Search

• Variational Quantum Circuits (VQCs) play a key role in several applications. • VQCs are parameterized quantum circuits trained by using classical optimizers. • The paper proposes to apply memetic algorithms to train VQCs. • The designed memetic algorithm outperforms the state-of-the-art classical optimizers. Among the ready-to-implement quantum algorithms, Variational Quantum Circuits (VQCs) play a key role in several applications, including machine learning. Their strength lies in the use of a parameterized quantum circuit that is trained by means of an optimization algorithm run on a classical computer. In such a scenario, there is a strong need to design appropriate classical optimization schemes that deal efficiently with VQCs and pave the way for quantum advantage in machine learning. Among possible optimization schemes, those based on evolutionary computation are finding increasing interest, given the unconventional and nonanalytical nature of the problem to be solved. This paper proposes to apply memetic algorithms to train VQCs used as quantum classifiers and shows the benefits of exploiting this evolutionary optimization technique through a comparative experimental session. [ABSTRACT FROM AUTHOR]

A self-training algorithm is a classical semi-supervised learning algorithm that uses a small number of labeled samples and a large number of unlabeled samples to train a classifier. However, the existing self-training algorithms consider only the geometric distance between data while ignoring the data distribution when calculating the similarity between samples. In addition, misclassified samples can severely affect the performance of a self-training algorithm. To address the above two problems, this paper proposes a self-training algorithm based on data editing with mass-based dissimilarity (STDEMB). First, the mass matrix with the mass-based dissimilarity is obtained, and then the mass-based local density of each sample is determined based on its k nearest neighbors. Inspired by density peak clustering (DPC), this study designs a prototype tree based on the prototype concept. In addition, an efficient two-stage data editing algorithm is developed to edit misclassified samples and efficiently select high-confidence samples during the self-training process. The proposed STDEMB algorithm is verified by experiments using accuracy and F-score as evaluation metrics. The experimental results on 18 benchmark datasets demonstrate the effectiveness of the proposed STDEMB algorithm. • Mass-based dissimilarity is used to o account for the effects of data distribution. • A prototype tree was designed to efficiently identify high confidence samples. • A two-stage data editing algorithm was developed for editing misclassified samples. • Numerous experiments were conducted to prove the performance of the proposed STDEMB. [ABSTRACT FROM AUTHOR]

Twin support vector machine (TSVM) is a practical machine learning algorithm, whereas traditional TSVM can be limited for data with outliers or noises. To address this problem, we propose a novel TSVM with the symmetric LINEX loss function (SLTSVM) for robust classification. There are several advantages of our method: (1) The performance of the proposed SLTSVM for data with outliers or noise can be improved by using the symmetric LINEX loss function. (2) The introduction of regularization term can effectively improve the generalization ability of our model. (3) An efficient iterative algorithm is developed to solve the optimization problems of our SLTSVM. (4) The convergence and time complexity of the iterative algorithm are analyzed in detail. Furthermore, our model does not involve loss function parameter, which makes our method more competitive. Experimental results on synthetic, benchmark and image datasets with label noises and feature noises demonstrate that our proposed method slightly outperforms other state-of-the-art methods on most datasets. • This paper proposes SLTSVM by introducing symmetric LIENX loss function. • An interpretable method is proposed for selecting the loss parameter. • The convergence of the designed solution algorithm are further analyzed. • Experiments show that our method is efficient for data with outliers or noises. [ABSTRACT FROM AUTHOR]

Achieving precision in the prediction of buildings' dynamic heat load is crucial for the advancement of smart heating systems. This research highlights the urgent need to enhance the accuracy of models predicting dynamic heat load. Through literature review, distinguished machine learning and regression algorithms were chosen to formulate prediction models. These models employ a data time-step adaptive strategy, a physics-guided loss function, and fundamental principles of heat transfer. Optimization algorithms of a mathematical nature were utilized to fine-tune the parameters and the framework of long short-term memory (LSTM) and multi-layer perceptron (MLP) models. An analytical comparison was undertaken between physics-guided models and those not guided by physics. Principal conclusions are: 1) Pelican optimization algorithm (POA)-LSTM model emerges as superior in heat load prediction accuracy of an office building, with percentage errors for actual and simulated datasets ranging from −6.7 % to 5.8 % and −5.2 %–4.5 %, respectively, and the mean absolute percentage error (MAPE) standing at 2.3 % and 1.3 %. 2) The linear regression model exhibits the lowest precision, with a MAPE of 17.5 % and 4.0 % for the 7-day prediction results in the actual and simulated datasets, respectively. These findings provide support for improving heat load prediction in heating systems. • The authors have implemented a total of 20 physically-guided models for predicting building thermal load, among which the POA-LSTM model demonstrates the highest accuracy. • The disparities in thermal load prediction accuracy between the physically-guided machine learning models and the physically-guided mathematical regression models have been identified. • The accuracy of thermal load prediction was compared between the five physical guidance models proposed in this paper and the five non-physical guidance models mentioned in other papers. [ABSTRACT FROM AUTHOR]

• Distinct DG Output Modes Validation: The simulation validates distinct DG output modes, impacting prediction. • Mode-Based State Estimation: The paper proposes an innovative mode-based state estimation using IPSO-DBSCAN clustering, overcoming k-means limitations. • Enhanced Data Recovery using DBSCAN: Enhanced data recovery employs DBSCAN with improved secondary clustering, guided by similarity and homogeneity, outperforming traditional methods. • BiGRU-PF State Estimation: BiGRU-PF enhances state estimation accuracy and robustness in distribution networks by detecting DG output modes, addressing k-means limitations, and improving data recovery. This paper proposes a new forecasting-aided state estimation (FASE) method for distribution systems that mitigates issues with uncertain distributed generation (DG) and lost measurements. We utilize an Improved Particle Swarm Optimization (IPSO)-optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for examination of historical DG output data. Based on identified DG output modes, it facilitates precise state prediction and data reconstruction,. The proposed method employs a Bidirectional Gated Recurrent Unit (BiGRU) neural network for state prediction and a particle filter (PF) for final state filtering. The method verification is provided through Python simulations of the Distribution Transformer Unit (DTU)7k distribution network system, demonstrating improved accuracy and robustness against sudden load change and bad data in measurements. [ABSTRACT FROM AUTHOR]

In the last years, the massive deployment of new photovoltaic (PV) power plants has launched the connection of PV inverters to the electrical network. A single medium-sized ground-mounted PV plant may have thousands of these inverters linked to the grid and even more PV panels on the DC side. Upon reaching such a substantial magnitude of devices involved in grid-connected installations, the effective operation, management, predictive maintenance, and fault detection becomes increasingly challenging without integrating advanced prediction and automated anomaly detection systems. Artificial intelligence algorithms, grounded in data measurements, can be pivotal in addressing this challenge. This paper proposes several regression-based methods to predict PV plants' energy generation, which is useful for detecting transient and long-term anomalies. These models are trained using a Recursive Least Squares (RLS) method and require a minimum number of variables to yield satisfactory outcomes, which is one of the paper's contributions. They mainly rely on energy generation measurements and geolocation. Within the scope of this research, two distinct algorithms have been implemented and validated. The first algorithm, a simplified model, is engineered to analyse the daily efficiency variation, prioritizing the identification of faults and abnormal operational profiles in PV plants. On the other hand, the second algorithm adopts a more intricate model tailored to facilitate long-term diagnosis, enabling the assessment of PV efficiency degradation. In this work, both algorithms are described and their performance is validated using the historical data from more than 20 PV plants placed in different climatic regions. • Photovoltaic systems' modelling using linear regression models. • Photovoltaic fault detection using linear regression coefficients evaluation. • Automatic fault detection for photovoltaic plants with low sensors' availability. • Short-term and long-term efficiency trend evaluation of photovoltaic plants. [ABSTRACT FROM AUTHOR]

The emergence of IoT has introduced new security concerns, particularly the detection of large-scale network attacks initiated by compromised IoT devices. The diverse nature of IoT devices adds complexity to attack detection, necessitating the classification of devices based on their unique characteristics and behavior patterns. This paper presents a novel device classification method grounded in traffic differentials before and after IoT devices succumb to compromise. The study defines the concept of attack sensitivity and designs a method for calculating the value. The K-means algorithm is used to classify devices into predefined categories based on their attack sensitivity values. The effectiveness of this method is demonstrated through experiments on a public dataset. Additionally, a multi-class classification model is developed to identify newly added devices to the IoT environment, with good results in accuracy, precision, recall, F1 score, and FPR (0.999, 0.997–1,0.997–1,0.998–1,0–0.001). Overall, The device classification method proposed in this paper, based on attack sensitivity, not only enables a rational definition of device categories but also ensures precise classification for devices newly integrated into the IoT environment. This lays the foundation for achieving more precise attack detection and protection, advancing the field towards enhanced cybersecurity measures. [ABSTRACT FROM AUTHOR]

This comprehensive review focuses on the Autonomous Driving System (ADS), which aims to reduce human errors that are the reason for about 95% of car accidents. The ADS consists of six stages: sensors, perception, localization, assessment, path planning, and control. We explain the main state-of-the-art techniques used in each stage, analyzing 275 papers, with 162 specifically on path planning due to its complexity, NP-hard optimization nature, and pivotal role in ADS. This paper categorizes path planning techniques into three primary groups: traditional (graph-based, sampling-based, gradient-based, optimization-based, interpolation curve algorithms), machine and deep learning, and meta-heuristic optimization, detailing their advantages and drawbacks. Findings show that meta-heuristic optimization methods, representing 23% of our study, are preferred for being general problem solvers capable of handling complex problems. In addition, they have faster convergence and reduced risk of local minima. Machine and deep learning techniques, accounting for 25%, are favored for their learning capabilities and fast responses to known scenarios. The trend towards hybrid algorithms (27%) combines various methods, merging each algorithm's benefits and overcoming the other's drawbacks. Moreover, adaptive parameter tuning is crucial to enhance efficiency, applicability, and balancing the search capability. This review sheds light on the future of path planning in autonomous driving systems, helping to tackle current challenges and unlock the full capabilities of autonomous vehicles. [ABSTRACT FROM AUTHOR]

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

The peak shear strength of clayey soil-geomembrane interfaces is a vital parameter for the design of relevant engineering infrastructure. However, due to the large number of influence factors and the complex action mechanism, accurate prediction of the peak shear strength for clayey soil-geomembrane interfaces is always a challenge. In this paper, a machine learning model was established by combining Mind Evolutionary Algorithm (MEA) and the ensemble algorithm of Adaptive Boosting Algorithm (ADA)-Back Propagation Artificial Neural Network (BPANN) to predict the peak shear strength of clayey soil-geomembrane interfaces based on the results of 623 laboratory interface direct shear experiments. By comparing with the conventional machine learning algorithms, including Particle Swarm Optimisation Algorithm (PSO) and Genetic Algorithm (GA) tuned ADA-BPANN, MEA tuned Support Vector Machine (SVM) and Random Forest (RF), the superior performance of MEA tuned ADA-BPANN has been validated, with higher predicting precision, shorter training time, and the avoidance of local optimum and overfitting. By adopting the proposed novel model, sensitivity analysis was carried out, which indicates that normal pressure has the largest influence on the peak shear strength, followed by geomembrane roughness. Furthermore, an analytical equation was proposed to assess the peak shear strength that allows the usage of machine learning skills for the practitioners with limited machine learning knowledge. The present research highlights the potential of the MEA tuned ADA-BPANN model as a useful tool to assist in preciously estimating the peak shear strength of clayey soil-geomembrane interfaces, which can provide benefits for the design of relevant engineering applications. • The ensemble artificial intelligence algorithms in predicting the peak shear strength of interfaces is compared. • An analytical equation for estimating the peak shear strength is proposed. • Physical experiments are conducted to validate the effectiveness of the proposed analytical equation. [ABSTRACT FROM AUTHOR]

Interactive teaching is very popular in the field of education, especially in college preschool education teaching. In this study, the experimental performance of the evaluation system based on scientific emotion construction is analyzed by the machine learning algorithm. The experimental results show that the classification model realized by the machine learning algorithm is feasible and effective for the construction of an interactive design teaching evaluation system of preschool education in colleges and universities. The main research content of this experiment is for the teaching evaluation text, this paper intends to use NB, KNN, LR, and SVM algorithms as the meta-learning algorithm in the framework, the classification effect of the meta-classifier is ranked as SVM > LR > KNN > NB. From the above data comparison, the SVM meta-classifier in the algorithm in this paper has achieved the best classification effect. The SVM meta-classifier based on the algorithm in this paper performs well, and the classification accuracy rate reaches 92.1%. This shows that this model is very suitable for studying the. And the classification accuracy rate reaches 92.1%. This shows that this model is very suitable for studying the construction of interactive teaching evaluation systems under emotional education. • The experimental results show that the classification model realized by machine learning algorithm. • This shows that this model is very suitable for studying the construction of interactive teaching. • The main research content of this experiment is for the teaching evaluation text. • This paper intends to use NB, KNN, LR and SVM algorithms as the meta-learning algorithm. [ABSTRACT FROM AUTHOR]

Semi-Supervised Graph Clustering (SSGC) has emerged as a pivotal field at the intersection of graph clustering and semi-supervised learning (SSL), offering innovative solutions to intricate data analysis problems. However, despite its significance and wide-ranging applications, there exists a notable void in the literature—a comprehensive survey specifically dedicated to SSGC techniques and their diverse applications remains conspicuously absent. Addressing this gap, this paper presents a systematic and comprehensive review of SSGC methodologies, spanning from well-established approaches to cutting-edge developments. Through a meticulous categorization, critical examination, and insightful discussion of these techniques, this survey not only illuminates the current landscape of SSGC but also identifies unexplored avenues for exploration and innovation. In this paper we present a comprehensive survey of conventional graph construction, graph clustering, SSL methods, evaluation metrics and their primary development process. We then provide a taxonomy of SSGC techniques based on their structures and principles and thoroughly analyze and discuss the related models. Furthermore, we review the applications of SSGC in various fields. Lastly, we summarize the limitations of current SSGC algorithms and discuss the future directions of the field. [ABSTRACT FROM AUTHOR]

Semi-Supervised Graph Clustering (SSGC) has emerged as a pivotal field at the intersection of graph clustering and semi-supervised learning (SSL), offering innovative solutions to intricate data analysis problems. However, despite its significance and wide-ranging applications, there exists a notable void in the literature—a comprehensive survey specifically dedicated to SSGC techniques and their diverse applications remains conspicuously absent. Addressing this gap, this paper presents a systematic and comprehensive review of SSGC methodologies, spanning from well-established approaches to cutting-edge developments. Through a meticulous categorization, critical examination, and insightful discussion of these techniques, this survey not only illuminates the current landscape of SSGC but also identifies unexplored avenues for exploration and innovation. In this paper we present a comprehensive survey of conventional graph construction, graph clustering, SSL methods, evaluation metrics and their primary development process. We then provide a taxonomy of SSGC techniques based on their structures and principles and thoroughly analyze and discuss the related models. Furthermore, we review the applications of SSGC in various fields. Lastly, we summarize the limitations of current SSGC algorithms and discuss the future directions of the field. [ABSTRACT FROM AUTHOR]

Advances over the past decade at the intersection of information fusion methods and Semi-Supervised Learning (SSL) are investigated in this paper that grapple with challenges related to limited labelled data. To do so, a bibliographic review of papers published since 2013 is presented, in which ensemble methods are combined with new machine learning algorithms. A total of 128 new proposals using SSL algorithms for ensemble construction are identified and classified. All the methods are categorised by approach, ensemble type, and base classifier. Experimental protocols, pre-processing, dataset usage, unlabelled ratios, and statistical tests are also assessed, underlining the major trends, and some shortcomings of particular studies. It is evident from this literature review that foundational algorithms such as self-training and co-training are influencing current developments, and that innovative ensemble techniques are continuing to emerge. Additionally, valuable guidelines are identified in the review for improving research into intrinsically semi-supervised and unsupervised pre-processing methods, especially for regression tasks. • A set of 128 recent semi-supervised ensemble methods is identified and analysed. • Semi-supervised approach, ensemble, base and preprocessing methods are identified. • The experimental protocol, settings, and data set properties are also categorised. • Some trends and shortcomings are identified in these methods and studies. [ABSTRACT FROM AUTHOR]

In the era of rapid paper publications in various venues, automatic citation recommendations would be highly useful to researchers when they write papers. Local citation recommendation aims to recommend possible papers to cite given local citation contexts. Previous work mainly computes the similarity score between citation contexts and cited papers on a one-to-one basis, which is quite time-consuming. We train a pair of neural network encoders that map citation contexts and all possible cited papers to the same vector space, respectively. After that, we index the positions of all cited papers in the vector space. This makes our process for searching recommended papers considerably faster. On the other hand, existing methods tend to recommend papers that are highly similar to each other, which makes recommendations lack diversity. Therefore, we extend our algorithm to perform multi-topic recommendations. We generate multi-topic training examples based on the index we mentioned earlier. Furthermore, we specially design a multi-group contrastive learning method to train our model so that it can distinguish different topics. Empirical experiments show that our model outperforms previous methods by a wide margin. Our model is also light weighted and has been deployed online so that researchers can use it to obtain recommended citations for their own paper in real-time. • Proposed FLCR algorithm with sentence-transformer & k-d tree. • Introduced multi-topic citation recommendation for diverse contexts. • Developed large-scale dataset with 1.7 million citation contexts for evaluation. • Demonstrated significant performance improvement over previous methods. • Deployed demo for real-time citation recommendations. [ABSTRACT FROM AUTHOR]

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

In this paper, to investigate the problem of radio wave propagation in complex environments, a new algorithm is proposed based on the equivalence principle algorithm and the domain decomposition method to rapidly and accurately predict electromagnetic scattering and radio wave propagation in half-space. First, equivalent surfaces are introduced to decompose the obstacle region and replace the scattering effect of obstacles within the equivalent surfaces with equivalent input and output electromagnetic currents. Then, the operator S, representing the relationship between the input and output equivalent electromagnetic currents on the equivalent surfaces, and the operator T, representing the interactions between the equivalent electromagnetic currents on each equivalent surface, are derived; this allows the calculation process of the overall spatial field in a complex environment to be simplified to the iterative calculation process of operators S and T. To reduce the complexity of calculating S, a neural network embedded with physical information is introduced to replace the calculation process. Finally, the training results are applied to an example and compared with the theoretical numerical results yielded by the method of moments in different cases with obstacles. The results reveal that the new method proposed in this paper is highly accurate and achieves a substantial improvement in calculation speed. Therefore, our proposed algorithm provides a new and reliable method for calculating the spatial field in complex environments. • The EPA is introduced to use equivalent surfaces to replace the scattering inside it. • The operators S and T are introduced into the process of solving the field. • A neural network with physical information embedded is applied to calculate the S. • Random undulating terrains are generated by Karhunen–Loève expansion. • MoM providing a good foundation for training is used to generate dataset. [ABSTRACT FROM AUTHOR]

Despite the existence of evidence-based rehabilitation strategies that address biomechanical deficits, the persistence of recurrent ankle problems in 70% of patients with acute ankle sprains highlights the unresolved nature of this issue. Artificial intelligence (AI) emerges as a promising tool to identify definitive predictors for ankle sprains. This paper aims to summarize the use of AI in investigating the ankle biomechanics of healthy and subjects with ankle sprains. Articles published between 2010 and 2023 were searched from five electronic databases. 59 papers were included for analysis with regards to: i). types of motion tested (functional vs. purposeful ankle movement); ii) types of biomechanical parameters measured (kinetic vs kinematic); iii) types of sensor systems used (lab-based vs field-based); and, iv) AI techniques used. Most studies (83.1%) examined biomechanics during functional motion. Single kinematic parameter, specifically ankle range of motion, could obtain accuracy up to 100% in identifying injury status. Wearable sensor exhibited high reliability for use in both laboratory and on-field/clinical settings. AI algorithms primarily utilized electromyography and joint angle information as input data. Support vector machine was the most used supervised learning algorithm (18.64%), while artificial neural network demonstrated the highest accuracy in eight studies. The potential for remote patient monitoring is evident with the adoption of field-based devices. Nevertheless, AI-based sensors are underutilized in detecting ankle motions at risk of sprain. We identify three key challenges: sensor designs, the controllability of AI models, and the integration of AI-sensor models, providing valuable insights for future research. [Display omitted] • Application of sensors and artificial intelligence to analyse ankle biomechanics. • Lab sensors predict parameters, paving the way for post-modern rehabilitation. • Field devices show potential for ankle injury prediction. • Focus on streamlined smart sensors and effective data management in the future. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a distributed machine learning method to protect users' privacy and security. It currently faces the following two problems (McMahan et al., 2017): (1) The performance of the global model degrades when dealing with Non-Independent Identically Distributed (Non-IID) data. Other existing classical methods do not have a rigorous theory based on error processing ; (2) In the process of global model aggregation, the classical FL algorithm either directly averages local models or solely considers the proportion of local data to assign weights to the models, without accounting for the discrepancies between the local models. In this paper, a federated aggregation algorithm Federated Maximum Mean Discrepancy (FedMMD) is proposed to address the deviation between the local models and Non-IID. First of all, this paper utilizes the Dilated Convolution Meet Transformer (DCMT) model for local model feature extraction. This approach aims to capture more feature information and minimize the impact of Non-IID scenarios. Secondly, the learning stability of the local model data participating in the aggregation is compared with Maximum Mean Discrepancy (MMD). The weights of the local models involved in the aggregation are determined using the SKNQ (Student–Keuls–Newman-Q) method and the entropy weight method. The SKNQ method calculates and compares the MMD across multiple clients, while the entropy weight method assigns different weights to clients based on their deviations. On the standard dataset, the FedAvg algorithm (McMahan et al., 2017), the FedProx algorithm (Li et al., 2020) and the FedMMD algorithm are compared. The experimental results demonstrate that the FedMMD algorithm, used in training the global model, not only enhances the accuracy of learning IID and Non-IID data but also improves the generalization capability of the global model. • An DCMT model is proposed to alleviate the model fluctuations caused by NonIID data. • An MMD method is proposed to compared horizontally before the model is aggregated. • Entropy weight method and the SKNQ method are combined to allocate local models' weight when they are fused into global model. [ABSTRACT FROM AUTHOR]

Accurate prediction of traffic flow is crucial to building a smart city. Given the nonlinearity of traffic flow, this paper proposes an extreme learning machine (ELM) algorithm based on residual correction and Tent chaos sequence combined with the DROP strategy. The algorithm is referred to as TRELM-DROP. The Tent chaos strategy and residual correction method reduce the impact of randomness in traffic flow. On this basis, the Tent and residual correction strategy avoids the weight optimization of the ELM algorithm using the iterative method. A DROP strategy is proposed in the proposed algorithm to improve its ability to predict traffic flow under varying conditions. A comprehensive comparison of 36 real-world datasets is presented in this paper, comparing TRELM-DROP with other benchmark models. The results show that the proposed algorithm can produce the best prediction performance regarding various prediction error metrics under various traffic conditions without iterative optimization. • An improved non-iterative traffic flow forecasting model is proposed. • Tent chaos strategy and residual correction strategy are developed. • A DROP strategy combining Dropout and Dropconnect is proposed. [ABSTRACT FROM AUTHOR]

In this paper, the measured input–output data sequences with pinning gain are proposed via the topology of multi-agent systems (MAS), where the requirement of reinforcement learning algorithm on internal state is avoided by pinning gain and the measured data of leader and neighbors. Besides, a data-based tracking state is given, which can be applied to MAS with different control matrices. According to the sequences and tracking state, a distributed control policy and corresponding reinforcement learning algorithm are proposed for the output synchronization. The proposed algorithm overcomes the shortcoming that previous algorithms can not be applied to MAS with different control matrices in the absence of model information and full-state vector. Finally, the effectiveness of proposed algorithm is verified by simulation examples. [ABSTRACT FROM AUTHOR]

Detecting anomalies in telemetry data captured on-board a spacecraft is critical to ensure its safe operation. Although there exist various techniques for automatically detecting point, contextual, and collective anomalies from time-series data, quantifying their performance remains under-researched. In this paper, we thoroughly validate our approach for the task of anomalous event detection that is built upon a two-stage technique, in which the telemetry signal is predicted using a long short-term memory network based on the historical data, and then the prediction is compared with the actual (captured) data. If the difference between those two is sufficiently large, we can infer that an anomalous event has happened. To evaluate the capabilities of such detection techniques over the simulated and benchmark time-series data, we investigate a set of commonly used metrics obtained for a range of anomaly detection approaches, and present their shortcomings, especially related to their inability of capturing the temporal aspects of the detectors. We tackle this issue by introducing new quality metrics which enable us to objectively verify if the detectors can timely spot the anomalies in sequential data. The experimental study showed that inferring the conclusions based on a subset of metrics can lead to biased observations, as the best algorithms determined based on the overlap metrics, including the Dice coefficient, do not necessarily correspond to the algorithms that offer the fastest detection. Finally, we discuss the Antelope Toolbox—our software tool for simulating nominal telemetry data of given characteristics, alongside well-defined anomalous events, and to perform the quantitative and qualitative analysis of anomaly detection algorithms over such simulated events. • We investigate the quality metrics to verify anomaly detection in telemetry data. • We introduce new measures that capture temporal aspects of anomaly detectors. • We present an end-to-end machine learning pipeline for anomaly detection. • We objectively assess 15 anomaly detection algorithms using all metrics. • Exploiting only a subset of all metrics can easily lead to biased conclusions. [ABSTRACT FROM AUTHOR]

Large neural networks usually perform well for executing machine learning tasks. However, models that achieve state-of-the-art performance involve arbitrarily large number of parameters and therefore their training is very expensive. It is thus desired to implement methods with small per-iteration costs, fast convergence rates, and reduced tuning. This paper proposes a multivariate adaptive gradient descent method that meets the above attributes. The proposed method updates every element of the model parameters separately in a computationally efficient manner using an adaptive vector-form learning rate, resulting in low per-iteration cost. The adaptive learning rate computes the absolute difference of current and previous model parameters over the difference in subgradients of current and previous state estimates. In the deterministic setting, we show that the cost function value converges at a linear rate for smooth and strongly convex cost functions. Whereas in both the deterministic and stochastic setting, we show that the gradient converges in expectation at the order of O (1 / k) for a non-convex cost function with Lipschitz continuous gradient. In addition, we show that after T iterates, the cost function of the last iterate scales as O (log (T) / T) for non-smooth strongly convex cost functions. Effectiveness of the proposed method is validated on convex functions, smooth non-convex function, non-smooth convex function, and four image classification data sets, whilst showing that its execution requires hardly any tuning unlike existing popular optimizers that entail relatively large tuning efforts. Our empirical results show that our proposed algorithm provides the best overall performance when comparing it to tuned state-of-the-art optimizers. [ABSTRACT FROM AUTHOR]

The increasing digitization and datification of all aspects of people's daily life, and the consequent growth in the use of personal data, are increasingly challenging the current development and adoption of Machine Learning (ML). First, the sheer complexity and amount of data available in these applications strongly demands for ML algorithms that can be trained directly on complex structures, which can be naturally described by graphs. In fact, graphs inherently capture information about entities, their attributes, and relationships between them. Directly applying ML to graphs relieves domain experts and data scientists from the challenging and time-consuming problem of designing a suitable vector-based data representation used by classical ML techniques. Second, ML algorithms should not only be designed to achieve high technical and functional standards; as the automated decisions provided by these algorithms can have a relevant impact on people's lives, their behavior has to be aligned with the values and principles of individuals and society. This demands for designing automated algorithms that we, as humans, can trust, fulfilling the requirements of fairness, robustness, privacy, and explainability. Third, designing effective ML algorithms requires skills and expertise developed at different levels. This substantially hinders the democratization and widespread availability of such technology for society at large, which in turn demands for improving the level of automatization and systematization of their design process, while also providing guarantees on their performance. For this reason, this paper provides an overview of the current works focused towards learning trustworthily, automatically, and with guarantees on graphs. [ABSTRACT FROM AUTHOR]

The Wasserstein distance in the optimal transport (OT) model is being widely used in machine learning applications due to its mathematical and geometric properties. Since the entropy regularized OT is a convex problem, and for its large-scale problems, many algorithms have been proposed. Existing methods mainly adopt iterative random projection techniques to approximate the Wasserstein distance in the OT model. In this paper, we employ the entropic domain decomposition algorithm with mini-batch learning to calculate the entropy regularized OT problem and investigate the stability of this algorithm. The algorithm performs on different cells of the domain instead of using the projection technique and it is based on a mini-batch loss function. The corresponding solution in each iteration is derived from the dual problem of entropy regularized OT on each decomposed cell. Once the solutions to the dual problem on all decomposed cells are obtained, the corresponding transport plan in each iteration can be obtained. We show that the transport plan computed by its dual variables is admissible, and we also give the sub-gradient approximation result. In addition, we exploit the statistical concentration result of the subsampled mini-batch Wasserstein distance on decomposed cells. Finally, the numerical experiments validate that the proposed algorithm can save computational time further. [ABSTRACT FROM AUTHOR]

The concept of randomized neural networks (RNNs), such as the random vector functional link network (RVFL) and extreme learning machine (ELM), is a widely accepted and efficient network method for constructing single-hidden layer feedforward networks (SLFNs). Due to its exceptional approximation capabilities, RNN is being extensively used in various fields. While the RNN concept has shown great promise, its performance can be unpredictable in imperfect conditions, such as weight noises and outliers. Thus, there is a need to develop more reliable and robust RNN algorithms. To address this issue, this paper proposes a new objective function that addresses the combined effect of weight noise and training data outliers for RVFL networks. Based on the half-quadratic optimization method, we then propose a novel algorithm, named noise-aware RNN (NARNN), to optimize the proposed objective function. The convergence of the NARNN is also theoretically validated. We also discuss the way to use the NARNN for ensemble deep RVFL (edRVFL) networks. Finally, we present an extension of the NARNN to concurrently address weight noise, stuck-at-fault, and outliers. The experimental results demonstrate that the proposed algorithm outperforms a number of state-of-the-art robust RNN algorithms. [ABSTRACT FROM AUTHOR]

This paper introduces a deep learning method for image classification that leverages knowledge formalized as a graph created from information represented by pairs attribute/value. The proposed method investigates a loss function that adaptively combines the classical cross-entropy commonly used in deep learning with a novel penalty function. The novel loss function is derived from the representation of nodes after embedding the knowledge graph and incorporates the proximity between class and image nodes. Its formulation enables the model to focus on identifying the boundary between the most challenging classes to distinguish. Experimental results on several image databases demonstrate improved performance compared to state-of-the-art methods, including classical deep learning algorithms and recent algorithms that incorporate knowledge represented by a graph. [ABSTRACT FROM AUTHOR]

• MMODE is developed as a new hybrid gene selection method for tumor identification. • MMODE combines multi-tasking and multi-objective frameworks. • MMODE uses a new elite strategy and a new guidance strategy. • MMODE selects a few genes and achieves high classification accuracy. A key preprocessing step in tumor recognition based on microarray expression profile data and machine learning is to identify tumor marker genes. Gene selection aims to select the most relevant gene subset from the original ultra-high dimensional microarray expression profile data to improve tumor identification performance. Inspired by evolutionary multitasking (EMT) and multi-objective optimization, this paper puts forward a novel multitasking multi-objective differential evolution gene selection algorithm (MMODE) which uses new elite and guidance strategies to select the best gene subsets. MMODE initializes two different populations according to different filtering criteria to increase the diversity of the search. These two populations guide their respective populations to search in the optimal direction through knowledge transfer in the evolutionary process. In addition, MMODE employs new elite and guidance strategies that enables individuals to narrow the search range and jump out of local optima. The proposed algorithm is validated on 13 publicly available microarray expression datasets in comparison with state-of-the-art gene selection algorithms. The experimental results show that MMODE can find smaller gene subsets and achieve higher classification accuracy compared with other algorithms. [ABSTRACT FROM AUTHOR]

Mixed integer Model Predictive Control (MPC) problems arise in the operation of systems where discrete and continuous decisions must be taken simultaneously to compensate for disturbances. The efficient solution of mixed integer MPC problems requires the computationally efficient online solution of mixed integer optimization problems, which are generally difficult to solve. In this paper, we propose a machine learning-based branch and check Generalized Benders Decomposition algorithm for the efficient solution of such problems. We use machine learning to approximate the effect of the complicating variables on the subproblem by approximating the Benders cuts without solving the subproblem, therefore, alleviating the need to solve the subproblem multiple times. The proposed approach is applied to a mixed integer economic MPC case study on the operation of chemical processes. We show that the proposed algorithm always finds feasible solutions to the optimization problem, given that the mixed integer MPC problem is feasible, and leads to a significant reduction in solution time (up to 97% or 50 ×) while incurring small error (in the order of 1%) compared to the application of standard and accelerated Generalized Benders Decomposition. • A machine learning-aided branch and check algorithm is proposed for mixed integer MPC • Benders cuts are approximated via machine learning-based surrogate models • The returned solution is feasible, given that the optimization problem is feasible • Case studies highlight the computational efficiency of the proposed algorithm [ABSTRACT FROM AUTHOR]

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the Q -values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon (n), and our empirical experiments show that a poorly chosen static value for n can in many cases lead to worse performance than single-step DQN. Inspired by the success of n -step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call 'Elastic Step DQN' (ES-DQN) to alleviate overestimation bias in DQNs. ES-DQN dynamically varies the step size horizon in multi-step updates based on the similarity between states visited. Our empirical evaluation shows that ES-DQN out-performs n -step with fixed n updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias. [ABSTRACT FROM AUTHOR]

Biochemical sensors have become indispensable tools for real-time, on-site monitoring and analysis in diverse domains such as healthcare, environmental protection, and food safety. The rapid evolution of artificial intelligence (AI) has opened new frontiers for enhancing the capabilities of these sensors across a spectrum of detection modalities. This paper delves into the recent integration of AI algorithms into biochemical sensors, examining this advancement from a functional standpoint and focusing on the empowerments it brings to electrochemical, electrochemiluminescence, colorimetric, and Raman sensors. AI techniques aim to enhance the capabilities of biochemical sensors beyond traditional techniques and have enabled improved selectivity, drift correction, efficiency, resolution, assisted diagnosis, and biomarker screening from complex multidimensional data. In the end, we provide a personal perspective on future development and address the remaining challenges in the commercialization of AI-based biochemical sensors. • We introduce the common types and functions of AI algorithms used in biochemical sensors. • AI algorithms enhance biochemical sensors' performance, achieving highly sensitive, precise, and high-throughput analysis. • AI-assisted sensors unlock tremendous benefits across healthcare, environmental protection, and food safety. • A personal perspective on the challenges and future opportunities is discussed. [ABSTRACT FROM AUTHOR]

Accurately capturing data on the external loads that large structural systems endure is crucial for improving the performance of energy equipment. This paper introduces a novel hybrid model-data-driven framework for the dynamic load identification of interval structures, which seamlessly combines finite-element modeling with machine learning techniques. To address potential ill-posed issues in model-driven methods and the interpretability limitations of data-driven methods, we propose a physics-informed neural network. This neural network effectively inverts uncertain modal responses with low data requirements and high predictive performance high by integrating the underlying modal transformation equation into the loss function of a fully connected neural network. To identify the modal loads using predicted modal displacement/acceleration responses, we introduce a pioneering dynamics inversion method. This method modifies the traditional Kalman filter with an assumption of unknown inputs to reduce the sensitivity of load identification process to different noises. In addition, our approach incorporates a subinterval Chebyshev expansion method to adaptively determine the interval boundaries of external loads. The efficiency of the proposed method is assessed through two numerical examples and validated through comparative research against baseline methods. Our findings suggest that this approach enhances precision, robustness, and generalization in dynamic load identification, even when facing challenges such as limited training data, significant noise interference, and non-zero initial conditions. • A novel hybrid model-data-driven dynamic load identification method for interval structures is proposed. • A physics-informed neural network is established to inverse the uncertain modal responses effectively. • Two improved Kalman filter algorithms are developed to identify the modal loads at specified parameters. [ABSTRACT FROM AUTHOR]

Analyzing the runtime behaviors of Android apps is crucial for malware detection. In this paper, we attempt to learn the behavior level features of an app from function calls. The challenges of this task are twofold. First, the absence of function attributes hinders the understanding of app behaviors. Second, the graphical representation of function calls cannot be directly processed by classical machine learning algorithms. In this paper, we develop two methods to overcome these challenges. Based on function embedding, we first propose the concept of enhanced function call graphs (E-FCGs) to characterize app runtime behaviors. We then develop a Graph Convolutional Network (GCN) based algorithm to obtain vector representations of E-FCGs. Extensive experiments show that the features learned by our method can achieve surprisingly high detection performance on a variety of classifiers (e.g., LR, DT, SVM, KNN, RF, MLP and CNN), significantly outperforming the traditional static features. [ABSTRACT FROM AUTHOR]

In the 5G smart grid, battery liquid leakage negatively affects the safe storage and transportation of electricity. Image edge detection help locate the liquid leakage phenomenon. This paper proposes a digitalization-based algorithm that converts the image to the codeword and judges the edge by the code weight. Its main steps are image sampling, quantization, coding and judging. Compared with traditional Sobel and Canny operators, the algorithm dramatically enhances detection ability with machine learning. Moreover, this paper applies the algorithm to detect the leakage of infrared battery images in the 5G smart grid; The results show that it can accurately extract the liquid leakage location, improving fault diagnosis and early risk warning. [ABSTRACT FROM AUTHOR]

• Basic factors affecting deep learning models for streamflow forecasting. • Hybrid deep learning models for streamflow forecasting. • Input and hyperparameter optimization of deep learning models. • Limitation and prospects in streamflow forecasting. Deep learning has emerged as a powerful tool for streamflow forecasting and its applications have garnered significant interest in the hydrological community. Despite the publication of several review articles on machine learning applications in streamflow forecasting, no review paper has yet focused explicitly on deep learning and its hybrid forms. This paper starts with some characteristics of deep learning models to provide a quick view of deep learning. Next, the configurations and characteristics of hybrid deep learning models, which is a hybridization of modeling techniques with deep learning, are discussed. Another vital role while implementing deep learning modeling is the methods applied for input and hyperparameter optimization. Finally, the limitations encountered in streamflow forecasting using deep learning models and recommendations for further research are outlined. This review covers related studies from 2017 to 2023 to provide the most recent snapshot of deep learning modeling applications in streamflow forecasting. These efforts are expected to contribute to the advancement of streamflow forecasting, potentially enabling more informed decision-making in water resource management. [ABSTRACT FROM AUTHOR]

• The AES power system intelligent energy scheduling environment is built. • The BI-LSTM-Att action network is propose by combining BI-LSTM with attention mechanism. • The DQN-CE algorithm is proposed by improving the DQN algorithm. • The experiments on an all-electric ferry is conducted using a variety of methods. At present, Ship energy scheduling based on deep reinforcement learning (DRL) is an important research direction in which Deep Q learning algorithm (DQN) has been successfully applied in the field of energy scheduling. In terms of the shortcomings of DQN in all electric ships(AES) energy scheduling, such that, the insufficient performance of using multiplayer perceptron(MLP) as action network and the degradation of convergence performance due to over estimation of Q value, in this paper, we propose a DQN cross entropy(DQN-CE) energy scheduling algorithm combing bi-directional LSTM and attention mechanism(BI-LSTM-Att). Instead of using MLP, firstly, we use BI-LSTM-Att as action network of DQN, and then an improved DRL algorithm called DQN-CE is proposed, that is, we add cross-entropy loss of predicted action of the next time for the target network and the action network to DQN. Finally, we conduct simulation experiments on an all-electric ferry, and the experimental results show that the energy scheduling algorithm proposed in this paper reduces the economic consumption by 4.11%, increases the utilization rate of energy storage system by 24.4%, and reduces the exploration time of agent training by 31.3% compared with the original DQN energy scheduling algorithm. Finally, the effectiveness and superiority of the algorithm were further verified in the new case study. [ABSTRACT FROM AUTHOR]

This paper proposes an online reinforcement learning(RL) for solving Stackelberg games with completely unknown dynamic systems. To deal with the hierarchical optimal control problem, the key is to find the solution of a two-level optimal control with the leader's optimal problem being constrained. Firstly, the leader–follower coupled Hamiltonian-Jacobi(HJ) equations subject to the follower's costate equation is derived. Secondly, an off-policy scheme is designed following the policy iteration(PI) algorithm based on model. The improved off-policy algorithm is given for obtaining the solution to the leader–follower coupled HJ equations. The algorithm is built without requiring any knowledge of the dynamic system, and the leader–follower optimal control policies are directly constructed by the extracted data. Meanwhile, the existence of the Stackelberg equilibrium is demonstrated. Lastly, NNs for each player are built, and NN learning is accomplished online with Kronecker product technique and vectorization, which simples the NN form and could decrease computation burden. Simulation examples are presented to demonstrate the proposed learning algorithm. [ABSTRACT FROM AUTHOR]

Communication in parallel systems imposes significant overhead which often turns out to be a bottleneck in parallel machine learning. To relieve some of this overhead, in this paper, we present EventGraD - an algorithm with event-triggered communication for stochastic gradient descent in parallel machine learning. The main idea of this algorithm is to modify the requirement of communication at every iteration in standard implementations of stochastic gradient descent in parallel machine learning to communicating only when necessary at certain iterations. We provide theoretical analysis of convergence of our proposed algorithm. We also implement the proposed algorithm for data-parallel training of a popular residual neural network used for training the CIFAR-10 dataset and show that EventGraD can reduce the communication load by up to 60% while retaining the same level of accuracy. In addition, EventGraD can be combined with other approaches such as Top-K sparsification to decrease communication further while maintaining accuracy. [ABSTRACT FROM AUTHOR]

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model. [ABSTRACT FROM AUTHOR]