Algorithms, Volume 15, Issue 3 (March 2022) – 30 articles

In this article, multi-fidelity kriging and sparse polynomial chaos expansion (SPCE) surrogate models are constructed. In addition, a novel combination of the two surrogate approaches into a multi-fidelity SPCE-Kriging model will be presented. Accurate surrogate models, once obtained, can be employed for evaluating a large number of designs for uncertainty quantification, optimization, or design space exploration. Analytical benchmark problems are used to show that accurate multi-fidelity surrogate models can be obtained at lower computational cost than high-fidelity models. The benchmarks include non-polynomial and polynomial functions of various input dimensions, lower dimensional heterogeneous non-polynomial functions, as well as a coupled spring-mass-system. Overall, multi-fidelity models are more accurate than high-fidelity ones for the same cost, especially when only a few high-fidelity training points are employed. Full-order PCEs tend to be a factor of two or so worse than SPCES in terms of overall accuracy. The combination of the two approaches into the SPCE-Kriging model leads to a more accurate and flexible method overall. Full article

Most computer programs or applications need fast data structures. The performance of a data structure is necessarily influenced by the complexity of its common operations; thus, any data-structure that exhibits a theoretical complexity of amortized constant time in several of its main operations should draw a lot of attention. Such is the case of a family of data structures that is called hash tables. However, what is the real efficiency of these hash tables? That is an interesting question with no simple answer and there are some issues to be considered. Of course, there is not a unique hash table; in fact, there are several sub-groups of hash tables, and, even more, not all programming languages use the same variety of hash tables in their default hash table implementation, neither they have the same interface. Nevertheless, all hash tables do have a common issue: they have to solve hash collisions; that is a potential weakness and it also induces a classification of hash tables according to the strategy to solve collisions. In this paper, some key concepts about hash tables are exposed and some definitions about those key concepts are reviewed and clarified, especially in order to study the characteristics of the main strategies to implement hash tables and how they deal with hash collisions. Then, some benchmark cases are designed and presented to assess the performance of hash tables. The cases have been designed to be randomized, to be self-tested, to be representative of a real user cases, and to expose and analyze the impact of different factors over the performance across different hash tables and programming languages. Then, all cases have been programmed using C++, Java and Python and analyzed in terms of interfaces and efficiency (time and memory). The benchmark yields important results about the performance of these structures and its (lack of) relationship with complexity analysis. Full article

Topology optimization offers a possibility to derive load-compliant structures. These structures tend to be complex, and conventional manufacturing offers only limited possibilities for their production. Additive manufacturing provides a remedy due to its high design freedom. However, this type of manufacturing can cause areas of different material properties in the final part. For example, in selective laser melting, three areas of different porosity can occur depending on the process parameters, the geometry of the part and the print direction, resulting in a direct interrelation between manufacturing and design. In order to address this interrelation in design finding, this contribution presents an optimization method in which the three porous areas are identified and the associated material properties are considered iteratively in a topology optimization. For this purpose, the topology optimization is interrupted in each iteration. Afterwards, the three areas as well as the material properties are determined and transferred back to the topology optimization, whereby those properties are used for the calculation of the next iteration. By using the optimization method, a design with increased volume-specific stiffness compared to a design of a standard topology optimization can be created and will be used in the future as a basis for the extension by a global strength constraint to maintain the maximum permissible stress and the minimum wall thickness. Full article

Remaining useful life (RUL) prediction is a key enabler for predictive maintenance. In fact, the possibility of accurately and reliably predicting the RUL of a system, based on a record of its monitoring data, can allow users to schedule maintenance interventions before faults occur. In the recent literature, several data-driven methods for RUL prediction have been proposed. However, most of them are based on traditional (connectivist) neural networks, such as convolutional neural networks, and alternative mechanisms have barely been explored. Here, we tackle the RUL prediction problem for the first time by using a membrane computing paradigm, namely that of Spiking Neural P (in short, SN P) systems. First, we show how SN P systems can be adapted to handle the RUL prediction problem. Then, we propose the use of a neuro-evolutionary algorithm to optimize the structure and parameters of the SN P systems. Our results on two datasets, namely the CMAPSS and new CMAPSS benchmarks from NASA, are fairly comparable with those obtained by much more complex deep networks, showing a reasonable compromise between performance and number of trainable parameters, which in turn correlates with memory consumption and computing time. Full article

In this work, we propose $D^3$-Tree, a dynamic distributed deterministic structure for data management in decentralized networks, by engineering and extending an existing decentralized structure. Conducting an extensive experimental study, we verify that the implemented structure outperforms other well-known hierarchical tree-based structures since it provides better complexities regarding load-balancing operations. More specifically, the structure achieves an $O(logN)$ amortized bound (N is the number of nodes present in the network), using an efficient deterministic load-balancing mechanism, which is general enough to be applied to other hierarchical tree-based structures. Moreover, our structure achieves $O(logN)$ worst-case search performance. Last but not least, we investigate the structure’s fault tolerance, which hasn’t been sufficiently tackled in previous work, both theoretically and through rigorous experimentation. We prove that $D^3$-Tree is highly fault-tolerant and achieves $O(logN)$ amortized search cost under massive node failures, accompanied by a significant success rate. Afterwards, by incorporating this novel balancing scheme into the ART (Autonomous Range Tree) structure, we go one step further to achieve sub-logarithmic complexity and propose the ART${}^{+}$ structure. ART${}^{+}$ achieves an $O\left({log}_b^{2}logN\right)$ communication cost for query and update operations (b is a double-exponentially power of 2 and N is the total number of nodes). Moreover, ART${}^{+}$ is a fully dynamic and fault-tolerant structure, which supports the join/leave node operations in $O(loglogN)$ expected WHP (with high proability) number of hops and performs load-balancing in $O(loglogN)$ amortized cost. Full article

In the field of agricultural research, Machine Learning (ML) has been used to increase agricultural productivity and minimize its environmental impact, proving to be an essential technique to support decision making. Accurate harvest time prediction is a challenge for fruit production in a sustainable manner, which could eventually reduce food waste. Linear models have been used to estimate period duration; however, they present variability when used to estimate the chronological time of apple tree stages. This study proposes the PredHarv model, which is a machine learning model that uses Recurrent Neural Networks (RNN) to predict the start date of the apple harvest, given the weather conditions related to the temperature expected for the period. Predictions are made from the phenological phase of the beginning of flowering, using a multivariate approach, based on the time series of phenology and meteorological data. The computational model contributes to anticipating information about the harvest date, enabling the grower to better plan activities, avoiding costs, and consequently improving productivity. We developed a prototype of the model and performed experiments with real datasets from agricultural institutions. We evaluated the metrics, and the results obtained in evaluation scenarios demonstrate that the model is efficient, has good generalizability, and is capable of improving the accuracy of the prediction results. Full article

Vibration signal analysis is the most common technique used for mechanical vibration monitoring. By using vibration sensors, the fault prognosis of rotating machinery provides a way to detect possible machine damage at an early stage and prevent property losses by taking appropriate measures. We first propose a digital integrator in frequency domain by combining fast Fourier transform with digital filtering. The velocity and displacement signals are, respectively, obtained from an acceleration signal by means of two digital integrators. We then propose a fast method for the calculation of the envelope spectra and instantaneous frequency by using the spectral properties of the signals. Cepstrum is also introduced in order to detect the unidentifiable periodic signal in the power spectrum. Further, a fault prognosis algorithm is presented by exploiting these spectral analyses. Finally, we design and implement a visualized real-time vibration analyzer on a Raspberry Pi embedded system, where our fault prognosis algorithm is the core algorithm. The real-time signals of acceleration, velocity, displacement of vibration, as well as their corresponding spectra and statistics, are visualized. The developed fault prognosis system has been successfully deployed in a water company. Full article

The COVID-19 epidemic has highlighted the significance of sanitization and maintaining hygienic access to clean water to reduce mortality and morbidity cases worldwide. Diarrhea is one of the prevalent waterborne diseases caused due to contaminated water in many low-income countries with similar living conditions. According to the latest statistics from the World Health Organization (WHO), diarrhea is among the top five primary causes of death worldwide in low-income nations. The condition affects people in every age group due to a lack of proper water used for daily living. In this study, a stacking ensemble machine learning model was employed against traditional models to extract clinical knowledge for better understanding patients’ characteristics; disease prevalence; hygienic conditions; quality of water used for cooking, bathing, and toiletries; chemicals used; therapist’s medications; and symptoms that are reflected in the field study data. Results revealed that the ensemble model provides higher accuracy with 98.90% as part of training and testing phases when experimented against frequently used J48, Naïve Bayes, SVM, NN, PART, Random Forest, and Logistic Regression models. Managing outcomes of this research in the early stages could assist people in low-income countries to have a better lifestyle, fewer infections, and minimize expensive hospital visits. Full article

Computing sample means on Riemannian manifolds is typically computationally costly, as exemplified by computation of the Fréchet mean, which often requires finding minimizing geodesics to each data point for each step of an iterative optimization scheme. When closed-form expressions for geodesics are not available, this leads to a nested optimization problem that is costly to solve. The implied computational cost impacts applications in both geometric statistics and in geometric deep learning. The weighted diffusion mean offers an alternative to the weighted Fréchet mean. We show how the diffusion mean and the weighted diffusion mean can be estimated with a stochastic simulation scheme that does not require nested optimization. We achieve this by conditioning a Brownian motion in a product manifold to hit the diagonal at a predetermined time. We develop the theoretical foundation for the sampling-based mean estimation, we develop two simulation schemes, and we demonstrate the applicability of the method with examples of sampled means on two manifolds. Full article

Currently, artificial intelligence is in an important period of growth. Due to the technology boom, it is now possible to solve problems that could not be resolved previously. For example, through goal-driven learning, it is possible that intelligent machines or agents may be able to perform tasks without human intervention. However, this also leads to the problem of understanding the agent’s decision making. Therefore, explainable goal-driven learning attempts to eliminate this gap. This work focuses on the adaptability of two explainability methods in continuous environments. The methods based on learning and introspection proposed a probability value for success to explain the agent’s behavior. These had already been tested in discrete environments. The continuous environment used in this study is the car-racing problem. This is a simulated car racing game that forms part of the Python Open AI Gym Library. The agents in this environment were trained with the Deep Q-Network algorithm, and in parallel the explainability methods were implemented. This research included a proposal for carrying out the adaptation and implementation of these methods in continuous states. The adaptation of the learning method produced major changes, implemented through an artificial neural network. The obtained probabilities of both methods were consistent throughout the experiments. The probability result was greater in the learning method. In terms of computational resources, the introspection method was slightly better than its counterpart. Full article

In this paper, we show that a basic fixed point method used to enclose the greatest fixed point in a Kleene algebra will allow us to compute inner and outer approximations of invariant-based sets for continuous-time nonlinear dynamical systems. Our contribution is to provide the definitions and theorems that will allow us to make the link between the theory of invariant sets and the Kleene algebra. This link has never be done before and will allow us to compute rigorously sets that can be defined as a combination of positive invariant sets. Some illustrating examples show the nice properties of the approach. Full article

At present, the unsupervised visual representation learning of the point cloud model is mainly based on generative methods, but the generative methods pay too much attention to the details of each point, thus ignoring the learning of semantic information. Therefore, this paper proposes a discriminative method for the contrastive learning of three-dimensional point cloud visual representations, which can effectively learn the visual representation of point cloud models. The self-attention point cloud capsule network is designed as the backbone network, which can effectively extract the features of point cloud data. By compressing the digital capsule layer, the class dependence of features is eliminated, and the generalization ability of the model and the ability of feature queues to store features are improved. Aiming at the equivariance of the capsule network, the Jaccard loss function is constructed, which is conducive to the network distinguishing the characteristics of positive and negative samples, thereby improving the performance of the contrastive learning. The model is pre-trained on the ShapeNetCore data set, and the pre-trained model is used for classification and segmentation tasks. The classification accuracy on the ModelNet40 data set is 0.1% higher than that of the best unsupervised method, PointCapsNet, and when only 10% of the label data is used, the classification accuracy exceeds 80%. The mIoU of part segmentation on the ShapeNet data set is 1.2% higher than the best comparison method, MulUnsupervised. The experimental results of classification and segmentation show that the proposed method has good performance in accuracy. The alignment and uniformity of features are better than the generative method of PointCapsNet, which proves that this method can learn the visual representation of the three-dimensional point cloud model more effectively. Full article

Agricultural machinery rental is a new service form that uses big data in agriculture to improve the utilization rate of agricultural machinery and promote the development of the agricultural economy. To realize agricultural machinery scheduling optimization in cloud services, a dynamic artificial bee-ant colony algorithm (DABAA) is proposed to solve the above problem. First, to improve the practicability of the mathematical model in agricultural production, a dynamic coefficient is proposed. Then the mutation operation is combined with the artificial bee colony (ABC) algorithm to improve the algorithm. Then, iterative threshold adjustment and optimal fusion point evaluation are used to combine the ABC algorithm with the ant colony optimization (ACO) algorithm, which not only improves the search precision but also improves the running speed. Finally, two groups of comparison experiments are carried out, and the results show that the DABAA can obviously improve the running speed and accuracy of cloud services in agricultural machinery rental. Full article

There is a growing interest in topic modeling to decipher the valuable information embedded in natural texts. However, there are no studies training an unsupervised model to automatically categorize the social networks (SN) messages according to personality traits. Most of the existing literature relied on the Big 5 framework and psychological reports to recognize the personality of users. Furthermore, collecting datasets for other personality themes is an inherent problem that requires unprecedented time and human efforts, and it is bounded with privacy constraints. Alternatively, this study hypothesized that a small set of seed words is enough to decipher the psycholinguistics states encoded in texts, and the auxiliary knowledge could synergize the unsupervised model to categorize the messages according to human traits. Therefore, this study devised a dataless model called Seed-guided Latent Dirichlet Allocation (SLDA) to categorize the SN messages according to the PEN model that comprised Psychoticism, Extraversion, and Neuroticism traits. The intrinsic evaluations were conducted to determine the performance and disclose the nature of texts generated by SLDA, especially in the context of Psychoticism. The extrinsic evaluations were conducted using several machine learning classifiers to posit how well the topic model has identified latent semantic structure that persists over time in the training documents. The findings have shown that SLDA outperformed other models by attaining a coherence score up to 0.78, whereas the machine learning classifiers can achieve precision up to 0.993. We also will be shared the corpus generated by SLDA for further empirical studies. Full article

Prediction of intrinsic disordered proteins is a hot area in the field of bio-information. Due to the high cost of evaluating the disordered regions of protein sequences using experimental methods, we used a low-complexity prediction scheme. Sequence complexity is used in this scheme to calculate five features for each residue of the protein sequence, including the Shannon entropy, the Topo-logical entropy, the Permutation entropy and the weighted average values of two propensities. Particularly, this is the first time that permutation entropy has been applied to the field of protein sequencing. In addition, in the data preprocessing stage, an appropriately sized sliding window and a comprehensive oversampling scheme can be used to improve the prediction performance of our scheme, and two ensemble learning algorithms are also used to verify the prediction results before and after. The results show that adding permutation entropy improves the performance of the prediction algorithm, in which the MCC value can be improved from the original 0.465 to 0.526 in our scheme, proving its universality. Finally, we compare the simulation results of our scheme with those of some existing schemes to demonstrate its effectiveness. Full article

Evolutionary algorithms, such as genetic algorithms have been used in various optimization problems. In this paper, we propose to apply this algorithm to obtain the layout design/redesign in order to improve the patient flow in an outpatient clinic. Layout designs are planned considering long-term requirements whereas the layout keeps modifying as per short-term demands. Over a period of time, the layout often does not remain efficient. Therefore, there is a need for such a model that helps in decision making on layout redesigns, and it must also optimize workflow by incorporating the flow constraints. In this study, we propose to minimize the waiting times by obtaining optimal and sub-optimal layout designs. A genetic algorithm is implemented to redesign the layouts based on the changing dynamics of patient demand, clinical pathways and services offered. The workflow is simulated with current layout and optimized layouts, and the results in terms of waiting time and cycle time are compared. The study shows that when layout design or redesign incorporate the workflow and pathways along with associated constraints, improves waiting time and cycle time of patients in the outpatient clinic. The distance between the departments/locations is translated to travelling time and overall travel distance/time is minimized by rearranging the allocations of departments to the location through genetic algorithms. Full article

Nowadays, eye fatigue is becoming more common globally. However, there was no objective and effective method for eye fatigue detection except the sample survey questionnaire. An eye fatigue detection method by machine learning based on the Single-Channel Electrooculography-based System is proposed. Subjects are required to finish the industry-standard questionnaires of eye fatigue; the results are used as data labels. Then, we collect their electrooculography signals through a single-channel device. From the electrooculography signals, the five most relevant feature values of eye fatigue are extracted. A machine learning model that uses the five feature values as its input is designed for eye fatigue detection. Experimental results show that there is an objective link between electrooculography and eye fatigue. This method could be used in daily eye fatigue detection and it is promised in the future. Full article

Detecting insulators on a power transmission line is of great importance for the safe operation of power systems. Aiming at the problem of the missed detection and misjudgment of the original feature extraction network VGG16 of a faster region-convolutional neural network (R-CNN) in the face of insulators of different sizes, in order to improve the accuracy of insulators’ detection on power transmission lines, an improved faster R-CNN algorithm is proposed. The improved algorithm replaces the original backbone feature extraction network VGG16 in faster R-CNN with the Resnet50 network with deeper layers and a more complex structure, adding an efficient channel attention module based on the channel attention mechanism. Experimental results show that the feature extraction performance has been effectively improved through the improvement of the backbone feature extraction network. The network model is trained on a training set consisting of 6174 insulator pictures, and is tested on a testing set consisting of 686 pictures. Compared with the traditional faster R-CNN, the mean average precision of the improved faster R-CNN increases to 89.37%, with an improvement of 1.63%. Full article

Cardiovascular disease (CVD) is a global public health problem. It is a disease of multifactorial origin, and with this characteristic, having an accurate diagnosis of its incidence is a problem that health personnel face every day. That is why having all the indispensable tools to achieve optimal results is of utmost importance. Time is an essential factor when identifying heart problems, specialists look for and develop options to improve this aspect, which requires a thorough analysis of the patient, electrocardiograms being the factor standard for diagnosis and monitoring of patients. In this paper, we review patents and combined systems for the analysis of existing electrocardiogram signals, specific to cardiovascular diseases. All these methods and equipment have the purpose of giving an accurate diagnosis and a prediction of the presence of CVD in patients with positive risk factors. These are considered as the first diagnostic option, based on the guidelines already established in the field of preventive cardiology. The methodology consists of the searching of specific electrocardiography and cardiovascular disease subjects, taking as a reference the use of various patent databases. A total of 2634 patents were obtained in the consulted databases. Of that total, only 30 patents that met all the previous criteria were considered; furthermore, a second in-depth review of their information was conducted. It is expected that studying and reviewing these patents will allow us to know the variety of tools available for the different pathologies that make up CVD, not only for its immediate diagnosis because, as mentioned, the time factor is decisive for the best forecast but also to allow us to follow up on all the cases that arise, being able to provide a better quality of life to patients with CVD or even being able to lead them to a full recovery. Full article

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all. Similarly, if the agent receives also rewards that create suboptimal modes of the objective function, it will likely prematurely stop exploring. More recent methods add auxiliary intrinsic rewards to encourage exploration. However, auxiliary rewards lead to a non-stationary target for the Q-function. In this paper, we present a novel approach that (1) plans exploration actions far into the future by using a long-term visitation count, and (2) decouples exploration and exploitation by learning a separate function assessing the exploration value of the actions. Contrary to existing methods that use models of reward and dynamics, our approach is off-policy and model-free. We further propose new tabular environments for benchmarking exploration in reinforcement learning. Empirical results on classic and novel benchmarks show that the proposed approach outperforms existing methods in environments with sparse rewards, especially in the presence of rewards that create suboptimal modes of the objective function. Results also suggest that our approach scales gracefully with the size of the environment. Full article

Accurately predicting user–item interactions is critically important in many real applications, including recommender systems and user behavior analysis in social networks. One major drawback of existing studies is that they generally directly analyze the sparse user–item interaction data without considering their semantic correlations and the structural information hidden in the data. Another limitation is that existing approaches usually embed the users and items into the different embedding spaces in a static way, but ignore the dynamic characteristics of both users and items. In this paper, we propose to learn the dynamic embedding vector trajectories rather than the static embedding vectors for users and items simultaneously. A Metapath-guided Recursive RNN based Shift embedding method named MRRNN-S is proposed to learn the continuously evolving embeddings of users and items for more accurately predicting their future interactions. The proposed MRRNN-S is extended from our previous model RRNN-S which was proposed in the earlier work. Comparedwith RRNN-S, we add the word2vec module and the skip-gram-based meta-path module to better capture the rich auxiliary information from the user–item interaction data. Specifically, we first regard the interaction data of each user with items as sentence data to model their semantic and sequential information and construct the user–item interaction graph. Then we sample the instances of meta-paths to capture the heterogeneity and structural information from the user–item interaction graph. A recursive RNN is proposed to iteratively and mutually learn the dynamic user and item embeddings in the same latent space based on their historical interactions. Next, a shift embedding module is proposed to predict the future user embeddings. To predict which item a user will interact with, we output the item embedding instead of the pairwise interaction probability between users and items, which is much more efficient. Through extensive experiments on three real-world datasets, we demonstrate that MRRNN-S achieves superior performance by extensive comparison with state-of-the-art baseline models. Full article

We propose a novel algorithm to determine the Euclidean shortest path (ESP) from a given point (source) to another point (destination) inside a tubular space. The method is based on the observation data of a virtual particle (VP) assumed to move along this path. In the first step, the geometric properties of the shortest path inside the considered space are presented and proven. Utilizing these properties, the desired ESP can be segmented into three partitions depending on the visibility of the VP. Our algorithm will check which partition the VP belongs to and calculate the correct direction of its movement, and thus the shortest path will be traced. The proposed method is then compared to Dijkstra’s algorithm, considering different types of tubular spaces. In all cases, the solution provided by the proposed algorithm is smoother, shorter, and has a higher accuracy with a faster calculation speed than that obtained by Dijkstra’s method. Full article

The Expectation Maximisation (EM) algorithm is widely used to optimise non-convex likelihood functions with latent variables. Many authors modified its simple design to fit more specific situations. For instance, the Expectation (E) step has been replaced by Monte Carlo (MC), Markov Chain Monte Carlo or tempered approximations, etc. Most of the well-studied approximations belong to the stochastic class. By comparison, the literature is lacking when it comes to deterministic approximations. In this paper, we introduce a theoretical framework, with state-of-the-art convergence guarantees, for any deterministic approximation of the E step. We analyse theoretically and empirically several approximations that fit into this framework. First, for intractable E-steps, we introduce a deterministic version of MC-EM using Riemann sums. A straightforward method, not requiring any hyper-parameter fine-tuning, useful when the low dimensionality does not warrant a MC-EM. Then, we consider the tempered approximation, borrowed from the Simulated Annealing literature and used to escape local extrema. We prove that the tempered EM verifies the convergence guarantees for a wider range of temperature profiles than previously considered. We showcase empirically how new non-trivial profiles can more successfully escape adversarial initialisations. Finally, we combine the Riemann and tempered approximations into a method that accomplishes both their purposes. Full article

CrossFit has gained recognition and interest among physically active populations being one of the most popular and rapidly growing exercise regimens worldwide. Due to the intense and repetitive nature of CrossFit, concerns have been raised over the potential injury risks that are associated with its training including rhabdomyolysis and musculoskeletal injuries. However, identification of risk factors for predicting injuries in CrossFit athletes has been limited by the absence of relevant big epidemiological studies. The main purpose of this paper is the identification of risk factors and the development of machine learning-based models using ensemble learning that can predict CrossFit injuries. To accomplish the aforementioned targets, a survey-based epidemiological study was conducted in Greece to collect data on musculoskeletal injuries in CrossFit practitioners. A Machine Learning (ML) pipeline was then implemented that involved data pre-processing, feature selection and well-known ML models. The performance of the proposed ML models was assessed using a comprehensive cross validation mechanism whereas a discussion on the nature of the selected features is also provided. An area under the curve (AUC) of 77.93% was achieved by the best ML model using ensemble learning (Adaboost) on the group of six selected risk factors. The effectiveness of the proposed approach was evaluated in a comparative analysis with respect to numerous performance metrics including accuracy, sensitivity, specificity, AUC and confusion matrices to confirm its clinical relevance. The results are the basis for the development of reliable tools for the prediction of injuries in CrossFit. Full article

Road traffic congestion has became a major problem in most countries because it affects sustainable mobility. Partitioning a transport network into homogeneous areas can be very useful for monitoring traffic as congestion is spatially correlated in adjacent roads, and it propagates at different speeds as a function of time. Spectral clustering has been successfully applied for the partitioning of transportation networks based on the spatial characteristics of congestion at a specific time. However, this type of classification is not suitable for data that change over time. Evolutionary spectral clustering represents a state-of-the-art algorithm for grouping objects evolving over time. However, the disadvantages of this algorithm are the cubic time complexity and the high memory demand, which make it insufficient to handle a large number of data sets. In this paper, we propose an efficient evolutionary spectral clustering algorithm that solves the drawbacks of evolutionary spectral clustering by reducing the size of the eigenvalue problem. This algorithm is applied in a dynamic environment to partition a transportation network into connected homogeneous regions that evolve with time. The number of clusters is selected automatically by using a density peak algorithm adopted for the classification of traffic congestion based on the sparse snake similarity matrix. Experiments on the real network of Amsterdam city demonstrate the superiority of the proposed algorithm in robustness and effectiveness. Full article

Cereals are an important and major source of the human diet. They constitute more than two-thirds of the world’s food source and cover more than 56% of the world’s cultivatable land. These important sources of food are affected by a variety of damaging diseases, causing significant loss in annual production. In this regard, detection of diseases at an early stage and quantification of the severity has acquired the urgent attention of researchers worldwide. One emerging and popular approach for this task is the utilization of machine learning techniques. In this work, we have identified the most common and damaging diseases affecting cereal crop production, and we also reviewed 45 works performed on the detection and classification of various diseases that occur on six cereal crops within the past five years. In addition, we identified and summarised numerous publicly available datasets for each cereal crop, which the lack thereof we identified as the main challenges faced for researching the application of machine learning in cereal crop detection. In this survey, we identified deep convolutional neural networks trained on hyperspectral data as the most effective approach for early detection of diseases and transfer learning as the most commonly used and yielding the best result training method. Full article

In this paper, a monitoring method for DC-DC converters in photovoltaic applications is presented. The primary goal is to prevent catastrophic failures by detecting malfunctioning conditions during the operation of the electrical system. The proposed prognostic procedure is based on machine learning techniques and focuses on the variations of passive components with respect to their nominal range. A theoretical study is proposed to choose the best measurements for the prognostic analysis and adapt the monitoring method to a photovoltaic system. In order to facilitate this study, a graphical assessment of testability is presented, and the effects of the variable solar irradiance on the selected measurements are also considered from a graphical point of view. The main technique presented in this paper to identify the malfunction conditions is based on a Multilayer neural network with Multi-Valued Neurons. The performances of this classifier applied on a Zeta converter are compared to those of a Support Vector Machine algorithm. The simulations carried out in the Simulink environment show a classification rate higher than 90%, and this means that the monitoring method allows the identification of problems in the initial phases, thus guaranteeing the possibility to change the work set-up and organize maintenance operations for DC-DC converters. Full article

Stochastic games provide a framework for interactions among multiple agents and enable a myriad of applications. In these games, agents decide on actions simultaneously. After taking an action, the state of every agent updates to the next state, and each agent receives a reward. However, finding an equilibrium (if exists) in this game is often difficult when the number of agents becomes large. This paper focuses on finding a mean-field equilibrium (MFE) in an action-coupled stochastic game setting in an episodic framework. It is assumed that an agent can approximate the impact of the other agents’ by the empirical distribution of the mean of the actions. All agents know the action distribution and employ lower-myopic best response dynamics to choose the optimal oblivious strategy. This paper proposes a posterior sampling-based approach for reinforcement learning in the mean-field game, where each agent samples a transition probability from the previous transitions. We show that the policy and action distributions converge to the optimal oblivious strategy and the limiting distribution, respectively, which constitute an MFE. Full article

A domain that has gained popularity in the past few years is personalized advertisement. Researchers and developers collect user contextual attributes (e.g., location, time, history, etc.) and apply state-of-the-art algorithms to present relevant ads. A problem occurs when the user has limited or no data available and, therefore, the algorithms cannot work well. This situation is widely referred in the literature as the ‘cold-start’ case. The aim of this manuscript is to explore this problem and present a prediction approach for personalized mobile advertising systems that addresses the cold-start, and especially the frozen user case, when a user has no data at all. The approach consists of three steps: (a) identify existing datasets and use specific attributes that could be gathered from a frozen user, (b) train and test machine learning models in the existing datasets and predict click-through rate, and (c) the development phase and the usage in a system. Full article