Search

This paper proposes a new method to estimate behavioural curves from Near-Infra-Red (NIR) iris images for classifying Fitness for Duty using a biometric capture device. Fitness for Duty (FFD) techniques detect whether a subject is Fit to safely perform a given task, which means no reduced alertness condition and security, or the subject is unfit, that could impact a reduced alertness condition by sleepiness or consumption of alcohol and drugs. The analysis showed essential differences in pupil and iris behaviour to classify the workers in "Fit" or "Unfit" conditions. The best results can distinguish subjects robustly under alcohol, drug consumption, and sleep conditions. The Multi-Layer-Perceptron and Gradient Boosted Machine reached the best results in all groups with an overall accuracy for Fit and Unfit classes of 74.0% and 75.5%, respectively. These results open a new application for iris capture devices. • This work is a step forward in Iris biometric applications. • This research proposes a new database and method to detect Fitness for Duty. • This paper proposes a new method to estimate behavioural curves from iris images • Fitness for Duty allows us to detect Fit/Unfit subjects and save lives • This method classifies alcohol, drug, and sleepiness using an iris image. [ABSTRACT FROM AUTHOR]

• A feature selection method based on binary dandelion algorithm is proposed. • The algorithm applies a sine-cosine operator and a restart strategy. • Mutual information and quick bit mutation improve the performance of the algorithm. • The algorithm performs well on datasets with larger dimensions. Feature selection (FS) is an important data preprocessing technology for machine learning and data mining. Metaheuristic algorithm (MH) has been widely used in feature selection because of its powerful search function. This paper presents an improved Binary Dandelion Algorithm using Sine Cosine operator and Restart strategy (SCRBDA) for feature selection. First, the sine cosine operator is used in the radius formula of the core dandelions (CD), which significantly enhances the ability of algorithm development and exploration. Secondly, the algorithm uses a restart strategy to increase its ability to get rid of local optimum. Thirdly, mutual information is used to guide the generation of some dandelions, which pays more attention to the correlation between the selected features and categories. Finally, quick bit mutation is used as the mutation strategy to improve the diversity of the population. The SCRBDA proposed in this paper was tested on 18 datasets of different sizes from UCI machine learning database. The SCRBDA was compared with 8 other classical feature selection algorithms, and the performance of the proposed algorithm was evaluated through feature subset size, classification accuracy, fitness value, and F1-score. The experimental results show that SCRBDA achieves the best performance, which has stronger feature reduction ability and achieves better overall performance on most datasets. Especially on large-scale datasets, SCRBDA can obtain extremely smaller feature subsets while maintaining much higher classification accuracy, and satisfactory F1-score. [ABSTRACT FROM AUTHOR]

Intelligent Fault-Tolerant Control (IFTC) refers to the applications of machine learning algorithms for fault diagnosis and design of Fault-Tolerant Control (FTC). The overall goal of the FTC is to accommodate defects in the system components while they are in use and maintain stability with little to no performance reduction. These systems are crucial for mission-critical and safety-related applications where the safety of people is at stake and service continuity is crucial. In this review paper, a systematic study has been done for the development of FTC with machine learning, deep learning, and transfer learning algorithms. The challenges and limitations faced with their possible solutions through machine learning theories for the IFTC model are lined up. This paper guides researchers on the different possible types of machine learning algorithms and their advanced forms like deep learning and transfer learning. The differences among these are highlighted by the challenges and limitations of each. The paper is significant such that most of the important literature references from the Scopus database particularly related to important electrical and mechanical industrial problems have been discussed to guide the researchers who want to apply IFTC for specific industrial problems, being the research gap. Finally, future research directions for the development of IFTC are highlighted. [ABSTRACT FROM AUTHOR]

Identifying the abnormal samples from a data set and determining their type are two key tasks of anomaly detection. However, the existing anomaly detection algorithms are generally faced with the defects of weak generalization ability and insufficient interpretation, the core reason of which is that they cannot mine specific features for different abnormal types. In this paper, a new anomaly detection algorithm aiming at feature selection for different abnormal types is developed. Inspired by self-supervised learning, we take the stationarity of variance changes of abnormal score similarity as a pretext task and combine it with wrapped search method. Then, the features and the corresponding parameters for different abnormal types can be screened to apply to the downstream task of anomaly integration detection. To verify the efficiency of the new algorithm, we conduct two sets of experiments to compare the new algorithm with 11 classical anomaly detection and 3 clustering anomaly detection algorithms on the data sets WDBC, WPBC and Wilt from DAMI database with the evaluation measures P@n , Adj- P@n , AP, Adj-AP and AUC. The experiment results show that, both in the identification and classification on abnormal samples, all performance measures of the new algorithm are explicitly better than that of the contrastive algorithms. Also, we apply the new algorithm to the Chinese auto insurance market, and find that the results can help managers to identify the main patterns of fraudulent claims and to summarize the feature combinations of fraud behaviors. In general, the new algorithm developed in this paper has the following advantages compared with traditional algorithms: 1) It can directly capture abnormal features and realize effective recognition of abnormal types, which effectively bridge the gap between abnormal judgement and feature screening. 2) Automatic screening of abnormal features can be completed under the condition of self-updating learning optimal strategy. 3) Only a few features are extracted from all features to reveal the abnormal characteristics, which significantly improves the interpretability and generalization ability of the algorithm and its results. In a word, through the novel self-supervised design method, feature screening is skillfully integrated into the anomaly detection task, which may provide a new way for anomaly detection research. [ABSTRACT FROM AUTHOR]

Seamless positioning ability has become an essential requirement in large-scale smart city scenes with the development of Artificial Intelligence of Things technology. The performance of seamless positioning is limited by the inaccurate crowdsourced navigation database, cumulative error of built-in sensors, and changeable measurement errors of different location sources. In order to solve these problems, this paper presents the CrowdLOC-S framework, which provides a concrete and accurate indoor/outdoor localization performance using the combination of crowdsourced Wi-Fi fingerprinting, Global Navigation Satellite System (GNSS), and low-cost sensors. A data and model dual-driven based trajectory estimator is developed for improving the long-term positioning performance of built-in sensors, and a hybrid one-dimensional convolutional neural network (1D-CNN), Bi-directional Long Short-Term Memory (Bi-LSTM), and Multilayer Perceptron (MLP) enhanced quality indicator is proposed for quality evaluation of crowdsourced trajectories and further Wi-Fi fingerprinting database construction. Besides, the transfer learning approach is applied in the quality indicator for autonomously predicting the location errors towards different indoor and outdoor location sources and realizing seamless scenes switching. Finally, a unified extended Kalman filter is developed to realize multi-source integration-based seamless localization using the positioning information provided by indoor and outdoor location sources and corresponding quality indicator results. Comprehensive experiments demonstrate that the presented CrowdLOC-S system is proven to realize precise and efficient indoor and outdoor positioning performance in complex and large-scale urban environments. [ABSTRACT FROM AUTHOR]

Emotion assessment is a challenging task in the human–computer interaction interface. Previous studies have examined the relationship between emotion and color, but they fail to accurately analyze emotional semantics due to the numerous elements in human–computer interaction interfaces. As a result, a combination model of a backpropagation neural network (BPNN) and an artificial bee colony algorithm (ABC) was presented in this paper to predict the emotion semantics of the human–computer interaction interface. The mechanism of generating the weights and thresholds for each layer of BPNN was converted to the search for an optimal honey source. Meanwhile, according to experiment results and evaluation of elements in human–computer interaction interfaces, this paper has assessed the relationships amongst the eight key elements (ratio of graphics to text, color difference, color distribution, color harmony, theme style, white space ratio, frame style, number of colors) and emotion word pairs (moderation-fancy, calm-pleasure, confusing-clear, cold-kind, coarse-elegant). Furthermore, an emotion application database was established to determine how the amalgamation of critical elements affects the users' feelings about the human–computer interaction interface to help designers build a user-centric interface. Finally, the database can be applied to relieve mental health problems by meeting the psychological expectations of users as mental healthcare intervention during the COVID-19 pandemic. Also, it can help designers to design a pleasurable visual interaction interface for a particular element to convey health-related information and protective measures. [ABSTRACT FROM AUTHOR]

This paper applies computational linguistics learning methods to the banking industry and climate change fields. We introduce our data-driven framework, climateBUG, with the aim of detecting latent information about how banks discuss their activities related to climate change using natural language processing (NLP). This framework consists of an ingestion pipeline, a configurable database, and a set of API's. In addition, climateBUG offers two standalone components, namely a unique annotated corpus of approximately 1.1M statements from EU banks' annual and sustainability reporting and a deep learning model adapted to the semantics of the corpus. When benchmarking on classification performance, our model outperforms other models with similar scopes due to its stronger domain relevance. We also provide examples of how the framework can be applied from a user perspective. • A data-driven framework to detect qualitative information in banks' annual reporting. • Natural language processing is applied to non-financial reporting and sustainability. • Framework developed with an interdisciplinary approach and relevant domain knowledge. • Framework includes annotated data and learning model as standalone components. [ABSTRACT FROM AUTHOR]

Deep learning-based no-reference image quality assessment (NRIQA) methods have demonstrated advanced performance. In this paper, a deep learning-based NRIQA method with strong error-aware and content-aware capabilities is proposed, which consists of Error-Aware Reconstruction Network (EARNet) module, Content Feature Extraction Network (CFENet) module, and Subjective Quality Regression Network (SQRNet) module. We first build a database to pre-train EARNet to obtain the ability to extract error features. For content features, CFENet pre-trained on large-scale image classification tasks is adopted to extract. The pre-trained EARNet and CFENet are serially connected with SQRNet so that the features received by SQRNet are both error-aware and content-aware. Extensive experimental results show that the proposed method achieves state-of-the-art performance on many well-known IQA databases. The robustness of the proposed method is verified on the large-scale Waterloo Exploration Database (WED), and its superiority is demonstrated by the group maximum differentiated (gMAD) competition game. Furthermore, we also verify that the proposed EARNet is highly extensible, which can further improve the performance of the existing deep learning-based NRIQA method. • A blind image quality assessment method based on deep learning is proposed. • The proposed model has both error and content awareness. • The proposed method has advanced performance and high scalability. • Creatively designed a joint loss to guide the model in generating error maps. [ABSTRACT FROM AUTHOR]

This paper introduces new flexible loss functions for binary classification in Gradient-Boosted Decision Trees (GBDT) that combine Dice-based and cross-entropy-based losses and offer link functions from either a generalized extreme value (GEV) or exponentiated exponential logistic (EEL) distribution. Testing 27 different GBDT models using XGBoost on a Freddie Mac mortgage loan database showed that the choice of the loss function is useful. Specifically, when the class imbalance ratio (IR) is less than 99, using a skewed GEV distribution-based link function in XGBoost enhances discriminatory power and classification accuracy while retaining a simple model structure, which is particularly important in credit scoring applications. In cases where class imbalances are severe, typically between IRs of 99 and 200, we found that an advanced loss function, which is composed of a symmetric hybrid loss function and a link derived from a positively skewed EEL distribution, outperforms other XGBoost variants. Based on our findings, the accuracy improvements of these proposed extensions result in lower misclassification costs, which are especially evident when IR is below 99, which results in higher profitability for the business. Furthermore, the study highlights the transparency associated with GBDT, which is also an integral component of financial applications. Researchers and practitioners can use these insights to create more accurate and discriminative machine learning models, with possible extensions to other GBDT implementations and machine learning techniques that take into account loss functions. The source code for the proposed approach is publicly available at https://github.com/jm-ml/flexible-losses-for-binary-classification-with-GBDT. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is the latest designing and interacting technology used to support organizations in the competitive electronic commerce (E-commerce) context. The studies on AI in E-commerce remain fragmentary since few papers review the evolutionary process of knowledge infrastructure. To bridge this gap, we constructed a conceptual framework from the resource orchestration perspective, and retrieved 2252 documents from the Web of Science (WoS) database dating from 1998 to 2022 to synthesize the extant research on AI in E-commerce. Specifically, we integrated main path analysis with science mapping analysis covering the strategic diagram and evolution map. Through qualitative analysis of critical nodes in main paths, this article found that knowledge disseminated around recommender systems (RSs). This article also examined the performance traits and inter-relationships of significant themes over three consecutive time zones, as well as identified four main AI-enabled outcomes (thematic areas): Optimization and decision support , Trust and personalized recommendation , Sentiment analysis, and AI theories with allied technologies. Potential research prospects and implications are proposed based on these findings. Overall, this article provides state-of-the-art information on how AI can facilitate the implementation of E-commerce operations and could serve as a stepping stone to newcomers in the scientific community. [ABSTRACT FROM AUTHOR]

It is essential to guarantee product quality by detecting defects in industrial printed labels. Defect detection based on reference comparison is a common method to achieve this task. However, this method yields poor performance under large deformations of printed labels, due to the lack of accurate registration ability between testing images and reference images. Therefore, it is an urgent task to achieve accurate image registration for printed label defect detection. In this paper, a coarse-to-fine end-to-end registration network, named APPR-Net, is proposed to deal with the large deformation. First, we adopt a strategy of image patch splitting and stitching to improve the scalability of image resolution. Second, we design a four-stream affine transformation module followed by a multi-scale pyramid registration network, where a coarse registration is obtained by the former module and then gradually refined by the later network in a coarse-to-fine manner. Third, we introduce a distortion loss function to constrain the text distortion of the warped image after image registration. Finally, to simulate printed labels with defects and large deformation, we build a synthetic database based on real-world industrial printed labels for performance comparison. The results demonstrate that the proposed APPR-Net significantly outperforms other compared methods. • Propose a coarse-to-fine registration network to deal with large deformation. • Take advantages of image patch splitting and stitching strategy. • Design a four-stream affine transformation module followed by a pyramid network. • Introduce a distortion loss function to constrain text distortions. • Build a synthetic database based on real-world printed labels. [ABSTRACT FROM AUTHOR]

The study of High-Utility Itemset Mining (HUIM) and Frequent Itemset Mining (FIM) is crucial since it explains consumer behavior and offers actionable advice to improve business results. HUIM algorithms have been successfully established to identify high-utility itemsets, including those with negative utilities. The problem with these approaches is that they presume incorrectly that items with negative utility across transactions would always be losses. Products with positive profitability may seem negative when combined with other items to increase sales or reduce inventory. Using strict upper-bound approaches, this paper presents strategies for making database scanning more efficient and reducing the number of prospective candidates. We also prove that it is correct to use the proposed upper-bounds for pruning on several types of items in the database. Based on all the proposed solutions, we develop a novel algorithm to solve this problem efficiently. To demonstrate their efficiency, the algorithms are tested against states-of-art HUIM algorithm on diverse datasets with regard to size and characteristics with unstable negative profits. [ABSTRACT FROM AUTHOR]

The mining of frequent itemsets and association rules is a core problem in data mining and an essential task in data analysis. In this paper, we present SufRec, a new algorithm for finding frequent itemsets and association rules. We give two versions. In both versions, the mining of the frequent itemsets is decomposed as a sequence of tasks. The first version (the SufRecDep algorithm) proceeds the tasks successively, each one using the results of the previous ones. The second version (the SufRecInd algorithm) performs the tasks independently of each other. Both versions are recursive with respect to the items and have thus the advantage to be particularly efficient for updating the mining process when new items are added to the database or when others are excluded. Moreover, the task-independent processing of SufRecInd makes it very easy to build parallel versions of SufRec. We present two parallel SufRec algorithms. With the first one, P-FIFO-SufRec, the processors perform the tasks according to the order in which the items appear in the database, preserving the recursive nature of SufRec. For second one, P-PAST-SufRec, the set of items is fixed and the tasks are pre-assigned to each processor. In order to evaluate the performance of SufRec, we carry out a consequent experimental study. In particular, we compare its running times with those of well-known parallel and non-parallel frequent itemsets mining algorithms. • Construction of SufRec, a new algorithm for frequent itemsets mining (FIM). • Construction of parallel versions of SufRec algorithm. • Experimental study comparing SufRec with well-known FIM algorithms. • Applications to the case where the list of items changes over time. [ABSTRACT FROM AUTHOR]

Dysarthria is a motor speech disability caused by weak muscles and organs involved in the articulation process, thereby affecting the speech intelligibility of individuals. Because this condition is linked to physical exhaustion disabilities, individuals not only have communication difficulties, but also have difficulty interacting with digital devices. Automatic speech recognition (ASR) makes an important difference for individuals with dysarthria since modern digital devices offer a better interaction medium that enables them to interact with their community and computers. Still, the performance of ASR technologies is poor in recognizing dysarthric speech, particularly for acute dysarthria. Multiple challenges, including dysarthric phoneme inaccuracy and labeling imperfection, are facing dysarthric ASR technologies. This paper proposes a spatio-temporal dysarthric ASR (DASR) system using Spatial Convolutional Neural Network (SCNN) and Multi-Head Attention Transformer (MHAT) to visually extract the speech features, and DASR learns the shapes of phonemes pronounced by dysarthric individuals. This visual DASR feature modeling eliminates phoneme-related challenges. The UA-Speech database is utilized in this paper, including different speakers with different speech intelligibility levels. However, because the proportion of usable speech data to the number of distinctive classes in the UA-speech database was small, the proposed DASR system leverages transfer learning to generate synthetic leverage and visuals. In benchmarking with other DASRs examined in this study, the proposed DASR system outperformed and improved the recognition accuracy for 20.72% of the UA-Speech database. The largest improvements were achieved for very-low (25.75%) and low intelligibility (33.67%). [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 study aims to develop a robotic mood transition for a patient robot with emotional expression abilities in care education. The RU-FEMOIN database is utilized for the emotional expressions of the robot, which contains facial expression images of 41 Japanese people divided into different age groups. The primary objectives of the study are to provide feedback to caregivers to react immediately to the emotions felt by the robot during care training and to establish seamless communication of emotions between caregivers and the robot. This method ensures that the user's emotions are reflected in the robot's emotions, and the robot can express continuous mood transitions. A robot's mood transition is generated based on the user's current facial expression, according to the RU-FEMOIN database, to achieve interaction between the patient robot and caregivers. The study presents an advanced patient robotic system based on human–robot interaction on the CNT using the robot's facial expression method. • The paper presents a system of the robotic mood transition of patient robots. • The objective is to develop the novel database of facial expression in Japanese. • The robotic mood transition can be expressed emotional states in care education. • This system provides facial expression-based feedback for care training. [ABSTRACT FROM AUTHOR]

Integrating disparate and distributed vegetation data is critical for consistent and informed national policy development and management. Australia's National Vegetation Information System (NVIS) under the Department of Climate Change, Energy, the Environment and Water (DCCEEW) is the only nationally consistent vegetation database and hierarchical typology of vegetation types in different locations. Currently, this database employs manual approaches for integrating disparate state and territory datasets which is labour intensive and can be prone to human errors. To cope with the ever-increasing need for up to date vegetation data derived from heterogeneous data sources, a Semi-Automated Hybrid Matcher (SAHM) is proposed in this paper. SAHM utilises both schema level and instance level matching following a two-tier matching framework. A key novel technique in SAHM called Multivariate Statistical Matching is proposed for automated schema scoring which takes advantage of domain knowledge and correlations between attributes to enhance the matching. To verify the effectiveness of the proposed framework, the performance of the individual as well as combined components of SAHM have been evaluated. The empirical evaluation shows the effectiveness of the proposed framework which outperforms existing state of the art methods like Cupid, Coma, Similarity Flooding, Jaccard Leven Matcher, Distribution Based Matcher, and EmbDI. In particular, SAHM achieves between 88% and 100% accuracy with significantly better F1 scores in comparison with state-of-the-art techniques. SAHM is also shown to be several orders of magnitude more efficient than existing techniques. • The Integration of the National vegetation database is key for policy development. • A novel semi-automated hybrid schema matching framework, SAHM is proposed. • SAHM is a two-tiered matching solution that uses schema and instance information. • SAHM yields better schema matching results in comparison with the State-of-the-art. [ABSTRACT FROM AUTHOR]

High utility pattern mining (HUPM) plays a significant role in data mining technologies. Traditional HUPM algorithms may produce a large number of high utility patterns (HUPs) when the database is dense or the data is massive. To address this issue, closed high utility pattern (CHUP) mining was proposed, providing a high-level overview of the HUPs and helpful information for decision-makers. However, CHUPs do not consider the factors of period and recency. Therefore, this paper is the first to introduce period and recency into closed high utility pattern mining and proposes the CPR-Miner algorithm to mine closed periodic recent high utility patterns. These patterns have more practical value since they are closed sets of HUPs. Due to the increasing number of factors to be considered, new upper bounds and pruning strategies are also proposed, significantly improving the algorithm's efficiency. To test the performance of our algorithm and our new pruning strategies, we improved the PHM algorithm to generate the PR-Miner algorithm. Experimental results show a significant efficiency of the new pruning strategies and demonstrate that CPR-Miner outperforms the PR-Miner algorithm in all aspects. • Periodicity and recency are introduced within closed high utility pattern mining. • New data structures are designed to store the utility, period, and recency information. • Novel pruning strategies are proposed to avoid unnecessary list joint operation. • The proposed algorithm gets significant results on several datasets. [ABSTRACT FROM AUTHOR]

With the explosive growth of the medical images, the high-resolution CT image(CI) data is of great value for medical research as well as a clinical diagnosis. Finding CI s similar to the input one from the large- scale CI database can effectively assist physicians to diagnose. The state-of-the-art content-based similarity retrieval of CI s often ignores the effect of image details on retrieval accuracy, and the retrieval accuracy and efficiency are usually not satisfactory. To address this challenge, in this paper, we take lung CI as an example and propose a progressive D etail- C ontent-based S imilarity R etrieval (DCSR) of the lung CI s based on a W eakly S upervised deep L earning N etwork(WSLN) model. Two enabling techniques (i.e., the WSLN model and the DIndex scheme) are proposed to facilitate the DCSR processing of the large lung CI s. The experimental dataset is from three public datasets. Extensive experiments show that the WSLN -based DCSR method is about 45% more effective than the state-of-the-art methods in terms of the mean average precision(MAP). Meanwhile, the retrieval efficiency of the DIndex scheme is about 200% higher than that of sequential retrieval. [ABSTRACT FROM AUTHOR]

A novel lane-changing trajectory control strategy in an iterative learning framework is proposed and its impact on fuel consumption of the off-ramp traffic system is analyzed in this paper. The iterative learning framework includes three layers. In the calibration layer, the lane-changing decision process is modelled by probabilistic neural network while a back-propagation neural network is designed to imitate the lane-changing trajectory. Moreover, we use a cost function and numerical simulation in the optimization layer to optimize the trajectory database and calibrate the proposed framework, respectively. In the application layer, simulation experiments are conducted to examine the fuel consumption of individuals and systems. The results indicate that connected automated vehicles (CAVs) can dissipate quickly after congestion is formed and complete lane-change and avoidance behavior in a more stable state after iterative learning. CAVs can reduce fuel consumption by 35% compared with human-driven vehicles. [ABSTRACT FROM AUTHOR]

This article proposes a novel design methodology for circular concrete-filled steel tubular (CFST) columns, combining a large experimental database, an artificial neural network, and the balancing-composite-motion-optimization algorithm. First, the experimental database consisting of 1245 compression tests was compiled from the available literature, involving five input parameters: cross-sectional outer diameter, thickness of steel tube, length of column, yield strength of steel and cylindrical compressive strength of concrete, and one output variable: the measured axial capacity of columns. Second, the artificial neural network model was trained and validated using that database, in combination with various error measurement criteria: mean-squared-error, mean-absolute-error, and coefficient of determination. The optimization problem to find the optimal design of circular CFST columns was then formulated as a function of material cost and the geometrical parameters of the cross-section. Finally, balancing-composite-motion-optimization was employed to solve the aforementioned nonlinear optimization problem. The proposed model's performance was compared with the widely used standards EC4, AISC, and DBJ, especially for scenarios exceeding the limitations of individual material strengths. Results showed that the proposed equation exhibited the best predictive performance. For practical application, we have derived an explicit prediction equation and implemented it in Excel, a user-friendly interface (the Excel file is appended to this paper). Thus, the proposed method in this study can assist existing codes in finding the optimal design of CFST columns, as the current standards have limitations as to the characteristic strength of the materials. [ABSTRACT FROM AUTHOR]

• Game method is used in interval cross evaluation. • Build a variety of evaluation strategies to linearize the model. • Using entropy theory to aggregate the results of different evaluation strategies. Cross-efficiency evaluation is an effective method for the ranking of decision-making units (DMUs) in data envelopment analysis, which is the performed method for peer-evaluation and self-evaluation. In most cross-efficiency evaluation methods, the peer evaluation result is completely constrained by the evaluator's optimal self-evaluation weights. DMUs are connected by a competitive relationship; therefore, they can be regarded as players in the game and the cross efficiency value can be regarded as payment because of this competition. DMUs need to consider the impact of their own weights on other DMUs to identify a set of weights for evaluating themselves. Based on the idea of non-cooperative games in the cross evaluation of DMUs, this paper considers the interval cross game efficiency of DMUs with the interval data. The interval data theory is combined, the best production state and the worst production state are taken as reference states, and four evaluation strategy models are proposed according to the opposition and coordination relationship. Then, the bijective and injective interval game cross models, as well as the algorithm corresponding to the four evaluation strategies are constructed. Moreover, the result of the self-evaluation is used as the initial parameter to prove the existence of the solution and the convergence of the algorithm. Based on the priority relationship of the evaluation results under different strategies, the interval entropy method is used to aggregate the results and obtain the final cross efficiency of the interval game. Furthermore, both the applicability and superiority of this model are exemplified by an example. Finally, based on the method of this paper, the efficiency of forest carbon sequestration in China are studied, seven natural regions in China are ranked by forest carbon sequestration efficiency values reasonably, and the current regions development of forest carbon sequestration in China are evaluated. [ABSTRACT FROM AUTHOR]

Numerous studies have investigated image classification. In particular, recent methods based on deep learning have exhibited high accuracies. However, various existing state-of-the-art methods based on deep learning show different accuracies depending on the database and environment. Accordingly, different deep learning models need to be used in image classification studies according to the database, environment, and research field. This study investigated a technique to increase the accuracy of the existing deep learning-based models. The proposed method was applied to various existing state-of-the-art methods. In the proposed method, a convolution neural network (CNN) is trained using the classification activation map (CAM) to focus on specific areas in the input image. The CAM image is used as the ground-truth image. Furthermore, the concept of the CAM-based categorical adversarial network (CAM-CAN), in which the CNN is trained based on a generative adversarial network, is proposed in this paper. An action recognition experiment was performed using the self-collected Dongguk thermal image database (DTh-DB) and open database, and the results revealed that the accuracies of the existing state-of-the-art methods significantly increased after applying the proposed method. For instance, the accuracies obtained using the DTh-DB, TPR, PPV, ACC, and F1 with the conventional DenseNet201 model were 80.14%, 75.28%, 96.0%, and 75.91%, respectively. After applying the proposed method, the accuracies increased to 86.53%, 89.90%, 97.64%, and 85.84%, respectively. [ABSTRACT FROM AUTHOR]

• A novel large-scale consensus reaching process framework is proposed. • Integrate decision makers' historical preferences into cluster analysis. • Simulation experiments are designed to show the validity of the framework. In the large-scale group decision making (LSGDM) problems, it is common that some decision makers might refuse to modify their preferences to achieve a consensus or even form an alliance to exhibit non-cooperative behaviors for their own interests. These non-cooperative behaviors might bias or hinder the consensus reaching process (CRP). In this paper, we propose a large-scale consensus model to manage non-cooperative behaviors based on the clustering method using the historical preference data of decision makers. In the proposed framework, all the historical preference data of decision makers are used for clustering to catch their features, by which the decision makers with the three defined non-cooperative behaviors will be more centralized. Then, the clusters with non-cooperative behaviors will be detected better through their preference adjustments. On this basis, the penalty strategy of the decision makers in clusters with non-cooperative behaviors would be more effective. Simulation experiments and comparison studies are presented to demonstrate the validity of the proposed consensus framework against traditional frameworks for coping with non-cooperative behaviors. [ABSTRACT FROM AUTHOR]

Quantile regression neural network (QRNN) model has received wide attentions in recent years to explore complex nonlinear problems. However, when the responses y i are subject to censoring (left censoring, right censoring and interval censoring might occur), predictions by using observed data, will lead to unbelievable results. Thus, new method for QRNN model with censored data is appealing. In this paper, we propose an iterative approach based on the data augmentation method for censored QRNN model estimation. Firstly the censored data are imputed through a data augmentation process, then the QRNN model is updated with the imputed data, finally we make predictions through the updated QRNN model. It is worth mentioning that simulation studies and real data illustrations show the superiority of our proposed method. Using the results based on full uncensored data as the benchmark, we compare the estimation efficiency of the proposed method with the existing ones. Our method outperforms others in terms of quantile loss and prediction interval width, yielding prediction results that are much closer to the benchmark. The proposed estimation method for censored QRNN model can be easily adapted to deal with different censoring types including left censoring, right censoring and interval censoring, remedying the defect that existing method is only suitable for right censoring type. • A novel iterative estimation method for the censored QRNN model is developed. • The proposed method works for any censoring type. • The proposed method can be generally prompted to a universality class. [ABSTRACT FROM AUTHOR]

Driver pathways have been acknowledged to play critical roles in the initiation and progression of cancers►hence it is essential for precision medicine related studies to develop accurate and efficient methods to identify them. Although previous approaches have shown promising results by integrating multi-omics data, their preset artificial parameters may decrease the convenience to use and limit the application scalability. In this paper, a novel integration approach is proposed to incorporate four omics data, i.e., construct a weighted non-binary mutation matrix without presetting artificial parameters. A parameter-free identification model is put forward based on it. It takes advantage of the association between genes in the PPI network as well as balances the contribution of coverage and mutual exclusivity with the harmonic mean. Furthermore, a cooperative co-evolution algorithm is proposed for solving this model. In the algorithm, a particle swarm optimization algorithm suitable for solving combinatorial problems is presented. Three cooperative operators are devised to construct the cooperation among the populations and the swarm to increase the population diversity. Both real biological datasets and simulated ones were exerted to perform experimental comparisons among the proposed method and six other state-of-the-art ones. The gene sets identified by the presented method generally contain more genes involved in known signaling pathways than those obtained by the other methods. Simultaneously, both high accuracy and high efficiency of the proposed method were verified in experiments, making it practical in realistic applications and an effective supplementary tool to identify driver pathways. • A non-binary mutation matrix is constructed without artificial adjustable parameters. • The model incorporates gene association and balances coverage and mutual exclusivity. • A PSO algorithm suitable for solving combinatorial problems is presented. • A co-operative co-evolution algorithm is put forward for solving the presented model. • The performance is compared among the proposed method and seven state of the art ones. [ABSTRACT FROM AUTHOR]

This paper develops smoothing data association based on integrated probabilistic data association (FLIPDA-S) tracker to identify a multicopter UAV (MUAV) and estimate its trajectory in an uncertain and cluttered environment. Recently, a number of unidentified MUAVs have been flown in prohibited airspace and a radar system has been utilized to identify the MUAV and track the trajectory. However, target tracking methods could have difficulties to track the target MUAV through randomly distributed and moving objects. The vehicle state estimation (VSE) algorithm, which utilize FLIPDA-S in this paper, adopts UAV kinematics and dynamics for tracking a UAV in clutter and false targets with significant UAV identification performance. The performance of the method has been validated with and without an initial position of the target MUAV. Both numerical simulation and experiments are demonstrated to verify the effectiveness and accuracy of FLIPDA-S with VSE algorithm to track UAVs in an uncertain and clutter environment. [ABSTRACT FROM AUTHOR]

• A Cat Map Registration process help land use users improve their data sharing and optimize functionalities. • New Paillier Map-based Authentication model which generates minimum block generation time and size. • Blockchain-based cloud environment prevents malicious model to falsely provide the class image data to malicious users. Internet of Things (IoT) is a materializing technology that has considerable technical, social, and economic importance. The present day predictions for the influence of IoT are highly monumental. This is because data of any form is found to be predominant to the IoT paradigm, therefore serving different applications like smart home, smart city, healthcare, smart grid, smart farms, manufacturing, and so on. Hence, several heterogeneous sensors are said in existence to estimate different types of parameters and found to be useful for different users. In this paper, a secured image sharing method called a Blockchain Chaotic and Paillier Map-based Authentication (BC-PMA) to provide image data integrity and security by deploying a cloud computing environment is proposed. The BC-PMA method is split into three sections. First, registration of corresponding classes of images in the cloud server via blockchain is presented by employing the Cat Map Registration model. The second step involves the authentication process carried out by employing Paillier Map-based Authentication where validation is ensured via smart contracts. Finally, upon successful authentication, unique and separate classes of images are provided with the respective, therefore ensuring secured classes of image sharing between users in the cloud environment. The results have been analyzed against traditional blockchain-based methods and validated with enhanced simulated results, that good authentication accuracy, minimizing the false positive rate, block generation time, and size considerably. Experimental Result shows that the Authentication Accuracy of the proposed BC-PMA method is improved by 23%, and minimizes the False Positive Rate and Computational Cost by 32% and 22% when compared to the Existing Method. [ABSTRACT FROM AUTHOR]

For estimation performance ranking, the ranking vector (RV) approach using pairwise comparison information is efficient and processes advanced properties (e,g, homogeneity, invariance, monotonicity, decisiveness, and getting around intransitivity problem). However, the existing RV approach does not use quantity information of comparison and thus may be unreliable for inadequate number of error measures. To address this drawback, we develop two extended versions of the previously proposed RV approach in this paper. The first one focusing on using quantity information is based on a novel data normalization approach named pairwise data normalization. It quantifies the relative distance (goodness) of two elements with respect to a perfect point as the reference. The second version accounts for attribute difference and determines the weights of attributes accordingly. If the data of an error measure are highly different from those of others, this error measure should be weighted more in the performance ranking because it definitely reflects a different performance aspect. We compare different RV approaches, analyze their pros and cons, and discuss how to apply them for different cases. Examples are also provided to illustrate the application of these approaches to estimation performance ranking. • A new data normalization method named pairwise data normalization is proposed. • We propose an extended RV approach by considering the quantity information. • We propose another extended version by considering attributes differences. • We fully compare different RV approaches and analyze their pros and cons. [ABSTRACT FROM AUTHOR]

Person re-identification still facing several challenges related to many factors such as complex poses, occlusion, misalignment and bad detection. Recent works in the literature focus on extracting local information from the human body but most of them rely on full supervision during training. We propose in this paper a new end-to-end trainable neural network, named Attention Dropping Network (ADN), for diverse rich visual cues discovery without extra human semantic parsing. ADN aims to find fine-grained local information to address the shared person re-identification challenges. Concretely, our network consists of two branches. The Attention Global Branch learns pixel-level local regions based on a fine-grained attention mechanism while the Feature Dropping Branch learns additional missed features in a weakly supervised manner. The fine-grained attention mechanism allows our model to be robust to complex pose variations and to avoid the redundant backgrounds. Extensive experiments over three benchmark datasets (Market-1501, DukeMTMC-reID, and CUHK03) demonstrate the effectiveness and robustness of the proposed network in handling the problems of complex poses, misalignment and occlusions. • Weakly supervised data augmentation based network for fine-grained person re-identification. • Modeling the spatial relationship of a fine-grained region for person re-identification. • Discovering more complementary feature representation in a weakly supervised fashion. [ABSTRACT FROM AUTHOR]

• Apply dynamic utility calculation framework to mine closed high utility itemsets. • Dramatically reduce the cost of database scans by adopting the P-set structure. • Propose a new CHUIM algorithm, named iEFIM-Closed. • Conduct experiments to measure the performance of the proposed algorithm. The problem of discovering high-utility itemsets (HUIs) in transaction databases, which is an extension of Frequent Itemset Mining, is a commonly encountered mining task. Researchers have proposed algorithms to efficiently mine highly profitable itemsets in customer transaction databases, in which the unit profits of items are fixed. However, this assumption does not reflect the true nature of the utility measure of items in real-life transaction databases, which might vary over time. Moreover, since this important characteristic is ignored by all the current HUI mining algorithms, they are either not applicable to this type of database, or they generate inaccurate results. In addition, the HUI mining algorithms' traditional limitation is that they produce a huge number of HUIs for users. In this paper, we define the problem of mining a lossless, concise and compact representation of HUIs, called closed HUIs (CHUIs), in dynamic unit profit databases. Based on newly defined of utility measure, a novel algorithm, called iEFIM-Closed, is introduced. This relies on this new utility measure, a novel compact database format to reduce the cost of database scans and increase the efficiency of the mining process. Experimental evaluations show that iEFIM-Closed significantly outperforms state-of-the-art algorithms for mining CHUIs on sparse databases with dynamic profit, and has competitive performance in dense databases in terms of runtime, the cost of database scans and scalability. [ABSTRACT FROM AUTHOR]

• The new method of classifier selection for imbalanced data is proposed. • Selection rule uses the dominance in the FPR/FNR space and crowding distance. • Tests on two real datasets confirm that new method improves the prediction. The goal of the paper is to develop a new algorithm for predicting whether the company will go bankrupt on the base of unbalanced data. To do it, we propose to consider the classification as a multi-objective optimization problem and construct a prediction model as an ensemble while minimizing the parameters FPR (False Positive Rate) and FNR (False Negative Rate) at the same time. To create the ensemble, the proposed algorithm of a Multi-Objective Classifier Selection (MOCS) selects only classifiers that belong to the Pareto-optimal set in FPR/FNR space; that is, there is no dominance between them, and they satisfy some additional conditions. In the general case, MOCS is determined by three parameters: two threshold values that limit false rates (FNR and FPR), and the crowding distance, which defines the uniqueness of the classifier's results. We tested the proposed algorithm on data collected from 2457 Russian companies, 456 of which went bankrupt, and 5910 Polish companies, 410 of which received bankruptcy status. Datasets contain features such as financial ratios and business environment factors. In the testing, we used more than 70 combinations of under-sampling, over-sampling, and no sampling methods with static and dynamic classification models. Final ensembles include seven classifiers for the Russian dataset and four classifiers for the Polish dataset combined by soft voting rule. In both cases, the proposed algorithm produces a significant improvement of prediction results as in terms of standard metrics (geometric mean, the area under the ROC curve) and in the visual representation in the FNR/FPR space, namely in the shift from a Pareto-optimal set of classifiers. [ABSTRACT FROM AUTHOR]