Search

Background Objective Methods Results Conclusion Peripheral blood‐derived hematopoietic stem cells (HSCs) are widely used for various adult stem cell transplants. To obtain sufficient HSCs from healthy volunteer donors during the apheresis process and ensure that the donors are exposed to fewer apheresis‐related side effects, calculation methods have been developed for the prediction of processed blood volume or CD34+ count. However, there is no consensus on a formula to predict the volume of blood to be processed or the number of stem cells to be obtained.This study aimed to estimate the predicted blood volume and CD34+ cell counts using collection efficiency (CE)‐based formulas and evaluate their accuracy compared to the actual CD34+ cell counts. It also seeks to identify the factors that affect CE.Data from 397 healthy, unrelated stem cell donors were retrospectively analyzed. An algorithm using four different CE2 metrics (1st quartile, mean, 3rd quartile, and median) was developed to predict the volume of blood to be processed using the Spectra Optia continuous mononuclear cell collection procedure.When employing the mean CE2 algorithm, the results revealed a strong correlation (r = .894, p < .001) between predicted and actual CD34+ values. The study also identified strong associations between pre‐apheresis CD34+, pre‐apheresis leukocyte count, the use of two doses of G‐CSF, and low CE2.These findings suggest that the mean CE2 algorithm could be a potent, straightforward, and accurate tool for predicting CD34+ stem cell counts in healthy allogeneic stem cell donors and potentially optimizing stem cell collection procedures. [ABSTRACT FROM AUTHOR]

Recent advances in AI-based learning models have significantly increased the accuracy of Automatic Personality Recognition (APR). However, these methods either require training data from the same subject or the meta-information from the training set to learn the personality-related features (i.e., subject-dependency). The variance of feature extraction for different subjects compromises the possibility of designing a dependency-free system for APR. To address this problem, we present an unsupervised multimodal learning framework to infer personality traits from audio, visual, and verbal modalities. Our method both extracts the handcraft features and transfers deep-learning based embeddings from other tasks (e.g., emotion recognition) to recognize personality traits. Since these representations are extracted locally in the time domain, we present an unsupervised temporal aggregation method to aggregate the extracted features over the temporal dimension. We evaluate our method on the ChaLearn dataset, the most widely referenced dataset for APR, using a dependency-free split of the dataset. Our results show that the proposed feature extraction and temporal aggregation modules do not require personality annotations in training but still outperform other state-of-the-art baseline methods. We also address the problem of subject-dependency in the original split of the ChaLearn dataset. The newly proposed split (i.e., data for training, validation, and testing) of the dataset can benefit the community by providing a more accurate method to validate the subject-generalizability of APR algorithms. [ABSTRACT FROM AUTHOR]

Road accidents are on the rise worldwide, causing 1.35 million deaths per year, thus encouraging the search for solutions. The promising proposal of autonomous vehicles stands out in this regard, although fully automated driving is still far from being an achievable reality. Therefore, efforts have focused on predicting and explaining the risk of accidents using real-time telematics data. This study aims to analyze the factors, machine learning algorithms, and explainability methods most used to assess the risk of vehicle accidents based on driving behavior. A systematic review of the literature produced between 2013 and July 2023 on factors, prediction algorithms, and explainability methods to predict the risk of traffic accidents was carried out. Factors were categorized into five domains, and the most commonly used predictive algorithms and explainability methods were determined. We selected 80 articles from journals indexed in the Web of Science and Scopus databases, identifying 115 factors within the domains of environment, traffic, vehicle, driver, and management, with speed and acceleration being the most extensively examined. Regarding machine learning advancements in accident risk prediction, we identified 22 base algorithms, with convolutional neural network and gradient boosting being the most commonly used. For explainability, we discovered six methods, with random forest being the predominant choice, particularly for feature importance analysis. This study categorizes the factors affecting road accident risk, presents key prediction algorithms, and outlines methods to explain the risk assessment based on driving behavior, taking vehicle weight into consideration. [ABSTRACT FROM AUTHOR]

Research in agriculture is a promising field, and crop prediction for particular land areas is especially critical to agriculture. Such prediction depends on the soil, minerals, and environment, the last of which has been short-changed by changing climatic conditions. Consequently, crop prediction for a particular zone presents difficulties for farmers. This is where machine learning (ML) steps in with techniques that are widely applied in agriculture. This work proposes a weighted stacked ensemble (WSE) method for the crop prediction process. It combines two base learners or classifiers to construct the WSE, which is a single predictive ensemble model, using weighted instances. The experimental outcomes show that the proposed WSE outperforms other classification and ensemble techniques in terms of improved crop prediction accuracy. [ABSTRACT FROM AUTHOR]

Background: There exist few maximal oxygen uptake (VO2max) non-exercise-based prediction equations, fewer using machine learning (ML), and none specifically for older adults. Since direct measurement of VO2max is infeasible in large epidemiologic cohort studies, we sought to develop, validate, compare, and assess the transportability of several ML VO2max prediction algorithms. Methods: The Baltimore Longitudinal Study of Aging (BLSA) participants with valid VO2max tests were included (n = 1080). Least absolute shrinkage and selection operator, linear- and tree-boosted extreme gradient boosting, random forest, and support vector machine (SVM) algorithms were trained to predict VO2max values. We developed these algorithms for: (a) the overall BLSA, (b) by sex, (c) using all BLSA variables, and (d) variables common in aging cohorts. Finally, we quantified the associations between measured and predicted VO2max and mortality. Results: The age was 69.0 ± 10.4 years (mean ± SD) and the measured VO2max was 21.6 ± 5.9 mL/kg/min. Least absolute shrinkage and selection operator, linear- and tree-boosted extreme gradient boosting, random forest, and support vector machine yielded root mean squared errors of 3.4 mL/kg/min, 3.6 mL/kg/min, 3.4 mL/kg/min, 3.6 mL/kg/min, and 3.5 mL/kg/min, respectively. Incremental quartiles of measured VO2max showed an inverse gradient in mortality risk. Predicted VO2max variables yielded similar effect estimates but were not robust to adjustment. Conclusion: Measured VO2max is a strong predictor of mortality. Using ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to adjustment. Future studies should seek to reproduce these results so that VO2max, an important vital sign, can be more broadly studied as a modifiable target for promoting functional resiliency and healthy aging.

Precision medicine has the ambition to improve treatment response and clinical outcomes through patient stratification and holds great potential for the treatment of mental disorders. However, several important factors are needed to transform current practice into a precision psychiatry framework. Most important are 1) the generation of accessible large real-world training and test data including genomic data integrated from multiple sources, 2) the development and validation of advanced analytical tools for stratification and prediction, and 3) the development of clinically useful management platforms for patient monitoring that can be integrated into health care systems in real-life settings. This narrative review summarizes strategies for obtaining the key elements—well-powered samples from large biobanks integrated with electronic health records and health registry data using novel artificial intelligence algorithms—to predict outcomes in severe mental disorders and translate these models into clinical management and treatment approaches. Key elements are massive mental health data and novel artificial intelligence algorithms. For the clinical translation of these strategies, we discuss a precision medicine platform for improved management of mental disorders. We use cases to illustrate how precision medicine interventions could be brought into psychiatry to improve the clinical outcomes of mental disorders. [ABSTRACT FROM AUTHOR]

Post-silicon validation is one of the most critical processes in modern semiconductor manufacturing. Specifically, correct and deep understanding in test cases of manufactured devices is key to enable post-silicon tuning and debugging. This analysis is typically performed by experienced human experts. However, with the fast development in semiconductor industry, test cases can contain hundreds of variables. The resulting high-dimensionality poses enormous challenges to experts. Thereby, some recent prior works have introduced data-driven variable selection algorithms to tackle these problems and achieved notable success. Nevertheless, for these methods, experts are not involved in training and inference phases, which may lead to bias and inaccuracy due to the lack of prior knowledge. Hence, this letter for the first time aims to design a novel conditional variable selection approach while keeping experts in the loop. In this way, we expect that our algorithm can be more efficiently and effectively trained to identify the most critical variables under certain expert knowledge. Extensive experiments on both synthetic and real-world datasets from industry have been conducted and shown the effectiveness of our method. [ABSTRACT FROM AUTHOR]

In intelligent transportation systems, one key challenge for managing ride-hailing services is the balancing of traffic supply and demand while meeting passenger needs within vehicle availability constraints. Accurate origin–destination (OD) demand predictions can empower platforms to execute timely reallocation of cruising vehicles and improve ride-sharing services. Nonetheless, the complexity of OD-based demand prediction arises from intricate spatiotemporal dependencies and a higher need for precision compared to zone-based predictions, which leads to many unprecedented OD pairs. To tackle this issue, we design a comprehensive set of 102 features, including travel demand, passenger count, travel volume, liveliness, weather, and cross features. We also introduce an enhanced conformer model, which is composed of a single conformer block that integrates feedforward layers, multihead self-attention mechanisms, and depth-wise separable convolution layers. To address the cold-start problem and manage large values, we design a specific algorithm for OD pairs lacking training data and apply a technique to handle larger values. Our approach demonstrates a marked improvement in prediction performance, with an 18% decrease in the total travel demand error and up to a 47% reduction for certain larger values in some cases. Through extensive experiments on a dataset collected from a city, provided by a ride-hailing platform, our proposed methods significantly outperform the most advanced models. [ABSTRACT FROM AUTHOR]

Most SNPs associated with complex diseases seem to lie in non-coding regions of the genome; however, their contribution to gene expression and disease phenotype remains poorly understood. Here, we established a workflow to provide assistance in prioritising the functional relevance of non-coding SNPs of candidate genes as susceptibility loci in polygenic neurological disorders. To illustrate the applicability of our workflow, we considered the multifactorial disorder migraine as a model to follow our step-by-step approach. We annotated the overlap of selected SNPs with regulatory elements and assessed their potential impact on gene expression based on publicly available prediction algorithms and functional genomics information. Some migraine risk loci have been hypothesised to reside in non-coding regions and to be implicated in the neurotransmission pathway. In this study, we used a set of 22 non-coding SNPs from neurotransmission and synaptic machinery-related genes previously suggested to be involved in migraine susceptibility based on our candidate gene association studies. After prioritising these SNPs, we focused on non-reported ones that demonstrated high regulatory potential: (1) VAMP2 _rs1150 (3′ UTR) was predicted as a target of hsa-mir-5010-3p miRNA, possibly disrupting its own gene expression; (2) STX1A _rs6951030 (proximal enhancer) may affect the binding affinity of zinc-finger transcription factors (namely ZNF423) and disturb TBL2 gene expression; and (3) SNAP25 _rs2327264 (distal enhancer) expected to be in a binding site of ONECUT2 transcription factor. This study demonstrated the applicability of our practical workflow to facilitate the prioritisation of potentially relevant non-coding SNPs and predict their functional impact in multifactorial neurological diseases. [ABSTRACT FROM AUTHOR]

Direct Laser Interference Patterning (DLIP) is a versatile tool used to produce microstructures for functionalized surfaces on different materials. However, monitoring strategies are needed to ensure repeatability and quality control during the fabrication of surface patterns with micro- and submicron resolution features. This study proposes a new approach for identifying the spatial period on the surface using airborne acoustic emission during DLIP. The acoustic emission parameters from a single laser pulse on the material are analyzed using different prediction algorithms to classify and compare different spatial periods. Line-like patterns were produced on aluminum substrates using a pulsed laser source, and the laser fluence was varied to obtain variation in the data set. The preliminary results show that the four algorithms can detect and identify the spatial period for different laser fluences with an accuracy of up to 96%. This approach could be used for an automated setup workflow and eliminates the need for manual measurement of this parameter. It is an important step towards a fully automated initialization of surface processing in the micrometer range. [ABSTRACT FROM AUTHOR]

Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations. Specifically, we first learn spatial co-occurrence and temporal transition correlations in a statistical manner. Then, we design spatial and temporal knowledge-embedded layers that introduce the multi-head cross-attention mechanism to fully explore the interaction between visual representation and the knowledge to generate spatial- and temporal-embedded representations, respectively. Finally, we aggregate these representations for each subject-object pair to predict the final semantic labels and their relationships. Extensive experiments show that STKET outperforms current competing algorithms by a large margin, e.g., improving the mR@50 by 8.1%, 4.7%, and 2.1% on different settings over current algorithms. [ABSTRACT FROM AUTHOR]

This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently propagated through the whole network until reaching the output layer. The sign of each composition value indicates whether the corresponding feature excites or inhibits the neuron, while the absolute value quantifies its impact. The FCP algorithm is executed on a post-hoc basis, i.e., once the learning process is completed. Aiming to illustrate the FCP algorithm, this paper develops a case study concerning bias detection in a fairness problem in which the ground truth is known. The simulation results show that the composition values closely align with the expected behavior of protected features. The source code and supplementary material for this paper are available at https://github.com/igraugar/fcp. [ABSTRACT FROM AUTHOR]

The article examines the prospects for using an automation system to search for parking spaces. This system is aimed at solving the problems that drivers face when searching for available parking spaces, especially in crowded urban areas near residential buildings or shopping centers. A comprehensive literature review and problem analysis revealed existing shortcomings associated with traditional parking search methods: their localized scale and fragmented nature. The article continues the analysis of existing solutions, exploring such well-known mobile applications as ParkMobile and SpotHero, sensor-based and IoT systems, as well as integrated parking technologies. It also provides a comprehensive overview of the technologies on which this type of system is based - GPS, real-time data analysis and sensor networks to simplify parking. The research and analysis identified the innovative potential of automation systems to improve parking management in urban areas. The ability of technology to optimize the use of parking spaces and the entire parking process in general, as well as increase overall urban mobility. The proposed automation system, as an alternative option for searching for parking spaces, has shown high accuracy in predicting the availability of free spaces, providing drivers with real-time information for making informed decisions. A preliminary assessment of the system's operation was carried out based on user feedback and showed good results and further ways to improve the proposed solution. In addition, the system's integration capabilities and user-friendly interface ensure hassle-free and convenient parking in crowded residential areas of the city. Ref. 6, pic. 4, tabl. 3

Once a freight train is delayed on a busy railway under a quasi-moving-block signaling system, the speed of its following trains may fluctuate, without proper adjustment. Updating the reference speed profile of the delayed freight train is an urgent task to improve the train operation performance and rail utilization ratio. To this end, this article proposes a speed profile optimization method for following delayed trains that is based on the idea of model predictive control (MPC). The state change time of the block section ahead is predicted for each following train according to the speed profile of its preceding train, based on which the distance between the following train and each speed protection curve (DTC) is predicted. The DTC is taken as a key optimization index for the speed profile optimization, and the other optimization indices are train delay and energy consumption. A two-step hierarchical optimization algorithm is proposed in this article. In the upper level, each prediction step is defined as the traveling time of the preceding train in each block section ahead, and the train target cruising speed sequence is calculated, with the dimension decided by the prediction horizon, using particle swarm optimization. In the lower level, the optimal speed profile is calculated based on the rolling optimization algorithm of the train speed curve in the prediction horizon. The proposed algorithm repeats the optimization process with updated train information after each control horizon. Three simulations are presented, which consider a downhill scenario, steep uphill scenario, and temporary speed limit, respectively. Then, the MPC parameters are analyzed and the optimized speed profiles are compared with the other algorithm. [ABSTRACT FROM AUTHOR]

Recently, smart cities have emerged as one of the most important global trends initiated by many countries. The rapid development of the Internet of Things (IoT) and 5G connectivity enables numerous smart system technologies. One of the most critical aspects of smart cities is Intelligent Transportation Systems (ITS) which allow for accurate traffic forecasting. Existing traffic forecasting approaches use simple models based on univariate historical datasets or fuse historical traffic data with other datasets, such as air pollution records. These techniques interpreted traffic data points as independent samples despite their time dependency, resulting in poor prediction accuracy. In this paper, we propose an enhanced traffic prediction approach using the sliding window technique. The proposed approach transforms the traffic data points into time-series sequence data using the sliding window technique. Moreover, the proposed approach exploits traffic and pollution datasets for multivariate traffic prediction. The proposed approach compares different machine/deep learning techniques for prediction and evaluates their accuracy compared to a baseline benchmark. The experimental results show that the proposed approach significantly enhances the evaluation metrics values for the tested machine and deep learning techniques by an average value of 36% and 24%, respectively, compared to the base-line benchmark.

Road accidents are on the rise worldwide, causing 1.35 million deaths per year, thus encouraging the search for solutions. The promising proposal of autonomous vehicles stands out in this regard, although fully automated driving is still far from being an achievable reality. Therefore, efforts have focused on predicting and explaining the risk of accidents using real-time telematics data. This study aims to analyze the factors, machine learning algorithms, and explainability methods most used to assess the risk of vehicle accidents based on driving behavior. A systematic review of the literature produced between 2013 and July 2023 on factors, prediction algorithms, and explainability methods to predict the risk of traffic accidents was carried out. Factors were categorized into five domains, and the most commonly used predictive algorithms and explainability methods were determined. We selected 80 articles from journals indexed in the Web of Science and Scopus databases, identifying 115 factors within the domains of environment, traffic, vehicle, driver, and management, with speed and acceleration being the most extensively examined. Regarding machine learning advancements in accident risk prediction, we identified 22 base algorithms, with convolutional neural network and gradient boosting being the most commonly used. For explainability, we discovered six methods, with random forest being the predominant choice, particularly for feature importance analysis. This study categorizes the factors affecting road accident risk, presents key prediction algorithms, and outlines methods to explain the risk assessment based on driving behavior, taking vehicle weight into consideration.

The significant requirement for natural resources, specifically as ingredients of cement, is accelerating due to the considerable growth of the construction sector. Further, cement production adversely affects climate change due to the generation of bulk CO2 emissions. At the same time, a significant quantum of ceramic waste is generated either in the ceramic production process or due to the demolition of ceramic products each year. The unavailability of an adequate way to dispose of this ceramic waste negatively impacts the environment and landfills. Numerous researchers have explored the potential of utilizing this ceramic waste powder as a partial cement replacement to reduce the allied issues. Hence, in the current study, the supervised machine learning (ML) algorithms, i.e., Decision Tree (DT), AdaBoost (AdB), Bagging (Bg), Random Forest (RF), Gradient Boosting (GB) and XGBoost (XGB) are employed for predicting the Compressive Strength (CS) of ceramic waste powder concrete (CWPC). The performance of models is also assessed by using the coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Nash Sutcliffe efficiency (NSE). The k-fold cross-validation technique is applied afterwards to validate the model's performance. For predicting the CS of CWPC, the RF algorithm is the most effective among the employed algorithms, with a higher R2 value of 0.97 and significantly lesser RMSE and MAE values of 1.40 and 1.13, respectively. SHAP analysis shows that the curing days feature has the highest influence on the CS of CWPC. As per quantitative Environmental Impact Assessment (EIA), the concrete with 10% CWP content can have 6.78%, 8.68%, 7.18%, and 7.19% reduced impacts on natural resources, climate change, ecosystem quality, and human health, respectively. Moreover, the effects on non-renewable energy resources, depletion of the ozone layer, and global warming can also primarily be reduced by a maximum of 7%, 6%, and 9%, respectively. The application of ML techniques for estimating the CS of CWPC would benefit the field of civil engineering in terms of conserving resources, effort, and time.

Parkinson's disease (PD) is progressive and heterogeneous. Levodopa is widely prescribed to control PD, and its long‐term‐treatment leads to dyskinesia in a dose‐dependent manner. Interpretation of clinical trials comparing different drug treatments for PD is complicated by different dose intensities employed: higher doses of levodopa produce better symptomatic control but more late complications. Thus, the dose must be recalibrated and reduced gradually. Since recommendations for gradually reducing Levodopa are currently lacking and estimation of Levodopa amount can help doctor to correctly prescribe drug amount, this study aims to predict Levodopa amount and incremental doses using Hybrid Machine Learning Systems (HMLS) and a mixture of radiomics and clinical features. We selected 264 patients from PPMI and obtained 950 features including imaging and nominating features. We generated seven datasets constructed from the dataset in years 0 and 1, which linked with outcomes, (O1) patients being on/off drug in year 1, (O2) dose amount in year 1, and (O3‐8) incremental dose from 1st to 2nd, 2nd to 3rd, 3rd to 4th, 4th to 5th, 1st to 4th, 1st to 5th year. HMLSs included 10 feature extraction/9 feature selection algorithms followed by 10 prediction algorithms. To predict O1, timeless dataset + Random Forest + ReliefA had the highest accuracy~88.5% ± 2.2%, and external testing~91.6%. Furthermore, to predict O2, timeless dataset + Minimum Redundancy Maximum Relevance Algorithm (MRMR) + K Nearest Neighbor Regressor (KNN‐R) achieved a mean absolute error (MAE) ~ 47.5 ± 13.6 ([30.3:850 milligram]) and external testing~31.9. To predict dose increments (O3‐8), HMLSs: Unsupervised Feature Selection with Ordinal Locality + KNNR, ReliefA + KNNR, ReliefA + KNNR, Local Learning‐based Clustering Feature Selection + KNNR, MRMR + KNNR, and MRMR + KNNR applied to timeless datasets resulted in MAEs ~ 0.42 ± 0.18, 0.10 ± 0.09, 0.04 ± 0.01, 0.24 ± 0.15, 0.25 ± 0.05, and 0.33 ± 0.26 ([0.23:29.7]), respectively. Moreover, their external testing confirmed our findings. We demonstrated that timeless datasets including a mixture of clinical and imaging features, linked with appropriate HMLSs, significantly improve prediction performances. [ABSTRACT FROM AUTHOR]

For near-field synthetic aperture interferometric radiometer (SAIR) systems, imaging distance plays an important role in the imaging reconstruction. However, most current SAIR imaging algorithms treat the imaging distance as an exact known value, which may have a serious influence on imaging reconstruction quality caused by the misestimate of the practical imaging distance. In this letter, we propose a distance adaptive near-field SAIR imaging algorithm based on deep learning (DL) approach to handle this problem. The complex correlation operation block (CCOB) is proposed to predict the distance parameter and reconstruct the image first. And the residual attention enhanced module is utilized to further improve the imaging quality. The simulation results indicate that the proposed algorithm can accurately predict the imaging distance and achieve high-precision image reconstruction at different distances. [ABSTRACT FROM AUTHOR]

Seismic analysis and interpretation are sensitive to data resolution. High-density acquisition, deconvolution, and inverse $Q$ filtering are traditional methods for resolution improvement. These methods have drawbacks such as strict assumptions and complex parameter solving processes. In this letter, we propose a channel attention U-Net and physical convolution combination (CAUC) algorithm to overcome these limitations. First, we design a channel attention U-Net (CAU) to establish a sophisticated nonlinear relationship between low-frequency data and coarse reflection coefficients. Specifically, we use a channel attention block after each downsampling convolution block to extract important local features of seismic data. Second, we convolve the coarse reflection coefficients with the wavelets to obtain high-resolution data. This physical convolution operation has a solid theoretical foundation. Therefore, our algorithm benefits not only from the learning ability of the neural network but also from the explainability of the physical operation. Both synthetic and field data are employed to verify the validity of the new algorithm. The traditional fast iterative shrinkage-thresholding algorithm (FISTA) and deep convolutional neural network (CNN) are used for comparison. The results show the superiority of the proposed method, especially in enhancing details such as thin layers and continuity. [ABSTRACT FROM AUTHOR]

In previous research, most multiobject tracking (MOT) algorithms focus on the optical image dataset, while the synthetic aperture radar (SAR) image dataset faces the characteristics of few prior samples, high false alarm rate, and various defocusing interference. On the SAR image dataset, a robust MOT algorithm is proposed to fulfill multi-ship tracking in complex imaging conditions. First, the kernelized correlation filters (KCFs) algorithm, a single-object tracking algorithm, is modified and applied to reduce the impact of false alarms on tracking performance. After that, different matching strategies are adaptively adapted to associate the targets based on the three intersection patterns between the predictions and the detections, which can reduce the impact of the deviated detections. Finally, the tracker’s time limit with Gaussian distribution is proposed to improve the reassociation ability after the tracking interruption caused by the defocusing. The experiment results demonstrate the robust tracking ability of the proposed MOT algorithm. [ABSTRACT FROM AUTHOR]

Depression is one of the most common mental health disorders, and a large number of depressed people commit suicide each year. Potential depression sufferers usually do not consult psychological doctors because they feel ashamed or are unaware of any depression, which may result in severe delay of diagnosis and treatment. In the meantime, evidence shows that social media data provides valuable clues about physical and mental health conditions. In this paper, we argue that it is feasible to identify depression at an early stage by mining online social behaviours. Our approach, which is innovative to the practice of depression detection, does not rely on the extraction of numerous or complicated features to achieve accurate depression detection. Instead, we propose a novel classifier, namely, Cost-sensitive Boosting Pruning Trees (CBPT), which demonstrates a strong classification ability on two publicly accessible Twitter depression detection datasets. To comprehensively evaluate the classification capability of CBPT, we use additional three datasets from the UCI machine learning repository and CBPT obtains appealing classification results against several state of the arts boosting algorithms. Finally, we comprehensively explore the influence factors for the model prediction, and the results manifest that our proposed framework is promising for identifying Twitter users with depression. [ABSTRACT FROM AUTHOR]

Accurate food demand forecasting is one of the critical aspects of successfully managing restaurants, cafeterias, canteens, and refectories. This paper aims to develop demand forecasting models for a university refectory. Our study focused on the development of Machine Learning-based forecasting models which take into account the calendar effect and meal ingredients to predict the heavy demand for food within a limited timeframe (e.g., lunch) and without pre-booking. We have developed eighteen prediction models gathered under five main techniques. Three Artificial Neural Network models (i.e., Feed Forward, Function Fitting, and Cascade Forward), four Gauss Process Regression models (i.e., Rational Quadratic, Squared Exponential, Matern 5/2, and Exponential), six Support Vector Regression models (i.e., Linear, Quadratic, Cubic, Fine Gaussian, Medium Gaussian, and Coarse Gaussian), three Regression Tree models (i.e., Fine, Medium, and Coarse), two Ensemble Decision Tree (EDT) models (i.e., Boosted and Bagged) and one Linear Regression model were applied. When evaluated in terms of method diversity, prediction performance, and application area, to the best of our knowledge, this study offers a different contribution from previous studies. The EDT Boosted model obtained the best prediction performance (i.e., Mean Squared Error = 0,51, Mean Absolute Erro = 0,50, and R = 0,96).

As fake news spreads rapidly in social media, attempts to develop detection technology to automatically identify fake news are actively being developed, recently. However, most of them focus only on the linguistic and compositional characteristics of fake news (e.g., source or authors indication, length of a message, frequency of negative words). Compared to them, this study proposes a fake news detection model based on machine learning that reflects the characteristics of users, news content, and social networks based on social capital. To comprehensively reflect the characteristics related to the spread of fake news, this study applied the XGBoost model to estimate the feature importance of each variable to derive the priority factors that preferentially affect fake news detection. Based on the derived variables, we established SVM, RF, LR, CART, and NNET, which are representative classification models of machine learning, and compared the performance rate of fake news detection. To generalize the established models (i.e., to avoid overfitting or underfitting), this study performed a cross-validation step, and to compare the predictive accuracy of the established models. As a result, the RF model indicated the highest prediction rate at about 94%, while the NNET had the lowest performance rate at about 92.1%. The results of this study are expected to contribute to improve the fake news detection system in preparation for the more sophisticated generation and spread of fake news.

Antimicrobial peptides (AMPs), which are parts of the innate immune response found among all classes of life, are promising in broad-spectrum antibiotics and drug-resistant infection treatments. Although AMPs effectively kill bacteria, numerous AMPs widely distributed in the sequence space remain unknown to humans. Therefore, the de novo design of AMPs involves the exploration of vast sequence space to identify peptides with high antimicrobial activity and good diversity among the known AMPs. Computational intelligence approaches have successfully identified some AMPs; however, most of them fail to address the diversity of the obtained AMPs. This paper reports an evolutionary multi-objective approach for AMP design to optimize both the antimicrobial activity and diversity among identified AMPs. Our approach employs a deep learning model to predict a peptide's antimicrobial activity and a niche sharing method to estimate a peptide's density. Then, an evolutionary multi-objective algorithm is presented to simultaneously optimize the objectives of antimicrobial activity and diversity. The algorithm takes the advantage of a decomposition-based framework to search for AMPs with good diversity. These AMPs are collected by an elite archive during the evolution process. Moreover, a local search strategy is applied to enhance the quality of the identified AMPs. The experimental results show that the proposed approach outperforms the state-of-the-art designs in searching for various AMPs. The AMPs generated by the proposed approach have high antimicrobial activities and are distinct from each other and among the AMPs in the datasets. [ABSTRACT FROM AUTHOR]

A model of a particle flow forming a copy of some image and the distance between the copy and the image are estimated using a special probability metric. The ability of the flow of balls to cover the surface, when grinding the balls, was investigated using formulas of stochastic geometry. Reconstruction of characteristics of an inhomogeneous Poisson flow by inaccurate observations is analysed using the Poisson flow point colouring theorem. The dependence of the Poisson parameter of the distribution of the number of customers in a queuing system with an infinite number of servers and a deterministic service time on the peak load created by an inhomogeneous input Poisson flow is estimated. All these models consist of an inhomogeneous Poisson flow of points and marks glued to each point of the flow and are characterised by their mass, area, volume, observability (or non-observability), and service time. The presence of an asymptotic power–law relationship between model objective functions and parameters of mark crushing is established. These results may be applied in nanotechnology, powder metallurgy, ecology, and consumer services in the implementation of the "Smart City" program. The proposed approach is phenomenological in nature and is justified by the results of real observations and experiments. [ABSTRACT FROM AUTHOR]

Atypical facial expression is one of the early symptoms of autism spectrum disorder (ASD) characterized by reduced regularity and lack of coordination of facial movements. Automatic quantification of these behaviors can offer novel biomarkers for screening, diagnosis, and treatment monitoring of ASD. In this work, 40 toddlers with ASD and 396 typically developing toddlers were shown developmentally-appropriate and engaging movies presented on a smart tablet during a well-child pediatric visit. The movies consisted of social and non-social dynamic scenes designed to evoke certain behavioral and affective responses. The front-facing camera of the tablet was used to capture the toddlers’ face. Facial landmarks’ dynamics were then automatically computed using computer vision algorithms. Subsequently, the complexity of the landmarks’ dynamics was estimated for the eyebrows and mouth regions using multiscale entropy. Compared to typically developing toddlers, toddlers with ASD showed higher complexity (i.e., less predictability) in these landmarks’ dynamics. This complexity in facial dynamics contained novel information not captured by traditional facial affect analyses. These results suggest that computer vision analysis of facial landmark movements is a promising approach for detecting and quantifying early behavioral symptoms associated with ASD. [ABSTRACT FROM AUTHOR]

Bedside patient monitors are ubiquitous tools in modern critical care units to provide timely patient status. However, current systems suffer from high volume of false alarms leading to alarm fatigue, one of top technical hazards in clinical settings. Many studies are racing to develop improved algorithms towards precision patient monitoring, while little has been done to investigate the aspect of algorithm generalizability across different health institutions. Our group has been developing an evolving framework termed SuperAlarm that extracts multivariate patterns in data streams (monitor alarms, electronic health records and physiologic waveforms) of modern health enterprise to predict patient deterioration and has demonstrated great potential in mitigating alarm fatigue. In this study, we further investigate the generalizability of SuperAlarm by designing a comprehensive approach to achieve performance comparison in predicting in-hospital code blue (CB) events across two health institutions. SuperAlarm model trained with alarm data in one institution is tested on both internal and external test sets. Results show comparable performance with sensitivity up to 80% within one-hour window of events and over 90% in reduction of false alarms in both institutions. Cross-institutional performance agreement can be further improved by predicting a more stringent CB subtype (cardiopulmonary arrest), with internal sensitivity lying within 95% confident interval of external one up to 8-hour before event onset. The cross-institutional performance comparison offers first-hand knowledge on both advantages and challenges in generalizing a prediction algorithm across different institutions, which hold key information to guide the design of model training and deployment strategy.

Redundant manipulators have been investigated and employed in various fields, and its trajectory tracking is of much importance in the field of robotic control. In this article, a model predictive control (MPC) scheme for the trajectory tracking of redundant manipulators is constructed, which minimizes the tracking error, velocity norm, and acceleration norm simultaneously. The commonly used trajectory tracking schemes for redundant manipulators, such as the minimum-velocity-norm scheme and minimum-acceleration-norm scheme, handle joint limits at different levels by introducing additional parameters, which reduces the feasible region of decision variables. In contrast, the proposed scheme directly considers these limits at three different levels, without reducing the feasible region of decision variables. In addition, to compensate for the deficiencies of most existing algorithms in noise environments, an error-summation enhanced Newton (ESEN) algorithm is proposed for solving the MPC scheme. Through theoretical analysis, it is determined that the proposed ESEN algorithm has a small steady-state error under noise conditions. Finally, in contrast with the comparative trajectory tracking schemes, as determined through computer simulations and experiments, the proposed MPC scheme solved by the ESEN algorithm not only enables the redundant manipulator to perform the trajectory tracking task in excellent fashion, but also offers advantages of high efficiency, fast responsiveness, and strong noise tolerance. [ABSTRACT FROM AUTHOR]

Unnecessary laboratory testing contributes to patient morbidity and healthcare waste. Despite prior attempts at curbing such overutilization, there remains opportunity for improvement using novel data-driven approaches. This study presents the development and early evaluation of a clinical decision support tool that uses a predictive model to help providers reduce low-yield, repetitive laboratory testing in hospitalized patients. We developed an EHR-embedded SMART on FHIR application that utilizes a laboratory test result prediction model based on historical laboratory data. A combination of semi-structured physician interviews, usability testing, and quantitative analysis on retrospective laboratory data were used to inform the tool's development and evaluate its acceptability and potential clinical impact. Physicians identified culture and lack of awareness of repeat orders as key drivers for overuse of inpatient blood testing. Users expressed an openness to a lab prediction model and 13/15 physicians believed the tool would alter their ordering practices. The application received a median System Usability Scale score of 75, corresponding to the 75th percentile of software tools. On average, physicians desired a prediction certainty of 85% before discontinuing a routine recurring laboratory order and a higher certainty of 90% before being alerted. Simulation on historical lab data indicates that filtering based on accepted thresholds could have reduced ∼22% of repeat chemistry panels. The use of a predictive algorithm as a means to calculate the utility of a diagnostic test is a promising paradigm for curbing laboratory test overutilization. An EHR-embedded clinical decision support tool employing such a model is a novel and acceptable intervention with the potential to reduce low-yield, repetitive laboratory testing. [ABSTRACT FROM AUTHOR]

Microgrids are industrial technologies that can provide energy resources for the Internet of Things (IoT) demands in smart grids. Hybrid microgrids supply quality power to the IoT devices and ensure high resiliency in supply and demand for PV-based grid-tied microgrids. In this system, the usage of predictive energy management systems (EMS) is essential to dispatch power from different resources, while the battery energy storage system (BESS) is feeding the loads. In this article, we deploy a one-day-ahead prediction algorithm using a deep neural network for a fast-response BESS in an intelligent energy management system (I-EMS) that is called SIEMS. The main role of the SIEMS is to maintain the SOC at high rates based on the one-day-ahead information about solar power, which depends on meteorological conditions. The remaining power is supplied by the main grid for sustained power streaming between BESS and end-users. Considering the usage of information and communication technology components in the microgrids, the main objective of this article is focused on the hybrid microgrid performance under cyber-physical security adversarial attacks. Fast gradient sign, basic iterative, and DeepFool methods, which are investigated for the first time in power systems e.g., smart grid and microgrids, in order to produce perturbation for training data. To secure the microgrid’s SIEMS, we propose two Defence algorithms based on defensive distillation and adversarial training strategies for the first time in EMSs. We apply and evaluate these benchmark adversarial attack and Defence methods against the proposed machine learning models to increase the robustness of the models in the system against adversarial attacks. [ABSTRACT FROM AUTHOR]

Model-free predictive current control (MFPCC) that only needs the input and output data of the system can eliminate the influence of the motor parameters mismatch. In the conventional finite control set MFPCC (FCS-MFPCC), the delay and distortion that exist in the current variations update can affect the future current prediction and the current tracking performance. This article studies an improved current variations updating mechanism to improve the update frequency. Based on the ultralocal model, the current variations corresponding to the different voltage vectors can be updated at every control period. Then, the stator currents can be predicted with the accurate current variations, and the optimal voltage vector can be selected by minimizing the cost function without using motor parameters. Besides, a sliding mode observer is designed to observe the ultralocal model's parameters fast. Furthermore, the two voltage vectors and the optimal duration are introduced to improve the current tracking performance. Meanwhile, in order to guarantee the accuracy of the future current prediction, the current compensation strategy is studied to revise the current estimation. Finally, the effectiveness of the proposed FCS-MFPCC strategy is verified through the simulation and experimental results. [ABSTRACT FROM AUTHOR]

Due to scatterer occlusion and missing during the observation time, the acquisition of the complete scatterer trajectory matrix is a hard task, which is the most important process in 3-D inverse synthetic aperture radar (ISAR) imaging of space targets based on 2-D ISAR image sequence. To cope with this problem, a novel fast scatterer trajectory association algorithm based on the cluster-based nearest neighbor standard filter (CNNSF) combined with the general Hough transform (GHT) is proposed. First, a modified dynamic equation for Kalman filter (KF) based on the scatterer projected trajectory model is derived. Then the state vector and covariance for the new dynamic equation are initialized by utilizing the GHT. Finally, the complete scatterer trajectory matrix is achieved efficiently by utilizing the proposed trajectory association algorithm based on the CNNSF algorithm. Simulation results demonstrate the correctness of the dynamic equation and the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Two-dimensional phase unwrapping (2-D PU) is a crucial step in interferometric signal processing. The accuracy of phase unwrapping (PU) will significantly affect subsequent processing. Existing algorithms perform poorly in areas with rapid terrain changes or with low coherence. In order to solve the above problems, this letter proposes a method of using a neural network to predict residuals, followed by the minimum $L^{1}$ -norm algorithm for phase reconstruction. The network for predicting residuals is called residual prediction network (RPNet). To construct more complex loss terms, the continuous relaxation strategy is applied to its training. The proposed method overcomes the effects of noise and terrain changes due to the accurate prediction of residuals. The compensated phase gradients enable the minimum $L^{1}$ -norm algorithm to reconstruct phases more accurately. The experimental results performed on simulation and interferometric synthetic aperture radar (InSAR) data demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Recent developments in brain-machine interface technology have rendered seizure prediction possible. However, the transmission of a large volume of electrophysiological signals between sensors and processing apparatuses and the related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computational resources, especially for power-critical wearable and implantable medical devices. Although many data compression methods can be adopted to compress the signals to reduce communication bandwidth requirement, they require complex compression and reconstruction procedures before the signal can be used for seizure prediction. In this paper, we propose $\text{C}^{{2}}$ SP-Net, a framework to jointly solve compression, prediction, and reconstruction without extra computation overhead. The framework consists of a plug-and-play in-sensor compression matrix to reduce transmission bandwidth requirements. The compressed signal can be utilized for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Compression and classification overhead from the energy consumption perspective, prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated using various compression ratios. The experimental results illustrate that our proposed framework is energy efficient and outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.6% in prediction accuracy with a compression ratio ranging from 1/2 to 1/16. [ABSTRACT FROM AUTHOR]

Freezing of Gait (FOG) is among the most debilitating symptoms of Parkinson’s Disease (PD), characterized by a sudden inability to generate effective stepping. In preparation for the development of a real-time FOG prediction and intervention device, this work presents a novel FOG prediction algorithm based on detection of altered interlimb coordination of the legs, as measured using two inertial movement sensors and analyzed using a wavelet coherence algorithm. Methods: Fourteen participants with PD (in OFF state) were asked to walk in challenging conditions (e.g. with turning, dual-task walking, etc.) while wearing inertial motion sensors (waist, 2 shanks) and being videotaped. Occasionally, participants were asked to voluntarily stop (VOL). FOG and VOL events were identified by trained researchers based on videos. Wavelet analysis was performed on shank sagittal velocity signals and a synchronization loss threshold (SLT) was defined and compared between FOG and VOL. A proof-of-concept analysis was performed for a subset of the data to obtain preliminary classification characteristics of the novel measure. Results: 128 FOG and 42 VOL episodes were analyzed. SLT occurred earlier for FOG (MED = 1.81 sec prior to stop, IQR = 1.57) than for VOL events (MED = 0.22 sec, IQR = 0.76) (Z =−4.3, p < 0.001, ES = 1.15). These time differences were not related with measures of disease severity. Preliminary results demonstrate sensitivity of 98%, specificity of 42% (mostly due to ‘turns’ detection) and balanced accuracy of 70% for SLT-based prediction, with good differentiation between FOG and VOL. Conclusions: Wavelet analysis provides a relatively simple, promising approach for prediction of FOG in people with PD. [ABSTRACT FROM AUTHOR]

Infantile spasms (IS) is a typical childhood epileptic disorder with generalized seizures. The sudden, frequent and complex characteristics of infantile spasms are the main causes of sudden death, severe comorbidities and other adverse consequences. Effective prediction is highly critical to infantile spasms subjects, but few related studies have been done in the past. To address this, this study proposes a seizure prediction framework for infantile spasms by combining the statistical analysis and deep learning model. The analysis is conducted on dividing the continuous scalp electroencephalograms (sEEG) into 5 phases: Interictal, Preictal, Seizure Prediction Horizon (SPH), Seizure, and Postictal. The brain network of Phase-Locking Value (PLV) of 5 typical brain rhythms is constructed, and the mechanism of epileptic changes is analyzed by statistical methods. It is found that 1) the connections between the prefrontal, occipital, and central regions show a large variability at each stage of seizure transition, and 2) 4 sub-bands of brain rhythms ($\theta $ , $\alpha $ , $\beta $ , $\gamma $) are predominant. Group and individual variabilities are validated by using the Resnet18 deep model on data from 25 patients with infantile spasms, where the consistent results to statistical analyses can be observed. The optimized model achieves an average of $79.78~\%$ , $94.46\%$ , $75.46\%$ accuracy, specificity, and recall rate, respectively. The method accomplishes the analysis of the synergy between infantile spasms mechanism, model, data and algorithm, providing a guideline to build an intelligent and systematic model for comprehensive IS seizure prediction. [ABSTRACT FROM AUTHOR]

Current works on image emotion distribution learning typically extract visual representations from the holistic image or explore emotion-related regions in the image from a global-wise perspective. However, different regions of an image contribute differently to the arousal of each emotion. Existing works do not deeply explore corresponding emotion-aware regions of each emotion in the image, nor do they fully capture the relationship between each emotion-aware region and the emotion labels. In this article, we propose a novel attention based emotion distribution learning method, which can explore the emotion-related regions of images from the perspective of each emotion category, and can conduct region relationship learning. Specifically, we introduce a semantic guided attention detection network to generate class-wise attention maps for each emotion and a global-wise attention map for the holistic image. Meanwhile, an emotional graph-based network is adopted to capture the correlation between each region and the emotion distribution. Experiments on several benchmark datasets demonstrate the superiority of the proposed method compared to related works. [ABSTRACT FROM AUTHOR]

Forecasting the future average speed fluctuation is conducive to timely perceiving the degree of urban road congestion. Nevertheless, a new challenge has arisen in accurately predicting the spot speed on an urban road network area composed by multiple road segments. To surmount this, an intelligent method for spot speed estimation, namely, the fusion deep learning model with sequence-to-sequence structure (Seq2Seq-FDL), is proposed. It is a sequence-to-sequence learning structure that covers the encoding context vector. The unidirectional convolutional long short-term memory (ConvLSTM) and bidirectional ConvLSTM networks are used to capture traffic short-term and periodic spatiotemporal synchronization characteristics, respectively. Finally, the prediction results are computed by linear feature fusion. Furthermore, the black-box effect of the proposed model is explained by the least absolute shrinkage and selection operator regression model based on Granger causality, and the rationality of the model is verified with an example of spot speed in a road network of Guangzhou. The experimental results were shown to indicate that the traffic spatiotemporal characteristics significantly contributed to the prediction effect of the Seq2Seq-FDL model. The prediction accuracy was superior to a convolutional neural network-connected LSTM network and a ConvLSTM network with or without a bidirectional LSTM; the proposed model presented good applicability in the multiple-time-step prediction of spot speed for multiple road segments. [ABSTRACT FROM AUTHOR]

Affected by the nondeterministic nature of flight trajectories, the external environment, and airport operational conditions, the prediction of the estimated time of arrival (ETA) is one of the most challenging tasks for air traffic control in the terminal maneuvering area (TMA). Previous studies lack adequate utilization of the spatial and temporal behaviors embedded in continuous trajectories. We propose a novel spatiotemporal neural network model for estimating the time of arrival (STNN-ETA), which consists of three components: 1) trajectory pattern recognition, which classifies historical trajectories into several patterns/clusters; 2) trajectory prediction, which predicts a target flight’s subsequent positions based on trajectory pattern matching; and 3) arrival time prediction, in which nonlinear function and recurrent units are adopted to capture spatiotemporal features for prediction purposes. In the proposed model, we also utilize spatial and temporal attention mechanisms to focus on important features from radar echo maps and trajectory series, respectively, and suppress unnecessary ones for ETA prediction. To validate the effectiveness of the proposed method, we apply it to predict the ETA of flights within the Beijing TMA. Extensive experiments show that STNN-ETA outperforms the state-of-the-art models in terms of the mean absolute error. [ABSTRACT FROM AUTHOR]

Location prediction based on contextual information is the core of a plethora of personalized location-based services (LBSs). Several applications require the use of techniques for predicting travel destinations based on human movement. Network analyses of human behavioral data show how the spatial-temporal regularity of human movement can be harnessed for inferring human mobility patterns. However, techniques are often based on a limited number of contextual features, which may limit prediction accuracy, especially if only historical location data are used. Using movement data obtained from public transportation users, we investigate the utility of contextual features derived via the installation of Bluetooth beacons in transportation vehicles and software tools in end-users’ travel applications. Using a multiclass random forest classifier, we show that contextual information of a user’s past travel history and at journey onset goes beyond spatial information and boosts destination prediction accuracy. The likely destination and travel-path length obtained at journey onset can then serve as the input for a stochastic-based model to predict a destination based on acquired trajectory information. Here we show that previously predicted destinations boost the performance of a Markov chain network. Thus, various contextual information at the start of a journey provides information beyond the location information acquired during a journey’s progression that can be employed for destination prediction. These findings have strong implications for LBSs as they require accurate destination prediction at early stages of a journey while at the same time mitigating the privacy concerns associated with collection of location data. [ABSTRACT FROM AUTHOR]

The estimation of nested functions (i.e., functions of functions) is one of the central reasons for the success and popularity of machine learning. Today, artificial neural networks are the predominant class of algorithms in this area, known as representational learning. Here, we introduce Representational Gradient Boosting (RGB), a nonparametric algorithm that estimates functions with multi-layer architectures obtained using backpropagation in the space of functions. RGB does not need to assume a functional form in the nodes or output (e.g., linear models or rectified linear units), but rather estimates these transformations. RGB can be seen as an optimized stacking procedure where a meta algorithm learns how to combine different classes of functions (e.g., Neural Networks (NN) and Gradient Boosting (GB)), while building and optimizing them jointly in an attempt to compensate each other’s weaknesses. This highlights a stark difference with current approaches to meta-learning that combine models only after they have been built independently. We showed that providing optimized stacking is one of the main advantages of RGB over current approaches. Additionally, due to the nested nature of RGB we also showed how it improves over GB in problems that have several high-order interactions. Finally, we investigate both theoretically and in practice the problem of recovering nested functions and the value of prior knowledge. [ABSTRACT FROM AUTHOR]

The lack of studying the complex organization of directed network usually limits the understanding of the underlying relationship between network structures and functions. Structural controllability and structural predictability, two seemingly unrelated subjects, are revealed in this article to be both highly dependent on the critical links previously thought to only be able to influence the number of driver nodes in controllable directed networks. Here, we show that critical links can not only contribute to structural controllability but can also have a significant impact on the structural predictability of networks, suggesting the universal pattern of structural reciprocity in directed networks. In addition, it is shown that the fraction and location of critical links have a strong influence on the performance of prediction algorithms. Moreover, these empirical results are interpreted by introducing the link centrality based on corresponding line graphs. This work bridges the gap between the two independent research fields, and it provides indications of developing advanced control strategies and prediction algorithms from a microscopic perspective. [ABSTRACT FROM AUTHOR]