility and ease of use in real-time applications. The IoT’s foremost task is ensuring that there is proper communication between different types of applications and devices, and that the application layer protocols fulfill this necessity. However, as the number of applications grows, it is necessary to modify or enhance the application layer protocols according to specific IoT applications, allowing specific issues to be addressed, such as dynamic adaption to network conditions and interoperability. Recently, several IoT application layer protocols have been enhanced and modified according to application requirements. However, no existing survey articles have focused on these protocols. In this article, we survey traditional and recent advances in IoT application layer protocols, as well as relevant real-time applications and their adapted application layer protocols for improving performance. As changing the nature of protocols for each application is unrealistic, machine learning offers means of making protocols intelligent and able to adapt dynamically. In this context, we focus on providing open challenges to drive IoT application layer protocols in such a direction.

This article presents a planner for a master dual-arm robot to manipulate tethered tools with the help of an assistant dual-arm robot. The assistant robot assists the master robot by manipulating the tool cable and avoiding collisions. The provided assistance allows the master robot to perform tool placements on the robot workspace table and regrasp it, which would typically fail since cable tension may change the tool positions. It also allows the master robot to perform tool handovers, which would normally cause entanglements or collisions with the cable and the environment without assistance. Simulations and real-world experiments are performed to validate the proposed planner. Experimental results show that with the help of the assistant dual-arm robot and the proposed method, the master robot obtained improved flexibility in working with tethered tools.

Many efforts have been dedicated to addressing data loss in various domains. While task-specific solutions may eliminate the respective issue in certain applications, finding a generic method for missing data estimation is rather complex. In this regard, this article proposes a novel missing data imputation algorithm, which has supreme generalization ability for a vast variety of applications. Making use of both complete and incomplete parts of data, the proposed algorithm reduces the effect of missing ratio, which makes it suitable for situations with very high missing ratios. In addition, this feature enables model construction on incomplete training sets, which is rarely addressed in the literature. Moreover, the nonparametric nature of this new algorithm brings about supreme flexibility against all variations of missing values and data distribution. We incorporate the advantages of denoising autoencoders and ladder architecture into a novel formulation based on deep neural networks. To evaluate the proposed algorithm, a comparative study is performed using a number of reputable imputation techniques. In this process, real-world benchmark datasets from different domains are selected. On top of that, a real cyber-physical system is also evaluated to study the generalization ability of the proposed algorithm for distinct applications. To do so, we conduct studies based on three missing data mechanisms, namely: 1) missing completely at random; 2) missing at random; and 3) missing not at random. The attained results indicate the superiority of the proposed method in these experiments.

The tuning of Microwave Cavity Filters (MCFs) is mostly conducted by experienced operators, and thus is time and resource intensive. The automatic tuning method has received lots of research attention. However, the experience of tuning experts is not described systematically, and the existing methods are not adequate for MCFs with individual differences. Considering that fuzzy expert systems are superior in flexibility and interpretability, a dynamic attention based heuristic fuzzy expert system is proposed in this paper to achieve automatic tuning with high applicability, accuracy, and efficiency. First, the dynamic tuning process is divided into several stages, and the evaluation function of filtering performance is designed for each stage. Second, an improved expert system with dynamic attention is constructed to facilitate the comprehensive evaluation of filtering performance and to balance tuning efficiency and accuracy. Third, a heuristic fuzzy logic system is presented to obtain appropriate tuning values, with low design complexity of fuzzy rules and high utilization of tuning process information. Last, the effectiveness, applicability, and practicality of the proposed method are demonstrated by both simulations and experiments.

Computational experiments are an important method for carrying out the quantitative analysis of complex systems and play a major role in mapping the real world to the virtual world. However, the flexibility of computational experiments leads to arbitrary modeling processes and unconvincing results, which greatly hinder the large-scale application of this method. In this context, the verification of computational models has become an urgent problem in this field. Currently, model evaluation is still in its infancy and the existing evaluation methods are not mature enough. Thus, we took epidemic models as the research object and proposed a capability maturity evaluation framework for computational models of artificial society. The framework differs from previous assessment methods that focus on the validity of results, but instead provides a comprehensive evaluation from two perspectives: 1) evaluation of the model itself--by comparing the expectation with the final implementation, we can obtain whether the model meets the expectation and 2) comparison between different models--by evaluating the implementation process of each model and comparing the results, we can identify more mature models. The implementation of the model is evaluated from input, process, and output. Further, specific analyses and evaluations are conducted for several representative COVID-19 models to verify the validity of this evaluation framework. The results of the case study show that the proposed evaluation framework can help decision-makers identify more mature and referential models, and point out the directions where modelers can improve their models. IEEE

Most existing voltage optimization approaches of low voltage distribution networks (LVDNs) assume users follow the regulations unconditionally,which is not always true.To tackle this, we propose a real-time peer to peer flexibility trading scheme for LVDNs. Besides distributed optimization, our scheme offers a way to let users trade their flexibility, in case some users do not want to follow the system regulations at some point. The scheme consists of flexibility allocation and trading. Player compatibility equilibrium and Bernoulli trials are employed to approximate the Pareto optimum in flexibility allocation,while consensus and voltage reference are used to provide real-time offers for flexibility trading. The proposed scheme is computationally tractable and can work with limited communication in a decentralized manner. All the user data is used locally so that privacy is well protected. A network based on a real Belgian semiurban LVDN is employed to validate the proposed scheme with three different scenarios. Besides, the flexibility allocation is benchmarked with a centralized ACOPF algorithm. The case studies result clearly prove the effectiveness and robustness of the proposed scheme. ispartof: Ieee Transactions On Power Systems vol:37 issue:4 pages:2821-2832 status: published

Security and privacy of data-in-transit are critical issues in Industry 4.0 which are further amplified by the use of faster communication technologies such as 6G. Along with security issues, computation and communication costs, as well as data confidentiality, must be also accommodated. In this work, we design a cybertwin-based cloud-centric network architecture to improve the flexibility and scalability of 6G industrial networks. Cybertwin not only enables the deployment of advanced security solutions but also provides an always-on connection. However, the security of data-in-transit over wireless communication between users/things and cybertwin remains a concern. Hence, a privacy-preserving authentication scheme based on digital signature and authenticated key exchange protocol is designed to address the security concerns of data exchanged. Additionally, we conduct a security analysis that proves that the scheme resists several attacks in the industry 4.0 environment. Moreover, the evaluation performed confirmed the superiority of the proposed work comparing to the existing works.

Power systems are facing the challenges of integrating massive electric vehicles (EVs) and lacking operational flexibility. An optimal and efficient coordination strategy is needed to coordinate the operations among EV charging stations (CSs) and the distribution system operator (DSO) and to make full use of the EVs charging flexibility for improving the operational flexibility of power systems. To this end, this paper proposes a CSs-DSO distributed coordination strategy. The proposed strategy integrates a supply-curve-based quantification method to quantify the EVs flexibility contribution and a Nash bargaining game-theory-based peer-to-peer (P2P) transactions model for maximizing the profits of entities participating in the coordination. To tackle the CSs-DSO coordination problem that has a bi-level-parallel coupling structure, an analytical target cascading (ATC) and alternating direction method of multipliers (ADMM) jointly-based distributed solution approach is proposed. First, the CSs-DSO bi-level model is decoupled by ATC with tie-line power being the only exchanged information; then, the model is further decomposed for each CS by ADMM for protecting the CSs privacy and autonomy. The effect of coordination and the computational efficiency of the proposed strategy is verified by numerical simulations on a modified IEEE 33-bus distribution system connecting multiple CSs.

The increase of cyberattacks by using the Internet of Things devices has exposed multiple vulnerabilities not only on devices but also on IoT infrastructures. Now, small devices can affect different networks and their services. This paper presents a review of the vulnerabilities on wireless technologies that gives connectivity to IoT, and the experiences using Software Defined Radio SDR for implementing wireless attacks to IoT technologies are assessed. A systematic literature review was conducted. The types of vulnerabilities and attacks that can affect the wireless technologies that stand the IoT ecosystem and SDR platforms were compared, and recent methods to overcome these attacks were identified. On the IoT reference model, the perception layer was identified as the most vulnerable. Most attacks at this level occur due to hardware limitations, physical device exposure, and heterogeneity of technologies. Future cybersecurity systems based on SDR technologies have notable advantages due to their flexibility and adaptability to new communication technologies and their potential to develop advanced tools. However, the IoT’s cybersecurity challenges are so complex that merging SDR hardware with cognitive and intelligent techniques is highly advisable. Some of these techniques could include deep learning to adapt mitigation systems to rapid technological changes.

The rising volume of sensitive and personal data being harvested by data controllers has increased the security essentials in the cloud system. The cloud module is not used just to store the data, but also to process them on cloud premises. Security for the cloud premises is essential as the cloud has lot of outsourced, unprotected sensitive data for the public access. This has resulted repeated data violations, and thus there is a need for the advanced legal data protection constraints. Various studies were conducted to adopt the privacy preservation in the cloud, and most of the state-of-the-art techniques fail to handle the optimal privacy when dealing with sensitive data, as it requires separate data sanitization and restoration models. To overcome this challenge, this paper tempts to develop the privacy preservation model in the cloud environment using the advancements of artificial intelligent techniques. Artificial Intelligent capabilities are working in the business cloud computing environment to make organizations more efficient, strategic, and insight-driven. However, by hosting the data, cloud computing offers businesses high flexibility, agility, and cost savings. The two main phases of the proposed privacy preservation system are the data sanitization and restoration. Moreover, the proposed sanitization process depends on the optimal key generation, which is performed by the hybrid meta-heuristic algorithm. This hybrid algorithm merges two well-performed algorithms, such as Shark Smell Optimization (SSO) and Jaya Algorithm (JA), and thus termed as Jaya-based Shark Smell Optimization (J-SSO). The optimal key generation is accomplished by deriving a multi-objective function that involves the parameters, such as the degree of modification, hiding ratio, and information preservation ratio. Finally, the performance analysis has proved the efficiency of the proposed model over the state-of-the-art models in enhancing cloud security.

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often over-simplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a two-stage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods., Comment: Author copy of the manuscript submitted to IEEE Trans on Power Systems

Vehicular networks have tremendous potential to improve the road safety and traffic efficiency, and the adoption of the Space-Air-Ground Integrated Network (SAGIN) architecture in vehicular networks can greatly improve the performance of vehicular networks by leveraging the respective advantages of the space, air, and ground segments on coverage, flexibility, reliability, and availability, which results in Space-Air-Ground Integrated Vehicular Networks (SAGIVNs). Trust management is an important tool for constructing trustworthy SAGIVNs, and privacy preservation is also a primary concern in SAGIVNs. They have conflicting requirements and a satisfactory balance between them is urgently required. In this article, we propose a novel Privacy-Preserving Trust Management (PPTM) scheme for the emergency message dissemination in SAGIVNs. The proposed scheme can realize precise trust management and strong conditional privacy preservation simultaneously with low communication overhead, and can provide strong applicability, strong robustness, and multiple other attractive features. Furthermore, the exhaustive theoretical analysis and simulation evaluation are detailed. The results reveal that the proposed scheme is significantly superior to the existing schemes in several aspects.

Batteries can provide valuable operational flexibility to facilitate the system efficiency. However, there lacks market environments to effectively harness and monetize the value of these assets. Most existing works apply a profit-oriented single-signal pricing scheme, which mixes the value of energy and flexibility together and may ultimately raise the electricity bill. Therefore, this paper proposes a profit-neutral double-signal retail pricing scheme that distinguishes elastic market players (i.e., batteries) from inelastic market players (i.e., inflexible loads) and quantifies the value of energy and flexibility separately. Experimental results indicate that under the incentive provided by the proposed retail pricing scheme: 1) The system efficiency benefit aligns with benefits to both batteries and inflexible loads; 2) Value of operational flexibility, contributing to improve the energy efficiency, can be transparently priced and fairly allocated among batteries; and 3) The dominant role in which inflexible loads play on determining the market price is avoided.

Cascading failure is a ubiquitous phenomenon that can paralyze networked systems in a short time. Many traditional studies of cascading failures have been conducted from the perspective of either an attacker or a defender. In reality, however, malicious attacks on networks are rarely a one-sided process. Instead, both the attacker and defender are actively involved. We use game theory to study the strategies of both sides in terms of an attacker-defender game on complex networks. Based on the concept of the Stackelberg competition, we propose a multi-round attacker-defender game model on complex networks, allowing high flexibility in the available actions for both sides in the game. The model we propose allows the two sides to specify certain parameters of the network to attack/defend and further allocate a certain amount of resources for the attack/defense. Such flexibility allows the model to capture the actions of the attackers and defenders more precisely and simulate the attack process in a more realistic manner. We propose an iterative search algorithm to search for desirable strategies with systematic experiments on various types of networks and associated parameters and in terms of different relative resource owned by the attacker and defender.

Despite the advantages of scalability and flexibility, Security Function Virtualization (SFV) raises concerns about its own security. To enhance the security of SFV, a promising approach is to run critical components of off-the-shelf security software inside SGX enclaves. This idea, however, is hardly practical due to the difficulty of detaching components from the monolithic security function and the unacceptable cost of running them in enclaves. In this work, we propose S-Blocks, an architecture to modularize a virtual security function (VSF) and protect its key modules with SGX in an efficient manner. Through systematically decomposing modules of a VSF into related elements, it is easy to put the key modules and elements of the VSF into an enclave. Furthermore, aiming at addressing state consistency and secure migration issues of security function scaling, we design a fine-grained state synchronization and migration mechanism to ensure lose-free, order-preserving, and state security for VSFs. To demonstrate the effectiveness of our approach, we prototype S-Blocks using Fast-Click on a real Skylake platform and implement three main types of virtual security functions based on the S-Blocks architecture. Our evaluation results show that S-Blocks only imposes a manageable performance overhead, and low latency and resource consumption when protecting VSFs.

The past several decades have witnessed a growing enthusiasm to implement the market as an information aggregation tool. However, some deep-rooted pricing anomalies frequently observed in various markets loom large, questioning the rationality of such eagerness. One of these anomalies is the favorite-longshot bias, and sometimes its opposite, the reverse favorite-longshot-bias. We propose an equilibrium model consisting of bettors with cumulative prospect theory-based utility and heterogeneous beliefs to explain these two anomalies in a unified framework. Unlike existing results that mostly focus on one aspect of the underlying model, our model enables us to isolate and analyze the impacts of probability weighting, loss aversion, belief concentration, and belief tailedness. We show how these parameters jointly determine the properties of the equilibrium price. Empirical results also suggest this model has adequate flexibility to explain the behavior of actual historical data.

Community detection is one of the popular research topics in the field of complex networks analysis. It aims to identify communities, represented as cohesive subgroups or clusters, where nodes in the same community link to each other more densely than others outside. Due to the interpretability, simplicity, flexibility, and generality, nonnegative matrix factorization (NMF) has become a very ideal model for community detection and lots of related methods have been presented. To facilitate research on NMF-based community detection, in this article, we make a comprehensive review on NMF-based methods for community detection, especially the state-of-the-art methods presented in high prestige journals or conferences. First, we introduce the basic principles of NMF and explain why NMF can detect communities and design a general framework of NMF-based community detection. Second, according to the applicable network types, we propose a taxonomy to divide the existing NMF-based methods for community detection into six categories, namely, topology networks, signed networks, attributed networks, multilayer networks, dynamic networks, and large-scale networks. We deeply analyze representative methods in every category. Finally, we summarize the common problems faced by all methods and potential solutions and propose four promising research directions. We believe that this survey can fully demonstrate the versatility of NMF-based community detection and serve as a useful guideline for researchers in related fields.

Conventional Semi-supervised learning (SSL) approaches are limited by the reliance on assumptions of samples (manifold assumption, cluster assumption and smoothness assumption) and may fail to reach their full potential when it comes to industrial scenarios with complicated data characteristics. In this paper, a semi-supervised process quality evaluation framework is proposed based on conditional variational auto-encoder. Label inference process is utilized to handle unlabeled samples during training stage and to directly predict the label during the evaluation stage. Real NVP (real-valued non-volume preserving) is introduced to optimize the posterior distribution in order to increase flexibility. The proposed framework does not rely on assumptions of data distributions and it learns the hidden distributions from samples. Gear hobbing simulation and experiment investigations are conducted to verify the effectiveness of the proposed framework. The results indicate that the proposed method can achieve remarkable classification performance compared with other state-of-the-art approaches.

Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an effective end-to-end framework named Document Enhancement Generative Adversarial Networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images. To the best of our knowledge, this practice has not been studied within the context of generative adversarial deep networks. We demonstrate that, in different tasks (document clean up, binarization, deblurring and watermark removal), DE-GAN can produce an enhanced version of the degraded document with a high quality. In addition, our approach provides consistent improvements compared to state-of-the-art methods over the widely used DIBCO 2013, DIBCO 2017 and H-DIBCO 2018 datasets, proving its ability to restore a degraded document image to its ideal condition. The obtained results on a wide variety of degradation reveal the flexibility of the proposed model to be exploited in other document enhancement problems., Accepted in IEEE TPAMI

The concept of the fifth generation (5G) mobile network system has emerged in recent years as telecommunication operators and service providers look to upgrade their infrastructure and delivery modes to meet the growing demand. Concepts such as softwarization, virtualization, and machine learning will be key components as innovative and flexible enablers of such networks. In particular, paradigms such as software-defined networks, software-defined perimeter, cloud & edge computing, and network function virtualization will play a major role in addressing several 5G networks' challenges, especially in terms of flexibility, programmability, scalability, and security. In this work, the role and potential of these paradigms in the context of V2X communication is discussed. To do so, the paper starts off by providing an overview and background of V2X communications. Then, the paper discusses in more details the various challenges facing V2X communications and some of the previous literature work done to tackle them. Furthermore, the paper describes how softwarization, virtualization, and machine learning can be adapted to tackle the challenges of such networks.

Image cropping aims to improve the composition as well as aesthetic quality of an image by removing extraneous content from it. Most of the existing image cropping databases provide only one or several human-annotated bounding boxes as the groundtruths, which can hardly reflect the non-uniqueness and flexibility of image cropping in practice. The employed evaluation metrics such as intersection-over-union cannot reliably reflect the real performance of a cropping model, either. This work revisits the problem of image cropping, and presents a grid anchor based formulation by considering the special properties and requirements (e.g., local redundancy, content preservation, aspect ratio) of image cropping. Our formulation reduces the searching space of candidate crops from millions to no more than ninety. Consequently, a grid anchor based cropping benchmark is constructed, where all crops of each image are annotated and more reliable evaluation metrics are defined. To meet the practical demands of robust performance and high efficiency, we also design an effective and lightweight cropping model. By simultaneously considering the region of interest and region of discard, and leveraging multi-scale information, our model can robustly output visually pleasing crops for images of different scenes. With less than 2.5M parameters, our model runs at a speed of 200 FPS on one single GTX 1080Ti GPU and 12 FPS on one i7-6800K CPU. The code is available at: \url{https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping-Pytorch}., Extension of a CVPR 2019 paper. Dataset and PyTorch Code are released. arXiv admin note: substantial text overlap with arXiv:1904.04441

For a general production network, state-of-the-art methods for constructing sparse flexible designs are heuristic in nature, typically computing a proxy for the quality of unseen networks and using that estimate in a greedy manner to modify a current design. This paper develops two machine learning-based approaches to constructing sparse flexible designs that leverage a neural network to accurately and quickly predict the performance of large numbers of candidate designs. We demonstrate that our heuristics are competitive with existing approaches and produce high-quality solutions for both balanced and unbalanced networks. Finally, we introduce a novel application of process flexibility in healthcare operations to demonstrate the effectiveness of our approach in a large numerical case study. We study the flexibility of linear accelerators that deliver radiation to treat various types of cancer. We demonstrate how clinical constraints can be easily absorbed into the machine learning subroutine and how our sparse flexible treatment networks meet or beat the performance of those designed by state-of-the-art methods.

Under the needs of processing huge amounts of data, providing high-quality service, and protecting user privacy in artificial intelligence of things (AIoT), federated learning (FL) has been treated as a promising technique to facilitate distributed learning with privacy protection. Although the importance of developing privacy-preserving FL has attracted a lot of attentions, the existing research only focuses on FL with independent identically distributed (i.i.d.) data and lacks study of non-i.i.d. scenario. What is worse, the assumption of i.i.d. data is impractical, reducing the performance of privacy protection in real applications. In this article, we carry out an innovative exploration of privacy protection in FL with non-i.i.d. data. First, a thorough analysis on privacy leakage in FL is conducted with proving the performance upper bound of privacy inference attack. Based on our analysis, a novel algorithm, 2DP-FL, is designed to achieve differential privacy by adding noise during training local models and when distributing global model. Especially, our 2DP-FL algorithm has a flexibility of noise addition to meet various needs and has a convergence upper bound. Finally, the real-data experiments can validate the results of our the oretical analysis and the advantages of 2DP-FL in privacy protection, learning convergence, and model accuracy.

Demand response (DR) is an important technique to explore the demand-side flexibility. The wide deployment of smart meters makes it possible to quantify the baseline load. As an intermediate agent, demand response aggregator needs to obtain the aggregated baseline load (ABL) for the DR event. Previous studies about the household level estimation focus on the estimation method. However, for ABL estimation, customer division is an important issue. A major limitation is the mismatch between the objectives of segmentation and estimation. Therefore, this paper proposes a new closed-loop method for estimating the ABL, which utilizes the contextual bandit with policy gradient to link the segmentation with the estimation. As such, the ABL estimation accuracy can guide the segmentation to divide the customers. The segmentation and estimation optimize collaboratively to improve the ABL estimation accuracy. An ensemble method for combining network’s weights during the training process is proposed. Moreover, a pre-and post-event adjustment method is developed to further improve the estimation accuracy. Comprehensive comparisons demonstrate the proposed method can achieve the best estimation performance with regard to the MAPE and RMSE. It improves the estimation accuracy by 7% in terms of MAPE, and 11% in terms of RMSE.

Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.

Seismic data denoising has always been an indispensable step in the seismic exploration workflow. The quality of the results directly affects the results of subsequent inversion and migration imaging. In this article, we proposed a fast and flexible convolutional neural network (FFCNN) based on DnCNN. In contrast to the existing DnCNN and other artificial intelligence (AI)-based denoisers, FFCNN enjoys several desirable properties: 1) downsampling and upscaling operations, which can sensibly reduce runtimes and memory requirements while maintaining the denoising performance, and 2) we introduced noised level maps, which can make that a single convolutional neural network (CNN) model is expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises by noting M can be nonuniform. Another benefit of increasing the noise-level map is that we can preserve more useful seismic data information by controlling the tradeoff of noise removal effect and seismic data detail preservation. For real seismic data denoised work, the main work and advantages of this article are concentrated on the following two aspects: 1) we introduced a data augmentation strategy to overcome the lack of well-labeled samples and 2) transfer learning has been introduced to the training processing, which used the well-trained synthetic seismic data denoising network as a pretrained model. In this way, we can greatly accelerate and optimize the learning efficiency of the training network. Ultimately, we can greatly improve the computational efficiency and denoising performance based on this intelligent denoised network FFCNN. Finally, numerical experiments prove the effectiveness of our method in synthetic and real seismic data.

The Internet-of-Things (IoT) is evolving into the Internet-of-Video-Things (IoVT) that supports massive smart devices and multiple video applications. However, how to effectively control massive devices and transmit large-volume video data have become challenges in the current IoVT. Inspired by Device-to-Device (D2D) communications and coalitional game, this paper constructs a self-organized D2D collaborative video content sharing framework for the IoVT. Specifically, we first propose a collaboration mechanism by introducing the social attributes of IoVT devices and their owners. In this mechanism, D2D collaborative coalitions are automatically formed among IoVT devices and video content is shared in the coalitions through D2D links. By this way, the burden of controlling massive IoVT devices and video data traffic are offloaded. Then, by integrating the scalability of the Scalable-High-Efficiency-Video-Coding (SHVC) streams and the flexibility of D2D networking, a collaborative video streaming strategy is developed. It takes advantages of provider set arrangement and transmission scheduling to reduce the impact of network instability on video services. Simulation results verify the effectiveness of the proposed mechanism and strategy.

Electronic learning (e-learning) has become one of the widely used modes of pedagogy in higher education today due to the convenience and flexibility offered in comparison to traditional learning activities. Advancements in Information and Communication Technology have eased learner connectivity online and enabled access to an extensive range of learning materials on the World Wide Web. Post covid-19 pandemic, online learning has become the most essential and inevitable medium of learning in primary, secondary and higher education. In recent times, Massive Open Online Courses (MOOCs) have transformed the current education strategy by offering a technology-rich and flexible form of online learning. A key component to assess the learner’s progress and effectiveness of online teaching is the Multiple Choice Question (MCQ) assessment in most of the MOOC courses. Uncertainty exists on the reliability and validity of the assessment component as it raises a qualm whether the real knowledge acquisition level reflects upon the assessment score. This is due to the possibility of random and smart guesses, learners can attempt, as MCQ assessments are more vulnerable than essay type assessments. This paper presents the architecture, development, evaluation of the I-Quiz system, an intelligent assessment tool, which captures and analyses both the implicit and explicit non-verbal behaviour of learner and provides insights about the learner’s real knowledge acquisition level. The I-Quiz system uses an innovative way to analyse the learner non-verbal behaviour and trains the agent using machine learning techniques. The intelligent agent in the system evaluates and predicts the real knowledge acquisition level of learners. A total of 500 undergraduate engineering students were asked to attend an on-Screen MCQ assessment test using the I-Quiz system comprising 20 multiple choice questions related to advanced C programming. The non-verbal behaviour of the learner is recorded using a front-facing camera during the entire assessment period. The resultant dataset of non-verbal behaviour and question-answer scores is used to train the random forest classifier model to predict the real knowledge acquisition level of the learner. The trained model after hyperparameter tuning and cross validation achieved a normalized prediction accuracy of 85.68%. © 2021 CRL Publishing. All rights reserved.

It is generally conceded that, due to security and privacy concerns, enterprises and users are reluctant to embrace the cloud computing paradigm and hence benefit from the cost reductions and the increased flexibility or business agility that this paradigm brings about. These concerns stem mainly from the significantly-expanded attack surfaces that result from the heterogeneous nature of cloud services and the dynamicity inherent in cloud environments. In order to alleviate these concerns, effective and flexible access control approaches are required to consider the contextual parameters that characterise data access requests in the cloud. In this respect, this work presents PaaSword: a novel holistic access control framework-essentially a PaaS offering-that extends the popular XACML standard with semantic reasoning capabilities that support the federation of effective context-aware access control policies and their infusion into cloud applications with minimal manual intervention and effort. To determine the performance of our solution, a comparative evaluation test is presented and discussed, against a well-known reference implementation of the XACML standard, namely the open source WSO2 Balana engine.

This paper presents the concept of a new hybrid model called spherical fuzzy N-soft expert sets, which is an extension of spherical fuzzy soft expert sets. The proposed model is highly suitable to describe the multinary data evaluation in terms of spherical fuzzy soft information considering multiple experts’ opinions. Some fundamental properties, including subset, weak complement, spherical fuzzy complement, spherical fuzzy weak complement, union, intersection, AND operation, and OR operation, are discussed. Our proposed concepts are explained with detailed examples. An efficient algorithm is developed to solve multi-attribute group decision-making (MAGDM) problems. Further, to guarantee the high applicability scope and flexibility of our initiated framework, two real-world MAGDM problems, that is, predicting local election results using survey ratings before the election and ranking credibility of the smartphones using customer feedback, are solved. Finally, to endorse the accuracy and advantages of the proposed technique, a comprehensive comparative analysis of the presented approach with existing models such as spherical fuzzy soft expert sets and N-soft sets is provided.

Regression models are used in a wide range of applications providing a powerful scientific tool for researchers from different fields. Linear, or simple parametric, models are often not sufficient to describe complex relationships between input variables and a response. Such relationships can be better described through flexible approaches such as neural networks, but this results in less interpretable models and potential overfitting. Alternatively, specific parametric nonlinear functions can be used, but the specification of such functions is in general complicated. In this paper, we introduce a flexible approach for the construction and selection of highly flexible nonlinear parametric regression models. Nonlinear features are generated hierarchically, similarly to deep learning, but have additional flexibility on the possible types of features to be considered. This flexibility, combined with variable selection, allows us to find a small set of important features and thereby more interpretable models. Within the space of possible functions, a Bayesian approach, introducing priors for functions based on their complexity, is considered. A genetically modified mode jumping Markov chain Monte Carlo algorithm is adopted to perform Bayesian inference and estimate posterior probabilities for model averaging. In various applications, we illustrate how our approach is used to obtain meaningful nonlinear models. Additionally, we compare its predictive performance with several machine learning algorithms., 42 pages; 18 Tables. arXiv admin note: text overlap with arXiv:1806.02160

As a valuable tool for representing uncertain information, probabilistic hesitant fuzzy sets (PHFS) have gained considerable recognition and in-depth discussion in recent years to increase the flexibility and manifest hesitant information in decision-making problems. However, decision-makers (DMs) cannot express all preferences only through a few probabilistic terms in actual decision-making. Much critical information is hidden behind the original information provided by the DMs. Keeping that in mind, we are interested in mining deeper uncertain information from the original probabilistic hesitant fuzzy evaluation data. To achieve the target, we put forward a novel representation tool called the normal wiggly probabilistic hesitant fuzzy set (NWPHFS) to extract deeper uncertain preferences from original probabilistic information. NWPHFS retains the original evaluation information and carries and assesses the potential uncertain details for increasing the rationality of decision-making outcomes. Herein, we propose some fundamental concepts of NWPHFS, for instance, some elementary operational laws, distance measures between two NWPHFSs, and score function. We also suggest two new aggregation operators, that is, the normal wiggly probabilistic hesitant fuzzy weighted averaging (NWPHFWA) and normal wiggly probabilistic hesitant fuzzy weighted geometric (NWPHFWG). A novel mechanism is proposed here to work out multiattribute decision-making (MADM) in solving normal wiggly probabilistic decision-making problems. Through a practical example of environmental quality assessment, the specific calculation steps of this method are epitomized. Finally, we have demonstrated the feasibility and advancement of the proposed approach via a comprehensive comparative study.

Defining and quantifying complexity is one of the major challenges of modern science and contemporary societies. This task is particularly critical for model selection, which is aimed at properly identifying the most adequate equations to interpret the available data. The traditional solution of equating the complexity of the models to the number of their parameters is clearly unsatisfactory. Three alternative approaches are proposed in this work. The first one estimates the flexibility of the proposed models to quantify their potential to overfit. The second interprets complexity as lack of stability and is implemented by computing the variations in the predictions due to uncertainties in their parameters. The third alternative is focused on assessing the consistency of extrapolation of the candidate models. All the upgrades are easy to implement and typically outperform the traditional versions of model selection criteria and constitute a good set of alternatives to be deployed, depending on the priorities of the investigators and the characteristics of the application.

AI-driven edge computing is a development trend of the Industrial Internet of Things (IIoT). However, most existing solutions ignore the limitations of flexibility, security, and real-time performance caused by the rigid architecture of industrial control systems and the “end-to-end” computing paradigm of IIoT. This paper proposes an edge computing scheme for AI-driven IIoT. Specifically, we design a novel software-defined industry control architecture to enhance the flexibility and security of IIoT edge systems. The architecture decouples the software and hardware of Industrial devices by virtualization and industrial modeling technologies, which improves the flexibility and programmability of IIoT edge systems and alleviates the privacy issue of industrial data. Moreover, we adopt a new edge computing method, dispersed computing, to AI-driven IIoT to achieves better real-time performance and resource utilization. The proposed computing method optimizes the computing and networking of AI-driven industrial applications jointly by a multiobjective optimization scheduling algorithm. We also evaluated the performance of our scheme through experiments.

With the rapid development of cloud computing, more and more enterprises would like to upload and store their data in the public cloud. When the parts of the business of an enterprise are purchased by another enterprise, the corresponding data will be transferred to the acquiring enterprise. For the usual case, how to outsource the computation cost of data transfer to the cloud How to ensure the remote purchased data integrity Thus, it is important to study provable data possession with outsourced data transfer (DT-PDP). In this paper, for the first time, we propose the novel concept: DT-PDP. By taking use of DT-PDP, the following three security requirements can be satisfied: (1) the other un-purchased data security of acquired enterprise can be ensured; (2) the purchased data integrity and privacy can be ensured; (3) the data transferability's computation can be outsourced to the public cloud servers. For the security concept of DT-PDP, we give its motivation, system model and security model. Then, we design a concrete DT-PDP scheme based on the bilinear pairings. At last, we analyze the security, efficiency and flexibility of the concrete DT-PDP scheme. It shows that our scheme is provably secure and efficient.

Summary In recent years, researchers have identified certain RNAs as druggable targets for small molecules to treat several human pathologies. However, these regulatory RNAs are challenging targets due to their intrinsic structural flexibility and poorly characterized structure-function relationships. Standard drug-discovery approaches have therefore been adjusted to identify and optimize RNA-targeted small molecules. In this context, our review first outlines the regulatory RNAs that have been structurally and functionally characterized and identified as druggable targets for small molecules. Using representative case studies, we then critically examine the power and challenges of molecular modeling, docking, and simulations and the synergistic interconnection of computational tools with experimental methods for RNA-targeted structure-based drug design.

Although the concepts of nonuniform sampling (NUS​​​​​​​) and non-Fourier spectral reconstruction in multidimensional NMR began to emerge 4 decades ago (Bodenhausen and Ernst, 1981; Barna and Laue, 1987), it is only relatively recently that NUS has become more commonplace. Advantages of NUS include the ability to tailor experiments to reduce data collection time and to improve spectral quality, whether through detection of closely spaced peaks (i.e., “resolution”) or peaks of weak intensity (i.e., “sensitivity”). Wider adoption of these methods is the result of improvements in computational performance, a growing abundance and flexibility of software, support from NMR spectrometer vendors, and the increased data sampling demands imposed by higher magnetic fields. However, the identification of best practices still remains a significant and unmet challenge. Unlike the discrete Fourier transform, non-Fourier methods used to reconstruct spectra from NUS data are nonlinear, depend on the complexity and nature of the signals, and lack quantitative or formal theory describing their performance. Seemingly subtle algorithmic differences may lead to significant variabilities in spectral qualities and artifacts. A community-based critical assessment of NUS challenge problems has been initiated, called the “Nonuniform Sampling Contest” (NUScon), with the objective of determining best practices for processing and analyzing NUS experiments. We address this objective by constructing challenges from NMR experiments that we inject with synthetic signals, and we process these challenges using workflows submitted by the community. In the initial rounds of NUScon our aim is to establish objective criteria for evaluating the quality of spectral reconstructions. We present here a software package for performing the quantitative analyses, and we present the results from the first two rounds of NUScon. We discuss the challenges that remain and present a roadmap for continued community-driven development with the ultimate aim of providing best practices in this rapidly evolving field. The NUScon software package and all data from evaluating the challenge problems are hosted on the NMRbox platform.

Summary Metal halide perovskites (MHPs) have catapulted to the forefront of energy research due to the unique combination of high device performance, low materials cost, and facile solution processability. A remarkable merit of these materials is their compositional flexibility allowing for multiple substitutions at all crystallographic sites, and hence thousands of possible pure compounds and virtually a near-infinite number of multicomponent solid solutions. Harnessing the full potential of MHPs necessitates rapid exploration of multidimensional chemical space toward desired functionalities. Recent advances in laboratory automation, ranging from bespoke fully automated robotic labs to microfluidic systems and to pipetting robots, have enabled high-throughput experimental workflows for synthesizing MHPs. Here, we provide an overview of the state of the art in the automated MHP synthesis and existing methods for navigating multicomponent compositional space. We highlight the limitations and pitfalls of the existing strategies and formulate the requirements for necessary machine learning tools including causal and Bayesian methods, as well as strategies based on co-navigation of theoritical and experimental spaces. We argue that ultimately the goal of automated experiments is to simultaneously optimize the materials synthesis and refine the theoretical models that underpin target functionalities. Furthermore, the near-term development of automated experimentation will not lead to the full exclusion of human operator but rather automatization of repetitive operations, deferring human role to high-level slow decisions. We also discuss the emerging opportunities leveraging machine learning-guided automated synthesis to the development of high-performance perovskite optoelectronics.

The auto industry is critically dependent on lean and flexible manufacturing systems to sustain in today’s dynamic and price sensitive markets. In the current work, a machine learning-based predictive modeling and control strategy is proposed for the attainment of lean manufacturing (LM) through effective management of manufacturing flexibility. Firstly, lean manufacturing models were identified based on machine, labour, volume, routing, product flexibilities and material handling for forty six auto parts manufacturing companies in Pune region (India). As many as twenty three lean manufacturing models were derived based on system identification (control theory) structures: auto regressive with exogenous variables (ARX), auto regressive moving average with exogenous variables (ARMAX), output error (OE) and Box Jenkins (BJ) methods. All predictive models were compared for their relative performances based on validation indices such as the FIT%, mean squared error (MSE), final prediction error (FPE) and the number of model parameters. The ARX 750 structure attained the best predictive characteristics for LM (FIT 91.86%). This model was controlled for a set point of 0.8 LM level and corresponding levels of flexibilities were determined. The machine flexibility (MF) was identified to be the most significant contributor to lean manufacturing at a level of 0.7596. Consequently, MF was also modeled based on its seven sub parameters. The ARMAX 2120 structure obtained the best performance characteristics (FIT 99.94%) for MF modeling. Furthermore, this MF model was controlled at a level of 0.7596 (corresponding to 0.8 LM) and the required levels of MF sub parameters were determined. Thus, the current work provides definite guidelines for company managers to target quantitative attainment of specific machine flexibility parameters to ultimately attain an improved lean manufacturing level in the automotive industry.

In industrial production, smart wearables (e.g. data glasses) are becoming more relevant to support employees. While economic aspects have so far been the focus of the introduction, changes for work design have been neglected. The aim of the Delphi study was to describe changes through the use of smart wearables and to derive implications for work design. Six description dimensions (application, implications for work design, data use, personalization, flexibility, introductory purpose) were identified and 18 scenarios were developed. The assessment of the scenarios in terms of desirability and degree of dissemination showed that scenarios for work-related and ergonomic support are particularly desirable and scenarios for changes in cooperation are considered particularly likely. Data usage is a relevant factor for the assumed degree of dissemination but not for the assessment of desirability. In operational practice, work design and economic aspects are important for assessing the scenarios.Practical Relevance: The results show possible development scenarios for production work when using smart wearables and highlight possible implications for work design. Positive and negative effects on task, knowledge, social and contextual characteristics are identified, which offer suggestions for a conscious selection and design of the use of technology in practice.

Information flow control (IFC) can effectively resist Trojans and viruses that steal information from systems, and is usually adopted to protect the confidentiality of systems with a high security level. However, covert channel attacks can bypass IFC by exploiting its implementation defects. Thus, it is crucial to verify the system security and identify potential covert channels. Decentralized IFC (DIFC) is a key innovation that provides new flexible mechanisms, including decentralized declassification and taint tracking. However, the flexibility of DIFC systems also brings security risks. At present, there is a lack of a systematic and automatic security analysis approach for complex DIFC systems. In this paper, we propose a formal and automatic method to analyze the security of DIFC systems by using the FDR2 tool. We provide a new definition of noninterference, based on which the security analysis is performed. The analysis results indicate that our approach can both effectively detect covert channels in DIFC systems and accommodate conditional declassification information. The proposed method is more efficient and accurate than existing manual methods of covert channel detection.

Connected electric vehicles (CEVs) can help cities to reduce road congestion and increase road safety. With the technical improvement made to the battery system in terms of capacity and flexibility, CEVs, as mobile power plants can be an important actor for the electricity markets. Especially, they can trade electricity between each other when supply stations are full or temporarily not available. In this article, we propose an advanced decentralized electricity trading framework between CEVs in parking lots based on consortium blockchain, machine learning, and Game theoretic model. We design a distributed smart contract solution based on a stochastic bidding process, which helps CEVs to sell and buy electricity with their maximum profitability. Finally, numerical simulations with MATLAB and Solidity are conducted to prove the effectiveness of our proposed solution. Also, a comparison with another method in terms of CEVs’ profitability improvement and energy trading management is provided.

This paper aims to evaluate the factors affecting mobile applications used to access and control security cameras at home and office. Survey data from 397 mobile applications users in Southern California, USA were collected to test the proposed research model and hypotheses through structural equation modeling. This study finds that system quality, information quality, and service quality of mobile applications have a positive effect on the perceived usefulness and perceived ease of use of these applications and introduce several net benefit represented in increased control of users' security, increased convenience and flexibility and privacy when using those mobile applications for access their security cameras at both home and office. There is a lack of researches in this area which makes this study among the first to attempts to fill this gap by empirically investigating the factors affecting mobile applications of home and office security cameras as well as the benefits they introduce to uses.

BackgroundDifferential correlation networks are increasingly used to delineate changes in interactions among biomolecules. They characterize differences between omics networks under two different conditions, and can be used to delineate mechanisms of disease initiation and progression.ResultsWe present a new R package, , that facilitates the estimation and visualization of differential correlation networks using multiple correlation measures and inference methods. The software is implemented in , and , and is available athttps://github.com/sqyu/CorDiffViz. Visualization has been tested for the Chrome and Firefox web browsers. A demo is available athttps://diffcornet.github.io/CorDiffViz/demo.html.ConclusionsOur software offers considerable flexibility by allowing the user to interact with the visualization and choose from different estimation methods and visualizations. It also allows the user to easily toggle between correlation networks for samples under one condition and differential correlations between samples under two conditions. Moreover, the software facilitates integrative analysis of cross-correlation networks between two omics data sets.

Heterogeneous Information Network (HIN) is a natural and general representation of data in recommender systems. Combining HIN and recommender systems can not only help model user behaviors but also make the recommendation results explainable by aligning the users/items with various types of entities in the network. Over the past few years, path-based reasoning models have shown great capacity in HIN-based recommendation. The basic idea of these models is to explore HIN with predefined path schemes. Despite their effectiveness, these models are often confronted with the following limitations: (1) Most prior path-based reasoning models only consider the influence of the predecessors on the subsequent nodes when modeling the sequences, and ignore the reciprocity between the nodes in a path; (2) The weights of nodes in the same path instance are usually assumed to be constant, whereas varied weights of nodes can bring more flexibility and lead to expressive modeling; (3) User-item interactions are noisy, but they are often indiscriminately exploited. To overcome the aforementioned issues, in this paper, we propose a novel path-based reasoning approach for recommendation over HIN. Concretely, we use a bidirectional LSTM to enable the two-way modeling of paths and capture the reciprocity between nodes. Then an attention mechanism is employed to learn the dynamical influence of nodes in different contexts. Finally, the adversarial regularization terms are imposed on the loss function of the model to mitigate the effects of noise and enhance HIN-based recommendation. Extensive experiments conducted on three public datasets show that our model outperforms the state-of-the-art baselines. The case study further demonstrates the feasibility of our model on the explainable recommendation task., 11 pages, 5 figures, Neurocomputing

Recently, Self-Attention Networks (SANs) have shown its flexibility in parallel computation and effectiveness of modeling both short- and long-term dependencies. However, SANs face two problems: 1) the weighted averaging inhibits relations among neighboring words (i.e., local context); and 2) it calculates dependencies between representations without considering contextual information (i.e., global context). Both local and global contexts have proven useful for modeling dependencies among neural representations in a variety of natural language processing tasks. Accordingly, we augment SANs with the ability of capturing usefully local and global context, and meanwhile maintain their simplicity and flexibility. Firstly, we cast local context modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised version. Secondly, we leverage the internal representations that embed sentence-level information as the global context. Specifically, we propose to contextualize the transformations of query and key layers, which are used to calculate the relevance between elements. Since the two approaches are potentially complementary to each other, we propose to combine them to further improve the performance. Empirical results on machine translation and linguistics probing tasks demonstrate the effectiveness and universality of the proposed approaches. Further analyses confirm that our approaches successfully capture contextual information as expected.

Structure-based drug design depends on the detailed knowledge of the three-dimensional (3D) structures of protein–ligand binding complexes, but accurate prediction of ligand-binding poses is still a major challenge for molecular docking due to deficiency of scoring functions (SFs) and ignorance of protein flexibility upon ligand binding. In this study, based on a cross-docking dataset dedicatedly constructed from the PDBbind database, we developed several XGBoost-trained classifiers to discriminate the near-native binding poses from decoys, and systematically assessed their performance with/without the involvement of the cross-docked poses in the training/test sets. The calculation results illustrate that using Extended Connectivity Interaction Features (ECIF), Vina energy terms and docking pose ranks as the features can achieve the best performance, according to the validation through the random splitting or refined-core splitting and the testing on the re-docked or cross-docked poses. Besides, it is found that, despite the significant decrease of the performance for the threefold clustered cross-validation, the inclusion of the Vina energy terms can effectively ensure the lower limit of the performance of the models and thus improve their generalization capability. Furthermore, our calculation results also highlight the importance of the incorporation of the cross-docked poses into the training of the SFs with wide application domain and high robustness for binding pose prediction. The source code and the newly-developed cross-docking datasets can be freely available at https://github.com/sc8668/ml_pose_prediction and https://zenodo.org/record/5525936, respectively, under an open-source license. We believe that our study may provide valuable guidance for the development and assessment of new machine learning-based SFs (MLSFs) for the predictions of protein–ligand binding poses.