Search

Multi-instance learning (MIL), as a special version of classification, focuses on labeled sets (bags) consisting of unlabeled instances and has drawn accumulative attention due to its significant importance in practical applications. However, most existing MIL methods just utilize partial information (bags or instances) of MIL data to construct the kernel function, resulting in deteriorated classification performance of MIL. In this paper, we propose a Double Similarities weighted Multi-Instance Learning (DSMIL) kernel framework, which utilizes the similarities of Bag-to-Bag (B2B) and Instance-to-Bag (I2B). In the proposed kernel framework, the similarities of B2B and I2B could be derived from the prototypes distance of inter-bag and similarity matrix of intra-bag, respectively, based on the affinity propagation (AP) clustering of the bag. Meanwhile, we give theoretical proof of the validity of the designed kernel function. Experimental results on benchmark and semi-synthetic datasets show that our proposed method obtains competitive classification performance and achieves robustness to parameters and noise. • A double similarities weighted MIL kernel is proposed and proved as a valid kernel. • The DSMIL integrates the similarities of B2B and I2B into the kernel function. • The DSMIL obtains competitive results on benchmark datasets and newsgroups dataset. [ABSTRACT FROM AUTHOR]

Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on various practical tasks. However, most existing works ignore the impact of per-class distribution, therefore their performance may be limited due to the diversity of various categories. In this paper, we propose a novel class-aware progressive self-training (CPS) algorithm for training graph convolutional networks (GCNs). Compared to other self-training algorithms for GCNs' learning, the proposed CPS algorithm leverages the class distribution to update the original graph structure in each self-training loop, including: (a) find these high-confident unlabeled nodes in the graph for each category to add pseudo labels, in order to enlarge the current set of labeled nodes; (b) delete these noisy edges between different classes for graph sparsification. Then, the optimized graph is used for next self-training loops in hopes of enhancing the classification performance. We evaluate the proposed CPS on several datasets commonly used for GCNs' learning, and the experimental results show that the proposed CPS algorithm outperforms other baselines. [ABSTRACT FROM AUTHOR]

Predicting the difficulty of playing a musical score is essential for structuring and exploring score collections. Despite its importance for music education, the automatic difficulty classification of piano scores is not yet solved, mainly due to the lack of annotated data and the subjectiveness of the annotations. This paper aims to advance the state-of-the-art in score difficulty classification with two major contributions. To address the lack of data, we present Can I Play It? (CIPI) dataset, a machine-readable piano score dataset with difficulty annotations obtained from the renowned classical music publisher Henle Verlag. The dataset is created by matching public domain scores with difficulty labels from Henle Verlag, then reviewed and corrected by an expert pianist. As a second contribution, we explore various input representations from score information to pre-trained ML models for piano fingering and expressiveness inspired by the musicology definition of performance. We show that combining the outputs of multiple classifiers performs better than the classifiers on their own, pointing to the fact that the representations capture different aspects of difficulty. In addition, we conduct numerous experiments that lay a foundation for score difficulty classification and create a basis for future research. Our best-performing model reports a 39.5% balanced accuracy and 1.1 median square error across the nine difficulty levels proposed in this study. Code, dataset, and models are made available for reproducibility. • Introducing CIPI, the most comprehensive piano difficulty dataset, with 652 pieces across 9 levels. • We design models using various music performance aspects, guided by musicology insights. • Using multi-view music performance model predictions boosts accuracy. • Choosing the right loss function is vital for ordinal regression tasks as difficulty prediction. • We carry out extensive experiments helpful for further research. [ABSTRACT FROM AUTHOR]

Optimizing drug dosages is essential for effective treatment. Clinical protocols may not suit all types of patients evenly, due to many drug trials not being designed to account for all comorbities or clinically relevant outcomes. Methodologies to optimize drug policies with observational data exist, but struggle due to limited data completeness in clinical settings. Computational methods can help overcome these challenges by leveraging field knowledge. This paper proposes an Individualized Doser (IDoser), a core dosing model that links drug dose to relevant covariates via a set of coefficients and includes a loss function to code needed assumptions and requirements. Coordinate descent is used to obtain a fitted model with minimal loss. The loss function also measures performance when validating the model with unseen data. We validated the proposed approach using the case of follicle-stimulating hormone (FSH) dosing for controlled ovarian stimulation (COS). When compared to clinical practice, IDoser achieved a net improvement of up to 31.97% in the validation cases. We present a simple but effective method to bridge the gap between current clinical dosing policies and gold policies based on the true underlying and often unknown dose–response functions. [Display omitted] • IDoser allows to incorporate domain knowledge in the dosing model. • The search for policy solutions is customizable depending on the dosing problem. • For FSH dosing, up to 31.97% improvement was observed against a clinical practice. • Its flexible capabilities indicate potential applicability for similar problems. [ABSTRACT FROM AUTHOR]

Automated Essay Scoring (AES) is a challenging topic in Natural Language Processing. Recently, deep learning models have achieved remarkable performance for the AES task. However, applying deep learning models to the AES system in practice is expensive when both data collection and model training are taken into consideration. This paper aims to tackle this problem by proposing the Crowdsourcing-based Automated Essay Scoring (CAES) framework. The proposed framework gradually collects data through crowdsourcing and incrementally trains the AES models. In particular, we propose the Incremental Learning with Dynamic Exemplar Herding (ILDEH) approach to simultaneously tackle catastrophic forgetting and concept drift. The proposed approach dynamically updates the exemplar set by the Dynamic Exemplar Herding algorithm to obtain the best approximation of the overall data distribution and selectively apply knowledge distillation on the model outputs by Linear Outlier Suppression loss to retain the learned knowledge. Moreover, we use a lightweight AES model for effective and efficient essay scoring. The experimental results show that our proposed ILDEH approach outperforms other strong baseline approaches for the AES task. Moreover, the CAES framework is able to steadily improve the AES performance in the crowdsourcing environment with only 10.6% training time of the conventional approach. Further analysis shows that one single CPU server can support daily updates of more than 300 AES models, which is sufficient for most practical AES systems. • We proposed the Crowdsourcing-based Automated Essay Scoring (CAES) framework. • We proposed an incremental learning approach to efficiently train AES models. • Our proposed approach outperforms strong baseline approaches. • The CAES framework requires only 10.6% of the conventional training time. • The CAES framework supports daily update of 300 AES models on a single CPU server. [ABSTRACT FROM AUTHOR]

Animation drama and movies are important entertainment sources for children and young people. However, many of these entertainment videos introduce ideas such as violence, fighting, abuse, and car accidents, which are not suitable for children and young people. In order to prevent children from viewing these videos, different countries' government bodies put restrictions on age on these videos. Violence detection is mostly done using manual inspection, which is time and resource consuming and cannot achieve a very good result. Therefore, artificial technologies such as deep learning and machine learning can detect violence in a video. Bleeding is one of the distinct characteristics of violent actions presented in such videos. This paper aims to propose a system that can detect a given video's blood in real-time. Researchers have proposed different image processing-based techniques to detect violence, but their proposed systems lack precision and real-time detection. To this end, a deep learning-based approach is proposed to detect violence in a given video and images. A Faster R-CNN model is modified due to the sophisticated characteristics of the violence in the cartoon and animation images to achieve the highest performance. The backbone of the proposed violence detection model is changed to a modified RegNet model to extract the features from the frame. The standard inner lateral connection is replaced with the modulated deformable convolutional (MDC) layer to extract deformable feature maps. A novel distributed attention module (DAM) is proposed on the feature pyramid network to improve the performance of the feature extraction. The multiscale Region of interest (ROI) Align is adapted to improve the detection performance of violence in a different scenario. Moreover, the classification approach is integrated with the detection model to classify the different levels of violence in a given frame. We have explored state-of-the-art object detection methods such as Faster R-CNN, Cascade R-CNN, yolov3-spp, SSD, FCOS, and yolov5 to detect violence in a particular frame of a video. We compared the different models' performances and found out that the modified Faster R-CNN is appropriate for real-time blood detection in a given video or image with high accuracy. This study makes a significant contribution to detecting violence in animation videos which will help different platforms and government bodies to regulate entertainment content. [ABSTRACT FROM AUTHOR]

• Exploring the effect of locally weighted learning with machine learning model. • Gain ratio are used to select the most important environmental factor. • LWL-RS-ADT appears as an accurate model in assessing landslide susceptibility. Assessing landslide susceptibility and predicting the possibility of landslide event is the foundation and prerequisite for emergency response and management of landslide disaster. The target of current paper is to propose five integration models based on integrating locally weighted learning (LWL) with a radial basis function classifier (RBF), Fisher's linear discriminant (FLDA), quadratic discriminant analysis (QDA), a Credal decision tree (CDT), an alternating decision tree (ADT) and random subspace (RS) and the performance of five integration models were compared for modeling landslide susceptibility. Yongxin County from China was employed as a study area, 364 landslide locations and fifteen environmental factors were applied. The results demonstrate that the proposed LWL-RS-ADT model is more reliable and stable than the other models. Among the fifteen environmental factors, NDVI, lithology, and altitude are the very significant factors in the six models. It is concluded that the proposed integration models provide an effective way to predict the susceptibility of landslides. [ABSTRACT FROM AUTHOR]

• Propose an improved random forest based on the improvement of decision trees. • Improve the evaluation mechanism for the classification effect of decision trees. • Propose a method for quantifying the diversity between decision trees. • Multiple tests verify the superiority of the proposed improved random forest. Random forest is one of the most widely used machine learning algorithms. Decision trees used to construct the random forest may have low classification accuracies or high correlations, which affects the comprehensive performance of the random forest. Aiming at these problems, the authors proposed an improved random forest based on the classification accuracy and correlation measurement of decision trees in this paper. Its main idea includes two parts, one is retaining the classification and regression trees (CARTs) with better classification effects, the other is reducing the correlations between the CARTs. Specifically, in the classification effect evaluation part, each CART was applied to make predictions on three reserved data sets, then the average classification accuracies were achieved, respectively. Thus, all the CARTs were sorted in descending order according to their achieved average classification accuracies. In the correlation measurement part, the improved dot product method was proposed to calculate the cosine similarity, i.e., the correlation, between CARTs in the feature space. By using the achieved average classification accuracy as reference, the grid search method was used to find the inner product threshold. On this basis, the CARTs with low average classification accuracy among CART pairs whose inner product values are higher than the inner product threshold were marked as deletable. The achieved average classification accuracies and correlations of CARTs were comprehensively considered, those with high correlation and weak classification effect were deleted, and those with better quality were retained to construct the random forest. Multiple experiments show that, the proposed improved random forest achieved higher average classification accuracy than the five random forests used for comparison, and the lead was stable. The G-means and out-of-bag data (OBD) score obtained by the proposed improved random forest were also higher than the five random forests, and the lead was more obvious. In addition, the test results of three non-parametric tests show that, there were significant diversities between the proposed improved random forest and the other five random forests. This effectively proves the superiority and practicability of the proposed improved random forest. [ABSTRACT FROM AUTHOR]

Common objectives in machine learning research are to predict the output quality of manufacturing processes, to perform root cause analysis in case of reduced quality, and to propose intervention strategies. The cost of reduced quality must be weighed against the cost of the interventions, which depend on required downtime, personnel costs, and material costs. Furthermore, there is a risk of false negatives, i.e., failure to identify the true root causes, or false positives, i.e., adjustments that further reduce the quality. A policy for process adjustments describes when and where to perform interventions, and we say that a policy is worthwhile if it reduces the expected operational cost. In this paper, we describe a data-driven alarm and root cause analysis framework, that given a predictive and explanatory model trained on high-dimensional process and quality data, can be used to search for a worthwhile adjustment policy. The framework was evaluated on large-scale simulated process and quality data. We find that worthwhile adjustment policies can be derived also for problems with a large number of explanatory variables. Interestingly, the performance of the adjustment policies is almost exclusively driven by the quality of the model fits. Based on these results, we discuss key areas of future research, and how worthwhile adjustment policies can be implemented in real world applications. • Framework for finding a process adjustment policy for quality improvement. • Uses a pre-trained predictive and explanatory machine learning model. • Cost function defines compromise between quality and interventions. • Simulation experiments for finding an optimal policy and estimating its cost. • Benefits from research in time series forecasting and local explanation methods. [ABSTRACT FROM AUTHOR]

The human skin, the largest organ with multiple layered functionalities, houses melanocytes in the deeper strata of its epidermis. These cells can be adversely impacted by ultraviolet radiation, thereby instigating melanoma, the deadliest form of skin cancer. Failure to detect melanoma at an early stage can potentially lead to metastasis, forming complex tumors in other tissues. Despite substantial efforts, visual inspections can occasionally overlook melanoma cases due to inherent subjectivity. To surmount this challenge, an automated detection system is necessary. Recent attempts to establish such a system have predominantly employed "push-through" strategies involving deep (neural) networks and their ensembles, which however necessitate significant computational resources. This paper presents a novel approach, amalgamating a conventional machine learning technique, Bag of Visual Words, with a pretrained deep neural network for comprehensive deep feature extraction from enhanced input image patches. The proposed method, assessed on the ISIC Challenge 2017 dataset, surpassed all other entries on the challenge leader-board, registering an accuracy of 96.2% in the task of lesion classification. • Novel method for melanoma detection combining Bag of Visual Words with a deep network. • Patch-based feature extraction from lesion images integrated into BoVW with K-means. • Successful image enhancement technique for feature extraction from lesion images. • Efficient framework: modular architecture, easy updates, less training delay. [ABSTRACT FROM AUTHOR]

A metaheuristic-based structural optimization method, whilst being popularly adopted due to its advantages in by-passing gradient function calculations, requires the use of time-consuming advanced analyses for constraint evaluation. To overcome this drawback, the present paper proposes a robust (machine learning-based) optimization method that combines the light gradient boosting machine (LightGBM) with the efficient p-best differential evolution (E p DE) method. In essence, the LightGBM classification model is constructed to assess the constraint (safety and integrity) satisfaction of structures. An efficient framework using a so-called safety parameter is proposed to prevent inaccurate predictions of the LightGBM model. The E p DE processes the optimization procedures on the constructed classification LightGBM model. This enables an enhanced machine learning-based optimization technique that not only maintains the sufficiently accurate optimal design of structures but also significantly reduces the required computing efforts, as compared to standard optimization schemes. Various examples of steel structure designs (i.e., two of which have been provided herein) have been successfully performed by the proposed approach. These illustrate the accuracy and robustness of the proposed method, where good comparisons with reference algorithms (including standard DE with "DE/rand/1" mutational strategy, Jaya, Rao-1 and CaDE) are evidenced. The statistical values collected present the accuracy and reliability of the proposed method in obtaining the minimum total weight designs with substantial (some 60%) reduction of computing efforts required to furnish optimal results. [ABSTRACT FROM AUTHOR]

The presence of Beggiatoa Spp. indicates anoxic conditions or 'poor condition' in marine sediments beneath aquaculture pens, resulting from organic enrichment. Currently, the most efficient approach to estimate Beggiatoa Spp. coverage, and thus the extent of the issue, involves video surveys which are scored by human observers for presence of this bacteria. However, this approach is highly time-consuming and relies heavily on the expertise and experience of the individuals involved, thus affecting its accuracy. Machine learning-based computer vision techniques, such as Convolutional Neural Networks (CNNs), offer the potential for automated estimation of Beggiatoa Spp. coverage. However, most existing machine learning methods focus solely on the estimation of the coverage via presence, absence of a single type of Beggiatoa Spp.. These approaches typically rely on binary classification to distinguish the object from the background when estimating coverage. Nevertheless, the inclusion of subordinate categories within high-level classifications poses a great challenge for accurately estimating their coverage rates. In this paper, an adaptive ensemble learning approach was proposed to estimate Beggiatoa Spp. coverage. Unlike other approaches, the proposed approach is capable in adaptively extracting and fusing features from underwater images and accurately estimating the coverages of multiple types of Beggiatoa Spp. through ensemble learning. Experimental results demonstrated that our proposed approach outperforms other approaches in terms of both effectiveness and efficiency in estimating Beggiatoa Spp. coverage. • Adaptive feature extraction and fusion enhance relevant and informative features' identification. • Adaptive feature extraction and fusion enhance feature representation and reduce time cost. • Flexible ensemble learning framework improves accuracy, robustness, and efficiency. • Flexible ensemble learning framework can be extended to other models or applications. • Novel machine learning-based approach estimates subordinate categories of Beggiatoa Spp. coverage. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has made its way into many disciplines ranging from health care to self-driving cars. In financial markets, we see a rich literature for DL applications. Particularly, investors require robust algorithms that can navigate and make sense of extremely noisy and volatile markets. In this work, we use deep learning to select a portfolio of stocks and use a genetic algorithm to optimize the hyperparameters of DL. The work analyzes the improvement in using genetic-based hyperparameter optimization over grid searches. The Genetic Algorithm brings 40% improvements in prediction when compared to a random-grid search. Novelty-wise, the work couples a genetic-based hyperparameter optimization with multiple Deep RankNet models to predict the behavior of financial assets. Our results show promising portfolio returns 20% better than the general market. In the highly volatile COVID 19 period, the models exceed market returns by more than double. Overall, this paper brings a comprehensive work that integrates hyperparameter optimization, Deep RankNet, LSTM, period size variations, input variable transformation, feature selection, training/evaluation ratio analysis, and multiple portfolio selection strategies. [ABSTRACT FROM AUTHOR]

Machine learning techniques have been widely used and are mostly performed by predicting point estimation. Nevertheless, there are various scenarios that require more information beyond only point estimation. Probabilistic prediction is a typical research topic that provides probability distribution while predicting, which addressed with much attention recently. Most of the previous works make an assumption on the probabilistic distribution to a certain extent, which may lead to potential errors in the subsequent decision-making procedure. In this paper, we propose a distribution-free method for regression problems on real-value response under the probabilistic prediction framework and present an effective boosting-based method to perform the training process. Moreover, we introduce a further improved method to accomplish an unbiased mean estimation of the target distribution. Thorough experiments on multiple benchmark data are conducted to demonstrate the effectiveness of the proposed method with regard to different measures. • A distribution-free framework for probabilistic forecasting. • Use a mixture of Gaussian distribution as the target distribution. • An effective boosting-based strategy. • Providing unbiased mean estimation. [ABSTRACT FROM AUTHOR]

With the advent of the era of big data, more and more complex networks and knowledge based systems require data visualization for analysis and presentation, where graphs have become a standard representation model. Graph drawing addresses the problems of constructing geometric representations of graphs to make them easy to analyze. In this paper we aim to reduce the edge crossing number in the context of the incremental graph drawing problem (IGDP), in which we want to preserve the layout of a graph over successive drawings to present complex networks or knowledge-based systems. Specifically, we propose a metaheuristic algorithm called multiple neighborhood solution-based tabu search (MNSB-TS) by combining a solution-based tabu strategy and a multiple neighborhood structure for solving the incremental graph drawing problem. Our MNSB-TS approach introduces four neighborhood operators to accompany the solution-based tabu strategy for determining the tabu status of each neighbor solution. Extensive computational experiments on public benchmark instances demonstrate that the proposed MNSB-TS is highly competitive in comparison with the state-of-the-art heuristics and the exact optimization solver Gurobi. Key components of the approach are analyzed to evaluate their impact on algorithm performance and learn which search mechanisms are better suited for incremental graph drawing. • A novel method combines a solution-based tabu search and multiple neighborhood search. • The corresponding fast neighborhood evaluation methods for intensification. • A dynamic diversification phase which varies the diversification intensity. • The conducted experiments show the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

As giant pandas (Ailuropoda melanoleuca) are difficult to conceive and prone to abortion, humans have turned to artificial captive breeding to increase their population. Therefore, it is crucial for their reproduction to analyze their pregnancy status accurately and promptly in artificial captive breeding. To determine whether a giant panda is pregnant, with the current methods, experts must keep a close eye on them and frequently collect their urine or blood, which requires significant resources with a high misdiagnosis rate, and will adversely affect giant pandas' daily lives. Consequently, it is essential to rapidly advance the development of automated, precise methods that will not disrupt the pandas' lives to analyze giant pandas' behaviors and determine whether or not they are pregnant. In this paper, we propose an end-to-end intelligent system for predicting the pregnancy status of giant pandas and their Expected Date of Delivery (EDD). We first introduce expert knowledge to machine learning methods to solve this problem, which can significantly improve the accuracy of prediction. Experimental results show that this system achieves an accuracy of 91.5% for the pregnancy diagnosis and 0.579 days of mean average error for EDD prediction when the observation period is 5 days. Our automated system significantly reduces the need for human intervention, thus minimizing disruptions to the pandas' daily lives. It has the potential to contribute to the health and genetic diversity of the giant pandas, as well as aid in the panda's artificial reproduction and population growth. • An intelligent system automatically analyzes the pregnancy status of giant pandas. • Hierarchical behavior definition for acquiring comprehensive behavior description. • Effective pregnancy analysis model based on efficient channel attention mechanism. • Scalable sliding window mechanism to deal with insufficient data. [ABSTRACT FROM AUTHOR]

Although some machine learning (ML) models have successfully developed for ultra-high-performance concrete (UHPC), they do not provide insights and explicit relations between all input variables and its compressive strength. This paper will address these ambiguities and provide a tool to predict the compressive strength by explainable and interpretable equations and plots. Explicit semi-empirical formulas are derived from a multivariate polynomial regression (Lasso) and automated feature engineering and selection (Autofeat) using a 810 dataset of UHPC with 15 input variables, which are collected from literature. Coefficient of determination R 2 = 0.8223 is the same for the first-order degree (linear regression) of both models, however, the Autofeat achieves a better result than Lasso for the third-order degree with R 2 = 0.9616 vs. R 2 = 0.9503. A comprehensive parametric study is carried out via relative feature importance and partial dependence plots to explain and gain profound insights into the effects of some important input variables on the compressive strength of UHPC. Some details discussions related to these effects with previous studies are also presented. The proposed models not only show better performance with those from reference in terms of R 2 , especially for Autofeat model but also have explicit relations of compressive strength with 15 input variables. Hence, they can be used as a reliable tool in mixture design optimization of the UHPC. • Explicit formulas are derived to predict the compressive strength of UHPC. • Multivariate polynomial regression and automated feature engineering are used. • Relative feature importance and partial dependence plots are used to explain mechanism. • The proposed models show better performance with explicit relations of strength. [ABSTRACT FROM AUTHOR]

With a recently defined AutoGCOP framework, the design of local search algorithms has been defined as the composition of elementary algorithmic components. The effective compositions of the best algorithms thus retain useful knowledge of effective algorithm design. This paper investigates machine learning to learn and extract useful knowledge in effective algorithmic compositions. The process of forecasting algorithmic components in the design of effective local search algorithms is defined as a sequence classification task, and solved by a long short-term memory (LSTM) neural network to systematically analyse algorithmic compositions. Compared with other learning models, the results reveal the superior prediction performance of the proposed LSTM. Further analysis identifies some key features of algorithmic compositions and confirms their effectiveness for improving the prediction, thus supporting effective automated algorithm design. • The design of local search algorithms is defined as a sequence classification task. • LSTM is applied to forecast algorithmic components for automated composition. • LSTM has a better classification performance as compared with other classifiers. • Key features for sequence classification are identified to support algorithm design. [ABSTRACT FROM AUTHOR]

The Computational Fluid Dynamics (CFD) simulations at different fidelity levels are a common tool for predicting the aerodynamic performance in many engineering applications such as; automotive and aerospace to cite a few. However, the associated computational costs with these simulations are not trivial, and using the CFD simulations might easily become unpractical specially at the early design stages. The number of the required CFD simulations could be reduced immensely by using Artificial Intelligence (AI) methods which can predict, for example, the aerodynamic coefficients based on previous and limited CFD simulations. Having discussed the AI potential to minimize the CFD usage, the objective of this work is to investigate and compare the ability of different AI methods to predict the aerodynamic coefficients using the same CFD database from the literature. In this study, three different AI methods, namely; machine learning (e.g. Extreme Gradient Boosting (XGB), CatBoost, Bagging, Light Gradient Boosting Machine (Light-GBM), Random Forest (RFR), Gradient Boosting), deep learning (e.g. One Dimensional Convolutional Neural Network (Conv1D)) and surrogate models (e.g. Gaussian Process Regression (GPR)) have been utilized to estimate a sample CFD database (e.g. NACA0012, RAE2822) from the existing literature, and the prediction performance of these methods have been compared. The results show that, the aerodynamic coefficients predicted using CatBoost, XGB and Bagging are in good agreement with the reference CFD results. Furthermore, the proposed Conv1D method with LeakyReLU activation function showed a promising results in the development of aerodynamic models which can be used in the early stages of the air vehicles design. The obtained results from this work indicate that the CatBoost and the XGB models required much smaller training time compared to the Conv1D method, moreover, the proposed regression trees; CatBoost, Bagging and XGB can reduce the required number of CFD simulations significantly. • Various artificial intelligence methods were studied to predict aerodynamic data. • Regression tree models such as XGB, Catboost and LightGBM were used. • Surrogate models and deep learning models (i.e. Conv1D) also were used. • Detailed comparison were presented between the aforementioned models. • The paper suggests the suitability of XGB and Catboost for aerodynamics cases. [ABSTRACT FROM AUTHOR]

• A multi-objective robust parameter optimization for additive manufacturing process. • Modified k-means simultaneously optimize the mean and variance of multiple responses. • Modified k-means-based optimization with higher performances than conventional method. Metal additive manufacturing (AM) technology, especially laser powder bed fusion (LPBF), has received abundant interest from industries and the research community. Process optimization methods have thus multiplied to improve the overall quality of the final parts. However, little attention has been given to the quality repeatability issue. This paper proposes a novel multi-objective robust parameter optimization framework to explore optimal process parameters with respect to relative density and dimensional accuracy of LPBF-fabricated parts. Specifically, a modified k-means clustering, named the Extended and Weighted K-means (EWK-means), was constructed to simultaneously optimize the mean and the variance of the multiple responses. Experiments were conducted to verify the effectiveness of the proposed optimization framework. In addition, the effects of the process parameters, environment-related parameters, and physical properties on the hardness of the parts were analyzed using several machine learning models. The results showed that the proposed method achieved a set of optimal process parameters with better quality and satisfactory variability in the printed parts compared with other robust parameter optimization methods. [ABSTRACT FROM AUTHOR]

• The paper is dedicated to proposed a cluster-based routing protocol for WBAN. • The paper utilizes the benefits of machine learning. • A novel approach, MGWOQL, is proposed for cluster head selection and updation. • The multi-objective function is designed to select the optimal cluster head node. • The result shows better network longevity, residual energy, and path loss. Recently, Wireless Body Area Networks (WBAN) have been developed to advance Internet-of-Things (IoT) that play an essential role in biomedical applications. While deploying these applications practically, there may arise associated issues. Among all the available problems, the primary concern is energy utilization among these resource-limited sensors during data communication. These sensors continuously sense the signal and send messages to other nodes. There is a need to optimize the energy utilization in WBAN. This paper proposes a cluster-based routing protocol for WBAN with the benefits of machine learning to predict energy wastage. A Modified Grey Wolf Optimization with Q-Learning (MGWOQL) is proposed for cluster head selection and updating. The proposed protocol used different objective functions to minimize the energy utilization of clusters by selecting the optimal cluster head (CH). The simulation was performed on the MATLAB platform under different conditions. The result analysis shows its efficiency in terms of energy for WBAN. [ABSTRACT FROM AUTHOR]

• A property in the iterative process of FPC is discovered. • A novel initialization method of FPC is proposed. • A strategy to improve the efficiency of FPC is given. • The method makes the recommendation algorithm have a high convergence speed. In recent years, the problem of matrix completion based on rank minimization has received widespread attention in machine learning. The tightest convex relaxation of this problem is the linearly constrained nuclear norm minimization. Fixed point continuation (FPC), as a representative nuclear norm relaxation matrix completion algorithm, has been proven to perform well in theories and experiments. However, the traditional FPC algorithm initializes the matrix to be completed by zero, which does not make full use of the shrinkage characteristics of the singular value shrinkage operator on the matrix elements and the known field data information, then will lead to slow convergence and poor accuracy. Aiming at this problem, this paper analyzes the shrinkage properties of matrix elements in the iterative process of the FPC algorithm. Combined with the known rating information in the recommendation systems, a new initialization method of overestimation based on FPC is proposed, and it is applied to the rating prediction in the recommendation systems. The experimental results show that the initialization method proposed in this paper greatly improves the algorithm efficiency and prediction accuracy. [ABSTRACT FROM AUTHOR]

To deal with increasing amounts of data, decision and policymakers frequently turn to advances in machine learning and artificial intelligence to capitalise on the potential reward. But there is also a reluctance to trust black-box models, especially when such models are used to support decisions and policies that affect people directly, like those associated with transport and people's mobility. Recent developments focus on explainable artificial intelligence to bolster models' trustworthiness. In this paper, we demonstrate the use of an explainable-by-design model, Bayesian Networks, on travel behaviour. The model incorporates various demographic and socioeconomic variables to describe full day activity chains: activity and mode choice, as well as the activity and trip durations. More importantly, this paper shows how the model can be used to provide the most relevant explanation for people's observed travel behaviour. The overall goal is to show that model explanations can be quantified and, therefore, assist policymakers to truly make evidence-based decisions. This goal is achieved through two case studies to explain people's vulnerability as it pertains to their total trip duration. • Bayesian network approach to demonstrate explainable artificial intelligence (XAI). • Network structure includes demographic, travel and temporal variables. • Bayesian networks is both behaviourally rich and intuitively interpretable. • Quantify vulnerability explanations for travel behaviour. [ABSTRACT FROM AUTHOR]

The past decade has witnessed the rapid development of Artificial Intelligence (AI), especially the explosion of deep learning-related connectionist approaches. This study combines traditional literature review, bibliometric methods, and the Science of Science (SciSci) theory to scrutinize the development context of AI in the last decade on AMiner. 4 4 www.aminer.cn , AMiner is an academic mining system, which will be introduced in the following section. With the assistance of AMiner tools and datasets, this paper aims to describe a further explicit context and evolution of AI in the past decade from the development of connectionist approaches. Five aspects of the past decade are highlighted: self-learning and self-coding algorithms, Recurrent Neural Networks (RNN) algorithms, reinforcement learning, pre-trained models, and other typical deep learning algorithms, which represent the significant progress of this field. By combining these critical parts, we then summarize the current limitations and corresponding future of AI trends in the next decade and discuss some topics about the next generation of AI. Discoveries in this paper will benefit AI research in promoting understanding of the current critical stage and future trends of AI development and the AI industry in the dramatic ascendant for the academic research results transformation and its industrial layout. [ABSTRACT FROM AUTHOR]

Max-cut is one of the most classic NP-hard combinatorial optimization problems. The symmetry nature of it leads to special difficulty in extracting meaningful configuration information for learning; none of the state-of-the-art algorithms has employed any learning operators. This paper proposes an original learning method for max-cut, namely post-flip edge-state learning (PF-ESL). Different from previous algorithms, PF-ESL regards edge-states (cut or not cut) rather than vertex-positions as the critical information of a configuration, and extracts their statistics over a population for learning. It is based on following observations. 1) Edges are the only factors considered by the objective function. 2) Edge-states keep invariant when rotating a local configuration to its symmetry position, but vertex-positions do not. These suggest that edge-states contain more meaningful information about a configuration than vertex-positions do. It is impossible to set the state of an edge without influencing some other edges' states due to their dependencies. Therefore, instead of setting edge-states directly, PF-ESL samples the flips on vertices. Flips on vertices are sampled according to their capacities in increasing the similarity on edge-states between the given solution and a population. PF-ESL is employed in an EDA (Estimation of Distribution Algorithm) perturbation operator and a path-relinking operator. Experimental results show that our algorithm is competitive, and show that edge-state learning is value-added for both the two operators. The main contributions of this paper are as follows. Firstly, previous state-of-the-art evolutionary algorithms for max-cut focus on vertex positions in their evolutionary operation, this paper proposes a new and more reasonable perspective suggesting that edge-states are the critical information of divided graphs rather than vertex positions, and introduces a novel method to measure and utilize their similarities based on it. Such a perspective is fundamental to learning based algorithms design for max-cut and other graph partitioning problems, and can shed lights on future researches. Furthermore, since max-cut is one of the most classic and fundamental NP hard problems, many real-world problems involve dividing graph data into different parts to optimize certain functions, this new perspective may inspire related or similar problems. Secondly, besides the original edge-states based perspective, and the post-flip edge-states learning (PFESL) operator based on it, our memetic algorithm also incorporates a novel evolutionary framework which alternates between EDA based Iterated Tabu search (ITS) and path relinking based genetic algorithm. Finally, the proposed algorithm provides competitive results on two mostly used benchmark sets and improves the best-known results of 6 most challenging instances. • An original edge-state perspective for design learning operators for max-cut. • A novel learning operator to learn edge states. • A new evolutionary framework for max-cut. • It provides competitive results on two mostly used benchmark sets. [ABSTRACT FROM AUTHOR]

Globally, all the major crops are significantly affected by diseases every year, as manual inspection across diverse fields is time-consuming, tedious, and requires expert knowledge. This leads to significant crop loss in different parts of the world. To provide effective solutions, several smart agriculture solutions are deployed for the control of pests and plant diseases using vision-based machine learning techniques. Despite rapid growth in the field, not many methods have been explored for their suitability in real-time applications. Several open challenges need to be addressed for the applicability of machine learning techniques in IoT-based smart agriculture solutions. Starting from data capturing methods and the availability of public datasets, the present paper provides a comprehensive review of vision-based machine learning techniques for plant disease detection. Initially, 1337 articles were selected from various scholarly resources to perform the survey. Based on the saliency of approaches, 148 articles are reviewed in this paper. Interestingly, a significant amount of research in this direction is taken up by Chinese and Indian researchers, and deep learning is the current research trend, as in other fields. The review concludes that a majority of existing methods exhibit their efficacy on public datasets captured mostly in controlled environmental conditions, but their generalization capability for in-field plant disease detection has not been explored. Lightweight CNN-based methods, on the other hand, have been designed for a limited number of diseases only, and are generally trained on small datasets. The scarcity of large-scale, in-field public datasets is one of the major bottlenecks in developing solutions that can work for a wide variety of plant diseases. [ABSTRACT FROM AUTHOR]

Vertical federated learning (VFL) is a privacy preserving collaborative machine learning technique designed for distributed learning scenarios in which data from different parties have overlap in the sample space. In this paper, a VFL method for feature selection, which is an effective dimensionality reduction technique that selects a subset of informative features from high-dimensional data by eliminating irrelevant and redundant features, is proposed. Because of the potential insufficiency of useful information for learning informative features and the difficulty in sharing raw data among parties due to the increasing awareness of data privacy protection, it is desirable to exploit information from multiple parties without raw data sharing. In this paper, we propose a VFL-based feature selection method that leverages deep learning models as well as complementary information from features in the same samples at multiple parties without data disclosure. In order to further improve feature selection performance, information of samples that do not have features appearing in all parties are also utilized. Promising results in extensive experiments show the effectiveness of the proposed approach in terms of collaborative feature selection without data sharing. • In this paper, we bridge this gap by proposing a novel VFL-based feature selection method—Vertical Federated Learning-based Feature Selection (VFLFS). To the best of our knowledge, this is the first deep learning-based vertical federated learning approach with feature selection. • A strategy to make use of non-overlapping samples is also proposed to improve feature selection effectiveness. • The proposed VFLFS approach has been evaluated extensively based on real-world datasets. The results show that VFLFS can significantly improve model performance under VFL settings compared to four state of the art baselines, especially in conditions where a large proportion of the data samples do not overlap across data owners. [ABSTRACT FROM AUTHOR]

Road accidents cause a large number of public fatalities in developing countries affecting them economically. It has been more than a decade since automobile industries are into developing intelligent vehicles with a major objective of road safety. In order to warn or assist the drivers, various automobile manufacturers have been focusing on developing autonomous or semi-autonomous vehicles, but not much effort has been drawn towards developing the smart infrastructure to supplement the development of intelligent vehicles. This paper proposes a framework for a smart vehicle monitoring system to provide smooth mobility of vehicles using roadside units such as streetlights. Such a system aims to eliminate the necessity of equipping each vehicle with smart sensors, which is typically an expensive scheme in most of the developing and underdeveloped countries around the world. This paper attempts to approach the problem of vehicle collision prediction by designing the system based on the concepts from science and engineering such as relative motion and vectors and implementing it using a machine learning-based model. These concepts led to the generation of datasets over which the prediction model was trained. The performance of the proposed model has been simulated using the software - Virtual Crash. [ABSTRACT FROM AUTHOR]

Surface roughness prediction is important for polishing with high production efficiency and low cost since it can reduce the time required for trials and testing. Although many prediction methods have been proposed, there are no studies focusing on the surface roughness prediction in multi-jet polishing (MJP) process. This paper presents the development of a robust surface roughness prediction model based on ensemble learning with a genetic algorithm (ELGA), that can be used for the prediction of surface roughness in the MJP of 3D-printed 316L stainless steel. This paper firstly provides a brief review of the current status of the surface roughness prediction method. Then the development of the ELGA surface roughness prediction model is introduced in detail, which consists of four modules, namely pre-processing module, multi-algorithm regression module, GA module and ensemble module. After that, a series of MJP experiments on 316L stainless steel are conducted to test the effectiveness of the proposed ELGA method. Moreover, the ELGA is compared with six other machine learning-based surface roughness prediction models based on the experiment results. Comparison results show that ELGA model yields the lowest average MAE for the surface roughness prediction in MJP. [ABSTRACT FROM AUTHOR]

This paper considers a new adaptive-critic optimal output regulation scheme for continuous-time general linear systems with unknown dynamics and unmeasurable disturbance. The objective of researching the optimal output regulation problem is pursuing the stability of the closed-loop system while enabling the output to optimally track the reference signal with disturbance rejection. The problem is solved by employing an approximate optimal regulator that consist of optimal feedback control obtained by a data-driven learning algorithm and optimal feedforward control achieved by solving regulator equation. The missing system matrices of the plant are exactly figured out by employing state/input data. Moreover, by employing the minimal polynomial of the exosystem matrix, the parameter of interference in the output equation is available. Then, a predefined cost function is presented based on the regulator equation that aims to design the optimal control law. The stability analysis demonstrate that the presented control scheme can stabilize the closed-loop system, meanwhile the output asymptotically tracks the reference signal. Finally, the effectiveness of the developed optimal control scheme is validated through an application towards the drum water level control of boiler-turbine systems. • The approach proposed in this paper no longer require the state equation of BTS. • Achieving output regulation for model-free system with unmeasurable disturbance. • The first trial integrating output regulation and ACDs for water level control in BTS. [ABSTRACT FROM AUTHOR]

• IoT and machine learning promote soil moisture forecast for smart irrigation. • Our approach is fully data-driven and independent of domain-knowledge features. • Results come from twelve fields on four farms, from eight crop types in four years. • Boosting outperforms neural networks, and blended models improve performance. • Poor data quality is a challenge for machine learning soil moisture forecast. The rise of the Internet of Things allowed higher spatial–temporal resolution soil moisture data captured through in situ sensing. Such abundance of data enables machine learning-based soil moisture forecast as an alternative to traditional mechanistic approaches for irrigation water need estimation. This paper develops a guideline for soil moisture forecast modeling based on machine learning, tested in a real case analysis comprehending eight crop types in twelve fields from four farms distributed over diverse climatic scenarios in Brazil. Instead of a single value, we predict the following days' minimum and maximum values as targets to monitor risks of extreme soil moisture values. Furthermore, modeling soil moisture directly in volumetric water content (VWC) is better than modeling soil matric potential (SMP) to later convert in soil moisture VWC. We test several algorithms and find out that LightGBM outperforms linear regression, decision tree, random forest, multilayer perceptron, LSTM, and StemGNN. Also, blending predictions via algorithm ensemble provides an additional accuracy gain. For model training and accuracy measurement, we use weighted datasets to privilege rare but critical data points. We show that soil moisture forecast reaches its maximum performance considering only past soil moisture, a context-aware index, and a precipitation forecast. Finally, we demonstrate that traditional domain-knowledge features - such as evapotranspiration, crop phenology, and soil hydraulic behavior - are not relevant to improving SM forecast performance. Consequently, our paper suggests full data-driven approaches for irrigation water need estimation, observed some care regarding data quality. [ABSTRACT FROM AUTHOR]

Based on environmental and species monitoring data, Species Distribution Modelling (SDM) tries to build a model to predict the distribution of a species across a geographic area. These models can then be used to manage the activities in the area in order to prevent negative economic and environmental impacts. In marine ecosystems, SDM can be used to regulate fishing practices or manage protected areas. This paper presents DeepData, a new no-code web-based machine learning platform to facilitate the work of marine biologists with SDM. The DeepData tool enables to automate SDM, by automating the creation and validation of the model by marine biologists. Biologists mostly use probabilistic algorithms, such as maximum entropy, generalized linear models and generalized additive models. The DeepData tool also allows the use of machine learning algorithms, such as classification and regression trees, random forests and support vector machines. Moreover, besides the usage of machine learning algorithms, other steps in SDM, such as data preparation and model evaluation, are also discussed in the paper. Furthermore, a concrete explanation of the use of the DeepData tool is presented, as well as the details of implementation and evaluation. • DeepData is a species distribution model web-based tool for model simulation. • DeepData allows the use of various statistical and machine learning models. • DeepData models' parameters can be specified by the user. • DeepData allows the user to insert its own species and environmental data. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is fast becoming a general purpose technology with outstanding impacts in industries worldwide, thus supporting the Industry 4.0 revolution. In particular, the energy sector is one of those that has taken more advantages from the implementation of AI approaches, especially Machine Learning models, for several applications, including energy performance benchmarking of buildings. However, the black-box approach could lead to a lack of result interpretability thus preventing the effective application of AI in some real-world scenarios. For this reason, eXplainable Artificial Intelligence (XAI) tools can be effectively embedded within an AI-based Energy Analytics methodology in order to enhance the explainability of the model results. In this paper, we propose an explainable AI-based benchmarking framework for estimating the membership to specific energy performance classes of a large set of Energy Performance Certificates (EPCs) of flats. The classification is obtained by leveraging different black-box classifiers characterized by high accuracy, yet their inference mechanism is not human-readable. Therefore, a generalizable XAI methodology, based on the combination of a local explainer together with a clustering algorithm, is employed to explain the model results and causal effects between the predictors and target variable to better understand the model behaviour, and the motivations behind correct and wrong performed classifications. The paper provides a general methodological approach capable to exploit a limited number of instances to extract, explain and interpret inference mechanisms learnt by the model that are useful for the end-user. The framework was tested on about 100,000 EPCs of flats located in Italy. • A data-driven benchmarking process of building energy performance is proposed. • A set of about 100,000 energy performance certificates of buildings is analysed. • Five classification algorithms are considered for developing the benchmarking tool. • Clustering analysis and XAI are coupled for extracting human-readable patterns. • Classification results are explained for understanding the model behaviour. [ABSTRACT FROM AUTHOR]

• Developing four crowd datasets (SIMCD) that represent two major crowd scenarios. • Proposing level of crowdedness and severity level features for model evaluation. • Introducing a workflow for crowd dataset generation using MassMotion. • Identifying lack of real and synthetic crowd datasets for anomaly detection. Smart Crowd management (SCM) solutions can mitigate overcrowding disasters by implementing efficient crowd learning models that can anticipate critical crowd conditions and potential catastrophes. Developing an SCM solution involves monitoring crowds and modelling their dynamics. Crowd monitoring produces vast amounts of data, with features such as densities and speeds, which are essential for training and evaluating crowd learning models. By and large, crowd datasets can be classified as real (e.g., real monitoring of crowds) or synthetic (e.g., simulation of crowds). Using real crowd datasets can produce effective and reliable crowd learning models. However, acquiring real crowd data faces several challenges, including the expensive installation of a sensory infrastructure, the data pre-processing costs and the lack of real datasets that cover particular crowd scenarios. Consequently, crowd management literature has adopted simulation tools for generating synthetic datasets to overcome the challenges associated with their real counterparts. The majority of existing datasets, whether real or synthetic, can be used for crowd counting applications or analysing the activities of individuals rather than collective crowd behaviour. Accordingly, this paper demonstrates the process of generating bespoke synthetic crowd datasets that can be used for crowd anomaly detection and prediction, using the MassMotion crowd simulator. The developed datasets present two types of crowd anomalies; namely, high densities and contra-flow walking direction. These datasets are: SIMulated Crowd Data (SIMCD)-Single Anomaly and SIMCD-Multiple Anomalies for anomaly detection tasks, besides two SIMCD-Prediction datasets for crowd prediction tasks. Furthermore, the paper demonstrates the data preparation (pre-processing) process by aggregating the data and proposing new essential features, such as the level of crowdedness and the crowd severity level, that are useful for developing crowd prediction and anomaly detection models. [ABSTRACT FROM AUTHOR]

Drug design is a research process with a goal of creating a chemical drug to produce the desired biological effect. Because of the long time and the high cost issues associated with traditional drug discovery, there is a need to develop new techniques and strategies to increase the diminishing effectiveness of traditional approaches. Ligand-Based Virtual Screening (LBVS) plays a vital role in the early stage of the drug discovery. It could constitute a possible solution to solve the time and cost problems. Subsequently, the researchers are looking for new methods to find new active compounds and bring them to market in a short time. LBVS can be enhanced by different methods and strategies such as Machine Learning and Deep Learning. In this paper, a Deep Convolutional Neural Network method is proposed to enhance the performances of Ligand-Based Virtual Screening process (DCNNLB). Two main contributions are presented in this paper, The first contribution consists of designing a model based on Deep Convolutional Neural Network (DCNN) for LBVS. We propose several topological network models to find the one that gives the best performance such as accuracy and recall. For this, many network topology configurations have been proposed, and a variety of parameters have been taken into account. Furthermore, our proposed model is trained on all compounds of all activity classes of the Drug Data Report Database (MDDR). Thus, it presented a mean accuracy of 0.98 for all three MDDR Datasets. The second contribution is to generate a new learning representation in order to better represent chemical compound. This representation is based on the extraction of the automatic features learning from the weights of our proposed model. Consequently, it is very efficient in calculating molecular similarity and performances of the LBVS process. The obtained results with the three different datasets drawn from the MDDR and the performance evaluation with ANOVA test, have proved the superiority in performance of our proposed method compared to the different conventional methods. [Display omitted] • New molecular representations obtained by the proposed deep convolutional model. • Enhancement in effectiveness of similarity searching with DCNNLB method in LBVS. • Decreasing in training time by using the molecular learning representation. • The proposed DCNNLB method significantly outperforms the conventional TAN method. [ABSTRACT FROM AUTHOR]

• A embedding method MAHE-IM for IM on heterogeneous network. • MAHE-IM extracts and aggregates multiple heterogeneous relationships. • Eight network embedding and seven GNN methods extended for IM. • MAHE-IM outperforms eighteen state-of-the-art algorithms. • A web server (https://mahe-im.com/) is developed for maximizing user convenience. Influence maximization (IM), as an essential problem in social network analysis, can identify a minimum group of the influential nodes to maximize the spread of information on the network. The majority of IM studies focus on homogeneous networks, whereas in real world, heterogeneous networks are ubiquitous. The existing IM methods based on homogeneous networks do not consider a variety of complex heterogeneous relationships and the attribute of different types of nodes, which don't accommodate most real scenario. It is of great significance to study IM methods based on heterogeneous networks, where efficient integrating complex multiple semantic relationships and structures embedded in the heterogeneous network is the key breakthrough point. In this paper, a novel deep learning algorithm for influence maximization on heterogeneous networks based on a multiple aggregation of heterogeneous relation embedding named MAHE-IM is proposed, which can capture the heterogeneous high-order structure and semantic features of heterogeneous information networks. For more comprehensive and systematical evaluation of MAHE-IM, we further extend fourteen state-of-the-art homogeneous and heterogeneous network embedding and graph neural network methods for IM problem and propose fourteen extented IM algorithms. Four popular IM algorithms and our extended fourteen IM algorithms are taken as eighteen baseline algorithms, which can be categorized three types: greedy-based, network embedding-based and GNN-based IM algorithms. Compared with eighteen baseline algorithms, the experimental results illustrate that MAHE-IM is significantly efficient and effective. MAHE-IM is more practical on heterogeneous networks. In addition, in order to maximize the convenience for users, a webserver (https://mahe-im.com/) is developed. The users can obtain the IM results by submitting their heterogeneous networks to the webserver. The corresponding source code and used data in this paper can also be available at https://mahe-im.com/ and https://codeocean.com/capsule/4091031/tree/v1. [ABSTRACT FROM AUTHOR]

Recently, the energy issue is an important factor all over the world due to the fact of sustainability perspective. This paper has proposed a new Transfer Learning (TL) based PV energy yield model, which generalizes the knowledge transfer process from the source domain to the target domain differ on time and location. The solar power yield forecasting highly depends on meteorological data, which has high variability influenced by both time and target place/location. Therefore, a solar energy forecasting model from a source may not perform well to a target domain due to differences in the data distribution as evident by the experiment result presented in this paper. The extended historical data-driven solar power yield models may perform better to a certain extent with the complex nonlinear meteorological data relationships. But due to rapid climate change issue, the knowledge learned from historical data may not apply to the near future. Furthermore, it is impractical to assume the availability of a large dataset and ignore the probability of negative knowledge transfer tendency of traditional regression models. To address this gap, this paper has proposed Transfer Support Vector Regression (Tr-SVR) that uses a novel weighting model based on patterns of a hybrid dataset, both source and target data for training. The proposed Tr-SVR only transfer the knowledge fits the target domain to reduce negative transfer and dependency on long historical data. The experimental results show that when the distribution of training and test data differs, the traditional machine learning method represented by ANN may face serious generalization challenges. In this scenario, the proposed Tr-SVR model has clear advantages in terms of error metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Maximum error, Mean Absolute Percentage Error (MAPE), and Sum of Squares of the Error (SSE). • A novel weighting technique for support vector machine to reduce negative transfer. • Proposed a Transfer Support Vector Regression (Tr-SVR) model powered by weighted-SVM. • Validated the proposed model both theoretically and empirically using four datasets. • Presented a comparative study between the proposed model with baseline models. [ABSTRACT FROM AUTHOR]

• Showed the feasibility of identifying health condition in drivers by monitoring their actions. • Built model of driver behavior through machine learning from observation. • Falconet system employs Neuroevolution and Particle Swarm Optimization to build model. This paper describes our investigation to determine whether undesirable health conditions of an automobile driver can be identified in real time solely by monitoring and assessing his/her driving behavior. The concept has great potential to reduce the accident rate on roadways, especially for young inexperienced drivers who may be suffering from chronic health conditions that when uncontrolled, can result in dangerous driving actions. Our approach involves building models of "normal" and "abnormal" driving by an individual through machine learning from observation (MLfO, or simply LfO). Conceptually, discrepancies between actual driving actions taken by a driver in real time and the actions prescribed by a model of her/his normal driving, and/or similarities to a model of his/her abnormal driving, could indicate a dangerous medical condition. If appropriate, the system could alert the driver and/or the appropriate authorities (e.g., EMTs, police, or parents if a minor) of the potential for danger. More specifically, our research created models of human driving through the use of an LfO system developed previously in our laboratory called Force-feedback Approach to Learning from Coaching and Observation with Natural and Experiential Training (Falconet). Time-stamped traces of actions taken by 12 human test subjects in a driving simulator were collected and used to create the models of human driving behavior through Falconet. Then the overall actions prescribed by the models (called the agents) were compared to the original traces to ascertain whether similarities and/or differences between the human test subject behaviors and the agent behaviors could be indicative of the target conditions. In our use case presented here, the target condition was Attention Deficit/Hyperactivity Disorder (ADHD), a condition that afflicts many driving age teenagers and which can be detrimental to safe driving when not under control through medication. The work described in this paper is exploratory in nature, with the objective of showing scientific feasibility. The results of extensive testing indicate that the agents created with the Falconet system produced promising results, being able to correctly characterize traces in up to nearly 82% of the test cases presented. Nevertheless, as is typical in such exploratory works, we found that much further work remains to be done before this concept becomes ready for commercial application. In this paper we describe the approach taken, the agents created and the extensive quantitative experiments conducted, as well as any insights learned. Areas of further research are also identified and discussed. [ABSTRACT FROM AUTHOR]

Finding a more efficient trading strategy has always been one of the main concerns in financial market trading. In order to create trading strategies that lead to higher profits, historical data must be used. Due to a large amount of financial data and various factors affecting them, algorithmic trading and, more recently, artificial intelligence are employed to overcome the decision-making complexity. This paper aims to introduce a new approach using Twin-Delayed DDPG (TD3) and the daily close price to create a trading strategy. As a continuous action space deep reinforcement learning algorithm, in contrast to the discrete ones, the TD3 provides us with both the number of trading shares and the trading positions. In order to evaluate the performance of the proposed algorithm, the comparison results of our approach and other commonly-used algorithms such as technical analysis, reinforcement learning, supervised learning, stochastic strategies, and deterministic strategies are reported. By employing both position and the number of trading shares, we show that the performance of a trading strategy can be improved in terms of Return and Sharpe ratio. • Proposing an autonomous trading algorithm. • Providing smart trading capability in stock markets. • Employing a continuous action space DRL model. • Facilitating Money management. [ABSTRACT FROM AUTHOR]

Most intracellular activities of living organisms are performed by proteins that have unique and complex 3-Dimensional (3D) structures, playing very important roles in their operations. Due to importance and challenges of predicting 3D structures for proteins, laboratory methods with limitations such as time consuming and high cost have been developed. Computational methods use a sequence of amino acids to obtain the 3D structure. They encounter with a nondeterministic problem having polynomial completion time (NP-Complete problem); with a chain of amino acids as input, and a protein, with 3D structure, as output. In this paper, a new population-based algorithm, under Predatory Search Strategy-Particle Swarm Optimization (PSS-PSO) framework, is presented for predicting the 3D structure; using Hydrophobic-Polar (HP) model on Face-Centered Cubic (FCC) lattice. In this approach, name TRL-PSSPSO, two new moves are proposed to direct each solution toward the native structure: Local Move for reaching a dense hydrophobic core and large H-H contacts and Meta Move for reaching optimal structure, by using Transfer learning. Two datasets are considered for evaluating and the results on some set of standard protein benchmarks show outperforming the state-of-the-art approaches. They show that the proposed approach can improve the accuracy of template-free prediction in an acceptable manner. [ABSTRACT FROM AUTHOR]

As an epigenetic modification that plays an important role in modifying gene function and controlling gene expression during cell development, DNA N4-methylcytosine (4mC) is still lack of researching. It is therefore necessary to accurately predict the 4mC sites to make fully aware of its mechanism and function. In this paper, we propose a novel model which is called Structural Sparse Regularized Random Vector Functional Link Network (SSR-RVFL) for predicting 4mC sites. Compared with other state-of-the-art methods, SSR-RVFL performs better and achieves higher prediction accuracy. There are total six benchmark datasets used in the experiments, namely C. e l e g a n s , D. e l a n o g a s t e r , E. c o l i , A. t h a l i a n a G. s u b t e r r a n e u s and G. p i c k e r i n g i i. Our model improves the accuracy by 0.42%, 0.45%, 0.48%, 0.91%, 0.66% and 0.7% on these six benchmark datasets respectively, so it can be regarded as a more effective prediction tool. • Structural Sparse Regularized Random Vector Functional Link Network (SSR-RVFL) is proposed for predicting 4mC sites. • SSR-RVFL performs better and achieves higher prediction accuracy than state-of-the-art methods. • An efficient iterative solution method for the proposed algorithm is provided. [ABSTRACT FROM AUTHOR]

With the ongoing digitization of the manufacturing industry and the ability to bring together data from specific manufacturing processes, there is enormous potential to use machine learning (ML) techniques to improve such processes. In this context, the competitive automotive industry can take advantage of the ML power by predicting defects before they occur, aiming to reduce the scrap rate and increase the robustness and reliability of the production processes. In a real world scenario, small and medium size companies do not have the amount of data the big companies have, which can prevent the usage of ML models in this vital niche for the industry. A collaboration in terms of data usage to develop powerful and general industry solutions is hindered by data privacy concerns despite similar problems. This paper addresses these concerns by providing a framework based on the Federated Learning (FL) method combined with Digital Envelopes (DE) to allow the ML models training while keeping the data of the partners and the models parameters private and protected against external cyber-attacks, which is one of the weaknesses of FL as of now. A case study was carried out to demonstrate the effectiveness of the proposed framework on handling data poisoning attacks to the training data and also the models' weights. • Data poisoning disrupt the performance of the standard Federated Learning method. • The model performance drops consistently with the amount of poisoned data. • SecFL correctly identified malicious data and performed the defined action point. • SecFL achieved performance was very good and comparable with the baseline numbers. • SecFL assures data integrity, confidentiality, non-repudiation, and authenticity. [ABSTRACT FROM AUTHOR]

• Develop a novel two-layer coordinated multi-agent reinforcement learning algorithm. • Synergize traffic signals through local cooperation and global coordination. • Optimization of vehicle emissions and traffic congestion as simultaneous goals. • Proposed method is performed in synthetic network and Cologne urban network on SUMO. Intersection traffic signal control considering vehicle emissions has become an important topic, however, the decision complexity of traffic signal control increases dramatically in a dynamic traffic environment with multi-intersections. It is a severe challenge to coordinate traffic signals at multi-intersections based on Internet of Things information to improve the traffic condition of the road network. This paper proposes a two-layer coordination algorithm based on multi-agent reinforcement learning—Multi-agent Coordinated Policy Optimization (MACoPO), for solving traffic signal control at multi-intersections. MACoPO consists of local cooperation, which adjusts the weights of individual rewards and neighborhood agents' rewards by using local cooperation factors (LCF), and global coordination, which updates the LCF to maximize global rewards. The state and reward functions are designed in terms of the current state of the signal, waiting queue length, vehicle density and emission concentration in the lane, vehicle delay, and vehicle emissions, thus making full use of the intersection state information. The proposed method is extensively assessed through simulation experiments using artificial and real road networks and the numerical results confirm its effectiveness in complex and dynamic real-time traffic environments with multi-intersections. [ABSTRACT FROM AUTHOR]

Visibility in foggy weather is of great value for traffic management and pollution monitoring. However, vision-based fog visibility estimation methods are usually based on a single image to approximate the visibility in foggy weather, and most existing data-driven machine learning models struggle to capture effective features and achieve high estimation accuracy due to the severe image degradation caused by reduced visibility and lack of real scene images. Therefore, this paper proposes a novel deep learning framework based on multi visual feature fusion for fog visibility estimation, named VENet, which comprises of two subtask networks (for fog level classification and fog visibility estimation) constructed in a cascade structure. A special feature extractor and an anchor-based regression method (ARM) are proposed to help improve the accuracy. Further, a standard Fog Visibility Estimation Image (FVEI) dataset containing 15,000 images of real fog scenes is established. This dataset greatly bridges the lack of suitable data in the field of vision-based visibility estimation. Extensive experiments have been conducted to demonstrate the performance of the proposed VENet, where the error of fog visibility estimation is less than 5% at 500 m and the fog level classification accuracy is at least 92.3%. In addition, the proposed VENet has been applied on Yunnan Xiangli and Mazhao Expressway surveillance with promising performance in practice. [ABSTRACT FROM AUTHOR]

Causal machine learning (ML) algorithms recover graphical structures that tell us something about cause-and-effect relationships. The causal representation provided by these algorithms enables transparency and explainability, which is necessary for decision making in critical real-world problems. Yet, causal ML has had limited impact in practice compared to associational ML. This paper investigates the challenges of causal ML with application to COVID-19 UK pandemic data. We collate data from various public sources and investigate what the various structure learning algorithms learn from these data. We explore the impact of different data formats on algorithms spanning different classes of learning, and assess the results produced by each algorithm, and groups of algorithms, in terms of graphical structure, model dimensionality, sensitivity analysis, confounding variables, predictive and interventional inference. We use these results to highlight open problems in causal structure learning and directions for future research. To facilitate future work, we make all graphs, models, data sets, and source code publicly available online. [ABSTRACT FROM AUTHOR]

Stock forecasting plays a pivotal role in time series forecasting as it enables informed and effective investment decisions by minimizing risks. In this paper, a novel hybrid model for stock price forecasting is proposed to explore the impact of a decomposition-reconstruction method fused with machine learning models, aiming to enhance the predictive ability of the model. Following the decomposition-prediction-reconstruction principle, the hybrid model incorporates wavelet transform, integrating Encoder Forest (EF) with Informer. To mitigate the influence of long-time series noise on stock forecasting, the original data is decomposed into high-frequency signal components (CD) and low-frequency signal components (CA). The Informer and Encoder Forest are trained to predict the future CA and CD, respectively. The hybrid model is implemented for all stocks in three industries of the china stock market. Several models including MLP, RNN, LSTM, Informer, WT + RNN + DT, WT + LSTM + RF, EMD + Informer + EF, VMD + Informer + EF, CEEMD + Informer + EF, and CEEMDAN + Informer + EF are designed as compared methods to verify the superiority and advancement of the proposed technique. Evaluating the performance of individual models reveals that the prediction accuracy follows the ranking: MLP < RNN < LSTM < Informer. Comparing the results of the hybrid model with those of the individual models demonstrates that the hybrid model improves prediction accuracy. This comparison also indicates that the wavelet transform and tree models can enhance the accuracy of the model without altering the initial ranking of the prediction effect. It is worth noting that WT and EMD-like methods employ different data decomposition approaches, leading to diverse outcomes. Experimental results indicate that WT is better suited for a hybrid model that combines two distinct methods. All experimental results indicated that the proposed hybrid model has higher prediction accuracy, stronger generalization ability, and stronger practicability, which is more suitable for Stock forecasting problems. [ABSTRACT FROM AUTHOR]

[Display omitted] Combustible gas is widely used in industry and daily life but presents an unavoidable explosion hazard. Predicting explosion overpressure and guiding engineering design is an effective way to reduce the consequences of explosions. This paper presents a novel approach that integrates explosive theory and data science. Starting from the first principle, a dimensionless mathematical formula was constructed based on the explosive theory. Gas species, gas concentration, container parameters, and ignition position were fully considered by the formula, and built into data sets using machine learning techniques as characteristic parameters. The SVR algorithm, the BP algorithm, and the DNN algorithm all attest to the superiority. And the predictive physical consistency of this method has been proven. Simultaneously, the dataset constructed by this method effectively reduces the number of features. The PSO algorithm was used for parameter optimization based on the DNN algorithm guided by theory for building F-P (First principle) PSO-DNN Model. In the comparison of prediction results, the mean relative error of the F-P PSO-DNN model is 15%, 19% lower than that of the best performing Molkov model. [ABSTRACT FROM AUTHOR]

• A class incremental learning framework is proposed for open sets. • The framework is implemented based on multiple one-class classifiers (OCCs). • An improved deep SVDD is proposed as the basic OCC of the framework. • Several tricks (e.g., feature fusion, band attention) are used to improve OCC. • HSI combined with this method has broad application prospects in seed industry. Rapid and non-destructive classification of seed varieties is one of the important goals pursued by modern seed industry. Due to the large number of maize varieties in practice, collecting training samples that exhaust all varieties to train a classifier is extremely difficult. Therefore, maize seed classification in the real world faces the challenge of variety renewal and rejection of unknown varieties. This paper proposes an end-to-end trainable incremental learning (IL) framework based on hypercube data. This method achieves class-IL via learning one-class classifier (OCC) incrementally, and directly uses raw data as input without additional data preprocessing and feature extraction. The OCC is a dual deep support vector data description, which makes full use of spectral and spatial information to establish an exclusive hypersphere for a specific variety to receive the variety and reject unknown varieties. To remove the interference of redundant bands, a band attention and sparse constraint module is added to automatically assign the weights of redundant bands to zero, thereby maximally improving the performance of the model. Moreover, a new loss function is defined to alleviate the difficulty of parameter updating after sparse constraint. Experimental results on our open set indicate that the accuracy of the proposed method for receiving known varieties and rejecting unknown varieties are both above 91 %, which has significant advantages over the other two state-of-the-art IL methods. In the future, the corresponding OCCs can also be deleted from the whole framework according to the varieties eliminated by the government to reduce computational overhead and inter-class interference. Overall, the proposed method can perform both IL and open set recognition. [ABSTRACT FROM AUTHOR]

Recent regulations concerning the Right to be Forgotten have greatly influenced the operation of recommender systems, because users now have the right to withdraw their private data. Besides simply deleting the target data in the database, unlearning the associated data lineage e.g., the learned personal features and preferences in the model, is also necessary for data withdrawal. Existing unlearning methods are mainly devised for generalized machine learning models in classification tasks. In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i.e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items. To tackle the above issues, we propose a highly efficient recommendation unlearning method based on Selective and Collaborative Influence Function (SCIF). Our proposed method can (i) avoid any kind of retraining which is computationally prohibitive for large-scale systems, (ii) further enhance efficiency by selectively updating user embedding and (iii) preserve the collaboration across the remaining users and items. Furthermore, in order to evaluate the unlearning completeness, we define a Membership Inference Oracle (MIO) that verifies whether the unlearned data points were part of the model's training set, thereby determining if a data point was completely unlearned. Extensive experiments on two benchmark datasets demonstrate that our proposed method can not only greatly enhance unlearning efficiency, but also achieve adequate unlearning completeness. More importantly, our proposed method outperforms the State-Of-The-Art (SOTA) unlearning method regarding comprehensive recommendation metrics. • We propose a highly-efficient recommendation unlearning method. • The proposed method greatly improves both unlearning efficiency and model utility. • We define a membership inference oracle to evaluate unlearning completeness. • Experiments show that the proposed method outperforms the competing methods. [ABSTRACT FROM AUTHOR]

The continuous malicious software (malware) attacks on smartphones pose a serious threat to the security of users, especially the dominant platform Android. Data-driven methods based on machine learning algorithms are a promising way to defend against that. In this paper, we explore the limitations of this kind of methods in improving the performance of malware detection, e.g., considering each feature in isolation and relying on balanced class data, and propose a multi-model ensemble framework MEFDroid by combining individual predictors, where hybrid deep learning based feature extraction methods are adopted to learn meaningful features from raw data. Besides, a novel fusion scheme is exploited to fuse multi-level representations and mine their correlations to maximize the utilization of original information. To evaluate the effectiveness of the MEFDroid framework, we conduct a step-by-step model justification experiment to investigate how the proposed algorithms (i.e., ESAES, EDAES and EDAFS) enhance the malware detection performance gradually. We also compare the proposed algorithms with classical machine learning methods, conventional sampling solutions for the imbalance problem. Besides, we investigate the reliability of our proposed methods using another public dataset. Our extensive experimental results demonstrate that the target model EDAFS in MEFDroid outperforms others in terms of most metrics, which means that it is an effective alternative solution to detect Android malware. [ABSTRACT FROM AUTHOR]