Search

• One-step abductive multi-target learning with diverse noisy samples (OSAMTL-DiNS) is proposed. • OSAMTL-DiNS is applied to tumour segmentation for breast cancer (TSfBC). • OSAMTL-DiNS enables various approaches for noisy labels achieving more rational results in TSfBC. • A predictive model pre-trained with OSAMTL-DiNS for TSfBC is released. Recent studies have demonstrated the effectiveness of the combination of machine learning and logical reasoning, including data-driven logical reasoning, knowledge driven machine learning and abductive learning, in inventing advanced technologies for different artificial intelligence applications. One-step abductive multi-target learning (OSAMTL), an approach inspired by abductive learning, via simply combining machine learning and logical reasoning in a one-step balanced multi-target learning way, has as well shown its effectiveness in handling complex noisy labels of a single noisy sample in medical histopathology whole slide image analysis (MHWSIA). However, OSAMTL is not suitable for the situation where diverse noisy samples (DiNS) are provided for a learning task. In this paper, giving definition of DiNS, we propose one-step abductive multi-target learning with DiNS (OSAMTL-DiNS) to expand the original OSAMTL to handle complex noisy labels of DiNS. Applying OSAMTL-DiNS to tumour segmentation for breast cancer in MHWSIA, we show that OSAMTL-DiNS is able to enable various state-of-the-art approaches for learning from noisy labels to achieve more rational predictions. We released a model pre-trained with OSAMTL-DiNS for tumour segmentation in HE-stained pre-treatment biopsy images in breast cancer, which has been successfully applied as a pre-processing tool to extract tumour-associated stroma compartment for predicting the pathological complete response to neoadjuvant chemotherapy in breast cancer. [ABSTRACT FROM AUTHOR]

• The paper explores AI decision-making to enhance transparency of CIN diagnosis using colposcopy images. • The study presents interpretable insights for clinical validation using different XAI methods. • Saliency method showed best result, using gradients to reveal likely malignancy traits. • Expert Clinic Validation of results conducted, along with statistical analyses. Although artificial intelligence techniques have performed well in analysing medical images, it is essential to consider the degree of understanding or interpretation in evaluations. This is especially important when diagnostic support is involved, as the trustworthiness of machine learning predictions needs to be clarified and evaluated. For deep learning algorithms to be translated into clinical practice, they must be made less opaque. To examine the classification of cervical dysplasia-diagnosed patients, we will explore explainable artificial intelligence (XAI) approaches, by implementing seven different interpretation techniques (Saliency, XRAI, Integrated Gradients, Smooth Gradients, Smooth Integrated Gradients, Grad-CAM, Smoothgrad-CAM). These XAI techniques shall be explored in order to assess the performance of four Convolutional Neural Network models (AlexNet, VGG16, MobileNet, and InceptionNet). Our results show that saliency qualities most closely match expert annotations, and there is a moderate to strong association between a model's sensitivity and the agreement between humans and computers. We also discovered a relevant relationship between expert insights and computational learning. This highlights the potential role of human expertise in influencing effective computer learning. [ABSTRACT FROM AUTHOR]

Intelligent Decision Support Systems (DSS) have gained considerable interest within the field of construction engineering through the utilization of Artificial Intelligence (AI) and Machine Learning (ML) methodologies. These systems possess the capacity to enhance decision-making processes and optimize the results of projects. Nevertheless, it is imperative to conduct a thorough and inclusive examination that incorporates and evaluates the various methodologies employed within this particular discipline, thereby bridging the existing void in research. The current state of research in the field of AI and ML in construction engineering is characterized by a dearth of comprehensive reviews that encompass the wide array of methodologies utilized. Although certain studies have delved into specific facets of this subject, there remains a novelty and research gap in terms of a holistic examination of the topic. The objective of this review is to conduct a comprehensive analysis of AI and ML methodologies in the field of construction engineering, with a specific emphasis on their practical applications, advantages, and constraints. The study also ascertains potential areas for future research and improvement in the domain of Intelligent DSS. This study employed a rigorous approach that involved an extensive review of scholarly literature and empirical investigations from 2001 to June 2023. The findings of the analysis indicate a noticeable increase in the number of research papers focusing on Intelligent DSS within the field of construction engineering during the last twenty years. The field has witnessed the emergence of key research areas, namely the utilization of Internet of Things (IoT), explainable AI, supply chain optimization, sustainable construction practices, and human–machine collaboration. The results of this study hold significant implications for the construction industry. The incorporation of AI and ML techniques within Intelligent DSS can effectively tackle various issues such as cost overruns, project delays, and safety concerns. [ABSTRACT FROM AUTHOR]

The conventional standardized theoretical models (such as Webster, Alcelik, Indo-HCM) used for the delay estimation revolve around the mathematical hypothesis and assumptions, making them static with limitations in accommodating the dynamic traffic behaviors. Recent advances in artificial intelligence make machine learning techniques suitable for estimating vehicle control delay compared to conventional methods. This paper demonstrates the application of several machine learning models developed by focusing on the fluctuations of traffic observed at an intersection having heterogeneous traffic conditions in Ahmedabad city for delay estimation. Several parameters are extracted from on-field and video surveys. However, not all parameters are relevant for accurately estimating vehicle control delay. Hence, a feature selection process consisting of several feature-scoring techniques from filter, wrapper, and embedded methods is applied to all the parameters. This process gave insights into the most statistically relevant independent parameters, and out of all the parameters, cycle time was found to be insignificant, with a feature score of 0 from almost all techniques. Hence, it was removed, and then the prominent parameters were then used to build a vehicle control delay model using support vector regression (SVR), K-nearest neighbor (KNN), artificial neural network (ANN), random forest regression (RF), and decision tree regression (DT). Error distribution, standard deviation of errors, coefficient of Determination (R2), and Root Mean Squared Error (RMSE) are the parameters used for evaluating the performance of the machine learning models. RF outperformed them all with a standard deviation of errors, R2, and RMSE of 11.065, 0.926, and 11.081 on testing data. But ANN, KNN, and DT also performed satisfactorily. Compared with conventional standardized theoretical models, all the machine learning models except SVR performed better. [ABSTRACT FROM AUTHOR]

In recent years, the enormous development of Machine Learning, especially Deep Learning, has led to the widespread adoption of Artificial Intelligence (AI) systems in a large variety of contexts. Many of these systems provide excellent results but act as black-boxes. This can be accepted in various contexts, but there are others (e.g., medical ones) where a result returned by a system cannot be accepted without an explanation on how it was obtained. Explainable AI (XAI) is an area of AI well suited to explain the behavior of AI systems that act as black-boxes. In this paper, we propose a model-agnostic XAI framework to explain the behavior of classifiers. Our framework is based on network theory; thus, it is able to make use of the enormous amount of results that researchers in this area have discovered over time. Being network-based, our framework is completely different from the other model-agnostic XAI approaches. Furthermore, it is parameter-free and is able to handle heterogeneous features that may not even be independent of each other. Finally, it introduces the notion of dyscrasia that allows us to detect not only which features are important in a particular task but also how they interact with each other. • Performing model-agnostic Explainable AI on classifiers. • Introducing the concept of dyscrasia of feature occurrences. • Assessing the relevance of a feature during classification. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) technologies are increasingly applied to traffic flow prediction (TFP) to enhance prediction accuracy. This study utilizes bibliometric methods and network analysis measures to gain insights into the research status, development process, opportunities, and challenges of AI-based TFP research based on the literature data retrieved from the Web of Science core collection. The study first conducts basic statistical analysis of all papers. Subsequently, cooperation network analysis is conducted to identify the most productive countries/territories, institutions, and authors, the cooperative relationships, and the formed research communities. Co-citation network analysis is then employed to identify publications that have made outstanding contributions to the AI-based TFP field. Finally, the main path analysis of the paper citation network is used to analyze the knowledge diffusion process, while the keyword co-occurrence analysis is conducted to reveal the evolution characteristics of the research topics. Based on the bibliometric analysis results, we gain insights into the opportunities and challenges in this field from the perspectives of data, models, and applications, and provide pertinent suggestions for future research. Overall, this study can assist researchers in capturing the state-of-the-art and research directions in AI-based TFP. [ABSTRACT FROM AUTHOR]

Due to the increasing use of Machine Learning models in high stakes decision making settings, it has become increasingly important to have tools to understand how models arrive at decisions. Assuming an already trained Supervised Classification model, post-hoc explanations can be obtained via so-called counterfactual analysis: a counterfactual explanation of an instance indicates how this instance should be minimally modified so that the perturbed instance is classified in the desired class by the given Machine Learning classification model. Most of the Counterfactual Analysis literature focuses on the single-instance single-counterfactual setting, in which the analysis is done for one single instance to provide one single counterfactual explanation. Taking a stakeholder's perspective, in this paper we introduce the so-called collective counterfactual explanations. By means of novel Mathematical Optimization models, we provide a counterfactual explanation for each instance in a group of interest, so that the total cost of the perturbations is minimized under some linking constraints. Making the process of constructing counterfactuals collective instead of individual enables us to detect the features that are critical to the entire dataset to have the individuals classified in the desired class. Our methodology allows for some instances to be treated individually, as in the single-instance single-counterfactual case, performing the collective counterfactual analysis for a fraction of records of the group of interest. This way, outliers are identified and handled appropriately. Under some assumptions on the classifier and the space in which counterfactuals are sought, finding collective counterfactual explanations is reduced to solving a convex quadratic linearly constrained mixed integer optimization problem, which, for datasets of moderate size, can be solved to optimality using existing solvers. The performance of our approach is illustrated on real-world datasets, demonstrating its usefulness. • A new model for Explainable Artificial Intelligence is proposed. • Counterfactual Explanations for a full group of individuals are sought. • Sparsity both at individual and group level is achieved. [ABSTRACT FROM AUTHOR]

Optimal path planning is a fundamental problem in artificial intelligence (AI) and has wide applications in areas such as robotics, transportation, and logistics. In this paper, we propose a novel approach for ordering algorithms in pathfinding problems using the concept of shell layers. Our approach aims to improve the computational efficiency and distance cost of ordering algorithms. To evaluate the effectiveness of our approach, we compare it with five state-of-the-art techniques commonly used in the field of ordering algorithms on eight different scenarios with varying configurations. Our results show that our proposed approach outperformed the state-of-the-art techniques in terms of time-computational complexity and distance cost in most of the scenarios, demonstrating its potential as a new state-of-the-art technique for ordering algorithms. Specifically, our approach outperformed the nearest neighbor, A*, branch and bound, Christofides, and genetics ordering algorithms. However, we also identified two specific situations where our approach was outperformed by two state-of-the-art algorithms due to the specific distribution of the goal nodes. These findings highlight the importance of evaluating and comparing ordering algorithms in various scenarios. Our approach has significant implications for AI research and development, as it has the potential to improve the performance of pathfinding algorithms in various applications. We also discuss the limitations of our approach and potential areas for further research, such as investigating the effectiveness of our approach in different types of graphs and exploring the potential use of machine learning techniques to optimize the shell layer construction. The code for this study is available at https://github.com/abdullah1aloush1/MuGONA. • Equally-spaced nodes formed over workspace with obstacles, optimizing search process. • Efficient neighboring graph built for equally-spaced nodes, reducing complexity. • Path optimization for navigation by ordering goal nodes, reducing time and distance. • Path smoothing for navigation via interpolation to yield a trajectory on path nodes. [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]

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]

In recent days, the research on student's intelligence level modelling is a challenging Artificial Intelligence (AI) task, which gains more attraction because it provides actionable insights to the tutor by analysing the intelligence level of the learners. Each learner's knowledge, comprehension, and intellectual capacities are unique. It is critical to identify these capacities and provide learners, particularly slow learners, with the necessary knowledge. Cognitive Performance Test (CPT) is an essential component for assessing the knowledge level of students. The reasoning level or coefficient deals with the analysis of the thinking capability in a logical way. It also reflects the child's learning potential. The main aim of the proposed system is to design a Cognitive Knowledge Representation Model (CKRM), which fuses Cognitive Performance Metrics (CPM) calculation and Reasoning Coefficient Calculation (RCC) algorithms to assess the student's intelligence level. The result of the proposed system is stratification of students to three different ranges of reasoning coefficient. The CKRM consists of the following phases: data collection, statistical Exploratory Data Analysis (EDA), model building and analysis, which involve the assessment of the knowledge level using CPT and calculation of reasoning coefficient using First Order Logic (FOL), and finally model evaluation using cognitive evaluation metrics. CPM and RCC algorithms have been proposed in this paper to calculate the student's reasoning coefficient by using the forward chaining FOL inference engine. The dataset is a real time data which consists of the academic and cognitive performance details of school students from classes 1 to 6 for the year 2019 to 2020. The academic data are collected from the Educational Management Information System (EMIS) maintained by the school. The cognitive performance data are collected by conducting the tests for the students using the memory training application called Lumosity. The proposed system's performance is evaluated using ten Machine Learning (ML) algorithms in which the Quadratic Discriminant Analysis achieved an accuracy of 0.97 for classes 1, 2, and 3. For classes 4, 5, and 6, nearly twelve ML algorithms are evaluated in which Random Forest (RF) Classifier achieved an accuracy of 0.98. Six math expert committee teachers concluded that the reasoning coefficient value was acceptable with an average accuracy of 0.92 for classes 1, 2, 3 and 0.9 for classes 4, 5, 6. In comparison to the pre-existing models employed in the prior research, it was determined that the created CKRM (academic and cognitive) was superior. The cognitive metrics such as taskability, Response Time (RT), knowledge capacity and utilization has also been evaluated. The average values of taskability, RT, knowledge capacity and knowledge utilization are 0.85, 0.81, 0.55, and 0.44. The ultimate goal is to make customized teaching easier; hence, this article involves determining a student's cognitive level by estimating their reasoning coefficient. The suggested approach analyses and categorizes students' cognitive abilities, such as memory, reasoning, problem solving, thinking, and logical reasoning, using three different reasoning coefficients. This approach assists teachers in determining the degree of intelligence of their students. • Cognitive Knowledge Representation Model (CKRM) to assess students' reasoning level. • Knowledge level assessment of students based on Cognitive Performance Test. • Computation of Cognitive Performance Metrics and Reasoning Coefficient. • Performance analysis using expert judgements and cognitive evaluation metrics. • Average accuracy score using expert judgemental analysis is 0.914. [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]

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]

Data-driven intelligent systems provide a possible solution to condition-based maintenance of wind turbines without experts' knowledge or mechanism models. However, the accuracy of fault diagnosis results is easily impaired by the data imbalance in real-world applications. In this paper, a novel method is proposed to address the mentioned problem. Specifically, spatial and temporal information of supervisory control and data acquisition (SCADA) data is extracted, and a contrastive learning strategy is developed to obtain the data representations correlated with the health conditions. Additionally, the bollards of the data distributions are determined in the representation space, and they are matched with the data centers of each health state. Under this circumstance, the unexpected effects of data imbalance on data representations are relieved, leading to effective decision boundaries regardless of the sample numbers. Then, a classifier is trained on the learned representations to recognize the faults in wind turbines. Compared with several baselines and state-of-the-art approaches, the impressive performance of the proposed method is demonstrated with simulated data and actual measurements from a utility-scale wind turbine. This research provides useful insights into the efficient development of wind energy with data-driven intelligent systems. [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]

This paper shows the development of a tool with which to solve the most critical aspect of the porthole die design problem using a predictive model based on machine learning (ML). The model relies on a large amount of geometrical data regarding successful porthole die designs, information on which was obtained thanks to a collaboration with a leading extrusion company. In all cases, the dies were made of H-13 hot work steel and the billet material was 6063 aluminium alloy. The predictive model was chosen from a series of probes with different algorithms belonging to various ML families, which were applied to the analysis of geometrical data corresponding to 596 ports from 88 first trial dies. Algorithms based on the generation of multiple decision trees together with the boosting technique obtained the most promising results, the best by far being the CatBoost algorithm. The explainability of this model is based on a post-hoc approach using the SHAP (SHapley Additive exPlanations) tool. The results obtained with this ML-based model are notably better than those of a previous model based on linear regression as regards both the R2 metric and the results obtained with the application examples. An additional practical advantage is its explainability, which is a great help when deciding the best way in which to adjust an initial design to the predictive model. This ML-based model is, therefore, an optimal means to integrate the experience and know-how accumulated through many designs over time in order to apply it to new designs. It will also provide an aid in generating the starting point for the design of high-difficulty dies, in order to minimise the number of FEM (finite element method) simulation/correction iterations required until an optimal solution is achieved. It is not aimed to eliminate FEM simulation from the design tasks, but rather to help improve and accelerate the whole process of designing porthole dies. The work presented herein addresses a validation model for a very common porthole die typology: four cavity and four port per cavity dies for 6xxx series aluminium alloys. However, a wide range of research regarding the generalisation of this model or its extension to other porthole die typologies must still be carried out. [ABSTRACT FROM AUTHOR]

In the railway domain, rolling stock maintenance affects service operation time and efficiency. Minimizing train unavailability is essential for reducing capital loss and operational costs. To this aim, prediction of failures of rolling stock equipment is crucial to proactively trigger proper maintenance activities. Indeed, predictive maintenance is a golden example of the digital transformation within Industry 4.0, which affects several engineering processes in the railway domain. Nowadays, it may leverage artificial intelligence and machine learning algorithms to forecast failures and schedule the optimal time for maintenance actions. Generally, rail systems deteriorate gradually over time or fail directly, leading to data that vary extremely slowly. Indeed, ML approaches for predictive maintenance should consider this type of data to accurately predict and forecast failures. This paper proposes a methodology based on Long Short-Term Memory deep learning algorithms for predictive maintenance of railway rolling stock equipment. The methodology allows us to properly learn long-term dependencies for gradually changing data, and both predicting and forecasting failures of rail equipment. In the framework of an academic-industrial partnership, the methodology is experimented on a train traction converter cooling system, demonstrating its applicability and benefits. The results show that it outperforms state-of-the-art methods, reaching a failure prediction and forecasting accuracy over 99%, with a false alarm rate of ∼ 0. 4 % and a mean absolute error in the order of 1 0 − 4 , respectively. [ABSTRACT FROM AUTHOR]

Every day the innovative IoT technology is expanding further and further in our environment, with applications deployed in various contexts including cities. Communities can indeed address problems linked to urbanization thanks to this technology through the Smart City concept and thus support a sustainable development of their cities. Artificial intelligence and namely its machine learning branch is expected to reinforce this trend by making smart cities even smarter. However, smart cities can only be successful if they can be trusted and, with this in mind, machine learning can potentially be an efficient tool to mitigate cyberattacks. This paper can be divided into two main parts. In the first part the ability of Gradient Boosting and Deep Learning to make long-term predictions of noise level is studied based on noise data collected in the suburb of an English city. In the second part, we proposed an approach for detecting noise levels anomalies based on predictions. Two types of injections were taken into consideration namely punctual noise level attacks and gradual noise level attacks. Specifically, for the punctual attacks, when the difference between the actual sensed and predicted noise levels is greater than a given threshold, we considered that there is an anomaly in the data. For the gradual attacks, we used a criterion comparing the mean absolute error of predictions in the attacked set of data to statistics of the absolute error in the training set. The obtained results show that our approach, which uses a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) hybrid network for the noise level prediction, can effectively be used to detect the aforementioned types of anomalies. In the case of punctual attacks an increase in sound intensity of 5 dB was detected, while for gradual attacks, smaller changes can be detected. • Urban noise data forecasting is performed using deep learning models and gradient boosting. • Noise data from parking meters deployed in an English city. • Several deep learning models (LSTM, CNN-LSTM, Transformer, TFT) are studied. • Accurate short-term (one hour) and long-term (6 days) forecasts are obtained. • Detection of anomalous data. [ABSTRACT FROM AUTHOR]

• Presented an extensive overview on different stages of electrocardiogram analysis. • Summarized the most notable developments of smart health monitoring systems. • Discussed the latest hardware implementations of real-time ECG monitoring systems. • Identified challenges and limitations for various automatic ECG diagnosis systems. • Outlines the future vision of next generation ECG monitoring systems for healthcare. Over the last decade, cardiovascular diseases (CVD's) are the leading cause of death globally. Early prediction of CVD's can help in reducing the complications of high-risk patients. The electrocardiogram (ECG) is an efficient aiding tool, provides accurate information about various cardiac conditions of the human heart. Evaluation and interpretation of ECG signal has become the major goal in current research to identify and mitigate risky cardiovascular conditions. The ECG signal is efficiently analysed and classified using signal processing techniques, ranging from traditional to machine learning approaches and its subbranches, such as deep learning are used for the early detection and diagnosis of cardiac conditions and arrhythmias. The development of novel types of body sensors increases the need for automated, low-cost, real-time, and efficient ECG monitoring systems that can be used at home or in ambulatory settings. IoT in healthcare industry enables the doctors and specialists to diagnose the patient status remotely in a smart and efficient manner. Motivated with all the research done in this area for early diagnosis of cardiac abnormalities and save the life of high-risk patients, we surveyed numerous research works reported in the literature and provide a glance on several aspects of ECG signal monitoring systems. We first introduce the step-by-step framework of ECG signal analysis starting data acquisition to classification, describes each stage analysis of both traditional and advanced machine learning models that have been reported in the literature. We provide a deep discussion on ECG signal acquisition, pre-recorded clinical ECG data taken from the databases, signal processing and denoising, detection of feature based on feature engineering, and signal classification along with the comparative assessment amongst reviewed studies. This work also presents the detailed analysis of smart health care system that employs portable and wearable devices, as well as the Internet of Things (IoT) and wireless technologies, as an innovative medium for data transmission that allows for remote access to a patient's health status at lower costs and with greater efficiency. Moreover, this work provides an extensive knowledge on various hardware platforms that have been adopted for the development of biomedical processors including microcontrollers, FPGA and ASIC. Additionally, the challenges and limitations are discussed in this research field and directions for future work are suggested. This is the first review paper of its kind to present a comprehensive discussion on all aspects of cardiovascular disease monitoring systems in one place. [ABSTRACT FROM AUTHOR]

While artificial intelligence is widely employed in many applications, it is vulnerable to bias and unethical use. Therefore, fairness evaluation tools and bias mitigation algorithms have drawn considerable attention. The main concern arises when an intelligent system is developed to make life-changing decisions in a social application. The ethical aspects of the decisions are vital because they significantly affect human lives. Therefore, numerous techniques have been developed to prevent discrimination in the learning algorithm output. This survey paper focuses on the application of fairness techniques in healthcare, organizational justice, and finance. Different kinds of discrimination are identified and comprehensively discussed in each application, and state-of-the-art fairness methods in each category are reviewed. • Fairness algorithms in healthcare, organizational justice, and finance. • Discrimination in accessing medical services and insurance. • Unfair AI model has destructive effects on employee engagement and motivation. • Lending and credit-scoring model in AI fair models. [ABSTRACT FROM AUTHOR]

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated Model-agnostic Explanations (AcME), an interpretability approach that quickly provides feature importance scores both at the global and the local level. AcME can be applied a posteriori to each regression or classification model based on tabular data. Not only AcME computes feature ranking, but it also provides a what-if analysis tool to assess how changes in features values would affect model predictions. We evaluated the proposed approach on synthetic and real-world datasets, also in comparison with SHapley Additive exPlanations (SHAP), the approach we drew inspiration from, which is currently one of the state-of-the-art model-agnostic interpretability approaches. We achieved comparable results in terms of quality of produced explanations while reducing dramatically the computational time and providing consistent visualization for global and local interpretations. To foster research in this field, and for the sake of reproducibility, we also provide a repository with the code used for the experiments. • AcME, a new interpretability approach for Machine Learning, is proposed. • AcME is a model-agnostic, global and local approach. • AcME allows fast computational time w.r.t. to state-of-the-art approaches. • The effectiveness of AcME is demonstrated on both synthetic and real data. [ABSTRACT FROM AUTHOR]

In this paper, we present a fundamental framework for defining different types of explanations of AI systems and the criteria for evaluating their quality. Starting from a structural view of how explanations can be constructed, i.e., in terms of an explanandum (what needs to be explained), multiple explanantia (explanations, clues, or parts of information that explain), and a relationship linking explanandum and explanantia, we propose an explanandum-based typology and point to other possible typologies based on how explanantia are presented and how they relate to explanandia. We also highlight two broad and complementary perspectives for defining possible quality criteria for assessing explainability: epistemological and psychological (cognitive). These definition attempts aim to support the three main functions that we believe should attract the interest and further research of XAI scholars: clear inventories, clear verification criteria, and clear validation methods. • We propose a framework for defining different types of explanations of AI systems. • We contextualize current XAI discourses within the proposed framework. • We highlight two broad perspectives for defining quality criteria for explainability. • We discuss the relevance of our framework in light of current and upcoming AI regulation. • We confer fundamental aspects for future research of XAI scholars. [ABSTRACT FROM AUTHOR]

• A significant contribution of artificial emotional intelligence in recent years. • Comparative study of conventional and deep learning techniques. • Limitations and issues in existing techniques and how to overcome them. • Research gap and challenges to obtain better emotion recognition performance. • Research opportunities and future direction in artificial emotional intelligence. Artificial intelligence substantially changes the global world, influencing technologies, machines, and objects in various encouraging aspects nowadays; emotion recognition is also one of them. This paper describes a significant contribution of emotion recognition by applying conventional and deep learning methodologies by focusing on limitations and demanding challenges. It also intends to explore the comparative study on recently applied machine learning and deep learning-based algorithms, which provide the best accuracy rates to recognize emotions. This Comparative study consists of different feature extractions, classifier models, and datasets that recognize the emotions within a facial image, speech, and non-verbal communication and describes their features and principles for future research work. We have shown the balancing accuracy, and efficiency of using hybrid classification techniques briefly explained in Speech emotion recognition. This review study would be more beneficial in enhancing automated decision-making services in various customer-based industries and observing patients in the health care sector, industries, public sectors, private sectors, and production firms. [ABSTRACT FROM AUTHOR]

• Narrative review of machine learning methods used on end-stage kidney disease. • Techniques to predict survival in kidney transplantation and dialysis therapy. • Models used to analyze the incidence of infection or tacrolimus toxicity. • Algorithms used to analyze other dialysis variables to predict mortality. In the field of medicine, decision-making has traditionally been carried out based on the best available scientific information and the experience of specialists using data found in analog formats such as radiographies, medical reports, and handwritten notes, among others. In this sense, the Big Data phenomenon is changing the world of medicine since the technologies that have been developed have made available to researchers and clinicians enormous amounts of data in digital formats that can be used to complement or help in complex tasks such as mentioned decision making. A key element in this process is data analysis techniques, since without them it is not possible to exploit the information. Currently the most used techniques are based on algorithms in the area of artificial intelligence and more specifically machine learning. This paper focuses on a specific domain of medicine, renal replacement therapies for end-stage renal disease, where machine learning is beginning to be used as a complementary tool to predict or make decisions. This paper provides a narrative review of the main machine learning methods that are being used to conduct end-stage renal disease treatment analyses. [ABSTRACT FROM AUTHOR]

Artificial intelligence and robotics are advancing at an incredible pace; however, there is a risk associated with the data privacy and personal information of users interacting with these systems and platforms. In this context, the federated learning approach emerged to enable large-scale, distributed learning without the need to transmit or store any information necessary to train the learning models. In a previous paper, we presented a system capable of detecting, locating, and classifying what kind of contact occurs between humans and one of our robots using innovative contact microphone technology. In this work we go further, improving the previously presented touch system with a multi-user, multi-robot, distributed, and scalable learning approach that is able to learn in a collaborative and incremental way while respecting the privacy of the user's information. The system has been successfully evaluated in a real environment with 28 different users divided in 7 different groups. To assess the performance of our system with this federated learning approach, we compared it to the same distributed learning system without federated learning. That is, the control group for this comparison is a central node directly receiving all the training examples obtained by each robot locally. We found that in this context the inclusion of federated learning improves the results concerning traditional distributed learning. • Federated learning allows large-scale distributed learning and protects privacy. • The robots are able to collaboratively interpret human–robot touch interactions. • The robots decide when to upload their models to the central node asynchronously. • Cooperation between robots improves the results from conventional learning methods. [ABSTRACT FROM AUTHOR]

Augmented Reality (AR) is an augmented depiction of reality formed by overlaying digital information on an image of objects being seen through a device. Artificial Intelligence (AI) techniques have experienced unprecedented growth and are being applied in various industries. The combination of AR and AI is the next prominent direction in upcoming years with many industries and academia recognizing the importance of their adoption. With the advancements in the silicone industry that push the boundaries of Moore's law, processors will be less expensive, more efficient, and power-optimized in the forthcoming years. This is a tremendous support and necessity for an AR boom, and with the help of AI, there is an excellent potential for smart industries to increase the production speed and workforce training along with improved manufacturing, error handling, assembly, and packaging. In this work, we provide a systematic review of recent advances, tools, techniques, and platforms of AI-empowered AR along with the challenges of using AI in AR applications. This paper will serve as a guideline for future research in the domain of AI-assisted AR in industrial applications. • The trend of AR and AI applications in the industry is analyzed. • Types of AI techniques for mobile AR applications are provided. • Various platforms and frameworks for AR applications are illustrated. • Usage of AR/AI in various manufacturing sectors is reviewed. • Challenges for implementing AR & AI techniques in the industry are discussed. [ABSTRACT FROM AUTHOR]

Deep learning is a type of machine learning that adapts a deep hierarchy of concepts. Deep learning classifiers link the most basic version of concepts at the input layer to the most abstract version of concepts at the output layer, also known as a class or label. However, once trained over a finite set of classes, some deep learning models do not have the power to say that a given input does not belong to any of the classes and simply cannot be linked. Correctly invalidating the prediction of unrelated classes is a challenging problem that has been tackled in many ways in the literature. Novelty detection gives deep learning the ability to output "do not know" for novel/unseen classes. Still, no attention has been given to the security aspects of novelty detection. In this paper, we consider the case study of abstraction-based novelty detection and show its weakness against adversarial samples. We show the feasibility of crafting adversarial samples that bypass the novelty detection monitoring and fool the deep learning classifier at the same time. In other words, novelty detection itself ends up as an attack surface. Moreover, we call for further research from a defender's point of view. We investigate auto-encoders as a plausible defense mechanism and assess its performance. • Study the security aspects of novelty detection. • Investigate the case of abstraction-based novelty detection. • Show the feasibility of bypassing the novelty detection monitoring. • Study the novelty detection configuration against the attack settings. • Propose efficient defense mechanisms to protect novelty detection. [ABSTRACT FROM AUTHOR]

Developing expert systems that make use of artificial intelligence (AI) to provide predictive analytics as well as targeted recommendations for decision support has been gaining momentum in recent years. Both academia and industry are looking into creating such systems to solve real-world problems and tackle specific challenges. In our work, we investigate the potential application of different machine learning approaches to solutions around competitive cycling. Specifically, we build and evaluate prediction models that are capable of accurately predicting a cyclist's speed and heart rate using sensory information collected during bike rides. In addition, we create a recommendation module that is able to provide real-time action suggestions to cyclists regarding their posture with the goal of improving their overall performance. We achieve this using a combination of model-based reinforcement learning (RL) and deep RL. In particular, we use model-based RL to learn a "simulator" of bike rides using the prediction models and action profiles extracted from sensors placed on the cyclists' back. We then use deep Q-learning in the simulator to extract policies that improve a cyclist's behavior during a bike ride. Our evaluation shows that by recommending specific actions throughout the ride, cyclists can increase their overall average speed with only a minimal impact on their heart rate. The results presented in this paper constitute clear evidence that advanced AI techniques are a prime candidate for further developing intelligent solutions in competitive cycling and other similar areas. • Sensory information from bike rides is used to predict speed and heart rate. • The predictive models are used as a simulator of new bike rides. • We use the simulator to train a recommendation system about a cyclist's posture. • The system's sparse suggestions improve the speed with a minimal impact on heart rate [ABSTRACT FROM AUTHOR]

Cellular networks are important for the success of modern communication systems, which support billions of mobile users and devices. Powered by artificial intelligence techniques, cellular networks are becoming increasingly smarter, and cellular traffic prediction is an important basis for realizing various applications that have originated from this trend. In this survey, we review the relevant studies on cellular traffic prediction and classify the prediction problems as the temporal and spatiotemporal prediction problems. The prediction models with artificial intelligence are categorized into statistical, machine learning, and deep learning models and then compared. Various applications based on cellular traffic prediction are summarized along with their current progress. The potential research directions are pointed out for future research. To the best of our knowledge, this paper is the first comprehensive survey on cellular traffic prediction. • Artificial intelligence for cellular traffic prediction is reviewed comprehensively. • Cellular traffic prediction problems, models, and evaluation metrics are classified. • The potential applications and directions for future research are pointed out. [ABSTRACT FROM AUTHOR]

Based on a solid mathematical background, this paper proposes a method for Symbolic Regression that enables the extraction of mathematical expressions from a dataset. Contrary to other approaches, such as Genetic Programming, the proposed method is deterministic and, consequently, does not require the creation of a population of initial solutions. Instead, a simple expression is grown until it fits the data. This method has been compared with four well-known Symbolic Regression techniques with a large number of datasets. As a result, on average, the proposed method returns better performance than the other techniques, with the advantage of returning mathematical expressions that can be easily used by different systems. Additionally, this method makes it possible to establish a threshold at the complexity of the expressions generated, i.e., the system can return mathematical expressions that are easily analyzed by the user, as opposed to other techniques that return very large expressions. • Novel technique for Machine Learning and Symbolic Regression. • Possibility to explicitly set the complexity of the developed expression. • Results compared to other Symbolic Regression techniques and better on a large number of datasets. • Much simpler expressions than in GP. [ABSTRACT FROM AUTHOR]

Statistical methods enable rational and quantitative studies of systems or processes, and support management decisions. Statistical Process Control (SPC) is a standard methodology for measuring, controlling and improving the quality of processes and products through statistics. Presented by Walter A. Shewhart in the 1920's, control charts are among the most popular SPC tools for monitoring processes. However, despite their age, their application in Artificial Intelligence (AI) has only recently begun appearing in the literature. In this paper, we use SPC and AI techniques to present a new process monitoring tool. The proposed classification control chart, which we call class-chart, offers a more robust and flexible alternative to traditional SPC tools. In addition to the ability to recognize patterns and diagnose problems, regardless of the sample scenario, this new approach is capable of performing its monitoring functions on a large scale, predicting market scenarios and processes on large volumes of data. We evaluate the performance of the class-chart by the average run length in extensive numerical simulations. Finally, two real data sets are used to illustrate the applicability of the proposed control chart for classification data. • New monitoring tool based on Statistical Process Control and Artificial Intelligence. • Quality characteristic of interest is multiple categorical and latent. • So-called class-chart is more robust and flexible than usual process monitoring tools. • Ability to take control of future predictions. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel density-based radar scanning clustering algorithm. Its main objective is to quickly discover and accurately extract individual clusters by employing the radar scanning strategy. By using this algorithm, the number of clusters does not need to be specified beforehand. Two techniques are utilized in our proposed method. First, we use a fast mean-shift algorithm with adaptive radius and active subsets to effectively locate the centers, reducing the computational time significantly. Second, we employ the shape of the probability density function of the distribution of distances between a selected point and the other points in the data set. This is performed to determine the critical parameters of the radiuses of the fast mean-shift algorithm and radiuses of clusters. The new algorithm has four merits. It reduces the computational complexity, overcomes problems caused by high dimensionality, is capable of dealing with heterogeneous spherical data sets, and lastly, is robust to noise and outliers. After applying our proposed method to several kinds of synthetic and real-world data sets, the results indicate that the density-based radar scanning algorithm is efficient and accurate. • The proposed algorithm discovers and extracts clusters by a radar scanning strategy. • The number of clusters does not need to be given beforehand. • This algorithm reduces time complexity and solves high dimensionality. • It is capable of dealing with heterogeneous data. • It is robust and invulnerable to noise and outliers. [ABSTRACT FROM AUTHOR]

OneClass SVM is a popular method for unsupervised anomaly detection. As many other methods, it suffers from the black box problem: it is difficult to justify, in an intuitive and simple manner, why the decision frontier is identifying data points as anomalous or non anomalous. This problem is being widely addressed for supervised models. However, it is still an uncharted area for unsupervised learning. In this paper, we evaluate several rule extraction techniques over OneClass SVM models, while presenting alternative designs for some of those algorithms. Furthermore, we propose algorithms for computing metrics related to eXplainable Artificial Intelligence (XAI) regarding the "comprehensibility", "representativeness", "stability" and "diversity" of the extracted rules. We evaluate our proposals with different data sets, including real-world data coming from industry. Consequently, our proposal contributes to extending XAI techniques to unsupervised machine learning models. • Rule extraction for unsupervised outlier detection models using OCSVM. • Design and evaluate alternatives over rule extraction algorithms. • XAI metric evaluation: comprehensibility, representativeness, stability and diversity. • Quantify quality of the explanations with XAI metrics for P@1 rules. • Measure the kernel influence in the number of rules generated. [ABSTRACT FROM AUTHOR]

• Background information on social spam and the spamming process. • Social spam taxonomy comprising spam content and spammer account is outlined. • A review of social spam, Deepfakes, and spammer detection techniques is presented. • Several challenges, open issues, and future research directions are discussed. Online Social Networks are perpetually evolving and used in plenteous applications such as content sharing, chatting, making friends/followers, customer engagements, commercials, product reviews/promotions, online games, and news, etc. The substantial issues related to the colossal flood of social spam in social media are polarizing sentiments, impacting users' online interaction time, degrading available information quality, network bandwidth, computing power, and speed. Simultaneously, groups of coordinated automated accounts/bots often use social networking sites to spread spam, rumors, bogus reviews, and fake news for targeted users or mass communication. The latest developments in the form of artificial intelligence-enabled Deepfakes have exacerbated these issues at large. Consequently, it becomes extremely relevant to review recent work concerning social spam and spammer detection to counter this issue and its effect. This paper provides a brief introduction to social spam, the spamming process, and social spam taxonomy. The comprehensive review entails several dimensionality reduction techniques used for feature selection/extraction, features used, various machine learning and deep learning techniques used for social spam and spammer detection, and their merits and demerits. Artificial intelligence and deep learning empowered Deepfake (text, image, and video) spam, and their countermeasures are also explored. Furthermore, meticulous discussions, existing challenges, and emerging issues such as robustness of detection systems, scalability, real-time datasets, evade strategies used by spammers, coordinated inauthentic behavior, and adversarial attacks on machine learning-based spam detectors, etc., have been discussed with possible directions for future research. [ABSTRACT FROM AUTHOR]

• A bibliometric analysis on machine learning research in all engineering fields. • VOSviewer is employed to this study based on retrieved 3057 articles. • Research distributions of this topic are identified. • A detailed discussion on the knowledge bases, research hotspots and frontiers. In this work, we conducted a visualized bibliometric analysis to map the research trends of machine learning in engineering (MLE) based on articles indexed in the Web of Science Core Collection published between 2000 and 2019. The research distributions, knowledge bases, research hotspots, and research frontiers for MLE studies are revealed by using VOSviewer software and visualization technology. The growth of the literature related to MLE averaged 24.3% in the past two decades. A total of 3057 peer-reviewed papers from 96 countries published in 1299 different journals were identified. The USA was the most productive country, with 23.73% of the overall articles and 32.25% of the overall citations. The most active research organization was MIT, with 41 publications and 1079 citations, and the Journal of Machine Learning Research had the largest number of citations in the field of MLE. In particular, our findings indicate that the research issues of "random forests", "support vector machine", "extreme learning machine", "deep learning", "statistical learning theory", and "Python machine learning" formed the knowledge bases of MLE from 2000 to 2019, while the research hotspots focused on applications of machine learning benchmark algorithms. Burst detection analysis results showed that more burst keywords emerged and had a higher frequency of change after 2010. This study provides an insight view of the overall research trends of MLE and may help researchers better understand this research field and predict its dynamic directions. [ABSTRACT FROM AUTHOR]

• We study fairness of AI algorithms in Privileged Group Selection Bias data settings. • A typical domain which often presents such selection bias is AI-based hiring. • We demonstrate that such selection bias can indeed lead to a high algorithmic bias. • We propose three in-process and pre-process fairness mechanisms. • Our methods improve fairness considerably with a minimal compromise in accuracy. An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. In this paper, we study the fairness of AI algorithms in data settings for which unprivileged groups are extremely under-represented compared to privileged groups. A typical domain which often presents such Privileged Group Selection Bias (PGSB) is AI-based hiring, which stems from an inherent lack of labeled information for rejected applicants. We first demonstrate that such a selection bias can lead to a high algorithmic bias, even if privileged and unprivileged groups are treated exactly the same. We then propose several methods to overcome this type of bias. In particular, we suggest three in-process and pre-process fairness mechanisms, combined with both supervised and semi-supervised learning algorithms. An extensive evaluation that was conducted using two real-world datasets, reveals that the proposed methods are able to improve fairness considerably, with only a minimal compromise in accuracy. This is despite the limited information available for unprivileged groups and the inherent trade-off between fairness and accuracy. [ABSTRACT FROM AUTHOR]

Recent trends in intelligent manufacturing are transforming shop floor environments into digital factories, thanks to a pervasive integration of information and communication technologies in production lines. Industrial processes become the source of high-volume heterogeneous data, paving the way to create manufacturing intelligence by means of machine learning and data-driven methodologies. In such settings, predictive diagnostics play a crucial role, as they promise to predict future critical conditions in the production process. Unfortunately, the diffusion of data-driven predictive maintenance methodologies is limited by (i) the absence of timely ground-truth knowledge (i.e., class labels), required in the learning phase of data-driven supervised approaches, and (ii) the limited availability of data-mining expertise among application-domain experts, required to harness the power of machine learning techniques. Innovative data-driven services are needed to support domain experts in (i) applying powerful self-learning intelligent techniques with limited technical expertise and (ii) easily understanding results and choices operated by such intelligent techniques, to increase trust by means of transparency. To this aim, this paper presents UDaMP, an integrated platform to support manufacturing intelligence by providing a transparent, self-tuning, unsupervised discovery and assisted data labelling service for predictive maintenance, specifically targeted at cyclic industrial processes. UDaMP includes (i) production-cycle-aware feature engineering, (ii) unsupervised discovery of production-cycle categories, (iii) self-tuning of the optimal number of categories, (iv) human-readable characterisation of production-cycle categories, and (v) assisted data labelling for domain experts. Scalable clustering algorithms automatically discover groups of production cycles sharing common time-independent properties. A self-tuning strategy is integrated to automatically configure the specific input parameter and select the best approach for the data under analysis. Each cluster is then locally characterised through the data distribution of the top 10 most relevant features to support domain experts in uncovering its meaning. Experimental evaluation of UDaMP has been performed on real-world data collected in two different industrial settings. • Semi-supervised labelling of production cycles for predictive maintenance. • Wide applicability to any cycle-based production process without ground truth labels. • Exploitable by domain experts thanks to transparent self-tuning techniques. [ABSTRACT FROM AUTHOR]

• CASTLE aims to combine local and global features to explain any AI system predictions. • Model's global knowledge, as rules, supports the local explanation generation process. • CASTLE estimates how clusters' representative points in uence predictions. • It supports any explanation type (e.g. rule-based, feature importance, counterfactual). With Artificial Intelligence becoming part of a rapidly increasing number of industrial applications, more and more requirements about their transparency and trustworthiness are being demanded to AI systems, especially in military, medical and financial domains, where decisions have a huge impact on lives. In this paper, we propose a novel model-agnostic Explainable AI (XAI) technique, named Cluster-aided Space Transformation for Local Explanation (CASTLE) , able to provide rule-based explanations based on both the local and global model's workings, i.e. its detailed "knowledge" in the neighborhood of the target instance and its general knowledge on the training dataset, respectively. The framework has been evaluated on six datasets in terms of temporal efficiency, cluster quality and model significance. Eventually, we asked 36 users to evaluate the explainability of the framework, getting as result an increase of interpretability of 6 % with respect to another state-of-the-art technique, named Anchors. [ABSTRACT FROM AUTHOR]